Merge tag 'drm-intel-next-2015-03-27-merge' of git://anongit.freedesktop.org/drm-intel into drm-next

This backmerges 4.0-rc6 due to the recent fixes in rc5/6

- DP link rate refactoring from Ville
- byt/bsw rps tuning from Chris
- kerneldoc for the shrinker code
- more dynamic ppgtt pte work (Michel, Ben, ...)
- vlv dpll code refactoring to prep fro bxt (Imre)
- refactoring the sprite colorkey code (Ville)
- rotated ggtt view support from Tvrtko
- roll out struct drm_atomic_state to prep for atomic update (Ander)

* tag 'drm-intel-next-2015-03-27-merge' of git://anongit.freedesktop.org/drm-intel: (473 commits)
  Linux 4.0-rc6
  arm64: juno: Fix misleading name of UART reference clock
  drm/i915: Update DRIVER_DATE to 20150327
  drm/i915: Skip allocating shadow batch for 0-length batches
  drm/i915: Handle error to get connector state when staging config
  drm/i915: Compare GGTT view structs instead of types
  drm/i915: fix simple_return.cocci warnings
  drm/i915: Add module param to test the load detect code
  drm/i915: Remove usage of encoder->new_crtc from clock computations
  drm/i915: Don't look at staged config crtc when changing DRRS state
  drm/i915: Convert intel_pipe_will_have_type() to using atomic state
  drm/i915: Pass an atomic state to modeset_global_resources() functions
  drm/i915: Add dynamic page trace events
  drm/i915: Finish gen6/7 dynamic page table allocation
  drm/i915: Remove unnecessary gen6_ppgtt_unmap_pages
  drm/i915: Fix i915_dma_map_single positive error code
  drm/i915: Prevent out of range pt in gen6_for_each_pde
  drm/i915: fix definition of the DRM_IOCTL_I915_GET_SPRITE_COLORKEY ioctl
  drm/i915: Rip out GET_SPRITE_COLORKEY ioctl
  watchdog: imgpdc: Fix default heartbeat
  ...

Documentation/DocBook/drm.tmpl

@@ -4184,7 +4184,7 @@ int num_ioctls;</synopsis>
       <sect2>
         <title>Buffer Object Eviction</title>
 	<para>
-	  This section documents the interface function for evicting buffer
+	  This section documents the interface functions for evicting buffer
 	  objects to make space available in the virtual gpu address spaces.
 	  Note that this is mostly orthogonal to shrinking buffer objects
 	  caches, which has the goal to make main memory (shared with the gpu
@@ -4192,6 +4192,17 @@ int num_ioctls;</synopsis>
 	</para>
 !Idrivers/gpu/drm/i915/i915_gem_evict.c
       </sect2>
+      <sect2>
+        <title>Buffer Object Memory Shrinking</title>
+	<para>
+	  This section documents the interface function for shrinking memory
+	  usage of buffer object caches. Shrinking is used to make main memory
+	  available.  Note that this is mostly orthogonal to evicting buffer
+	  objects, which has the goal to make space in gpu virtual address
+	  spaces.
+	</para>
+!Idrivers/gpu/drm/i915/i915_gem_shrinker.c
+      </sect2>
     </sect1>
 
     <sect1>

MAINTAINERS

@@ -1186,7 +1186,7 @@ M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-mvebu/
-F:	drivers/rtc/armada38x-rtc
+F:	drivers/rtc/rtc-armada38x.c
 
 ARM/Marvell Berlin SoC support
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
@@ -1362,6 +1362,7 @@ F:	drivers/i2c/busses/i2c-rk3x.c
 F:	drivers/*/*rockchip*
 F:	drivers/*/*/*rockchip*
 F:	sound/soc/rockchip/
+N:	rockchip
 
 ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
 M:	Kukjin Kim <kgene@kernel.org>
@@ -1675,8 +1676,8 @@ F:	drivers/misc/eeprom/at24.c
 F:	include/linux/platform_data/at24.h
 
 ATA OVER ETHERNET (AOE) DRIVER
-M:	"Ed L. Cashin" <ecashin@coraid.com>
+M:	"Ed L. Cashin" <ed.cashin@acm.org>
-W:	http://support.coraid.com/support/linux
+W:	http://www.openaoe.org/
 S:	Supported
 F:	Documentation/aoe/
 F:	drivers/block/aoe/
@@ -1741,7 +1742,7 @@ S:	Maintained
 F:	drivers/net/ethernet/atheros/
 
 ATM
-M:	Chas Williams <chas@cmf.nrl.navy.mil>
+M:	Chas Williams <3chas3@gmail.com>
 L:	linux-atm-general@lists.sourceforge.net (moderated for non-subscribers)
 L:	netdev@vger.kernel.org
 W:	http://linux-atm.sourceforge.net
@@ -3252,6 +3253,13 @@ S:	Maintained
 F:	Documentation/hwmon/dme1737
 F:	drivers/hwmon/dme1737.c
 
+DMI/SMBIOS SUPPORT
+M:	Jean Delvare <jdelvare@suse.de>
+S:	Maintained
+F:	drivers/firmware/dmi-id.c
+F:	drivers/firmware/dmi_scan.c
+F:	include/linux/dmi.h
+
 DOCKING STATION DRIVER
 M:	Shaohua Li <shaohua.li@intel.com>
 L:	linux-acpi@vger.kernel.org
@@ -10206,6 +10214,13 @@ S:	Maintained
 F:	Documentation/usb/ohci.txt
 F:	drivers/usb/host/ohci*
 
+USB OTG FSM (Finite State Machine)
+M:	Peter Chen <Peter.Chen@freescale.com>
+T:	git git://github.com/hzpeterchen/linux-usb.git
+L:	linux-usb@vger.kernel.org
+S:	Maintained
+F:	drivers/usb/common/usb-otg-fsm.c
+
 USB OVER IP DRIVER
 M:	Valentina Manea <valentina.manea.m@gmail.com>
 M:	Shuah Khan <shuah.kh@samsung.com>

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc6
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*

arch/arc/kernel/signal.c

@@ -67,7 +67,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs,
 	       sigset_t *set)
 {
 	int err;
-	err = __copy_to_user(&(sf->uc.uc_mcontext.regs), regs,
+	err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), regs,
 			     sizeof(sf->uc.uc_mcontext.regs.scratch));
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
 
@@ -83,7 +83,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
 	if (!err)
 		set_current_blocked(&set);
 
-	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs),
+	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs.scratch),
 				sizeof(sf->uc.uc_mcontext.regs.scratch));
 
 	return err;
@@ -131,6 +131,15 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	/* Don't restart from sigreturn */
 	syscall_wont_restart(regs);
 
+	/*
+	 * Ensure that sigreturn always returns to user mode (in case the
+	 * regs saved on user stack got fudged between save and sigreturn)
+	 * Otherwise it is easy to panic the kernel with a custom
+	 * signal handler and/or restorer which clobberes the status32/ret
+	 * to return to a bogus location in kernel mode.
+	 */
+	regs->status32 |= STATUS_U_MASK;
+
 	return regs->r0;
 
 badframe:
@@ -229,8 +238,11 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
 
 	/*
 	 * handler returns using sigreturn stub provided already by userpsace
+	 * If not, nuke the process right away
 	 */
-	BUG_ON(!(ksig->ka.sa.sa_flags & SA_RESTORER));
+	if(!(ksig->ka.sa.sa_flags & SA_RESTORER))
+		return 1;
+
 	regs->blink = (unsigned long)ksig->ka.sa.sa_restorer;
 
 	/* User Stack for signal handler will be above the frame just carved */
@@ -296,12 +308,12 @@ static void
 handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
 	sigset_t *oldset = sigmask_to_save();
-	int ret;
+	int failed;
 
 	/* Set up the stack frame */
-	ret = setup_rt_frame(ksig, oldset, regs);
+	failed = setup_rt_frame(ksig, oldset, regs);
 
-	signal_setup_done(ret, ksig, 0);
+	signal_setup_done(failed, ksig, 0);
 }
 
 void do_signal(struct pt_regs *regs)

arch/arm/Kconfig

@@ -619,6 +619,7 @@ config ARCH_PXA
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
 	select HAVE_IDE
+	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
 	select PLAT_PXA
 	select SPARSE_IRQ

arch/arm/boot/dts/dm8168-evm.dts

@@ -36,6 +36,20 @@
 		>;
 	};
 
+	mmc_pins: pinmux_mmc_pins {
+		pinctrl-single,pins = <
+			DM816X_IOPAD(0x0a70, MUX_MODE0)			/* SD_POW */
+			DM816X_IOPAD(0x0a74, MUX_MODE0)			/* SD_CLK */
+			DM816X_IOPAD(0x0a78, MUX_MODE0)			/* SD_CMD */
+			DM816X_IOPAD(0x0a7C, MUX_MODE0)			/* SD_DAT0 */
+			DM816X_IOPAD(0x0a80, MUX_MODE0)			/* SD_DAT1 */
+			DM816X_IOPAD(0x0a84, MUX_MODE0)			/* SD_DAT2 */
+			DM816X_IOPAD(0x0a88, MUX_MODE0)			/* SD_DAT2 */
+			DM816X_IOPAD(0x0a8c, MUX_MODE2)			/* GP1[7] */
+			DM816X_IOPAD(0x0a90, MUX_MODE2)			/* GP1[8] */
+		>;
+	};
+
 	usb0_pins: pinmux_usb0_pins {
 		pinctrl-single,pins = <
 			DM816X_IOPAD(0x0d00, MUX_MODE0)			/* USB0_DRVVBUS */
@@ -137,7 +151,12 @@
 };
 
 &mmc1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mmc_pins>;
 	vmmc-supply = <&vmmcsd_fixed>;
+	bus-width = <4>;
+	cd-gpios = <&gpio2 7 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 8 GPIO_ACTIVE_LOW>;
 };
 
 /* At least dm8168-evm rev c won't support multipoint, later may */

arch/arm/boot/dts/dm816x.dtsi

@@ -150,17 +150,27 @@
 		};
 
 		gpio1: gpio@48032000 {
-			compatible = "ti,omap3-gpio";
+			compatible = "ti,omap4-gpio";
 			ti,hwmods = "gpio1";
+			ti,gpio-always-on;
 			reg = <0x48032000 0x1000>;
-			interrupts = <97>;
+			interrupts = <96>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
 		};
 
 		gpio2: gpio@4804c000 {
-			compatible = "ti,omap3-gpio";
+			compatible = "ti,omap4-gpio";
 			ti,hwmods = "gpio2";
+			ti,gpio-always-on;
 			reg = <0x4804c000 0x1000>;
-			interrupts = <99>;
+			interrupts = <98>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
 		};
 
 		gpmc: gpmc@50000000 {

arch/arm/boot/dts/dra7.dtsi

@@ -1111,7 +1111,6 @@
 					      "wkupclk", "refclk",
 					      "div-clk", "phy-div";
 				#phy-cells = <0>;
-				ti,hwmods = "pcie1-phy";
 			};
 
 			pcie2_phy: pciephy@4a095000 {
@@ -1130,7 +1129,6 @@
 					      "wkupclk", "refclk",
 					      "div-clk", "phy-div";
 				#phy-cells = <0>;
-				ti,hwmods = "pcie2-phy";
 				status = "disabled";
 			};
 		};

arch/arm/boot/dts/omap3.dtsi

@@ -92,6 +92,8 @@
 			ti,hwmods = "aes";
 			reg = <0x480c5000 0x50>;
 			interrupts = <0>;
+			dmas = <&sdma 65 &sdma 66>;
+			dma-names = "tx", "rx";
 		};
 
 		prm: prm@48306000 {
@@ -550,6 +552,8 @@
 			ti,hwmods = "sham";
 			reg = <0x480c3000 0x64>;
 			interrupts = <49>;
+			dmas = <&sdma 69>;
+			dma-names = "rx";
 		};
 
 		smartreflex_core: smartreflex@480cb000 {

arch/arm/boot/dts/rk3288.dtsi

@@ -411,6 +411,7 @@
 			"mac_clk_rx", "mac_clk_tx",
 			"clk_mac_ref", "clk_mac_refout",
 			"aclk_mac", "pclk_mac";
+		status = "disabled";
 	};
 
 	usb_host0_ehci: usb@ff500000 {

arch/arm/boot/dts/socfpga.dtsi

@@ -660,7 +660,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0xfff01000 0x1000>;
-			interrupts = <0 156 4>;
+			interrupts = <0 155 4>;
 			num-cs = <4>;
 			clocks = <&spi_m_clk>;
 			status = "disabled";

arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts

@@ -56,6 +56,22 @@
 	model = "Olimex A10-OLinuXino-LIME";
 	compatible = "olimex,a10-olinuxino-lime", "allwinner,sun4i-a10";
 
+	cpus {
+		cpu0: cpu@0 {
+			/*
+			 * The A10-Lime is known to be unstable
+			 * when running at 1008 MHz
+			 */
+			operating-points = <
+				/* kHz    uV */
+				912000  1350000
+				864000  1300000
+				624000  1250000
+				>;
+			cooling-max-level = <2>;
+		};
+	};
+
 	soc@01c00000 {
 		emac: ethernet@01c0b000 {
 			pinctrl-names = "default";

arch/arm/boot/dts/sun4i-a10.dtsi

@@ -75,7 +75,6 @@
 			clock-latency = <244144>; /* 8 32k periods */
 			operating-points = <
 				/* kHz    uV */
-				1056000 1500000
 				1008000 1400000
 				912000  1350000
 				864000  1300000
@@ -83,7 +82,7 @@
 				>;
 			#cooling-cells = <2>;
 			cooling-min-level = <0>;
-			cooling-max-level = <4>;
+			cooling-max-level = <3>;
 		};
 	};
 

arch/arm/boot/dts/sun5i-a13.dtsi

@@ -47,7 +47,6 @@
 			clock-latency = <244144>; /* 8 32k periods */
 			operating-points = <
 				/* kHz    uV */
-				1104000	1500000
 				1008000 1400000
 				912000  1350000
 				864000  1300000
@@ -57,7 +56,7 @@
 				>;
 			#cooling-cells = <2>;
 			cooling-min-level = <0>;
-			cooling-max-level = <6>;
+			cooling-max-level = <5>;
 		};
 	};
 

arch/arm/boot/dts/sun7i-a20.dtsi

@@ -105,7 +105,6 @@
 			clock-latency = <244144>; /* 8 32k periods */
 			operating-points = <
 				/* kHz    uV */
-				1008000 1450000
 				960000  1400000
 				912000  1400000
 				864000  1300000
@@ -116,7 +115,7 @@
 				>;
 			#cooling-cells = <2>;
 			cooling-min-level = <0>;
-			cooling-max-level = <7>;
+			cooling-max-level = <6>;
 		};
 
 		cpu@1 {

arch/arm/crypto/aesbs-core.S_shipped

@@ -58,14 +58,18 @@
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__	7
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
 #endif
 
 #ifdef __thumb__
 # define adrl adr
 #endif
 
-#if __ARM_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
 .text
 .syntax	unified 	@ ARMv7-capable assembler is expected to handle this
 #ifdef __thumb2__
@@ -74,8 +78,6 @@
 .code   32
 #endif
 
-.fpu	neon
-
 .type	_bsaes_decrypt8,%function
 .align	4
 _bsaes_decrypt8:
@@ -2095,9 +2097,11 @@ bsaes_xts_decrypt:
 	vld1.8	{q8}, [r0]			@ initial tweak
 	adr	r2, .Lxts_magic
 
+#ifndef	XTS_CHAIN_TWEAK
 	tst	r9, #0xf			@ if not multiple of 16
 	it	ne				@ Thumb2 thing, sanity check in ARM
 	subne	r9, #0x10			@ subtract another 16 bytes
+#endif
 	subs	r9, #0x80
 
 	blo	.Lxts_dec_short

arch/arm/crypto/bsaes-armv7.pl

@@ -701,14 +701,18 @@ $code.=<<___;
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__	7
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
 #endif
 
 #ifdef __thumb__
 # define adrl adr
 #endif
 
-#if __ARM_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
 .text
 .syntax	unified 	@ ARMv7-capable assembler is expected to handle this
 #ifdef __thumb2__
@@ -717,8 +721,6 @@ $code.=<<___;
 .code   32
 #endif
 
-.fpu	neon
-
 .type	_bsaes_decrypt8,%function
 .align	4
 _bsaes_decrypt8:
@@ -2076,9 +2078,11 @@ bsaes_xts_decrypt:
 	vld1.8	{@XMM[8]}, [r0]			@ initial tweak
 	adr	$magic, .Lxts_magic
 
+#ifndef	XTS_CHAIN_TWEAK
 	tst	$len, #0xf			@ if not multiple of 16
 	it	ne				@ Thumb2 thing, sanity check in ARM
 	subne	$len, #0x10			@ subtract another 16 bytes
+#endif
 	subs	$len, #0x80
 
 	blo	.Lxts_dec_short

arch/arm/include/asm/kvm_mmu.h

@@ -149,31 +149,30 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
 })
 
+#define kvm_pgd_index(addr)			pgd_index(addr)
+
 static inline bool kvm_page_empty(void *ptr)
 {
 	struct page *ptr_page = virt_to_page(ptr);
 	return page_count(ptr_page) == 1;
 }
 
-
 #define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
 #define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
 #define kvm_pud_table_empty(kvm, pudp) (0)
 
 #define KVM_PREALLOC_LEVEL	0
 
-static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
-{
-	return 0;
-}
-
-static inline void kvm_free_hwpgd(struct kvm *kvm) { }
-
 static inline void *kvm_get_hwpgd(struct kvm *kvm)
 {
 	return kvm->arch.pgd;
 }
 
+static inline unsigned int kvm_get_hwpgd_size(void)
+{
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
+}
+
 struct kvm;
 
 #define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))

arch/arm/kernel/setup.c

@@ -246,12 +246,9 @@ static int __get_cpu_architecture(void)
 		if (cpu_arch)
 			cpu_arch += CPU_ARCH_ARMv3;
 	} else if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) {
-		unsigned int mmfr0;
-
 		/* Revised CPUID format. Read the Memory Model Feature
 		 * Register 0 and check for VMSAv7 or PMSAv7 */
-		asm("mrc	p15, 0, %0, c0, c1, 4"
+		unsigned int mmfr0 = read_cpuid_ext(CPUID_EXT_MMFR0);
-		    : "=r" (mmfr0));
 		if ((mmfr0 & 0x0000000f) >= 0x00000003 ||
 		    (mmfr0 & 0x000000f0) >= 0x00000030)
 			cpu_arch = CPU_ARCH_ARMv7;

arch/arm/kvm/mmu.c

@@ -290,7 +290,7 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 	phys_addr_t addr = start, end = start + size;
 	phys_addr_t next;
 
-	pgd = pgdp + pgd_index(addr);
+	pgd = pgdp + kvm_pgd_index(addr);
 	do {
 		next = kvm_pgd_addr_end(addr, end);
 		if (!pgd_none(*pgd))
@@ -355,7 +355,7 @@ static void stage2_flush_memslot(struct kvm *kvm,
 	phys_addr_t next;
 	pgd_t *pgd;
 
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	do {
 		next = kvm_pgd_addr_end(addr, end);
 		stage2_flush_puds(kvm, pgd, addr, next);
@@ -632,6 +632,20 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
 				     __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE);
 }
 
+/* Free the HW pgd, one page at a time */
+static void kvm_free_hwpgd(void *hwpgd)
+{
+	free_pages_exact(hwpgd, kvm_get_hwpgd_size());
+}
+
+/* Allocate the HW PGD, making sure that each page gets its own refcount */
+static void *kvm_alloc_hwpgd(void)
+{
+	unsigned int size = kvm_get_hwpgd_size();
+
+	return alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
+}
+
 /**
  * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
  * @kvm:	The KVM struct pointer for the VM.
@@ -645,15 +659,31 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
  */
 int kvm_alloc_stage2_pgd(struct kvm *kvm)
 {
-	int ret;
 	pgd_t *pgd;
+	void *hwpgd;
 
 	if (kvm->arch.pgd != NULL) {
 		kvm_err("kvm_arch already initialized?\n");
 		return -EINVAL;
 	}
 
+	hwpgd = kvm_alloc_hwpgd();
+	if (!hwpgd)
+		return -ENOMEM;
+
+	/* When the kernel uses more levels of page tables than the
+	 * guest, we allocate a fake PGD and pre-populate it to point
+	 * to the next-level page table, which will be the real
+	 * initial page table pointed to by the VTTBR.
+	 *
+	 * When KVM_PREALLOC_LEVEL==2, we allocate a single page for
+	 * the PMD and the kernel will use folded pud.
+	 * When KVM_PREALLOC_LEVEL==1, we allocate 2 consecutive PUD
+	 * pages.
+	 */
 	if (KVM_PREALLOC_LEVEL > 0) {
+		int i;
+
 		/*
 		 * Allocate fake pgd for the page table manipulation macros to
 		 * work.  This is not used by the hardware and we have no
@@ -661,30 +691,32 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 		 */
 		pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
 				       GFP_KERNEL | __GFP_ZERO);
+
+		if (!pgd) {
+			kvm_free_hwpgd(hwpgd);
+			return -ENOMEM;
+		}
+
+		/* Plug the HW PGD into the fake one. */
+		for (i = 0; i < PTRS_PER_S2_PGD; i++) {
+			if (KVM_PREALLOC_LEVEL == 1)
+				pgd_populate(NULL, pgd + i,
+					     (pud_t *)hwpgd + i * PTRS_PER_PUD);
+			else if (KVM_PREALLOC_LEVEL == 2)
+				pud_populate(NULL, pud_offset(pgd, 0) + i,
+					     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
+		}
 	} else {
 		/*
 		 * Allocate actual first-level Stage-2 page table used by the
 		 * hardware for Stage-2 page table walks.
 		 */
-		pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER);
+		pgd = (pgd_t *)hwpgd;
 	}
 
-	if (!pgd)
-		return -ENOMEM;
-
-	ret = kvm_prealloc_hwpgd(kvm, pgd);
-	if (ret)
-		goto out_err;
-
 	kvm_clean_pgd(pgd);
 	kvm->arch.pgd = pgd;
 	return 0;
-out_err:
-	if (KVM_PREALLOC_LEVEL > 0)
-		kfree(pgd);
-	else
-		free_pages((unsigned long)pgd, S2_PGD_ORDER);
-	return ret;
 }
 
 /**
@@ -785,11 +817,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
 		return;
 
 	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
-	kvm_free_hwpgd(kvm);
+	kvm_free_hwpgd(kvm_get_hwpgd(kvm));
 	if (KVM_PREALLOC_LEVEL > 0)
 		kfree(kvm->arch.pgd);
-	else
+
-		free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER);
 	kvm->arch.pgd = NULL;
 }
 
@@ -799,7 +830,7 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
 	pgd_t *pgd;
 	pud_t *pud;
 
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	if (WARN_ON(pgd_none(*pgd))) {
 		if (!cache)
 			return NULL;
@@ -1089,7 +1120,7 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 	pgd_t *pgd;
 	phys_addr_t next;
 
-	pgd = kvm->arch.pgd + pgd_index(addr);
+	pgd = kvm->arch.pgd + kvm_pgd_index(addr);
 	do {
 		/*
 		 * Release kvm_mmu_lock periodically if the memory region is

arch/arm/mach-omap2/id.c

@@ -720,6 +720,8 @@ static const char * __init omap_get_family(void)
 		return kasprintf(GFP_KERNEL, "OMAP4");
 	else if (soc_is_omap54xx())
 		return kasprintf(GFP_KERNEL, "OMAP5");
+	else if (soc_is_am33xx() || soc_is_am335x())
+		return kasprintf(GFP_KERNEL, "AM33xx");
 	else if (soc_is_am43xx())
 		return kasprintf(GFP_KERNEL, "AM43xx");
 	else if (soc_is_dra7xx())

arch/arm/mach-pxa/irq.c

@@ -11,6 +11,7 @@
  *  it under the terms of the GNU General Public License version 2 as
  *  published by the Free Software Foundation.
  */
+#include <linux/bitops.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
@@ -40,7 +41,6 @@
 #define ICHP_VAL_IRQ		(1 << 31)
 #define ICHP_IRQ(i)		(((i) >> 16) & 0x7fff)
 #define IPR_VALID		(1 << 31)
-#define IRQ_BIT(n)		(((n) - PXA_IRQ(0)) & 0x1f)
 
 #define MAX_INTERNAL_IRQS	128
 
@@ -51,6 +51,7 @@
 static void __iomem *pxa_irq_base;
 static int pxa_internal_irq_nr;
 static bool cpu_has_ipr;
+static struct irq_domain *pxa_irq_domain;
 
 static inline void __iomem *irq_base(int i)
 {
@@ -66,18 +67,20 @@ static inline void __iomem *irq_base(int i)
 void pxa_mask_irq(struct irq_data *d)
 {
 	void __iomem *base = irq_data_get_irq_chip_data(d);
+	irq_hw_number_t irq = irqd_to_hwirq(d);
 	uint32_t icmr = __raw_readl(base + ICMR);
 
-	icmr &= ~(1 << IRQ_BIT(d->irq));
+	icmr &= ~BIT(irq & 0x1f);
 	__raw_writel(icmr, base + ICMR);
 }
 
 void pxa_unmask_irq(struct irq_data *d)
 {
 	void __iomem *base = irq_data_get_irq_chip_data(d);
+	irq_hw_number_t irq = irqd_to_hwirq(d);
 	uint32_t icmr = __raw_readl(base + ICMR);
 
-	icmr |= 1 << IRQ_BIT(d->irq);
+	icmr |= BIT(irq & 0x1f);
 	__raw_writel(icmr, base + ICMR);
 }
 
@@ -118,40 +121,63 @@ asmlinkage void __exception_irq_entry ichp_handle_irq(struct pt_regs *regs)
 	} while (1);
 }
 
-void __init pxa_init_irq(int irq_nr, int (*fn)(struct irq_data *, unsigned int))
+static int pxa_irq_map(struct irq_domain *h, unsigned int virq,
+		       irq_hw_number_t hw)
 {
-	int irq, i, n;
+	void __iomem *base = irq_base(hw / 32);
 
-	BUG_ON(irq_nr > MAX_INTERNAL_IRQS);
+	/* initialize interrupt priority */
+	if (cpu_has_ipr)
+		__raw_writel(hw | IPR_VALID, pxa_irq_base + IPR(hw));
+
+	irq_set_chip_and_handler(virq, &pxa_internal_irq_chip,
+				 handle_level_irq);
+	irq_set_chip_data(virq, base);
+	set_irq_flags(virq, IRQF_VALID);
+
+	return 0;
+}
+
+static struct irq_domain_ops pxa_irq_ops = {
+	.map    = pxa_irq_map,
+	.xlate  = irq_domain_xlate_onecell,
+};
+
+static __init void
+pxa_init_irq_common(struct device_node *node, int irq_nr,
+		    int (*fn)(struct irq_data *, unsigned int))
+{
+	int n;
 
 	pxa_internal_irq_nr = irq_nr;
-	cpu_has_ipr = !cpu_is_pxa25x();
+	pxa_irq_domain = irq_domain_add_legacy(node, irq_nr,
-	pxa_irq_base = io_p2v(0x40d00000);
+					       PXA_IRQ(0), 0,
+					       &pxa_irq_ops, NULL);
+	if (!pxa_irq_domain)
+		panic("Unable to add PXA IRQ domain\n");
+	irq_set_default_host(pxa_irq_domain);
 
 	for (n = 0; n < irq_nr; n += 32) {
 		void __iomem *base = irq_base(n >> 5);
 
 		__raw_writel(0, base + ICMR);	/* disable all IRQs */
 		__raw_writel(0, base + ICLR);	/* all IRQs are IRQ, not FIQ */
-		for (i = n; (i < (n + 32)) && (i < irq_nr); i++) {
-			/* initialize interrupt priority */
-			if (cpu_has_ipr)
-				__raw_writel(i | IPR_VALID, pxa_irq_base + IPR(i));
-
-			irq = PXA_IRQ(i);
-			irq_set_chip_and_handler(irq, &pxa_internal_irq_chip,
-						 handle_level_irq);
-			irq_set_chip_data(irq, base);
-			set_irq_flags(irq, IRQF_VALID);
-		}
 	}
-
 	/* only unmasked interrupts kick us out of idle */
 	__raw_writel(1, irq_base(0) + ICCR);
 
 	pxa_internal_irq_chip.irq_set_wake = fn;
 }
 
+void __init pxa_init_irq(int irq_nr, int (*fn)(struct irq_data *, unsigned int))
+{
+	BUG_ON(irq_nr > MAX_INTERNAL_IRQS);
+
+	pxa_irq_base = io_p2v(0x40d00000);
+	cpu_has_ipr = !cpu_is_pxa25x();
+	pxa_init_irq_common(NULL, irq_nr, fn);
+}
+
 #ifdef CONFIG_PM
 static unsigned long saved_icmr[MAX_INTERNAL_IRQS/32];
 static unsigned long saved_ipr[MAX_INTERNAL_IRQS];
@@ -203,30 +229,6 @@ struct syscore_ops pxa_irq_syscore_ops = {
 };
 
 #ifdef CONFIG_OF
-static struct irq_domain *pxa_irq_domain;
-
-static int pxa_irq_map(struct irq_domain *h, unsigned int virq,
-		       irq_hw_number_t hw)
-{
-	void __iomem *base = irq_base(hw / 32);
-
-	/* initialize interrupt priority */
-	if (cpu_has_ipr)
-		__raw_writel(hw | IPR_VALID, pxa_irq_base + IPR(hw));
-
-	irq_set_chip_and_handler(hw, &pxa_internal_irq_chip,
-				 handle_level_irq);
-	irq_set_chip_data(hw, base);
-	set_irq_flags(hw, IRQF_VALID);
-
-	return 0;
-}
-
-static struct irq_domain_ops pxa_irq_ops = {
-	.map    = pxa_irq_map,
-	.xlate  = irq_domain_xlate_onecell,
-};
-
 static const struct of_device_id intc_ids[] __initconst = {
 	{ .compatible = "marvell,pxa-intc", },
 	{}
@@ -236,7 +238,7 @@ void __init pxa_dt_irq_init(int (*fn)(struct irq_data *, unsigned int))
 {
 	struct device_node *node;
 	struct resource res;
-	int n, ret;
+	int ret;
 
 	node = of_find_matching_node(NULL, intc_ids);
 	if (!node) {
@@ -267,23 +269,6 @@ void __init pxa_dt_irq_init(int (*fn)(struct irq_data *, unsigned int))
 		return;
 	}
 
-	pxa_irq_domain = irq_domain_add_legacy(node, pxa_internal_irq_nr, 0, 0,
+	pxa_init_irq_common(node, pxa_internal_irq_nr, fn);
-					       &pxa_irq_ops, NULL);
-	if (!pxa_irq_domain)
-		panic("Unable to add PXA IRQ domain\n");
-
-	irq_set_default_host(pxa_irq_domain);
-
-	for (n = 0; n < pxa_internal_irq_nr; n += 32) {
-		void __iomem *base = irq_base(n >> 5);
-
-		__raw_writel(0, base + ICMR);	/* disable all IRQs */
-		__raw_writel(0, base + ICLR);	/* all IRQs are IRQ, not FIQ */
-	}
-
-	/* only unmasked interrupts kick us out of idle */
-	__raw_writel(1, irq_base(0) + ICCR);
-
-	pxa_internal_irq_chip.irq_set_wake = fn;
 }
 #endif /* CONFIG_OF */

arch/arm/mach-pxa/zeus.c

@@ -412,7 +412,7 @@ static struct fixed_voltage_config can_regulator_pdata = {
 };
 
 static struct platform_device can_regulator_device = {
-	.name	= "reg-fixed-volage",
+	.name	= "reg-fixed-voltage",
 	.id	= 0,
 	.dev	= {
 		.platform_data	= &can_regulator_pdata,

arch/arm/mach-sunxi/Kconfig

@@ -1,10 +1,12 @@
 menuconfig ARCH_SUNXI
 	bool "Allwinner SoCs" if ARCH_MULTI_V7
 	select ARCH_REQUIRE_GPIOLIB
+	select ARCH_HAS_RESET_CONTROLLER
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
 	select PINCTRL
 	select SUN4I_TIMER
+	select RESET_CONTROLLER
 
 if ARCH_SUNXI
 
@@ -20,10 +22,8 @@ config MACH_SUN5I
 config MACH_SUN6I
 	bool "Allwinner A31 (sun6i) SoCs support"
 	default ARCH_SUNXI
-	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
-	select RESET_CONTROLLER
 	select SUN5I_HSTIMER
 
 config MACH_SUN7I
@@ -37,16 +37,12 @@ config MACH_SUN7I
 config MACH_SUN8I
 	bool "Allwinner A23 (sun8i) SoCs support"
 	default ARCH_SUNXI
-	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
-	select RESET_CONTROLLER
 
 config MACH_SUN9I
 	bool "Allwinner (sun9i) SoCs support"
 	default ARCH_SUNXI
-	select ARCH_HAS_RESET_CONTROLLER
 	select ARM_GIC
-	select RESET_CONTROLLER
 
 endif

arch/arm/mm/cache-l2x0.c

@@ -1131,23 +1131,22 @@ static void __init l2c310_of_parse(const struct device_node *np,
 	}
 
 	ret = l2x0_cache_size_of_parse(np, aux_val, aux_mask, &assoc, SZ_512K);
-	if (ret)
+	if (!ret) {
-		return;
+		switch (assoc) {
-
+		case 16:
-	switch (assoc) {
+			*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-	case 16:
+			*aux_val |= L310_AUX_CTRL_ASSOCIATIVITY_16;
-		*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+			*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-		*aux_val |= L310_AUX_CTRL_ASSOCIATIVITY_16;
+			break;
-		*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+		case 8:
-		break;
+			*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-	case 8:
+			*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-		*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+			break;
-		*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+		default:
-		break;
+			pr_err("L2C-310 OF cache associativity %d invalid, only 8 or 16 permitted\n",
-	default:
+			       assoc);
-		pr_err("L2C-310 OF cache associativity %d invalid, only 8 or 16 permitted\n",
+			break;
-		       assoc);
+		}
-		break;
 	}
 
 	prefetch = l2x0_saved_regs.prefetch_ctrl;

arch/arm/mm/dma-mapping.c

@@ -171,7 +171,7 @@ static int __dma_supported(struct device *dev, u64 mask, bool warn)
 	 */
 	if (sizeof(mask) != sizeof(dma_addr_t) &&
 	    mask > (dma_addr_t)~0 &&
-	    dma_to_pfn(dev, ~0) < max_pfn) {
+	    dma_to_pfn(dev, ~0) < max_pfn - 1) {
 		if (warn) {
 			dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n",
 				 mask);

arch/arm/mm/fault.c

@@ -552,6 +552,7 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	pr_alert("Unhandled fault: %s (0x%03x) at 0x%08lx\n",
 		inf->name, fsr, addr);
+	show_pte(current->mm, addr);
 
 	info.si_signo = inf->sig;
 	info.si_errno = 0;

arch/arm/mm/pageattr.c

@@ -49,7 +49,10 @@ static int change_memory_common(unsigned long addr, int numpages,
 		WARN_ON_ONCE(1);
 	}
 
-	if (!is_module_address(start) || !is_module_address(end - 1))
+	if (start < MODULES_VADDR || start >= MODULES_END)
+		return -EINVAL;
+
+	if (end < MODULES_VADDR || start >= MODULES_END)
 		return -EINVAL;
 
 	data.set_mask = set_mask;

arch/arm/plat-omap/dmtimer.c

@@ -799,6 +799,7 @@ static int omap_dm_timer_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	const struct of_device_id *match;
 	const struct dmtimer_platform_data *pdata;
+	int ret;
 
 	match = of_match_device(of_match_ptr(omap_timer_match), dev);
 	pdata = match ? match->data : dev->platform_data;
@@ -860,7 +861,12 @@ static int omap_dm_timer_probe(struct platform_device *pdev)
 	}
 
 	if (!timer->reserved) {
-		pm_runtime_get_sync(dev);
+		ret = pm_runtime_get_sync(dev);
+		if (ret < 0) {
+			dev_err(dev, "%s: pm_runtime_get_sync failed!\n",
+				__func__);
+			goto err_get_sync;
+		}
 		__omap_dm_timer_init_regs(timer);
 		pm_runtime_put(dev);
 	}
@@ -873,6 +879,11 @@ static int omap_dm_timer_probe(struct platform_device *pdev)
 	dev_dbg(dev, "Device Probed.\n");
 
 	return 0;
+
+err_get_sync:
+	pm_runtime_put_noidle(dev);
+	pm_runtime_disable(dev);
+	return ret;
 }
 
 /**
@@ -899,6 +910,8 @@ static int omap_dm_timer_remove(struct platform_device *pdev)
 		}
 	spin_unlock_irqrestore(&dm_timer_lock, flags);
 
+	pm_runtime_disable(&pdev->dev);
+
 	return ret;
 }
 

arch/arm64/boot/dts/arm/juno-clocks.dtsi

@@ -8,7 +8,7 @@
  */
 
 	/* SoC fixed clocks */
-	soc_uartclk: refclk72738khz {
+	soc_uartclk: refclk7273800hz {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <7273800>;

arch/arm64/include/asm/cmpxchg.h

@@ -246,14 +246,30 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	__ret; \
 })
 
-#define this_cpu_cmpxchg_1(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+#define _protect_cmpxchg_local(pcp, o, n)			\
-#define this_cpu_cmpxchg_2(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+({								\
-#define this_cpu_cmpxchg_4(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+	typeof(*raw_cpu_ptr(&(pcp))) __ret;			\
-#define this_cpu_cmpxchg_8(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+	preempt_disable();					\
+	__ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n);	\
+	preempt_enable();					\
+	__ret;							\
+})
 
-#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \
+#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
-	cmpxchg_double_local(raw_cpu_ptr(&(ptr1)), raw_cpu_ptr(&(ptr2)), \
+#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
-				o1, o2, n1, n2)
+#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+
+#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2)		\
+({									\
+	int __ret;							\
+	preempt_disable();						\
+	__ret = cmpxchg_double_local(	raw_cpu_ptr(&(ptr1)),		\
+					raw_cpu_ptr(&(ptr2)),		\
+					o1, o2, n1, n2);		\
+	preempt_enable();						\
+	__ret;								\
+})
 
 #define cmpxchg64(ptr,o,n)		cmpxchg((ptr),(o),(n))
 #define cmpxchg64_local(ptr,o,n)	cmpxchg_local((ptr),(o),(n))

arch/arm64/include/asm/kvm_arm.h

@@ -129,6 +129,9 @@
  * 40 bits wide (T0SZ = 24).  Systems with a PARange smaller than 40 bits are
  * not known to exist and will break with this configuration.
  *
+ * VTCR_EL2.PS is extracted from ID_AA64MMFR0_EL1.PARange at boot time
+ * (see hyp-init.S).
+ *
  * Note that when using 4K pages, we concatenate two first level page tables
  * together.
  *
@@ -138,7 +141,6 @@
 #ifdef CONFIG_ARM64_64K_PAGES
 /*
  * Stage2 translation configuration:
- * 40bits output (PS = 2)
  * 40bits input  (T0SZ = 24)
  * 64kB pages (TG0 = 1)
  * 2 level page tables (SL = 1)
@@ -150,7 +152,6 @@
 #else
 /*
  * Stage2 translation configuration:
- * 40bits output (PS = 2)
  * 40bits input  (T0SZ = 24)
  * 4kB pages (TG0 = 0)
  * 3 level page tables (SL = 1)

arch/arm64/include/asm/kvm_mmu.h

@@ -158,6 +158,8 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 #define PTRS_PER_S2_PGD		(1 << PTRS_PER_S2_PGD_SHIFT)
 #define S2_PGD_ORDER		get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
 
+#define kvm_pgd_index(addr)	(((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+
 /*
  * If we are concatenating first level stage-2 page tables, we would have less
  * than or equal to 16 pointers in the fake PGD, because that's what the
@@ -171,43 +173,6 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
 #define KVM_PREALLOC_LEVEL	(0)
 #endif
 
-/**
- * kvm_prealloc_hwpgd - allocate inital table for VTTBR
- * @kvm:	The KVM struct pointer for the VM.
- * @pgd:	The kernel pseudo pgd
- *
- * When the kernel uses more levels of page tables than the guest, we allocate
- * a fake PGD and pre-populate it to point to the next-level page table, which
- * will be the real initial page table pointed to by the VTTBR.
- *
- * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and
- * the kernel will use folded pud.  When KVM_PREALLOC_LEVEL==1, we
- * allocate 2 consecutive PUD pages.
- */
-static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd)
-{
-	unsigned int i;
-	unsigned long hwpgd;
-
-	if (KVM_PREALLOC_LEVEL == 0)
-		return 0;
-
-	hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT);
-	if (!hwpgd)
-		return -ENOMEM;
-
-	for (i = 0; i < PTRS_PER_S2_PGD; i++) {
-		if (KVM_PREALLOC_LEVEL == 1)
-			pgd_populate(NULL, pgd + i,
-				     (pud_t *)hwpgd + i * PTRS_PER_PUD);
-		else if (KVM_PREALLOC_LEVEL == 2)
-			pud_populate(NULL, pud_offset(pgd, 0) + i,
-				     (pmd_t *)hwpgd + i * PTRS_PER_PMD);
-	}
-
-	return 0;
-}
-
 static inline void *kvm_get_hwpgd(struct kvm *kvm)
 {
 	pgd_t *pgd = kvm->arch.pgd;
@@ -224,12 +189,11 @@ static inline void *kvm_get_hwpgd(struct kvm *kvm)
 	return pmd_offset(pud, 0);
 }
 
-static inline void kvm_free_hwpgd(struct kvm *kvm)
+static inline unsigned int kvm_get_hwpgd_size(void)
 {
-	if (KVM_PREALLOC_LEVEL > 0) {
+	if (KVM_PREALLOC_LEVEL > 0)
-		unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm);
+		return PTRS_PER_S2_PGD * PAGE_SIZE;
-		free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT);
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
-	}
 }
 
 static inline bool kvm_page_empty(void *ptr)

arch/arm64/include/asm/mmu_context.h

@@ -151,6 +151,15 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	unsigned int cpu = smp_processor_id();
 
+	/*
+	 * init_mm.pgd does not contain any user mappings and it is always
+	 * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
+	 */
+	if (next == &init_mm) {
+		cpu_set_reserved_ttbr0();
+		return;
+	}
+
 	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
 		check_and_switch_context(next, tsk);
 }

arch/arm64/include/asm/percpu.h

@@ -204,25 +204,47 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
 	return ret;
 }
 
-#define _percpu_add(pcp, val) \
+#define _percpu_read(pcp)						\
-	__percpu_add(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+({									\
+	typeof(pcp) __retval;						\
+	preempt_disable();						\
+	__retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), 	\
+					      sizeof(pcp));		\
+	preempt_enable();						\
+	__retval;							\
+})
 
-#define _percpu_add_return(pcp, val) (typeof(pcp)) (_percpu_add(pcp, val))
+#define _percpu_write(pcp, val)						\
+do {									\
+	preempt_disable();						\
+	__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), 	\
+				sizeof(pcp));				\
+	preempt_enable();						\
+} while(0)								\
+
+#define _pcp_protect(operation, pcp, val)			\
+({								\
+	typeof(pcp) __retval;					\
+	preempt_disable();					\
+	__retval = (typeof(pcp))operation(raw_cpu_ptr(&(pcp)),	\
+					  (val), sizeof(pcp));	\
+	preempt_enable();					\
+	__retval;						\
+})
+
+#define _percpu_add(pcp, val) \
+	_pcp_protect(__percpu_add, pcp, val)
+
+#define _percpu_add_return(pcp, val) _percpu_add(pcp, val)
 
 #define _percpu_and(pcp, val) \
-	__percpu_and(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+	_pcp_protect(__percpu_and, pcp, val)
 
 #define _percpu_or(pcp, val) \
-	__percpu_or(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+	_pcp_protect(__percpu_or, pcp, val)
-
-#define _percpu_read(pcp) (typeof(pcp))	\
-	(__percpu_read(raw_cpu_ptr(&(pcp)), sizeof(pcp)))
-
-#define _percpu_write(pcp, val) \
-	__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp))
 
 #define _percpu_xchg(pcp, val) (typeof(pcp)) \
-	(__percpu_xchg(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp)))
+	_pcp_protect(__percpu_xchg, pcp, (unsigned long)(val))
 
 #define this_cpu_add_1(pcp, val) _percpu_add(pcp, val)
 #define this_cpu_add_2(pcp, val) _percpu_add(pcp, val)

arch/arm64/include/asm/proc-fns.h

@@ -39,7 +39,11 @@ extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
 #include <asm/memory.h>
 
-#define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm)
+#define cpu_switch_mm(pgd,mm)				\
+do {							\
+	BUG_ON(pgd == swapper_pg_dir);			\
+	cpu_do_switch_mm(virt_to_phys(pgd),mm);		\
+} while (0)
 
 #define cpu_get_pgd()					\
 ({							\

arch/arm64/kernel/efi.c

@@ -337,7 +337,11 @@ core_initcall(arm64_dmi_init);
 
 static void efi_set_pgd(struct mm_struct *mm)
 {
-	cpu_switch_mm(mm->pgd, mm);
+	if (mm == &init_mm)
+		cpu_set_reserved_ttbr0();
+	else
+		cpu_switch_mm(mm->pgd, mm);
+
 	flush_tlb_all();
 	if (icache_is_aivivt())
 		__flush_icache_all();

arch/arm64/mm/dma-mapping.c

@@ -51,7 +51,7 @@ static int __init early_coherent_pool(char *p)
 }
 early_param("coherent_pool", early_coherent_pool);
 
-static void *__alloc_from_pool(size_t size, struct page **ret_page)
+static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags)
 {
 	unsigned long val;
 	void *ptr = NULL;
@@ -67,6 +67,8 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page)
 
 		*ret_page = phys_to_page(phys);
 		ptr = (void *)val;
+		if (flags & __GFP_ZERO)
+			memset(ptr, 0, size);
 	}
 
 	return ptr;
@@ -101,6 +103,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 		flags |= GFP_DMA;
 	if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) {
 		struct page *page;
+		void *addr;
 
 		size = PAGE_ALIGN(size);
 		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
@@ -109,7 +112,10 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 			return NULL;
 
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
-		return page_address(page);
+		addr = page_address(page);
+		if (flags & __GFP_ZERO)
+			memset(addr, 0, size);
+		return addr;
 	} else {
 		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
 	}
@@ -146,7 +152,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 
 	if (!coherent && !(flags & __GFP_WAIT)) {
 		struct page *page = NULL;
-		void *addr = __alloc_from_pool(size, &page);
+		void *addr = __alloc_from_pool(size, &page, flags);
 
 		if (addr)
 			*dma_handle = phys_to_dma(dev, page_to_phys(page));

arch/metag/include/asm/io.h

@@ -2,6 +2,7 @@
 #define _ASM_METAG_IO_H
 
 #include <linux/types.h>
+#include <asm/pgtable-bits.h>
 
 #define IO_SPACE_LIMIT  0
 

arch/metag/include/asm/pgtable-bits.h

@@ -0,0 +1,104 @@
+/*
+ * Meta page table definitions.
+ */
+
+#ifndef _METAG_PGTABLE_BITS_H
+#define _METAG_PGTABLE_BITS_H
+
+#include <asm/metag_mem.h>
+
+/*
+ * Definitions for MMU descriptors
+ *
+ * These are the hardware bits in the MMCU pte entries.
+ * Derived from the Meta toolkit headers.
+ */
+#define _PAGE_PRESENT		MMCU_ENTRY_VAL_BIT
+#define _PAGE_WRITE		MMCU_ENTRY_WR_BIT
+#define _PAGE_PRIV		MMCU_ENTRY_PRIV_BIT
+/* Write combine bit - this can cause writes to occur out of order */
+#define _PAGE_WR_COMBINE	MMCU_ENTRY_WRC_BIT
+/* Sys coherent bit - this bit is never used by Linux */
+#define _PAGE_SYS_COHERENT	MMCU_ENTRY_SYS_BIT
+#define _PAGE_ALWAYS_ZERO_1	0x020
+#define _PAGE_CACHE_CTRL0	0x040
+#define _PAGE_CACHE_CTRL1	0x080
+#define _PAGE_ALWAYS_ZERO_2	0x100
+#define _PAGE_ALWAYS_ZERO_3	0x200
+#define _PAGE_ALWAYS_ZERO_4	0x400
+#define _PAGE_ALWAYS_ZERO_5	0x800
+
+/* These are software bits that we stuff into the gaps in the hardware
+ * pte entries that are not used.  Note, these DO get stored in the actual
+ * hardware, but the hardware just does not use them.
+ */
+#define _PAGE_ACCESSED		_PAGE_ALWAYS_ZERO_1
+#define _PAGE_DIRTY		_PAGE_ALWAYS_ZERO_2
+
+/* Pages owned, and protected by, the kernel. */
+#define _PAGE_KERNEL		_PAGE_PRIV
+
+/* No cacheing of this page */
+#define _PAGE_CACHE_WIN0	(MMCU_CWIN_UNCACHED << MMCU_ENTRY_CWIN_S)
+/* burst cacheing - good for data streaming */
+#define _PAGE_CACHE_WIN1	(MMCU_CWIN_BURST << MMCU_ENTRY_CWIN_S)
+/* One cache way per thread */
+#define _PAGE_CACHE_WIN2	(MMCU_CWIN_C1SET << MMCU_ENTRY_CWIN_S)
+/* Full on cacheing */
+#define _PAGE_CACHE_WIN3	(MMCU_CWIN_CACHED << MMCU_ENTRY_CWIN_S)
+
+#define _PAGE_CACHEABLE		(_PAGE_CACHE_WIN3 | _PAGE_WR_COMBINE)
+
+/* which bits are used for cache control ... */
+#define _PAGE_CACHE_MASK	(_PAGE_CACHE_CTRL0 | _PAGE_CACHE_CTRL1 | \
+				 _PAGE_WR_COMBINE)
+
+/* This is a mask of the bits that pte_modify is allowed to change. */
+#define _PAGE_CHG_MASK		(PAGE_MASK)
+
+#define _PAGE_SZ_SHIFT		1
+#define _PAGE_SZ_4K		(0x0)
+#define _PAGE_SZ_8K		(0x1 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_16K		(0x2 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_32K		(0x3 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_64K		(0x4 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_128K		(0x5 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_256K		(0x6 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_512K		(0x7 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_1M		(0x8 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_2M		(0x9 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_4M		(0xa << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_MASK		(0xf << _PAGE_SZ_SHIFT)
+
+#if defined(CONFIG_PAGE_SIZE_4K)
+#define _PAGE_SZ		(_PAGE_SZ_4K)
+#elif defined(CONFIG_PAGE_SIZE_8K)
+#define _PAGE_SZ		(_PAGE_SZ_8K)
+#elif defined(CONFIG_PAGE_SIZE_16K)
+#define _PAGE_SZ		(_PAGE_SZ_16K)
+#endif
+#define _PAGE_TABLE		(_PAGE_SZ | _PAGE_PRESENT)
+
+#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_8K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_16K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_32K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_64K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_128K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_256K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K)
+# define _PAGE_SZHUGE		(_PAGE_SZ_512K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M)
+# define _PAGE_SZHUGE		(_PAGE_SZ_1M)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M)
+# define _PAGE_SZHUGE		(_PAGE_SZ_2M)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M)
+# define _PAGE_SZHUGE		(_PAGE_SZ_4M)
+#endif
+
+#endif /* _METAG_PGTABLE_BITS_H */

arch/metag/include/asm/pgtable.h

@@ -5,6 +5,7 @@
 #ifndef _METAG_PGTABLE_H
 #define _METAG_PGTABLE_H
 
+#include <asm/pgtable-bits.h>
 #include <asm-generic/pgtable-nopmd.h>
 
 /* Invalid regions on Meta: 0x00000000-0x001FFFFF and 0xFFFF0000-0xFFFFFFFF */
@@ -20,100 +21,6 @@
 #define VMALLOC_END		0x7FFFFFFF
 #endif
 
-/*
- * Definitions for MMU descriptors
- *
- * These are the hardware bits in the MMCU pte entries.
- * Derived from the Meta toolkit headers.
- */
-#define _PAGE_PRESENT		MMCU_ENTRY_VAL_BIT
-#define _PAGE_WRITE		MMCU_ENTRY_WR_BIT
-#define _PAGE_PRIV		MMCU_ENTRY_PRIV_BIT
-/* Write combine bit - this can cause writes to occur out of order */
-#define _PAGE_WR_COMBINE	MMCU_ENTRY_WRC_BIT
-/* Sys coherent bit - this bit is never used by Linux */
-#define _PAGE_SYS_COHERENT	MMCU_ENTRY_SYS_BIT
-#define _PAGE_ALWAYS_ZERO_1	0x020
-#define _PAGE_CACHE_CTRL0	0x040
-#define _PAGE_CACHE_CTRL1	0x080
-#define _PAGE_ALWAYS_ZERO_2	0x100
-#define _PAGE_ALWAYS_ZERO_3	0x200
-#define _PAGE_ALWAYS_ZERO_4	0x400
-#define _PAGE_ALWAYS_ZERO_5	0x800
-
-/* These are software bits that we stuff into the gaps in the hardware
- * pte entries that are not used.  Note, these DO get stored in the actual
- * hardware, but the hardware just does not use them.
- */
-#define _PAGE_ACCESSED		_PAGE_ALWAYS_ZERO_1
-#define _PAGE_DIRTY		_PAGE_ALWAYS_ZERO_2
-
-/* Pages owned, and protected by, the kernel. */
-#define _PAGE_KERNEL		_PAGE_PRIV
-
-/* No cacheing of this page */
-#define _PAGE_CACHE_WIN0	(MMCU_CWIN_UNCACHED << MMCU_ENTRY_CWIN_S)
-/* burst cacheing - good for data streaming */
-#define _PAGE_CACHE_WIN1	(MMCU_CWIN_BURST << MMCU_ENTRY_CWIN_S)
-/* One cache way per thread */
-#define _PAGE_CACHE_WIN2	(MMCU_CWIN_C1SET << MMCU_ENTRY_CWIN_S)
-/* Full on cacheing */
-#define _PAGE_CACHE_WIN3	(MMCU_CWIN_CACHED << MMCU_ENTRY_CWIN_S)
-
-#define _PAGE_CACHEABLE		(_PAGE_CACHE_WIN3 | _PAGE_WR_COMBINE)
-
-/* which bits are used for cache control ... */
-#define _PAGE_CACHE_MASK	(_PAGE_CACHE_CTRL0 | _PAGE_CACHE_CTRL1 | \
-				 _PAGE_WR_COMBINE)
-
-/* This is a mask of the bits that pte_modify is allowed to change. */
-#define _PAGE_CHG_MASK		(PAGE_MASK)
-
-#define _PAGE_SZ_SHIFT		1
-#define _PAGE_SZ_4K		(0x0)
-#define _PAGE_SZ_8K		(0x1 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_16K		(0x2 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_32K		(0x3 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_64K		(0x4 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_128K		(0x5 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_256K		(0x6 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_512K		(0x7 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_1M		(0x8 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_2M		(0x9 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_4M		(0xa << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_MASK		(0xf << _PAGE_SZ_SHIFT)
-
-#if defined(CONFIG_PAGE_SIZE_4K)
-#define _PAGE_SZ		(_PAGE_SZ_4K)
-#elif defined(CONFIG_PAGE_SIZE_8K)
-#define _PAGE_SZ		(_PAGE_SZ_8K)
-#elif defined(CONFIG_PAGE_SIZE_16K)
-#define _PAGE_SZ		(_PAGE_SZ_16K)
-#endif
-#define _PAGE_TABLE		(_PAGE_SZ | _PAGE_PRESENT)
-
-#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_8K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_16K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_32K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_64K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_128K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_256K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K)
-# define _PAGE_SZHUGE		(_PAGE_SZ_512K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M)
-# define _PAGE_SZHUGE		(_PAGE_SZ_1M)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M)
-# define _PAGE_SZHUGE		(_PAGE_SZ_2M)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M)
-# define _PAGE_SZHUGE		(_PAGE_SZ_4M)
-#endif
-
 /*
  * The Linux memory management assumes a three-level page table setup. On
  * Meta, we use that, but "fold" the mid level into the top-level page

arch/nios2/include/uapi/asm/Kbuild

@@ -1,6 +1,5 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 header-y += elf.h
-header-y += ucontext.h
 
 generic-y += ucontext.h

arch/nios2/mm/fault.c

@@ -126,7 +126,6 @@ good_area:
 		break;
 	}
 
-survive:
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
@@ -220,11 +219,6 @@ no_context:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (is_global_init(tsk)) {
-		yield();
-		down_read(&mm->mmap_sem);
-		goto survive;
-	}
 	if (!user_mode(regs))
 		goto no_context;
 	pagefault_out_of_memory();

arch/parisc/include/asm/pgalloc.h

@@ -26,7 +26,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	if (likely(pgd != NULL)) {
 		memset(pgd, 0, PAGE_SIZE<<PGD_ALLOC_ORDER);
-#ifdef CONFIG_64BIT
+#if PT_NLEVELS == 3
 		actual_pgd += PTRS_PER_PGD;
 		/* Populate first pmd with allocated memory.  We mark it
 		 * with PxD_FLAG_ATTACHED as a signal to the system that this
@@ -45,7 +45,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-#ifdef CONFIG_64BIT
+#if PT_NLEVELS == 3
 	pgd -= PTRS_PER_PGD;
 #endif
 	free_pages((unsigned long)pgd, PGD_ALLOC_ORDER);
@@ -72,12 +72,15 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-#ifdef CONFIG_64BIT
 	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
-		/* This is the permanent pmd attached to the pgd;
+		/*
-		 * cannot free it */
+		 * This is the permanent pmd attached to the pgd;
+		 * cannot free it.
+		 * Increment the counter to compensate for the decrement
+		 * done by generic mm code.
+		 */
+		mm_inc_nr_pmds(mm);
 		return;
-#endif
 	free_pages((unsigned long)pmd, PMD_ORDER);
 }
 
@@ -99,7 +102,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 static inline void
 pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 {
-#ifdef CONFIG_64BIT
+#if PT_NLEVELS == 3
 	/* preserve the gateway marker if this is the beginning of
 	 * the permanent pmd */
 	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)

arch/parisc/kernel/syscall_table.S

@@ -55,8 +55,8 @@
 #define ENTRY_COMP(_name_) .word sys_##_name_
 #endif
 
-	ENTRY_SAME(restart_syscall)	/* 0 */
+90:	ENTRY_SAME(restart_syscall)	/* 0 */
-	ENTRY_SAME(exit)
+91:	ENTRY_SAME(exit)
 	ENTRY_SAME(fork_wrapper)
 	ENTRY_SAME(read)
 	ENTRY_SAME(write)
@@ -439,7 +439,10 @@
 	ENTRY_SAME(bpf)
 	ENTRY_COMP(execveat)
 
-	/* Nothing yet */
+
+.ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
+.error "size of syscall table does not fit value of __NR_Linux_syscalls"
+.endif
 
 #undef ENTRY_SAME
 #undef ENTRY_DIFF

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

@@ -153,6 +153,7 @@
 #define PPC_INST_MFSPR_PVR_MASK		0xfc1fffff
 #define PPC_INST_MFTMR			0x7c0002dc
 #define PPC_INST_MSGSND			0x7c00019c
+#define PPC_INST_MSGCLR			0x7c0001dc
 #define PPC_INST_MSGSNDP		0x7c00011c
 #define PPC_INST_MTTMR			0x7c0003dc
 #define PPC_INST_NOP			0x60000000
@@ -309,6 +310,8 @@
 					___PPC_RB(b) | __PPC_EH(eh))
 #define PPC_MSGSND(b)		stringify_in_c(.long PPC_INST_MSGSND | \
 					___PPC_RB(b))
+#define PPC_MSGCLR(b)		stringify_in_c(.long PPC_INST_MSGCLR | \
+					___PPC_RB(b))
 #define PPC_MSGSNDP(b)		stringify_in_c(.long PPC_INST_MSGSNDP | \
 					___PPC_RB(b))
 #define PPC_POPCNTB(a, s)	stringify_in_c(.long PPC_INST_POPCNTB | \

arch/powerpc/include/asm/reg.h

@@ -608,13 +608,16 @@
 #define   SRR1_ISI_N_OR_G	0x10000000 /* ISI: Access is no-exec or G */
 #define   SRR1_ISI_PROT		0x08000000 /* ISI: Other protection fault */
 #define   SRR1_WAKEMASK		0x00380000 /* reason for wakeup */
+#define   SRR1_WAKEMASK_P8	0x003c0000 /* reason for wakeup on POWER8 */
 #define   SRR1_WAKESYSERR	0x00300000 /* System error */
 #define   SRR1_WAKEEE		0x00200000 /* External interrupt */
 #define   SRR1_WAKEMT		0x00280000 /* mtctrl */
 #define	  SRR1_WAKEHMI		0x00280000 /* Hypervisor maintenance */
 #define   SRR1_WAKEDEC		0x00180000 /* Decrementer interrupt */
+#define   SRR1_WAKEDBELL	0x00140000 /* Privileged doorbell on P8 */
 #define   SRR1_WAKETHERM	0x00100000 /* Thermal management interrupt */
 #define	  SRR1_WAKERESET	0x00100000 /* System reset */
+#define   SRR1_WAKEHDBELL	0x000c0000 /* Hypervisor doorbell on P8 */
 #define	  SRR1_WAKESTATE	0x00030000 /* Powersave exit mask [46:47] */
 #define	  SRR1_WS_DEEPEST	0x00030000 /* Some resources not maintained,
 					  * may not be recoverable */

arch/powerpc/kernel/cputable.c

@@ -437,6 +437,26 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
+	{	/* Power8NVL */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x004c0000,
+		.cpu_name		= "POWER8NVL (raw)",
+		.cpu_features		= CPU_FTRS_POWER8,
+		.cpu_user_features	= COMMON_USER_POWER8,
+		.cpu_user_features2	= COMMON_USER2_POWER8,
+		.mmu_features		= MMU_FTRS_POWER8,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power8",
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= __setup_cpu_power8,
+		.cpu_restore		= __restore_cpu_power8,
+		.flush_tlb		= __flush_tlb_power8,
+		.machine_check_early	= __machine_check_early_realmode_p8,
+		.platform		= "power8",
+	},
 	{	/* Power8 DD1: Does not support doorbell IPIs */
 		.pvr_mask		= 0xffffff00,
 		.pvr_value		= 0x004d0100,

arch/powerpc/kernel/dbell.c

@@ -17,6 +17,7 @@
 
 #include <asm/dbell.h>
 #include <asm/irq_regs.h>
+#include <asm/kvm_ppc.h>
 
 #ifdef CONFIG_SMP
 void doorbell_setup_this_cpu(void)
@@ -41,6 +42,7 @@ void doorbell_exception(struct pt_regs *regs)
 
 	may_hard_irq_enable();
 
+	kvmppc_set_host_ipi(smp_processor_id(), 0);
 	__this_cpu_inc(irq_stat.doorbell_irqs);
 
 	smp_ipi_demux();

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

@@ -1408,7 +1408,7 @@ machine_check_handle_early:
 	bne	9f			/* continue in V mode if we are. */
 
 5:
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	/*
 	 * We are coming from kernel context. Check if we are coming from
 	 * guest. if yes, then we can continue. We will fall through

arch/powerpc/kvm/book3s_hv.c

@@ -636,7 +636,7 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	lppaca = (struct lppaca *)vcpu->arch.vpa.pinned_addr;
 	if (lppaca)
-		yield_count = lppaca->yield_count;
+		yield_count = be32_to_cpu(lppaca->yield_count);
 	spin_unlock(&vcpu->arch.vpa_update_lock);
 	return yield_count;
 }
@@ -942,20 +942,20 @@ static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
 static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
 		bool preserve_top32)
 {
+	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	u64 mask;
 
+	mutex_lock(&kvm->lock);
 	spin_lock(&vc->lock);
 	/*
 	 * If ILE (interrupt little-endian) has changed, update the
 	 * MSR_LE bit in the intr_msr for each vcpu in this vcore.
 	 */
 	if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) {
-		struct kvm *kvm = vcpu->kvm;
 		struct kvm_vcpu *vcpu;
 		int i;
 
-		mutex_lock(&kvm->lock);
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (vcpu->arch.vcore != vc)
 				continue;
@@ -964,7 +964,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
 			else
 				vcpu->arch.intr_msr &= ~MSR_LE;
 		}
-		mutex_unlock(&kvm->lock);
 	}
 
 	/*
@@ -981,6 +980,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
 		mask &= 0xFFFFFFFF;
 	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
 	spin_unlock(&vc->lock);
+	mutex_unlock(&kvm->lock);
 }
 
 static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1005,6 +1005,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	/* Save HEIR (HV emulation assist reg) in emul_inst
 	   if this is an HEI (HV emulation interrupt, e40) */
 	li	r3,KVM_INST_FETCH_FAILED
+	stw	r3,VCPU_LAST_INST(r9)
 	cmpwi	r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
 	bne	11f
 	mfspr	r3,SPRN_HEIR

arch/powerpc/platforms/powernv/smp.c

@@ -33,6 +33,8 @@
 #include <asm/runlatch.h>
 #include <asm/code-patching.h>
 #include <asm/dbell.h>
+#include <asm/kvm_ppc.h>
+#include <asm/ppc-opcode.h>
 
 #include "powernv.h"
 
@@ -149,7 +151,7 @@ static int pnv_smp_cpu_disable(void)
 static void pnv_smp_cpu_kill_self(void)
 {
 	unsigned int cpu;
-	unsigned long srr1;
+	unsigned long srr1, wmask;
 	u32 idle_states;
 
 	/* Standard hot unplug procedure */
@@ -161,6 +163,10 @@ static void pnv_smp_cpu_kill_self(void)
 	generic_set_cpu_dead(cpu);
 	smp_wmb();
 
+	wmask = SRR1_WAKEMASK;
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		wmask = SRR1_WAKEMASK_P8;
+
 	idle_states = pnv_get_supported_cpuidle_states();
 	/* We don't want to take decrementer interrupts while we are offline,
 	 * so clear LPCR:PECE1. We keep PECE2 enabled.
@@ -191,10 +197,14 @@ static void pnv_smp_cpu_kill_self(void)
 		 * having finished executing in a KVM guest, then srr1
 		 * contains 0.
 		 */
-		if ((srr1 & SRR1_WAKEMASK) == SRR1_WAKEEE) {
+		if ((srr1 & wmask) == SRR1_WAKEEE) {
 			icp_native_flush_interrupt();
 			local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
 			smp_mb();
+		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
+			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
+			kvmppc_set_host_ipi(cpu, 0);
 		}
 
 		if (cpu_core_split_required())

arch/powerpc/platforms/pseries/mobility.c

@@ -25,10 +25,10 @@
 static struct kobject *mobility_kobj;
 
 struct update_props_workarea {
-	u32 phandle;
+	__be32 phandle;
-	u32 state;
+	__be32 state;
-	u64 reserved;
+	__be64 reserved;
-	u32 nprops;
+	__be32 nprops;
 } __packed;
 
 #define NODE_ACTION_MASK	0xff000000
@@ -54,11 +54,11 @@ static int mobility_rtas_call(int token, char *buf, s32 scope)
 	return rc;
 }
 
-static int delete_dt_node(u32 phandle)
+static int delete_dt_node(__be32 phandle)
 {
 	struct device_node *dn;
 
-	dn = of_find_node_by_phandle(phandle);
+	dn = of_find_node_by_phandle(be32_to_cpu(phandle));
 	if (!dn)
 		return -ENOENT;
 
@@ -127,7 +127,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop,
 	return 0;
 }
 
-static int update_dt_node(u32 phandle, s32 scope)
+static int update_dt_node(__be32 phandle, s32 scope)
 {
 	struct update_props_workarea *upwa;
 	struct device_node *dn;
@@ -136,6 +136,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 	char *prop_data;
 	char *rtas_buf;
 	int update_properties_token;
+	u32 nprops;
 	u32 vd;
 
 	update_properties_token = rtas_token("ibm,update-properties");
@@ -146,7 +147,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 	if (!rtas_buf)
 		return -ENOMEM;
 
-	dn = of_find_node_by_phandle(phandle);
+	dn = of_find_node_by_phandle(be32_to_cpu(phandle));
 	if (!dn) {
 		kfree(rtas_buf);
 		return -ENOENT;
@@ -162,6 +163,7 @@ static int update_dt_node(u32 phandle, s32 scope)
 			break;
 
 		prop_data = rtas_buf + sizeof(*upwa);
+		nprops = be32_to_cpu(upwa->nprops);
 
 		/* On the first call to ibm,update-properties for a node the
 		 * the first property value descriptor contains an empty
@@ -170,17 +172,17 @@ static int update_dt_node(u32 phandle, s32 scope)
 		 */
 		if (*prop_data == 0) {
 			prop_data++;
-			vd = *(u32 *)prop_data;
+			vd = be32_to_cpu(*(__be32 *)prop_data);
 			prop_data += vd + sizeof(vd);
-			upwa->nprops--;
+			nprops--;
 		}
 
-		for (i = 0; i < upwa->nprops; i++) {
+		for (i = 0; i < nprops; i++) {
 			char *prop_name;
 
 			prop_name = prop_data;
 			prop_data += strlen(prop_name) + 1;
-			vd = *(u32 *)prop_data;
+			vd = be32_to_cpu(*(__be32 *)prop_data);
 			prop_data += sizeof(vd);
 
 			switch (vd) {
@@ -212,13 +214,13 @@ static int update_dt_node(u32 phandle, s32 scope)
 	return 0;
 }
 
-static int add_dt_node(u32 parent_phandle, u32 drc_index)
+static int add_dt_node(__be32 parent_phandle, __be32 drc_index)
 {
 	struct device_node *dn;
 	struct device_node *parent_dn;
 	int rc;
 
-	parent_dn = of_find_node_by_phandle(parent_phandle);
+	parent_dn = of_find_node_by_phandle(be32_to_cpu(parent_phandle));
 	if (!parent_dn)
 		return -ENOENT;
 
@@ -237,7 +239,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index)
 int pseries_devicetree_update(s32 scope)
 {
 	char *rtas_buf;
-	u32 *data;
+	__be32 *data;
 	int update_nodes_token;
 	int rc;
 
@@ -254,17 +256,17 @@ int pseries_devicetree_update(s32 scope)
 		if (rc && rc != 1)
 			break;
 
-		data = (u32 *)rtas_buf + 4;
+		data = (__be32 *)rtas_buf + 4;
-		while (*data & NODE_ACTION_MASK) {
+		while (be32_to_cpu(*data) & NODE_ACTION_MASK) {
 			int i;
-			u32 action = *data & NODE_ACTION_MASK;
+			u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK;
-			int node_count = *data & NODE_COUNT_MASK;
+			u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK;
 
 			data++;
 
 			for (i = 0; i < node_count; i++) {
-				u32 phandle = *data++;
+				__be32 phandle = *data++;
-				u32 drc_index;
+				__be32 drc_index;
 
 				switch (action) {
 				case DELETE_DT_NODE:

arch/s390/include/asm/elf.h

@@ -211,7 +211,7 @@ do {								\
 
 extern unsigned long mmap_rnd_mask;
 
-#define STACK_RND_MASK	(mmap_rnd_mask)
+#define STACK_RND_MASK	(test_thread_flag(TIF_31BIT) ? 0x7ff : mmap_rnd_mask)
 
 #define ARCH_DLINFO							    \
 do {									    \

arch/s390/kernel/ftrace.c

@@ -57,6 +57,44 @@
 
 unsigned long ftrace_plt;
 
+static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn)
+{
+#ifdef CC_USING_HOTPATCH
+	/* brcl 0,0 */
+	insn->opc = 0xc004;
+	insn->disp = 0;
+#else
+	/* stg r14,8(r15) */
+	insn->opc = 0xe3e0;
+	insn->disp = 0xf0080024;
+#endif
+}
+
+static inline int is_kprobe_on_ftrace(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+	if (insn->opc == BREAKPOINT_INSTRUCTION)
+		return 1;
+#endif
+	return 0;
+}
+
+static inline void ftrace_generate_kprobe_nop_insn(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+	insn->opc = BREAKPOINT_INSTRUCTION;
+	insn->disp = KPROBE_ON_FTRACE_NOP;
+#endif
+}
+
+static inline void ftrace_generate_kprobe_call_insn(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+	insn->opc = BREAKPOINT_INSTRUCTION;
+	insn->disp = KPROBE_ON_FTRACE_CALL;
+#endif
+}
+
 int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 		       unsigned long addr)
 {
@@ -72,16 +110,9 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		return -EFAULT;
 	if (addr == MCOUNT_ADDR) {
 		/* Initial code replacement */
-#ifdef CC_USING_HOTPATCH
+		ftrace_generate_orig_insn(&orig);
-		/* We expect to see brcl 0,0 */
-		ftrace_generate_nop_insn(&orig);
-#else
-		/* We expect to see stg r14,8(r15) */
-		orig.opc = 0xe3e0;
-		orig.disp = 0xf0080024;
-#endif
 		ftrace_generate_nop_insn(&new);
-	} else if (old.opc == BREAKPOINT_INSTRUCTION) {
+	} else if (is_kprobe_on_ftrace(&old)) {
 		/*
 		 * If we find a breakpoint instruction, a kprobe has been
 		 * placed at the beginning of the function. We write the
@@ -89,9 +120,8 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		 * bytes of the original instruction so that the kprobes
 		 * handler can execute a nop, if it reaches this breakpoint.
 		 */
-		new.opc = orig.opc = BREAKPOINT_INSTRUCTION;
+		ftrace_generate_kprobe_call_insn(&orig);
-		orig.disp = KPROBE_ON_FTRACE_CALL;
+		ftrace_generate_kprobe_nop_insn(&new);
-		new.disp = KPROBE_ON_FTRACE_NOP;
 	} else {
 		/* Replace ftrace call with a nop. */
 		ftrace_generate_call_insn(&orig, rec->ip);
@@ -111,7 +141,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
 		return -EFAULT;
-	if (old.opc == BREAKPOINT_INSTRUCTION) {
+	if (is_kprobe_on_ftrace(&old)) {
 		/*
 		 * If we find a breakpoint instruction, a kprobe has been
 		 * placed at the beginning of the function. We write the
@@ -119,9 +149,8 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		 * bytes of the original instruction so that the kprobes
 		 * handler can execute a brasl if it reaches this breakpoint.
 		 */
-		new.opc = orig.opc = BREAKPOINT_INSTRUCTION;
+		ftrace_generate_kprobe_nop_insn(&orig);
-		orig.disp = KPROBE_ON_FTRACE_NOP;
+		ftrace_generate_kprobe_call_insn(&new);
-		new.disp = KPROBE_ON_FTRACE_CALL;
 	} else {
 		/* Replace nop with an ftrace call. */
 		ftrace_generate_nop_insn(&orig);

arch/s390/kernel/perf_cpum_sf.c

@@ -1415,7 +1415,7 @@ CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG);
 
 static struct attribute *cpumsf_pmu_events_attr[] = {
 	CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC),
-	CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG),
+	NULL,
 	NULL,
 };
 
@@ -1606,8 +1606,11 @@ static int __init init_cpum_sampling_pmu(void)
 		return -EINVAL;
 	}
 
-	if (si.ad)
+	if (si.ad) {
 		sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
+		cpumsf_pmu_events_attr[1] =
+			CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG);
+	}
 
 	sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80);
 	if (!sfdbg)

arch/s390/kernel/swsusp_asm64.S

@@ -177,6 +177,17 @@ restart_entry:
 	lhi	%r1,1
 	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
 	sam64
+#ifdef CONFIG_SMP
+	larl	%r1,smp_cpu_mt_shift
+	icm	%r1,15,0(%r1)
+	jz	smt_done
+	llgfr	%r1,%r1
+smt_loop:
+	sigp	%r1,%r0,SIGP_SET_MULTI_THREADING
+	brc	8,smt_done			/* accepted */
+	brc	2,smt_loop			/* busy, try again */
+smt_done:
+#endif
 	larl	%r1,.Lnew_pgm_check_psw
 	lpswe	0(%r1)
 pgm_check_entry:

arch/s390/kvm/kvm-s390.c

@@ -165,7 +165,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_S390_CSS_SUPPORT:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_ENABLE_CAP_VM:

arch/sparc/Kconfig

@@ -86,6 +86,9 @@ config ARCH_DEFCONFIG
 	default "arch/sparc/configs/sparc32_defconfig" if SPARC32
 	default "arch/sparc/configs/sparc64_defconfig" if SPARC64
 
+config ARCH_PROC_KCORE_TEXT
+	def_bool y
+
 config IOMMU_HELPER
 	bool
 	default y if SPARC64

arch/sparc/include/asm/hypervisor.h

@@ -2957,6 +2957,17 @@ unsigned long sun4v_t5_set_perfreg(unsigned long reg_num,
 				   unsigned long reg_val);
 #endif
 
+
+#define HV_FAST_M7_GET_PERFREG	0x43
+#define HV_FAST_M7_SET_PERFREG	0x44
+
+#ifndef	__ASSEMBLY__
+unsigned long sun4v_m7_get_perfreg(unsigned long reg_num,
+				      unsigned long *reg_val);
+unsigned long sun4v_m7_set_perfreg(unsigned long reg_num,
+				      unsigned long reg_val);
+#endif
+
 /* Function numbers for HV_CORE_TRAP.  */
 #define HV_CORE_SET_VER			0x00
 #define HV_CORE_PUTCHAR			0x01
@@ -2981,6 +2992,7 @@ unsigned long sun4v_t5_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_M7_PERF			0x0114
 #define HV_GRP_NIAG_PERF		0x0200
 #define HV_GRP_FIRE_PERF		0x0201
 #define HV_GRP_N2_CPU			0x0202

arch/sparc/include/asm/io_64.h

@@ -407,16 +407,16 @@ static inline void iounmap(volatile void __iomem *addr)
 {
 }
 
-#define ioread8(X)			readb(X)
+#define ioread8			readb
-#define ioread16(X)			readw(X)
+#define ioread16		readw
-#define ioread16be(X)			__raw_readw(X)
+#define ioread16be		__raw_readw
-#define ioread32(X)			readl(X)
+#define ioread32		readl
-#define ioread32be(X)			__raw_readl(X)
+#define ioread32be		__raw_readl
-#define iowrite8(val,X)			writeb(val,X)
+#define iowrite8		writeb
-#define iowrite16(val,X)		writew(val,X)
+#define iowrite16		writew
-#define iowrite16be(val,X)		__raw_writew(val,X)
+#define iowrite16be		__raw_writew
-#define iowrite32(val,X)		writel(val,X)
+#define iowrite32		writel
-#define iowrite32be(val,X)		__raw_writel(val,X)
+#define iowrite32be		__raw_writel
 
 /* Create a virtual mapping cookie for an IO port range */
 void __iomem *ioport_map(unsigned long port, unsigned int nr);

arch/sparc/include/asm/starfire.h

@@ -12,7 +12,6 @@
 extern int this_is_starfire;
 
 void check_if_starfire(void);
-int starfire_hard_smp_processor_id(void);
 void starfire_hookup(int);
 unsigned int starfire_translate(unsigned long imap, unsigned int upaid);
 

arch/sparc/kernel/entry.h

@@ -98,11 +98,7 @@ void sun4v_do_mna(struct pt_regs *regs,
 void do_privop(struct pt_regs *regs);
 void do_privact(struct pt_regs *regs);
 void do_cee(struct pt_regs *regs);
-void do_cee_tl1(struct pt_regs *regs);
-void do_dae_tl1(struct pt_regs *regs);
-void do_iae_tl1(struct pt_regs *regs);
 void do_div0_tl1(struct pt_regs *regs);
-void do_fpdis_tl1(struct pt_regs *regs);
 void do_fpieee_tl1(struct pt_regs *regs);
 void do_fpother_tl1(struct pt_regs *regs);
 void do_ill_tl1(struct pt_regs *regs);

arch/sparc/kernel/hvapi.c

@@ -48,6 +48,7 @@ static struct api_info api_table[] = {
 	{ .group = HV_GRP_VT_CPU,				},
 	{ .group = HV_GRP_T5_CPU,				},
 	{ .group = HV_GRP_DIAG,		.flags = FLAG_PRE_API	},
+	{ .group = HV_GRP_M7_PERF,				},
 };
 
 static DEFINE_SPINLOCK(hvapi_lock);

arch/sparc/kernel/hvcalls.S

@@ -837,3 +837,19 @@ ENTRY(sun4v_t5_set_perfreg)
 	retl
 	 nop
 ENDPROC(sun4v_t5_set_perfreg)
+
+ENTRY(sun4v_m7_get_perfreg)
+	mov	%o1, %o4
+	mov	HV_FAST_M7_GET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	stx	%o1, [%o4]
+	retl
+	nop
+ENDPROC(sun4v_m7_get_perfreg)
+
+ENTRY(sun4v_m7_set_perfreg)
+	mov	HV_FAST_M7_SET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	retl
+	nop
+ENDPROC(sun4v_m7_set_perfreg)

arch/sparc/kernel/pcr.c

@@ -217,6 +217,31 @@ static const struct pcr_ops n5_pcr_ops = {
 	.pcr_nmi_disable	= PCR_N4_PICNPT,
 };
 
+static u64 m7_pcr_read(unsigned long reg_num)
+{
+	unsigned long val;
+
+	(void) sun4v_m7_get_perfreg(reg_num, &val);
+
+	return val;
+}
+
+static void m7_pcr_write(unsigned long reg_num, u64 val)
+{
+	(void) sun4v_m7_set_perfreg(reg_num, val);
+}
+
+static const struct pcr_ops m7_pcr_ops = {
+	.read_pcr		= m7_pcr_read,
+	.write_pcr		= m7_pcr_write,
+	.read_pic		= n4_pic_read,
+	.write_pic		= n4_pic_write,
+	.nmi_picl_value		= n4_picl_value,
+	.pcr_nmi_enable		= (PCR_N4_PICNPT | PCR_N4_STRACE |
+				   PCR_N4_UTRACE | PCR_N4_TOE |
+				   (26 << PCR_N4_SL_SHIFT)),
+	.pcr_nmi_disable	= PCR_N4_PICNPT,
+};
 
 static unsigned long perf_hsvc_group;
 static unsigned long perf_hsvc_major;
@@ -248,6 +273,10 @@ static int __init register_perf_hsvc(void)
 			perf_hsvc_group = HV_GRP_T5_CPU;
 			break;
 
+		case SUN4V_CHIP_SPARC_M7:
+			perf_hsvc_group = HV_GRP_M7_PERF;
+			break;
+
 		default:
 			return -ENODEV;
 		}
@@ -293,6 +322,10 @@ static int __init setup_sun4v_pcr_ops(void)
 		pcr_ops = &n5_pcr_ops;
 		break;
 
+	case SUN4V_CHIP_SPARC_M7:
+		pcr_ops = &m7_pcr_ops;
+		break;
+
 	default:
 		ret = -ENODEV;
 		break;

arch/sparc/kernel/perf_event.c

@@ -792,6 +792,42 @@ static const struct sparc_pmu niagara4_pmu = {
 	.num_pic_regs	= 4,
 };
 
+static void sparc_m7_write_pmc(int idx, u64 val)
+{
+	u64 pcr;
+
+	pcr = pcr_ops->read_pcr(idx);
+	/* ensure ov and ntc are reset */
+	pcr &= ~(PCR_N4_OV | PCR_N4_NTC);
+
+	pcr_ops->write_pic(idx, val & 0xffffffff);
+
+	pcr_ops->write_pcr(idx, pcr);
+}
+
+static const struct sparc_pmu sparc_m7_pmu = {
+	.event_map	= niagara4_event_map,
+	.cache_map	= &niagara4_cache_map,
+	.max_events	= ARRAY_SIZE(niagara4_perfmon_event_map),
+	.read_pmc	= sparc_vt_read_pmc,
+	.write_pmc	= sparc_m7_write_pmc,
+	.upper_shift	= 5,
+	.lower_shift	= 5,
+	.event_mask	= 0x7ff,
+	.user_bit	= PCR_N4_UTRACE,
+	.priv_bit	= PCR_N4_STRACE,
+
+	/* We explicitly don't support hypervisor tracing. */
+	.hv_bit		= 0,
+
+	.irq_bit	= PCR_N4_TOE,
+	.upper_nop	= 0,
+	.lower_nop	= 0,
+	.flags		= 0,
+	.max_hw_events	= 4,
+	.num_pcrs	= 4,
+	.num_pic_regs	= 4,
+};
 static const struct sparc_pmu *sparc_pmu __read_mostly;
 
 static u64 event_encoding(u64 event_id, int idx)
@@ -960,6 +996,8 @@ out:
 	cpuc->pcr[0] |= cpuc->event[0]->hw.config_base;
 }
 
+static void sparc_pmu_start(struct perf_event *event, int flags);
+
 /* On this PMU each PIC has it's own PCR control register.  */
 static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc)
 {
@@ -972,20 +1010,13 @@ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc)
 		struct perf_event *cp = cpuc->event[i];
 		struct hw_perf_event *hwc = &cp->hw;
 		int idx = hwc->idx;
-		u64 enc;
 
 		if (cpuc->current_idx[i] != PIC_NO_INDEX)
 			continue;
 
-		sparc_perf_event_set_period(cp, hwc, idx);
 		cpuc->current_idx[i] = idx;
 
-		enc = perf_event_get_enc(cpuc->events[i]);
+		sparc_pmu_start(cp, PERF_EF_RELOAD);
-		cpuc->pcr[idx] &= ~mask_for_index(idx);
-		if (hwc->state & PERF_HES_STOPPED)
-			cpuc->pcr[idx] |= nop_for_index(idx);
-		else
-			cpuc->pcr[idx] |= event_encoding(enc, idx);
 	}
 out:
 	for (i = 0; i < cpuc->n_events; i++) {
@@ -1101,7 +1132,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags)
 	int i;
 
 	local_irq_save(flags);
-	perf_pmu_disable(event->pmu);
 
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event[i]) {
@@ -1127,7 +1157,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags)
 		}
 	}
 
-	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
@@ -1361,7 +1390,6 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_pmu_disable(event->pmu);
 
 	n0 = cpuc->n_events;
 	if (n0 >= sparc_pmu->max_hw_events)
@@ -1394,7 +1422,6 @@ nocheck:
 
 	ret = 0;
 out:
-	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
@@ -1667,6 +1694,10 @@ static bool __init supported_pmu(void)
 		sparc_pmu = &niagara4_pmu;
 		return true;
 	}
+	if (!strcmp(sparc_pmu_type, "sparc-m7")) {
+		sparc_pmu = &sparc_m7_pmu;
+		return true;
+	}
 	return false;
 }
 

arch/sparc/kernel/process_64.c

@@ -287,6 +287,8 @@ void arch_trigger_all_cpu_backtrace(bool include_self)
 			printk("             TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n",
 			       gp->tpc, gp->o7, gp->i7, gp->rpc);
 		}
+
+		touch_nmi_watchdog();
 	}
 
 	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
@@ -362,6 +364,8 @@ static void pmu_snapshot_all_cpus(void)
 		       (cpu == this_cpu ? '*' : ' '), cpu,
 		       pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3],
 		       pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]);
+
+		touch_nmi_watchdog();
 	}
 
 	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));

arch/sparc/kernel/smp_64.c

@@ -1406,11 +1406,32 @@ void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs)
 	scheduler_ipi();
 }
 
-/* This is a nop because we capture all other cpus
+static void stop_this_cpu(void *dummy)
- * anyways when making the PROM active.
+{
- */
+	prom_stopself();
+}
+
 void smp_send_stop(void)
 {
+	int cpu;
+
+	if (tlb_type == hypervisor) {
+		for_each_online_cpu(cpu) {
+			if (cpu == smp_processor_id())
+				continue;
+#ifdef CONFIG_SUN_LDOMS
+			if (ldom_domaining_enabled) {
+				unsigned long hv_err;
+				hv_err = sun4v_cpu_stop(cpu);
+				if (hv_err)
+					printk(KERN_ERR "sun4v_cpu_stop() "
+					       "failed err=%lu\n", hv_err);
+			} else
+#endif
+				prom_stopcpu_cpuid(cpu);
+		}
+	} else
+		smp_call_function(stop_this_cpu, NULL, 0);
 }
 
 /**

arch/sparc/kernel/starfire.c

@@ -28,11 +28,6 @@ void check_if_starfire(void)
 		this_is_starfire = 1;
 }
 
-int starfire_hard_smp_processor_id(void)
-{
-	return upa_readl(0x1fff40000d0UL);
-}
-
 /*
  * Each Starfire board has 32 registers which perform translation
  * and delivery of traditional interrupt packets into the extended

arch/sparc/kernel/sys_sparc_64.c

@@ -333,7 +333,7 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second
 	long err;
 
 	/* No need for backward compatibility. We can start fresh... */
-	if (call <= SEMCTL) {
+	if (call <= SEMTIMEDOP) {
 		switch (call) {
 		case SEMOP:
 			err = sys_semtimedop(first, ptr,

arch/sparc/kernel/traps_64.c

@@ -2427,6 +2427,8 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs)
 		}
 		user_instruction_dump ((unsigned int __user *) regs->tpc);
 	}
+	if (panic_on_oops)
+		panic("Fatal exception");
 	if (regs->tstate & TSTATE_PRIV)
 		do_exit(SIGKILL);
 	do_exit(SIGSEGV);
@@ -2564,27 +2566,6 @@ void do_cee(struct pt_regs *regs)
 	die_if_kernel("TL0: Cache Error Exception", regs);
 }
 
-void do_cee_tl1(struct pt_regs *regs)
-{
-	exception_enter();
-	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
-	die_if_kernel("TL1: Cache Error Exception", regs);
-}
-
-void do_dae_tl1(struct pt_regs *regs)
-{
-	exception_enter();
-	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
-	die_if_kernel("TL1: Data Access Exception", regs);
-}
-
-void do_iae_tl1(struct pt_regs *regs)
-{
-	exception_enter();
-	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
-	die_if_kernel("TL1: Instruction Access Exception", regs);
-}
-
 void do_div0_tl1(struct pt_regs *regs)
 {
 	exception_enter();
@@ -2592,13 +2573,6 @@ void do_div0_tl1(struct pt_regs *regs)
 	die_if_kernel("TL1: DIV0 Exception", regs);
 }
 
-void do_fpdis_tl1(struct pt_regs *regs)
-{
-	exception_enter();
-	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
-	die_if_kernel("TL1: FPU Disabled", regs);
-}
-
 void do_fpieee_tl1(struct pt_regs *regs)
 {
 	exception_enter();

arch/sparc/lib/memmove.S

@@ -8,9 +8,11 @@
 
 	.text
 ENTRY(memmove) /* o0=dst o1=src o2=len */
-	mov		%o0, %g1
+	brz,pn		%o2, 99f
+	 mov		%o0, %g1
+
 	cmp		%o0, %o1
-	bleu,pt		%xcc, memcpy
+	bleu,pt		%xcc, 2f
 	 add		%o1, %o2, %g7
 	cmp		%g7, %o0
 	bleu,pt		%xcc, memcpy
@@ -24,7 +26,34 @@ ENTRY(memmove) /* o0=dst o1=src o2=len */
 	stb		%g7, [%o0]
 	bne,pt		%icc, 1b
 	 sub		%o0, 1, %o0
-
+99:
 	retl
 	 mov		%g1, %o0
+
+	/* We can't just call memcpy for these memmove cases.  On some
+	 * chips the memcpy uses cache initializing stores and when dst
+	 * and src are close enough, those can clobber the source data
+	 * before we've loaded it in.
+	 */
+2:	or		%o0, %o1, %g7
+	or		%o2, %g7, %g7
+	andcc		%g7, 0x7, %g0
+	bne,pn		%xcc, 4f
+	 nop
+
+3:	ldx		[%o1], %g7
+	add		%o1, 8, %o1
+	subcc		%o2, 8, %o2
+	add		%o0, 8, %o0
+	bne,pt		%icc, 3b
+	 stx		%g7, [%o0 - 0x8]
+	ba,a,pt		%xcc, 99b
+
+4:	ldub		[%o1], %g7
+	add		%o1, 1, %o1
+	subcc		%o2, 1, %o2
+	add		%o0, 1, %o0
+	bne,pt		%icc, 4b
+	 stb		%g7, [%o0 - 0x1]
+	ba,a,pt		%xcc, 99b
 ENDPROC(memmove)

arch/sparc/mm/init_64.c

@@ -2820,7 +2820,7 @@ static int __init report_memory(void)
 
 	return 0;
 }
-device_initcall(report_memory);
+arch_initcall(report_memory);
 
 #ifdef CONFIG_SMP
 #define do_flush_tlb_kernel_range	smp_flush_tlb_kernel_range

arch/x86/boot/compressed/aslr.c

@@ -14,13 +14,6 @@
 static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
 		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
 
-struct kaslr_setup_data {
-	__u64 next;
-	__u32 type;
-	__u32 len;
-	__u8 data[1];
-} kaslr_setup_data;
-
 #define I8254_PORT_CONTROL	0x43
 #define I8254_PORT_COUNTER0	0x40
 #define I8254_CMD_READBACK	0xC0
@@ -302,29 +295,7 @@ static unsigned long find_random_addr(unsigned long minimum,
 	return slots_fetch_random();
 }
 
-static void add_kaslr_setup_data(struct boot_params *params, __u8 enabled)
+unsigned char *choose_kernel_location(unsigned char *input,
-{
-	struct setup_data *data;
-
-	kaslr_setup_data.type = SETUP_KASLR;
-	kaslr_setup_data.len = 1;
-	kaslr_setup_data.next = 0;
-	kaslr_setup_data.data[0] = enabled;
-
-	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
-	while (data && data->next)
-		data = (struct setup_data *)(unsigned long)data->next;
-
-	if (data)
-		data->next = (unsigned long)&kaslr_setup_data;
-	else
-		params->hdr.setup_data = (unsigned long)&kaslr_setup_data;
-
-}
-
-unsigned char *choose_kernel_location(struct boot_params *params,
-				      unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size)
@@ -335,17 +306,14 @@ unsigned char *choose_kernel_location(struct boot_params *params,
 #ifdef CONFIG_HIBERNATION
 	if (!cmdline_find_option_bool("kaslr")) {
 		debug_putstr("KASLR disabled by default...\n");
-		add_kaslr_setup_data(params, 0);
 		goto out;
 	}
 #else
 	if (cmdline_find_option_bool("nokaslr")) {
 		debug_putstr("KASLR disabled by cmdline...\n");
-		add_kaslr_setup_data(params, 0);
 		goto out;
 	}
 #endif
-	add_kaslr_setup_data(params, 1);
 
 	/* Record the various known unsafe memory ranges. */
 	mem_avoid_init((unsigned long)input, input_size,

arch/x86/boot/compressed/misc.c

@@ -401,8 +401,7 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 	 * the entire decompressed kernel plus relocation table, or the
 	 * entire decompressed kernel plus .bss and .brk sections.
 	 */
-	output = choose_kernel_location(real_mode, input_data, input_len,
+	output = choose_kernel_location(input_data, input_len, output,
-					output,
 					output_len > run_size ? output_len
 							      : run_size);
 

arch/x86/boot/compressed/misc.h

@@ -57,8 +57,7 @@ int cmdline_find_option_bool(const char *option);
 
 #if CONFIG_RANDOMIZE_BASE
 /* aslr.c */
-unsigned char *choose_kernel_location(struct boot_params *params,
+unsigned char *choose_kernel_location(unsigned char *input,
-				      unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size);
@@ -66,8 +65,7 @@ unsigned char *choose_kernel_location(struct boot_params *params,
 bool has_cpuflag(int flag);
 #else
 static inline
-unsigned char *choose_kernel_location(struct boot_params *params,
+unsigned char *choose_kernel_location(unsigned char *input,
-				      unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size)

arch/x86/crypto/aesni-intel_glue.c

@@ -1155,7 +1155,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 		src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
 		if (!src)
 			return -ENOMEM;
-		assoc = (src + req->cryptlen + auth_tag_len);
+		assoc = (src + req->cryptlen);
 		scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
 		scatterwalk_map_and_copy(assoc, req->assoc, 0,
 			req->assoclen, 0);
@@ -1180,7 +1180,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 		scatterwalk_done(&src_sg_walk, 0, 0);
 		scatterwalk_done(&assoc_sg_walk, 0, 0);
 	} else {
-		scatterwalk_map_and_copy(dst, req->dst, 0, req->cryptlen, 1);
+		scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1);
 		kfree(src);
 	}
 	return retval;

arch/x86/include/asm/fpu-internal.h

@@ -370,7 +370,7 @@ static inline void drop_fpu(struct task_struct *tsk)
 	preempt_disable();
 	tsk->thread.fpu_counter = 0;
 	__drop_fpu(tsk);
-	clear_used_math();
+	clear_stopped_child_used_math(tsk);
 	preempt_enable();
 }
 

arch/x86/include/asm/page_types.h

@@ -51,8 +51,6 @@ extern int devmem_is_allowed(unsigned long pagenr);
 extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
-extern bool kaslr_enabled;
-
 static inline phys_addr_t get_max_mapped(void)
 {
 	return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT;

arch/x86/include/asm/pci_x86.h

@@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock;
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
 extern void (*pcibios_disable_irq)(struct pci_dev *dev);
 
+extern bool mp_should_keep_irq(struct device *dev);
+
 struct pci_raw_ops {
 	int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
 						int reg, int len, u32 *val);

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

@@ -7,7 +7,6 @@
 #define SETUP_DTB			2
 #define SETUP_PCI			3
 #define SETUP_EFI			4
-#define SETUP_KASLR			5
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF

arch/x86/kernel/acpi/boot.c

@@ -1337,6 +1337,26 @@ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d)
 	return 0;
 }
 
+/*
+ * ACPI offers an alternative platform interface model that removes
+ * ACPI hardware requirements for platforms that do not implement
+ * the PC Architecture.
+ *
+ * We initialize the Hardware-reduced ACPI model here:
+ */
+static void __init acpi_reduced_hw_init(void)
+{
+	if (acpi_gbl_reduced_hardware) {
+		/*
+		 * Override x86_init functions and bypass legacy pic
+		 * in Hardware-reduced ACPI mode
+		 */
+		x86_init.timers.timer_init	= x86_init_noop;
+		x86_init.irqs.pre_vector_init	= x86_init_noop;
+		legacy_pic			= &null_legacy_pic;
+	}
+}
+
 /*
  * If your system is blacklisted here, but you find that acpi=force
  * works for you, please contact linux-acpi@vger.kernel.org
@@ -1536,6 +1556,11 @@ int __init early_acpi_boot_init(void)
 	 */
 	early_acpi_process_madt();
 
+	/*
+	 * Hardware-reduced ACPI mode initialization:
+	 */
+	acpi_reduced_hw_init();
+
 	return 0;
 }
 

arch/x86/kernel/apic/apic_numachip.c

@@ -37,10 +37,12 @@ static const struct apic apic_numachip;
 static unsigned int get_apic_id(unsigned long x)
 {
 	unsigned long value;
-	unsigned int id;
+	unsigned int id = (x >> 24) & 0xff;
 
-	rdmsrl(MSR_FAM10H_NODE_ID, value);
+	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
-	id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U);
+		rdmsrl(MSR_FAM10H_NODE_ID, value);
+		id |= (value << 2) & 0xff00;
+	}
 
 	return id;
 }
@@ -155,10 +157,18 @@ static int __init numachip_probe(void)
 
 static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 {
-	if (c->phys_proc_id != node) {
+	u64 val;
-		c->phys_proc_id = node;
+	u32 nodes = 1;
-		per_cpu(cpu_llc_id, smp_processor_id()) = node;
+
+	this_cpu_write(cpu_llc_id, node);
+
+	/* Account for nodes per socket in multi-core-module processors */
+	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+		rdmsrl(MSR_FAM10H_NODE_ID, val);
+		nodes = ((val >> 3) & 7) + 1;
 	}
+
+	c->phys_proc_id = node / nodes;
 }
 
 static int __init numachip_system_init(void)

arch/x86/kernel/entry_64.S

@@ -364,12 +364,21 @@ system_call_fastpath:
  * Has incomplete stack frame and undefined top of stack.
  */
 ret_from_sys_call:
-	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
-	jnz int_ret_from_sys_call_fixup	/* Go the the slow path */
-
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
+
+	/*
+	 * We must check ti flags with interrupts (or at least preemption)
+	 * off because we must *never* return to userspace without
+	 * processing exit work that is enqueued if we're preempted here.
+	 * In particular, returning to userspace with any of the one-shot
+	 * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
+	 * very bad.
+	 */
+	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jnz int_ret_from_sys_call_fixup	/* Go the the slow path */
+
 	CFI_REMEMBER_STATE
 	/*
 	 * sysretq will re-enable interrupts:
@@ -386,7 +395,7 @@ ret_from_sys_call:
 
 int_ret_from_sys_call_fixup:
 	FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
-	jmp int_ret_from_sys_call
+	jmp int_ret_from_sys_call_irqs_off
 
 	/* Do syscall tracing */
 tracesys:
@@ -432,6 +441,7 @@ tracesys_phase2:
 GLOBAL(int_ret_from_sys_call)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
+int_ret_from_sys_call_irqs_off:
 	movl $_TIF_ALLWORK_MASK,%edi
 	/* edi:	mask to check */
 GLOBAL(int_with_check)

arch/x86/kernel/module.c

@@ -47,13 +47,21 @@ do {							\
 
 #ifdef CONFIG_RANDOMIZE_BASE
 static unsigned long module_load_offset;
+static int randomize_modules = 1;
 
 /* Mutex protects the module_load_offset. */
 static DEFINE_MUTEX(module_kaslr_mutex);
 
+static int __init parse_nokaslr(char *p)
+{
+	randomize_modules = 0;
+	return 0;
+}
+early_param("nokaslr", parse_nokaslr);
+
 static unsigned long int get_module_load_offset(void)
 {
-	if (kaslr_enabled) {
+	if (randomize_modules) {
 		mutex_lock(&module_kaslr_mutex);
 		/*
 		 * Calculate the module_load_offset the first time this

arch/x86/kernel/setup.c

@@ -122,8 +122,6 @@
 unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
 
-bool __read_mostly kaslr_enabled = false;
-
 #ifdef CONFIG_DMI
 RESERVE_BRK(dmi_alloc, 65536);
 #endif
@@ -427,11 +425,6 @@ static void __init reserve_initrd(void)
 }
 #endif /* CONFIG_BLK_DEV_INITRD */
 
-static void __init parse_kaslr_setup(u64 pa_data, u32 data_len)
-{
-	kaslr_enabled = (bool)(pa_data + sizeof(struct setup_data));
-}
-
 static void __init parse_setup_data(void)
 {
 	struct setup_data *data;
@@ -457,9 +450,6 @@ static void __init parse_setup_data(void)
 		case SETUP_EFI:
 			parse_efi_setup(pa_data, data_len);
 			break;
-		case SETUP_KASLR:
-			parse_kaslr_setup(pa_data, data_len);
-			break;
 		default:
 			break;
 		}
@@ -842,14 +832,10 @@ static void __init trim_low_memory_range(void)
 static int
 dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
 {
-	if (kaslr_enabled)
+	pr_emerg("Kernel Offset: 0x%lx from 0x%lx "
-		pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n",
+		 "(relocation range: 0x%lx-0x%lx)\n",
-			 (unsigned long)&_text - __START_KERNEL,
+		 (unsigned long)&_text - __START_KERNEL, __START_KERNEL,
-			 __START_KERNEL,
+		 __START_KERNEL_map, MODULES_VADDR-1);
-			 __START_KERNEL_map,
-			 MODULES_VADDR-1);
-	else
-		pr_emerg("Kernel Offset: disabled\n");
 
 	return 0;
 }

arch/x86/kernel/traps.c

@@ -384,7 +384,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 		goto exit;
 	conditional_sti(regs);
 
-	if (!user_mode(regs))
+	if (!user_mode_vm(regs))
 		die("bounds", regs, error_code);
 
 	if (!cpu_feature_enabled(X86_FEATURE_MPX)) {
@@ -637,7 +637,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	 * then it's very likely the result of an icebp/int01 trap.
 	 * User wants a sigtrap for that.
 	 */
-	if (!dr6 && user_mode(regs))
+	if (!dr6 && user_mode_vm(regs))
 		user_icebp = 1;
 
 	/* Catch kmemcheck conditions first of all! */

arch/x86/kernel/xsave.c

@@ -379,7 +379,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 		 * thread's fpu state, reconstruct fxstate from the fsave
 		 * header. Sanitize the copied state etc.
 		 */
-		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct fpu *fpu = &tsk->thread.fpu;
 		struct user_i387_ia32_struct env;
 		int err = 0;
 
@@ -393,14 +393,15 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 		 */
 		drop_fpu(tsk);
 
-		if (__copy_from_user(xsave, buf_fx, state_size) ||
+		if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
 		    __copy_from_user(&env, buf, sizeof(env))) {
+			fpu_finit(fpu);
 			err = -1;
 		} else {
 			sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
-			set_used_math();
 		}
 
+		set_used_math();
 		if (use_eager_fpu()) {
 			preempt_disable();
 			math_state_restore();

arch/x86/kvm/i8259.c

@@ -507,6 +507,7 @@ static int picdev_read(struct kvm_pic *s,
 		return -EOPNOTSUPP;
 
 	if (len != 1) {
+		memset(val, 0, len);
 		pr_pic_unimpl("non byte read\n");
 		return 0;
 	}

arch/x86/kvm/ioapic.c

@@ -422,6 +422,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 			struct kvm_ioapic *ioapic, int vector, int trigger_mode)
 {
 	int i;
+	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
 		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
@@ -443,7 +444,8 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 		kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
 		spin_lock(&ioapic->lock);
 
-		if (trigger_mode != IOAPIC_LEVEL_TRIG)
+		if (trigger_mode != IOAPIC_LEVEL_TRIG ||
+		    kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)
 			continue;
 
 		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);

arch/x86/kvm/lapic.c

@@ -833,8 +833,7 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 
 static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
 {
-	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
+	if (kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
-	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
 		int trigger_mode;
 		if (apic_test_vector(vector, apic->regs + APIC_TMR))
 			trigger_mode = IOAPIC_LEVEL_TRIG;

arch/x86/kvm/vmx.c

@@ -2168,7 +2168,10 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
 {
 	unsigned long *msr_bitmap;
 
-	if (irqchip_in_kernel(vcpu->kvm) && apic_x2apic_mode(vcpu->arch.apic)) {
+	if (is_guest_mode(vcpu))
+		msr_bitmap = vmx_msr_bitmap_nested;
+	else if (irqchip_in_kernel(vcpu->kvm) &&
+		apic_x2apic_mode(vcpu->arch.apic)) {
 		if (is_long_mode(vcpu))
 			msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
 		else
@@ -2476,8 +2479,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	if (enable_ept) {
 		/* nested EPT: emulate EPT also to L1 */
 		vmx->nested.nested_vmx_secondary_ctls_high |=
-			SECONDARY_EXEC_ENABLE_EPT |
+			SECONDARY_EXEC_ENABLE_EPT;
-			SECONDARY_EXEC_UNRESTRICTED_GUEST;
 		vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
 			 VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
 			 VMX_EPT_INVEPT_BIT;
@@ -2491,6 +2493,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	} else
 		vmx->nested.nested_vmx_ept_caps = 0;
 
+	if (enable_unrestricted_guest)
+		vmx->nested.nested_vmx_secondary_ctls_high |=
+			SECONDARY_EXEC_UNRESTRICTED_GUEST;
+
 	/* miscellaneous data */
 	rdmsr(MSR_IA32_VMX_MISC,
 		vmx->nested.nested_vmx_misc_low,
@@ -9218,9 +9224,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	}
 
 	if (cpu_has_vmx_msr_bitmap() &&
-	    exec_control & CPU_BASED_USE_MSR_BITMAPS &&
+	    exec_control & CPU_BASED_USE_MSR_BITMAPS) {
-	    nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) {
+		nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
-		vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_nested));
+		/* MSR_BITMAP will be set by following vmx_set_efer. */
 	} else
 		exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
 

arch/x86/kvm/x86.c

@@ -2744,7 +2744,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_USER_NMI:
 	case KVM_CAP_REINJECT_CONTROL:
 	case KVM_CAP_IRQ_INJECT_STATUS:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_IOEVENTFD_NO_LENGTH:
 	case KVM_CAP_PIT2:

arch/x86/pci/common.c

@@ -513,31 +513,6 @@ void __init pcibios_set_cache_line_size(void)
 	}
 }
 
-/*
- * Some device drivers assume dev->irq won't change after calling
- * pci_disable_device(). So delay releasing of IRQ resource to driver
- * unbinding time. Otherwise it will break PM subsystem and drivers
- * like xen-pciback etc.
- */
-static int pci_irq_notifier(struct notifier_block *nb, unsigned long action,
-			    void *data)
-{
-	struct pci_dev *dev = to_pci_dev(data);
-
-	if (action != BUS_NOTIFY_UNBOUND_DRIVER)
-		return NOTIFY_DONE;
-
-	if (pcibios_disable_irq)
-		pcibios_disable_irq(dev);
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block pci_irq_nb = {
-	.notifier_call = pci_irq_notifier,
-	.priority = INT_MIN,
-};
-
 int __init pcibios_init(void)
 {
 	if (!raw_pci_ops) {
@@ -550,9 +525,6 @@ int __init pcibios_init(void)
 
 	if (pci_bf_sort >= pci_force_bf)
 		pci_sort_breadthfirst();
-
-	bus_register_notifier(&pci_bus_type, &pci_irq_nb);
-
 	return 0;
 }
 
@@ -711,6 +683,12 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 	return 0;
 }
 
+void pcibios_disable_device (struct pci_dev *dev)
+{
+	if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq)
+		pcibios_disable_irq(dev);
+}
+
 int pci_ext_cfg_avail(void)
 {
 	if (raw_pci_ext_ops)

arch/x86/pci/intel_mid_pci.c

@@ -234,10 +234,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 
 static void intel_mid_pci_irq_disable(struct pci_dev *dev)
 {
-	if (dev->irq_managed && dev->irq > 0) {
+	if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+	    dev->irq > 0) {
 		mp_unmap_irq(dev->irq);
 		dev->irq_managed = 0;
-		dev->irq = 0;
 	}
 }
 

arch/x86/pci/irq.c

@@ -1256,9 +1256,22 @@ static int pirq_enable_irq(struct pci_dev *dev)
 	return 0;
 }
 
+bool mp_should_keep_irq(struct device *dev)
+{
+	if (dev->power.is_prepared)
+		return true;
+#ifdef CONFIG_PM
+	if (dev->power.runtime_status == RPM_SUSPENDING)
+		return true;
+#endif
+
+	return false;
+}
+
 static void pirq_disable_irq(struct pci_dev *dev)
 {
-	if (io_apic_assign_pci_irqs && dev->irq_managed && dev->irq) {
+	if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
+	    dev->irq_managed && dev->irq) {
 		mp_unmap_irq(dev->irq);
 		dev->irq = 0;
 		dev->irq_managed = 0;

arch/x86/vdso/vdso32/sigreturn.S

@@ -17,6 +17,7 @@
 	.text
 	.globl __kernel_sigreturn
 	.type __kernel_sigreturn,@function
+	nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */
 	ALIGN
 __kernel_sigreturn:
 .LSTART_sigreturn:

block/blk-merge.c

@@ -592,7 +592,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) {
 		struct bio_vec *bprev;
 
-		bprev = &rq->biotail->bi_io_vec[bio->bi_vcnt - 1];
+		bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1];
 		if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset))
 			return false;
 	}