Merge branch 'linus' into locking/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/ABI/testing/sysfs-devices-system-ibm-rtl

@@ -1,4 +1,4 @@
-What:           state
+What:           /sys/devices/system/ibm_rtl/state
 Date:           Sep 2010
 KernelVersion:  2.6.37
 Contact:        Vernon Mauery <vernux@us.ibm.com>
@@ -10,7 +10,7 @@ Description:    The state file allows a means by which to change in and
 Users:          The ibm-prtm userspace daemon uses this interface.
 
 
-What:           version
+What:           /sys/devices/system/ibm_rtl/version
 Date:           Sep 2010
 KernelVersion:  2.6.37
 Contact:        Vernon Mauery <vernux@us.ibm.com>

Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt → Documentation/devicetree/bindings/ipmi/aspeed,ast2400-ibt-bmc.txt

@@ -6,7 +6,7 @@ perform in-band IPMI communication with their host.
 
 Required properties:
 
-- compatible : should be "aspeed,ast2400-bt-bmc"
+- compatible : should be "aspeed,ast2400-ibt-bmc"
 - reg: physical address and size of the registers
 
 Optional properties:
@@ -17,7 +17,7 @@ Optional properties:
 Example:
 
 	ibt@1e789140 {
-		compatible = "aspeed,ast2400-bt-bmc";
+		compatible = "aspeed,ast2400-ibt-bmc";
 		reg = <0x1e789140 0x18>;
 		interrupts = <8>;
 	};

Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt

@@ -43,6 +43,9 @@ Optional properties:
   reset signal present internally in some host controller IC designs.
   See Documentation/devicetree/bindings/reset/reset.txt for details.
 
+* reset-names: request name for using "resets" property. Must be "reset".
+	(It will be used together with "resets" property.)
+
 * clocks: from common clock binding: handle to biu and ciu clocks for the
   bus interface unit clock and the card interface unit clock.
 
@@ -103,6 +106,8 @@ board specific portions as listed below.
 		interrupts = <0 75 0>;
 		#address-cells = <1>;
 		#size-cells = <0>;
+		resets = <&rst 20>;
+		reset-names = "reset";
 	};
 
 [board specific internal DMA resources]

Documentation/devicetree/bindings/pci/rockchip-pcie.txt

@@ -26,13 +26,16 @@ Required properties:
 	- "sys"
 	- "legacy"
 	- "client"
-- resets: Must contain five entries for each entry in reset-names.
+- resets: Must contain seven entries for each entry in reset-names.
 	   See ../reset/reset.txt for details.
 - reset-names: Must include the following names
 	- "core"
 	- "mgmt"
 	- "mgmt-sticky"
 	- "pipe"
+	- "pm"
+	- "aclk"
+	- "pclk"
 - pinctrl-names : The pin control state names
 - pinctrl-0: The "default" pinctrl state
 - #interrupt-cells: specifies the number of cells needed to encode an
@@ -86,8 +89,10 @@ pcie0: pcie@f8000000 {
 	reg = <0x0 0xf8000000 0x0 0x2000000>, <0x0 0xfd000000 0x0 0x1000000>;
 	reg-names = "axi-base", "apb-base";
 	resets = <&cru SRST_PCIE_CORE>, <&cru SRST_PCIE_MGMT>,
-		 <&cru SRST_PCIE_MGMT_STICKY>, <&cru SRST_PCIE_PIPE>;
-	reset-names = "core", "mgmt", "mgmt-sticky", "pipe";
+		 <&cru SRST_PCIE_MGMT_STICKY>, <&cru SRST_PCIE_PIPE> ,
+		 <&cru SRST_PCIE_PM>, <&cru SRST_P_PCIE>, <&cru SRST_A_PCIE>;
+	reset-names = "core", "mgmt", "mgmt-sticky", "pipe",
+		      "pm", "pclk", "aclk";
 	phys = <&pcie_phy>;
 	phy-names = "pcie-phy";
 	pinctrl-names = "default";

Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt

@@ -14,11 +14,6 @@ Required properies:
  - #size-cells	: The value of this property must be 1
  - ranges	: defines mapping between pin controller node (parent) to
    gpio-bank node (children).
- - interrupt-parent: phandle of the interrupt parent to which the external
-   GPIO interrupts are forwarded to.
- - st,syscfg: Should be phandle/offset pair. The phandle to the syscon node
-   which includes IRQ mux selection register, and the offset of the IRQ mux
-   selection register.
  - pins-are-numbered: Specify the subnodes are using numbered pinmux to
    specify pins.
 
@@ -37,6 +32,11 @@ Required properties:
 
 Optional properties:
  - reset:	  : Reference to the reset controller
+ - interrupt-parent: phandle of the interrupt parent to which the external
+   GPIO interrupts are forwarded to.
+ - st,syscfg: Should be phandle/offset pair. The phandle to the syscon node
+   which includes IRQ mux selection register, and the offset of the IRQ mux
+   selection register.
 
 Example:
 #include <dt-bindings/pinctrl/stm32f429-pinfunc.h>

Documentation/devicetree/bindings/sound/omap-abe-twl6040.txt

@@ -12,7 +12,7 @@ Required properties:
 
 Optional properties:
 - ti,dmic: phandle for the OMAP dmic node if the machine have it connected
-- ti,jack_detection: Need to be present if the board capable to detect jack
+- ti,jack-detection: Need to be present if the board capable to detect jack
   insertion, removal.
 
 Available audio endpoints for the audio-routing table:

Documentation/filesystems/Locking

@@ -447,7 +447,6 @@ prototypes:
 	int (*flush) (struct file *);
 	int (*release) (struct inode *, struct file *);
 	int (*fsync) (struct file *, loff_t start, loff_t end, int datasync);
-	int (*aio_fsync) (struct kiocb *, int datasync);
 	int (*fasync) (int, struct file *, int);
 	int (*lock) (struct file *, int, struct file_lock *);
 	ssize_t (*readv) (struct file *, const struct iovec *, unsigned long,

Documentation/filesystems/vfs.txt

@@ -828,7 +828,6 @@ struct file_operations {
 	int (*flush) (struct file *, fl_owner_t id);
 	int (*release) (struct inode *, struct file *);
 	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
-	int (*aio_fsync) (struct kiocb *, int datasync);
 	int (*fasync) (int, struct file *, int);
 	int (*lock) (struct file *, int, struct file_lock *);
 	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);

Documentation/i2c/i2c-topology

@@ -326,7 +326,7 @@ Two parent-locked sibling muxes
 
 This is a good topology.
 
-                                   .--------.
+                                    .--------.
                    .----------.  .--| dev D1 |
                    |  parent- |--'  '--------'
                 .--|  locked  |     .--------.
@@ -350,7 +350,7 @@ Mux-locked and parent-locked sibling muxes
 
 This is a good topology.
 
-                                   .--------.
+                                    .--------.
                    .----------.  .--| dev D1 |
                    |   mux-   |--'  '--------'
                 .--|  locked  |     .--------.

Documentation/networking/dsa/dsa.txt

@@ -67,13 +67,14 @@ Note that DSA does not currently create network interfaces for the "cpu" and
 Switch tagging protocols
 ------------------------
 
-DSA currently supports 4 different tagging protocols, and a tag-less mode as
+DSA currently supports 5 different tagging protocols, and a tag-less mode as
 well. The different protocols are implemented in:
 
 net/dsa/tag_trailer.c: Marvell's 4 trailer tag mode (legacy)
 net/dsa/tag_dsa.c: Marvell's original DSA tag
 net/dsa/tag_edsa.c: Marvell's enhanced DSA tag
 net/dsa/tag_brcm.c: Broadcom's 4 bytes tag
+net/dsa/tag_qca.c: Qualcomm's 2 bytes tag
 
 The exact format of the tag protocol is vendor specific, but in general, they
 all contain something which:

Documentation/virtual/kvm/api.txt

@@ -777,6 +777,17 @@ Gets the current timestamp of kvmclock as seen by the current guest. In
 conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
 such as migration.
 
+When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the
+set of bits that KVM can return in struct kvm_clock_data's flag member.
+
+The only flag defined now is KVM_CLOCK_TSC_STABLE.  If set, the returned
+value is the exact kvmclock value seen by all VCPUs at the instant
+when KVM_GET_CLOCK was called.  If clear, the returned value is simply
+CLOCK_MONOTONIC plus a constant offset; the offset can be modified
+with KVM_SET_CLOCK.  KVM will try to make all VCPUs follow this clock,
+but the exact value read by each VCPU could differ, because the host
+TSC is not stable.
+
 struct kvm_clock_data {
 	__u64 clock;  /* kvmclock current value */
 	__u32 flags;

MAINTAINERS

@@ -7084,6 +7084,7 @@ F:	drivers/scsi/53c700*
 LED SUBSYSTEM
 M:	Richard Purdie <rpurdie@rpsys.net>
 M:	Jacek Anaszewski <j.anaszewski@samsung.com>
+M:	Pavel Machek <pavel@ucw.cz>
 L:	linux-leds@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git
 S:	Maintained
@@ -8057,6 +8058,7 @@ F:	drivers/infiniband/hw/mlx4/
 F:	include/linux/mlx4/
 
 MELLANOX MLX5 core VPI driver
+M:	Saeed Mahameed <saeedm@mellanox.com>
 M:	Matan Barak <matanb@mellanox.com>
 M:	Leon Romanovsky <leonro@mellanox.com>
 L:	netdev@vger.kernel.org
@@ -9335,7 +9337,7 @@ PCI DRIVER FOR INTEL VOLUME MANAGEMENT DEVICE (VMD)
 M:	Keith Busch <keith.busch@intel.com>
 L:	linux-pci@vger.kernel.org
 S:	Supported
-F:	arch/x86/pci/vmd.c
+F:	drivers/pci/host/vmd.c
 
 PCIE DRIVER FOR ST SPEAR13XX
 M:	Pratyush Anand <pratyush.anand@gmail.com>

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc6
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*
@@ -370,7 +370,7 @@ LDFLAGS_MODULE  =
 CFLAGS_KERNEL	=
 AFLAGS_KERNEL	=
 LDFLAGS_vmlinux =
-CFLAGS_GCOV	= -fprofile-arcs -ftest-coverage -fno-tree-loop-im
+CFLAGS_GCOV	= -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized
 CFLAGS_KCOV	:= $(call cc-option,-fsanitize-coverage=trace-pc,)
 
 
@@ -399,11 +399,12 @@ KBUILD_CFLAGS   := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		   -fno-strict-aliasing -fno-common \
 		   -Werror-implicit-function-declaration \
 		   -Wno-format-security \
-		   -std=gnu89
+		   -std=gnu89 $(call cc-option,-fno-PIE)
+
 
 KBUILD_AFLAGS_KERNEL :=
 KBUILD_CFLAGS_KERNEL :=
-KBUILD_AFLAGS   := -D__ASSEMBLY__
+KBUILD_AFLAGS   := -D__ASSEMBLY__ $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS_MODULE  := -DMODULE
 KBUILD_CFLAGS_MODULE  := -DMODULE
 KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds
@@ -620,7 +621,6 @@ ARCH_CFLAGS :=
 include arch/$(SRCARCH)/Makefile
 
 KBUILD_CFLAGS	+= $(call cc-option,-fno-delete-null-pointer-checks,)
-KBUILD_CFLAGS	+= $(call cc-disable-warning,maybe-uninitialized,)
 KBUILD_CFLAGS	+= $(call cc-disable-warning,frame-address,)
 
 ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
@@ -629,15 +629,18 @@ KBUILD_CFLAGS	+= $(call cc-option,-fdata-sections,)
 endif
 
 ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
-KBUILD_CFLAGS	+= -Os
+KBUILD_CFLAGS	+= -Os $(call cc-disable-warning,maybe-uninitialized,)
 else
 ifdef CONFIG_PROFILE_ALL_BRANCHES
-KBUILD_CFLAGS	+= -O2
+KBUILD_CFLAGS	+= -O2 $(call cc-disable-warning,maybe-uninitialized,)
 else
 KBUILD_CFLAGS   += -O2
 endif
 endif
 
+KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0409, \
+			$(call cc-disable-warning,maybe-uninitialized,))
+
 # Tell gcc to never replace conditional load with a non-conditional one
 KBUILD_CFLAGS	+= $(call cc-option,--param=allow-store-data-races=0)
 

arch/arc/Makefile

@@ -50,6 +50,9 @@ atleast_gcc44 :=  $(call cc-ifversion, -ge, 0404, y)
 
 cflags-$(atleast_gcc44)			+= -fsection-anchors
 
+cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
+cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
+
 ifdef CONFIG_ISA_ARCV2
 
 ifndef CONFIG_ARC_HAS_LL64
@@ -68,7 +71,9 @@ cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables $(cfi)
 ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
 # Generic build system uses -O2, we want -O3
 # Note: No need to add to cflags-y as that happens anyways
-ARCH_CFLAGS += -O3
+#
+# Disable the false maybe-uninitialized warings gcc spits out at -O3
+ARCH_CFLAGS += -O3 $(call cc-disable-warning,maybe-uninitialized,)
 endif
 
 # small data is default for elf32 tool-chain. If not usable, disable it

arch/arc/boot/dts/axc001.dtsi

@@ -71,7 +71,7 @@
 			reg-io-width = <4>;
 		};
 
-		arcpmu0: pmu {
+		arcpct0: pct {
 			compatible = "snps,arc700-pct";
 		};
 	};

arch/arc/boot/dts/nsim_700.dts

@@ -69,7 +69,7 @@
 			};
 		};
 
-		arcpmu0: pmu {
+		arcpct0: pct {
 			compatible = "snps,arc700-pct";
 		};
 	};

arch/arc/boot/dts/nsimosci.dts

@@ -83,5 +83,9 @@
 			reg = <0xf0003000 0x44>;
 			interrupts = <7>;
 		};
+
+		arcpct0: pct {
+			compatible = "snps,arc700-pct";
+		};
 	};
 };

arch/arc/configs/nsim_700_defconfig

@@ -14,6 +14,7 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_KPROBES=y

arch/arc/configs/nsim_hs_defconfig

@@ -14,6 +14,7 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_KPROBES=y

arch/arc/configs/nsim_hs_smp_defconfig

@@ -12,6 +12,7 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_KPROBES=y

arch/arc/configs/nsimosci_defconfig

@@ -14,6 +14,7 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_KPROBES=y

arch/arc/configs/nsimosci_hs_defconfig

@@ -14,6 +14,7 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_KPROBES=y

arch/arc/configs/nsimosci_hs_smp_defconfig

@@ -10,6 +10,7 @@ CONFIG_IKCONFIG_PROC=y
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
+CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
@@ -34,7 +35,6 @@ CONFIG_INET=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
@@ -72,7 +72,6 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HWMON is not set
 CONFIG_DRM=y
 CONFIG_DRM_ARCPGU=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set

arch/arc/include/asm/arcregs.h

@@ -43,12 +43,14 @@
 #define STATUS_AE_BIT		5	/* Exception active */
 #define STATUS_DE_BIT		6	/* PC is in delay slot */
 #define STATUS_U_BIT		7	/* User/Kernel mode */
+#define STATUS_Z_BIT            11
 #define STATUS_L_BIT		12	/* Loop inhibit */
 
 /* These masks correspond to the status word(STATUS_32) bits */
 #define STATUS_AE_MASK		(1<<STATUS_AE_BIT)
 #define STATUS_DE_MASK		(1<<STATUS_DE_BIT)
 #define STATUS_U_MASK		(1<<STATUS_U_BIT)
+#define STATUS_Z_MASK		(1<<STATUS_Z_BIT)
 #define STATUS_L_MASK		(1<<STATUS_L_BIT)
 
 /*

arch/arc/include/asm/smp.h

@@ -37,9 +37,9 @@ extern const char *arc_platform_smp_cpuinfo(void);
  * API expected BY platform smp code (FROM arch smp code)
  *
  * smp_ipi_irq_setup:
- *	Takes @cpu and @irq to which the arch-common ISR is hooked up
+ *	Takes @cpu and @hwirq to which the arch-common ISR is hooked up
  */
-extern int smp_ipi_irq_setup(int cpu, int irq);
+extern int smp_ipi_irq_setup(int cpu, irq_hw_number_t hwirq);
 
 /*
  * struct plat_smp_ops	- SMP callbacks provided by platform to ARC SMP

arch/arc/kernel/devtree.c

@@ -31,6 +31,8 @@ static void __init arc_set_early_base_baud(unsigned long dt_root)
 		arc_base_baud = 166666666;	/* Fixed 166.6MHz clk (TB10x) */
 	else if (of_flat_dt_is_compatible(dt_root, "snps,arc-sdp"))
 		arc_base_baud = 33333333;	/* Fixed 33MHz clk (AXS10x) */
+	else if (of_flat_dt_is_compatible(dt_root, "ezchip,arc-nps"))
+		arc_base_baud = 800000000;      /* Fixed 800MHz clk (NPS) */
 	else
 		arc_base_baud = 50000000;	/* Fixed default 50MHz */
 }

arch/arc/kernel/mcip.c

@@ -181,6 +181,8 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
 {
 	unsigned long flags;
 	cpumask_t online;
+	unsigned int destination_bits;
+	unsigned int distribution_mode;
 
 	/* errout if no online cpu per @cpumask */
 	if (!cpumask_and(&online, cpumask, cpu_online_mask))
@@ -188,8 +190,15 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
 
 	raw_spin_lock_irqsave(&mcip_lock, flags);
 
-	idu_set_dest(data->hwirq, cpumask_bits(&online)[0]);
-	idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR);
+	destination_bits = cpumask_bits(&online)[0];
+	idu_set_dest(data->hwirq, destination_bits);
+
+	if (ffs(destination_bits) == fls(destination_bits))
+		distribution_mode = IDU_M_DISTRI_DEST;
+	else
+		distribution_mode = IDU_M_DISTRI_RR;
+
+	idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, distribution_mode);
 
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
 
@@ -207,16 +216,15 @@ static struct irq_chip idu_irq_chip = {
 
 };
 
-static int idu_first_irq;
+static irq_hw_number_t idu_first_hwirq;
 
 static void idu_cascade_isr(struct irq_desc *desc)
 {
-	struct irq_domain *domain = irq_desc_get_handler_data(desc);
-	unsigned int core_irq = irq_desc_get_irq(desc);
-	unsigned int idu_irq;
+	struct irq_domain *idu_domain = irq_desc_get_handler_data(desc);
+	irq_hw_number_t core_hwirq = irqd_to_hwirq(irq_desc_get_irq_data(desc));
+	irq_hw_number_t idu_hwirq = core_hwirq - idu_first_hwirq;
 
-	idu_irq = core_irq - idu_first_irq;
-	generic_handle_irq(irq_find_mapping(domain, idu_irq));
+	generic_handle_irq(irq_find_mapping(idu_domain, idu_hwirq));
 }
 
 static int idu_irq_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq)
@@ -282,7 +290,7 @@ idu_of_init(struct device_node *intc, struct device_node *parent)
 	struct irq_domain *domain;
 	/* Read IDU BCR to confirm nr_irqs */
 	int nr_irqs = of_irq_count(intc);
-	int i, irq;
+	int i, virq;
 	struct mcip_bcr mp;
 
 	READ_BCR(ARC_REG_MCIP_BCR, mp);
@@ -303,11 +311,11 @@ idu_of_init(struct device_node *intc, struct device_node *parent)
 		 * however we need it to get the parent virq and set IDU handler
 		 * as first level isr
 		 */
-		irq = irq_of_parse_and_map(intc, i);
+		virq = irq_of_parse_and_map(intc, i);
 		if (!i)
-			idu_first_irq = irq;
+			idu_first_hwirq = irqd_to_hwirq(irq_get_irq_data(virq));
 
-		irq_set_chained_handler_and_data(irq, idu_cascade_isr, domain);
+		irq_set_chained_handler_and_data(virq, idu_cascade_isr, domain);
 	}
 
 	__mcip_cmd(CMD_IDU_ENABLE, 0);

arch/arc/kernel/process.c

@@ -43,8 +43,8 @@ SYSCALL_DEFINE0(arc_gettls)
 
 SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
 {
-	int uval;
-	int ret;
+	struct pt_regs *regs = current_pt_regs();
+	int uval = -EFAULT;
 
 	/*
 	 * This is only for old cores lacking LLOCK/SCOND, which by defintion
@@ -54,24 +54,26 @@ SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
 	 */
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_SMP));
 
+	/* Z indicates to userspace if operation succeded */
+	regs->status32 &= ~STATUS_Z_MASK;
+
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
 	preempt_disable();
 
-	ret = __get_user(uval, uaddr);
-	if (ret)
+	if (__get_user(uval, uaddr))
 		goto done;
 
-	if (uval != expected)
-		ret = -EAGAIN;
-	else
-		ret = __put_user(new, uaddr);
+	if (uval == expected) {
+		if (!__put_user(new, uaddr))
+			regs->status32 |= STATUS_Z_MASK;
+	}
 
 done:
 	preempt_enable();
 
-	return ret;
+	return uval;
 }
 
 void arch_cpu_idle(void)

arch/arc/kernel/smp.c

@@ -22,6 +22,7 @@
 #include <linux/atomic.h>
 #include <linux/cpumask.h>
 #include <linux/reboot.h>
+#include <linux/irqdomain.h>
 #include <asm/processor.h>
 #include <asm/setup.h>
 #include <asm/mach_desc.h>
@@ -67,11 +68,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	int i;
 
 	/*
-	 * Initialise the present map, which describes the set of CPUs
-	 * actually populated at the present time.
+	 * if platform didn't set the present map already, do it now
+	 * boot cpu is set to present already by init/main.c
 	 */
-	for (i = 0; i < max_cpus; i++)
-		set_cpu_present(i, true);
+	if (num_present_cpus() <= 1) {
+		for (i = 0; i < max_cpus; i++)
+			set_cpu_present(i, true);
+	}
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
@@ -351,20 +354,24 @@ irqreturn_t do_IPI(int irq, void *dev_id)
  */
 static DEFINE_PER_CPU(int, ipi_dev);
 
-int smp_ipi_irq_setup(int cpu, int irq)
+int smp_ipi_irq_setup(int cpu, irq_hw_number_t hwirq)
 {
 	int *dev = per_cpu_ptr(&ipi_dev, cpu);
+	unsigned int virq = irq_find_mapping(NULL, hwirq);
+
+	if (!virq)
+		panic("Cannot find virq for root domain and hwirq=%lu", hwirq);
 
 	/* Boot cpu calls request, all call enable */
 	if (!cpu) {
 		int rc;
 
-		rc = request_percpu_irq(irq, do_IPI, "IPI Interrupt", dev);
+		rc = request_percpu_irq(virq, do_IPI, "IPI Interrupt", dev);
 		if (rc)
-			panic("Percpu IRQ request failed for %d\n", irq);
+			panic("Percpu IRQ request failed for %u\n", virq);
 	}
 
-	enable_percpu_irq(irq, 0);
+	enable_percpu_irq(virq, 0);
 
 	return 0;
 }

arch/arc/kernel/time.c

@@ -152,14 +152,17 @@ static cycle_t arc_read_rtc(struct clocksource *cs)
 		cycle_t  full;
 	} stamp;
 
-
-	__asm__ __volatile(
-	"1:						\n"
-	"	lr		%0, [AUX_RTC_LOW]	\n"
-	"	lr		%1, [AUX_RTC_HIGH]	\n"
-	"	lr		%2, [AUX_RTC_CTRL]	\n"
-	"	bbit0.nt	%2, 31, 1b		\n"
-	: "=r" (stamp.low), "=r" (stamp.high), "=r" (status));
+	/*
+	 * hardware has an internal state machine which tracks readout of
+	 * low/high and updates the CTRL.status if
+	 *  - interrupt/exception taken between the two reads
+	 *  - high increments after low has been read
+	 */
+	do {
+		stamp.low = read_aux_reg(AUX_RTC_LOW);
+		stamp.high = read_aux_reg(AUX_RTC_HIGH);
+		status = read_aux_reg(AUX_RTC_CTRL);
+	} while (!(status & _BITUL(31)));
 
 	return stamp.full;
 }

arch/arc/mm/dma.c

@@ -105,6 +105,31 @@ static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
 	__free_pages(page, get_order(size));
 }
 
+static int arc_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+			void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			unsigned long attrs)
+{
+	unsigned long user_count = vma_pages(vma);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long pfn = __phys_to_pfn(plat_dma_to_phys(dev, dma_addr));
+	unsigned long off = vma->vm_pgoff;
+	int ret = -ENXIO;
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off < count && user_count <= (count - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      user_count << PAGE_SHIFT,
+				      vma->vm_page_prot);
+	}
+
+	return ret;
+}
+
 /*
  * streaming DMA Mapping API...
  * CPU accesses page via normal paddr, thus needs to explicitly made
@@ -193,6 +218,7 @@ static int arc_dma_supported(struct device *dev, u64 dma_mask)
 struct dma_map_ops arc_dma_ops = {
 	.alloc			= arc_dma_alloc,
 	.free			= arc_dma_free,
+	.mmap			= arc_dma_mmap,
 	.map_page		= arc_dma_map_page,
 	.map_sg			= arc_dma_map_sg,
 	.sync_single_for_device	= arc_dma_sync_single_for_device,

arch/arc/plat-eznps/smp.c

@@ -140,16 +140,10 @@ static void eznps_init_per_cpu(int cpu)
 	mtm_enable_core(cpu);
 }
 
-static void eznps_ipi_clear(int irq)
-{
-	write_aux_reg(CTOP_AUX_IACK, 1 << irq);
-}
-
 struct plat_smp_ops plat_smp_ops = {
 	.info		= smp_cpuinfo_buf,
 	.init_early_smp	= eznps_init_cpumasks,
 	.cpu_kick	= eznps_smp_wakeup_cpu,
 	.ipi_send	= eznps_ipi_send,
 	.init_per_cpu	= eznps_init_per_cpu,
-	.ipi_clear	= eznps_ipi_clear,
 };

arch/arm/boot/dts/imx53-qsb.dts

@@ -64,8 +64,8 @@
 			};
 
 			ldo3_reg: ldo3 {
-				regulator-min-microvolt = <600000>;
-				regulator-max-microvolt = <1800000>;
+				regulator-min-microvolt = <1725000>;
+				regulator-max-microvolt = <3300000>;
 				regulator-always-on;
 			};
 
@@ -76,8 +76,8 @@
 			};
 
 			ldo5_reg: ldo5 {
-				regulator-min-microvolt = <1725000>;
-				regulator-max-microvolt = <3300000>;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3600000>;
 				regulator-always-on;
 			};
 
@@ -100,14 +100,14 @@
 			};
 
 			ldo9_reg: ldo9 {
-				regulator-min-microvolt = <1200000>;
+				regulator-min-microvolt = <1250000>;
 				regulator-max-microvolt = <3600000>;
 				regulator-always-on;
 			};
 
 			ldo10_reg: ldo10 {
-				regulator-min-microvolt = <1250000>;
-				regulator-max-microvolt = <3650000>;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3600000>;
 				regulator-always-on;
 			};
 		};

arch/arm/boot/dts/logicpd-som-lv.dtsi

@@ -13,6 +13,11 @@
 		};
 	};
 
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0>;
+	};
+
 	wl12xx_vmmc: wl12xx_vmmc {
 		compatible = "regulator-fixed";
 		regulator-name = "vwl1271";

arch/arm/boot/dts/logicpd-torpedo-som.dtsi

@@ -13,9 +13,9 @@
 		};
 	};
 
-	memory@0 {
+	memory@80000000 {
 		device_type = "memory";
-		reg = <0 0>;
+		reg = <0x80000000 0>;
 	};
 
 	leds {

arch/arm/boot/dts/omap5-board-common.dtsi

@@ -124,6 +124,7 @@
 		compatible = "ti,abe-twl6040";
 		ti,model = "omap5-uevm";
 
+		ti,jack-detection;
 		ti,mclk-freq = <19200000>;
 
 		ti,mcpdm = <&mcpdm>;
@@ -415,7 +416,7 @@
 			ti,backup-battery-charge-high-current;
 		};
 
-		gpadc {
+		gpadc: gpadc {
 			compatible = "ti,palmas-gpadc";
 			interrupts = <18 0
 				      16 0
@@ -475,8 +476,8 @@
 				smps6_reg: smps6 {
 					/* VDD_DDR3 - over VDD_SMPS6 */
 					regulator-name = "smps6";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <1200000>;
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
 					regulator-always-on;
 					regulator-boot-on;
 				};

arch/arm/boot/dts/stih410-b2260.dts

@@ -74,7 +74,7 @@
 		/* Low speed expansion connector */
 		spi0: spi@9844000 {
 			label = "LS-SPI0";
-			cs-gpio = <&pio30 3 0>;
+			cs-gpios = <&pio30 3 0>;
 			status = "okay";
 		};
 

arch/arm/boot/dts/sun8i-a23-a33.dtsi

@@ -282,11 +282,15 @@
 			uart1_pins_a: uart1@0 {
 				allwinner,pins = "PG6", "PG7";
 				allwinner,function = "uart1";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
 			uart1_pins_cts_rts_a: uart1-cts-rts@0 {
 				allwinner,pins = "PG8", "PG9";
 				allwinner,function = "uart1";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
 			mmc0_pins_a: mmc0@0 {

arch/arm/include/asm/kvm_asm.h

@@ -66,6 +66,7 @@ extern char __kvm_hyp_vector[];
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
+extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 

arch/arm/include/asm/kvm_host.h

@@ -57,6 +57,9 @@ struct kvm_arch {
 	/* VTTBR value associated with below pgd and vmid */
 	u64    vttbr;
 
+	/* The last vcpu id that ran on each physical CPU */
+	int __percpu *last_vcpu_ran;
+
 	/* Timer */
 	struct arch_timer_kvm	timer;
 

arch/arm/include/asm/kvm_hyp.h

@@ -71,6 +71,7 @@
 #define ICIALLUIS	__ACCESS_CP15(c7, 0, c1, 0)
 #define ATS1CPR		__ACCESS_CP15(c7, 0, c8, 0)
 #define TLBIALLIS	__ACCESS_CP15(c8, 0, c3, 0)
+#define TLBIALL		__ACCESS_CP15(c8, 0, c7, 0)
 #define TLBIALLNSNHIS	__ACCESS_CP15(c8, 4, c3, 4)
 #define PRRR		__ACCESS_CP15(c10, 0, c2, 0)
 #define NMRR		__ACCESS_CP15(c10, 0, c2, 1)

arch/arm/kernel/traps.c

@@ -74,6 +74,26 @@ void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long
 		dump_mem("", "Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs));
 }
 
+void dump_backtrace_stm(u32 *stack, u32 instruction)
+{
+	char str[80], *p;
+	unsigned int x;
+	int reg;
+
+	for (reg = 10, x = 0, p = str; reg >= 0; reg--) {
+		if (instruction & BIT(reg)) {
+			p += sprintf(p, " r%d:%08x", reg, *stack--);
+			if (++x == 6) {
+				x = 0;
+				p = str;
+				printk("%s\n", str);
+			}
+		}
+	}
+	if (p != str)
+		printk("%s\n", str);
+}
+
 #ifndef CONFIG_ARM_UNWIND
 /*
  * Stack pointers should always be within the kernels view of

arch/arm/kernel/vmlinux-xip.lds.S

@@ -3,6 +3,9 @@
  * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
  */
 
+/* No __ro_after_init data in the .rodata section - which will always be ro */
+#define RO_AFTER_INIT_DATA
+
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/thread_info.h>
@@ -223,6 +226,8 @@ SECTIONS
 		. = ALIGN(PAGE_SIZE);
 		__init_end = .;
 
+		*(.data..ro_after_init)
+
 		NOSAVE_DATA
 		CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
 		READ_MOSTLY_DATA(L1_CACHE_BYTES)

arch/arm/kvm/arm.c

@@ -114,11 +114,18 @@ void kvm_arch_check_processor_compat(void *rtn)
  */
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
-	int ret = 0;
+	int ret, cpu;
 
 	if (type)
 		return -EINVAL;
 
+	kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran));
+	if (!kvm->arch.last_vcpu_ran)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1;
+
 	ret = kvm_alloc_stage2_pgd(kvm);
 	if (ret)
 		goto out_fail_alloc;
@@ -141,6 +148,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 out_free_stage2_pgd:
 	kvm_free_stage2_pgd(kvm);
 out_fail_alloc:
+	free_percpu(kvm->arch.last_vcpu_ran);
+	kvm->arch.last_vcpu_ran = NULL;
 	return ret;
 }
 
@@ -168,6 +177,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	int i;
 
+	free_percpu(kvm->arch.last_vcpu_ran);
+	kvm->arch.last_vcpu_ran = NULL;
+
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (kvm->vcpus[i]) {
 			kvm_arch_vcpu_free(kvm->vcpus[i]);
@@ -312,6 +324,19 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+	int *last_ran;
+
+	last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran);
+
+	/*
+	 * We might get preempted before the vCPU actually runs, but
+	 * over-invalidation doesn't affect correctness.
+	 */
+	if (*last_ran != vcpu->vcpu_id) {
+		kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu);
+		*last_ran = vcpu->vcpu_id;
+	}
+
 	vcpu->cpu = cpu;
 	vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state);
 

arch/arm/kvm/hyp/tlb.c

@@ -55,6 +55,21 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	__kvm_tlb_flush_vmid(kvm);
 }
 
+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);
+	isb();
+
+	write_sysreg(0, TLBIALL);
+	dsb(nsh);
+	isb();
+
+	write_sysreg(0, VTTBR);
+}
+
 void __hyp_text __kvm_flush_vm_context(void)
 {
 	write_sysreg(0, TLBIALLNSNHIS);

arch/arm/lib/backtrace.S

@@ -10,6 +10,7 @@
  * 27/03/03 Ian Molton Clean up CONFIG_CPU
  *
  */
+#include <linux/kern_levels.h>
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 		.text
@@ -83,13 +84,13 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 		teq	r3, r1, lsr #11
 		ldreq	r0, [frame, #-8]	@ get sp
 		subeq	r0, r0, #4		@ point at the last arg
-		bleq	.Ldumpstm		@ dump saved registers
+		bleq	dump_backtrace_stm	@ dump saved registers
 
 1004:		ldr	r1, [sv_pc, #0]		@ if stmfd sp!, {..., fp, ip, lr, pc}
 		ldr	r3, .Ldsi		@ instruction exists,
 		teq	r3, r1, lsr #11
 		subeq	r0, frame, #16
-		bleq	.Ldumpstm		@ dump saved registers
+		bleq	dump_backtrace_stm	@ dump saved registers
 
 		teq	sv_fp, #0		@ zero saved fp means
 		beq	no_frame		@ no further frames
@@ -112,38 +113,6 @@ ENDPROC(c_backtrace)
 		.long	1004b, 1006b
 		.popsection
 
-#define instr r4
-#define reg   r5
-#define stack r6
-
-.Ldumpstm:	stmfd	sp!, {instr, reg, stack, r7, lr}
-		mov	stack, r0
-		mov	instr, r1
-		mov	reg, #10
-		mov	r7, #0
-1:		mov	r3, #1
- ARM(		tst	instr, r3, lsl reg	)
- THUMB(		lsl	r3, reg			)
- THUMB(		tst	instr, r3		)
-		beq	2f
-		add	r7, r7, #1
-		teq	r7, #6
-		moveq	r7, #0
-		adr	r3, .Lcr
-		addne	r3, r3, #1		@ skip newline
-		ldr	r2, [stack], #-4
-		mov	r1, reg
-		adr	r0, .Lfp
-		bl	printk
-2:		subs	reg, reg, #1
-		bpl	1b
-		teq	r7, #0
-		adrne	r0, .Lcr
-		blne	printk
-		ldmfd	sp!, {instr, reg, stack, r7, pc}
-
-.Lfp:		.asciz	" r%d:%08x%s"
-.Lcr:		.asciz	"\n"
 .Lbad:		.asciz	"Backtrace aborted due to bad frame pointer <%p>\n"
 		.align
 .Ldsi:		.word	0xe92dd800 >> 11	@ stmfd sp!, {... fp, ip, lr, pc}

arch/arm/mach-omap2/Kconfig

@@ -71,6 +71,7 @@ config SOC_AM43XX
 	select HAVE_ARM_TWD
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_775420
+	select OMAP_INTERCONNECT
 
 config SOC_DRA7XX
 	bool "TI DRA7XX"

arch/arm/mach-omap2/id.c

@@ -205,11 +205,15 @@ void __init omap2xxx_check_revision(void)
 
 #define OMAP3_SHOW_FEATURE(feat)		\
 	if (omap3_has_ ##feat())		\
-		printk(#feat" ");
+		n += scnprintf(buf + n, sizeof(buf) - n, #feat " ");
 
 static void __init omap3_cpuinfo(void)
 {
 	const char *cpu_name;
+	char buf[64];
+	int n = 0;
+
+	memset(buf, 0, sizeof(buf));
 
 	/*
 	 * OMAP3430 and OMAP3530 are assumed to be same.
@@ -241,10 +245,10 @@ static void __init omap3_cpuinfo(void)
 		cpu_name = "OMAP3503";
 	}
 
-	sprintf(soc_name, "%s", cpu_name);
+	scnprintf(soc_name, sizeof(soc_name), "%s", cpu_name);
 
 	/* Print verbose information */
-	pr_info("%s %s (", soc_name, soc_rev);
+	n += scnprintf(buf, sizeof(buf) - n, "%s %s (", soc_name, soc_rev);
 
 	OMAP3_SHOW_FEATURE(l2cache);
 	OMAP3_SHOW_FEATURE(iva);
@@ -252,8 +256,10 @@ static void __init omap3_cpuinfo(void)
 	OMAP3_SHOW_FEATURE(neon);
 	OMAP3_SHOW_FEATURE(isp);
 	OMAP3_SHOW_FEATURE(192mhz_clk);
-
-	printk(")\n");
+	if (*(buf + n - 1) == ' ')
+		n--;
+	n += scnprintf(buf + n, sizeof(buf) - n, ")\n");
+	pr_info("%s", buf);
 }
 
 #define OMAP3_CHECK_FEATURE(status,feat)				\

arch/arm/mach-omap2/prm3xxx.c

@@ -319,6 +319,9 @@ void __init omap3_prm_init_pm(bool has_uart4, bool has_iva)
 	if (has_uart4) {
 		en_uart4_mask = OMAP3630_EN_UART4_MASK;
 		grpsel_uart4_mask = OMAP3630_GRPSEL_UART4_MASK;
+	} else {
+		en_uart4_mask = 0;
+		grpsel_uart4_mask = 0;
 	}
 
 	/* Enable wakeups in PER */

arch/arm/mach-omap2/voltage.c

@@ -87,6 +87,12 @@ int voltdm_scale(struct voltagedomain *voltdm,
 		return -ENODATA;
 	}
 
+	if (!voltdm->volt_data) {
+		pr_err("%s: No voltage data defined for vdd_%s\n",
+			__func__, voltdm->name);
+		return -ENODATA;
+	}
+
 	/* Adjust voltage to the exact voltage from the OPP table */
 	for (i = 0; voltdm->volt_data[i].volt_nominal != 0; i++) {
 		if (voltdm->volt_data[i].volt_nominal >= target_volt) {

arch/arm/mm/dma-mapping.c

@@ -1167,7 +1167,7 @@ static int __init dma_debug_do_init(void)
 	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 	return 0;
 }
-fs_initcall(dma_debug_do_init);
+core_initcall(dma_debug_do_init);
 
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 

arch/arm/mm/proc-v7m.S

@@ -96,7 +96,7 @@ ENTRY(cpu_cm7_proc_fin)
 	ret	lr
 ENDPROC(cpu_cm7_proc_fin)
 
-	.section ".text.init", #alloc, #execinstr
+	.section ".init.text", #alloc, #execinstr
 
 __v7m_cm7_setup:
 	mov	r8, #(V7M_SCB_CCR_DC | V7M_SCB_CCR_IC| V7M_SCB_CCR_BP)

arch/arm64/boot/dts/marvell/armada-37xx.dtsi

@@ -105,7 +105,7 @@
 				status = "disabled";
 			};
 
-			nb_perih_clk: nb-periph-clk@13000{
+			nb_periph_clk: nb-periph-clk@13000 {
 				compatible = "marvell,armada-3700-periph-clock-nb";
 				reg = <0x13000 0x100>;
 				clocks = <&tbg 0>, <&tbg 1>, <&tbg 2>,
@@ -113,7 +113,7 @@
 				#clock-cells = <1>;
 			};
 
-			sb_perih_clk: sb-periph-clk@18000{
+			sb_periph_clk: sb-periph-clk@18000 {
 				compatible = "marvell,armada-3700-periph-clock-sb";
 				reg = <0x18000 0x100>;
 				clocks = <&tbg 0>, <&tbg 1>, <&tbg 2>,

arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi

@@ -130,8 +130,8 @@
 				reg = <0x700600 0x50>;
 				#address-cells = <0x1>;
 				#size-cells = <0x0>;
-				cell-index = <1>;
-				clocks = <&cps_syscon0 0 3>;
+				cell-index = <3>;
+				clocks = <&cps_syscon0 1 21>;
 				status = "disabled";
 			};
 
@@ -140,7 +140,7 @@
 				reg = <0x700680 0x50>;
 				#address-cells = <1>;
 				#size-cells = <0>;
-				cell-index = <2>;
+				cell-index = <4>;
 				clocks = <&cps_syscon0 1 21>;
 				status = "disabled";
 			};

arch/arm64/boot/dts/rockchip/rk3399.dtsi

@@ -300,8 +300,11 @@
 		ranges = <0x83000000 0x0 0xfa000000 0x0 0xfa000000 0x0 0x600000
 			  0x81000000 0x0 0xfa600000 0x0 0xfa600000 0x0 0x100000>;
 		resets = <&cru SRST_PCIE_CORE>, <&cru SRST_PCIE_MGMT>,
-			 <&cru SRST_PCIE_MGMT_STICKY>, <&cru SRST_PCIE_PIPE>;
-		reset-names = "core", "mgmt", "mgmt-sticky", "pipe";
+			 <&cru SRST_PCIE_MGMT_STICKY>, <&cru SRST_PCIE_PIPE>,
+			 <&cru SRST_PCIE_PM>, <&cru SRST_P_PCIE>,
+			 <&cru SRST_A_PCIE>;
+		reset-names = "core", "mgmt", "mgmt-sticky", "pipe",
+			      "pm", "pclk", "aclk";
 		status = "disabled";
 
 		pcie0_intc: interrupt-controller {

arch/arm64/include/asm/kvm_asm.h

@@ -54,6 +54,7 @@ extern char __kvm_hyp_vector[];
 extern void __kvm_flush_vm_context(void);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
 extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
+extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
 
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 

arch/arm64/include/asm/kvm_host.h

@@ -62,6 +62,9 @@ struct kvm_arch {
 	/* VTTBR value associated with above pgd and vmid */
 	u64    vttbr;
 
+	/* The last vcpu id that ran on each physical CPU */
+	int __percpu *last_vcpu_ran;
+
 	/* The maximum number of vCPUs depends on the used GIC model */
 	int max_vcpus;
 

arch/arm64/include/asm/kvm_mmu.h

@@ -128,7 +128,7 @@ static inline unsigned long __kern_hyp_va(unsigned long v)
 	return v;
 }
 
-#define kern_hyp_va(v) 	(typeof(v))(__kern_hyp_va((unsigned long)(v)))
+#define kern_hyp_va(v) 	((typeof(v))(__kern_hyp_va((unsigned long)(v))))
 
 /*
  * We currently only support a 40bit IPA.

arch/arm64/include/asm/perf_event.h

@@ -46,7 +46,15 @@
 #define	ARMV8_PMU_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
 #define	ARMV8_PMU_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
 
-#define ARMV8_PMU_EVTYPE_EVENT_SW_INCR	0	/* Software increment event */
+/*
+ * PMUv3 event types: required events
+ */
+#define ARMV8_PMUV3_PERFCTR_SW_INCR				0x00
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL			0x03
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE				0x04
+#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED				0x10
+#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES				0x11
+#define ARMV8_PMUV3_PERFCTR_BR_PRED				0x12
 
 /*
  * Event filters for PMUv3

arch/arm64/kernel/perf_event.c

@@ -31,17 +31,9 @@
 
 /*
  * ARMv8 PMUv3 Performance Events handling code.
- * Common event types.
+ * Common event types (some are defined in asm/perf_event.h).
  */
 
-/* Required events. */
-#define ARMV8_PMUV3_PERFCTR_SW_INCR				0x00
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL			0x03
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE				0x04
-#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED				0x10
-#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES				0x11
-#define ARMV8_PMUV3_PERFCTR_BR_PRED				0x12
-
 /* At least one of the following is required. */
 #define ARMV8_PMUV3_PERFCTR_INST_RETIRED			0x08
 #define ARMV8_PMUV3_PERFCTR_INST_SPEC				0x1B

arch/arm64/kvm/hyp/tlb.c

@@ -64,6 +64,21 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 	write_sysreg(0, vttbr_el2);
 }
 
+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();
+
+	asm volatile("tlbi vmalle1" : : );
+	dsb(nsh);
+	isb();
+
+	write_sysreg(0, vttbr_el2);
+}
+
 void __hyp_text __kvm_flush_vm_context(void)
 {
 	dsb(ishst);

arch/arm64/kvm/sys_regs.c

@@ -597,8 +597,14 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 
 			idx = ARMV8_PMU_CYCLE_IDX;
 		} else {
-			BUG();
+			return false;
 		}
+	} else if (r->CRn == 0 && r->CRm == 9) {
+		/* PMCCNTR */
+		if (pmu_access_event_counter_el0_disabled(vcpu))
+			return false;
+
+		idx = ARMV8_PMU_CYCLE_IDX;
 	} else if (r->CRn == 14 && (r->CRm & 12) == 8) {
 		/* PMEVCNTRn_EL0 */
 		if (pmu_access_event_counter_el0_disabled(vcpu))
@@ -606,7 +612,7 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 
 		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
 	} else {
-		BUG();
+		return false;
 	}
 
 	if (!pmu_counter_idx_valid(vcpu, idx))

arch/nios2/kernel/time.c

@@ -324,6 +324,7 @@ static int __init nios2_time_init(struct device_node *timer)
 		ret = nios2_clocksource_init(timer);
 		break;
 	default:
+		ret = 0;
 		break;
 	}
 

arch/powerpc/include/asm/exception-64s.h

@@ -91,7 +91,7 @@
  */
 #define LOAD_HANDLER(reg, label)					\
 	ld	reg,PACAKBASE(r13);	/* get high part of &label */	\
-	ori	reg,reg,(FIXED_SYMBOL_ABS_ADDR(label))@l;
+	ori	reg,reg,FIXED_SYMBOL_ABS_ADDR(label);
 
 #define __LOAD_HANDLER(reg, label)					\
 	ld	reg,PACAKBASE(r13);					\
@@ -158,14 +158,17 @@ BEGIN_FTR_SECTION_NESTED(943)						\
 	std	ra,offset(r13);						\
 END_FTR_SECTION_NESTED(ftr,ftr,943)
 
-#define EXCEPTION_PROLOG_0(area)					\
-	GET_PACA(r13);							\
+#define EXCEPTION_PROLOG_0_PACA(area)					\
 	std	r9,area+EX_R9(r13);	/* save r9 */			\
 	OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR);			\
 	HMT_MEDIUM;							\
 	std	r10,area+EX_R10(r13);	/* save r10 - r12 */		\
 	OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR)
 
+#define EXCEPTION_PROLOG_0(area)					\
+	GET_PACA(r13);							\
+	EXCEPTION_PROLOG_0_PACA(area)
+
 #define __EXCEPTION_PROLOG_1(area, extra, vec)				\
 	OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR);		\
 	OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR);		\
@@ -196,6 +199,12 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	EXCEPTION_PROLOG_1(area, extra, vec);				\
 	EXCEPTION_PROLOG_PSERIES_1(label, h);
 
+/* Have the PACA in r13 already */
+#define EXCEPTION_PROLOG_PSERIES_PACA(area, label, h, extra, vec)	\
+	EXCEPTION_PROLOG_0_PACA(area);					\
+	EXCEPTION_PROLOG_1(area, extra, vec);				\
+	EXCEPTION_PROLOG_PSERIES_1(label, h);
+
 #define __KVMTEST(h, n)							\
 	lbz	r10,HSTATE_IN_GUEST(r13);				\
 	cmpwi	r10,0;							\

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

@@ -460,5 +460,6 @@
 
 #define PPC_SLBIA(IH)	stringify_in_c(.long PPC_INST_SLBIA | \
 				       ((IH & 0x7) << 21))
+#define PPC_INVALIDATE_ERAT	PPC_SLBIA(7)
 
 #endif /* _ASM_POWERPC_PPC_OPCODE_H */

arch/powerpc/kernel/exceptions-64s.S

@@ -116,7 +116,9 @@ EXC_VIRT_NONE(0x4000, 0x4100)
 
 EXC_REAL_BEGIN(system_reset, 0x100, 0x200)
 	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
+	GET_PACA(r13)
+	clrrdi	r13,r13,1 /* Last bit of HSPRG0 is set if waking from winkle */
+	EXCEPTION_PROLOG_PSERIES_PACA(PACA_EXGEN, system_reset_common, EXC_STD,
 				 IDLETEST, 0x100)
 
 EXC_REAL_END(system_reset, 0x100, 0x200)
@@ -124,6 +126,9 @@ EXC_VIRT_NONE(0x4100, 0x4200)
 
 #ifdef CONFIG_PPC_P7_NAP
 EXC_COMMON_BEGIN(system_reset_idle_common)
+BEGIN_FTR_SECTION
+	GET_PACA(r13) /* Restore HSPRG0 to get the winkle bit in r13 */
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	bl	pnv_restore_hyp_resource
 
 	li	r0,PNV_THREAD_RUNNING
@@ -169,7 +174,7 @@ EXC_REAL_BEGIN(machine_check, 0x200, 0x300)
 	SET_SCRATCH0(r13)		/* save r13 */
 	/*
 	 * Running native on arch 2.06 or later, we may wakeup from winkle
-	 * inside machine check. If yes, then last bit of HSPGR0 would be set
+	 * inside machine check. If yes, then last bit of HSPRG0 would be set
 	 * to 1. Hence clear it unconditionally.
 	 */
 	GET_PACA(r13)
@@ -388,7 +393,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	/*
 	 * Go back to winkle. Please note that this thread was woken up in
 	 * machine check from winkle and have not restored the per-subcore
-	 * state. Hence before going back to winkle, set last bit of HSPGR0
+	 * state. Hence before going back to winkle, set last bit of HSPRG0
 	 * to 1. This will make sure that if this thread gets woken up
 	 * again at reset vector 0x100 then it will get chance to restore
 	 * the subcore state.

arch/powerpc/kernel/process.c

@@ -1215,7 +1215,7 @@ static void show_instructions(struct pt_regs *regs)
 		int instr;
 
 		if (!(i % 8))
-			printk("\n");
+			pr_cont("\n");
 
 #if !defined(CONFIG_BOOKE)
 		/* If executing with the IMMU off, adjust pc rather
@@ -1227,18 +1227,18 @@ static void show_instructions(struct pt_regs *regs)
 
 		if (!__kernel_text_address(pc) ||
 		     probe_kernel_address((unsigned int __user *)pc, instr)) {
-			printk(KERN_CONT "XXXXXXXX ");
+			pr_cont("XXXXXXXX ");
 		} else {
 			if (regs->nip == pc)
-				printk(KERN_CONT "<%08x> ", instr);
+				pr_cont("<%08x> ", instr);
 			else
-				printk(KERN_CONT "%08x ", instr);
+				pr_cont("%08x ", instr);
 		}
 
 		pc += sizeof(int);
 	}
 
-	printk("\n");
+	pr_cont("\n");
 }
 
 struct regbit {
@@ -1282,7 +1282,7 @@ static void print_bits(unsigned long val, struct regbit *bits, const char *sep)
 
 	for (; bits->bit; ++bits)
 		if (val & bits->bit) {
-			printk("%s%s", s, bits->name);
+			pr_cont("%s%s", s, bits->name);
 			s = sep;
 		}
 }
@@ -1305,9 +1305,9 @@ static void print_tm_bits(unsigned long val)
  *   T: Transactional	(bit 34)
  */
 	if (val & (MSR_TM | MSR_TS_S | MSR_TS_T)) {
-		printk(",TM[");
+		pr_cont(",TM[");
 		print_bits(val, msr_tm_bits, "");
-		printk("]");
+		pr_cont("]");
 	}
 }
 #else
@@ -1316,10 +1316,10 @@ static void print_tm_bits(unsigned long val) {}
 
 static void print_msr_bits(unsigned long val)
 {
-	printk("<");
+	pr_cont("<");
 	print_bits(val, msr_bits, ",");
 	print_tm_bits(val);
-	printk(">");
+	pr_cont(">");
 }
 
 #ifdef CONFIG_PPC64
@@ -1347,29 +1347,29 @@ void show_regs(struct pt_regs * regs)
 	printk("  CR: %08lx  XER: %08lx\n", regs->ccr, regs->xer);
 	trap = TRAP(regs);
 	if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
-		printk("CFAR: "REG" ", regs->orig_gpr3);
+		pr_cont("CFAR: "REG" ", regs->orig_gpr3);
 	if (trap == 0x200 || trap == 0x300 || trap == 0x600)
 #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
-		printk("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
+		pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
 #else
-		printk("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
+		pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
 #endif
 #ifdef CONFIG_PPC64
-	printk("SOFTE: %ld ", regs->softe);
+	pr_cont("SOFTE: %ld ", regs->softe);
 #endif
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (MSR_TM_ACTIVE(regs->msr))
-		printk("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch);
+		pr_cont("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch);
 #endif
 
 	for (i = 0;  i < 32;  i++) {
 		if ((i % REGS_PER_LINE) == 0)
-			printk("\nGPR%02d: ", i);
-		printk(REG " ", regs->gpr[i]);
+			pr_cont("\nGPR%02d: ", i);
+		pr_cont(REG " ", regs->gpr[i]);
 		if (i == LAST_VOLATILE && !FULL_REGS(regs))
 			break;
 	}
-	printk("\n");
+	pr_cont("\n");
 #ifdef CONFIG_KALLSYMS
 	/*
 	 * Lookup NIP late so we have the best change of getting the
@@ -1900,14 +1900,14 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
 			printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 			if ((ip == rth) && curr_frame >= 0) {
-				printk(" (%pS)",
+				pr_cont(" (%pS)",
 				       (void *)current->ret_stack[curr_frame].ret);
 				curr_frame--;
 			}
 #endif
 			if (firstframe)
-				printk(" (unreliable)");
-			printk("\n");
+				pr_cont(" (unreliable)");
+			pr_cont("\n");
 		}
 		firstframe = 0;
 

arch/powerpc/kernel/setup_64.c

@@ -226,17 +226,25 @@ static void __init configure_exceptions(void)
 		if (firmware_has_feature(FW_FEATURE_OPAL))
 			opal_configure_cores();
 
-		/* Enable AIL if supported, and we are in hypervisor mode */
-		if (early_cpu_has_feature(CPU_FTR_HVMODE) &&
-		    early_cpu_has_feature(CPU_FTR_ARCH_207S)) {
-			unsigned long lpcr = mfspr(SPRN_LPCR);
-			mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
-		}
+		/* AIL on native is done in cpu_ready_for_interrupts() */
 	}
 }
 
 static void cpu_ready_for_interrupts(void)
 {
+	/*
+	 * Enable AIL if supported, and we are in hypervisor mode. This
+	 * is called once for every processor.
+	 *
+	 * If we are not in hypervisor mode the job is done once for
+	 * the whole partition in configure_exceptions().
+	 */
+	if (early_cpu_has_feature(CPU_FTR_HVMODE) &&
+	    early_cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		unsigned long lpcr = mfspr(SPRN_LPCR);
+		mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
+	}
+
 	/* Set IR and DR in PACA MSR */
 	get_paca()->kernel_msr = MSR_KERNEL;
 }

arch/powerpc/mm/hash_utils_64.c

@@ -1029,6 +1029,10 @@ void hash__early_init_mmu_secondary(void)
 {
 	/* Initialize hash table for that CPU */
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+
+		if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+			update_hid_for_hash();
+
 		if (!cpu_has_feature(CPU_FTR_ARCH_300))
 			mtspr(SPRN_SDR1, _SDR1);
 		else

arch/powerpc/mm/pgtable-radix.c

@@ -388,6 +388,10 @@ void radix__early_init_mmu_secondary(void)
 	 * update partition table control register and UPRT
 	 */
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+
+		if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+			update_hid_for_radix();
+
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 

arch/powerpc/mm/tlb-radix.c

@@ -50,6 +50,8 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 	for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
 		__tlbiel_pid(pid, set, ric);
 	}
+	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+		asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
 	return;
 }
 
@@ -83,6 +85,8 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("ptesync": : :"memory");
+	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+		asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
 }
 
 static inline void _tlbie_va(unsigned long va, unsigned long pid,

arch/s390/kernel/vmlinux.lds.S

@@ -62,9 +62,11 @@ SECTIONS
 
 	. = ALIGN(PAGE_SIZE);
 	__start_ro_after_init = .;
+	__start_data_ro_after_init = .;
 	.data..ro_after_init : {
 		 *(.data..ro_after_init)
 	}
+	__end_data_ro_after_init = .;
 	EXCEPTION_TABLE(16)
 	. = ALIGN(PAGE_SIZE);
 	__end_ro_after_init = .;

arch/s390/pci/pci_dma.c

@@ -423,7 +423,7 @@ static int __s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	dma_addr_t dma_addr_base, dma_addr;
 	int flags = ZPCI_PTE_VALID;
 	struct scatterlist *s;
-	unsigned long pa;
+	unsigned long pa = 0;
 	int ret;
 
 	size = PAGE_ALIGN(size);

arch/sparc/Kconfig

@@ -43,6 +43,7 @@ config SPARC
 	select ARCH_HAS_SG_CHAIN
 	select CPU_NO_EFFICIENT_FFS
 	select HAVE_ARCH_HARDENED_USERCOPY
+	select PROVE_LOCKING_SMALL if PROVE_LOCKING
 
 config SPARC32
 	def_bool !64BIT
@@ -89,6 +90,14 @@ config ARCH_DEFCONFIG
 config ARCH_PROC_KCORE_TEXT
 	def_bool y
 
+config ARCH_ATU
+	bool
+	default y if SPARC64
+
+config ARCH_DMA_ADDR_T_64BIT
+	bool
+	default y if ARCH_ATU
+
 config IOMMU_HELPER
 	bool
 	default y if SPARC64
@@ -304,6 +313,20 @@ config ARCH_SPARSEMEM_ENABLE
 config ARCH_SPARSEMEM_DEFAULT
 	def_bool y if SPARC64
 
+config FORCE_MAX_ZONEORDER
+	int "Maximum zone order"
+	default "13"
+	help
+	  The kernel memory allocator divides physically contiguous memory
+	  blocks into "zones", where each zone is a power of two number of
+	  pages.  This option selects the largest power of two that the kernel
+	  keeps in the memory allocator.  If you need to allocate very large
+	  blocks of physically contiguous memory, then you may need to
+	  increase this value.
+
+	  This config option is actually maximum order plus one. For example,
+	  a value of 13 means that the largest free memory block is 2^12 pages.
+
 source "mm/Kconfig"
 
 if SPARC64

arch/sparc/include/asm/hypervisor.h

@@ -2335,6 +2335,348 @@ unsigned long sun4v_vintr_set_target(unsigned long dev_handle,
  */
 #define HV_FAST_PCI_MSG_SETVALID	0xd3
 
+/* PCI IOMMU v2 definitions and services
+ *
+ * While the PCI IO definitions above is valid IOMMU v2 adds new PCI IO
+ * definitions and services.
+ *
+ *	CTE		Clump Table Entry. First level table entry in the ATU.
+ *
+ *	pci_device_list
+ *			A 32-bit aligned list of pci_devices.
+ *
+ *	pci_device_listp
+ *			real address of a pci_device_list. 32-bit aligned.
+ *
+ *	iotte		IOMMU translation table entry.
+ *
+ *	iotte_attributes
+ *			IO Attributes for IOMMU v2 mappings. In addition to
+ *			read, write IOMMU v2 supports relax ordering
+ *
+ *	io_page_list	A 64-bit aligned list of real addresses. Each real
+ *			address in an io_page_list must be properly aligned
+ *			to the pagesize of the given IOTSB.
+ *
+ *	io_page_list_p	Real address of an io_page_list, 64-bit aligned.
+ *
+ *	IOTSB		IO Translation Storage Buffer. An aligned table of
+ *			IOTTEs. Each IOTSB has a pagesize, table size, and
+ *			virtual address associated with it that must match
+ *			a pagesize and table size supported by the un-derlying
+ *			hardware implementation. The alignment requirements
+ *			for an IOTSB depend on the pagesize used for that IOTSB.
+ *			Each IOTTE in an IOTSB maps one pagesize-sized page.
+ *			The size of the IOTSB dictates how large of a virtual
+ *			address space the IOTSB is capable of mapping.
+ *
+ *	iotsb_handle	An opaque identifier for an IOTSB. A devhandle plus
+ *			iotsb_handle represents a binding of an IOTSB to a
+ *			PCI root complex.
+ *
+ *	iotsb_index	Zero-based IOTTE number within an IOTSB.
+ */
+
+/* The index_count argument consists of two fields:
+ * bits 63:48 #iottes and bits 47:0 iotsb_index
+ */
+#define HV_PCI_IOTSB_INDEX_COUNT(__iottes, __iotsb_index) \
+	(((u64)(__iottes) << 48UL) | ((u64)(__iotsb_index)))
+
+/* pci_iotsb_conf()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_CONF
+ * ARG0:	devhandle
+ * ARG1:	r_addr
+ * ARG2:	size
+ * ARG3:	pagesize
+ * ARG4:	iova
+ * RET0:	status
+ * RET1:	iotsb_handle
+ * ERRORS:	EINVAL		Invalid devhandle, size, iova, or pagesize
+ *		EBADALIGN	r_addr is not properly aligned
+ *		ENORADDR	r_addr is not a valid real address
+ *		ETOOMANY	No further IOTSBs may be configured
+ *		EBUSY		Duplicate devhandle, raddir, iova combination
+ *
+ * Create an IOTSB suitable for the PCI root complex identified by devhandle,
+ * for the DMA virtual address defined by the argument iova.
+ *
+ * r_addr is the properly aligned base address of the IOTSB and size is the
+ * IOTSB (table) size in bytes.The IOTSB is required to be zeroed prior to
+ * being configured. If it contains any values other than zeros then the
+ * behavior is undefined.
+ *
+ * pagesize is the size of each page in the IOTSB. Note that the combination of
+ * size (table size) and pagesize must be valid.
+ *
+ * virt is the DMA virtual address this IOTSB will map.
+ *
+ * If successful, the opaque 64-bit handle iotsb_handle is returned in ret1.
+ * Once configured, privileged access to the IOTSB memory is prohibited and
+ * creates undefined behavior. The only permitted access is indirect via these
+ * services.
+ */
+#define HV_FAST_PCI_IOTSB_CONF		0x190
+
+/* pci_iotsb_info()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_INFO
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * RET0:	status
+ * RET1:	r_addr
+ * RET2:	size
+ * RET3:	pagesize
+ * RET4:	iova
+ * RET5:	#bound
+ * ERRORS:	EINVAL	Invalid devhandle or iotsb_handle
+ *
+ * This service returns configuration information about an IOTSB previously
+ * created with pci_iotsb_conf.
+ *
+ * iotsb_handle value 0 may be used with this service to inquire about the
+ * legacy IOTSB that may or may not exist. If the service succeeds, the return
+ * values describe the legacy IOTSB and I/O virtual addresses mapped by that
+ * table. However, the table base address r_addr may contain the value -1 which
+ * indicates a memory range that cannot be accessed or be reclaimed.
+ *
+ * The return value #bound contains the number of PCI devices that iotsb_handle
+ * is currently bound to.
+ */
+#define HV_FAST_PCI_IOTSB_INFO		0x191
+
+/* pci_iotsb_unconf()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_UNCONF
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * RET0:	status
+ * ERRORS:	EINVAL	Invalid devhandle or iotsb_handle
+ *		EBUSY	The IOTSB is bound and may not be unconfigured
+ *
+ * This service unconfigures the IOTSB identified by the devhandle and
+ * iotsb_handle arguments, previously created with pci_iotsb_conf.
+ * The IOTSB must not be currently bound to any device or the service will fail
+ *
+ * If the call succeeds, iotsb_handle is no longer valid.
+ */
+#define HV_FAST_PCI_IOTSB_UNCONF	0x192
+
+/* pci_iotsb_bind()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_BIND
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	pci_device
+ * RET0:	status
+ * ERRORS:	EINVAL	Invalid devhandle, iotsb_handle, or pci_device
+ *		EBUSY	A PCI function is already bound to an IOTSB at the same
+ *			address range as specified by devhandle, iotsb_handle.
+ *
+ * This service binds the PCI function specified by the argument pci_device to
+ * the IOTSB specified by the arguments devhandle and iotsb_handle.
+ *
+ * The PCI device function is bound to the specified IOTSB with the IOVA range
+ * specified when the IOTSB was configured via pci_iotsb_conf. If the function
+ * is already bound then it is unbound first.
+ */
+#define HV_FAST_PCI_IOTSB_BIND		0x193
+
+/* pci_iotsb_unbind()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_UNBIND
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	pci_device
+ * RET0:	status
+ * ERRORS:	EINVAL	Invalid devhandle, iotsb_handle, or pci_device
+ *		ENOMAP	The PCI function was not bound to the specified IOTSB
+ *
+ * This service unbinds the PCI device specified by the argument pci_device
+ * from the IOTSB identified  * by the arguments devhandle and iotsb_handle.
+ *
+ * If the PCI device is not bound to the specified IOTSB then this service will
+ * fail with status ENOMAP
+ */
+#define HV_FAST_PCI_IOTSB_UNBIND	0x194
+
+/* pci_iotsb_get_binding()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_GET_BINDING
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	iova
+ * RET0:	status
+ * RET1:	iotsb_handle
+ * ERRORS:	EINVAL	Invalid devhandle, pci_device, or iova
+ *		ENOMAP	The PCI function is not bound to an IOTSB at iova
+ *
+ * This service returns the IOTSB binding, iotsb_handle, for a given pci_device
+ * and DMA virtual address, iova.
+ *
+ * iova must be the base address of a DMA virtual address range as defined by
+ * the iommu-address-ranges property in the root complex device node defined
+ * by the argument devhandle.
+ */
+#define HV_FAST_PCI_IOTSB_GET_BINDING	0x195
+
+/* pci_iotsb_map()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_MAP
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	index_count
+ * ARG3:	iotte_attributes
+ * ARG4:	io_page_list_p
+ * RET0:	status
+ * RET1:	#mapped
+ * ERRORS:	EINVAL		Invalid devhandle, iotsb_handle, #iottes,
+ *				iotsb_index or iotte_attributes
+ *		EBADALIGN	Improperly aligned io_page_list_p or I/O page
+ *				address in the I/O page list.
+ *		ENORADDR	Invalid io_page_list_p or I/O page address in
+ *				the I/O page list.
+ *
+ * This service creates and flushes mappings in the IOTSB defined by the
+ * arguments devhandle, iotsb.
+ *
+ * The index_count argument consists of two fields. Bits 63:48 contain #iotte
+ * and bits 47:0 contain iotsb_index
+ *
+ * The first mapping is created in the IOTSB index specified by iotsb_index.
+ * Subsequent mappings are  created at iotsb_index+1 and so on.
+ *
+ * The attributes of each mapping are defined by the argument iotte_attributes.
+ *
+ * The io_page_list_p specifies the real address of the 64-bit-aligned list of
+ * #iottes I/O page addresses. Each page address must be a properly aligned
+ * real address of a page to be mapped in the IOTSB. The first entry in the I/O
+ * page list contains the real address of the first page, the 2nd entry for the
+ * 2nd page, and so on.
+ *
+ * #iottes must be greater than zero.
+ *
+ * The return value #mapped is the actual number of mappings created, which may
+ * be less than or equal to the argument #iottes. If the function returns
+ * successfully with a #mapped value less than the requested #iottes then the
+ * caller should continue to invoke the service with updated iotsb_index,
+ * #iottes, and io_page_list_p arguments until all pages are mapped.
+ *
+ * This service must not be used to demap a mapping. In other words, all
+ * mappings must be valid and have  one or both of the RW attribute bits set.
+ *
+ * Note:
+ * It is implementation-defined whether I/O page real address validity checking
+ * is done at time mappings are established or deferred until they are
+ * accessed.
+ */
+#define HV_FAST_PCI_IOTSB_MAP		0x196
+
+/* pci_iotsb_map_one()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_MAP_ONE
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	iotsb_index
+ * ARG3:	iotte_attributes
+ * ARG4:	r_addr
+ * RET0:	status
+ * ERRORS:	EINVAL		Invalid devhandle,iotsb_handle, iotsb_index
+ *				or iotte_attributes
+ *		EBADALIGN	Improperly aligned r_addr
+ *		ENORADDR	Invalid r_addr
+ *
+ * This service creates and flushes a single mapping in the IOTSB defined by the
+ * arguments devhandle, iotsb.
+ *
+ * The mapping for the page at r_addr is created at the IOTSB index specified by
+ * iotsb_index with  the attributes iotte_attributes.
+ *
+ * This service must not be used to demap a mapping. In other words, the mapping
+ * must be valid and have one or both of the RW attribute bits set.
+ *
+ * Note:
+ * It is implementation-defined whether I/O page real address validity checking
+ * is done at time mappings are established or deferred until they are
+ * accessed.
+ */
+#define HV_FAST_PCI_IOTSB_MAP_ONE	0x197
+
+/* pci_iotsb_demap()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_DEMAP
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	iotsb_index
+ * ARG3:	#iottes
+ * RET0:	status
+ * RET1:	#unmapped
+ * ERRORS:	EINVAL	Invalid devhandle, iotsb_handle, iotsb_index or #iottes
+ *
+ * This service unmaps and flushes up to #iottes mappings starting at index
+ * iotsb_index from the IOTSB defined by the arguments devhandle, iotsb.
+ *
+ * #iottes must be greater than zero.
+ *
+ * The actual number of IOTTEs unmapped is returned in #unmapped and may be less
+ * than or equal to the requested number of IOTTEs, #iottes.
+ *
+ * If #unmapped is less than #iottes, the caller should continue to invoke this
+ * service with updated iotsb_index and #iottes arguments until all pages are
+ * demapped.
+ */
+#define HV_FAST_PCI_IOTSB_DEMAP		0x198
+
+/* pci_iotsb_getmap()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_GETMAP
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	iotsb_index
+ * RET0:	status
+ * RET1:	r_addr
+ * RET2:	iotte_attributes
+ * ERRORS:	EINVAL	Invalid devhandle, iotsb_handle, or iotsb_index
+ *		ENOMAP	No mapping was found
+ *
+ * This service returns the mapping specified by index iotsb_index from the
+ * IOTSB defined by the arguments devhandle, iotsb.
+ *
+ * Upon success, the real address of the mapping shall be returned in
+ * r_addr and thethe IOTTE mapping attributes shall be returned in
+ * iotte_attributes.
+ *
+ * The return value iotte_attributes may not include optional features used in
+ * the call to create the  mapping.
+ */
+#define HV_FAST_PCI_IOTSB_GETMAP	0x199
+
+/* pci_iotsb_sync_mappings()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_SYNC_MAPPINGS
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	iotsb_index
+ * ARG3:	#iottes
+ * RET0:	status
+ * RET1:	#synced
+ * ERROS:	EINVAL	Invalid devhandle, iotsb_handle, iotsb_index, or #iottes
+ *
+ * This service synchronizes #iottes mappings starting at index iotsb_index in
+ * the IOTSB defined by the arguments devhandle, iotsb.
+ *
+ * #iottes must be greater than zero.
+ *
+ * The actual number of IOTTEs synchronized is returned in #synced, which may
+ * be less than or equal to the requested number, #iottes.
+ *
+ * Upon a successful return, #synced is less than #iottes, the caller should
+ * continue to invoke this service with updated iotsb_index and #iottes
+ * arguments until all pages are synchronized.
+ */
+#define HV_FAST_PCI_IOTSB_SYNC_MAPPINGS	0x19a
+
 /* Logical Domain Channel services.  */
 
 #define LDC_CHANNEL_DOWN		0
@@ -2993,6 +3335,7 @@ unsigned long sun4v_m7_set_perfreg(unsigned long reg_num,
 #define HV_GRP_SDIO			0x0108
 #define HV_GRP_SDIO_ERR			0x0109
 #define HV_GRP_REBOOT_DATA		0x0110
+#define HV_GRP_ATU			0x0111
 #define HV_GRP_M7_PERF			0x0114
 #define HV_GRP_NIAG_PERF		0x0200
 #define HV_GRP_FIRE_PERF		0x0201

arch/sparc/include/asm/iommu_64.h

@@ -24,8 +24,36 @@ struct iommu_arena {
 	unsigned int	limit;
 };
 
+#define ATU_64_SPACE_SIZE 0x800000000 /* 32G */
+
+/* Data structures for SPARC ATU architecture */
+struct atu_iotsb {
+	void	*table;		/* IOTSB table base virtual addr*/
+	u64	ra;		/* IOTSB table real addr */
+	u64	dvma_size;	/* ranges[3].size or OS slected 32G size */
+	u64	dvma_base;	/* ranges[3].base */
+	u64	table_size;	/* IOTSB table size */
+	u64	page_size;	/* IO PAGE size for IOTSB */
+	u32	iotsb_num;	/* tsbnum is same as iotsb_handle */
+};
+
+struct atu_ranges {
+	u64	base;
+	u64	size;
+};
+
+struct atu {
+	struct	atu_ranges	*ranges;
+	struct	atu_iotsb	*iotsb;
+	struct	iommu_map_table	tbl;
+	u64			base;
+	u64			size;
+	u64			dma_addr_mask;
+};
+
 struct iommu {
 	struct iommu_map_table	tbl;
+	struct atu		*atu;
 	spinlock_t		lock;
 	u32			dma_addr_mask;
 	iopte_t			*page_table;

arch/sparc/kernel/hvapi.c

@@ -39,6 +39,7 @@ static struct api_info api_table[] = {
 	{ .group = HV_GRP_SDIO,					},
 	{ .group = HV_GRP_SDIO_ERR,				},
 	{ .group = HV_GRP_REBOOT_DATA,				},
+	{ .group = HV_GRP_ATU,		.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_NIAG_PERF,	.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_FIRE_PERF,				},
 	{ .group = HV_GRP_N2_CPU,				},

arch/sparc/kernel/iommu.c

@@ -760,8 +760,12 @@ int dma_supported(struct device *dev, u64 device_mask)
 	struct iommu *iommu = dev->archdata.iommu;
 	u64 dma_addr_mask = iommu->dma_addr_mask;
 
-	if (device_mask >= (1UL << 32UL))
-		return 0;
+	if (device_mask > DMA_BIT_MASK(32)) {
+		if (iommu->atu)
+			dma_addr_mask = iommu->atu->dma_addr_mask;
+		else
+			return 0;
+	}
 
 	if ((device_mask & dma_addr_mask) == dma_addr_mask)
 		return 1;

arch/sparc/kernel/iommu_common.h

@@ -13,7 +13,6 @@
 #include <linux/scatterlist.h>
 #include <linux/device.h>
 #include <linux/iommu-helper.h>
-#include <linux/scatterlist.h>
 
 #include <asm/iommu.h>
 

arch/sparc/kernel/pci_sun4v.c

@@ -44,6 +44,9 @@ static struct vpci_version vpci_versions[] = {
 	{ .major = 1, .minor = 1 },
 };
 
+static unsigned long vatu_major = 1;
+static unsigned long vatu_minor = 1;
+
 #define PGLIST_NENTS	(PAGE_SIZE / sizeof(u64))
 
 struct iommu_batch {
@@ -69,34 +72,57 @@ static inline void iommu_batch_start(struct device *dev, unsigned long prot, uns
 }
 
 /* Interrupts must be disabled.  */
-static long iommu_batch_flush(struct iommu_batch *p)
+static long iommu_batch_flush(struct iommu_batch *p, u64 mask)
 {
 	struct pci_pbm_info *pbm = p->dev->archdata.host_controller;
+	u64 *pglist = p->pglist;
+	u64 index_count;
 	unsigned long devhandle = pbm->devhandle;
 	unsigned long prot = p->prot;
 	unsigned long entry = p->entry;
-	u64 *pglist = p->pglist;
 	unsigned long npages = p->npages;
+	unsigned long iotsb_num;
+	unsigned long ret;
+	long num;
 
 	/* VPCI maj=1, min=[0,1] only supports read and write */
 	if (vpci_major < 2)
 		prot &= (HV_PCI_MAP_ATTR_READ | HV_PCI_MAP_ATTR_WRITE);
 
 	while (npages != 0) {
-		long num;
-
-		num = pci_sun4v_iommu_map(devhandle, HV_PCI_TSBID(0, entry),
-					  npages, prot, __pa(pglist));
-		if (unlikely(num < 0)) {
-			if (printk_ratelimit())
-				printk("iommu_batch_flush: IOMMU map of "
-				       "[%08lx:%08llx:%lx:%lx:%lx] failed with "
-				       "status %ld\n",
-				       devhandle, HV_PCI_TSBID(0, entry),
-				       npages, prot, __pa(pglist), num);
-			return -1;
+		if (mask <= DMA_BIT_MASK(32)) {
+			num = pci_sun4v_iommu_map(devhandle,
+						  HV_PCI_TSBID(0, entry),
+						  npages,
+						  prot,
+						  __pa(pglist));
+			if (unlikely(num < 0)) {
+				pr_err_ratelimited("%s: IOMMU map of [%08lx:%08llx:%lx:%lx:%lx] failed with status %ld\n",
+						   __func__,
+						   devhandle,
+						   HV_PCI_TSBID(0, entry),
+						   npages, prot, __pa(pglist),
+						   num);
+				return -1;
+			}
+		} else {
+			index_count = HV_PCI_IOTSB_INDEX_COUNT(npages, entry),
+			iotsb_num = pbm->iommu->atu->iotsb->iotsb_num;
+			ret = pci_sun4v_iotsb_map(devhandle,
+						  iotsb_num,
+						  index_count,
+						  prot,
+						  __pa(pglist),
+						  &num);
+			if (unlikely(ret != HV_EOK)) {
+				pr_err_ratelimited("%s: ATU map of [%08lx:%lx:%llx:%lx:%lx] failed with status %ld\n",
+						   __func__,
+						   devhandle, iotsb_num,
+						   index_count, prot,
+						   __pa(pglist), ret);
+				return -1;
+			}
 		}
-
 		entry += num;
 		npages -= num;
 		pglist += num;
@@ -108,19 +134,19 @@ static long iommu_batch_flush(struct iommu_batch *p)
 	return 0;
 }
 
-static inline void iommu_batch_new_entry(unsigned long entry)
+static inline void iommu_batch_new_entry(unsigned long entry, u64 mask)
 {
 	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	if (p->entry + p->npages == entry)
 		return;
 	if (p->entry != ~0UL)
-		iommu_batch_flush(p);
+		iommu_batch_flush(p, mask);
 	p->entry = entry;
 }
 
 /* Interrupts must be disabled.  */
-static inline long iommu_batch_add(u64 phys_page)
+static inline long iommu_batch_add(u64 phys_page, u64 mask)
 {
 	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
@@ -128,28 +154,31 @@ static inline long iommu_batch_add(u64 phys_page)
 
 	p->pglist[p->npages++] = phys_page;
 	if (p->npages == PGLIST_NENTS)
-		return iommu_batch_flush(p);
+		return iommu_batch_flush(p, mask);
 
 	return 0;
 }
 
 /* Interrupts must be disabled.  */
-static inline long iommu_batch_end(void)
+static inline long iommu_batch_end(u64 mask)
 {
 	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	BUG_ON(p->npages >= PGLIST_NENTS);
 
-	return iommu_batch_flush(p);
+	return iommu_batch_flush(p, mask);
 }
 
 static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 				   dma_addr_t *dma_addrp, gfp_t gfp,
 				   unsigned long attrs)
 {
+	u64 mask;
 	unsigned long flags, order, first_page, npages, n;
 	unsigned long prot = 0;
 	struct iommu *iommu;
+	struct atu *atu;
+	struct iommu_map_table *tbl;
 	struct page *page;
 	void *ret;
 	long entry;
@@ -174,14 +203,21 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 	memset((char *)first_page, 0, PAGE_SIZE << order);
 
 	iommu = dev->archdata.iommu;
+	atu = iommu->atu;
+
+	mask = dev->coherent_dma_mask;
+	if (mask <= DMA_BIT_MASK(32))
+		tbl = &iommu->tbl;
+	else
+		tbl = &atu->tbl;
 
-	entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL,
+	entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL,
 				      (unsigned long)(-1), 0);
 
 	if (unlikely(entry == IOMMU_ERROR_CODE))
 		goto range_alloc_fail;
 
-	*dma_addrp = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT));
+	*dma_addrp = (tbl->table_map_base + (entry << IO_PAGE_SHIFT));
 	ret = (void *) first_page;
 	first_page = __pa(first_page);
 
@@ -193,12 +229,12 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 			  entry);
 
 	for (n = 0; n < npages; n++) {
-		long err = iommu_batch_add(first_page + (n * PAGE_SIZE));
+		long err = iommu_batch_add(first_page + (n * PAGE_SIZE), mask);
 		if (unlikely(err < 0L))
 			goto iommu_map_fail;
 	}
 
-	if (unlikely(iommu_batch_end() < 0L))
+	if (unlikely(iommu_batch_end(mask) < 0L))
 		goto iommu_map_fail;
 
 	local_irq_restore(flags);
@@ -206,25 +242,71 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 	return ret;
 
 iommu_map_fail:
-	iommu_tbl_range_free(&iommu->tbl, *dma_addrp, npages, IOMMU_ERROR_CODE);
+	iommu_tbl_range_free(tbl, *dma_addrp, npages, IOMMU_ERROR_CODE);
 
 range_alloc_fail:
 	free_pages(first_page, order);
 	return NULL;
 }
 
-static void dma_4v_iommu_demap(void *demap_arg, unsigned long entry,
-			       unsigned long npages)
+unsigned long dma_4v_iotsb_bind(unsigned long devhandle,
+				unsigned long iotsb_num,
+				struct pci_bus *bus_dev)
+{
+	struct pci_dev *pdev;
+	unsigned long err;
+	unsigned int bus;
+	unsigned int device;
+	unsigned int fun;
+
+	list_for_each_entry(pdev, &bus_dev->devices, bus_list) {
+		if (pdev->subordinate) {
+			/* No need to bind pci bridge */
+			dma_4v_iotsb_bind(devhandle, iotsb_num,
+					  pdev->subordinate);
+		} else {
+			bus = bus_dev->number;
+			device = PCI_SLOT(pdev->devfn);
+			fun = PCI_FUNC(pdev->devfn);
+			err = pci_sun4v_iotsb_bind(devhandle, iotsb_num,
+						   HV_PCI_DEVICE_BUILD(bus,
+								       device,
+								       fun));
+
+			/* If bind fails for one device it is going to fail
+			 * for rest of the devices because we are sharing
+			 * IOTSB. So in case of failure simply return with
+			 * error.
+			 */
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static void dma_4v_iommu_demap(struct device *dev, unsigned long devhandle,
+			       dma_addr_t dvma, unsigned long iotsb_num,
+			       unsigned long entry, unsigned long npages)
 {
-	u32 devhandle = *(u32 *)demap_arg;
 	unsigned long num, flags;
+	unsigned long ret;
 
 	local_irq_save(flags);
 	do {
-		num = pci_sun4v_iommu_demap(devhandle,
-					    HV_PCI_TSBID(0, entry),
-					    npages);
-
+		if (dvma <= DMA_BIT_MASK(32)) {
+			num = pci_sun4v_iommu_demap(devhandle,
+						    HV_PCI_TSBID(0, entry),
+						    npages);
+		} else {
+			ret = pci_sun4v_iotsb_demap(devhandle, iotsb_num,
+						    entry, npages, &num);
+			if (unlikely(ret != HV_EOK)) {
+				pr_err_ratelimited("pci_iotsb_demap() failed with error: %ld\n",
+						   ret);
+			}
+		}
 		entry += num;
 		npages -= num;
 	} while (npages != 0);
@@ -236,16 +318,28 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
 {
 	struct pci_pbm_info *pbm;
 	struct iommu *iommu;
+	struct atu *atu;
+	struct iommu_map_table *tbl;
 	unsigned long order, npages, entry;
+	unsigned long iotsb_num;
 	u32 devhandle;
 
 	npages = IO_PAGE_ALIGN(size) >> IO_PAGE_SHIFT;
 	iommu = dev->archdata.iommu;
 	pbm = dev->archdata.host_controller;
+	atu = iommu->atu;
 	devhandle = pbm->devhandle;
-	entry = ((dvma - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT);
-	dma_4v_iommu_demap(&devhandle, entry, npages);
-	iommu_tbl_range_free(&iommu->tbl, dvma, npages, IOMMU_ERROR_CODE);
+
+	if (dvma <= DMA_BIT_MASK(32)) {
+		tbl = &iommu->tbl;
+		iotsb_num = 0; /* we don't care for legacy iommu */
+	} else {
+		tbl = &atu->tbl;
+		iotsb_num = atu->iotsb->iotsb_num;
+	}
+	entry = ((dvma - tbl->table_map_base) >> IO_PAGE_SHIFT);
+	dma_4v_iommu_demap(dev, devhandle, dvma, iotsb_num, entry, npages);
+	iommu_tbl_range_free(tbl, dvma, npages, IOMMU_ERROR_CODE);
 	order = get_order(size);
 	if (order < 10)
 		free_pages((unsigned long)cpu, order);
@@ -257,13 +351,17 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 				  unsigned long attrs)
 {
 	struct iommu *iommu;
+	struct atu *atu;
+	struct iommu_map_table *tbl;
+	u64 mask;
 	unsigned long flags, npages, oaddr;
 	unsigned long i, base_paddr;
-	u32 bus_addr, ret;
 	unsigned long prot;
+	dma_addr_t bus_addr, ret;
 	long entry;
 
 	iommu = dev->archdata.iommu;
+	atu = iommu->atu;
 
 	if (unlikely(direction == DMA_NONE))
 		goto bad;
@@ -272,13 +370,19 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 	npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 
-	entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL,
+	mask = *dev->dma_mask;
+	if (mask <= DMA_BIT_MASK(32))
+		tbl = &iommu->tbl;
+	else
+		tbl = &atu->tbl;
+
+	entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL,
 				      (unsigned long)(-1), 0);
 
 	if (unlikely(entry == IOMMU_ERROR_CODE))
 		goto bad;
 
-	bus_addr = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT));
+	bus_addr = (tbl->table_map_base + (entry << IO_PAGE_SHIFT));
 	ret = bus_addr | (oaddr & ~IO_PAGE_MASK);
 	base_paddr = __pa(oaddr & IO_PAGE_MASK);
 	prot = HV_PCI_MAP_ATTR_READ;
@@ -293,11 +397,11 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 	iommu_batch_start(dev, prot, entry);
 
 	for (i = 0; i < npages; i++, base_paddr += IO_PAGE_SIZE) {
-		long err = iommu_batch_add(base_paddr);
+		long err = iommu_batch_add(base_paddr, mask);
 		if (unlikely(err < 0L))
 			goto iommu_map_fail;
 	}
-	if (unlikely(iommu_batch_end() < 0L))
+	if (unlikely(iommu_batch_end(mask) < 0L))
 		goto iommu_map_fail;
 
 	local_irq_restore(flags);
@@ -310,7 +414,7 @@ bad:
 	return DMA_ERROR_CODE;
 
 iommu_map_fail:
-	iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, IOMMU_ERROR_CODE);
+	iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE);
 	return DMA_ERROR_CODE;
 }
 
@@ -320,7 +424,10 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
 {
 	struct pci_pbm_info *pbm;
 	struct iommu *iommu;
+	struct atu *atu;
+	struct iommu_map_table *tbl;
 	unsigned long npages;
+	unsigned long iotsb_num;
 	long entry;
 	u32 devhandle;
 
@@ -332,14 +439,23 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
 
 	iommu = dev->archdata.iommu;
 	pbm = dev->archdata.host_controller;
+	atu = iommu->atu;
 	devhandle = pbm->devhandle;
 
 	npages = IO_PAGE_ALIGN(bus_addr + sz) - (bus_addr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 	bus_addr &= IO_PAGE_MASK;
-	entry = (bus_addr - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT;
-	dma_4v_iommu_demap(&devhandle, entry, npages);
-	iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, IOMMU_ERROR_CODE);
+
+	if (bus_addr <= DMA_BIT_MASK(32)) {
+		iotsb_num = 0; /* we don't care for legacy iommu */
+		tbl = &iommu->tbl;
+	} else {
+		iotsb_num = atu->iotsb->iotsb_num;
+		tbl = &atu->tbl;
+	}
+	entry = (bus_addr - tbl->table_map_base) >> IO_PAGE_SHIFT;
+	dma_4v_iommu_demap(dev, devhandle, bus_addr, iotsb_num, entry, npages);
+	iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE);
 }
 
 static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
@@ -353,12 +469,17 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	unsigned long seg_boundary_size;
 	int outcount, incount, i;
 	struct iommu *iommu;
+	struct atu *atu;
+	struct iommu_map_table *tbl;
+	u64 mask;
 	unsigned long base_shift;
 	long err;
 
 	BUG_ON(direction == DMA_NONE);
 
 	iommu = dev->archdata.iommu;
+	atu = iommu->atu;
+
 	if (nelems == 0 || !iommu)
 		return 0;
 	
@@ -384,7 +505,15 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	max_seg_size = dma_get_max_seg_size(dev);
 	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
 				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
-	base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT;
+
+	mask = *dev->dma_mask;
+	if (mask <= DMA_BIT_MASK(32))
+		tbl = &iommu->tbl;
+	else
+		tbl = &atu->tbl;
+
+	base_shift = tbl->table_map_base >> IO_PAGE_SHIFT;
+
 	for_each_sg(sglist, s, nelems, i) {
 		unsigned long paddr, npages, entry, out_entry = 0, slen;
 
@@ -397,27 +526,26 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 		/* Allocate iommu entries for that segment */
 		paddr = (unsigned long) SG_ENT_PHYS_ADDRESS(s);
 		npages = iommu_num_pages(paddr, slen, IO_PAGE_SIZE);
-		entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages,
+		entry = iommu_tbl_range_alloc(dev, tbl, npages,
 					      &handle, (unsigned long)(-1), 0);
 
 		/* Handle failure */
 		if (unlikely(entry == IOMMU_ERROR_CODE)) {
-			if (printk_ratelimit())
-				printk(KERN_INFO "iommu_alloc failed, iommu %p paddr %lx"
-				       " npages %lx\n", iommu, paddr, npages);
+			pr_err_ratelimited("iommu_alloc failed, iommu %p paddr %lx npages %lx\n",
+					   tbl, paddr, npages);
 			goto iommu_map_failed;
 		}
 
-		iommu_batch_new_entry(entry);
+		iommu_batch_new_entry(entry, mask);
 
 		/* Convert entry to a dma_addr_t */
-		dma_addr = iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT);
+		dma_addr = tbl->table_map_base + (entry << IO_PAGE_SHIFT);
 		dma_addr |= (s->offset & ~IO_PAGE_MASK);
 
 		/* Insert into HW table */
 		paddr &= IO_PAGE_MASK;
 		while (npages--) {
-			err = iommu_batch_add(paddr);
+			err = iommu_batch_add(paddr, mask);
 			if (unlikely(err < 0L))
 				goto iommu_map_failed;
 			paddr += IO_PAGE_SIZE;
@@ -452,7 +580,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 		dma_next = dma_addr + slen;
 	}
 
-	err = iommu_batch_end();
+	err = iommu_batch_end(mask);
 
 	if (unlikely(err < 0L))
 		goto iommu_map_failed;
@@ -475,7 +603,7 @@ iommu_map_failed:
 			vaddr = s->dma_address & IO_PAGE_MASK;
 			npages = iommu_num_pages(s->dma_address, s->dma_length,
 						 IO_PAGE_SIZE);
-			iommu_tbl_range_free(&iommu->tbl, vaddr, npages,
+			iommu_tbl_range_free(tbl, vaddr, npages,
 					     IOMMU_ERROR_CODE);
 			/* XXX demap? XXX */
 			s->dma_address = DMA_ERROR_CODE;
@@ -496,13 +624,16 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	struct pci_pbm_info *pbm;
 	struct scatterlist *sg;
 	struct iommu *iommu;
+	struct atu *atu;
 	unsigned long flags, entry;
+	unsigned long iotsb_num;
 	u32 devhandle;
 
 	BUG_ON(direction == DMA_NONE);
 
 	iommu = dev->archdata.iommu;
 	pbm = dev->archdata.host_controller;
+	atu = iommu->atu;
 	devhandle = pbm->devhandle;
 	
 	local_irq_save(flags);
@@ -512,15 +643,24 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		dma_addr_t dma_handle = sg->dma_address;
 		unsigned int len = sg->dma_length;
 		unsigned long npages;
-		struct iommu_map_table *tbl = &iommu->tbl;
+		struct iommu_map_table *tbl;
 		unsigned long shift = IO_PAGE_SHIFT;
 
 		if (!len)
 			break;
 		npages = iommu_num_pages(dma_handle, len, IO_PAGE_SIZE);
+
+		if (dma_handle <= DMA_BIT_MASK(32)) {
+			iotsb_num = 0; /* we don't care for legacy iommu */
+			tbl = &iommu->tbl;
+		} else {
+			iotsb_num = atu->iotsb->iotsb_num;
+			tbl = &atu->tbl;
+		}
 		entry = ((dma_handle - tbl->table_map_base) >> shift);
-		dma_4v_iommu_demap(&devhandle, entry, npages);
-		iommu_tbl_range_free(&iommu->tbl, dma_handle, npages,
+		dma_4v_iommu_demap(dev, devhandle, dma_handle, iotsb_num,
+				   entry, npages);
+		iommu_tbl_range_free(tbl, dma_handle, npages,
 				     IOMMU_ERROR_CODE);
 		sg = sg_next(sg);
 	}
@@ -581,6 +721,132 @@ static unsigned long probe_existing_entries(struct pci_pbm_info *pbm,
 	return cnt;
 }
 
+static int pci_sun4v_atu_alloc_iotsb(struct pci_pbm_info *pbm)
+{
+	struct atu *atu = pbm->iommu->atu;
+	struct atu_iotsb *iotsb;
+	void *table;
+	u64 table_size;
+	u64 iotsb_num;
+	unsigned long order;
+	unsigned long err;
+
+	iotsb = kzalloc(sizeof(*iotsb), GFP_KERNEL);
+	if (!iotsb) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+	atu->iotsb = iotsb;
+
+	/* calculate size of IOTSB */
+	table_size = (atu->size / IO_PAGE_SIZE) * 8;
+	order = get_order(table_size);
+	table = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
+	if (!table) {
+		err = -ENOMEM;
+		goto table_failed;
+	}
+	iotsb->table = table;
+	iotsb->ra = __pa(table);
+	iotsb->dvma_size = atu->size;
+	iotsb->dvma_base = atu->base;
+	iotsb->table_size = table_size;
+	iotsb->page_size = IO_PAGE_SIZE;
+
+	/* configure and register IOTSB with HV */
+	err = pci_sun4v_iotsb_conf(pbm->devhandle,
+				   iotsb->ra,
+				   iotsb->table_size,
+				   iotsb->page_size,
+				   iotsb->dvma_base,
+				   &iotsb_num);
+	if (err) {
+		pr_err(PFX "pci_iotsb_conf failed error: %ld\n", err);
+		goto iotsb_conf_failed;
+	}
+	iotsb->iotsb_num = iotsb_num;
+
+	err = dma_4v_iotsb_bind(pbm->devhandle, iotsb_num, pbm->pci_bus);
+	if (err) {
+		pr_err(PFX "pci_iotsb_bind failed error: %ld\n", err);
+		goto iotsb_conf_failed;
+	}
+
+	return 0;
+
+iotsb_conf_failed:
+	free_pages((unsigned long)table, order);
+table_failed:
+	kfree(iotsb);
+out_err:
+	return err;
+}
+
+static int pci_sun4v_atu_init(struct pci_pbm_info *pbm)
+{
+	struct atu *atu = pbm->iommu->atu;
+	unsigned long err;
+	const u64 *ranges;
+	u64 map_size, num_iotte;
+	u64 dma_mask;
+	const u32 *page_size;
+	int len;
+
+	ranges = of_get_property(pbm->op->dev.of_node, "iommu-address-ranges",
+				 &len);
+	if (!ranges) {
+		pr_err(PFX "No iommu-address-ranges\n");
+		return -EINVAL;
+	}
+
+	page_size = of_get_property(pbm->op->dev.of_node, "iommu-pagesizes",
+				    NULL);
+	if (!page_size) {
+		pr_err(PFX "No iommu-pagesizes\n");
+		return -EINVAL;
+	}
+
+	/* There are 4 iommu-address-ranges supported. Each range is pair of
+	 * {base, size}. The ranges[0] and ranges[1] are 32bit address space
+	 * while ranges[2] and ranges[3] are 64bit space.  We want to use 64bit
+	 * address ranges to support 64bit addressing. Because 'size' for
+	 * address ranges[2] and ranges[3] are same we can select either of
+	 * ranges[2] or ranges[3] for mapping. However due to 'size' is too
+	 * large for OS to allocate IOTSB we are using fix size 32G
+	 * (ATU_64_SPACE_SIZE) which is more than enough for all PCIe devices
+	 * to share.
+	 */
+	atu->ranges = (struct atu_ranges *)ranges;
+	atu->base = atu->ranges[3].base;
+	atu->size = ATU_64_SPACE_SIZE;
+
+	/* Create IOTSB */
+	err = pci_sun4v_atu_alloc_iotsb(pbm);
+	if (err) {
+		pr_err(PFX "Error creating ATU IOTSB\n");
+		return err;
+	}
+
+	/* Create ATU iommu map.
+	 * One bit represents one iotte in IOTSB table.
+	 */
+	dma_mask = (roundup_pow_of_two(atu->size) - 1UL);
+	num_iotte = atu->size / IO_PAGE_SIZE;
+	map_size = num_iotte / 8;
+	atu->tbl.table_map_base = atu->base;
+	atu->dma_addr_mask = dma_mask;
+	atu->tbl.map = kzalloc(map_size, GFP_KERNEL);
+	if (!atu->tbl.map)
+		return -ENOMEM;
+
+	iommu_tbl_pool_init(&atu->tbl, num_iotte, IO_PAGE_SHIFT,
+			    NULL, false /* no large_pool */,
+			    0 /* default npools */,
+			    false /* want span boundary checking */);
+
+	return 0;
+}
+
 static int pci_sun4v_iommu_init(struct pci_pbm_info *pbm)
 {
 	static const u32 vdma_default[] = { 0x80000000, 0x80000000 };
@@ -918,6 +1184,18 @@ static int pci_sun4v_pbm_init(struct pci_pbm_info *pbm,
 
 	pci_sun4v_scan_bus(pbm, &op->dev);
 
+	/* if atu_init fails its not complete failure.
+	 * we can still continue using legacy iommu.
+	 */
+	if (pbm->iommu->atu) {
+		err = pci_sun4v_atu_init(pbm);
+		if (err) {
+			kfree(pbm->iommu->atu);
+			pbm->iommu->atu = NULL;
+			pr_err(PFX "ATU init failed, err=%d\n", err);
+		}
+	}
+
 	pbm->next = pci_pbm_root;
 	pci_pbm_root = pbm;
 
@@ -931,8 +1209,10 @@ static int pci_sun4v_probe(struct platform_device *op)
 	struct pci_pbm_info *pbm;
 	struct device_node *dp;
 	struct iommu *iommu;
+	struct atu *atu;
 	u32 devhandle;
 	int i, err = -ENODEV;
+	static bool hv_atu = true;
 
 	dp = op->dev.of_node;
 
@@ -954,6 +1234,19 @@ static int pci_sun4v_probe(struct platform_device *op)
 		pr_info(PFX "Registered hvapi major[%lu] minor[%lu]\n",
 			vpci_major, vpci_minor);
 
+		err = sun4v_hvapi_register(HV_GRP_ATU, vatu_major, &vatu_minor);
+		if (err) {
+			/* don't return an error if we fail to register the
+			 * ATU group, but ATU hcalls won't be available.
+			 */
+			hv_atu = false;
+			pr_err(PFX "Could not register hvapi ATU err=%d\n",
+			       err);
+		} else {
+			pr_info(PFX "Registered hvapi ATU major[%lu] minor[%lu]\n",
+				vatu_major, vatu_minor);
+		}
+
 		dma_ops = &sun4v_dma_ops;
 	}
 
@@ -991,6 +1284,14 @@ static int pci_sun4v_probe(struct platform_device *op)
 	}
 
 	pbm->iommu = iommu;
+	iommu->atu = NULL;
+	if (hv_atu) {
+		atu = kzalloc(sizeof(*atu), GFP_KERNEL);
+		if (!atu)
+			pr_err(PFX "Could not allocate atu\n");
+		else
+			iommu->atu = atu;
+	}
 
 	err = pci_sun4v_pbm_init(pbm, op, devhandle);
 	if (err)
@@ -1001,6 +1302,7 @@ static int pci_sun4v_probe(struct platform_device *op)
 	return 0;
 
 out_free_iommu:
+	kfree(iommu->atu);
 	kfree(pbm->iommu);
 
 out_free_controller:

arch/sparc/kernel/pci_sun4v.h

@@ -89,4 +89,25 @@ unsigned long pci_sun4v_msg_setvalid(unsigned long devhandle,
 				     unsigned long msinum,
 				     unsigned long valid);
 
+/* Sun4v HV IOMMU v2 APIs */
+unsigned long pci_sun4v_iotsb_conf(unsigned long devhandle,
+				   unsigned long ra,
+				   unsigned long table_size,
+				   unsigned long page_size,
+				   unsigned long dvma_base,
+				   u64 *iotsb_num);
+unsigned long pci_sun4v_iotsb_bind(unsigned long devhandle,
+				   unsigned long iotsb_num,
+				   unsigned int pci_device);
+unsigned long pci_sun4v_iotsb_map(unsigned long devhandle,
+				  unsigned long iotsb_num,
+				  unsigned long iotsb_index_iottes,
+				  unsigned long io_attributes,
+				  unsigned long io_page_list_pa,
+				  long *mapped);
+unsigned long pci_sun4v_iotsb_demap(unsigned long devhandle,
+				    unsigned long iotsb_num,
+				    unsigned long iotsb_index,
+				    unsigned long iottes,
+				    unsigned long *demapped);
 #endif /* !(_PCI_SUN4V_H) */

arch/sparc/kernel/pci_sun4v_asm.S

@@ -360,3 +360,71 @@ ENTRY(pci_sun4v_msg_setvalid)
 	 mov	%o0, %o0
 ENDPROC(pci_sun4v_msg_setvalid)
 
+	/*
+	 * %o0:	devhandle
+	 * %o1:	r_addr
+	 * %o2:	size
+	 * %o3:	pagesize
+	 * %o4:	virt
+	 * %o5: &iotsb_num/&iotsb_handle
+	 *
+	 * returns %o0:	status
+	 *         %o1:	iotsb_num/iotsb_handle
+	 */
+ENTRY(pci_sun4v_iotsb_conf)
+	mov	%o5, %g1
+	mov	HV_FAST_PCI_IOTSB_CONF, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 stx	%o1, [%g1]
+ENDPROC(pci_sun4v_iotsb_conf)
+
+	/*
+	 * %o0:	devhandle
+	 * %o1:	iotsb_num/iotsb_handle
+	 * %o2:	pci_device
+	 *
+	 * returns %o0:	status
+	 */
+ENTRY(pci_sun4v_iotsb_bind)
+	mov	HV_FAST_PCI_IOTSB_BIND, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(pci_sun4v_iotsb_bind)
+
+	/*
+	 * %o0:	devhandle
+	 * %o1:	iotsb_num/iotsb_handle
+	 * %o2:	index_count
+	 * %o3:	iotte_attributes
+	 * %o4:	io_page_list_p
+	 * %o5: &mapped
+	 *
+	 * returns %o0:	status
+	 *         %o1:	#mapped
+	 */
+ENTRY(pci_sun4v_iotsb_map)
+	mov	%o5, %g1
+	mov	HV_FAST_PCI_IOTSB_MAP, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 stx	%o1, [%g1]
+ENDPROC(pci_sun4v_iotsb_map)
+
+	/*
+	 * %o0:	devhandle
+	 * %o1:	iotsb_num/iotsb_handle
+	 * %o2:	iotsb_index
+	 * %o3:	#iottes
+	 * %o4: &demapped
+	 *
+	 * returns %o0:	status
+	 *         %o1:	#demapped
+	 */
+ENTRY(pci_sun4v_iotsb_demap)
+	mov	HV_FAST_PCI_IOTSB_DEMAP, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 stx	%o1, [%o4]
+ENDPROC(pci_sun4v_iotsb_demap)

arch/sparc/kernel/signal_32.c

@@ -89,7 +89,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!invalid_frame_pointer(sf, sizeof(*sf)))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv_and_exit;
 
 	if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
@@ -150,7 +150,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 
 	synchronize_user_stack();
 	sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP];
-	if (!invalid_frame_pointer(sf, sizeof(*sf)))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv;
 
 	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))

arch/sparc/mm/init_64.c

@@ -802,8 +802,10 @@ struct mdesc_mblock {
 };
 static struct mdesc_mblock *mblocks;
 static int num_mblocks;
+static int find_numa_node_for_addr(unsigned long pa,
+				   struct node_mem_mask *pnode_mask);
 
-static unsigned long ra_to_pa(unsigned long addr)
+static unsigned long __init ra_to_pa(unsigned long addr)
 {
 	int i;
 
@@ -819,8 +821,11 @@ static unsigned long ra_to_pa(unsigned long addr)
 	return addr;
 }
 
-static int find_node(unsigned long addr)
+static int __init find_node(unsigned long addr)
 {
+	static bool search_mdesc = true;
+	static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL };
+	static int last_index;
 	int i;
 
 	addr = ra_to_pa(addr);
@@ -830,13 +835,30 @@ static int find_node(unsigned long addr)
 		if ((addr & p->mask) == p->val)
 			return i;
 	}
-	/* The following condition has been observed on LDOM guests.*/
-	WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node"
-		" rule. Some physical memory will be owned by node 0.");
-	return 0;
+	/* The following condition has been observed on LDOM guests because
+	 * node_masks only contains the best latency mask and value.
+	 * LDOM guest's mdesc can contain a single latency group to
+	 * cover multiple address range. Print warning message only if the
+	 * address cannot be found in node_masks nor mdesc.
+	 */
+	if ((search_mdesc) &&
+	    ((addr & last_mem_mask.mask) != last_mem_mask.val)) {
+		/* find the available node in the mdesc */
+		last_index = find_numa_node_for_addr(addr, &last_mem_mask);
+		numadbg("find_node: latency group for address 0x%lx is %d\n",
+			addr, last_index);
+		if ((last_index < 0) || (last_index >= num_node_masks)) {
+			/* WARN_ONCE() and use default group 0 */
+			WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0.");
+			search_mdesc = false;
+			last_index = 0;
+		}
+	}
+
+	return last_index;
 }
 
-static u64 memblock_nid_range(u64 start, u64 end, int *nid)
+static u64 __init memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = find_node(start);
 	start += PAGE_SIZE;
@@ -1160,6 +1182,41 @@ int __node_distance(int from, int to)
 	return numa_latency[from][to];
 }
 
+static int find_numa_node_for_addr(unsigned long pa,
+				   struct node_mem_mask *pnode_mask)
+{
+	struct mdesc_handle *md = mdesc_grab();
+	u64 node, arc;
+	int i = 0;
+
+	node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
+	if (node == MDESC_NODE_NULL)
+		goto out;
+
+	mdesc_for_each_node_by_name(md, node, "group") {
+		mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) {
+			u64 target = mdesc_arc_target(md, arc);
+			struct mdesc_mlgroup *m = find_mlgroup(target);
+
+			if (!m)
+				continue;
+			if ((pa & m->mask) == m->match) {
+				if (pnode_mask) {
+					pnode_mask->mask = m->mask;
+					pnode_mask->val = m->match;
+				}
+				mdesc_release(md);
+				return i;
+			}
+		}
+		i++;
+	}
+
+out:
+	mdesc_release(md);
+	return -1;
+}
+
 static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
 {
 	int i;

arch/tile/include/asm/cache.h

@@ -61,4 +61,7 @@
  */
 #define __write_once __read_mostly
 
+/* __ro_after_init is the generic name for the tile arch __write_once. */
+#define __ro_after_init __read_mostly
+
 #endif /* _ASM_TILE_CACHE_H */

arch/x86/crypto/aesni-intel_glue.c

@@ -888,7 +888,7 @@ static int helper_rfc4106_encrypt(struct aead_request *req)
 	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
 	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
 	struct scatter_walk src_sg_walk;
-	struct scatter_walk dst_sg_walk;
+	struct scatter_walk dst_sg_walk = {};
 	unsigned int i;
 
 	/* Assuming we are supporting rfc4106 64-bit extended */
@@ -968,7 +968,7 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
 	u8 authTag[16];
 	struct scatter_walk src_sg_walk;
-	struct scatter_walk dst_sg_walk;
+	struct scatter_walk dst_sg_walk = {};
 	unsigned int i;
 
 	if (unlikely(req->assoclen != 16 && req->assoclen != 20))

arch/x86/events/intel/uncore_snb.c

@@ -8,8 +8,12 @@
 #define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
 #define PCI_DEVICE_ID_INTEL_BDW_IMC	0x1604
-#define PCI_DEVICE_ID_INTEL_SKL_IMC	0x191f
-#define PCI_DEVICE_ID_INTEL_SKL_U_IMC	0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_U_IMC	0x1904
+#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC	0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC	0x1900
+#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC	0x1910
+#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC	0x190f
+#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC	0x191f
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -616,13 +620,29 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = {
 
 static const struct pci_device_id skl_uncore_pci_ids[] = {
 	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_Y_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
 	{ /* IMC */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_U_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HD_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SD_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 
 	{ /* end: all zeroes */ },
 };
@@ -666,8 +686,12 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
 	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
 	IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver),    /* 5th Gen Core U */
-	IMC_DEV(SKL_IMC, &skl_uncore_pci_driver),    /* 6th Gen Core */
+	IMC_DEV(SKL_Y_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core Y */
 	IMC_DEV(SKL_U_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core U */
+	IMC_DEV(SKL_HD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Dual Core */
+	IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Quad Core */
+	IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Dual Core */
+	IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Quad Core */
 	{  /* end marker */ }
 };
 

arch/x86/include/asm/intel-mid.h

@@ -17,6 +17,7 @@
 
 extern int intel_mid_pci_init(void);
 extern int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state);
+extern pci_power_t intel_mid_pci_get_power_state(struct pci_dev *pdev);
 
 extern void intel_mid_pwr_power_off(void);
 

arch/x86/kernel/apm_32.c

@@ -1042,8 +1042,11 @@ static int apm_get_power_status(u_short *status, u_short *bat, u_short *life)
 
 	if (apm_info.get_power_status_broken)
 		return APM_32_UNSUPPORTED;
-	if (apm_bios_call(&call))
+	if (apm_bios_call(&call)) {
+		if (!call.err)
+			return APM_NO_ERROR;
 		return call.err;
+	}
 	*status = call.ebx;
 	*bat = call.ecx;
 	if (apm_info.get_power_status_swabinminutes) {

arch/x86/kernel/cpu/amd.c

@@ -347,7 +347,6 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 #ifdef CONFIG_SMP
 	unsigned bits;
 	int cpu = smp_processor_id();
-	unsigned int socket_id, core_complex_id;
 
 	bits = c->x86_coreid_bits;
 	/* Low order bits define the core id (index of core in socket) */
@@ -365,10 +364,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 	 if (c->x86 != 0x17 || !cpuid_edx(0x80000006))
 		return;
 
-	socket_id	= (c->apicid >> bits) - 1;
-	core_complex_id	= (c->apicid & ((1 << bits) - 1)) >> 3;
-
-	per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id;
+	per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
 #endif
 }
 

arch/x86/kernel/cpu/common.c

@@ -978,6 +978,35 @@ static void x86_init_cache_qos(struct cpuinfo_x86 *c)
 	}
 }
 
+/*
+ * The physical to logical package id mapping is initialized from the
+ * acpi/mptables information. Make sure that CPUID actually agrees with
+ * that.
+ */
+static void sanitize_package_id(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned int pkg, apicid, cpu = smp_processor_id();
+
+	apicid = apic->cpu_present_to_apicid(cpu);
+	pkg = apicid >> boot_cpu_data.x86_coreid_bits;
+
+	if (apicid != c->initial_apicid) {
+		pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x CPUID: %x\n",
+		       cpu, apicid, c->initial_apicid);
+		c->initial_apicid = apicid;
+	}
+	if (pkg != c->phys_proc_id) {
+		pr_err(FW_BUG "CPU%u: Using firmware package id %u instead of %u\n",
+		       cpu, pkg, c->phys_proc_id);
+		c->phys_proc_id = pkg;
+	}
+	c->logical_proc_id = topology_phys_to_logical_pkg(pkg);
+#else
+	c->logical_proc_id = 0;
+#endif
+}
+
 /*
  * This does the hard work of actually picking apart the CPU stuff...
  */
@@ -1103,8 +1132,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 #ifdef CONFIG_NUMA
 	numa_add_cpu(smp_processor_id());
 #endif
-	/* The boot/hotplug time assigment got cleared, restore it */
-	c->logical_proc_id = topology_phys_to_logical_pkg(c->phys_proc_id);
+	sanitize_package_id(c);
 }
 
 /*

arch/x86/kvm/irq_comm.c

@@ -156,6 +156,16 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 }
 
 
+static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
+		    struct kvm *kvm, int irq_source_id, int level,
+		    bool line_status)
+{
+	if (!level)
+		return -1;
+
+	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
+}
+
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 			      struct kvm *kvm, int irq_source_id, int level,
 			      bool line_status)
@@ -163,18 +173,26 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 	struct kvm_lapic_irq irq;
 	int r;
 
-	if (unlikely(e->type != KVM_IRQ_ROUTING_MSI))
-		return -EWOULDBLOCK;
+	switch (e->type) {
+	case KVM_IRQ_ROUTING_HV_SINT:
+		return kvm_hv_set_sint(e, kvm, irq_source_id, level,
+				       line_status);
 
-	if (kvm_msi_route_invalid(kvm, e))
-		return -EINVAL;
+	case KVM_IRQ_ROUTING_MSI:
+		if (kvm_msi_route_invalid(kvm, e))
+			return -EINVAL;
 
-	kvm_set_msi_irq(kvm, e, &irq);
+		kvm_set_msi_irq(kvm, e, &irq);
 
-	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
-		return r;
-	else
-		return -EWOULDBLOCK;
+		if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
+			return r;
+		break;
+
+	default:
+		break;
+	}
+
+	return -EWOULDBLOCK;
 }
 
 int kvm_request_irq_source_id(struct kvm *kvm)
@@ -254,16 +272,6 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
-static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
-		    struct kvm *kvm, int irq_source_id, int level,
-		    bool line_status)
-{
-	if (!level)
-		return -1;
-
-	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
-}
-
 int kvm_set_routing_entry(struct kvm *kvm,
 			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
@@ -423,18 +431,6 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
-int kvm_arch_set_irq(struct kvm_kernel_irq_routing_entry *irq, struct kvm *kvm,
-		     int irq_source_id, int level, bool line_status)
-{
-	switch (irq->type) {
-	case KVM_IRQ_ROUTING_HV_SINT:
-		return kvm_hv_set_sint(irq, kvm, irq_source_id, level,
-				       line_status);
-	default:
-		return -EWOULDBLOCK;
-	}
-}
-
 void kvm_arch_irq_routing_update(struct kvm *kvm)
 {
 	kvm_hv_irq_routing_update(kvm);

arch/x86/kvm/x86.c

@@ -210,7 +210,18 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	struct kvm_shared_msrs *locals
 		= container_of(urn, struct kvm_shared_msrs, urn);
 	struct kvm_shared_msr_values *values;
+	unsigned long flags;
 
+	/*
+	 * Disabling irqs at this point since the following code could be
+	 * interrupted and executed through kvm_arch_hardware_disable()
+	 */
+	local_irq_save(flags);
+	if (locals->registered) {
+		locals->registered = false;
+		user_return_notifier_unregister(urn);
+	}
+	local_irq_restore(flags);
 	for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
 		values = &locals->values[slot];
 		if (values->host != values->curr) {
@@ -218,8 +229,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 			values->curr = values->host;
 		}
 	}
-	locals->registered = false;
-	user_return_notifier_unregister(urn);
 }
 
 static void shared_msr_update(unsigned slot, u32 msr)
@@ -1724,18 +1733,23 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 
 static u64 __get_kvmclock_ns(struct kvm *kvm)
 {
-	struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
 	struct kvm_arch *ka = &kvm->arch;
-	s64 ns;
+	struct pvclock_vcpu_time_info hv_clock;
 
-	if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) {
-		u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc());
-		ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc);
-	} else {
-		ns = ktime_get_boot_ns() + ka->kvmclock_offset;
+	spin_lock(&ka->pvclock_gtod_sync_lock);
+	if (!ka->use_master_clock) {
+		spin_unlock(&ka->pvclock_gtod_sync_lock);
+		return ktime_get_boot_ns() + ka->kvmclock_offset;
 	}
 
-	return ns;
+	hv_clock.tsc_timestamp = ka->master_cycle_now;
+	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
+	spin_unlock(&ka->pvclock_gtod_sync_lock);
+
+	kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
+			   &hv_clock.tsc_shift,
+			   &hv_clock.tsc_to_system_mul);
+	return __pvclock_read_cycles(&hv_clock, rdtsc());
 }
 
 u64 get_kvmclock_ns(struct kvm *kvm)
@@ -2596,7 +2610,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
 	case KVM_CAP_XEN_HVM:
-	case KVM_CAP_ADJUST_CLOCK:
 	case KVM_CAP_VCPU_EVENTS:
 	case KVM_CAP_HYPERV:
 	case KVM_CAP_HYPERV_VAPIC:
@@ -2623,6 +2636,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #endif
 		r = 1;
 		break;
+	case KVM_CAP_ADJUST_CLOCK:
+		r = KVM_CLOCK_TSC_STABLE;
+		break;
 	case KVM_CAP_X86_SMM:
 		/* SMBASE is usually relocated above 1M on modern chipsets,
 		 * and SMM handlers might indeed rely on 4G segment limits,
@@ -3415,6 +3431,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	};
 	case KVM_SET_VAPIC_ADDR: {
 		struct kvm_vapic_addr va;
+		int idx;
 
 		r = -EINVAL;
 		if (!lapic_in_kernel(vcpu))
@@ -3422,7 +3439,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&va, argp, sizeof va))
 			goto out;
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_X86_SETUP_MCE: {
@@ -4103,9 +4122,11 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		struct kvm_clock_data user_ns;
 		u64 now_ns;
 
-		now_ns = get_kvmclock_ns(kvm);
+		local_irq_disable();
+		now_ns = __get_kvmclock_ns(kvm);
 		user_ns.clock = now_ns;
-		user_ns.flags = 0;
+		user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0;
+		local_irq_enable();
 		memset(&user_ns.pad, 0, sizeof(user_ns.pad));
 
 		r = -EFAULT;

arch/x86/platform/efi/efi.c

@@ -861,7 +861,7 @@ static void __init __efi_enter_virtual_mode(void)
 	int count = 0, pg_shift = 0;
 	void *new_memmap = NULL;
 	efi_status_t status;
-	phys_addr_t pa;
+	unsigned long pa;
 
 	efi.systab = NULL;
 

arch/x86/platform/efi/efi_64.c

@@ -31,6 +31,7 @@
 #include <linux/io.h>
 #include <linux/reboot.h>
 #include <linux/slab.h>
+#include <linux/ucs2_string.h>
 
 #include <asm/setup.h>
 #include <asm/page.h>
@@ -211,6 +212,35 @@ void efi_sync_low_kernel_mappings(void)
 	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
 }
 
+/*
+ * Wrapper for slow_virt_to_phys() that handles NULL addresses.
+ */
+static inline phys_addr_t
+virt_to_phys_or_null_size(void *va, unsigned long size)
+{
+	bool bad_size;
+
+	if (!va)
+		return 0;
+
+	if (virt_addr_valid(va))
+		return virt_to_phys(va);
+
+	/*
+	 * A fully aligned variable on the stack is guaranteed not to
+	 * cross a page bounary. Try to catch strings on the stack by
+	 * checking that 'size' is a power of two.
+	 */
+	bad_size = size > PAGE_SIZE || !is_power_of_2(size);
+
+	WARN_ON(!IS_ALIGNED((unsigned long)va, size) || bad_size);
+
+	return slow_virt_to_phys(va);
+}
+
+#define virt_to_phys_or_null(addr)				\
+	virt_to_phys_or_null_size((addr), sizeof(*(addr)))
+
 int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
 	unsigned long pfn, text;
@@ -494,8 +524,8 @@ static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 
 	spin_lock(&rtc_lock);
 
-	phys_tm = virt_to_phys(tm);
-	phys_tc = virt_to_phys(tc);
+	phys_tm = virt_to_phys_or_null(tm);
+	phys_tc = virt_to_phys_or_null(tc);
 
 	status = efi_thunk(get_time, phys_tm, phys_tc);
 
@@ -511,7 +541,7 @@ static efi_status_t efi_thunk_set_time(efi_time_t *tm)
 
 	spin_lock(&rtc_lock);
 
-	phys_tm = virt_to_phys(tm);
+	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(set_time, phys_tm);
 
@@ -529,9 +559,9 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
 
 	spin_lock(&rtc_lock);
 
-	phys_enabled = virt_to_phys(enabled);
-	phys_pending = virt_to_phys(pending);
-	phys_tm = virt_to_phys(tm);
+	phys_enabled = virt_to_phys_or_null(enabled);
+	phys_pending = virt_to_phys_or_null(pending);
+	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(get_wakeup_time, phys_enabled,
 			     phys_pending, phys_tm);
@@ -549,7 +579,7 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 
 	spin_lock(&rtc_lock);
 
-	phys_tm = virt_to_phys(tm);
+	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(set_wakeup_time, enabled, phys_tm);
 
@@ -558,6 +588,10 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 	return status;
 }
 
+static unsigned long efi_name_size(efi_char16_t *name)
+{
+	return ucs2_strsize(name, EFI_VAR_NAME_LEN) + 1;
+}
 
 static efi_status_t
 efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
@@ -567,11 +601,11 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
 	u32 phys_name, phys_vendor, phys_attr;
 	u32 phys_data_size, phys_data;
 
-	phys_data_size = virt_to_phys(data_size);
-	phys_vendor = virt_to_phys(vendor);
-	phys_name = virt_to_phys(name);
-	phys_attr = virt_to_phys(attr);
-	phys_data = virt_to_phys(data);
+	phys_data_size = virt_to_phys_or_null(data_size);
+	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+	phys_attr = virt_to_phys_or_null(attr);
+	phys_data = virt_to_phys_or_null_size(data, *data_size);
 
 	status = efi_thunk(get_variable, phys_name, phys_vendor,
 			   phys_attr, phys_data_size, phys_data);
@@ -586,9 +620,9 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 	u32 phys_name, phys_vendor, phys_data;
 	efi_status_t status;
 
-	phys_name = virt_to_phys(name);
-	phys_vendor = virt_to_phys(vendor);
-	phys_data = virt_to_phys(data);
+	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_data = virt_to_phys_or_null_size(data, data_size);
 
 	/* If data_size is > sizeof(u32) we've got problems */
 	status = efi_thunk(set_variable, phys_name, phys_vendor,
@@ -605,9 +639,9 @@ efi_thunk_get_next_variable(unsigned long *name_size,
 	efi_status_t status;
 	u32 phys_name_size, phys_name, phys_vendor;
 
-	phys_name_size = virt_to_phys(name_size);
-	phys_vendor = virt_to_phys(vendor);
-	phys_name = virt_to_phys(name);
+	phys_name_size = virt_to_phys_or_null(name_size);
+	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_name = virt_to_phys_or_null_size(name, *name_size);
 
 	status = efi_thunk(get_next_variable, phys_name_size,
 			   phys_name, phys_vendor);
@@ -621,7 +655,7 @@ efi_thunk_get_next_high_mono_count(u32 *count)
 	efi_status_t status;
 	u32 phys_count;
 
-	phys_count = virt_to_phys(count);
+	phys_count = virt_to_phys_or_null(count);
 	status = efi_thunk(get_next_high_mono_count, phys_count);
 
 	return status;
@@ -633,7 +667,7 @@ efi_thunk_reset_system(int reset_type, efi_status_t status,
 {
 	u32 phys_data;
 
-	phys_data = virt_to_phys(data);
+	phys_data = virt_to_phys_or_null_size(data, data_size);
 
 	efi_thunk(reset_system, reset_type, status, data_size, phys_data);
 }
@@ -661,9 +695,9 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	phys_storage = virt_to_phys(storage_space);
-	phys_remaining = virt_to_phys(remaining_space);
-	phys_max = virt_to_phys(max_variable_size);
+	phys_storage = virt_to_phys_or_null(storage_space);
+	phys_remaining = virt_to_phys_or_null(remaining_space);
+	phys_max = virt_to_phys_or_null(max_variable_size);
 
 	status = efi_thunk(query_variable_info, attr, phys_storage,
 			   phys_remaining, phys_max);

arch/x86/platform/intel-mid/pwr.c

@@ -272,6 +272,25 @@ int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state)
 }
 EXPORT_SYMBOL_GPL(intel_mid_pci_set_power_state);
 
+pci_power_t intel_mid_pci_get_power_state(struct pci_dev *pdev)
+{
+	struct mid_pwr *pwr = midpwr;
+	int id, reg, bit;
+	u32 power;
+
+	if (!pwr || !pwr->available)
+		return PCI_UNKNOWN;
+
+	id = intel_mid_pwr_get_lss_id(pdev);
+	if (id < 0)
+		return PCI_UNKNOWN;
+
+	reg = (id * LSS_PWS_BITS) / 32;
+	bit = (id * LSS_PWS_BITS) % 32;
+	power = mid_pwr_get_state(pwr, reg);
+	return (__force pci_power_t)((power >> bit) & 3);
+}
+
 void intel_mid_pwr_power_off(void)
 {
 	struct mid_pwr *pwr = midpwr;

arch/x86/purgatory/Makefile

@@ -16,6 +16,7 @@ KCOV_INSTRUMENT := n
 
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large
 KBUILD_CFLAGS += -m$(BITS)
+KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)

arch/xtensa/include/uapi/asm/unistd.h

@@ -767,7 +767,14 @@ __SYSCALL(346, sys_preadv2, 6)
 #define __NR_pwritev2				347
 __SYSCALL(347, sys_pwritev2, 6)
 
-#define __NR_syscall_count			348
+#define __NR_pkey_mprotect			348
+__SYSCALL(348, sys_pkey_mprotect, 4)
+#define __NR_pkey_alloc				349
+__SYSCALL(349, sys_pkey_alloc, 2)
+#define __NR_pkey_free				350
+__SYSCALL(350, sys_pkey_free, 1)
+
+#define __NR_syscall_count			351
 
 /*
  * sysxtensa syscall handler

arch/xtensa/kernel/time.c

@@ -172,10 +172,11 @@ void __init time_init(void)
 {
 	of_clk_init(NULL);
 #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
-	printk("Calibrating CPU frequency ");
+	pr_info("Calibrating CPU frequency ");
 	calibrate_ccount();
-	printk("%d.%02d MHz\n", (int)ccount_freq/1000000,
-			(int)(ccount_freq/10000)%100);
+	pr_cont("%d.%02d MHz\n",
+		(int)ccount_freq / 1000000,
+		(int)(ccount_freq / 10000) % 100);
 #else
 	ccount_freq = CONFIG_XTENSA_CPU_CLOCK*1000000UL;
 #endif
@@ -210,9 +211,8 @@ irqreturn_t timer_interrupt(int irq, void *dev_id)
 void calibrate_delay(void)
 {
 	loops_per_jiffy = ccount_freq / HZ;
-	printk("Calibrating delay loop (skipped)... "
-	       "%lu.%02lu BogoMIPS preset\n",
-	       loops_per_jiffy/(1000000/HZ),
-	       (loops_per_jiffy/(10000/HZ)) % 100);
+	pr_info("Calibrating delay loop (skipped)... %lu.%02lu BogoMIPS preset\n",
+		loops_per_jiffy / (1000000 / HZ),
+		(loops_per_jiffy / (10000 / HZ)) % 100);
 }
 #endif

arch/xtensa/kernel/traps.c

@@ -465,26 +465,25 @@ void show_regs(struct pt_regs * regs)
 
 	for (i = 0; i < 16; i++) {
 		if ((i % 8) == 0)
-			printk(KERN_INFO "a%02d:", i);
-		printk(KERN_CONT " %08lx", regs->areg[i]);
+			pr_info("a%02d:", i);
+		pr_cont(" %08lx", regs->areg[i]);
 	}
-	printk(KERN_CONT "\n");
-
-	printk("pc: %08lx, ps: %08lx, depc: %08lx, excvaddr: %08lx\n",
-	       regs->pc, regs->ps, regs->depc, regs->excvaddr);
-	printk("lbeg: %08lx, lend: %08lx lcount: %08lx, sar: %08lx\n",
-	       regs->lbeg, regs->lend, regs->lcount, regs->sar);
+	pr_cont("\n");
+	pr_info("pc: %08lx, ps: %08lx, depc: %08lx, excvaddr: %08lx\n",
+		regs->pc, regs->ps, regs->depc, regs->excvaddr);
+	pr_info("lbeg: %08lx, lend: %08lx lcount: %08lx, sar: %08lx\n",
+		regs->lbeg, regs->lend, regs->lcount, regs->sar);
 	if (user_mode(regs))
-		printk("wb: %08lx, ws: %08lx, wmask: %08lx, syscall: %ld\n",
-		       regs->windowbase, regs->windowstart, regs->wmask,
-		       regs->syscall);
+		pr_cont("wb: %08lx, ws: %08lx, wmask: %08lx, syscall: %ld\n",
+			regs->windowbase, regs->windowstart, regs->wmask,
+			regs->syscall);
 }
 
 static int show_trace_cb(struct stackframe *frame, void *data)
 {
 	if (kernel_text_address(frame->pc)) {
-		printk(" [<%08lx>] ", frame->pc);
-		print_symbol("%s\n", frame->pc);
+		pr_cont(" [<%08lx>]", frame->pc);
+		print_symbol(" %s\n", frame->pc);
 	}
 	return 0;
 }
@@ -494,19 +493,13 @@ void show_trace(struct task_struct *task, unsigned long *sp)
 	if (!sp)
 		sp = stack_pointer(task);
 
-	printk("Call Trace:");
-#ifdef CONFIG_KALLSYMS
-	printk("\n");
-#endif
+	pr_info("Call Trace:\n");
 	walk_stackframe(sp, show_trace_cb, NULL);
-	printk("\n");
+#ifndef CONFIG_KALLSYMS
+	pr_cont("\n");
+#endif
 }
 
-/*
- * This routine abuses get_user()/put_user() to reference pointers
- * with at least a bit of error checking ...
- */
-
 static int kstack_depth_to_print = 24;
 
 void show_stack(struct task_struct *task, unsigned long *sp)
@@ -518,52 +511,29 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 		sp = stack_pointer(task);
 	stack = sp;
 
-	printk("\nStack: ");
+	pr_info("Stack:\n");
 
 	for (i = 0; i < kstack_depth_to_print; i++) {
 		if (kstack_end(sp))
 			break;
-		if (i && ((i % 8) == 0))
-			printk("\n       ");
-		printk("%08lx ", *sp++);
+		pr_cont(" %08lx", *sp++);
+		if (i % 8 == 7)
+			pr_cont("\n");
 	}
-	printk("\n");
 	show_trace(task, stack);
 }
 
-void show_code(unsigned int *pc)
-{
-	long i;
-
-	printk("\nCode:");
-
-	for(i = -3 ; i < 6 ; i++) {
-		unsigned long insn;
-		if (__get_user(insn, pc + i)) {
-			printk(" (Bad address in pc)\n");
-			break;
-		}
-		printk("%c%08lx%c",(i?' ':'<'),insn,(i?' ':'>'));
-	}
-}
-
 DEFINE_SPINLOCK(die_lock);
 
 void die(const char * str, struct pt_regs * regs, long err)
 {
 	static int die_counter;
-	int nl = 0;
 
 	console_verbose();
 	spin_lock_irq(&die_lock);
 
-	printk("%s: sig: %ld [#%d]\n", str, err, ++die_counter);
-#ifdef CONFIG_PREEMPT
-	printk("PREEMPT ");
-	nl = 1;
-#endif
-	if (nl)
-		printk("\n");
+	pr_info("%s: sig: %ld [#%d]%s\n", str, err, ++die_counter,
+		IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "");
 	show_regs(regs);
 	if (!user_mode(regs))
 		show_stack(NULL, (unsigned long*)regs->areg[1]);