Merge tag 'v3.12' into drm-intel-next

I want to merge in the new Broadwell support as a late hw enabling
pull request. But since the internal branch was based upon our
drm-intel-nightly integration branch I need to resolve all the
oustanding conflicts in drm/i915 with a backmerge to make the 60+
patches apply properly.

We'll propably have some fun because Linus will come up with a
slightly different merge solution.

Conflicts:
	drivers/gpu/drm/i915/i915_dma.c
	drivers/gpu/drm/i915/i915_drv.c
	drivers/gpu/drm/i915/intel_crt.c
	drivers/gpu/drm/i915/intel_ddi.c
	drivers/gpu/drm/i915/intel_display.c
	drivers/gpu/drm/i915/intel_dp.c
	drivers/gpu/drm/i915/intel_drv.h

All rather simple adjacent lines changed or partial backports from
-next to -fixes, with the exception of the thaw code in i915_dma.c.
That one needed a bit of shuffling to restore the intent.

Oh and the massive header file reordering in intel_drv.h is a bit
trouble. But not much.

v2: Also don't forget the fixup for the silent conflict that results
in compile fail ...

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

15 files changed, 89 insertions, 49 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ee2fb9d37745..f67e839f06c8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -860,7 +860,7 @@ source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors"
-	depends on X86_32 && !SMP && !X86_32_NON_STANDARD
+	depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI
 	---help---
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -885,11 +885,11 @@ config X86_UP_IOAPIC
 
 config X86_LOCAL_APIC
 	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC
+	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
 
 config X86_IO_APIC
 	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC
+	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI
 
 config X86_VISWS_APIC
 	def_bool y
@@ -1033,6 +1033,7 @@ config X86_REBOOTFIXUPS
 
 config MICROCODE
 	tristate "CPU microcode loading support"
+	depends on CPU_SUP_AMD || CPU_SUP_INTEL
 	select FW_LOADER
 	---help---
 
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index d3f5c63078d8..89270b4318db 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -374,7 +374,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 		 * Catch too early usage of this before alternatives
 		 * have run.
 		 */
-		asm goto("1: jmp %l[t_warn]\n"
+		asm_volatile_goto("1: jmp %l[t_warn]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"
@@ -388,7 +388,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 
 #endif
 
-		asm goto("1: jmp %l[t_no]\n"
+		asm_volatile_goto("1: jmp %l[t_no]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"
@@ -453,7 +453,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
  * have. Thus, we force the jump to the widest, 4-byte, signed relative
  * offset even though the last would often fit in less bytes.
  */
-		asm goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
+		asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"		/* src offset */
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 64507f35800c..6a2cefb4395a 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -18,7 +18,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:"
+	asm_volatile_goto("1:"
 		".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
index e7e6751648ed..07537a44216e 100644
--- a/arch/x86/include/asm/mutex_64.h
+++ b/arch/x86/include/asm/mutex_64.h
@@ -20,7 +20,7 @@
 static inline void __mutex_fastpath_lock(atomic_t *v,
 					 void (*fail_fn)(atomic_t *))
 {
-	asm volatile goto(LOCK_PREFIX "   decl %0\n"
+	asm_volatile_goto(LOCK_PREFIX "   decl %0\n"
 			  "   jns %l[exit]\n"
 			  : : "m" (v->counter)
 			  : "memory", "cc"
@@ -75,7 +75,7 @@ static inline int __mutex_fastpath_lock_retval(atomic_t *count)
 static inline void __mutex_fastpath_unlock(atomic_t *v,
 					   void (*fail_fn)(atomic_t *))
 {
-	asm volatile goto(LOCK_PREFIX "   incl %0\n"
+	asm_volatile_goto(LOCK_PREFIX "   incl %0\n"
 			  "   jg %l[exit]\n"
 			  : : "m" (v->counter)
 			  : "memory", "cc"
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 0da5200ee79d..b3e18f800302 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -128,7 +128,8 @@ do {							\
 do {									\
 	typedef typeof(var) pao_T__;					\
 	const int pao_ID__ = (__builtin_constant_p(val) &&		\
-			      ((val) == 1 || (val) == -1)) ? (val) : 0;	\
+			      ((val) == 1 || (val) == -1)) ?		\
+				(int)(val) : 0;				\
 	if (0) {							\
 		pao_T__ pao_tmp__;					\
 		pao_tmp__ = (val);					\
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1191ac1c9d25..a419814cea57 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -113,7 +113,7 @@ static int __init early_get_pnodeid(void)
 		break;
 	case UV3_HUB_PART_NUMBER:
 	case UV3_HUB_PART_NUMBER_X:
-		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1;
+		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE;
 		break;
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 897783b3302a..8a87a3224121 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1276,16 +1276,16 @@ void perf_events_lapic_init(void)
 static int __kprobes
 perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
-	int ret;
 	u64 start_clock;
 	u64 finish_clock;
+	int ret;
 
 	if (!atomic_read(&active_events))
 		return NMI_DONE;
 
-	start_clock = local_clock();
+	start_clock = sched_clock();
 	ret = x86_pmu.handle_irq(regs);
-	finish_clock = local_clock();
+	finish_clock = sched_clock();
 
 	perf_sample_event_took(finish_clock - start_clock);
 
@@ -1888,10 +1888,7 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
-	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
-		return;
-
-	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+	if (!sched_clock_stable)
 		return;
 
 	userpg->cap_user_time = 1;
@@ -1899,10 +1896,8 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	userpg->time_shift = CYC2NS_SCALE_FACTOR;
 	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
 
-	if (sched_clock_stable && !check_tsc_disabled()) {
-		userpg->cap_user_time_zero = 1;
-		userpg->time_zero = this_cpu_read(cyc2ns_offset);
-	}
+	userpg->cap_user_time_zero = 1;
+	userpg->time_zero = this_cpu_read(cyc2ns_offset);
 }
 
 /*
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 697b93af02dd..b2046e4d0b59 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -609,7 +609,7 @@ static struct dentry *d_kvm_debug;
 
 struct dentry *kvm_init_debugfs(void)
 {
-	d_kvm_debug = debugfs_create_dir("kvm", NULL);
+	d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
 	if (!d_kvm_debug)
 		printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n");
 
@@ -775,11 +775,22 @@ void __init kvm_spinlock_init(void)
 	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
 		return;
 
-	printk(KERN_INFO "KVM setup paravirtual spinlock\n");
+	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
+	pv_lock_ops.unlock_kick = kvm_unlock_kick;
+}
+
+static __init int kvm_spinlock_init_jump(void)
+{
+	if (!kvm_para_available())
+		return 0;
+	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
+		return 0;
 
 	static_key_slow_inc(&paravirt_ticketlocks_enabled);
+	printk(KERN_INFO "KVM setup paravirtual spinlock\n");
 
-	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
-	pv_lock_ops.unlock_kick = kvm_unlock_kick;
+	return 0;
 }
+early_initcall(kvm_spinlock_init_jump);
+
 #endif	/* CONFIG_PARAVIRT_SPINLOCKS */
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index ba77ebc2c353..6fcb49ce50a1 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -113,10 +113,10 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
 		u64 before, delta, whole_msecs;
 		int remainder_ns, decimal_msecs, thishandled;
 
-		before = local_clock();
+		before = sched_clock();
 		thishandled = a->handler(type, regs);
 		handled += thishandled;
-		delta = local_clock() - before;
+		delta = sched_clock() - before;
 		trace_nmi_handler(a->handler, (int)delta, thishandled);
 
 		if (delta < nmi_longest_ns)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e643e744e4d8..7e920bff99a3 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -326,6 +326,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"),
 		},
 	},
+	{	/* Handle problems with rebooting on the Latitude E5410. */
+		.callback = set_pci_reboot,
+		.ident = "Dell Latitude E5410",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5410"),
+		},
+	},
 	{	/* Handle problems with rebooting on the Latitude E5420. */
 		.callback = set_pci_reboot,
 		.ident = "Dell Latitude E5420",
diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c
index 22513e96b012..86179d409893 100644
--- a/arch/x86/kernel/sysfb_simplefb.c
+++ b/arch/x86/kernel/sysfb_simplefb.c
@@ -72,14 +72,14 @@ __init int create_simplefb(const struct screen_info *si,
 	 * the part that is occupied by the framebuffer */
 	len = mode->height * mode->stride;
 	len = PAGE_ALIGN(len);
-	if (len > si->lfb_size << 16) {
+	if (len > (u64)si->lfb_size << 16) {
 		printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n");
 		return -EINVAL;
 	}
 
 	/* setup IORESOURCE_MEM as framebuffer memory */
 	memset(&res, 0, sizeof(res));
-	res.flags = IORESOURCE_MEM;
+	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	res.name = simplefb_resname;
 	res.start = si->lfb_base;
 	res.end = si->lfb_base + len - 1;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a1216de9ffda..2b2fce1b2009 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3255,25 +3255,29 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 
 static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
 	if (!test_bit(VCPU_EXREG_PDPTR,
 		      (unsigned long *)&vcpu->arch.regs_dirty))
 		return;
 
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		vmcs_write64(GUEST_PDPTR0, vcpu->arch.mmu.pdptrs[0]);
-		vmcs_write64(GUEST_PDPTR1, vcpu->arch.mmu.pdptrs[1]);
-		vmcs_write64(GUEST_PDPTR2, vcpu->arch.mmu.pdptrs[2]);
-		vmcs_write64(GUEST_PDPTR3, vcpu->arch.mmu.pdptrs[3]);
+		vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]);
+		vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]);
+		vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]);
+		vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]);
 	}
 }
 
 static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 {
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		vcpu->arch.mmu.pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
-		vcpu->arch.mmu.pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
-		vcpu->arch.mmu.pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
-		vcpu->arch.mmu.pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
+		mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
+		mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
+		mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
+		mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
 	}
 
 	__set_bit(VCPU_EXREG_PDPTR,
@@ -5345,7 +5349,9 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	 * There are errata that may cause this bit to not be set:
 	 * AAK134, BY25.
 	 */
-	if (exit_qualification & INTR_INFO_UNBLOCK_NMI)
+	if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
+			cpu_has_virtual_nmis() &&
+			(exit_qualification & INTR_INFO_UNBLOCK_NMI))
 		vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI);
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
@@ -7775,10 +7781,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
 		vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
 		vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
-		__clear_bit(VCPU_EXREG_PDPTR,
-				(unsigned long *)&vcpu->arch.regs_avail);
-		__clear_bit(VCPU_EXREG_PDPTR,
-				(unsigned long *)&vcpu->arch.regs_dirty);
 	}
 
 	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 79c216aa0e2b..516593e1ce33 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -772,13 +772,21 @@ out:
 	return;
 }
 
+static void bpf_jit_free_deferred(struct work_struct *work)
+{
+	struct sk_filter *fp = container_of(work, struct sk_filter, work);
+	unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
+	struct bpf_binary_header *header = (void *)addr;
+
+	set_memory_rw(addr, header->pages);
+	module_free(NULL, header);
+	kfree(fp);
+}
+
 void bpf_jit_free(struct sk_filter *fp)
 {
 	if (fp->bpf_func != sk_run_filter) {
-		unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
-		struct bpf_binary_header *header = (void *)addr;
-
-		set_memory_rw(addr, header->pages);
-		module_free(NULL, header);
+		INIT_WORK(&fp->work, bpf_jit_free_deferred);
+		schedule_work(&fp->work);
 	}
 }
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 5596c7bdd327..082e88129712 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -700,7 +700,7 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 	if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed)
 		return -ENODEV;
 
-	if (start > end || !addr)
+	if (start > end)
 		return -EINVAL;
 
 	mutex_lock(&pci_mmcfg_lock);
@@ -716,6 +716,11 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end,
 		return -EEXIST;
 	}
 
+	if (!addr) {
+		mutex_unlock(&pci_mmcfg_lock);
+		return -EINVAL;
+	}
+
 	rc = -EBUSY;
 	cfg = pci_mmconfig_alloc(seg, start, end, addr);
 	if (cfg == NULL) {
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index d1e4777b4e75..31d04758b76f 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -278,6 +278,15 @@ static void __init xen_smp_prepare_boot_cpu(void)
 		   old memory can be recycled */
 		make_lowmem_page_readwrite(xen_initial_gdt);
 
+#ifdef CONFIG_X86_32
+		/*
+		 * Xen starts us with XEN_FLAT_RING1_DS, but linux code
+		 * expects __USER_DS
+		 */
+		loadsegment(ds, __USER_DS);
+		loadsegment(es, __USER_DS);
+#endif
+
 		xen_filter_cpu_maps();
 		xen_setup_vcpu_info_placement();
 	}