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

Conflicts:
	drivers/net/ethernet/broadcom/genet/bcmgenet.c
	net/core/sock.c

Conflicts were overlapping changes in bcmgenet and the
lockdep handling of sockets.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Documentation/admin-guide/kernel-parameters.txt

@@ -653,6 +653,9 @@
 	cpuidle.off=1	[CPU_IDLE]
 			disable the cpuidle sub-system
 
+	cpufreq.off=1	[CPU_FREQ]
+			disable the cpufreq sub-system
+
 	cpu_init_udelay=N
 			[X86] Delay for N microsec between assert and de-assert
 			of APIC INIT to start processors.  This delay occurs
@@ -1183,6 +1186,12 @@
 			functions that can be changed at run time by the
 			set_graph_notrace file in the debugfs tracing directory.
 
+	ftrace_graph_max_depth=<uint>
+			[FTRACE] Used with the function graph tracer. This is
+			the max depth it will trace into a function. This value
+			can be changed at run time by the max_graph_depth file
+			in the tracefs tracing directory. default: 0 (no limit)
+
 	gamecon.map[2|3]=
 			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
 			support via parallel port (up to 5 devices per port)

Documentation/arm64/silicon-errata.txt

@@ -68,3 +68,4 @@ stable kernels.
 |                |                 |                 |                             |
 | Qualcomm Tech. | Falkor v1       | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |
+| Qualcomm Tech. | QDF2400 ITS     | E0065           | QCOM_QDF2400_ERRATUM_0065   |

Documentation/cgroup-v2.txt

@@ -1142,16 +1142,17 @@ used by the kernel.
 
   pids.max
 
- A read-write single value file which exists on non-root cgroups.  The
- default is "max".
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
 
- Hard limit of number of processes.
+	Hard limit of number of processes.
 
   pids.current
 
- A read-only single value file which exists on all cgroups.
+	A read-only single value file which exists on all cgroups.
 
- The number of processes currently in the cgroup and its descendants.
+	The number of processes currently in the cgroup and its
+	descendants.
 
 Organisational operations are not blocked by cgroup policies, so it is
 possible to have pids.current > pids.max.  This can be done by either

Documentation/dev-tools/kcov.rst

@@ -10,7 +10,7 @@ Note that kcov does not aim to collect as much coverage as possible. It aims
 to collect more or less stable coverage that is function of syscall inputs.
 To achieve this goal it does not collect coverage in soft/hard interrupts
 and instrumentation of some inherently non-deterministic parts of kernel is
-disbled (e.g. scheduler, locking).
+disabled (e.g. scheduler, locking).
 
 Usage
 -----

Documentation/devicetree/bindings/powerpc/4xx/emac.txt

@@ -71,6 +71,9 @@
 			  For Axon it can be absent, though my current driver
 			  doesn't handle phy-address yet so for now, keep
 			  0x00ffffff in it.
+    - phy-handle	: Used to describe configurations where a external PHY
+			  is used. Please refer to:
+			  Documentation/devicetree/bindings/net/ethernet.txt
     - rx-fifo-size-gige : 1 cell, Rx fifo size in bytes for 1000 Mb/sec
 			  operations (if absent the value is the same as
 			  rx-fifo-size).  For Axon, either absent or 2048.
@@ -81,8 +84,22 @@
 			  offload, phandle of the TAH device node.
     - tah-channel       : 1 cell, optional. If appropriate, channel used on the
 			  TAH engine.
+    - fixed-link	: Fixed-link subnode describing a link to a non-MDIO
+			  managed entity. See
+			  Documentation/devicetree/bindings/net/fixed-link.txt
+			  for details.
+    - mdio subnode	: When the EMAC has a phy connected to its local
+			  mdio, which us supported by the kernel's network
+			  PHY library in drivers/net/phy, there must be device
+			  tree subnode with the following required properties:
+				- #address-cells: Must be <1>.
+				- #size-cells: Must be <0>.
 
-    Example:
+			  For PHY definitions: Please refer to
+			  Documentation/devicetree/bindings/net/phy.txt and
+			  Documentation/devicetree/bindings/net/ethernet.txt
+
+    Examples:
 
 	EMAC0: ethernet@40000800 {
 		device_type = "network";
@@ -104,6 +121,48 @@
 		zmii-channel = <0>;
 	};
 
+	EMAC1: ethernet@ef600c00 {
+		device_type = "network";
+		compatible = "ibm,emac-apm821xx", "ibm,emac4sync";
+		interrupt-parent = <&EMAC1>;
+		interrupts = <0 1>;
+		#interrupt-cells = <1>;
+		#address-cells = <0>;
+		#size-cells = <0>;
+		interrupt-map = <0 &UIC2 0x10 IRQ_TYPE_LEVEL_HIGH /* Status */
+				 1 &UIC2 0x14 IRQ_TYPE_LEVEL_HIGH /* Wake */>;
+		reg = <0xef600c00 0x000000c4>;
+		local-mac-address = [000000000000]; /* Filled in by U-Boot */
+		mal-device = <&MAL0>;
+		mal-tx-channel = <0>;
+		mal-rx-channel = <0>;
+		cell-index = <0>;
+		max-frame-size = <9000>;
+		rx-fifo-size = <16384>;
+		tx-fifo-size = <2048>;
+		fifo-entry-size = <10>;
+		phy-mode = "rgmii";
+		phy-handle = <&phy0>;
+		phy-map = <0x00000000>;
+		rgmii-device = <&RGMII0>;
+		rgmii-channel = <0>;
+		tah-device = <&TAH0>;
+		tah-channel = <0>;
+		has-inverted-stacr-oc;
+		has-new-stacr-staopc;
+
+	        mdio {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			phy0: ethernet-phy@0 {
+				compatible = "ethernet-phy-ieee802.3-c22";
+				reg = <0>;
+			};
+		};
+	};
+
+
       ii) McMAL node
 
     Required properties:
@@ -145,4 +204,3 @@
     - revision           : as provided by the RGMII new version register if
 			   available.
 			   For Axon: 0x0000012a
-

Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt

@@ -45,7 +45,7 @@ Required Properties:
 Optional Properties:
 - reg-names: In addition to the required properties, the following are optional
   - "efuse-address"	- Contains efuse base address used to pick up ABB info.
-  - "ldo-address"	- Contains address of ABB LDO overide register address.
+  - "ldo-address"	- Contains address of ABB LDO override register.
 	"efuse-address" is required for this.
 - ti,ldovbb-vset-mask	- Required if ldo-address is set, mask for LDO override
 	register to provide override vset value.

Documentation/devicetree/bindings/usb/usb251xb.txt

@@ -7,18 +7,18 @@ Required properties :
  - compatible : Should be "microchip,usb251xb" or one of the specific types:
 	"microchip,usb2512b", "microchip,usb2512bi", "microchip,usb2513b",
 	"microchip,usb2513bi", "microchip,usb2514b", "microchip,usb2514bi"
- - hub-reset-gpios : Should specify the gpio for hub reset
+ - reset-gpios : Should specify the gpio for hub reset
+ - reg : I2C address on the selected bus (default is <0x2C>)
 
 Optional properties :
- - reg : I2C address on the selected bus (default is <0x2C>)
  - skip-config : Skip Hub configuration, but only send the USB-Attach command
- - vendor-id : USB Vendor ID of the hub (16 bit, default is 0x0424)
- - product-id : USB Product ID of the hub (16 bit, default depends on type)
- - device-id : USB Device ID of the hub (16 bit, default is 0x0bb3)
- - language-id : USB Language ID (16 bit, default is 0x0000)
- - manufacturer : USB Manufacturer string (max 31 characters long)
- - product : USB Product string (max 31 characters long)
- - serial : USB Serial string (max 31 characters long)
+ - vendor-id : Set USB Vendor ID of the hub (16 bit, default is 0x0424)
+ - product-id : Set USB Product ID of the hub (16 bit, default depends on type)
+ - device-id : Set USB Device ID of the hub (16 bit, default is 0x0bb3)
+ - language-id : Set USB Language ID (16 bit, default is 0x0000)
+ - manufacturer : Set USB Manufacturer string (max 31 characters long)
+ - product : Set USB Product string (max 31 characters long)
+ - serial : Set USB Serial string (max 31 characters long)
  - {bus,self}-powered : selects between self- and bus-powered operation (default
 	is self-powered)
  - disable-hi-speed : disable USB Hi-Speed support
@@ -31,8 +31,10 @@ Optional properties :
 	(default is individual)
  - dynamic-power-switching : enable auto-switching from self- to bus-powered
 	operation if the local power source is removed or unavailable
- - oc-delay-{100us,4ms,8ms,16ms} : set over current timer delay (default is 8ms)
- - compound-device : indicated the hub is part of a compound device
+ - oc-delay-us : Delay time (in microseconds) for filtering the over-current
+	sense inputs. Valid values are 100, 4000, 8000 (default) and 16000. If
+	an invalid value is given, the default is used instead.
+ - compound-device : indicate the hub is part of a compound device
  - port-mapping-mode : enable port mapping mode
  - string-support : enable string descriptor support (required for manufacturer,
 	product and serial string configuration)
@@ -40,34 +42,15 @@ Optional properties :
 	device connected.
  - sp-disabled-ports : Specifies the ports which will be self-power disabled
  - bp-disabled-ports : Specifies the ports which will be bus-power disabled
- - max-sp-power : Specifies the maximum current the hub consumes from an
-	upstream port when operating as self-powered hub including the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 2).
- - max-bp-power : Specifies the maximum current the hub consumes from an
-	upstream port when operating as bus-powered hub including the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 100).
- - max-sp-current : Specifies the maximum current the hub consumes from an
-	upstream port when operating as self-powered hub EXCLUDING the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 2).
- - max-bp-current : Specifies the maximum current the hub consumes from an
-	upstream port when operating as bus-powered hub EXCLUDING the power
-	consumption of a permanently attached peripheral if the hub is
-	configured as a compound device. The value is given in mA in a 0 - 500
-	range (default is 100).
- - power-on-time : Specifies the time it takes from the time the host initiates
-	the power-on sequence to a port until the port has adequate power. The
-	value is given in ms in a 0 - 510 range (default is 100ms).
+ - power-on-time-ms : Specifies the time it takes from the time the host
+	initiates the power-on sequence to a port until the port has adequate
+	power. The value is given in ms in a 0 - 510 range (default is 100ms).
 
 Examples:
 	usb2512b@2c {
 		compatible = "microchip,usb2512b";
-		hub-reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+		reg = <0x2c>;
+		reset-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	};
 
 	usb2514b@2c {

Documentation/networking/ip-sysctl.txt

@@ -1006,7 +1006,8 @@ accept_redirects - BOOLEAN
 		FALSE (router)
 
 forwarding - BOOLEAN
-	Enable IP forwarding on this interface.
+	Enable IP forwarding on this interface.  This controls whether packets
+	received _on_ this interface can be forwarded.
 
 mc_forwarding - BOOLEAN
 	Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE

Documentation/trace/kprobetrace.txt

@@ -12,7 +12,7 @@ kprobes can probe (this means, all functions body except for __kprobes
 functions). Unlike the Tracepoint based event, this can be added and removed
 dynamically, on the fly.
 
-To enable this feature, build your kernel with CONFIG_KPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.
 
 Similar to the events tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via

Documentation/trace/uprobetracer.txt

@@ -7,7 +7,7 @@
 Overview
 --------
 Uprobe based trace events are similar to kprobe based trace events.
-To enable this feature, build your kernel with CONFIG_UPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y.
 
 Similar to the kprobe-event tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via

Documentation/virtual/kvm/api.txt

@@ -951,6 +951,10 @@ This ioctl allows the user to create or modify a guest physical memory
 slot.  When changing an existing slot, it may be moved in the guest
 physical memory space, or its flags may be modified.  It may not be
 resized.  Slots may not overlap in guest physical address space.
+Bits 0-15 of "slot" specifies the slot id and this value should be
+less than the maximum number of user memory slots supported per VM.
+The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS,
+if this capability is supported by the architecture.
 
 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
 specifies the address space which is being modified.  They must be

Documentation/vm/userfaultfd.txt

@@ -172,10 +172,6 @@ the same read(2) protocol as for the page fault notifications. The
 manager has to explicitly enable these events by setting appropriate
 bits in uffdio_api.features passed to UFFDIO_API ioctl:
 
-UFFD_FEATURE_EVENT_EXIT - enable notification about exit() of the
-non-cooperative process. When the monitored process exits, the uffd
-manager will get UFFD_EVENT_EXIT.
-
 UFFD_FEATURE_EVENT_FORK - enable userfaultfd hooks for fork(). When
 this feature is enabled, the userfaultfd context of the parent process
 is duplicated into the newly created process. The manager receives

MAINTAINERS

@@ -8313,7 +8313,6 @@ M:	Richard Leitner <richard.leitner@skidata.com>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/usb/misc/usb251xb.c
-F:	include/linux/platform_data/usb251xb.h
 F:	Documentation/devicetree/bindings/usb/usb251xb.txt
 
 MICROSOFT SURFACE PRO 3 BUTTON DRIVER

Makefile

 VERSION = 4
-PATCHLEVEL = 10
+PATCHLEVEL = 11
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc2
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*

arch/arc/include/asm/hugepage.h

@@ -11,6 +11,7 @@
 #define _ASM_ARC_HUGEPAGE_H
 
 #include <linux/types.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 static inline pte_t pmd_pte(pmd_t pmd)

arch/arc/include/asm/pgtable.h

@@ -37,6 +37,7 @@
 
 #include <asm/page.h>
 #include <asm/mmu.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #include <linux/const.h>
 

arch/arm/include/asm/kvm_arm.h

@@ -209,6 +209,7 @@
 #define HSR_EC_IABT_HYP	(0x21)
 #define HSR_EC_DABT	(0x24)
 #define HSR_EC_DABT_HYP	(0x25)
+#define HSR_EC_MAX	(0x3f)
 
 #define HSR_WFI_IS_WFE		(_AC(1, UL) << 0)
 

arch/arm/include/asm/kvm_host.h

@@ -30,7 +30,6 @@
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
 #define KVM_USER_MEM_SLOTS 32
-#define KVM_PRIVATE_MEM_SLOTS 4
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HAVE_ONE_REG
 #define KVM_HALT_POLL_NS_DEFAULT 500000

arch/arm/include/asm/pgtable.h

@@ -20,6 +20,7 @@
 
 #else
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>

arch/arm/kvm/arm.c

@@ -221,6 +221,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
+	case KVM_CAP_NR_MEMSLOTS:
+		r = KVM_USER_MEM_SLOTS;
+		break;
 	case KVM_CAP_MSI_DEVID:
 		if (!kvm)
 			r = -EINVAL;

arch/arm/kvm/handle_exit.c

@@ -79,7 +79,19 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+	kvm_pr_unimpl("Unknown exception class: hsr: %#08x\n",
+		      hsr);
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
+	[0 ... HSR_EC_MAX]	= kvm_handle_unknown_ec,
 	[HSR_EC_WFI]		= kvm_handle_wfx,
 	[HSR_EC_CP15_32]	= kvm_handle_cp15_32,
 	[HSR_EC_CP15_64]	= kvm_handle_cp15_64,
@@ -98,13 +110,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 {
 	u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
 
-	if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
-	    !arm_exit_handlers[hsr_ec]) {
-		kvm_err("Unknown exception class: hsr: %#08x\n",
-			(unsigned int)kvm_vcpu_get_hsr(vcpu));
-		BUG();
-	}
-
 	return arm_exit_handlers[hsr_ec];
 }
 

arch/arm/xen/mm.c

@@ -198,6 +198,8 @@ static const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.unmap_page = xen_swiotlb_unmap_page,
 	.dma_supported = xen_swiotlb_dma_supported,
 	.set_dma_mask = xen_swiotlb_set_dma_mask,
+	.mmap = xen_swiotlb_dma_mmap,
+	.get_sgtable = xen_swiotlb_get_sgtable,
 };
 
 int __init xen_mm_init(void)

arch/arm64/Kconfig

@@ -508,6 +508,16 @@ config QCOM_FALKOR_ERRATUM_1009
 
 	  If unsure, say Y.
 
+config QCOM_QDF2400_ERRATUM_0065
+	bool "QDF2400 E0065: Incorrect GITS_TYPER.ITT_Entry_size"
+	default y
+	help
+	  On Qualcomm Datacenter Technologies QDF2400 SoC, ITS hardware reports
+	  ITE size incorrectly. The GITS_TYPER.ITT_Entry_size field should have
+	  been indicated as 16Bytes (0xf), not 8Bytes (0x7).
+
+	  If unsure, say Y.
+
 endmenu
 
 

arch/arm64/include/asm/kvm_host.h

@@ -30,8 +30,7 @@
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
-#define KVM_USER_MEM_SLOTS 32
-#define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_USER_MEM_SLOTS 512
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HALT_POLL_NS_DEFAULT 500000
 

arch/arm64/include/asm/pgtable-types.h

@@ -55,9 +55,13 @@ typedef struct { pteval_t pgprot; } pgprot_t;
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
 #if CONFIG_PGTABLE_LEVELS == 2
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #elif CONFIG_PGTABLE_LEVELS == 3
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
+#elif CONFIG_PGTABLE_LEVELS == 4
+#include <asm-generic/5level-fixup.h>
 #endif
 
 #endif	/* __ASM_PGTABLE_TYPES_H */

arch/arm64/kvm/handle_exit.c

@@ -135,7 +135,19 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return ret;
 }
 
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+	kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n",
+		      hsr, esr_get_class_string(hsr));
+
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
 static exit_handle_fn arm_exit_handlers[] = {
+	[0 ... ESR_ELx_EC_MAX]	= kvm_handle_unknown_ec,
 	[ESR_ELx_EC_WFx]	= kvm_handle_wfx,
 	[ESR_ELx_EC_CP15_32]	= kvm_handle_cp15_32,
 	[ESR_ELx_EC_CP15_64]	= kvm_handle_cp15_64,
@@ -162,13 +174,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 	u8 hsr_ec = ESR_ELx_EC(hsr);
 
-	if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
-	    !arm_exit_handlers[hsr_ec]) {
-		kvm_err("Unknown exception class: hsr: %#08x -- %s\n",
-			hsr, esr_get_class_string(hsr));
-		BUG();
-	}
-
 	return arm_exit_handlers[hsr_ec];
 }
 

arch/arm64/kvm/hyp/tlb.c

@@ -18,14 +18,62 @@
 #include <asm/kvm_hyp.h>
 #include <asm/tlbflush.h>
 
+static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
+{
+	u64 val;
+
+	/*
+	 * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
+	 * most TLB operations target EL2/EL0. In order to affect the
+	 * guest TLBs (EL1/EL0), we need to change one of these two
+	 * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
+	 * let's flip TGE before executing the TLB operation.
+	 */
+	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+	val = read_sysreg(hcr_el2);
+	val &= ~HCR_TGE;
+	write_sysreg(val, hcr_el2);
+	isb();
+}
+
+static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm)
+{
+	write_sysreg(kvm->arch.vttbr, vttbr_el2);
+	isb();
+}
+
+static hyp_alternate_select(__tlb_switch_to_guest,
+			    __tlb_switch_to_guest_nvhe,
+			    __tlb_switch_to_guest_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
+static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm)
+{
+	/*
+	 * We're done with the TLB operation, let's restore the host's
+	 * view of HCR_EL2.
+	 */
+	write_sysreg(0, vttbr_el2);
+	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+}
+
+static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm)
+{
+	write_sysreg(0, vttbr_el2);
+}
+
+static hyp_alternate_select(__tlb_switch_to_host,
+			    __tlb_switch_to_host_nvhe,
+			    __tlb_switch_to_host_vhe,
+			    ARM64_HAS_VIRT_HOST_EXTN);
+
 void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
 	dsb(ishst);
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -46,7 +94,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	dsb(ish);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
@@ -55,14 +103,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
@@ -70,14 +117,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
 
 	/* Switch to requested VMID */
-	write_sysreg(kvm->arch.vttbr, vttbr_el2);
-	isb();
+	__tlb_switch_to_guest()(kvm);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	write_sysreg(0, vttbr_el2);
+	__tlb_switch_to_host()(kvm);
 }
 
 void __hyp_text __kvm_flush_vm_context(void)

arch/avr32/include/asm/pgtable-2level.h

@@ -8,6 +8,7 @@
 #ifndef __ASM_AVR32_PGTABLE_2LEVEL_H
 #define __ASM_AVR32_PGTABLE_2LEVEL_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /*

arch/avr32/oprofile/backtrace.c

@@ -14,7 +14,7 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/sched.h>
+#include <linux/ptrace.h>
 #include <linux/uaccess.h>
 
 /* The first two words of each frame on the stack look like this if we have

arch/cris/arch-v32/drivers/cryptocop.c

@@ -2086,7 +2086,7 @@ static void cryptocop_job_queue_close(void)
 		dma_in_cfg.en = regk_dma_no;
 		REG_WR(dma, IN_DMA_INST, rw_cfg, dma_in_cfg);
 
-		/* Disble the cryptocop. */
+		/* Disable the cryptocop. */
 		rw_cfg = REG_RD(strcop, regi_strcop, rw_cfg);
 		rw_cfg.en = 0;
 		REG_WR(strcop, regi_strcop, rw_cfg, rw_cfg);

arch/cris/include/asm/pgtable.h

@@ -6,6 +6,7 @@
 #define _CRIS_PGTABLE_H
 
 #include <asm/page.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #ifndef __ASSEMBLY__

arch/frv/include/asm/pgtable.h

@@ -16,6 +16,7 @@
 #ifndef _ASM_PGTABLE_H
 #define _ASM_PGTABLE_H
 
+#include <asm-generic/5level-fixup.h>
 #include <asm/mem-layout.h>
 #include <asm/setup.h>
 #include <asm/processor.h>

arch/h8300/include/asm/pgtable.h

 #ifndef _H8300_PGTABLE_H
 #define _H8300_PGTABLE_H
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #include <asm-generic/pgtable.h>
 #define pgtable_cache_init()   do { } while (0)

arch/h8300/kernel/ptrace_h.c

@@ -9,7 +9,7 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <asm/ptrace.h>
 
 #define BREAKINST 0x5730 /* trapa #3 */

arch/hexagon/include/asm/pgtable.h

@@ -26,6 +26,7 @@
  */
 #include <linux/swap.h>
 #include <asm/page.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /* A handy thing to have if one has the RAM. Declared in head.S */

arch/ia64/include/asm/pgtable.h

@@ -587,8 +587,10 @@ extern struct page *zero_page_memmap_ptr;
 
 
 #if CONFIG_PGTABLE_LEVELS == 3
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #endif
+#include <asm-generic/5level-fixup.h>
 #include <asm-generic/pgtable.h>
 
 #endif /* _ASM_IA64_PGTABLE_H */

arch/metag/include/asm/pgtable.h

@@ -6,6 +6,7 @@
 #define _METAG_PGTABLE_H
 
 #include <asm/pgtable-bits.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /* Invalid regions on Meta: 0x00000000-0x001FFFFF and 0xFFFF0000-0xFFFFFFFF */

arch/microblaze/include/asm/page.h

@@ -95,7 +95,8 @@ typedef struct { unsigned long pgd; } pgd_t;
 #   else /* CONFIG_MMU */
 typedef struct { unsigned long	ste[64]; }	pmd_t;
 typedef struct { pmd_t		pue[1]; }	pud_t;
-typedef struct { pud_t		pge[1]; }	pgd_t;
+typedef struct { pud_t		p4e[1]; }	p4d_t;
+typedef struct { p4d_t		pge[1]; }	pgd_t;
 #   endif /* CONFIG_MMU */
 
 # define pte_val(x)	((x).pte)

arch/mips/cavium-octeon/cpu.c

@@ -10,7 +10,9 @@
 #include <linux/irqflags.h>
 #include <linux/notifier.h>
 #include <linux/prefetch.h>
+#include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/cop2.h>
 #include <asm/current.h>

arch/mips/cavium-octeon/crypto/octeon-crypto.c

@@ -9,6 +9,7 @@
 #include <asm/cop2.h>
 #include <linux/export.h>
 #include <linux/interrupt.h>
+#include <linux/sched/task_stack.h>
 
 #include "octeon-crypto.h"
 

arch/mips/cavium-octeon/smp.c

@@ -12,6 +12,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/init.h>
 #include <linux/export.h>
 

arch/mips/include/asm/fpu.h

@@ -12,6 +12,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
+#include <linux/ptrace.h>
 #include <linux/thread_info.h>
 #include <linux/bitops.h>
 

arch/mips/include/asm/pgtable-32.h

@@ -16,6 +16,7 @@
 #include <asm/cachectl.h>
 #include <asm/fixmap.h>
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 extern int temp_tlb_entry;

arch/mips/include/asm/pgtable-64.h

@@ -17,6 +17,7 @@
 #include <asm/cachectl.h>
 #include <asm/fixmap.h>
 
+#define __ARCH_USE_5LEVEL_HACK
 #if defined(CONFIG_PAGE_SIZE_64KB) && !defined(CONFIG_MIPS_VA_BITS_48)
 #include <asm-generic/pgtable-nopmd.h>
 #else

arch/mips/kernel/smp-bmips.c

@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/smp.h>

arch/mips/kernel/smp-mt.c

@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip/mips-gic.h>
 #include <linux/compiler.h>
+#include <linux/sched/task_stack.h>
 #include <linux/smp.h>
 
 #include <linux/atomic.h>

arch/mips/loongson64/loongson-3/cop2-ex.c

@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/notifier.h>
+#include <linux/ptrace.h>
 
 #include <asm/fpu.h>
 #include <asm/cop2.h>

arch/mips/netlogic/common/smp.c

@@ -35,6 +35,7 @@
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/init.h>
+#include <linux/sched/task_stack.h>
 #include <linux/smp.h>
 #include <linux/irq.h>
 

arch/mips/netlogic/xlp/cop2-ex.c

@@ -9,11 +9,14 @@
  * Copyright (C) 2009 Wind River Systems,
  *   written by Ralf Baechle <ralf@linux-mips.org>
  */
+#include <linux/capability.h>
 #include <linux/init.h>
 #include <linux/irqflags.h>
 #include <linux/notifier.h>
 #include <linux/prefetch.h>
+#include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/cop2.h>
 #include <asm/current.h>

arch/mips/sgi-ip22/ip28-berr.c

@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 #include <linux/seq_file.h>
 
 #include <asm/addrspace.h>

arch/mips/sgi-ip27/ip27-berr.c

@@ -12,7 +12,9 @@
 #include <linux/signal.h>	/* for SIGBUS */
 #include <linux/sched.h>	/* schow_regs(), force_sig() */
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 
+#include <asm/ptrace.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/sn0/hub.h>

arch/mips/sgi-ip27/ip27-smp.c

@@ -8,10 +8,13 @@
  */
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/topology.h>
 #include <linux/nodemask.h>
+
 #include <asm/page.h>
 #include <asm/processor.h>
+#include <asm/ptrace.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/gda.h>
 #include <asm/sn/intr.h>

arch/mips/sgi-ip32/ip32-berr.c

@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 #include <asm/traps.h>
 #include <linux/uaccess.h>
 #include <asm/addrspace.h>

arch/mips/sgi-ip32/ip32-reset.c

@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/notifier.h>
 #include <linux/delay.h>
 #include <linux/rtc/ds1685.h>

arch/mn10300/include/asm/page.h

@@ -57,6 +57,7 @@ typedef struct page *pgtable_t;
 #define __pgd(x)	((pgd_t) { (x) })
 #define __pgprot(x)	((pgprot_t) { (x) })
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #endif /* !__ASSEMBLY__ */

arch/nios2/include/asm/pgtable.h

@@ -22,6 +22,7 @@
 #include <asm/tlbflush.h>
 
 #include <asm/pgtable-bits.h>
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #define FIRST_USER_ADDRESS	0UL

arch/openrisc/include/asm/pgtable.h

@@ -25,6 +25,7 @@
 #ifndef __ASM_OPENRISC_PGTABLE_H
 #define __ASM_OPENRISC_PGTABLE_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #ifndef __ASSEMBLY__

arch/powerpc/Kconfig

@@ -80,93 +80,99 @@ config ARCH_HAS_DMA_SET_COHERENT_MASK
 config PPC
 	bool
 	default y
-	select BUILDTIME_EXTABLE_SORT
+	#
+	# Please keep this list sorted alphabetically.
+	#
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
+	select ARCH_HAS_DMA_SET_COHERENT_MASK
+	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE
+	select ARCH_HAS_SG_CHAIN
+	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
+	select ARCH_USE_BUILTIN_BSWAP
+	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select BINFMT_ELF
-	select ARCH_HAS_ELF_RANDOMIZE
-	select OF
-	select OF_EARLY_FLATTREE
-	select OF_RESERVED_MEM
-	select HAVE_FTRACE_MCOUNT_RECORD
+	select BUILDTIME_EXTABLE_SORT
+	select CLONE_BACKWARDS
+	select DCACHE_WORD_ACCESS		if PPC64 && CPU_LITTLE_ENDIAN
+	select EDAC_ATOMIC_SCRUB
+	select EDAC_SUPPORT
+	select GENERIC_ATOMIC64			if PPC32
+	select GENERIC_CLOCKEVENTS
+	select GENERIC_CLOCKEVENTS_BROADCAST	if SMP
+	select GENERIC_CMOS_UPDATE
+	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_IRQ_SHOW
+	select GENERIC_IRQ_SHOW_LEVEL
+	select GENERIC_SMP_IDLE_THREAD
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
+	select GENERIC_TIME_VSYSCALL_OLD
+	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_HARDENED_USERCOPY
+	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_CBPF_JIT			if !PPC64
+	select HAVE_CONTEXT_TRACKING		if PPC64
+	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DEBUG_STACKOVERFLOW
+	select HAVE_DMA_API_DEBUG
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
-	select HAVE_FUNCTION_TRACER
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS	if MPROFILE_KERNEL
+	select HAVE_EBPF_JIT			if PPC64
+	select HAVE_EFFICIENT_UNALIGNED_ACCESS	if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
-	select SYSCTL_EXCEPTION_TRACE
-	select VIRT_TO_BUS if !PPC64
+	select HAVE_GENERIC_RCU_GUP
+	select HAVE_HW_BREAKPOINT		if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
 	select HAVE_IDE
 	select HAVE_IOREMAP_PROT
-	select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+	select HAVE_IRQ_EXIT_ON_IRQ_STACK
+	select HAVE_KERNEL_GZIP
 	select HAVE_KPROBES
-	select HAVE_OPTPROBES if PPC64
-	select HAVE_ARCH_KGDB
 	select HAVE_KRETPROBES
-	select HAVE_ARCH_TRACEHOOK
+	select HAVE_LIVEPATCH			if HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
-	select HAVE_DMA_API_DEBUG
+	select HAVE_MOD_ARCH_SPECIFIC
+	select HAVE_NMI				if PERF_EVENTS
 	select HAVE_OPROFILE
-	select HAVE_DEBUG_KMEMLEAK
-	select ARCH_HAS_SG_CHAIN
-	select GENERIC_ATOMIC64 if PPC32
+	select HAVE_OPTPROBES			if PPC64
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_EVENTS_NMI		if PPC64
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_RCU_TABLE_FREE		if SMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
-	select ARCH_WANT_IPC_PARSE_VERSION
-	select SPARSE_IRQ
+	select HAVE_SYSCALL_TRACEPOINTS
+	select HAVE_VIRT_CPU_ACCOUNTING
 	select IRQ_DOMAIN
-	select GENERIC_IRQ_SHOW
-	select GENERIC_IRQ_SHOW_LEVEL
 	select IRQ_FORCED_THREADING
-	select HAVE_RCU_TABLE_FREE if SMP
-	select HAVE_SYSCALL_TRACEPOINTS
-	select HAVE_CBPF_JIT if !PPC64
-	select HAVE_EBPF_JIT if PPC64
-	select HAVE_ARCH_JUMP_LABEL
-	select ARCH_HAVE_NMI_SAFE_CMPXCHG
-	select ARCH_HAS_GCOV_PROFILE_ALL
-	select GENERIC_SMP_IDLE_THREAD
-	select GENERIC_CMOS_UPDATE
-	select GENERIC_TIME_VSYSCALL_OLD
-	select GENERIC_CLOCKEVENTS
-	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
-	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
-	select GENERIC_STRNCPY_FROM_USER
-	select GENERIC_STRNLEN_USER
-	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
-	select CLONE_BACKWARDS
-	select ARCH_USE_BUILTIN_BSWAP
-	select OLD_SIGSUSPEND
-	select OLD_SIGACTION if PPC32
-	select HAVE_DEBUG_STACKOVERFLOW
-	select HAVE_IRQ_EXIT_ON_IRQ_STACK
-	select ARCH_USE_CMPXCHG_LOCKREF if PPC64
-	select HAVE_ARCH_AUDITSYSCALL
-	select ARCH_SUPPORTS_ATOMIC_RMW
-	select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
 	select NO_BOOTMEM
-	select HAVE_GENERIC_RCU_GUP
-	select HAVE_PERF_EVENTS_NMI if PPC64
-	select HAVE_NMI if PERF_EVENTS
-	select EDAC_SUPPORT
-	select EDAC_ATOMIC_SCRUB
-	select ARCH_HAS_DMA_SET_COHERENT_MASK
-	select ARCH_HAS_DEVMEM_IS_ALLOWED
-	select HAVE_ARCH_SECCOMP_FILTER
-	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
-	select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
-	select GENERIC_CPU_AUTOPROBE
-	select HAVE_VIRT_CPU_ACCOUNTING
-	select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
-	select HAVE_ARCH_HARDENED_USERCOPY
-	select HAVE_KERNEL_GZIP
-	select HAVE_CONTEXT_TRACKING if PPC64
+	select OF
+	select OF_EARLY_FLATTREE
+	select OF_RESERVED_MEM
+	select OLD_SIGACTION			if PPC32
+	select OLD_SIGSUSPEND
+	select SPARSE_IRQ
+	select SYSCTL_EXCEPTION_TRACE
+	select VIRT_TO_BUS			if !PPC64
+	#
+	# Please keep this list sorted alphabetically.
+	#
 
 config GENERIC_CSUM
 	def_bool n

arch/powerpc/Makefile

@@ -72,8 +72,15 @@ GNUTARGET	:= powerpc
 MULTIPLEWORD	:= -mmultiple
 endif
 
-cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mbig-endian)
+ifdef CONFIG_PPC64
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mabi=elfv1)
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mcall-aixdesc)
+aflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mabi=elfv1)
+aflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mabi=elfv2
+endif
+
 cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mlittle-endian
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mbig-endian)
 ifneq ($(cc-name),clang)
   cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mno-strict-align
 endif
@@ -113,7 +120,9 @@ ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc))
 AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2)
 else
+CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcall-aixdesc)
+AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
 endif
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)

arch/powerpc/boot/zImage.lds.S

@@ -68,6 +68,7 @@ SECTIONS
   }
 
 #ifdef CONFIG_PPC64_BOOT_WRAPPER
+  . = ALIGN(256);
   .got :
   {
     __toc_start = .;

arch/powerpc/crypto/crc32c-vpmsum_glue.c

@@ -52,7 +52,7 @@ static int crc32c_vpmsum_cra_init(struct crypto_tfm *tfm)
 {
 	u32 *key = crypto_tfm_ctx(tfm);
 
-	*key = 0;
+	*key = ~0;
 
 	return 0;
 }

arch/powerpc/include/asm/bitops.h

@@ -51,6 +51,10 @@
 #define PPC_BIT(bit)		(1UL << PPC_BITLSHIFT(bit))
 #define PPC_BITMASK(bs, be)	((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
 
+/* Put a PPC bit into a "normal" bit position */
+#define PPC_BITEXTRACT(bits, ppc_bit, dst_bit)			\
+	((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit))
+
 #include <asm/barrier.h>
 
 /* Macro for generating the ***_bits() functions */

arch/powerpc/include/asm/book3s/32/pgtable.h

 #ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H
 #define _ASM_POWERPC_BOOK3S_32_PGTABLE_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #include <asm/book3s/32/hash.h>

arch/powerpc/include/asm/book3s/64/pgtable.h

 #ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
 #define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
 
+#include <asm-generic/5level-fixup.h>
+
 #ifndef __ASSEMBLY__
 #include <linux/mmdebug.h>
 #endif
+
 /*
  * Common bits between hash and Radix page table
  */
@@ -347,23 +350,58 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
 	__r;							\
 })
 
+static inline int __pte_write(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
+}
+
+#ifdef CONFIG_NUMA_BALANCING
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+	/*
+	 * Saved write ptes are prot none ptes that doesn't have
+	 * privileged bit sit. We mark prot none as one which has
+	 * present and pviliged bit set and RWX cleared. To mark
+	 * protnone which used to have _PAGE_WRITE set we clear
+	 * the privileged bit.
+	 */
+	return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
+}
+#else
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+	return false;
+}
+#endif
+
+static inline int pte_write(pte_t pte)
+{
+	return __pte_write(pte) || pte_savedwrite(pte);
+}
+
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
-		return;
-
-	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+	if (__pte_write(*ptep))
+		pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+	else if (unlikely(pte_savedwrite(*ptep)))
+		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0);
 }
 
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
-		return;
-
-	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+	/*
+	 * We should not find protnone for hugetlb, but this complete the
+	 * interface.
+	 */
+	if (__pte_write(*ptep))
+		pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+	else if (unlikely(pte_savedwrite(*ptep)))
+		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1);
 }
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
@@ -397,11 +435,6 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
 	pte_update(mm, addr, ptep, ~0UL, 0, 0);
 }
 
-static inline int pte_write(pte_t pte)
-{
-	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
-}
-
 static inline int pte_dirty(pte_t pte)
 {
 	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY));
@@ -465,19 +498,12 @@ static inline pte_t pte_clear_savedwrite(pte_t pte)
 	VM_BUG_ON(!pte_protnone(pte));
 	return __pte(pte_val(pte) | _PAGE_PRIVILEGED);
 }
-
-#define pte_savedwrite pte_savedwrite
-static inline bool pte_savedwrite(pte_t pte)
+#else
+#define pte_clear_savedwrite pte_clear_savedwrite
+static inline pte_t pte_clear_savedwrite(pte_t pte)
 {
-	/*
-	 * Saved write ptes are prot none ptes that doesn't have
-	 * privileged bit sit. We mark prot none as one which has
-	 * present and pviliged bit set and RWX cleared. To mark
-	 * protnone which used to have _PAGE_WRITE set we clear
-	 * the privileged bit.
-	 */
-	VM_BUG_ON(!pte_protnone(pte));
-	return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
+	VM_WARN_ON(1);
+	return __pte(pte_val(pte) & ~_PAGE_WRITE);
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
@@ -506,6 +532,8 @@ static inline unsigned long pte_pfn(pte_t pte)
 /* Generic modifiers for PTE bits */
 static inline pte_t pte_wrprotect(pte_t pte)
 {
+	if (unlikely(pte_savedwrite(pte)))
+		return pte_clear_savedwrite(pte);
 	return __pte(pte_val(pte) & ~_PAGE_WRITE);
 }
 
@@ -926,6 +954,7 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
+#define __pmd_write(pmd)	__pte_write(pmd_pte(pmd))
 #define pmd_savedwrite(pmd)	pte_savedwrite(pmd_pte(pmd))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -982,11 +1011,10 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pmd_t *pmdp)
 {
-
-	if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_WRITE)) == 0)
-		return;
-
-	pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+	if (__pmd_write((*pmdp)))
+		pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+	else if (unlikely(pmd_savedwrite(*pmdp)))
+		pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED);
 }
 
 static inline int pmd_trans_huge(pmd_t pmd)

arch/powerpc/include/asm/checksum.h

@@ -112,7 +112,7 @@ static inline __wsum csum_add(__wsum csum, __wsum addend)
 
 #ifdef __powerpc64__
 	res += (__force u64)addend;
-	return (__force __wsum)((u32)res + (res >> 32));
+	return (__force __wsum) from64to32(res);
 #else
 	asm("addc %0,%0,%1;"
 	    "addze %0,%0;"

arch/powerpc/include/asm/cpuidle.h

@@ -70,8 +70,8 @@ static inline void report_invalid_psscr_val(u64 psscr_val, int err)
 	std	r0,0(r1);					\
 	ptesync;						\
 	ld	r0,0(r1);					\
-1:	cmpd	cr0,r0,r0;					\
-	bne	1b;						\
+236:	cmpd	cr0,r0,r0;					\
+	bne	236b;						\
 	IDLE_INST;						\
 
 #define	IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST)			\

arch/powerpc/include/asm/elf.h

@@ -144,8 +144,8 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define ARCH_DLINFO_CACHE_GEOMETRY					\
 	NEW_AUX_ENT(AT_L1I_CACHESIZE, ppc64_caches.l1i.size);		\
 	NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, get_cache_geometry(l1i));	\
-	NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1i.size);		\
-	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1i));	\
+	NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1d.size);		\
+	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1d));	\
 	NEW_AUX_ENT(AT_L2_CACHESIZE, ppc64_caches.l2.size);		\
 	NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, get_cache_geometry(l2));	\
 	NEW_AUX_ENT(AT_L3_CACHESIZE, ppc64_caches.l3.size);		\

arch/powerpc/include/asm/mce.h

@@ -66,6 +66,55 @@
 
 #define P8_DSISR_MC_SLB_ERRORS		(P7_DSISR_MC_SLB_ERRORS | \
 					 P8_DSISR_MC_ERAT_MULTIHIT_SEC)
+
+/*
+ * Machine Check bits on power9
+ */
+#define P9_SRR1_MC_LOADSTORE(srr1)	(((srr1) >> PPC_BITLSHIFT(42)) & 1)
+
+#define P9_SRR1_MC_IFETCH(srr1)	(	\
+	PPC_BITEXTRACT(srr1, 45, 0) |	\
+	PPC_BITEXTRACT(srr1, 44, 1) |	\
+	PPC_BITEXTRACT(srr1, 43, 2) |	\
+	PPC_BITEXTRACT(srr1, 36, 3) )
+
+/* 0 is reserved */
+#define P9_SRR1_MC_IFETCH_UE				1
+#define P9_SRR1_MC_IFETCH_SLB_PARITY			2
+#define P9_SRR1_MC_IFETCH_SLB_MULTIHIT			3
+#define P9_SRR1_MC_IFETCH_ERAT_MULTIHIT			4
+#define P9_SRR1_MC_IFETCH_TLB_MULTIHIT			5
+#define P9_SRR1_MC_IFETCH_UE_TLB_RELOAD			6
+/* 7 is reserved */
+#define P9_SRR1_MC_IFETCH_LINK_TIMEOUT			8
+#define P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT	9
+/* 10 ? */
+#define P9_SRR1_MC_IFETCH_RA			11
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK		12
+#define P9_SRR1_MC_IFETCH_RA_ASYNC_STORE		13
+#define P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT	14
+#define P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN	15
+
+/* DSISR bits for machine check (On Power9) */
+#define P9_DSISR_MC_UE					(PPC_BIT(48))
+#define P9_DSISR_MC_UE_TABLEWALK			(PPC_BIT(49))
+#define P9_DSISR_MC_LINK_LOAD_TIMEOUT			(PPC_BIT(50))
+#define P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT		(PPC_BIT(51))
+#define P9_DSISR_MC_ERAT_MULTIHIT			(PPC_BIT(52))
+#define P9_DSISR_MC_TLB_MULTIHIT_MFTLB			(PPC_BIT(53))
+#define P9_DSISR_MC_USER_TLBIE				(PPC_BIT(54))
+#define P9_DSISR_MC_SLB_PARITY_MFSLB			(PPC_BIT(55))
+#define P9_DSISR_MC_SLB_MULTIHIT_MFSLB			(PPC_BIT(56))
+#define P9_DSISR_MC_RA_LOAD				(PPC_BIT(57))
+#define P9_DSISR_MC_RA_TABLEWALK			(PPC_BIT(58))
+#define P9_DSISR_MC_RA_TABLEWALK_FOREIGN		(PPC_BIT(59))
+#define P9_DSISR_MC_RA_FOREIGN				(PPC_BIT(60))
+
+/* SLB error bits */
+#define P9_DSISR_MC_SLB_ERRORS		(P9_DSISR_MC_ERAT_MULTIHIT | \
+					 P9_DSISR_MC_SLB_PARITY_MFSLB | \
+					 P9_DSISR_MC_SLB_MULTIHIT_MFSLB)
+
 enum MCE_Version {
 	MCE_V1 = 1,
 };
@@ -93,6 +142,9 @@ enum MCE_ErrorType {
 	MCE_ERROR_TYPE_SLB = 2,
 	MCE_ERROR_TYPE_ERAT = 3,
 	MCE_ERROR_TYPE_TLB = 4,
+	MCE_ERROR_TYPE_USER = 5,
+	MCE_ERROR_TYPE_RA = 6,
+	MCE_ERROR_TYPE_LINK = 7,
 };
 
 enum MCE_UeErrorType {
@@ -121,6 +173,32 @@ enum MCE_TlbErrorType {
 	MCE_TLB_ERROR_MULTIHIT = 2,
 };
 
+enum MCE_UserErrorType {
+	MCE_USER_ERROR_INDETERMINATE = 0,
+	MCE_USER_ERROR_TLBIE = 1,
+};
+
+enum MCE_RaErrorType {
+	MCE_RA_ERROR_INDETERMINATE = 0,
+	MCE_RA_ERROR_IFETCH = 1,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN = 3,
+	MCE_RA_ERROR_LOAD = 4,
+	MCE_RA_ERROR_STORE = 5,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 6,
+	MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN = 7,
+	MCE_RA_ERROR_LOAD_STORE_FOREIGN = 8,
+};
+
+enum MCE_LinkErrorType {
+	MCE_LINK_ERROR_INDETERMINATE = 0,
+	MCE_LINK_ERROR_IFETCH_TIMEOUT = 1,
+	MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT = 2,
+	MCE_LINK_ERROR_LOAD_TIMEOUT = 3,
+	MCE_LINK_ERROR_STORE_TIMEOUT = 4,
+	MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT = 5,
+};
+
 struct machine_check_event {
 	enum MCE_Version	version:8;	/* 0x00 */
 	uint8_t			in_use;		/* 0x01 */
@@ -166,6 +244,30 @@ struct machine_check_event {
 			uint64_t	effective_address;
 			uint8_t		reserved_2[16];
 		} tlb_error;
+
+		struct {
+			enum MCE_UserErrorType user_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} user_error;
+
+		struct {
+			enum MCE_RaErrorType ra_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} ra_error;
+
+		struct {
+			enum MCE_LinkErrorType link_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} link_error;
 	} u;
 };
 
@@ -176,8 +278,12 @@ struct mce_error_info {
 		enum MCE_SlbErrorType slb_error_type:8;
 		enum MCE_EratErrorType erat_error_type:8;
 		enum MCE_TlbErrorType tlb_error_type:8;
+		enum MCE_UserErrorType user_error_type:8;
+		enum MCE_RaErrorType ra_error_type:8;
+		enum MCE_LinkErrorType link_error_type:8;
 	} u;
-	uint8_t		reserved[2];
+	enum MCE_Severity	severity:8;
+	enum MCE_Initiator	initiator:8;
 };
 
 #define MAX_MC_EVT	100

arch/powerpc/include/asm/nohash/32/pgtable.h

 #ifndef _ASM_POWERPC_NOHASH_32_PGTABLE_H
 #define _ASM_POWERPC_NOHASH_32_PGTABLE_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 #ifndef __ASSEMBLY__

arch/powerpc/include/asm/nohash/64/pgtable-4k.h

 #ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
 #define _ASM_POWERPC_NOHASH_64_PGTABLE_4K_H
+
+#include <asm-generic/5level-fixup.h>
+
 /*
  * Entries per page directory level.  The PTE level must use a 64b record
  * for each page table entry.  The PMD and PGD level use a 32b record for

arch/powerpc/include/asm/nohash/64/pgtable-64k.h

 #ifndef _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
 #define _ASM_POWERPC_NOHASH_64_PGTABLE_64K_H
 
+#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 

arch/powerpc/include/asm/nohash/pgtable.h

@@ -230,7 +230,7 @@ static inline int hugepd_ok(hugepd_t hpd)
 	return ((hpd_val(hpd) & 0x4) != 0);
 #else
 	/* We clear the top bit to indicate hugepd */
-	return ((hpd_val(hpd) & PD_HUGE) ==  0);
+	return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0);
 #endif
 }
 

arch/powerpc/include/asm/ppc-opcode.h

@@ -284,6 +284,13 @@
 #define PPC_INST_BRANCH_COND		0x40800000
 #define PPC_INST_LBZCIX			0x7c0006aa
 #define PPC_INST_STBCIX			0x7c0007aa
+#define PPC_INST_LWZX			0x7c00002e
+#define PPC_INST_LFSX			0x7c00042e
+#define PPC_INST_STFSX			0x7c00052e
+#define PPC_INST_LFDX			0x7c0004ae
+#define PPC_INST_STFDX			0x7c0005ae
+#define PPC_INST_LVX			0x7c0000ce
+#define PPC_INST_STVX			0x7c0001ce
 
 /* macros to insert fields into opcodes */
 #define ___PPC_RA(a)	(((a) & 0x1f) << 16)

arch/powerpc/include/asm/prom.h

@@ -160,12 +160,18 @@ struct of_drconf_cell {
 #define OV5_PFO_HW_ENCR		0x1120	/* PFO Encryption Accelerator */
 #define OV5_SUB_PROCESSORS	0x1501	/* 1,2,or 4 Sub-Processors supported */
 #define OV5_XIVE_EXPLOIT	0x1701	/* XIVE exploitation supported */
-#define OV5_MMU_RADIX_300	0x1880	/* ISA v3.00 radix MMU supported */
-#define OV5_MMU_HASH_300	0x1840	/* ISA v3.00 hash MMU supported */
-#define OV5_MMU_SEGM_RADIX	0x1820	/* radix mode (no segmentation) */
-#define OV5_MMU_PROC_TBL	0x1810	/* hcall selects SLB or proc table */
-#define OV5_MMU_SLB		0x1800	/* always use SLB */
-#define OV5_MMU_GTSE		0x1808	/* Guest translation shootdown */
+/* MMU Base Architecture */
+#define OV5_MMU_SUPPORT		0x18C0	/* MMU Mode Support Mask */
+#define OV5_MMU_HASH		0x1800	/* Hash MMU Only */
+#define OV5_MMU_RADIX		0x1840	/* Radix MMU Only */
+#define OV5_MMU_EITHER		0x1880	/* Hash or Radix Supported */
+#define OV5_MMU_DYNAMIC		0x18C0	/* Hash or Radix Can Switch Later */
+#define OV5_NMMU		0x1820	/* Nest MMU Available */
+/* Hash Table Extensions */
+#define OV5_HASH_SEG_TBL	0x1980	/* In Memory Segment Tables Available */
+#define OV5_HASH_GTSE		0x1940	/* Guest Translation Shoot Down Avail */
+/* Radix Table Extensions */
+#define OV5_RADIX_GTSE		0x1A40	/* Guest Translation Shoot Down Avail */
 
 /* Option Vector 6: IBM PAPR hints */
 #define OV6_LINUX		0x02	/* Linux is our OS */

arch/powerpc/kernel/cputable.c

@@ -77,6 +77,7 @@ extern void __flush_tlb_power8(unsigned int action);
 extern void __flush_tlb_power9(unsigned int action);
 extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
 extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
 #endif /* CONFIG_PPC64 */
 #if defined(CONFIG_E500)
 extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
@@ -540,6 +541,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
 		.flush_tlb		= __flush_tlb_power9,
+		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
 	{	/* Power9 */
@@ -559,6 +561,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_setup		= __setup_cpu_power9,
 		.cpu_restore		= __restore_cpu_power9,
 		.flush_tlb		= __flush_tlb_power9,
+		.machine_check_early	= __machine_check_early_realmode_p9,
 		.platform		= "power9",
 	},
 	{	/* Cell Broadband Engine */

arch/powerpc/kernel/idle_book3s.S

@@ -276,19 +276,21 @@ power_enter_stop:
  */
 	andis.   r4,r3,PSSCR_EC_ESL_MASK_SHIFTED
 	clrldi   r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */
-	bne	 1f
+	bne	 .Lhandle_esl_ec_set
 	IDLE_STATE_ENTER_SEQ(PPC_STOP)
 	li	r3,0  /* Since we didn't lose state, return 0 */
 	b 	pnv_wakeup_noloss
+
+.Lhandle_esl_ec_set:
 /*
  * Check if the requested state is a deep idle state.
  */
-1:	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
+	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
 	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
 	cmpd	r3,r4
-	bge	2f
+	bge	.Lhandle_deep_stop
 	IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP)
-2:
+.Lhandle_deep_stop:
 /*
  * Entering deep idle state.
  * Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to

arch/powerpc/kernel/mce.c

@@ -58,6 +58,15 @@ static void mce_set_error_info(struct machine_check_event *mce,
 	case MCE_ERROR_TYPE_TLB:
 		mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
 		break;
+	case MCE_ERROR_TYPE_USER:
+		mce->u.user_error.user_error_type = mce_err->u.user_error_type;
+		break;
+	case MCE_ERROR_TYPE_RA:
+		mce->u.ra_error.ra_error_type = mce_err->u.ra_error_type;
+		break;
+	case MCE_ERROR_TYPE_LINK:
+		mce->u.link_error.link_error_type = mce_err->u.link_error_type;
+		break;
 	case MCE_ERROR_TYPE_UNKNOWN:
 	default:
 		break;
@@ -90,13 +99,14 @@ void save_mce_event(struct pt_regs *regs, long handled,
 	mce->gpr3 = regs->gpr[3];
 	mce->in_use = 1;
 
-	mce->initiator = MCE_INITIATOR_CPU;
 	/* Mark it recovered if we have handled it and MSR(RI=1). */
 	if (handled && (regs->msr & MSR_RI))
 		mce->disposition = MCE_DISPOSITION_RECOVERED;
 	else
 		mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
-	mce->severity = MCE_SEV_ERROR_SYNC;
+
+	mce->initiator = mce_err->initiator;
+	mce->severity = mce_err->severity;
 
 	/*
 	 * Populate the mce error_type and type-specific error_type.
@@ -115,6 +125,15 @@ void save_mce_event(struct pt_regs *regs, long handled,
 	} else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
 		mce->u.erat_error.effective_address_provided = true;
 		mce->u.erat_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_USER) {
+		mce->u.user_error.effective_address_provided = true;
+		mce->u.user_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_RA) {
+		mce->u.ra_error.effective_address_provided = true;
+		mce->u.ra_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_LINK) {
+		mce->u.link_error.effective_address_provided = true;
+		mce->u.link_error.effective_address = addr;
 	} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
 		mce->u.ue_error.effective_address_provided = true;
 		mce->u.ue_error.effective_address = addr;
@@ -239,6 +258,29 @@ void machine_check_print_event_info(struct machine_check_event *evt)
 		"Parity",
 		"Multihit",
 	};
+	static const char *mc_user_types[] = {
+		"Indeterminate",
+		"tlbie(l) invalid",
+	};
+	static const char *mc_ra_types[] = {
+		"Indeterminate",
+		"Instruction fetch (bad)",
+		"Page table walk ifetch (bad)",
+		"Page table walk ifetch (foreign)",
+		"Load (bad)",
+		"Store (bad)",
+		"Page table walk Load/Store (bad)",
+		"Page table walk Load/Store (foreign)",
+		"Load/Store (foreign)",
+	};
+	static const char *mc_link_types[] = {
+		"Indeterminate",
+		"Instruction fetch (timeout)",
+		"Page table walk ifetch (timeout)",
+		"Load (timeout)",
+		"Store (timeout)",
+		"Page table walk Load/Store (timeout)",
+	};
 
 	/* Print things out */
 	if (evt->version != MCE_V1) {
@@ -315,6 +357,36 @@ void machine_check_print_event_info(struct machine_check_event *evt)
 			printk("%s    Effective address: %016llx\n",
 			       level, evt->u.tlb_error.effective_address);
 		break;
+	case MCE_ERROR_TYPE_USER:
+		subtype = evt->u.user_error.user_error_type <
+			ARRAY_SIZE(mc_user_types) ?
+			mc_user_types[evt->u.user_error.user_error_type]
+			: "Unknown";
+		printk("%s  Error type: User [%s]\n", level, subtype);
+		if (evt->u.user_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.user_error.effective_address);
+		break;
+	case MCE_ERROR_TYPE_RA:
+		subtype = evt->u.ra_error.ra_error_type <
+			ARRAY_SIZE(mc_ra_types) ?
+			mc_ra_types[evt->u.ra_error.ra_error_type]
+			: "Unknown";
+		printk("%s  Error type: Real address [%s]\n", level, subtype);
+		if (evt->u.ra_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.ra_error.effective_address);
+		break;
+	case MCE_ERROR_TYPE_LINK:
+		subtype = evt->u.link_error.link_error_type <
+			ARRAY_SIZE(mc_link_types) ?
+			mc_link_types[evt->u.link_error.link_error_type]
+			: "Unknown";
+		printk("%s  Error type: Link [%s]\n", level, subtype);
+		if (evt->u.link_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.link_error.effective_address);
+		break;
 	default:
 	case MCE_ERROR_TYPE_UNKNOWN:
 		printk("%s  Error type: Unknown\n", level);
@@ -341,6 +413,18 @@ uint64_t get_mce_fault_addr(struct machine_check_event *evt)
 		if (evt->u.tlb_error.effective_address_provided)
 			return evt->u.tlb_error.effective_address;
 		break;
+	case MCE_ERROR_TYPE_USER:
+		if (evt->u.user_error.effective_address_provided)
+			return evt->u.user_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_RA:
+		if (evt->u.ra_error.effective_address_provided)
+			return evt->u.ra_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_LINK:
+		if (evt->u.link_error.effective_address_provided)
+			return evt->u.link_error.effective_address;
+		break;
 	default:
 	case MCE_ERROR_TYPE_UNKNOWN:
 		break;

arch/powerpc/kernel/mce_power.c

@@ -116,6 +116,51 @@ static void flush_and_reload_slb(void)
 }
 #endif
 
+static void flush_erat(void)
+{
+	asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
+}
+
+#define MCE_FLUSH_SLB 1
+#define MCE_FLUSH_TLB 2
+#define MCE_FLUSH_ERAT 3
+
+static int mce_flush(int what)
+{
+#ifdef CONFIG_PPC_STD_MMU_64
+	if (what == MCE_FLUSH_SLB) {
+		flush_and_reload_slb();
+		return 1;
+	}
+#endif
+	if (what == MCE_FLUSH_ERAT) {
+		flush_erat();
+		return 1;
+	}
+	if (what == MCE_FLUSH_TLB) {
+		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
+			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static int mce_handle_flush_derrors(uint64_t dsisr, uint64_t slb, uint64_t tlb, uint64_t erat)
+{
+	if ((dsisr & slb) && mce_flush(MCE_FLUSH_SLB))
+		dsisr &= ~slb;
+	if ((dsisr & erat) && mce_flush(MCE_FLUSH_ERAT))
+		dsisr &= ~erat;
+	if ((dsisr & tlb) && mce_flush(MCE_FLUSH_TLB))
+		dsisr &= ~tlb;
+	/* Any other errors we don't understand? */
+	if (dsisr)
+		return 0;
+	return 1;
+}
+
 static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
 {
 	long handled = 1;
@@ -281,6 +326,9 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs)
 	long handled = 1;
 	struct mce_error_info mce_error_info = { 0 };
 
+	mce_error_info.severity = MCE_SEV_ERROR_SYNC;
+	mce_error_info.initiator = MCE_INITIATOR_CPU;
+
 	srr1 = regs->msr;
 	nip = regs->nip;
 
@@ -352,6 +400,9 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs)
 	long handled = 1;
 	struct mce_error_info mce_error_info = { 0 };
 
+	mce_error_info.severity = MCE_SEV_ERROR_SYNC;
+	mce_error_info.initiator = MCE_INITIATOR_CPU;
+
 	srr1 = regs->msr;
 	nip = regs->nip;
 
@@ -372,3 +423,189 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs)
 	save_mce_event(regs, handled, &mce_error_info, nip, addr);
 	return handled;
 }
+
+static int mce_handle_derror_p9(struct pt_regs *regs)
+{
+	uint64_t dsisr = regs->dsisr;
+
+	return mce_handle_flush_derrors(dsisr,
+			P9_DSISR_MC_SLB_PARITY_MFSLB |
+			P9_DSISR_MC_SLB_MULTIHIT_MFSLB,
+
+			P9_DSISR_MC_TLB_MULTIHIT_MFTLB,
+
+			P9_DSISR_MC_ERAT_MULTIHIT);
+}
+
+static int mce_handle_ierror_p9(struct pt_regs *regs)
+{
+	uint64_t srr1 = regs->msr;
+
+	switch (P9_SRR1_MC_IFETCH(srr1)) {
+	case P9_SRR1_MC_IFETCH_SLB_PARITY:
+	case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
+		return mce_flush(MCE_FLUSH_SLB);
+	case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
+		return mce_flush(MCE_FLUSH_TLB);
+	case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
+		return mce_flush(MCE_FLUSH_ERAT);
+	default:
+		return 0;
+	}
+}
+
+static void mce_get_derror_p9(struct pt_regs *regs,
+		struct mce_error_info *mce_err, uint64_t *addr)
+{
+	uint64_t dsisr = regs->dsisr;
+
+	mce_err->severity = MCE_SEV_ERROR_SYNC;
+	mce_err->initiator = MCE_INITIATOR_CPU;
+
+	if (dsisr & P9_DSISR_MC_USER_TLBIE)
+		*addr = regs->nip;
+	else
+		*addr = regs->dar;
+
+	if (dsisr & P9_DSISR_MC_UE) {
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
+	} else if (dsisr & P9_DSISR_MC_UE_TABLEWALK) {
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+	} else if (dsisr & P9_DSISR_MC_LINK_LOAD_TIMEOUT) {
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_LOAD_TIMEOUT;
+	} else if (dsisr & P9_DSISR_MC_LINK_TABLEWALK_TIMEOUT) {
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_LOAD_STORE_TIMEOUT;
+	} else if (dsisr & P9_DSISR_MC_ERAT_MULTIHIT) {
+		mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+		mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+	} else if (dsisr & P9_DSISR_MC_TLB_MULTIHIT_MFTLB) {
+		mce_err->error_type = MCE_ERROR_TYPE_TLB;
+		mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+	} else if (dsisr & P9_DSISR_MC_USER_TLBIE) {
+		mce_err->error_type = MCE_ERROR_TYPE_USER;
+		mce_err->u.user_error_type = MCE_USER_ERROR_TLBIE;
+	} else if (dsisr & P9_DSISR_MC_SLB_PARITY_MFSLB) {
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+	} else if (dsisr & P9_DSISR_MC_SLB_MULTIHIT_MFSLB) {
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+	} else if (dsisr & P9_DSISR_MC_RA_LOAD) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD;
+	} else if (dsisr & P9_DSISR_MC_RA_TABLEWALK) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+	} else if (dsisr & P9_DSISR_MC_RA_TABLEWALK_FOREIGN) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN;
+	} else if (dsisr & P9_DSISR_MC_RA_FOREIGN) {
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_LOAD_STORE_FOREIGN;
+	}
+}
+
+static void mce_get_ierror_p9(struct pt_regs *regs,
+		struct mce_error_info *mce_err, uint64_t *addr)
+{
+	uint64_t srr1 = regs->msr;
+
+	switch (P9_SRR1_MC_IFETCH(srr1)) {
+	case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
+	case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
+		mce_err->severity = MCE_SEV_FATAL;
+		break;
+	default:
+		mce_err->severity = MCE_SEV_ERROR_SYNC;
+		break;
+	}
+
+	mce_err->initiator = MCE_INITIATOR_CPU;
+
+	*addr = regs->nip;
+
+	switch (P9_SRR1_MC_IFETCH(srr1)) {
+	case P9_SRR1_MC_IFETCH_UE:
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_SLB_PARITY:
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+		break;
+	case P9_SRR1_MC_IFETCH_SLB_MULTIHIT:
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+		break;
+	case P9_SRR1_MC_IFETCH_ERAT_MULTIHIT:
+		mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+		mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+		break;
+	case P9_SRR1_MC_IFETCH_TLB_MULTIHIT:
+		mce_err->error_type = MCE_ERROR_TYPE_TLB;
+		mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+		break;
+	case P9_SRR1_MC_IFETCH_UE_TLB_RELOAD:
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_LINK_TIMEOUT:
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_IFETCH_TIMEOUT;
+		break;
+	case P9_SRR1_MC_IFETCH_LINK_TABLEWALK_TIMEOUT:
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_PAGE_TABLE_WALK_IFETCH_TIMEOUT;
+		break;
+	case P9_SRR1_MC_IFETCH_RA:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_RA_TABLEWALK:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH;
+		break;
+	case P9_SRR1_MC_IFETCH_RA_ASYNC_STORE:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_STORE;
+		break;
+	case P9_SRR1_MC_IFETCH_LINK_ASYNC_STORE_TIMEOUT:
+		mce_err->error_type = MCE_ERROR_TYPE_LINK;
+		mce_err->u.link_error_type = MCE_LINK_ERROR_STORE_TIMEOUT;
+		break;
+	case P9_SRR1_MC_IFETCH_RA_TABLEWALK_FOREIGN:
+		mce_err->error_type = MCE_ERROR_TYPE_RA;
+		mce_err->u.ra_error_type = MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN;
+		break;
+	default:
+		break;
+	}
+}
+
+long __machine_check_early_realmode_p9(struct pt_regs *regs)
+{
+	uint64_t nip, addr;
+	long handled;
+	struct mce_error_info mce_error_info = { 0 };
+
+	nip = regs->nip;
+
+	if (P9_SRR1_MC_LOADSTORE(regs->msr)) {
+		handled = mce_handle_derror_p9(regs);
+		mce_get_derror_p9(regs, &mce_error_info, &addr);
+	} else {
+		handled = mce_handle_ierror_p9(regs);
+		mce_get_ierror_p9(regs, &mce_error_info, &addr);
+	}
+
+	/* Handle UE error. */
+	if (mce_error_info.error_type == MCE_ERROR_TYPE_UE)
+		handled = mce_handle_ue_error(regs);
+
+	save_mce_event(regs, handled, &mce_error_info, nip, addr);
+	return handled;
+}

arch/powerpc/kernel/prom_init.c

@@ -168,6 +168,14 @@ static unsigned long __initdata prom_tce_alloc_start;
 static unsigned long __initdata prom_tce_alloc_end;
 #endif
 
+static bool __initdata prom_radix_disable;
+
+struct platform_support {
+	bool hash_mmu;
+	bool radix_mmu;
+	bool radix_gtse;
+};
+
 /* Platforms codes are now obsolete in the kernel. Now only used within this
  * file and ultimately gone too. Feel free to change them if you need, they
  * are not shared with anything outside of this file anymore
@@ -626,6 +634,12 @@ static void __init early_cmdline_parse(void)
 		prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000);
 #endif
 	}
+
+	opt = strstr(prom_cmd_line, "disable_radix");
+	if (opt) {
+		prom_debug("Radix disabled from cmdline\n");
+		prom_radix_disable = true;
+	}
 }
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
@@ -695,6 +709,8 @@ struct option_vector5 {
 	u8 byte22;
 	u8 intarch;
 	u8 mmu;
+	u8 hash_ext;
+	u8 radix_ext;
 } __packed;
 
 struct option_vector6 {
@@ -850,8 +866,9 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
 		.reserved3 = 0,
 		.subprocessors = 1,
 		.intarch = 0,
-		.mmu = OV5_FEAT(OV5_MMU_RADIX_300) | OV5_FEAT(OV5_MMU_HASH_300) |
-			OV5_FEAT(OV5_MMU_PROC_TBL) | OV5_FEAT(OV5_MMU_GTSE),
+		.mmu = 0,
+		.hash_ext = 0,
+		.radix_ext = 0,
 	},
 
 	/* option vector 6: IBM PAPR hints */
@@ -990,6 +1007,92 @@ static int __init prom_count_smt_threads(void)
 
 }
 
+static void __init prom_parse_mmu_model(u8 val,
+					struct platform_support *support)
+{
+	switch (val) {
+	case OV5_FEAT(OV5_MMU_DYNAMIC):
+	case OV5_FEAT(OV5_MMU_EITHER): /* Either Available */
+		prom_debug("MMU - either supported\n");
+		support->radix_mmu = !prom_radix_disable;
+		support->hash_mmu = true;
+		break;
+	case OV5_FEAT(OV5_MMU_RADIX): /* Only Radix */
+		prom_debug("MMU - radix only\n");
+		if (prom_radix_disable) {
+			/*
+			 * If we __have__ to do radix, we're better off ignoring
+			 * the command line rather than not booting.
+			 */
+			prom_printf("WARNING: Ignoring cmdline option disable_radix\n");
+		}
+		support->radix_mmu = true;
+		break;
+	case OV5_FEAT(OV5_MMU_HASH):
+		prom_debug("MMU - hash only\n");
+		support->hash_mmu = true;
+		break;
+	default:
+		prom_debug("Unknown mmu support option: 0x%x\n", val);
+		break;
+	}
+}
+
+static void __init prom_parse_platform_support(u8 index, u8 val,
+					       struct platform_support *support)
+{
+	switch (index) {
+	case OV5_INDX(OV5_MMU_SUPPORT): /* MMU Model */
+		prom_parse_mmu_model(val & OV5_FEAT(OV5_MMU_SUPPORT), support);
+		break;
+	case OV5_INDX(OV5_RADIX_GTSE): /* Radix Extensions */
+		if (val & OV5_FEAT(OV5_RADIX_GTSE)) {
+			prom_debug("Radix - GTSE supported\n");
+			support->radix_gtse = true;
+		}
+		break;
+	}
+}
+
+static void __init prom_check_platform_support(void)
+{
+	struct platform_support supported = {
+		.hash_mmu = false,
+		.radix_mmu = false,
+		.radix_gtse = false
+	};
+	int prop_len = prom_getproplen(prom.chosen,
+				       "ibm,arch-vec-5-platform-support");
+	if (prop_len > 1) {
+		int i;
+		u8 vec[prop_len];
+		prom_debug("Found ibm,arch-vec-5-platform-support, len: %d\n",
+			   prop_len);
+		prom_getprop(prom.chosen, "ibm,arch-vec-5-platform-support",
+			     &vec, sizeof(vec));
+		for (i = 0; i < prop_len; i += 2) {
+			prom_debug("%d: index = 0x%x val = 0x%x\n", i / 2
+								  , vec[i]
+								  , vec[i + 1]);
+			prom_parse_platform_support(vec[i], vec[i + 1],
+						    &supported);
+		}
+	}
+
+	if (supported.radix_mmu && supported.radix_gtse) {
+		/* Radix preferred - but we require GTSE for now */
+		prom_debug("Asking for radix with GTSE\n");
+		ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX);
+		ibm_architecture_vec.vec5.radix_ext = OV5_FEAT(OV5_RADIX_GTSE);
+	} else if (supported.hash_mmu) {
+		/* Default to hash mmu (if we can) */
+		prom_debug("Asking for hash\n");
+		ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_HASH);
+	} else {
+		/* We're probably on a legacy hypervisor */
+		prom_debug("Assuming legacy hash support\n");
+	}
+}
 
 static void __init prom_send_capabilities(void)
 {
@@ -997,6 +1100,9 @@ static void __init prom_send_capabilities(void)
 	prom_arg_t ret;
 	u32 cores;
 
+	/* Check ibm,arch-vec-5-platform-support and fixup vec5 if required */
+	prom_check_platform_support();
+
 	root = call_prom("open", 1, 1, ADDR("/"));
 	if (root != 0) {
 		/* We need to tell the FW about the number of cores we support.
@@ -2993,6 +3099,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 */
 	prom_check_initrd(r3, r4);
 
+	/*
+	 * Do early parsing of command line
+	 */
+	early_cmdline_parse();
+
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 	/*
 	 * On pSeries, inform the firmware about our capabilities
@@ -3008,11 +3119,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	if (of_platform != PLATFORM_POWERMAC)
 		copy_and_flush(0, kbase, 0x100, 0);
 
-	/*
-	 * Do early parsing of command line
-	 */
-	early_cmdline_parse();
-
 	/*
 	 * Initialize memory management within prom_init
 	 */

arch/powerpc/kernel/setup_64.c

@@ -408,7 +408,10 @@ static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize,
 	info->line_size = lsize;
 	info->block_size = bsize;
 	info->log_block_size = __ilog2(bsize);
-	info->blocks_per_page = PAGE_SIZE / bsize;
+	if (bsize)
+		info->blocks_per_page = PAGE_SIZE / bsize;
+	else
+		info->blocks_per_page = 0;
 
 	if (sets == 0)
 		info->assoc = 0xffff;

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -601,7 +601,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 							 hva, NULL, NULL);
 			if (ptep) {
 				pte = kvmppc_read_update_linux_pte(ptep, 1);
-				if (pte_write(pte))
+				if (__pte_write(pte))
 					write_ok = 1;
 			}
 			local_irq_restore(flags);

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -256,7 +256,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		}
 		pte = kvmppc_read_update_linux_pte(ptep, writing);
 		if (pte_present(pte) && !pte_protnone(pte)) {
-			if (writing && !pte_write(pte))
+			if (writing && !__pte_write(pte))
 				/* make the actual HPTE be read-only */
 				ptel = hpte_make_readonly(ptel);
 			is_ci = pte_ci(pte);

arch/powerpc/lib/Makefile

@@ -20,6 +20,7 @@ obj64-y	+= copypage_64.o copyuser_64.o usercopy_64.o mem_64.o hweight_64.o \
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o
+obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
 
 obj-y			+= checksum_$(BITS).o checksum_wrappers.o
 

arch/powerpc/lib/sstep.c

@@ -1799,8 +1799,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto instr_done;
 
 	case LARX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (op.ea & (size - 1))
 			break;		/* can't handle misaligned */
 		if (!address_ok(regs, op.ea, size))
@@ -1823,8 +1821,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto ldst_done;
 
 	case STCX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (op.ea & (size - 1))
 			break;		/* can't handle misaligned */
 		if (!address_ok(regs, op.ea, size))
@@ -1849,8 +1845,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto ldst_done;
 
 	case LOAD:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = read_mem(&regs->gpr[op.reg], op.ea, size, regs);
 		if (!err) {
 			if (op.type & SIGNEXT)
@@ -1862,8 +1856,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef CONFIG_PPC_FPU
 	case LOAD_FP:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (size == 4)
 			err = do_fp_load(op.reg, do_lfs, op.ea, size, regs);
 		else
@@ -1872,15 +1864,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 #endif
 #ifdef CONFIG_ALTIVEC
 	case LOAD_VMX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs);
 		goto ldst_done;
 #endif
 #ifdef CONFIG_VSX
 	case LOAD_VSX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs);
 		goto ldst_done;
 #endif
@@ -1903,8 +1891,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto instr_done;
 
 	case STORE:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if ((op.type & UPDATE) && size == sizeof(long) &&
 		    op.reg == 1 && op.update_reg == 1 &&
 		    !(regs->msr & MSR_PR) &&
@@ -1917,8 +1903,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef CONFIG_PPC_FPU
 	case STORE_FP:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (size == 4)
 			err = do_fp_store(op.reg, do_stfs, op.ea, size, regs);
 		else
@@ -1927,15 +1911,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 #endif
 #ifdef CONFIG_ALTIVEC
 	case STORE_VMX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs);
 		goto ldst_done;
 #endif
 #ifdef CONFIG_VSX
 	case STORE_VSX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs);
 		goto ldst_done;
 #endif

arch/powerpc/lib/test_emulate_step.c

+/*
+ * Simple sanity test for emulate_step load/store instructions.
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * This program is free software;  you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "emulate_step_test: " fmt
+
+#include <linux/ptrace.h>
+#include <asm/sstep.h>
+#include <asm/ppc-opcode.h>
+
+#define IMM_L(i)		((uintptr_t)(i) & 0xffff)
+
+/*
+ * Defined with TEST_ prefix so it does not conflict with other
+ * definitions.
+ */
+#define TEST_LD(r, base, i)	(PPC_INST_LD | ___PPC_RT(r) |		\
+					___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZ(r, base, i)	(PPC_INST_LWZ | ___PPC_RT(r) |		\
+					___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZX(t, a, b)	(PPC_INST_LWZX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STD(r, base, i)	(PPC_INST_STD | ___PPC_RS(r) |		\
+					___PPC_RA(base) | ((i) & 0xfffc))
+#define TEST_LDARX(t, a, b, eh)	(PPC_INST_LDARX | ___PPC_RT(t) |	\
+					___PPC_RA(a) | ___PPC_RB(b) |	\
+					__PPC_EH(eh))
+#define TEST_STDCX(s, a, b)	(PPC_INST_STDCX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFSX(t, a, b)	(PPC_INST_LFSX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFSX(s, a, b)	(PPC_INST_STFSX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFDX(t, a, b)	(PPC_INST_LFDX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFDX(s, a, b)	(PPC_INST_STFDX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LVX(t, a, b)	(PPC_INST_LVX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STVX(s, a, b)	(PPC_INST_STVX | ___PPC_RS(s) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LXVD2X(s, a, b)	(PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b))
+#define TEST_STXVD2X(s, a, b)	(PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b))
+
+
+static void __init init_pt_regs(struct pt_regs *regs)
+{
+	static unsigned long msr;
+	static bool msr_cached;
+
+	memset(regs, 0, sizeof(struct pt_regs));
+
+	if (likely(msr_cached)) {
+		regs->msr = msr;
+		return;
+	}
+
+	asm volatile("mfmsr %0" : "=r"(regs->msr));
+
+	regs->msr |= MSR_FP;
+	regs->msr |= MSR_VEC;
+	regs->msr |= MSR_VSX;
+
+	msr = regs->msr;
+	msr_cached = true;
+}
+
+static void __init show_result(char *ins, char *result)
+{
+	pr_info("%-14s : %s\n", ins, result);
+}
+
+static void __init test_ld(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x23;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+
+	/* ld r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_LD(5, 3, 0));
+
+	if (stepped == 1 && regs.gpr[5] == a)
+		show_result("ld", "PASS");
+	else
+		show_result("ld", "FAIL");
+}
+
+static void __init test_lwz(void)
+{
+	struct pt_regs regs;
+	unsigned int a = 0x4545;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+
+	/* lwz r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_LWZ(5, 3, 0));
+
+	if (stepped == 1 && regs.gpr[5] == a)
+		show_result("lwz", "PASS");
+	else
+		show_result("lwz", "FAIL");
+}
+
+static void __init test_lwzx(void)
+{
+	struct pt_regs regs;
+	unsigned int a[3] = {0x0, 0x0, 0x1234};
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) a;
+	regs.gpr[4] = 8;
+	regs.gpr[5] = 0x8765;
+
+	/* lwzx r5, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LWZX(5, 3, 4));
+	if (stepped == 1 && regs.gpr[5] == a[2])
+		show_result("lwzx", "PASS");
+	else
+		show_result("lwzx", "FAIL");
+}
+
+static void __init test_std(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x1234;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+	regs.gpr[5] = 0x5678;
+
+	/* std r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_STD(5, 3, 0));
+	if (stepped == 1 || regs.gpr[5] == a)
+		show_result("std", "PASS");
+	else
+		show_result("std", "FAIL");
+}
+
+static void __init test_ldarx_stdcx(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x1234;
+	int stepped = -1;
+	unsigned long cr0_eq = 0x1 << 29; /* eq bit of CR0 */
+
+	init_pt_regs(&regs);
+	asm volatile("mfcr %0" : "=r"(regs.ccr));
+
+
+	/*** ldarx ***/
+
+	regs.gpr[3] = (unsigned long) &a;
+	regs.gpr[4] = 0;
+	regs.gpr[5] = 0x5678;
+
+	/* ldarx r5, r3, r4, 0 */
+	stepped = emulate_step(&regs, TEST_LDARX(5, 3, 4, 0));
+
+	/*
+	 * Don't touch 'a' here. Touching 'a' can do Load/store
+	 * of 'a' which result in failure of subsequent stdcx.
+	 * Instead, use hardcoded value for comparison.
+	 */
+	if (stepped <= 0 || regs.gpr[5] != 0x1234) {
+		show_result("ldarx / stdcx.", "FAIL (ldarx)");
+		return;
+	}
+
+
+	/*** stdcx. ***/
+
+	regs.gpr[5] = 0x9ABC;
+
+	/* stdcx. r5, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STDCX(5, 3, 4));
+
+	/*
+	 * Two possible scenarios that indicates successful emulation
+	 * of stdcx. :
+	 *  1. Reservation is active and store is performed. In this
+	 *     case cr0.eq bit will be set to 1.
+	 *  2. Reservation is not active and store is not performed.
+	 *     In this case cr0.eq bit will be set to 0.
+	 */
+	if (stepped == 1 && ((regs.gpr[5] == a && (regs.ccr & cr0_eq))
+			|| (regs.gpr[5] != a && !(regs.ccr & cr0_eq))))
+		show_result("ldarx / stdcx.", "PASS");
+	else
+		show_result("ldarx / stdcx.", "FAIL (stdcx.)");
+}
+
+#ifdef CONFIG_PPC_FPU
+static void __init test_lfsx_stfsx(void)
+{
+	struct pt_regs regs;
+	union {
+		float a;
+		int b;
+	} c;
+	int cached_b;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lfsx ***/
+
+	c.a = 123.45;
+	cached_b = c.b;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lfsx frt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LFSX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lfsx", "PASS");
+	else
+		show_result("lfsx", "FAIL");
+
+
+	/*** stfsx ***/
+
+	c.a = 678.91;
+
+	/* stfsx frs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STFSX(10, 3, 4));
+
+	if (stepped == 1 && c.b == cached_b)
+		show_result("stfsx", "PASS");
+	else
+		show_result("stfsx", "FAIL");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+	struct pt_regs regs;
+	union {
+		double a;
+		long b;
+	} c;
+	long cached_b;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lfdx ***/
+
+	c.a = 123456.78;
+	cached_b = c.b;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lfdx frt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LFDX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lfdx", "PASS");
+	else
+		show_result("lfdx", "FAIL");
+
+
+	/*** stfdx ***/
+
+	c.a = 987654.32;
+
+	/* stfdx frs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STFDX(10, 3, 4));
+
+	if (stepped == 1 && c.b == cached_b)
+		show_result("stfdx", "PASS");
+	else
+		show_result("stfdx", "FAIL");
+}
+#else
+static void __init test_lfsx_stfsx(void)
+{
+	show_result("lfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+	show_result("stfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+	show_result("lfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+	show_result("stfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+static void __init test_lvx_stvx(void)
+{
+	struct pt_regs regs;
+	union {
+		vector128 a;
+		u32 b[4];
+	} c;
+	u32 cached_b[4];
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lvx ***/
+
+	cached_b[0] = c.b[0] = 923745;
+	cached_b[1] = c.b[1] = 2139478;
+	cached_b[2] = c.b[2] = 9012;
+	cached_b[3] = c.b[3] = 982134;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lvx vrt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LVX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lvx", "PASS");
+	else
+		show_result("lvx", "FAIL");
+
+
+	/*** stvx ***/
+
+	c.b[0] = 4987513;
+	c.b[1] = 84313948;
+	c.b[2] = 71;
+	c.b[3] = 498532;
+
+	/* stvx vrs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STVX(10, 3, 4));
+
+	if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+		show_result("stvx", "PASS");
+	else
+		show_result("stvx", "FAIL");
+}
+#else
+static void __init test_lvx_stvx(void)
+{
+	show_result("lvx", "SKIP (CONFIG_ALTIVEC is not set)");
+	show_result("stvx", "SKIP (CONFIG_ALTIVEC is not set)");
+}
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+static void __init test_lxvd2x_stxvd2x(void)
+{
+	struct pt_regs regs;
+	union {
+		vector128 a;
+		u32 b[4];
+	} c;
+	u32 cached_b[4];
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lxvd2x ***/
+
+	cached_b[0] = c.b[0] = 18233;
+	cached_b[1] = c.b[1] = 34863571;
+	cached_b[2] = c.b[2] = 834;
+	cached_b[3] = c.b[3] = 6138911;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lxvd2x vsr39, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LXVD2X(39, 3, 4));
+
+	if (stepped == 1)
+		show_result("lxvd2x", "PASS");
+	else
+		show_result("lxvd2x", "FAIL");
+
+
+	/*** stxvd2x ***/
+
+	c.b[0] = 21379463;
+	c.b[1] = 87;
+	c.b[2] = 374234;
+	c.b[3] = 4;
+
+	/* stxvd2x vsr39, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STXVD2X(39, 3, 4));
+
+	if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+		show_result("stxvd2x", "PASS");
+	else
+		show_result("stxvd2x", "FAIL");
+}
+#else
+static void __init test_lxvd2x_stxvd2x(void)
+{
+	show_result("lxvd2x", "SKIP (CONFIG_VSX is not set)");
+	show_result("stxvd2x", "SKIP (CONFIG_VSX is not set)");
+}
+#endif /* CONFIG_VSX */
+
+static int __init test_emulate_step(void)
+{
+	test_ld();
+	test_lwz();
+	test_lwzx();
+	test_std();
+	test_ldarx_stdcx();
+	test_lfsx_stfsx();
+	test_lfdx_stfdx();
+	test_lvx_stvx();
+	test_lxvd2x_stxvd2x();
+
+	return 0;
+}
+late_initcall(test_emulate_step);

arch/powerpc/mm/init_64.c

@@ -356,18 +356,42 @@ static void early_check_vec5(void)
 	unsigned long root, chosen;
 	int size;
 	const u8 *vec5;
+	u8 mmu_supported;
 
 	root = of_get_flat_dt_root();
 	chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
-	if (chosen == -FDT_ERR_NOTFOUND)
+	if (chosen == -FDT_ERR_NOTFOUND) {
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
 		return;
+	}
 	vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
-	if (!vec5)
+	if (!vec5) {
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
 		return;
-	if (size <= OV5_INDX(OV5_MMU_RADIX_300) ||
-	    !(vec5[OV5_INDX(OV5_MMU_RADIX_300)] & OV5_FEAT(OV5_MMU_RADIX_300)))
-		/* Hypervisor doesn't support radix */
+	}
+	if (size <= OV5_INDX(OV5_MMU_SUPPORT)) {
 		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+		return;
+	}
+
+	/* Check for supported configuration */
+	mmu_supported = vec5[OV5_INDX(OV5_MMU_SUPPORT)] &
+			OV5_FEAT(OV5_MMU_SUPPORT);
+	if (mmu_supported == OV5_FEAT(OV5_MMU_RADIX)) {
+		/* Hypervisor only supports radix - check enabled && GTSE */
+		if (!early_radix_enabled()) {
+			pr_warn("WARNING: Ignoring cmdline option disable_radix\n");
+		}
+		if (!(vec5[OV5_INDX(OV5_RADIX_GTSE)] &
+						OV5_FEAT(OV5_RADIX_GTSE))) {
+			pr_warn("WARNING: Hypervisor doesn't support RADIX with GTSE\n");
+		}
+		/* Do radix anyway - the hypervisor said we had to */
+		cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
+	} else if (mmu_supported == OV5_FEAT(OV5_MMU_HASH)) {
+		/* Hypervisor only supports hash - disable radix */
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+	}
 }
 
 void __init mmu_early_init_devtree(void)
@@ -383,7 +407,7 @@ void __init mmu_early_init_devtree(void)
 	 * even though the ibm,architecture-vec-5 property created by
 	 * skiboot doesn't have the necessary bits set.
 	 */
-	if (early_radix_enabled() && !(mfmsr() & MSR_HV))
+	if (!(mfmsr() & MSR_HV))
 		early_check_vec5();
 
 	if (early_radix_enabled())

arch/powerpc/mm/pgtable-radix.c

@@ -186,6 +186,10 @@ static void __init radix_init_pgtable(void)
 	 */
 	register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12);
 	pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd);
+	asm volatile("ptesync" : : : "memory");
+	asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
+		     "r" (TLBIEL_INVAL_SET_LPID), "r" (0));
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
 
 static void __init radix_init_partition_table(void)

arch/powerpc/perf/core-book3s.c

@@ -188,6 +188,8 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
 			sdsync = POWER7P_MMCRA_SDAR_VALID;
 		else if (ppmu->flags & PPMU_ALT_SIPR)
 			sdsync = POWER6_MMCRA_SDSYNC;
+		else if (ppmu->flags & PPMU_NO_SIAR)
+			sdsync = MMCRA_SAMPLE_ENABLE;
 		else
 			sdsync = MMCRA_SDSYNC;
 

arch/powerpc/perf/isa207-common.c

@@ -65,12 +65,41 @@ static bool is_event_valid(u64 event)
 	return !(event & ~valid_mask);
 }
 
-static u64 mmcra_sdar_mode(u64 event)
+static inline bool is_event_marked(u64 event)
 {
-	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
-		return p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+	if (event & EVENT_IS_MARKED)
+		return true;
+
+	return false;
+}
 
-	return MMCRA_SDAR_MODE_TLB;
+static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
+{
+	/*
+	 * MMCRA[SDAR_MODE] specifices how the SDAR should be updated in
+	 * continous sampling mode.
+	 *
+	 * Incase of Power8:
+	 * MMCRA[SDAR_MODE] will be programmed as "0b01" for continous sampling
+	 * mode and will be un-changed when setting MMCRA[63] (Marked events).
+	 *
+	 * Incase of Power9:
+	 * Marked event: MMCRA[SDAR_MODE] will be set to 0b00 ('No Updates'),
+	 *               or if group already have any marked events.
+	 * Non-Marked events (for DD1):
+	 *	MMCRA[SDAR_MODE] will be set to 0b01
+	 * For rest
+	 *	MMCRA[SDAR_MODE] will be set from event code.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE))
+			*mmcra &= MMCRA_SDAR_MODE_NO_UPDATES;
+		else if (!cpu_has_feature(CPU_FTR_POWER9_DD1))
+			*mmcra |=  p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+		else if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+			*mmcra |= MMCRA_SDAR_MODE_TLB;
+	} else
+		*mmcra |= MMCRA_SDAR_MODE_TLB;
 }
 
 static u64 thresh_cmp_val(u64 value)
@@ -180,7 +209,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
 		value |= CNST_L1_QUAL_VAL(cache);
 	}
 
-	if (event & EVENT_IS_MARKED) {
+	if (is_event_marked(event)) {
 		mask  |= CNST_SAMPLE_MASK;
 		value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
 	}
@@ -276,7 +305,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
 		}
 
 		/* In continuous sampling mode, update SDAR on TLB miss */
-		mmcra |= mmcra_sdar_mode(event[i]);
+		mmcra_sdar_mode(event[i], &mmcra);
 
 		if (event[i] & EVENT_IS_L1) {
 			cache = event[i] >> EVENT_CACHE_SEL_SHIFT;
@@ -285,7 +314,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
 			mmcr1 |= (cache & 1) << MMCR1_DC_QUAL_SHIFT;
 		}
 
-		if (event[i] & EVENT_IS_MARKED) {
+		if (is_event_marked(event[i])) {
 			mmcra |= MMCRA_SAMPLE_ENABLE;
 
 			val = (event[i] >> EVENT_SAMPLE_SHIFT) & EVENT_SAMPLE_MASK;

arch/powerpc/perf/isa207-common.h

@@ -246,6 +246,7 @@
 #define MMCRA_THR_CMP_SHIFT		32
 #define MMCRA_SDAR_MODE_SHIFT		42
 #define MMCRA_SDAR_MODE_TLB		(1ull << MMCRA_SDAR_MODE_SHIFT)
+#define MMCRA_SDAR_MODE_NO_UPDATES	~(0x3ull << MMCRA_SDAR_MODE_SHIFT)
 #define MMCRA_IFM_SHIFT			30
 
 /* MMCR1 Threshold Compare bit constant for power9 */

arch/powerpc/platforms/powernv/opal-wrappers.S

@@ -39,8 +39,8 @@ opal_tracepoint_refcount:
 BEGIN_FTR_SECTION;						\
 	b	1f;						\
 END_FTR_SECTION(0, 1);						\
-	ld	r12,opal_tracepoint_refcount@toc(r2);		\
-	cmpdi	r12,0;						\
+	ld	r11,opal_tracepoint_refcount@toc(r2);		\
+	cmpdi	r11,0;						\
 	bne-	LABEL;						\
 1:
 

arch/powerpc/platforms/powernv/opal.c

@@ -395,7 +395,6 @@ static int opal_recover_mce(struct pt_regs *regs,
 					struct machine_check_event *evt)
 {
 	int recovered = 0;
-	uint64_t ea = get_mce_fault_addr(evt);
 
 	if (!(regs->msr & MSR_RI)) {
 		/* If MSR_RI isn't set, we cannot recover */
@@ -404,26 +403,18 @@ static int opal_recover_mce(struct pt_regs *regs,
 	} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
 		/* Platform corrected itself */
 		recovered = 1;
-	} else if (ea && !is_kernel_addr(ea)) {
+	} else if (evt->severity == MCE_SEV_FATAL) {
+		/* Fatal machine check */
+		pr_err("Machine check interrupt is fatal\n");
+		recovered = 0;
+	} else if ((evt->severity == MCE_SEV_ERROR_SYNC) &&
+			(user_mode(regs) && !is_global_init(current))) {
 		/*
-		 * Faulting address is not in kernel text. We should be fine.
-		 * We need to find which process uses this address.
 		 * For now, kill the task if we have received exception when
 		 * in userspace.
 		 *
 		 * TODO: Queue up this address for hwpoisioning later.
 		 */
-		if (user_mode(regs) && !is_global_init(current)) {
-			_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
-			recovered = 1;
-		} else
-			recovered = 0;
-	} else if (user_mode(regs) && !is_global_init(current) &&
-		evt->severity == MCE_SEV_ERROR_SYNC) {
-		/*
-		 * If we have received a synchronous error when in userspace
-		 * kill the task.
-		 */
 		_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
 		recovered = 1;
 	}

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -1775,17 +1775,20 @@ static u64 pnv_pci_ioda_dma_get_required_mask(struct pci_dev *pdev)
 }
 
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
-				   struct pci_bus *bus)
+				   struct pci_bus *bus,
+				   bool add_to_group)
 {
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
 		set_dma_offset(&dev->dev, pe->tce_bypass_base);
-		iommu_add_device(&dev->dev);
+		if (add_to_group)
+			iommu_add_device(&dev->dev);
 
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
-			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
+					add_to_group);
 	}
 }
 
@@ -2191,7 +2194,7 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
 		set_iommu_table_base(&pe->pdev->dev, tbl);
 		iommu_add_device(&pe->pdev->dev);
 	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
-		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
 
 	return;
  fail:
@@ -2426,6 +2429,8 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 
 	pnv_pci_ioda2_set_bypass(pe, false);
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
+	if (pe->pbus)
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
 	pnv_ioda2_table_free(tbl);
 }
 
@@ -2435,6 +2440,8 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
 						table_group);
 
 	pnv_pci_ioda2_setup_default_config(pe);
+	if (pe->pbus)
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
 }
 
 static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
@@ -2624,6 +2631,9 @@ static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
 	level_shift = entries_shift + 3;
 	level_shift = max_t(unsigned, level_shift, PAGE_SHIFT);
 
+	if ((level_shift - 3) * levels + page_shift >= 60)
+		return -EINVAL;
+
 	/* Allocate TCE table */
 	addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
 			levels, tce_table_size, &offset, &total_allocated);
@@ -2728,7 +2738,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	if (pe->flags & PNV_IODA_PE_DEV)
 		iommu_add_device(&pe->pdev->dev);
 	else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
-		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
 }
 
 #ifdef CONFIG_PCI_MSI

arch/powerpc/purgatory/trampoline.S

@@ -116,13 +116,13 @@ dt_offset:
 
 	.data
 	.balign 8
-.globl sha256_digest
-sha256_digest:
+.globl purgatory_sha256_digest
+purgatory_sha256_digest:
 	.skip	32
-	.size sha256_digest, . - sha256_digest
+	.size purgatory_sha256_digest, . - purgatory_sha256_digest
 
 	.balign 8
-.globl sha_regions
-sha_regions:
+.globl purgatory_sha_regions
+purgatory_sha_regions:
 	.skip	8 * 2 * 16
-	.size sha_regions, . - sha_regions
+	.size purgatory_sha_regions, . - purgatory_sha_regions

arch/powerpc/sysdev/axonram.c

@@ -274,7 +274,9 @@ static int axon_ram_probe(struct platform_device *device)
 			if (bank->disk->major > 0)
 				unregister_blkdev(bank->disk->major,
 						bank->disk->disk_name);
-			del_gendisk(bank->disk);
+			if (bank->disk->flags & GENHD_FL_UP)
+				del_gendisk(bank->disk);
+			put_disk(bank->disk);
 		}
 		device->dev.platform_data = NULL;
 		if (bank->io_addr != 0)
@@ -299,6 +301,7 @@ axon_ram_remove(struct platform_device *device)
 	device_remove_file(&device->dev, &dev_attr_ecc);
 	free_irq(bank->irq_id, device);
 	del_gendisk(bank->disk);
+	put_disk(bank->disk);
 	iounmap((void __iomem *) bank->io_addr);
 	kfree(bank);
 

arch/powerpc/sysdev/xics/icp-opal.c

@@ -91,6 +91,16 @@ static unsigned int icp_opal_get_irq(void)
 
 static void icp_opal_set_cpu_priority(unsigned char cppr)
 {
+	/*
+	 * Here be dragons. The caller has asked to allow only IPI's and not
+	 * external interrupts. But OPAL XIVE doesn't support that. So instead
+	 * of allowing no interrupts allow all. That's still not right, but
+	 * currently the only caller who does this is xics_migrate_irqs_away()
+	 * and it works in that case.
+	 */
+	if (cppr >= DEFAULT_PRIORITY)
+		cppr = LOWEST_PRIORITY;
+
 	xics_set_base_cppr(cppr);
 	opal_int_set_cppr(cppr);
 	iosync();

arch/powerpc/sysdev/xics/xics-common.c

@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/delay.h>
 
 #include <asm/prom.h>
 #include <asm/io.h>
@@ -198,9 +199,6 @@ void xics_migrate_irqs_away(void)
 	/* Remove ourselves from the global interrupt queue */
 	xics_set_cpu_giq(xics_default_distrib_server, 0);
 
-	/* Allow IPIs again... */
-	icp_ops->set_priority(DEFAULT_PRIORITY);
-
 	for_each_irq_desc(virq, desc) {
 		struct irq_chip *chip;
 		long server;
@@ -255,6 +253,19 @@ void xics_migrate_irqs_away(void)
 unlock:
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
+
+	/* Allow "sufficient" time to drop any inflight IRQ's */
+	mdelay(5);
+
+	/*
+	 * Allow IPIs again. This is done at the very end, after migrating all
+	 * interrupts, the expectation is that we'll only get woken up by an IPI
+	 * interrupt beyond this point, but leave externals masked just to be
+	 * safe. If we're using icp-opal this may actually allow all
+	 * interrupts anyway, but that should be OK.
+	 */
+	icp_ops->set_priority(DEFAULT_PRIORITY);
+
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 

arch/s390/configs/default_defconfig

@@ -609,7 +609,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y

arch/s390/configs/gcov_defconfig

@@ -560,7 +560,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y

arch/s390/configs/performance_defconfig

@@ -558,7 +558,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y