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

Conflicts:
	drivers/net/ethernet/emulex/benet/be_main.c
	drivers/net/ethernet/intel/igb/igb_main.c
	drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
	include/net/scm.h
	net/batman-adv/routing.c
	net/ipv4/tcp_input.c

The e{uid,gid} --> {uid,gid} credentials fix conflicted with the
cleanup in net-next to now pass cred structs around.

The be2net driver had a bug fix in 'net' that overlapped with the VLAN
interface changes by Patrick McHardy in net-next.

An IGB conflict existed because in 'net' the build_skb() support was
reverted, and in 'net-next' there was a comment style fix within that
code.

Several batman-adv conflicts were resolved by making sure that all
calls to batadv_is_my_mac() are changed to have a new bat_priv first
argument.

Eric Dumazet's TS ECR fix in TCP in 'net' conflicted with the F-RTO
rewrite in 'net-next', mostly overlapping changes.

Thanks to Stephen Rothwell and Antonio Quartulli for help with several
of these merge resolutions.

Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/DocBook/device-drivers.tmpl

@@ -227,7 +227,7 @@ X!Isound/sound_firmware.c
   <chapter id="uart16x50">
      <title>16x50 UART Driver</title>
 !Edrivers/tty/serial/serial_core.c
-!Edrivers/tty/serial/8250/8250.c
+!Edrivers/tty/serial/8250/8250_core.c
   </chapter>
 
   <chapter id="fbdev">

Documentation/kernel-parameters.txt

@@ -596,9 +596,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			is selected automatically. Check
 			Documentation/kdump/kdump.txt for further details.
 
-	crashkernel_low=size[KMG]
-			[KNL, x86] parts under 4G.
-
 	crashkernel=range1:size1[,range2:size2,...][@offset]
 			[KNL] Same as above, but depends on the memory
 			in the running system. The syntax of range is
@@ -606,6 +603,26 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			a memory unit (amount[KMG]). See also
 			Documentation/kdump/kdump.txt for an example.
 
+	crashkernel=size[KMG],high
+			[KNL, x86_64] range could be above 4G. Allow kernel
+			to allocate physical memory region from top, so could
+			be above 4G if system have more than 4G ram installed.
+			Otherwise memory region will be allocated below 4G, if
+			available.
+			It will be ignored if crashkernel=X is specified.
+	crashkernel=size[KMG],low
+			[KNL, x86_64] range under 4G. When crashkernel=X,high
+			is passed, kernel could allocate physical memory region
+			above 4G, that cause second kernel crash on system
+			that require some amount of low memory, e.g. swiotlb
+			requires at least 64M+32K low memory.  Kernel would
+			try to allocate 72M below 4G automatically.
+			This one let user to specify own low range under 4G
+			for second kernel instead.
+			0: to disable low allocation.
+			It will be ignored when crashkernel=X,high is not used
+			or memory reserved is below 4G.
+
 	cs89x0_dma=	[HW,NET]
 			Format: <dma>
 
@@ -788,6 +805,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	edd=		[EDD]
 			Format: {"off" | "on" | "skip[mbr]"}
 
+	efi_no_storage_paranoia [EFI; X86]
+			Using this parameter you can use more than 50% of
+			your efi variable storage. Use this parameter only if
+			you are really sure that your UEFI does sane gc and
+			fulfills the spec otherwise your board may brick.
+
 	eisa_irq_edge=	[PARISC,HW]
 			See header of drivers/parisc/eisa.c.
 

Documentation/scsi/LICENSE.qla2xxx

@@ -1,4 +1,4 @@
-Copyright (c) 2003-2012 QLogic Corporation
+Copyright (c) 2003-2013 QLogic Corporation
 QLogic Linux FC-FCoE Driver
 
 This program includes a device driver for Linux 3.x.

MAINTAINERS

@@ -4941,6 +4941,12 @@ W:	logfs.org
 S:	Maintained
 F:	fs/logfs/
 
+LPC32XX MACHINE SUPPORT
+M:	Roland Stigge <stigge@antcom.de>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/mach-lpc32xx/
+
 LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI)
 M:	Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com>
 M:	Sreekanth Reddy <Sreekanth.Reddy@lsi.com>
@@ -6627,7 +6633,7 @@ S:	Supported
 F:	fs/reiserfs/
 
 REGISTER MAP ABSTRACTION
-M:	Mark Brown <broonie@opensource.wolfsonmicro.com>
+M:	Mark Brown <broonie@kernel.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regmap.git
 S:	Supported
 F:	drivers/base/regmap/
@@ -7375,7 +7381,7 @@ F:	sound/
 
 SOUND - SOC LAYER / DYNAMIC AUDIO POWER MANAGEMENT (ASoC)
 M:	Liam Girdwood <lgirdwood@gmail.com>
-M:	Mark Brown <broonie@opensource.wolfsonmicro.com>
+M:	Mark Brown <broonie@kernel.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 W:	http://alsa-project.org/main/index.php/ASoC
@@ -7464,7 +7470,7 @@ F:	drivers/clk/spear/
 
 SPI SUBSYSTEM
 M:	Grant Likely <grant.likely@secretlab.ca>
-M:	Mark Brown <broonie@opensource.wolfsonmicro.com>
+M:	Mark Brown <broonie@kernel.org>
 L:	spi-devel-general@lists.sourceforge.net
 Q:	http://patchwork.kernel.org/project/spi-devel-general/list/
 T:	git git://git.secretlab.ca/git/linux-2.6.git
@@ -8709,7 +8715,7 @@ F:	drivers/scsi/vmw_pvscsi.h
 
 VOLTAGE AND CURRENT REGULATOR FRAMEWORK
 M:	Liam Girdwood <lrg@ti.com>
-M:	Mark Brown <broonie@opensource.wolfsonmicro.com>
+M:	Mark Brown <broonie@kernel.org>
 W:	http://opensource.wolfsonmicro.com/node/15
 W:	http://www.slimlogic.co.uk/?p=48
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lrg/regulator.git

Makefile

@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc8
 NAME = Unicycling Gorilla
 
 # *DOCUMENTATION*
@@ -513,7 +513,8 @@ ifeq ($(KBUILD_EXTMOD),)
 # Carefully list dependencies so we do not try to build scripts twice
 # in parallel
 PHONY += scripts
-scripts: scripts_basic include/config/auto.conf include/config/tristate.conf
+scripts: scripts_basic include/config/auto.conf include/config/tristate.conf \
+	 asm-generic
 	$(Q)$(MAKE) $(build)=$(@)
 
 # Objects we will link into vmlinux / subdirs we need to visit

arch/alpha/Makefile

@@ -12,7 +12,7 @@ NM := $(NM) -B
 
 LDFLAGS_vmlinux	:= -static -N #-relax
 CHECKFLAGS	+= -D__alpha__ -m64
-cflags-y	:= -pipe -mno-fp-regs -ffixed-8 -msmall-data
+cflags-y	:= -pipe -mno-fp-regs -ffixed-8
 cflags-y	+= $(call cc-option, -fno-jump-tables)
 
 cpuflags-$(CONFIG_ALPHA_EV4)		:= -mcpu=ev4

arch/alpha/include/asm/floppy.h

@@ -26,7 +26,7 @@
 #define fd_disable_irq()        disable_irq(FLOPPY_IRQ)
 #define fd_cacheflush(addr,size) /* nothing */
 #define fd_request_irq()        request_irq(FLOPPY_IRQ, floppy_interrupt,\
-					    IRQF_DISABLED, "floppy", NULL)
+					    0, "floppy", NULL)
 #define fd_free_irq()           free_irq(FLOPPY_IRQ, NULL)
 
 #ifdef CONFIG_PCI

arch/alpha/kernel/irq.c

@@ -117,13 +117,6 @@ handle_irq(int irq)
 		return;
 	}
 
-	/*
-	 * From here we must proceed with IPL_MAX. Note that we do not
-	 * explicitly enable interrupts afterwards - some MILO PALcode
-	 * (namely LX164 one) seems to have severe problems with RTI
-	 * at IPL 0.
-	 */
-	local_irq_disable();
 	irq_enter();
 	generic_handle_irq_desc(irq, desc);
 	irq_exit();

arch/alpha/kernel/irq_alpha.c

@@ -45,6 +45,14 @@ do_entInt(unsigned long type, unsigned long vector,
 	  unsigned long la_ptr, struct pt_regs *regs)
 {
 	struct pt_regs *old_regs;
+
+	/*
+	 * Disable interrupts during IRQ handling.
+	 * Note that there is no matching local_irq_enable() due to
+	 * severe problems with RTI at IPL0 and some MILO PALcode
+	 * (namely LX164).
+	 */
+	local_irq_disable();
 	switch (type) {
 	case 0:
 #ifdef CONFIG_SMP
@@ -62,7 +70,6 @@ do_entInt(unsigned long type, unsigned long vector,
 	  {
 		long cpu;
 
-		local_irq_disable();
 		smp_percpu_timer_interrupt(regs);
 		cpu = smp_processor_id();
 		if (cpu != boot_cpuid) {
@@ -222,7 +229,6 @@ process_mcheck_info(unsigned long vector, unsigned long la_ptr,
 
 struct irqaction timer_irqaction = {
 	.handler	= timer_interrupt,
-	.flags		= IRQF_DISABLED,
 	.name		= "timer",
 };
 

arch/alpha/kernel/sys_nautilus.c

@@ -188,6 +188,10 @@ nautilus_machine_check(unsigned long vector, unsigned long la_ptr)
 extern void free_reserved_mem(void *, void *);
 extern void pcibios_claim_one_bus(struct pci_bus *);
 
+static struct resource irongate_io = {
+	.name	= "Irongate PCI IO",
+	.flags	= IORESOURCE_IO,
+};
 static struct resource irongate_mem = {
 	.name	= "Irongate PCI MEM",
 	.flags	= IORESOURCE_MEM,
@@ -209,6 +213,7 @@ nautilus_init_pci(void)
 
 	irongate = pci_get_bus_and_slot(0, 0);
 	bus->self = irongate;
+	bus->resource[0] = &irongate_io;
 	bus->resource[1] = &irongate_mem;
 
 	pci_bus_size_bridges(bus);

arch/alpha/kernel/sys_titan.c

@@ -280,15 +280,15 @@ titan_late_init(void)
 	 * all reported to the kernel as machine checks, so the handler
 	 * is a nop so it can be called to count the individual events.
 	 */
-	titan_request_irq(63+16, titan_intr_nop, IRQF_DISABLED,
+	titan_request_irq(63+16, titan_intr_nop, 0,
 		    "CChip Error", NULL);
-	titan_request_irq(62+16, titan_intr_nop, IRQF_DISABLED,
+	titan_request_irq(62+16, titan_intr_nop, 0,
 		    "PChip 0 H_Error", NULL);
-	titan_request_irq(61+16, titan_intr_nop, IRQF_DISABLED,
+	titan_request_irq(61+16, titan_intr_nop, 0,
 		    "PChip 1 H_Error", NULL);
-	titan_request_irq(60+16, titan_intr_nop, IRQF_DISABLED,
+	titan_request_irq(60+16, titan_intr_nop, 0,
 		    "PChip 0 C_Error", NULL);
-	titan_request_irq(59+16, titan_intr_nop, IRQF_DISABLED,
+	titan_request_irq(59+16, titan_intr_nop, 0,
 		    "PChip 1 C_Error", NULL);
 
 	/* 
@@ -348,9 +348,9 @@ privateer_init_pci(void)
 	 * Hook a couple of extra err interrupts that the
 	 * common titan code won't.
 	 */
-	titan_request_irq(53+16, titan_intr_nop, IRQF_DISABLED,
+	titan_request_irq(53+16, titan_intr_nop, 0,
 		    "NMI", NULL);
-	titan_request_irq(50+16, titan_intr_nop, IRQF_DISABLED,
+	titan_request_irq(50+16, titan_intr_nop, 0,
 		    "Temperature Warning", NULL);
 
 	/*

arch/arc/include/asm/irqflags.h

@@ -39,7 +39,7 @@ static inline long arch_local_irq_save(void)
 	"	flag.nz %0		\n"
 	: "=r"(temp), "=r"(flags)
 	: "n"((STATUS_E1_MASK | STATUS_E2_MASK))
-	: "cc");
+	: "memory", "cc");
 
 	return flags;
 }
@@ -53,7 +53,8 @@ static inline void arch_local_irq_restore(unsigned long flags)
 	__asm__ __volatile__(
 	"	flag %0			\n"
 	:
-	: "r"(flags));
+	: "r"(flags)
+	: "memory");
 }
 
 /*
@@ -73,7 +74,8 @@ static inline void arch_local_irq_disable(void)
 	"	and %0, %0, %1		\n"
 	"	flag %0			\n"
 	: "=&r"(temp)
-	: "n"(~(STATUS_E1_MASK | STATUS_E2_MASK)));
+	: "n"(~(STATUS_E1_MASK | STATUS_E2_MASK))
+	: "memory");
 }
 
 /*
@@ -85,7 +87,9 @@ static inline long arch_local_save_flags(void)
 
 	__asm__ __volatile__(
 	"	lr  %0, [status32]	\n"
-	: "=&r"(temp));
+	: "=&r"(temp)
+	:
+	: "memory");
 
 	return temp;
 }

arch/arm/boot/dts/imx28-m28evk.dts

@@ -152,7 +152,6 @@
 			i2c0: i2c@80058000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&i2c0_pins_a>;
-				clock-frequency = <400000>;
 				status = "okay";
 
 				sgtl5000: codec@0a {

arch/arm/boot/dts/imx28-sps1.dts

@@ -70,7 +70,6 @@
 			i2c0: i2c@80058000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&i2c0_pins_a>;
-				clock-frequency = <400000>;
 				status = "okay";
 
 				rtc: rtc@51 {

arch/arm/boot/dts/imx6qdl.dtsi

@@ -91,6 +91,7 @@
 			compatible = "arm,cortex-a9-twd-timer";
 			reg = <0x00a00600 0x20>;
 			interrupts = <1 13 0xf01>;
+			clocks = <&clks 15>;
 		};
 
 		L2: l2-cache@00a02000 {

arch/arm/boot/dts/kirkwood-iomega_ix2_200.dts

@@ -96,11 +96,11 @@
 				marvell,function = "gpio";
 			};
 			pmx_led_rebuild_brt_ctrl_1: pmx-led-rebuild-brt-ctrl-1 {
-				marvell,pins = "mpp44";
+				marvell,pins = "mpp46";
 				marvell,function = "gpio";
 			};
 			pmx_led_rebuild_brt_ctrl_2: pmx-led-rebuild-brt-ctrl-2 {
-				marvell,pins = "mpp45";
+				marvell,pins = "mpp47";
 				marvell,function = "gpio";
 			};
 
@@ -157,14 +157,14 @@
 			gpios = <&gpio0 16 0>;
 			linux,default-trigger = "default-on";
 		};
-		health_led1 {
+		rebuild_led {
+			label = "status:white:rebuild_led";
+			gpios = <&gpio1 4 0>;
+		};
+		health_led {
 			label = "status:red:health_led";
 			gpios = <&gpio1 5 0>;
 		};
-		health_led2 {
-			label = "status:white:health_led";
-			gpios = <&gpio1 4 0>;
-		};
 		backup_led {
 			label = "status:blue:backup_led";
 			gpios = <&gpio0 15 0>;

arch/arm/include/asm/glue-cache.h

@@ -19,14 +19,6 @@
 #undef _CACHE
 #undef MULTI_CACHE
 
-#if defined(CONFIG_CPU_CACHE_V3)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE v3
-# endif
-#endif
-
 #if defined(CONFIG_CPU_CACHE_V4)
 # ifdef _CACHE
 #  define MULTI_CACHE 1

arch/arm/include/asm/hardware/iop3xx.h

@@ -37,7 +37,7 @@ extern int iop3xx_get_init_atu(void);
  * IOP3XX processor registers
  */
 #define IOP3XX_PERIPHERAL_PHYS_BASE	0xffffe000
-#define IOP3XX_PERIPHERAL_VIRT_BASE	0xfeffe000
+#define IOP3XX_PERIPHERAL_VIRT_BASE	0xfedfe000
 #define IOP3XX_PERIPHERAL_SIZE		0x00002000
 #define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\
 					IOP3XX_PERIPHERAL_SIZE - 1)

arch/arm/include/asm/pgtable-3level.h

@@ -111,7 +111,7 @@
 #define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */
 #define L_PTE_S2_MT_WRITEBACK	 (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */
 #define L_PTE_S2_RDONLY		 (_AT(pteval_t, 1) << 6)   /* HAP[1]   */
-#define L_PTE_S2_RDWR		 (_AT(pteval_t, 2) << 6)   /* HAP[2:1] */
+#define L_PTE_S2_RDWR		 (_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
 
 /*
  * Hyp-mode PL2 PTE definitions for LPAE.

arch/arm/include/asm/tlbflush.h

@@ -14,7 +14,6 @@
 
 #include <asm/glue.h>
 
-#define TLB_V3_PAGE	(1 << 0)
 #define TLB_V4_U_PAGE	(1 << 1)
 #define TLB_V4_D_PAGE	(1 << 2)
 #define TLB_V4_I_PAGE	(1 << 3)
@@ -22,7 +21,6 @@
 #define TLB_V6_D_PAGE	(1 << 5)
 #define TLB_V6_I_PAGE	(1 << 6)
 
-#define TLB_V3_FULL	(1 << 8)
 #define TLB_V4_U_FULL	(1 << 9)
 #define TLB_V4_D_FULL	(1 << 10)
 #define TLB_V4_I_FULL	(1 << 11)
@@ -52,7 +50,6 @@
  *	=============
  *
  *	We have the following to choose from:
- *	  v3    - ARMv3
  *	  v4    - ARMv4 without write buffer
  *	  v4wb  - ARMv4 with write buffer without I TLB flush entry instruction
  *	  v4wbi - ARMv4 with write buffer with I TLB flush entry instruction
@@ -330,7 +327,6 @@ static inline void local_flush_tlb_all(void)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
 	tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
 	tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
 	tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
@@ -351,9 +347,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
+	if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
 		if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
-			tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
 			tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
 			tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
 			tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
@@ -385,9 +380,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
+	if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
 	    cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
-		tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr);
 		tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
 		tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr);
 		tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr);
@@ -418,7 +412,6 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr);
 	tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
 	tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
 	tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);

arch/arm/kernel/hw_breakpoint.c

@@ -1043,7 +1043,7 @@ static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata dbg_cpu_pm_nb = {
+static struct notifier_block dbg_cpu_pm_nb = {
 	.notifier_call = dbg_cpu_pm_notify,
 };
 

arch/arm/kernel/perf_event.c

@@ -253,7 +253,10 @@ validate_event(struct pmu_hw_events *hw_events,
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct pmu *leader_pmu = event->group_leader->pmu;
 
-	if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
+	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+		return 1;
+
+	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
 		return 1;
 
 	return armpmu->get_event_idx(hw_events, event) >= 0;

arch/arm/kernel/sched_clock.c

@@ -45,12 +45,12 @@ static u32 notrace jiffy_sched_clock_read(void)
 
 static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
 
-static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 {
 	return (cyc * mult) >> shift;
 }
 
-static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask)
+static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
 {
 	u64 epoch_ns;
 	u32 epoch_cyc;

arch/arm/kernel/setup.c

@@ -56,7 +56,6 @@
 #include <asm/virt.h>
 
 #include "atags.h"
-#include "tcm.h"
 
 
 #if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE)
@@ -798,8 +797,6 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_crashkernel();
 
-	tcm_init();
-
 #ifdef CONFIG_MULTI_IRQ_HANDLER
 	handle_arch_irq = mdesc->handle_irq;
 #endif

arch/arm/kernel/tcm.c

@@ -17,7 +17,6 @@
 #include <asm/mach/map.h>
 #include <asm/memory.h>
 #include <asm/system_info.h>
-#include "tcm.h"
 
 static struct gen_pool *tcm_pool;
 static bool dtcm_present;

arch/arm/kvm/arm.c

@@ -201,6 +201,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 		break;
 	case KVM_CAP_ARM_SET_DEVICE_ADDR:
 		r = 1;
+		break;
 	case KVM_CAP_NR_VCPUS:
 		r = num_online_cpus();
 		break;

arch/arm/kvm/coproc.c

@@ -79,11 +79,11 @@ static bool access_dcsw(struct kvm_vcpu *vcpu,
 	u32 val;
 	int cpu;
 
-	cpu = get_cpu();
-
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p);
 
+	cpu = get_cpu();
+
 	cpumask_setall(&vcpu->arch.require_dcache_flush);
 	cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush);
 

arch/arm/mach-highbank/hotplug.c

@@ -28,13 +28,11 @@ extern void secondary_startup(void);
  */
 void __ref highbank_cpu_die(unsigned int cpu)
 {
-	flush_cache_all();
-
 	highbank_set_cpu_jump(cpu, phys_to_virt(0));
-	highbank_set_core_pwr();
 
-	cpu_do_idle();
+	flush_cache_louis();
+	highbank_set_core_pwr();
 
-	/* We should never return from idle */
-	panic("highbank: cpu %d unexpectedly exit from shutdown\n", cpu);
+	while (1)
+		cpu_do_idle();
 }

arch/arm/mach-imx/clk-imx35.c

@@ -257,6 +257,7 @@ int __init mx35_clocks_init(void)
 	clk_register_clkdev(clk[wdog_gate], NULL, "imx2-wdt.0");
 	clk_register_clkdev(clk[nfc_div], NULL, "imx25-nand.0");
 	clk_register_clkdev(clk[csi_gate], NULL, "mx3-camera.0");
+	clk_register_clkdev(clk[admux_gate], "audmux", NULL);
 
 	clk_prepare_enable(clk[spba_gate]);
 	clk_prepare_enable(clk[gpio1_gate]);
@@ -265,6 +266,7 @@ int __init mx35_clocks_init(void)
 	clk_prepare_enable(clk[iim_gate]);
 	clk_prepare_enable(clk[emi_gate]);
 	clk_prepare_enable(clk[max_gate]);
+	clk_prepare_enable(clk[iomuxc_gate]);
 
 	/*
 	 * SCC is needed to boot via mmc after a watchdog reset. The clock code

arch/arm/mach-imx/clk-imx6q.c

@@ -115,7 +115,7 @@ static const char *gpu2d_core_sels[]	= { "axi", "pll3_usb_otg", "pll2_pfd0_352m"
 static const char *gpu3d_core_sels[]	= { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd2_396m", };
 static const char *gpu3d_shader_sels[] = { "mmdc_ch0_axi", "pll3_usb_otg", "pll2_pfd1_594m", "pll2_pfd9_720m", };
 static const char *ipu_sels[]		= { "mmdc_ch0_axi", "pll2_pfd2_396m", "pll3_120m", "pll3_pfd1_540m", };
-static const char *ldb_di_sels[]	= { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_pfd1_540m", };
+static const char *ldb_di_sels[]	= { "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "mmdc_ch1_axi", "pll3_usb_otg", };
 static const char *ipu_di_pre_sels[]	= { "mmdc_ch0_axi", "pll3_usb_otg", "pll5_video", "pll2_pfd0_352m", "pll2_pfd2_396m", "pll3_pfd1_540m", };
 static const char *ipu1_di0_sels[]	= { "ipu1_di0_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", };
 static const char *ipu1_di1_sels[]	= { "ipu1_di1_pre", "dummy", "dummy", "ldb_di0", "ldb_di1", };
@@ -443,7 +443,6 @@ int __init mx6q_clocks_init(void)
 
 	clk_register_clkdev(clk[gpt_ipg], "ipg", "imx-gpt.0");
 	clk_register_clkdev(clk[gpt_ipg_per], "per", "imx-gpt.0");
-	clk_register_clkdev(clk[twd], NULL, "smp_twd");
 	clk_register_clkdev(clk[cko1_sel], "cko1_sel", NULL);
 	clk_register_clkdev(clk[ahb], "ahb", NULL);
 	clk_register_clkdev(clk[cko1], "cko1", NULL);

arch/arm/mach-kirkwood/board-iomega_ix2_200.c

@@ -20,10 +20,15 @@ static struct mv643xx_eth_platform_data iomega_ix2_200_ge00_data = {
 	.duplex         = DUPLEX_FULL,
 };
 
+static struct mv643xx_eth_platform_data iomega_ix2_200_ge01_data = {
+        .phy_addr       = MV643XX_ETH_PHY_ADDR(11),
+};
+
 void __init iomega_ix2_200_init(void)
 {
 	/*
 	 * Basic setup. Needs to be called early.
 	 */
-	kirkwood_ge01_init(&iomega_ix2_200_ge00_data);
+	kirkwood_ge00_init(&iomega_ix2_200_ge00_data);
+	kirkwood_ge01_init(&iomega_ix2_200_ge01_data);
 }

arch/arm/mach-mvebu/irq-armada-370-xp.c

@@ -61,7 +61,6 @@ static struct irq_domain *armada_370_xp_mpic_domain;
  */
 static void armada_370_xp_irq_mask(struct irq_data *d)
 {
-#ifdef CONFIG_SMP
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 
 	if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ)
@@ -70,15 +69,10 @@ static void armada_370_xp_irq_mask(struct irq_data *d)
 	else
 		writel(hwirq, per_cpu_int_base +
 				ARMADA_370_XP_INT_SET_MASK_OFFS);
-#else
-	writel(irqd_to_hwirq(d),
-	       per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS);
-#endif
 }
 
 static void armada_370_xp_irq_unmask(struct irq_data *d)
 {
-#ifdef CONFIG_SMP
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
 
 	if (hwirq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ)
@@ -87,10 +81,6 @@ static void armada_370_xp_irq_unmask(struct irq_data *d)
 	else
 		writel(hwirq, per_cpu_int_base +
 				ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
-#else
-	writel(irqd_to_hwirq(d),
-	       per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
-#endif
 }
 
 #ifdef CONFIG_SMP
@@ -146,7 +136,11 @@ static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
 				      unsigned int virq, irq_hw_number_t hw)
 {
 	armada_370_xp_irq_mask(irq_get_irq_data(virq));
-	writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS);
+	if (hw != ARMADA_370_XP_TIMER0_PER_CPU_IRQ)
+		writel(hw, per_cpu_int_base +
+			ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+	else
+		writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS);
 	irq_set_status_flags(virq, IRQ_LEVEL);
 
 	if (hw == ARMADA_370_XP_TIMER0_PER_CPU_IRQ) {

arch/arm/mach-s3c24xx/include/mach/irqs.h

@@ -188,10 +188,8 @@
 
 #if defined(CONFIG_CPU_S3C2416)
 #define NR_IRQS (IRQ_S3C2416_I2S1 + 1)
-#elif defined(CONFIG_CPU_S3C2443)
-#define NR_IRQS (IRQ_S3C2443_AC97+1)
 #else
-#define NR_IRQS (IRQ_S3C2440_AC97+1)
+#define NR_IRQS (IRQ_S3C2443_AC97 + 1)
 #endif
 
 /* compatibility define. */

arch/arm/mach-s3c24xx/irq.c

@@ -500,7 +500,7 @@ struct s3c_irq_intc *s3c24xx_init_intc(struct device_node *np,
 		base = (void *)0xfd000000;
 
 		intc->reg_mask = base + 0xa4;
-		intc->reg_pending = base + 0x08;
+		intc->reg_pending = base + 0xa8;
 		irq_num = 20;
 		irq_start = S3C2410_IRQ(32);
 		irq_offset = 4;

arch/arm/mm/Kconfig

@@ -43,7 +43,7 @@ config CPU_ARM740T
 	depends on !MMU
 	select CPU_32v4T
 	select CPU_ABRT_LV4T
-	select CPU_CACHE_V3	# although the core is v4t
+	select CPU_CACHE_V4
 	select CPU_CP15_MPU
 	select CPU_PABRT_LEGACY
 	help
@@ -469,9 +469,6 @@ config CPU_PABRT_V7
 	bool
 
 # The cache model
-config CPU_CACHE_V3
-	bool
-
 config CPU_CACHE_V4
 	bool
 

arch/arm/mm/Makefile

@@ -33,7 +33,6 @@ obj-$(CONFIG_CPU_PABRT_LEGACY)	+= pabort-legacy.o
 obj-$(CONFIG_CPU_PABRT_V6)	+= pabort-v6.o
 obj-$(CONFIG_CPU_PABRT_V7)	+= pabort-v7.o
 
-obj-$(CONFIG_CPU_CACHE_V3)	+= cache-v3.o
 obj-$(CONFIG_CPU_CACHE_V4)	+= cache-v4.o
 obj-$(CONFIG_CPU_CACHE_V4WT)	+= cache-v4wt.o
 obj-$(CONFIG_CPU_CACHE_V4WB)	+= cache-v4wb.o

arch/arm/mm/cache-feroceon-l2.c

@@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override)
 	outer_cache.inv_range = feroceon_l2_inv_range;
 	outer_cache.clean_range = feroceon_l2_clean_range;
 	outer_cache.flush_range = feroceon_l2_flush_range;
+	outer_cache.inv_all = l2_inv_all;
 
 	enable_l2();
 

arch/arm/mm/cache-v3.S

@@ -1,137 +0,0 @@
-/*
- *  linux/arch/arm/mm/cache-v3.S
- *
- *  Copyright (C) 1997-2002 Russell king
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/page.h>
-#include "proc-macros.S"
-
-/*
- *	flush_icache_all()
- *
- *	Unconditionally clean and invalidate the entire icache.
- */
-ENTRY(v3_flush_icache_all)
-	mov	pc, lr
-ENDPROC(v3_flush_icache_all)
-
-/*
- *	flush_user_cache_all()
- *
- *	Invalidate all cache entries in a particular address
- *	space.
- *
- *	- mm	- mm_struct describing address space
- */
-ENTRY(v3_flush_user_cache_all)
-	/* FALLTHROUGH */
-/*
- *	flush_kern_cache_all()
- *
- *	Clean and invalidate the entire cache.
- */
-ENTRY(v3_flush_kern_cache_all)
-	/* FALLTHROUGH */
-
-/*
- *	flush_user_cache_range(start, end, flags)
- *
- *	Invalidate a range of cache entries in the specified
- *	address space.
- *
- *	- start - start address (may not be aligned)
- *	- end	- end address (exclusive, may not be aligned)
- *	- flags	- vma_area_struct flags describing address space
- */
-ENTRY(v3_flush_user_cache_range)
-	mov	ip, #0
-	mcreq	p15, 0, ip, c7, c0, 0		@ flush ID cache
-	mov	pc, lr
-
-/*
- *	coherent_kern_range(start, end)
- *
- *	Ensure coherency between the Icache and the Dcache in the
- *	region described by start.  If you have non-snooping
- *	Harvard caches, you need to implement this function.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_coherent_kern_range)
-	/* FALLTHROUGH */
-
-/*
- *	coherent_user_range(start, end)
- *
- *	Ensure coherency between the Icache and the Dcache in the
- *	region described by start.  If you have non-snooping
- *	Harvard caches, you need to implement this function.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_coherent_user_range)
-	mov	r0, #0
-	mov	pc, lr
-
-/*
- *	flush_kern_dcache_area(void *page, size_t size)
- *
- *	Ensure no D cache aliasing occurs, either with itself or
- *	the I cache
- *
- *	- addr	- kernel address
- *	- size	- region size
- */
-ENTRY(v3_flush_kern_dcache_area)
-	/* FALLTHROUGH */
-
-/*
- *	dma_flush_range(start, end)
- *
- *	Clean and invalidate the specified virtual address range.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_dma_flush_range)
-	mov	r0, #0
-	mcr	p15, 0, r0, c7, c0, 0		@ flush ID cache
-	mov	pc, lr
-
-/*
- *	dma_unmap_area(start, size, dir)
- *	- start	- kernel virtual start address
- *	- size	- size of region
- *	- dir	- DMA direction
- */
-ENTRY(v3_dma_unmap_area)
-	teq	r2, #DMA_TO_DEVICE
-	bne	v3_dma_flush_range
-	/* FALLTHROUGH */
-
-/*
- *	dma_map_area(start, size, dir)
- *	- start	- kernel virtual start address
- *	- size	- size of region
- *	- dir	- DMA direction
- */
-ENTRY(v3_dma_map_area)
-	mov	pc, lr
-ENDPROC(v3_dma_unmap_area)
-ENDPROC(v3_dma_map_area)
-
-	.globl	v3_flush_kern_cache_louis
-	.equ	v3_flush_kern_cache_louis, v3_flush_kern_cache_all
-
-	__INITDATA
-
-	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
-	define_cache_functions v3

arch/arm/mm/cache-v4.S

@@ -58,7 +58,7 @@ ENTRY(v4_flush_kern_cache_all)
 ENTRY(v4_flush_user_cache_range)
 #ifdef CONFIG_CPU_CP15
 	mov	ip, #0
-	mcreq	p15, 0, ip, c7, c7, 0		@ flush ID cache
+	mcr	p15, 0, ip, c7, c7, 0		@ flush ID cache
 	mov	pc, lr
 #else
 	/* FALLTHROUGH */

arch/arm/mm/mmu.c

@@ -34,6 +34,7 @@
 #include <asm/mach/pci.h>
 
 #include "mm.h"
+#include "tcm.h"
 
 /*
  * empty_zero_page is a special page that is used for
@@ -1277,6 +1278,7 @@ void __init paging_init(struct machine_desc *mdesc)
 	dma_contiguous_remap();
 	devicemaps_init(mdesc);
 	kmap_init();
+	tcm_init();
 
 	top_pmd = pmd_off_k(0xffff0000);
 

arch/arm/mm/proc-arm740.S

@@ -77,24 +77,27 @@ __arm740_setup:
 	mcr	p15, 0, r0, c6,	c0		@ set area 0, default
 
 	ldr	r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM
-	ldr	r1, =(CONFIG_DRAM_SIZE >> 12)	@ size of RAM (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
+	ldr	r3, =(CONFIG_DRAM_SIZE >> 12)	@ size of RAM (must be >= 4KB)
+	mov	r4, #10				@ 11 is the minimum (4KB)
+1:	add	r4, r4, #1			@ area size *= 2
+	movs	r3, r3, lsr #1
 	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the area register value
+	orr	r0, r0, r4, lsl #1		@ the area register value
 	orr	r0, r0, #1			@ set enable bit
 	mcr	p15, 0, r0, c6,	c1		@ set area 1, RAM
 
 	ldr	r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH
-	ldr	r1, =(CONFIG_FLASH_SIZE >> 12)	@ size of FLASH (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
+	ldr	r3, =(CONFIG_FLASH_SIZE >> 12)	@ size of FLASH (must be >= 4KB)
+	cmp	r3, #0
+	moveq	r0, #0
+	beq	2f
+	mov	r4, #10				@ 11 is the minimum (4KB)
+1:	add	r4, r4, #1			@ area size *= 2
+	movs	r3, r3, lsr #1
 	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the area register value
+	orr	r0, r0, r4, lsl #1		@ the area register value
 	orr	r0, r0, #1			@ set enable bit
-	mcr	p15, 0, r0, c6,	c2		@ set area 2, ROM/FLASH
+2:	mcr	p15, 0, r0, c6,	c2		@ set area 2, ROM/FLASH
 
 	mov	r0, #0x06
 	mcr	p15, 0, r0, c2, c0		@ Region 1&2 cacheable
@@ -137,13 +140,14 @@ __arm740_proc_info:
 	.long	0x41807400
 	.long	0xfffffff0
 	.long	0
+	.long	0
 	b	__arm740_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
-	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT
+	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT
 	.long	cpu_arm740_name
 	.long	arm740_processor_functions
 	.long	0
 	.long	0
-	.long	v3_cache_fns			@ cache model
+	.long	v4_cache_fns			@ cache model
 	.size	__arm740_proc_info, . - __arm740_proc_info

arch/arm/mm/proc-arm920.S

@@ -387,7 +387,7 @@ ENTRY(cpu_arm920_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm920_suspend_size
 .equ	cpu_arm920_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_arm920_do_suspend)
 	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ PID

arch/arm/mm/proc-arm926.S

@@ -402,7 +402,7 @@ ENTRY(cpu_arm926_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm926_suspend_size
 .equ	cpu_arm926_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_arm926_do_suspend)
 	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ PID

arch/arm/mm/proc-mohawk.S

@@ -350,7 +350,7 @@ ENTRY(cpu_mohawk_set_pte_ext)
 
 .globl	cpu_mohawk_suspend_size
 .equ	cpu_mohawk_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_mohawk_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode

arch/arm/mm/proc-sa1100.S

@@ -172,7 +172,7 @@ ENTRY(cpu_sa1100_set_pte_ext)
 
 .globl	cpu_sa1100_suspend_size
 .equ	cpu_sa1100_suspend_size, 4 * 3
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_sa1100_do_suspend)
 	stmfd	sp!, {r4 - r6, lr}
 	mrc	p15, 0, r4, c3, c0, 0		@ domain ID

arch/arm/mm/proc-syms.c

@@ -17,7 +17,9 @@
 
 #ifndef MULTI_CPU
 EXPORT_SYMBOL(cpu_dcache_clean_area);
+#ifdef CONFIG_MMU
 EXPORT_SYMBOL(cpu_set_pte_ext);
+#endif
 #else
 EXPORT_SYMBOL(processor);
 #endif

arch/arm/mm/proc-v6.S

@@ -138,7 +138,7 @@ ENTRY(cpu_v6_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */
 .globl	cpu_v6_suspend_size
 .equ	cpu_v6_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v6_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID

arch/arm/mm/proc-xsc3.S

@@ -413,7 +413,7 @@ ENTRY(cpu_xsc3_set_pte_ext)
 
 .globl	cpu_xsc3_suspend_size
 .equ	cpu_xsc3_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_xsc3_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode

arch/arm/mm/proc-xscale.S

@@ -528,7 +528,7 @@ ENTRY(cpu_xscale_set_pte_ext)
 
 .globl	cpu_xscale_suspend_size
 .equ	cpu_xscale_suspend_size, 4 * 6
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_xscale_do_suspend)
 	stmfd	sp!, {r4 - r9, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode

arch/avr32/include/asm/io.h

@@ -165,6 +165,10 @@ BUILDIO_IOPORT(l, u32)
 #define readw_be			__raw_readw
 #define readl_be			__raw_readl
 
+#define writeb_relaxed			writeb
+#define writew_relaxed			writew
+#define writel_relaxed			writel
+
 #define writeb_be			__raw_writeb
 #define writew_be			__raw_writew
 #define writel_be			__raw_writel

arch/c6x/include/asm/irqflags.h

@@ -27,7 +27,7 @@ static inline unsigned long arch_local_save_flags(void)
 /* set interrupt enabled status */
 static inline void arch_local_irq_restore(unsigned long flags)
 {
-	asm volatile (" mvc .s2 %0,CSR\n" : : "b"(flags));
+	asm volatile (" mvc .s2 %0,CSR\n" : : "b"(flags) : "memory");
 }
 
 /* unconditionally enable interrupts */

arch/ia64/kernel/palinfo.c

@@ -849,17 +849,6 @@ static palinfo_entry_t palinfo_entries[]={
 
 #define NR_PALINFO_ENTRIES	(int) ARRAY_SIZE(palinfo_entries)
 
-/*
- * this array is used to keep track of the proc entries we create. This is
- * required in the module mode when we need to remove all entries. The procfs code
- * does not do recursion of deletion
- *
- * Notes:
- *	- +1 accounts for the cpuN directory entry in /proc/pal
- */
-#define NR_PALINFO_PROC_ENTRIES	(NR_CPUS*(NR_PALINFO_ENTRIES+1))
-
-static struct proc_dir_entry *palinfo_proc_entries[NR_PALINFO_PROC_ENTRIES];
 static struct proc_dir_entry *palinfo_dir;
 
 /*
@@ -971,60 +960,32 @@ palinfo_read_entry(char *page, char **start, off_t off, int count, int *eof, voi
 static void __cpuinit
 create_palinfo_proc_entries(unsigned int cpu)
 {
-#	define CPUSTR	"cpu%d"
-
 	pal_func_cpu_u_t f;
-	struct proc_dir_entry **pdir;
 	struct proc_dir_entry *cpu_dir;
 	int j;
-	char cpustr[sizeof(CPUSTR)];
-
-
-	/*
-	 * we keep track of created entries in a depth-first order for
-	 * cleanup purposes. Each entry is stored into palinfo_proc_entries
-	 */
-	sprintf(cpustr,CPUSTR, cpu);
+	char cpustr[3+4+1];	/* cpu numbers are up to 4095 on itanic */
+	sprintf(cpustr, "cpu%d", cpu);
 
 	cpu_dir = proc_mkdir(cpustr, palinfo_dir);
+	if (!cpu_dir)
+		return;
 
 	f.req_cpu = cpu;
 
-	/*
-	 * Compute the location to store per cpu entries
-	 * We dont store the top level entry in this list, but
-	 * remove it finally after removing all cpu entries.
-	 */
-	pdir = &palinfo_proc_entries[cpu*(NR_PALINFO_ENTRIES+1)];
-	*pdir++ = cpu_dir;
 	for (j=0; j < NR_PALINFO_ENTRIES; j++) {
 		f.func_id = j;
-		*pdir = create_proc_read_entry(
-				palinfo_entries[j].name, 0, cpu_dir,
-				palinfo_read_entry, (void *)f.value);
-		pdir++;
+		create_proc_read_entry(
+			palinfo_entries[j].name, 0, cpu_dir,
+			palinfo_read_entry, (void *)f.value);
 	}
 }
 
 static void
 remove_palinfo_proc_entries(unsigned int hcpu)
 {
-	int j;
-	struct proc_dir_entry *cpu_dir, **pdir;
-
-	pdir = &palinfo_proc_entries[hcpu*(NR_PALINFO_ENTRIES+1)];
-	cpu_dir = *pdir;
-	*pdir++=NULL;
-	for (j=0; j < (NR_PALINFO_ENTRIES); j++) {
-		if ((*pdir)) {
-			remove_proc_entry ((*pdir)->name, cpu_dir);
-			*pdir ++= NULL;
-		}
-	}
-
-	if (cpu_dir) {
-		remove_proc_entry(cpu_dir->name, palinfo_dir);
-	}
+	char cpustr[3+4+1];	/* cpu numbers are up to 4095 on itanic */
+	sprintf(cpustr, "cpu%d", hcpu);
+	remove_proc_subtree(cpustr, palinfo_dir);
 }
 
 static int __cpuinit palinfo_cpu_callback(struct notifier_block *nfb,
@@ -1058,6 +1019,8 @@ palinfo_init(void)
 
 	printk(KERN_INFO "PAL Information Facility v%s\n", PALINFO_VERSION);
 	palinfo_dir = proc_mkdir("pal", NULL);
+	if (!palinfo_dir)
+		return -ENOMEM;
 
 	/* Create palinfo dirs in /proc for all online cpus */
 	for_each_online_cpu(i) {
@@ -1073,22 +1036,8 @@ palinfo_init(void)
 static void __exit
 palinfo_exit(void)
 {
-	int i = 0;
-
-	/* remove all nodes: depth first pass. Could optimize this  */
-	for_each_online_cpu(i) {
-		remove_palinfo_proc_entries(i);
-	}
-
-	/*
-	 * Remove the top level entry finally
-	 */
-	remove_proc_entry(palinfo_dir->name, NULL);
-
-	/*
-	 * Unregister from cpu notifier callbacks
-	 */
 	unregister_hotcpu_notifier(&palinfo_cpu_notifier);
+	remove_proc_subtree("pal", NULL);
 }
 
 module_init(palinfo_init);

arch/m68k/include/asm/gpio.h

@@ -86,4 +86,24 @@ static inline int gpio_cansleep(unsigned gpio)
 	return gpio < MCFGPIO_PIN_MAX ? 0 : __gpio_cansleep(gpio);
 }
 
+static inline int gpio_request_one(unsigned gpio, unsigned long flags, const char *label)
+{
+	int err;
+
+	err = gpio_request(gpio, label);
+	if (err)
+		return err;
+
+	if (flags & GPIOF_DIR_IN)
+		err = gpio_direction_input(gpio);
+	else
+		err = gpio_direction_output(gpio,
+			(flags & GPIOF_INIT_HIGH) ? 1 : 0);
+
+	if (err)
+		gpio_free(gpio);
+
+	return err;
+}
+
 #endif

arch/powerpc/kernel/entry_64.S

@@ -304,7 +304,7 @@ syscall_exit_work:
 	subi	r12,r12,TI_FLAGS
 
 4:	/* Anything else left to do? */
-	SET_DEFAULT_THREAD_PPR(r3, r9)		/* Set thread.ppr = 3 */
+	SET_DEFAULT_THREAD_PPR(r3, r10)		/* Set thread.ppr = 3 */
 	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
 	beq	.ret_from_except_lite
 
@@ -657,7 +657,7 @@ resume_kernel:
 	/* Clear _TIF_EMULATE_STACK_STORE flag */
 	lis	r11,_TIF_EMULATE_STACK_STORE@h
 	addi	r5,r9,TI_FLAGS
-	ldarx	r4,0,r5
+0:	ldarx	r4,0,r5
 	andc	r4,r4,r11
 	stdcx.	r4,0,r5
 	bne-	0b

arch/powerpc/kernel/process.c

@@ -555,10 +555,12 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new)
 		new->thread.regs->msr |=
 			(MSR_FP | new->thread.fpexc_mode);
 	}
+#ifdef CONFIG_ALTIVEC
 	if (msr & MSR_VEC) {
 		do_load_up_transact_altivec(&new->thread);
 		new->thread.regs->msr |= MSR_VEC;
 	}
+#endif
 	/* We may as well turn on VSX too since all the state is restored now */
 	if (msr & MSR_VSX)
 		new->thread.regs->msr |= MSR_VSX;

arch/powerpc/kernel/signal_32.c

@@ -866,10 +866,12 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 		do_load_up_transact_fpu(&current->thread);
 		regs->msr |= (MSR_FP | current->thread.fpexc_mode);
 	}
+#ifdef CONFIG_ALTIVEC
 	if (msr & MSR_VEC) {
 		do_load_up_transact_altivec(&current->thread);
 		regs->msr |= MSR_VEC;
 	}
+#endif
 
 	return 0;
 }

arch/powerpc/kernel/signal_64.c

@@ -522,10 +522,12 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 		do_load_up_transact_fpu(&current->thread);
 		regs->msr |= (MSR_FP | current->thread.fpexc_mode);
 	}
+#ifdef CONFIG_ALTIVEC
 	if (msr & MSR_VEC) {
 		do_load_up_transact_altivec(&current->thread);
 		regs->msr |= MSR_VEC;
 	}
+#endif
 
 	return err;
 }

arch/powerpc/kernel/tm.S

@@ -309,6 +309,7 @@ _GLOBAL(tm_recheckpoint)
 	or	r5, r6, r5			/* Set MSR.FP+.VSX/.VEC */
 	mtmsr	r5
 
+#ifdef CONFIG_ALTIVEC
 	/* FP and VEC registers:  These are recheckpointed from thread.fpr[]
 	 * and thread.vr[] respectively.  The thread.transact_fpr[] version
 	 * is more modern, and will be loaded subsequently by any FPUnavailable
@@ -323,6 +324,7 @@ _GLOBAL(tm_recheckpoint)
 	REST_32VRS(0, r5, r3)			/* r5 scratch, r3 THREAD ptr */
 	ld	r5, THREAD_VRSAVE(r3)
 	mtspr	SPRN_VRSAVE, r5
+#endif
 
 dont_restore_vec:
 	andi.	r0, r4, MSR_FP

arch/powerpc/kvm/e500.h

@@ -26,17 +26,20 @@
 #define E500_PID_NUM   3
 #define E500_TLB_NUM   2
 
-#define E500_TLB_VALID 1
-#define E500_TLB_BITMAP 2
+/* entry is mapped somewhere in host TLB */
+#define E500_TLB_VALID		(1 << 0)
+/* TLB1 entry is mapped by host TLB1, tracked by bitmaps */
+#define E500_TLB_BITMAP		(1 << 1)
+/* TLB1 entry is mapped by host TLB0 */
 #define E500_TLB_TLB0		(1 << 2)
 
 struct tlbe_ref {
-	pfn_t pfn;
-	unsigned int flags; /* E500_TLB_* */
+	pfn_t pfn;		/* valid only for TLB0, except briefly */
+	unsigned int flags;	/* E500_TLB_* */
 };
 
 struct tlbe_priv {
-	struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */
+	struct tlbe_ref ref;
 };
 
 #ifdef CONFIG_KVM_E500V2
@@ -63,17 +66,6 @@ struct kvmppc_vcpu_e500 {
 
 	unsigned int gtlb_nv[E500_TLB_NUM];
 
-	/*
-	 * information associated with each host TLB entry --
-	 * TLB1 only for now.  If/when guest TLB1 entries can be
-	 * mapped with host TLB0, this will be used for that too.
-	 *
-	 * We don't want to use this for guest TLB0 because then we'd
-	 * have the overhead of doing the translation again even if
-	 * the entry is still in the guest TLB (e.g. we swapped out
-	 * and back, and our host TLB entries got evicted).
-	 */
-	struct tlbe_ref *tlb_refs[E500_TLB_NUM];
 	unsigned int host_tlb1_nv;
 
 	u32 svr;

arch/powerpc/kvm/e500_mmu_host.c

@@ -193,8 +193,11 @@ void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
 	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref;
 
 	/* Don't bother with unmapped entries */
-	if (!(ref->flags & E500_TLB_VALID))
-		return;
+	if (!(ref->flags & E500_TLB_VALID)) {
+		WARN(ref->flags & (E500_TLB_BITMAP | E500_TLB_TLB0),
+		     "%s: flags %x\n", __func__, ref->flags);
+		WARN_ON(tlbsel == 1 && vcpu_e500->g2h_tlb1_map[esel]);
+	}
 
 	if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) {
 		u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
@@ -248,7 +251,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
 					 pfn_t pfn)
 {
 	ref->pfn = pfn;
-	ref->flags = E500_TLB_VALID;
+	ref->flags |= E500_TLB_VALID;
 
 	if (tlbe_is_writable(gtlbe))
 		kvm_set_pfn_dirty(pfn);
@@ -257,6 +260,7 @@ static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
 static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
 {
 	if (ref->flags & E500_TLB_VALID) {
+		/* FIXME: don't log bogus pfn for TLB1 */
 		trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
 		ref->flags = 0;
 	}
@@ -274,36 +278,23 @@ static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500)
 
 static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
-	int tlbsel = 0;
-	int i;
-
-	for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
-		struct tlbe_ref *ref =
-			&vcpu_e500->gtlb_priv[tlbsel][i].ref;
-		kvmppc_e500_ref_release(ref);
-	}
-}
-
-static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	int stlbsel = 1;
+	int tlbsel;
 	int i;
 
-	kvmppc_e500_tlbil_all(vcpu_e500);
-
-	for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
-		struct tlbe_ref *ref =
-			&vcpu_e500->tlb_refs[stlbsel][i];
-		kvmppc_e500_ref_release(ref);
+	for (tlbsel = 0; tlbsel <= 1; tlbsel++) {
+		for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
+			struct tlbe_ref *ref =
+				&vcpu_e500->gtlb_priv[tlbsel][i].ref;
+			kvmppc_e500_ref_release(ref);
+		}
 	}
-
-	clear_tlb_privs(vcpu_e500);
 }
 
 void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	clear_tlb_refs(vcpu_e500);
+	kvmppc_e500_tlbil_all(vcpu_e500);
+	clear_tlb_privs(vcpu_e500);
 	clear_tlb1_bitmap(vcpu_e500);
 }
 
@@ -458,8 +449,6 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
 	}
 
-	/* Drop old ref and setup new one. */
-	kvmppc_e500_ref_release(ref);
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
 
 	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
@@ -507,14 +496,15 @@ static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500,
 	if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
 		vcpu_e500->host_tlb1_nv = 0;
 
-	vcpu_e500->tlb_refs[1][sesel] = *ref;
-	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
-	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
 	if (vcpu_e500->h2g_tlb1_rmap[sesel]) {
-		unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel];
+		unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel] - 1;
 		vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel);
 	}
-	vcpu_e500->h2g_tlb1_rmap[sesel] = esel;
+
+	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
+	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
+	vcpu_e500->h2g_tlb1_rmap[sesel] = esel + 1;
+	WARN_ON(!(ref->flags & E500_TLB_VALID));
 
 	return sesel;
 }
@@ -526,13 +516,12 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
 		struct kvm_book3e_206_tlb_entry *stlbe, int esel)
 {
-	struct tlbe_ref ref;
+	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[1][esel].ref;
 	int sesel;
 	int r;
 
-	ref.flags = 0;
 	r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe,
-				   &ref);
+				   ref);
 	if (r)
 		return r;
 
@@ -544,7 +533,7 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	}
 
 	/* Otherwise map into TLB1 */
-	sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel);
+	sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, ref, esel);
 	write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel);
 
 	return 0;
@@ -565,7 +554,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 	case 0:
 		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
-		/* Triggers after clear_tlb_refs or on initial mapping */
+		/* Triggers after clear_tlb_privs or on initial mapping */
 		if (!(priv->ref.flags & E500_TLB_VALID)) {
 			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
 		} else {
@@ -665,35 +654,16 @@ int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 		host_tlb_params[0].entries / host_tlb_params[0].ways;
 	host_tlb_params[1].sets = 1;
 
-	vcpu_e500->tlb_refs[0] =
-		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries,
-			GFP_KERNEL);
-	if (!vcpu_e500->tlb_refs[0])
-		goto err;
-
-	vcpu_e500->tlb_refs[1] =
-		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries,
-			GFP_KERNEL);
-	if (!vcpu_e500->tlb_refs[1])
-		goto err;
-
 	vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) *
 					   host_tlb_params[1].entries,
 					   GFP_KERNEL);
 	if (!vcpu_e500->h2g_tlb1_rmap)
-		goto err;
+		return -EINVAL;
 
 	return 0;
-
-err:
-	kfree(vcpu_e500->tlb_refs[0]);
-	kfree(vcpu_e500->tlb_refs[1]);
-	return -EINVAL;
 }
 
 void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	kfree(vcpu_e500->h2g_tlb1_rmap);
-	kfree(vcpu_e500->tlb_refs[0]);
-	kfree(vcpu_e500->tlb_refs[1]);
 }

arch/powerpc/kvm/e500mc.c

@@ -108,6 +108,8 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
 {
 }
 
+static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu_on_cpu);
+
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
@@ -136,8 +138,11 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	mtspr(SPRN_GDEAR, vcpu->arch.shared->dar);
 	mtspr(SPRN_GESR, vcpu->arch.shared->esr);
 
-	if (vcpu->arch.oldpir != mfspr(SPRN_PIR))
+	if (vcpu->arch.oldpir != mfspr(SPRN_PIR) ||
+	    __get_cpu_var(last_vcpu_on_cpu) != vcpu) {
 		kvmppc_e500_tlbil_all(vcpu_e500);
+		__get_cpu_var(last_vcpu_on_cpu) = vcpu;
+	}
 
 	kvmppc_load_guest_fp(vcpu);
 }

arch/powerpc/platforms/pseries/lpar.c

@@ -186,7 +186,13 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group)
 					   (0x1UL << 4), &dummy1, &dummy2);
 		if (lpar_rc == H_SUCCESS)
 			return i;
-		BUG_ON(lpar_rc != H_NOT_FOUND);
+
+		/*
+		 * The test for adjunct partition is performed before the
+		 * ANDCOND test.  H_RESOURCE may be returned, so we need to
+		 * check for that as well.
+		 */
+		BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE);
 
 		slot_offset++;
 		slot_offset &= 0x7;

arch/s390/include/asm/io.h

@@ -50,10 +50,6 @@ void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
 #define ioremap_nocache(addr, size)	ioremap(addr, size)
 #define ioremap_wc			ioremap_nocache
 
-/* TODO: s390 cannot support io_remap_pfn_range... */
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) 	       \
-	remap_pfn_range(vma, vaddr, pfn, size, prot)
-
 static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 {
 	return (void __iomem *) offset;

arch/s390/include/asm/pgtable.h

@@ -57,6 +57,10 @@ extern unsigned long zero_page_mask;
 	 (((unsigned long)(vaddr)) &zero_page_mask))))
 #define __HAVE_COLOR_ZERO_PAGE
 
+/* TODO: s390 cannot support io_remap_pfn_range... */
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) 	       \
+	remap_pfn_range(vma, vaddr, pfn, size, prot)
+
 #endif /* !__ASSEMBLY__ */
 
 /*

arch/sparc/include/asm/Kbuild

@@ -2,11 +2,16 @@
 
 
 generic-y += clkdev.h
+generic-y += cputime.h
 generic-y += div64.h
+generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += local64.h
+generic-y += mutex.h
 generic-y += irq_regs.h
 generic-y += local.h
 generic-y += module.h
+generic-y += serial.h
 generic-y += trace_clock.h
+generic-y += types.h
 generic-y += word-at-a-time.h

arch/sparc/include/asm/cputime.h

@@ -1,6 +0,0 @@
-#ifndef __SPARC_CPUTIME_H
-#define __SPARC_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __SPARC_CPUTIME_H */

arch/sparc/include/asm/emergency-restart.h

@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */

arch/sparc/include/asm/mutex.h

@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>

arch/sparc/include/asm/pgtable_64.h

@@ -915,6 +915,7 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 	return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
 }
 
+#include <asm/tlbflush.h>
 #include <asm-generic/pgtable.h>
 
 /* We provide our own get_unmapped_area to cope with VA holes and

arch/sparc/include/asm/serial.h

@@ -1,6 +0,0 @@
-#ifndef __SPARC_SERIAL_H
-#define __SPARC_SERIAL_H
-
-#define BASE_BAUD ( 1843200 / 16 )
-
-#endif /* __SPARC_SERIAL_H */

arch/sparc/include/asm/smp_32.h

@@ -36,7 +36,6 @@ typedef void (*smpfunc_t)(unsigned long, unsigned long, unsigned long,
 		       unsigned long, unsigned long);
 
 void cpu_panic(void);
-extern void smp4m_irq_rotate(int cpu);
 
 /*
  *	General functions that each host system must provide.
@@ -46,7 +45,6 @@ void sun4m_init_smp(void);
 void sun4d_init_smp(void);
 
 void smp_callin(void);
-void smp_boot_cpus(void);
 void smp_store_cpu_info(int);
 
 void smp_resched_interrupt(void);
@@ -107,9 +105,6 @@ extern int hard_smp_processor_id(void);
 
 #define raw_smp_processor_id()		(current_thread_info()->cpu)
 
-#define prof_multiplier(__cpu)		cpu_data(__cpu).multiplier
-#define prof_counter(__cpu)		cpu_data(__cpu).counter
-
 void smp_setup_cpu_possible_map(void);
 
 #endif /* !(__ASSEMBLY__) */

arch/sparc/include/asm/switch_to_64.h

@@ -18,8 +18,7 @@ do {						\
 	 * and 2 stores in this critical code path.  -DaveM
 	 */
 #define switch_to(prev, next, last)					\
-do {	flush_tlb_pending();						\
-	save_and_clear_fpu();						\
+do {	save_and_clear_fpu();						\
 	/* If you are tempted to conditionalize the following */	\
 	/* so that ASI is only written if it changes, think again. */	\
 	__asm__ __volatile__("wr %%g0, %0, %%asi"			\

arch/sparc/include/asm/tlbflush_64.h

@@ -11,24 +11,40 @@
 struct tlb_batch {
 	struct mm_struct *mm;
 	unsigned long tlb_nr;
+	unsigned long active;
 	unsigned long vaddrs[TLB_BATCH_NR];
 };
 
 extern void flush_tsb_kernel_range(unsigned long start, unsigned long end);
 extern void flush_tsb_user(struct tlb_batch *tb);
+extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
 
 /* TLB flush operations. */
 
-extern void flush_tlb_pending(void);
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+				  unsigned long vmaddr)
+{
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+}
+
+#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 
-#define flush_tlb_range(vma,start,end)	\
-	do { (void)(start); flush_tlb_pending(); } while (0)
-#define flush_tlb_page(vma,addr)	flush_tlb_pending()
-#define flush_tlb_mm(mm)		flush_tlb_pending()
+extern void flush_tlb_pending(void);
+extern void arch_enter_lazy_mmu_mode(void);
+extern void arch_leave_lazy_mmu_mode(void);
+#define arch_flush_lazy_mmu_mode()      do {} while (0)
 
 /* Local cpu only.  */
 extern void __flush_tlb_all(void);
-
+extern void __flush_tlb_page(unsigned long context, unsigned long vaddr);
 extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #ifndef CONFIG_SMP
@@ -38,15 +54,24 @@ do {	flush_tsb_kernel_range(start,end); \
 	__flush_tlb_kernel_range(start,end); \
 } while (0)
 
+static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	__flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
+}
+
 #else /* CONFIG_SMP */
 
 extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
 
 #define flush_tlb_kernel_range(start, end) \
 do {	flush_tsb_kernel_range(start,end); \
 	smp_flush_tlb_kernel_range(start, end); \
 } while (0)
 
+#define global_flush_tlb_page(mm, vaddr) \
+	smp_flush_tlb_page(mm, vaddr)
+
 #endif /* ! CONFIG_SMP */
 
 #endif /* _SPARC64_TLBFLUSH_H */

arch/sparc/include/uapi/asm/Kbuild

@@ -44,7 +44,6 @@ header-y += swab.h
 header-y += termbits.h
 header-y += termios.h
 header-y += traps.h
-header-y += types.h
 header-y += uctx.h
 header-y += unistd.h
 header-y += utrap.h

arch/sparc/include/uapi/asm/types.h

@@ -1,17 +0,0 @@
-#ifndef _SPARC_TYPES_H
-#define _SPARC_TYPES_H
-/*
- * This file is never included by application software unless
- * explicitly requested (e.g., via linux/types.h) in which case the
- * application is Linux specific so (user-) name space pollution is
- * not a major issue.  However, for interoperability, libraries still
- * need to be careful to avoid a name clashes.
- */
-
-#if defined(__sparc__)
-
-#include <asm-generic/int-ll64.h>
-
-#endif /* defined(__sparc__) */
-
-#endif /* defined(_SPARC_TYPES_H) */

arch/sparc/kernel/smp_64.c

@@ -849,7 +849,7 @@ void smp_tsb_sync(struct mm_struct *mm)
 }
 
 extern unsigned long xcall_flush_tlb_mm;
-extern unsigned long xcall_flush_tlb_pending;
+extern unsigned long xcall_flush_tlb_page;
 extern unsigned long xcall_flush_tlb_kernel_range;
 extern unsigned long xcall_fetch_glob_regs;
 extern unsigned long xcall_fetch_glob_pmu;
@@ -1074,23 +1074,56 @@ local_flush_and_out:
 	put_cpu();
 }
 
+struct tlb_pending_info {
+	unsigned long ctx;
+	unsigned long nr;
+	unsigned long *vaddrs;
+};
+
+static void tlb_pending_func(void *info)
+{
+	struct tlb_pending_info *t = info;
+
+	__flush_tlb_pending(t->ctx, t->nr, t->vaddrs);
+}
+
 void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs)
 {
 	u32 ctx = CTX_HWBITS(mm->context);
+	struct tlb_pending_info info;
 	int cpu = get_cpu();
 
+	info.ctx = ctx;
+	info.nr = nr;
+	info.vaddrs = vaddrs;
+
 	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
 		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
 	else
-		smp_cross_call_masked(&xcall_flush_tlb_pending,
-				      ctx, nr, (unsigned long) vaddrs,
-				      mm_cpumask(mm));
+		smp_call_function_many(mm_cpumask(mm), tlb_pending_func,
+				       &info, 1);
 
 	__flush_tlb_pending(ctx, nr, vaddrs);
 
 	put_cpu();
 }
 
+void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	unsigned long context = CTX_HWBITS(mm->context);
+	int cpu = get_cpu();
+
+	if (mm == current->mm && atomic_read(&mm->mm_users) == 1)
+		cpumask_copy(mm_cpumask(mm), cpumask_of(cpu));
+	else
+		smp_cross_call_masked(&xcall_flush_tlb_page,
+				      context, vaddr, 0,
+				      mm_cpumask(mm));
+	__flush_tlb_page(context, vaddr);
+
+	put_cpu();
+}
+
 void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
 	start &= PAGE_MASK;

arch/sparc/lib/bitext.c

@@ -119,11 +119,7 @@ void bit_map_clear(struct bit_map *t, int offset, int len)
 
 void bit_map_init(struct bit_map *t, unsigned long *map, int size)
 {
-
-	if ((size & 07) != 0)
-		BUG();
-	memset(map, 0, size>>3);
-
+	bitmap_zero(map, size);
 	memset(t, 0, sizeof *t);
 	spin_lock_init(&t->lock);
 	t->map = map;

arch/sparc/mm/iommu.c

@@ -34,7 +34,7 @@
 #define IOMMU_RNGE	IOMMU_RNGE_256MB
 #define IOMMU_START	0xF0000000
 #define IOMMU_WINSIZE	(256*1024*1024U)
-#define IOMMU_NPTES	(IOMMU_WINSIZE/PAGE_SIZE)	/* 64K PTEs, 265KB */
+#define IOMMU_NPTES	(IOMMU_WINSIZE/PAGE_SIZE)	/* 64K PTEs, 256KB */
 #define IOMMU_ORDER	6				/* 4096 * (1<<6) */
 
 /* srmmu.c */

arch/sparc/mm/srmmu.c

@@ -280,7 +280,9 @@ static void __init srmmu_nocache_init(void)
 		SRMMU_NOCACHE_ALIGN_MAX, 0UL);
 	memset(srmmu_nocache_pool, 0, srmmu_nocache_size);
 
-	srmmu_nocache_bitmap = __alloc_bootmem(bitmap_bits >> 3, SMP_CACHE_BYTES, 0UL);
+	srmmu_nocache_bitmap =
+		__alloc_bootmem(BITS_TO_LONGS(bitmap_bits) * sizeof(long),
+				SMP_CACHE_BYTES, 0UL);
 	bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits);
 
 	srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE);

arch/sparc/mm/tlb.c

@@ -24,11 +24,17 @@ static DEFINE_PER_CPU(struct tlb_batch, tlb_batch);
 void flush_tlb_pending(void)
 {
 	struct tlb_batch *tb = &get_cpu_var(tlb_batch);
+	struct mm_struct *mm = tb->mm;
 
-	if (tb->tlb_nr) {
-		flush_tsb_user(tb);
+	if (!tb->tlb_nr)
+		goto out;
 
-		if (CTX_VALID(tb->mm->context)) {
+	flush_tsb_user(tb);
+
+	if (CTX_VALID(mm->context)) {
+		if (tb->tlb_nr == 1) {
+			global_flush_tlb_page(mm, tb->vaddrs[0]);
+		} else {
 #ifdef CONFIG_SMP
 			smp_flush_tlb_pending(tb->mm, tb->tlb_nr,
 					      &tb->vaddrs[0]);
@@ -37,12 +43,30 @@ void flush_tlb_pending(void)
 					    tb->tlb_nr, &tb->vaddrs[0]);
 #endif
 		}
-		tb->tlb_nr = 0;
 	}
 
+	tb->tlb_nr = 0;
+
+out:
 	put_cpu_var(tlb_batch);
 }
 
+void arch_enter_lazy_mmu_mode(void)
+{
+	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+	tb->active = 1;
+}
+
+void arch_leave_lazy_mmu_mode(void)
+{
+	struct tlb_batch *tb = &__get_cpu_var(tlb_batch);
+
+	if (tb->tlb_nr)
+		flush_tlb_pending();
+	tb->active = 0;
+}
+
 static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 			      bool exec)
 {
@@ -60,6 +84,12 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 		nr = 0;
 	}
 
+	if (!tb->active) {
+		global_flush_tlb_page(mm, vaddr);
+		flush_tsb_user_page(mm, vaddr);
+		return;
+	}
+
 	if (nr == 0)
 		tb->mm = mm;
 

arch/sparc/mm/tsb.c

@@ -7,11 +7,10 @@
 #include <linux/preempt.h>
 #include <linux/slab.h>
 #include <asm/page.h>
-#include <asm/tlbflush.h>
-#include <asm/tlb.h>
-#include <asm/mmu_context.h>
 #include <asm/pgtable.h>
+#include <asm/mmu_context.h>
 #include <asm/tsb.h>
+#include <asm/tlb.h>
 #include <asm/oplib.h>
 
 extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
@@ -46,23 +45,27 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
 	}
 }
 
-static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
-			    unsigned long tsb, unsigned long nentries)
+static void __flush_tsb_one_entry(unsigned long tsb, unsigned long v,
+				  unsigned long hash_shift,
+				  unsigned long nentries)
 {
-	unsigned long i;
+	unsigned long tag, ent, hash;
 
-	for (i = 0; i < tb->tlb_nr; i++) {
-		unsigned long v = tb->vaddrs[i];
-		unsigned long tag, ent, hash;
+	v &= ~0x1UL;
+	hash = tsb_hash(v, hash_shift, nentries);
+	ent = tsb + (hash * sizeof(struct tsb));
+	tag = (v >> 22UL);
 
-		v &= ~0x1UL;
+	tsb_flush(ent, tag);
+}
 
-		hash = tsb_hash(v, hash_shift, nentries);
-		ent = tsb + (hash * sizeof(struct tsb));
-		tag = (v >> 22UL);
+static void __flush_tsb_one(struct tlb_batch *tb, unsigned long hash_shift,
+			    unsigned long tsb, unsigned long nentries)
+{
+	unsigned long i;
 
-		tsb_flush(ent, tag);
-	}
+	for (i = 0; i < tb->tlb_nr; i++)
+		__flush_tsb_one_entry(tsb, tb->vaddrs[i], hash_shift, nentries);
 }
 
 void flush_tsb_user(struct tlb_batch *tb)
@@ -90,6 +93,30 @@ void flush_tsb_user(struct tlb_batch *tb)
 	spin_unlock_irqrestore(&mm->context.lock, flags);
 }
 
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr)
+{
+	unsigned long nentries, base, flags;
+
+	spin_lock_irqsave(&mm->context.lock, flags);
+
+	base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
+	nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
+	if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+		base = __pa(base);
+	__flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries);
+
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
+		base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
+		nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
+		if (tlb_type == cheetah_plus || tlb_type == hypervisor)
+			base = __pa(base);
+		__flush_tsb_one_entry(base, vaddr, HPAGE_SHIFT, nentries);
+	}
+#endif
+	spin_unlock_irqrestore(&mm->context.lock, flags);
+}
+
 #define HV_PGSZ_IDX_BASE	HV_PGSZ_IDX_8K
 #define HV_PGSZ_MASK_BASE	HV_PGSZ_MASK_8K
 

arch/sparc/mm/ultra.S

@@ -52,6 +52,33 @@ __flush_tlb_mm:		/* 18 insns */
 	nop
 	nop
 
+	.align		32
+	.globl		__flush_tlb_page
+__flush_tlb_page:	/* 22 insns */
+	/* %o0 = context, %o1 = vaddr */
+	rdpr		%pstate, %g7
+	andn		%g7, PSTATE_IE, %g2
+	wrpr		%g2, %pstate
+	mov		SECONDARY_CONTEXT, %o4
+	ldxa		[%o4] ASI_DMMU, %g2
+	stxa		%o0, [%o4] ASI_DMMU
+	andcc		%o1, 1, %g0
+	andn		%o1, 1, %o3
+	be,pn		%icc, 1f
+	 or		%o3, 0x10, %o3
+	stxa		%g0, [%o3] ASI_IMMU_DEMAP
+1:	stxa		%g0, [%o3] ASI_DMMU_DEMAP
+	membar		#Sync
+	stxa		%g2, [%o4] ASI_DMMU
+	sethi		%hi(KERNBASE), %o4
+	flush		%o4
+	retl
+	 wrpr		%g7, 0x0, %pstate
+	nop
+	nop
+	nop
+	nop
+
 	.align		32
 	.globl		__flush_tlb_pending
 __flush_tlb_pending:	/* 26 insns */
@@ -203,6 +230,31 @@ __cheetah_flush_tlb_mm: /* 19 insns */
 	retl
 	 wrpr		%g7, 0x0, %pstate
 
+__cheetah_flush_tlb_page:	/* 22 insns */
+	/* %o0 = context, %o1 = vaddr */
+	rdpr		%pstate, %g7
+	andn		%g7, PSTATE_IE, %g2
+	wrpr		%g2, 0x0, %pstate
+	wrpr		%g0, 1, %tl
+	mov		PRIMARY_CONTEXT, %o4
+	ldxa		[%o4] ASI_DMMU, %g2
+	srlx		%g2, CTX_PGSZ1_NUC_SHIFT, %o3
+	sllx		%o3, CTX_PGSZ1_NUC_SHIFT, %o3
+	or		%o0, %o3, %o0	/* Preserve nucleus page size fields */
+	stxa		%o0, [%o4] ASI_DMMU
+	andcc		%o1, 1, %g0
+	be,pn		%icc, 1f
+	 andn		%o1, 1, %o3
+	stxa		%g0, [%o3] ASI_IMMU_DEMAP
+1:	stxa		%g0, [%o3] ASI_DMMU_DEMAP	
+	membar		#Sync
+	stxa		%g2, [%o4] ASI_DMMU
+	sethi		%hi(KERNBASE), %o4
+	flush		%o4
+	wrpr		%g0, 0, %tl
+	retl
+	 wrpr		%g7, 0x0, %pstate
+
 __cheetah_flush_tlb_pending:	/* 27 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	rdpr		%pstate, %g7
@@ -269,6 +321,20 @@ __hypervisor_flush_tlb_mm: /* 10 insns */
 	retl
 	 nop
 
+__hypervisor_flush_tlb_page: /* 11 insns */
+	/* %o0 = context, %o1 = vaddr */
+	mov		%o0, %g2
+	mov		%o1, %o0              /* ARG0: vaddr + IMMU-bit */
+	mov		%g2, %o1	      /* ARG1: mmu context */
+	mov		HV_MMU_ALL, %o2	      /* ARG2: flags */
+	srlx		%o0, PAGE_SHIFT, %o0
+	sllx		%o0, PAGE_SHIFT, %o0
+	ta		HV_MMU_UNMAP_ADDR_TRAP
+	brnz,pn		%o0, __hypervisor_tlb_tl0_error
+	 mov		HV_MMU_UNMAP_ADDR_TRAP, %o1
+	retl
+	 nop
+
 __hypervisor_flush_tlb_pending: /* 16 insns */
 	/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
 	sllx		%o1, 3, %g1
@@ -339,6 +405,13 @@ cheetah_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		19, %o2
 
+	sethi		%hi(__flush_tlb_page), %o0
+	or		%o0, %lo(__flush_tlb_page), %o0
+	sethi		%hi(__cheetah_flush_tlb_page), %o1
+	or		%o1, %lo(__cheetah_flush_tlb_page), %o1
+	call		tlb_patch_one
+	 mov		22, %o2
+
 	sethi		%hi(__flush_tlb_pending), %o0
 	or		%o0, %lo(__flush_tlb_pending), %o0
 	sethi		%hi(__cheetah_flush_tlb_pending), %o1
@@ -397,10 +470,9 @@ xcall_flush_tlb_mm:	/* 21 insns */
 	nop
 	nop
 
-	.globl		xcall_flush_tlb_pending
-xcall_flush_tlb_pending:	/* 21 insns */
-	/* %g5=context, %g1=nr, %g7=vaddrs[] */
-	sllx		%g1, 3, %g1
+	.globl		xcall_flush_tlb_page
+xcall_flush_tlb_page:	/* 17 insns */
+	/* %g5=context, %g1=vaddr */
 	mov		PRIMARY_CONTEXT, %g4
 	ldxa		[%g4] ASI_DMMU, %g2
 	srlx		%g2, CTX_PGSZ1_NUC_SHIFT, %g4
@@ -408,20 +480,16 @@ xcall_flush_tlb_pending:	/* 21 insns */
 	or		%g5, %g4, %g5
 	mov		PRIMARY_CONTEXT, %g4
 	stxa		%g5, [%g4] ASI_DMMU
-1:	sub		%g1, (1 << 3), %g1
-	ldx		[%g7 + %g1], %g5
-	andcc		%g5, 0x1, %g0
+	andcc		%g1, 0x1, %g0
 	be,pn		%icc, 2f
-
-	 andn		%g5, 0x1, %g5
+	 andn		%g1, 0x1, %g5
 	stxa		%g0, [%g5] ASI_IMMU_DEMAP
 2:	stxa		%g0, [%g5] ASI_DMMU_DEMAP
 	membar		#Sync
-	brnz,pt		%g1, 1b
-	 nop
 	stxa		%g2, [%g4] ASI_DMMU
 	retry
 	nop
+	nop
 
 	.globl		xcall_flush_tlb_kernel_range
 xcall_flush_tlb_kernel_range:	/* 25 insns */
@@ -656,15 +724,13 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
 	membar		#Sync
 	retry
 
-	.globl		__hypervisor_xcall_flush_tlb_pending
-__hypervisor_xcall_flush_tlb_pending: /* 21 insns */
-	/* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */
-	sllx		%g1, 3, %g1
+	.globl		__hypervisor_xcall_flush_tlb_page
+__hypervisor_xcall_flush_tlb_page: /* 17 insns */
+	/* %g5=ctx, %g1=vaddr */
 	mov		%o0, %g2
 	mov		%o1, %g3
 	mov		%o2, %g4
-1:	sub		%g1, (1 << 3), %g1
-	ldx		[%g7 + %g1], %o0	/* ARG0: virtual address */
+	mov		%g1, %o0	        /* ARG0: virtual address */
 	mov		%g5, %o1		/* ARG1: mmu context */
 	mov		HV_MMU_ALL, %o2		/* ARG2: flags */
 	srlx		%o0, PAGE_SHIFT, %o0
@@ -673,8 +739,6 @@ __hypervisor_xcall_flush_tlb_pending: /* 21 insns */
 	mov		HV_MMU_UNMAP_ADDR_TRAP, %g6
 	brnz,a,pn	%o0, __hypervisor_tlb_xcall_error
 	 mov		%o0, %g5
-	brnz,pt		%g1, 1b
-	 nop
 	mov		%g2, %o0
 	mov		%g3, %o1
 	mov		%g4, %o2
@@ -757,6 +821,13 @@ hypervisor_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		10, %o2
 
+	sethi		%hi(__flush_tlb_page), %o0
+	or		%o0, %lo(__flush_tlb_page), %o0
+	sethi		%hi(__hypervisor_flush_tlb_page), %o1
+	or		%o1, %lo(__hypervisor_flush_tlb_page), %o1
+	call		tlb_patch_one
+	 mov		11, %o2
+
 	sethi		%hi(__flush_tlb_pending), %o0
 	or		%o0, %lo(__flush_tlb_pending), %o0
 	sethi		%hi(__hypervisor_flush_tlb_pending), %o1
@@ -788,12 +859,12 @@ hypervisor_patch_cachetlbops:
 	call		tlb_patch_one
 	 mov		21, %o2
 
-	sethi		%hi(xcall_flush_tlb_pending), %o0
-	or		%o0, %lo(xcall_flush_tlb_pending), %o0
-	sethi		%hi(__hypervisor_xcall_flush_tlb_pending), %o1
-	or		%o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1
+	sethi		%hi(xcall_flush_tlb_page), %o0
+	or		%o0, %lo(xcall_flush_tlb_page), %o0
+	sethi		%hi(__hypervisor_xcall_flush_tlb_page), %o1
+	or		%o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1
 	call		tlb_patch_one
-	 mov		21, %o2
+	 mov		17, %o2
 
 	sethi		%hi(xcall_flush_tlb_kernel_range), %o0
 	or		%o0, %lo(xcall_flush_tlb_kernel_range), %o0

arch/tile/include/asm/irqflags.h

@@ -40,7 +40,15 @@
 #include <asm/percpu.h>
 #include <arch/spr_def.h>
 
-/* Set and clear kernel interrupt masks. */
+/*
+ * Set and clear kernel interrupt masks.
+ *
+ * NOTE: __insn_mtspr() is a compiler builtin marked as a memory
+ * clobber.  We rely on it being equivalent to a compiler barrier in
+ * this code since arch_local_irq_save() and friends must act as
+ * compiler barriers.  This compiler semantic is baked into enough
+ * places that the compiler will maintain it going forward.
+ */
 #if CHIP_HAS_SPLIT_INTR_MASK()
 #if INT_PERF_COUNT < 32 || INT_AUX_PERF_COUNT < 32 || INT_MEM_ERROR >= 32
 # error Fix assumptions about which word various interrupts are in

arch/x86/Kconfig

@@ -1549,6 +1549,7 @@ config X86_SMAP
 config EFI
 	bool "EFI runtime service support"
 	depends on ACPI
+	select UCS2_STRING
 	---help---
 	  This enables the kernel to use EFI runtime services that are
 	  available (such as the EFI variable services).

arch/x86/boot/compressed/Makefile

@@ -4,7 +4,7 @@
 # create a compressed vmlinux image from the original vmlinux
 #
 
-targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o
+targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
@@ -29,7 +29,6 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
 	$(obj)/piggy.o
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
-$(obj)/efi_stub_$(BITS).o: KBUILD_CLFAGS += -fshort-wchar -mno-red-zone
 
 ifeq ($(CONFIG_EFI_STUB), y)
 	VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
@@ -43,7 +42,7 @@ OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
-targets += vmlinux.bin.all vmlinux.relocs
+targets += $(patsubst $(obj)/%,%,$(VMLINUX_OBJS)) vmlinux.bin.all vmlinux.relocs
 
 CMD_RELOCS = arch/x86/tools/relocs
 quiet_cmd_relocs = RELOCS  $@

arch/x86/boot/compressed/eboot.c

@@ -251,6 +251,51 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size)
 	*size = len;
 }
 
+static efi_status_t setup_efi_vars(struct boot_params *params)
+{
+	struct setup_data *data;
+	struct efi_var_bootdata *efidata;
+	u64 store_size, remaining_size, var_size;
+	efi_status_t status;
+
+	if (!sys_table->runtime->query_variable_info)
+		return EFI_UNSUPPORTED;
+
+	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+	while (data && data->next)
+		data = (struct setup_data *)(unsigned long)data->next;
+
+	status = efi_call_phys4(sys_table->runtime->query_variable_info,
+				EFI_VARIABLE_NON_VOLATILE |
+				EFI_VARIABLE_BOOTSERVICE_ACCESS |
+				EFI_VARIABLE_RUNTIME_ACCESS, &store_size,
+				&remaining_size, &var_size);
+
+	if (status != EFI_SUCCESS)
+		return status;
+
+	status = efi_call_phys3(sys_table->boottime->allocate_pool,
+				EFI_LOADER_DATA, sizeof(*efidata), &efidata);
+
+	if (status != EFI_SUCCESS)
+		return status;
+
+	efidata->data.type = SETUP_EFI_VARS;
+	efidata->data.len = sizeof(struct efi_var_bootdata) -
+		sizeof(struct setup_data);
+	efidata->data.next = 0;
+	efidata->store_size = store_size;
+	efidata->remaining_size = remaining_size;
+	efidata->max_var_size = var_size;
+
+	if (data)
+		data->next = (unsigned long)efidata;
+	else
+		params->hdr.setup_data = (unsigned long)efidata;
+
+}
+
 static efi_status_t setup_efi_pci(struct boot_params *params)
 {
 	efi_pci_io_protocol *pci;
@@ -1157,6 +1202,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
 
 	setup_graphics(boot_params);
 
+	setup_efi_vars(boot_params);
+
 	setup_efi_pci(boot_params);
 
 	status = efi_call_phys3(sys_table->boottime->allocate_pool,

arch/x86/include/asm/efi.h

@@ -102,6 +102,13 @@ extern void efi_call_phys_epilog(void);
 extern void efi_unmap_memmap(void);
 extern void efi_memory_uc(u64 addr, unsigned long size);
 
+struct efi_var_bootdata {
+	struct setup_data data;
+	u64 store_size;
+	u64 remaining_size;
+	u64 max_var_size;
+};
+
 #ifdef CONFIG_EFI
 
 static inline bool efi_is_native(void)

arch/x86/include/asm/paravirt.h

@@ -703,7 +703,10 @@ static inline void arch_leave_lazy_mmu_mode(void)
 	PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
 }
 
-void arch_flush_lazy_mmu_mode(void);
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+	PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush);
+}
 
 static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 				phys_addr_t phys, pgprot_t flags)

arch/x86/include/asm/paravirt_types.h

@@ -91,6 +91,7 @@ struct pv_lazy_ops {
 	/* Set deferred update mode, used for batching operations. */
 	void (*enter)(void);
 	void (*leave)(void);
+	void (*flush)(void);
 };
 
 struct pv_time_ops {
@@ -679,6 +680,7 @@ void paravirt_end_context_switch(struct task_struct *next);
 
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);
+void paravirt_flush_lazy_mmu(void);
 
 void _paravirt_nop(void);
 u32 _paravirt_ident_32(u32);

arch/x86/include/asm/syscall.h

@@ -29,13 +29,13 @@ extern const unsigned long sys_call_table[];
  */
 static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 {
-	return regs->orig_ax & __SYSCALL_MASK;
+	return regs->orig_ax;
 }
 
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
-	regs->ax = regs->orig_ax & __SYSCALL_MASK;
+	regs->ax = regs->orig_ax;
 }
 
 static inline long syscall_get_error(struct task_struct *task,

arch/x86/include/asm/tlb.h

@@ -7,7 +7,7 @@
 
 #define tlb_flush(tlb)							\
 {									\
-	if (tlb->fullmm == 0)						\
+	if (!tlb->fullmm && !tlb->need_flush_all) 			\
 		flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL);	\
 	else								\
 		flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL);	\

arch/x86/include/uapi/asm/bootparam.h

@@ -6,6 +6,7 @@
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
 #define SETUP_PCI			3
+#define SETUP_EFI_VARS			4
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF

arch/x86/kernel/cpu/mshyperv.c

@@ -35,13 +35,6 @@ static bool __init ms_hyperv_platform(void)
 	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return false;
 
-	/*
-	 * Xen emulates Hyper-V to support enlightened Windows.
-	 * Check to see first if we are on a Xen Hypervisor.
-	 */
-	if (xen_cpuid_base())
-		return false;
-
 	cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
 	      &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
 
@@ -82,12 +75,6 @@ static void __init ms_hyperv_init_platform(void)
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
-#if IS_ENABLED(CONFIG_HYPERV)
-	/*
-	 * Setup the IDT for hypervisor callback.
-	 */
-	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
-#endif
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
@@ -103,6 +90,11 @@ static irq_handler_t vmbus_isr;
 
 void hv_register_vmbus_handler(int irq, irq_handler_t handler)
 {
+	/*
+	 * Setup the IDT for hypervisor callback.
+	 */
+	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
+
 	vmbus_irq = irq;
 	vmbus_isr = handler;
 }

arch/x86/kernel/cpu/perf_event_intel.c

@@ -153,8 +153,14 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 };
 
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
-	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
-	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
+	EVENT_EXTRA_END
+};
+
+static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
 	EVENT_EXTRA_END
 };
 
@@ -2097,7 +2103,10 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		x86_pmu.extra_regs = intel_snb_extra_regs;
+		if (boot_cpu_data.x86_model == 45)
+			x86_pmu.extra_regs = intel_snbep_extra_regs;
+		else
+			x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
@@ -2123,7 +2132,10 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_ivb_event_constraints;
 		x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		x86_pmu.extra_regs = intel_snb_extra_regs;
+		if (boot_cpu_data.x86_model == 62)
+			x86_pmu.extra_regs = intel_snbep_extra_regs;
+		else
+			x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;

arch/x86/kernel/cpu/perf_event_intel_ds.c

@@ -314,10 +314,11 @@ int intel_pmu_drain_bts_buffer(void)
 	if (top <= at)
 		return 0;
 
+	memset(&regs, 0, sizeof(regs));
+
 	ds->bts_index = ds->bts_buffer_base;
 
 	perf_sample_data_init(&data, 0, event->hw.last_period);
-	regs.ip     = 0;
 
 	/*
 	 * Prepare a generic sample, i.e. fill in the invariant fields.

arch/x86/kernel/microcode_core_early.c

@@ -45,9 +45,6 @@ static int __cpuinit x86_vendor(void)
 	u32 eax = 0x00000000;
 	u32 ebx, ecx = 0, edx;
 
-	if (!have_cpuid_p())
-		return X86_VENDOR_UNKNOWN;
-
 	native_cpuid(&eax, &ebx, &ecx, &edx);
 
 	if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx))
@@ -59,18 +56,45 @@ static int __cpuinit x86_vendor(void)
 	return X86_VENDOR_UNKNOWN;
 }
 
+static int __cpuinit x86_family(void)
+{
+	u32 eax = 0x00000001;
+	u32 ebx, ecx = 0, edx;
+	int x86;
+
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	x86 = (eax >> 8) & 0xf;
+	if (x86 == 15)
+		x86 += (eax >> 20) & 0xff;
+
+	return x86;
+}
+
 void __init load_ucode_bsp(void)
 {
-	int vendor = x86_vendor();
+	int vendor, x86;
+
+	if (!have_cpuid_p())
+		return;
 
-	if (vendor == X86_VENDOR_INTEL)
+	vendor = x86_vendor();
+	x86 = x86_family();
+
+	if (vendor == X86_VENDOR_INTEL && x86 >= 6)
 		load_ucode_intel_bsp();
 }
 
 void __cpuinit load_ucode_ap(void)
 {
-	int vendor = x86_vendor();
+	int vendor, x86;
+
+	if (!have_cpuid_p())
+		return;
+
+	vendor = x86_vendor();
+	x86 = x86_family();
 
-	if (vendor == X86_VENDOR_INTEL)
+	if (vendor == X86_VENDOR_INTEL && x86 >= 6)
 		load_ucode_intel_ap();
 }

arch/x86/kernel/paravirt.c

@@ -263,6 +263,18 @@ void paravirt_leave_lazy_mmu(void)
 	leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
+void paravirt_flush_lazy_mmu(void)
+{
+	preempt_disable();
+
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+
+	preempt_enable();
+}
+
 void paravirt_start_context_switch(struct task_struct *prev)
 {
 	BUG_ON(preemptible());
@@ -292,18 +304,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return this_cpu_read(paravirt_lazy_mode);
 }
 
-void arch_flush_lazy_mmu_mode(void)
-{
-	preempt_disable();
-
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-		arch_leave_lazy_mmu_mode();
-		arch_enter_lazy_mmu_mode();
-	}
-
-	preempt_enable();
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -475,6 +475,7 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.lazy_mode = {
 		.enter = paravirt_nop,
 		.leave = paravirt_nop,
+		.flush = paravirt_nop,
 	},
 
 	.set_fixmap = native_set_fixmap,

arch/x86/kernel/setup.c

@@ -507,11 +507,14 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
  * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * On 64bit, old kexec-tools need to under 896MiB.
  */
 #ifdef CONFIG_X86_32
-# define CRASH_KERNEL_ADDR_MAX	(512 << 20)
+# define CRASH_KERNEL_ADDR_LOW_MAX	(512 << 20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX	(512 << 20)
 #else
-# define CRASH_KERNEL_ADDR_MAX	MAXMEM
+# define CRASH_KERNEL_ADDR_LOW_MAX	(896UL<<20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX	MAXMEM
 #endif
 
 static void __init reserve_crashkernel_low(void)
@@ -521,19 +524,35 @@ static void __init reserve_crashkernel_low(void)
 	unsigned long long low_base = 0, low_size = 0;
 	unsigned long total_low_mem;
 	unsigned long long base;
+	bool auto_set = false;
 	int ret;
 
 	total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT));
+	/* crashkernel=Y,low */
 	ret = parse_crashkernel_low(boot_command_line, total_low_mem,
 						&low_size, &base);
-	if (ret != 0 || low_size <= 0)
-		return;
+	if (ret != 0) {
+		/*
+		 * two parts from lib/swiotlb.c:
+		 *	swiotlb size: user specified with swiotlb= or default.
+		 *	swiotlb overflow buffer: now is hardcoded to 32k.
+		 *		We round it to 8M for other buffers that
+		 *		may need to stay low too.
+		 */
+		low_size = swiotlb_size_or_default() + (8UL<<20);
+		auto_set = true;
+	} else {
+		/* passed with crashkernel=0,low ? */
+		if (!low_size)
+			return;
+	}
 
 	low_base = memblock_find_in_range(low_size, (1ULL<<32),
 					low_size, alignment);
 
 	if (!low_base) {
-		pr_info("crashkernel low reservation failed - No suitable area found.\n");
+		if (!auto_set)
+			pr_info("crashkernel low reservation failed - No suitable area found.\n");
 
 		return;
 	}
@@ -554,14 +573,22 @@ static void __init reserve_crashkernel(void)
 	const unsigned long long alignment = 16<<20;	/* 16M */
 	unsigned long long total_mem;
 	unsigned long long crash_size, crash_base;
+	bool high = false;
 	int ret;
 
 	total_mem = memblock_phys_mem_size();
 
+	/* crashkernel=XM */
 	ret = parse_crashkernel(boot_command_line, total_mem,
 			&crash_size, &crash_base);
-	if (ret != 0 || crash_size <= 0)
-		return;
+	if (ret != 0 || crash_size <= 0) {
+		/* crashkernel=X,high */
+		ret = parse_crashkernel_high(boot_command_line, total_mem,
+				&crash_size, &crash_base);
+		if (ret != 0 || crash_size <= 0)
+			return;
+		high = true;
+	}
 
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
@@ -569,7 +596,9 @@ static void __init reserve_crashkernel(void)
 		 *  kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
 		 */
 		crash_base = memblock_find_in_range(alignment,
-			       CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
+					high ? CRASH_KERNEL_ADDR_HIGH_MAX :
+					       CRASH_KERNEL_ADDR_LOW_MAX,
+					crash_size, alignment);
 
 		if (!crash_base) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");

arch/x86/kvm/lapic.c

@@ -1857,7 +1857,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
 	if (!pv_eoi_enabled(vcpu))
 		return 0;
 	return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
-					 addr);
+					 addr, sizeof(u8));
 }
 
 void kvm_lapic_init(void)