Backmerge v4.1-rc4 into into drm-next

We picked up a silent conflict in amdkfd with drm-fixes and drm-next,
backmerge v4.1-rc5 and fix the conflicts

Signed-off-by: Dave Airlie <airlied@redhat.com>

Conflicts:
	drivers/gpu/drm/drm_irq.c

15 files changed, 160 insertions, 60 deletions

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index ef17683484e9..48304b89b601 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1109,6 +1109,8 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	if (!cmdline_ptr)
 		goto fail;
 	hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
+	/* Fill in upper bits of command line address, NOP on 32 bit  */
+	boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32;
 
 	hdr->ramdisk_image = 0;
 	hdr->ramdisk_size = 0;
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index e42f758a0fbd..055ea9941dd5 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -50,7 +50,7 @@ extern const struct hypervisor_x86 *x86_hyper;
 /* Recognized hypervisors */
 extern const struct hypervisor_x86 x86_hyper_vmware;
 extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
-extern const struct hypervisor_x86 x86_hyper_xen_hvm;
+extern const struct hypervisor_x86 x86_hyper_xen;
 extern const struct hypervisor_x86 x86_hyper_kvm;
 
 extern void init_hypervisor(struct cpuinfo_x86 *c);
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index cf87de3fc390..64b611782ef0 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -169,7 +169,7 @@ static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 	struct __raw_tickets tmp = READ_ONCE(lock->tickets);
 
 	tmp.head &= ~TICKET_SLOWPATH_FLAG;
-	return (tmp.tail - tmp.head) > TICKET_LOCK_INC;
+	return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
 }
 #define arch_spin_is_contended	arch_spin_is_contended
 
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 358dcd338915..c44a5d53e464 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -269,4 +269,9 @@ static inline bool xen_arch_need_swiotlb(struct device *dev,
 	return false;
 }
 
+static inline unsigned long xen_get_swiotlb_free_pages(unsigned int order)
+{
+	return __get_free_pages(__GFP_NOWARN, order);
+}
+
 #endif /* _ASM_X86_XEN_PAGE_H */
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 36ce402a3fa5..d820d8eae96b 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -27,8 +27,8 @@
 
 static const __initconst struct hypervisor_x86 * const hypervisors[] =
 {
-#ifdef CONFIG_XEN_PVHVM
-	&x86_hyper_xen_hvm,
+#ifdef CONFIG_XEN
+	&x86_hyper_xen,
 #endif
 	&x86_hyper_vmware,
 	&x86_hyper_ms_hyperv,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 219d3fb423a1..3998131d1a68 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1134,7 +1134,7 @@ static __initconst const u64 slm_hw_cache_extra_regs
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS,
-		[ C(RESULT_MISS)   ] = SLM_DMND_READ|SLM_LLC_MISS,
+		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS,
@@ -1184,8 +1184,7 @@ static __initconst const u64 slm_hw_cache_event_ids
 	[ C(OP_READ) ] = {
 		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01b7,
+		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_WRITE) ] = {
 		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
@@ -1217,7 +1216,7 @@ static __initconst const u64 slm_hw_cache_event_ids
  [ C(ITLB) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
-		[ C(RESULT_MISS)   ] = 0x0282, /* ITLB.MISSES */
+		[ C(RESULT_MISS)   ] = 0x40205, /* PAGE_WALKS.I_SIDE_WALKS */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = -1,
@@ -2533,34 +2532,6 @@ ssize_t intel_event_sysfs_show(char *page, u64 config)
 	return x86_event_sysfs_show(page, config, event);
 }
 
-static __initconst const struct x86_pmu core_pmu = {
-	.name			= "core",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
-	.enable_all		= core_pmu_enable_all,
-	.enable			= core_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
-	.hw_config		= x86_pmu_hw_config,
-	.schedule_events	= x86_schedule_events,
-	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
-	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
-	.event_map		= intel_pmu_event_map,
-	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
-	.apic			= 1,
-	/*
-	 * Intel PMCs cannot be accessed sanely above 32 bit width,
-	 * so we install an artificial 1<<31 period regardless of
-	 * the generic event period:
-	 */
-	.max_period		= (1ULL << 31) - 1,
-	.get_event_constraints	= intel_get_event_constraints,
-	.put_event_constraints	= intel_put_event_constraints,
-	.event_constraints	= intel_core_event_constraints,
-	.guest_get_msrs		= core_guest_get_msrs,
-	.format_attrs		= intel_arch_formats_attr,
-	.events_sysfs_show	= intel_event_sysfs_show,
-};
-
 struct intel_shared_regs *allocate_shared_regs(int cpu)
 {
 	struct intel_shared_regs *regs;
@@ -2743,6 +2714,44 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	NULL,
 };
 
+static __initconst const struct x86_pmu core_pmu = {
+	.name			= "core",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= core_pmu_enable_all,
+	.enable			= core_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
+	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
+	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.event_map		= intel_pmu_event_map,
+	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
+	.apic			= 1,
+	/*
+	 * Intel PMCs cannot be accessed sanely above 32-bit width,
+	 * so we install an artificial 1<<31 period regardless of
+	 * the generic event period:
+	 */
+	.max_period		= (1ULL<<31) - 1,
+	.get_event_constraints	= intel_get_event_constraints,
+	.put_event_constraints	= intel_put_event_constraints,
+	.event_constraints	= intel_core_event_constraints,
+	.guest_get_msrs		= core_guest_get_msrs,
+	.format_attrs		= intel_arch_formats_attr,
+	.events_sysfs_show	= intel_event_sysfs_show,
+
+	/*
+	 * Virtual (or funny metal) CPU can define x86_pmu.extra_regs
+	 * together with PMU version 1 and thus be using core_pmu with
+	 * shared_regs. We need following callbacks here to allocate
+	 * it properly.
+	 */
+	.cpu_prepare		= intel_pmu_cpu_prepare,
+	.cpu_starting		= intel_pmu_cpu_starting,
+	.cpu_dying		= intel_pmu_cpu_dying,
+};
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 999289b94025..358c54ad20d4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -722,6 +722,7 @@ static int __init rapl_pmu_init(void)
 		break;
 	case 60: /* Haswell */
 	case 69: /* Haswell-Celeron */
+	case 61: /* Broadwell */
 		rapl_cntr_mask = RAPL_IDX_HSW;
 		rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
 		break;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 3001015b755c..4562e9e22c60 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -1,6 +1,13 @@
 /* Nehalem/SandBridge/Haswell uncore support */
 #include "perf_event_intel_uncore.h"
 
+/* Uncore IMC PCI IDs */
+#define PCI_DEVICE_ID_INTEL_SNB_IMC	0x0100
+#define PCI_DEVICE_ID_INTEL_IVB_IMC	0x0154
+#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC	0x0150
+#define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
+#define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
+
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
 #define SNB_UNC_CTL_UMASK_MASK			0x0000ff00
@@ -472,6 +479,10 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* end: all zeroes */ },
 };
 
@@ -502,6 +513,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver),    /* 3rd Gen Core processor */
 	IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
+	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
 	{  /* end marker */ }
 };
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 8213da62b1b7..6e338e3b1dc0 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -57,7 +57,7 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 	.io_bitmap		= { [0 ... IO_BITMAP_LONGS] = ~0 },
 #endif
 };
-EXPORT_PER_CPU_SYMBOL_GPL(cpu_tss);
+EXPORT_PER_CPU_SYMBOL(cpu_tss);
 
 #ifdef CONFIG_X86_64
 static DEFINE_PER_CPU(unsigned char, is_idle);
@@ -156,11 +156,13 @@ void flush_thread(void)
 		/* FPU state will be reallocated lazily at the first use. */
 		drop_fpu(tsk);
 		free_thread_xstate(tsk);
-	} else if (!used_math()) {
-		/* kthread execs. TODO: cleanup this horror. */
-		if (WARN_ON(init_fpu(tsk)))
-			force_sig(SIGKILL, tsk);
-		user_fpu_begin();
+	} else {
+		if (!tsk_used_math(tsk)) {
+			/* kthread execs. TODO: cleanup this horror. */
+			if (WARN_ON(init_fpu(tsk)))
+				force_sig(SIGKILL, tsk);
+			user_fpu_begin();
+		}
 		restore_init_xstate();
 	}
 }
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 5ead4d6cf3a7..70e7444c6835 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -351,18 +351,20 @@ int arch_ioremap_pmd_supported(void)
  */
 void *xlate_dev_mem_ptr(phys_addr_t phys)
 {
-	void *addr;
-	unsigned long start = phys & PAGE_MASK;
+	unsigned long start  = phys &  PAGE_MASK;
+	unsigned long offset = phys & ~PAGE_MASK;
+	unsigned long vaddr;
 
 	/* If page is RAM, we can use __va. Otherwise ioremap and unmap. */
 	if (page_is_ram(start >> PAGE_SHIFT))
 		return __va(phys);
 
-	addr = (void __force *)ioremap_cache(start, PAGE_SIZE);
-	if (addr)
-		addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK));
+	vaddr = (unsigned long)ioremap_cache(start, PAGE_SIZE);
+	/* Only add the offset on success and return NULL if the ioremap() failed: */
+	if (vaddr)
+		vaddr += offset;
 
-	return addr;
+	return (void *)vaddr;
 }
 
 void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 987514396c1e..99f76103c6b7 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -559,6 +559,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				if (is_ereg(dst_reg))
 					EMIT1(0x41);
 				EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
+
+				/* emit 'movzwl eax, ax' */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
 				break;
 			case 32:
 				/* emit 'bswap eax' to swap lower 4 bytes */
@@ -577,6 +584,27 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
+			switch (imm32) {
+			case 16:
+				/* emit 'movzwl eax, ax' to zero extend 16-bit
+				 * into 64 bit
+				 */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 32:
+				/* emit 'mov eax, eax' to clear upper 32-bits */
+				if (is_ereg(dst_reg))
+					EMIT1(0x45);
+				EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 64:
+				/* nop */
+				break;
+			}
 			break;
 
 			/* ST: *(u8*)(dst_reg + off) = imm */
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index e4695985f9de..d93963340c3c 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -325,6 +325,26 @@ static void release_pci_root_info(struct pci_host_bridge *bridge)
 	kfree(info);
 }
 
+/*
+ * An IO port or MMIO resource assigned to a PCI host bridge may be
+ * consumed by the host bridge itself or available to its child
+ * bus/devices. The ACPI specification defines a bit (Producer/Consumer)
+ * to tell whether the resource is consumed by the host bridge itself,
+ * but firmware hasn't used that bit consistently, so we can't rely on it.
+ *
+ * On x86 and IA64 platforms, all IO port and MMIO resources are assumed
+ * to be available to child bus/devices except one special case:
+ *     IO port [0xCF8-0xCFF] is consumed by the host bridge itself
+ *     to access PCI configuration space.
+ *
+ * So explicitly filter out PCI CFG IO ports[0xCF8-0xCFF].
+ */
+static bool resource_is_pcicfg_ioport(struct resource *res)
+{
+	return (res->flags & IORESOURCE_IO) &&
+		res->start == 0xCF8 && res->end == 0xCFF;
+}
+
 static void probe_pci_root_info(struct pci_root_info *info,
 				struct acpi_device *device,
 				int busnum, int domain,
@@ -346,8 +366,8 @@ static void probe_pci_root_info(struct pci_root_info *info,
 			"no IO and memory resources present in _CRS\n");
 	else
 		resource_list_for_each_entry_safe(entry, tmp, list) {
-			if ((entry->res->flags & IORESOURCE_WINDOW) == 0 ||
-			    (entry->res->flags & IORESOURCE_DISABLED))
+			if ((entry->res->flags & IORESOURCE_DISABLED) ||
+			    resource_is_pcicfg_ioport(entry->res))
 				resource_list_destroy_entry(entry);
 			else
 				entry->res->name = info->name;
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index 275a3a8b78af..e97032069f88 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -51,7 +51,7 @@ VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
 $(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
 
-HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/x86/include/uapi
 hostprogs-y			+= vdso2c
 
 quiet_cmd_vdso2c = VDSO2C  $@
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 94578efd3067..46957ead3060 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1760,6 +1760,9 @@ static struct notifier_block xen_hvm_cpu_notifier = {
 
 static void __init xen_hvm_guest_init(void)
 {
+	if (xen_pv_domain())
+		return;
+
 	init_hvm_pv_info();
 
 	xen_hvm_init_shared_info();
@@ -1775,6 +1778,7 @@ static void __init xen_hvm_guest_init(void)
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
 }
+#endif
 
 static bool xen_nopv = false;
 static __init int xen_parse_nopv(char *arg)
@@ -1784,14 +1788,11 @@ static __init int xen_parse_nopv(char *arg)
 }
 early_param("xen_nopv", xen_parse_nopv);
 
-static uint32_t __init xen_hvm_platform(void)
+static uint32_t __init xen_platform(void)
 {
 	if (xen_nopv)
 		return 0;
 
-	if (xen_pv_domain())
-		return 0;
-
 	return xen_cpuid_base();
 }
 
@@ -1809,11 +1810,19 @@ bool xen_hvm_need_lapic(void)
 }
 EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
 
-const struct hypervisor_x86 x86_hyper_xen_hvm __refconst = {
-	.name			= "Xen HVM",
-	.detect			= xen_hvm_platform,
+static void xen_set_cpu_features(struct cpuinfo_x86 *c)
+{
+	if (xen_pv_domain())
+		clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+}
+
+const struct hypervisor_x86 x86_hyper_xen = {
+	.name			= "Xen",
+	.detect			= xen_platform,
+#ifdef CONFIG_XEN_PVHVM
 	.init_platform		= xen_hvm_guest_init,
+#endif
 	.x2apic_available	= xen_x2apic_para_available,
+	.set_cpu_features       = xen_set_cpu_features,
 };
-EXPORT_SYMBOL(x86_hyper_xen_hvm);
-#endif
+EXPORT_SYMBOL(x86_hyper_xen);
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index d9497698645a..53b4c0811f4f 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -88,7 +88,17 @@ static void xen_vcpu_notify_restore(void *data)
 	tick_resume_local();
 }
 
+static void xen_vcpu_notify_suspend(void *data)
+{
+	tick_suspend_local();
+}
+
 void xen_arch_resume(void)
 {
 	on_each_cpu(xen_vcpu_notify_restore, NULL, 1);
 }
+
+void xen_arch_suspend(void)
+{
+	on_each_cpu(xen_vcpu_notify_suspend, NULL, 1);
+}