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
  ...
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 7a45775..f4976cd 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -4184,7 +4184,7 @@
       <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 @@
 	</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>
diff --git a/MAINTAINERS b/MAINTAINERS
index 7477888..36cf100 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1186,7 +1186,7 @@
 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/*/*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:	include/linux/platform_data/at24.h
 
 ATA OVER ETHERNET (AOE) DRIVER
-M:	"Ed L. Cashin" <ecashin@coraid.com>
-W:	http://support.coraid.com/support/linux
+M:	"Ed L. Cashin" <ed.cashin@acm.org>
+W:	http://www.openaoe.org/
 S:	Supported
 F:	Documentation/aoe/
 F:	drivers/block/aoe/
@@ -1741,7 +1742,7 @@
 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 @@
 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 @@
 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>
diff --git a/Makefile b/Makefile
index e734965..da36a3b 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc6
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 114234e..edda76f 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -67,7 +67,7 @@
 	       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 @@
 	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 @@
 	/* 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 @@
 
 	/*
 	 * 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 @@
 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)
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9f1f09a..cf4c0c9 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -619,6 +619,7 @@
 	select GENERIC_CLOCKEVENTS
 	select GPIO_PXA
 	select HAVE_IDE
+	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
 	select PLAT_PXA
 	select SPARSE_IRQ
diff --git a/arch/arm/boot/dts/dm8168-evm.dts b/arch/arm/boot/dts/dm8168-evm.dts
index d3a29c1..afe678f 100644
--- a/arch/arm/boot/dts/dm8168-evm.dts
+++ b/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 */
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index 3c97b5f..f35715b 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/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 {
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 127608d..c4659a9 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/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";
 			};
 		};
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index f4f78c4..3fdc84f 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/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 {
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index d771f68..eccc78d 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/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 {
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index 9d87609..d9176e6 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/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";
diff --git a/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts b/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts
index ab7891c..75742f8 100644
--- a/arch/arm/boot/dts/sun4i-a10-olinuxino-lime.dts
+++ b/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";
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 5c29258..eebb785 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/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>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index f8818f1..883cb4873 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/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>;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 3a8530b..fdd1817 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/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 {
diff --git a/arch/arm/crypto/aesbs-core.S_shipped b/arch/arm/crypto/aesbs-core.S_shipped
index 71e5fc7..1d1800f 100644
--- a/arch/arm/crypto/aesbs-core.S_shipped
+++ b/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 @@
 	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
diff --git a/arch/arm/crypto/bsaes-armv7.pl b/arch/arm/crypto/bsaes-armv7.pl
index be068db..a4d3856 100644
--- a/arch/arm/crypto/bsaes-armv7.pl
+++ b/arch/arm/crypto/bsaes-armv7.pl
@@ -701,14 +701,18 @@
 # 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__
@@ -717,8 +721,6 @@
 .code   32
 #endif
 
-.fpu	neon
-
 .type	_bsaes_decrypt8,%function
 .align	4
 _bsaes_decrypt8:
@@ -2076,9 +2078,11 @@
 	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
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index bf0fe99..4cf48c3 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -149,31 +149,30 @@
 	(__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))
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index e55408e..1d60beb 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -246,12 +246,9 @@
 		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"
-		    : "=r" (mmfr0));
+		unsigned int mmfr0 = read_cpuid_ext(CPUID_EXT_MMFR0);
 		if ((mmfr0 & 0x0000000f) >= 0x00000003 ||
 		    (mmfr0 & 0x000000f0) >= 0x00000030)
 			cpu_arch = CPU_ARCH_ARMv7;
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 3e6859b..5656d79 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -290,7 +290,7 @@
 	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 @@
 	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 @@
 				     __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 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 @@
 		 */
 		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 @@
 		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 @@
 	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 @@
 	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
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index 2a2f4d5..25f1bee 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -720,6 +720,8 @@
 		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())
diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c
index 0eecd83..89a7c06 100644
--- a/arch/arm/mach-pxa/irq.c
+++ b/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 @@
 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 @@
 	} 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_base = io_p2v(0x40d00000);
+	pxa_irq_domain = irq_domain_add_legacy(node, irq_nr,
+					       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 @@
 };
 
 #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 @@
 {
 	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 @@
 		return;
 	}
 
-	pxa_irq_domain = irq_domain_add_legacy(node, pxa_internal_irq_nr, 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 < 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;
+	pxa_init_irq_common(node, pxa_internal_irq_nr, fn);
 }
 #endif /* CONFIG_OF */
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index 205f9bf..ac2ae5c 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -412,7 +412,7 @@
 };
 
 static struct platform_device can_regulator_device = {
-	.name	= "reg-fixed-volage",
+	.name	= "reg-fixed-voltage",
 	.id	= 0,
 	.dev	= {
 		.platform_data	= &can_regulator_pdata,
diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig
index a77604f..81502b9 100644
--- a/arch/arm/mach-sunxi/Kconfig
+++ b/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_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_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
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index c6c7696..8f15f70 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -1131,23 +1131,22 @@
 	}
 
 	ret = l2x0_cache_size_of_parse(np, aux_val, aux_mask, &assoc, SZ_512K);
-	if (ret)
-		return;
-
-	switch (assoc) {
-	case 16:
-		*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-		*aux_val |= L310_AUX_CTRL_ASSOCIATIVITY_16;
-		*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-		break;
-	case 8:
-		*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-		*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
-		break;
-	default:
-		pr_err("L2C-310 OF cache associativity %d invalid, only 8 or 16 permitted\n",
-		       assoc);
-		break;
+	if (!ret) {
+		switch (assoc) {
+		case 16:
+			*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+			*aux_val |= L310_AUX_CTRL_ASSOCIATIVITY_16;
+			*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+			break;
+		case 8:
+			*aux_val &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+			*aux_mask &= ~L2X0_AUX_CTRL_ASSOC_MASK;
+			break;
+		default:
+			pr_err("L2C-310 OF cache associativity %d invalid, only 8 or 16 permitted\n",
+			       assoc);
+			break;
+		}
 	}
 
 	prefetch = l2x0_saved_regs.prefetch_ctrl;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 170a116..c274476 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -171,7 +171,7 @@
 	 */
 	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);
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index a982dc3..6333d9c 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -552,6 +552,7 @@
 
 	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;
diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c
index 004e35c..cf30daf 100644
--- a/arch/arm/mm/pageattr.c
+++ b/arch/arm/mm/pageattr.c
@@ -49,7 +49,10 @@
 		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;
diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c
index db10169..8ca94d3 100644
--- a/arch/arm/plat-omap/dmtimer.c
+++ b/arch/arm/plat-omap/dmtimer.c
@@ -799,6 +799,7 @@
 	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 @@
 	}
 
 	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 @@
 	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 @@
 		}
 	spin_unlock_irqrestore(&dm_timer_lock, flags);
 
+	pm_runtime_disable(&pdev->dev);
+
 	return ret;
 }
 
diff --git a/arch/arm64/boot/dts/arm/juno-clocks.dtsi b/arch/arm64/boot/dts/arm/juno-clocks.dtsi
index ea2b566..c9b89ef 100644
--- a/arch/arm64/boot/dts/arm/juno-clocks.dtsi
+++ b/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>;
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index cb95930..d8c25b7 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -246,14 +246,30 @@
 	__ret; \
 })
 
-#define this_cpu_cmpxchg_1(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), 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)
-#define this_cpu_cmpxchg_8(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
+#define _protect_cmpxchg_local(pcp, o, n)			\
+({								\
+	typeof(*raw_cpu_ptr(&(pcp))) __ret;			\
+	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) \
-	cmpxchg_double_local(raw_cpu_ptr(&(ptr1)), raw_cpu_ptr(&(ptr2)), \
-				o1, o2, n1, n2)
+#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#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))
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 94674eb..54bb4ba 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/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)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 6458b53..bbfb600 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -158,6 +158,8 @@
 #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 @@
 #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 @@
 	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) {
-		unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm);
-		free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT);
-	}
+	if (KVM_PREALLOC_LEVEL > 0)
+		return PTRS_PER_S2_PGD * PAGE_SIZE;
+	return PTRS_PER_S2_PGD * sizeof(pgd_t);
 }
 
 static inline bool kvm_page_empty(void *ptr)
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index a9eee33..101a42b 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -151,6 +151,15 @@
 {
 	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);
 }
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 09da25b..4fde8c1 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -204,25 +204,47 @@
 	return ret;
 }
 
-#define _percpu_add(pcp, val) \
-	__percpu_add(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+#define _percpu_read(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))
-
-#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))
+	_pcp_protect(__percpu_or, pcp, val)
 
 #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)
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 9a8fd84..941c375 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -39,7 +39,11 @@
 
 #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()					\
 ({							\
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 2b8d701..ab21e0d 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -337,7 +337,11 @@
 
 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();
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 58e0c2b..ef7d112 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -51,7 +51,7 @@
 }
 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 @@
 
 		*ret_page = phys_to_page(phys);
 		ptr = (void *)val;
+		if (flags & __GFP_ZERO)
+			memset(ptr, 0, size);
 	}
 
 	return ptr;
@@ -101,6 +103,7 @@
 		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 @@
 			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 @@
 
 	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));
diff --git a/arch/metag/include/asm/io.h b/arch/metag/include/asm/io.h
index 9359e50..d5779b0 100644
--- a/arch/metag/include/asm/io.h
+++ b/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
 
diff --git a/arch/metag/include/asm/pgtable-bits.h b/arch/metag/include/asm/pgtable-bits.h
new file mode 100644
index 0000000..25ba672
--- /dev/null
+++ b/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 */
diff --git a/arch/metag/include/asm/pgtable.h b/arch/metag/include/asm/pgtable.h
index d0604c0..ffa3a3a 100644
--- a/arch/metag/include/asm/pgtable.h
+++ b/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 */
@@ -21,100 +22,6 @@
 #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
  * table.
diff --git a/arch/nios2/include/uapi/asm/Kbuild b/arch/nios2/include/uapi/asm/Kbuild
index 37613119..e0bb972 100644
--- a/arch/nios2/include/uapi/asm/Kbuild
+++ b/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
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 0d231ad..0c9b6af 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -126,7 +126,6 @@
 		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 @@
  */
 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();
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index f213f5b..d174372 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
 
 	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 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 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_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)
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 5a8997d..8eefb12 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -55,8 +55,8 @@
 #define ENTRY_COMP(_name_) .word sys_##_name_
 #endif
 
-	ENTRY_SAME(restart_syscall)	/* 0 */
-	ENTRY_SAME(exit)
+90:	ENTRY_SAME(restart_syscall)	/* 0 */
+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
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 03cd858..4cbe23a 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/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 | \
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 1c874fb..af56b5c 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/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 */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index f337666..f830468 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -437,6 +437,26 @@
 		.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,
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index f421781..2128f3a 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/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 @@
 
 	may_hard_irq_enable();
 
+	kvmppc_set_host_ipi(smp_processor_id(), 0);
 	__this_cpu_inc(irq_stat.doorbell_irqs);
 
 	smp_ipi_demux();
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index c2df815..9519e6b 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1408,7 +1408,7 @@
 	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
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index de4018a..de74756 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -636,7 +636,7 @@
 	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 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 @@
 			else
 				vcpu->arch.intr_msr &= ~MSR_LE;
 		}
-		mutex_unlock(&kvm->lock);
 	}
 
 	/*
@@ -981,6 +980,7 @@
 		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,
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bb94e6f..6cbf163 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1005,6 +1005,7 @@
 	/* 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
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index fc34025..38a4508 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/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 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 @@
 	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 @@
 		 * 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())
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 90cf3dc..8f35d52 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -25,10 +25,10 @@
 static struct kobject *mobility_kobj;
 
 struct update_props_workarea {
-	u32 phandle;
-	u32 state;
-	u64 reserved;
-	u32 nprops;
+	__be32 phandle;
+	__be32 state;
+	__be64 reserved;
+	__be32 nprops;
 } __packed;
 
 #define NODE_ACTION_MASK	0xff000000
@@ -54,11 +54,11 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 			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 @@
 		 */
 		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 @@
 	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 @@
 int pseries_devicetree_update(s32 scope)
 {
 	char *rtas_buf;
-	u32 *data;
+	__be32 *data;
 	int update_nodes_token;
 	int rc;
 
@@ -254,17 +256,17 @@
 		if (rc && rc != 1)
 			break;
 
-		data = (u32 *)rtas_buf + 4;
-		while (*data & NODE_ACTION_MASK) {
+		data = (__be32 *)rtas_buf + 4;
+		while (be32_to_cpu(*data) & NODE_ACTION_MASK) {
 			int i;
-			u32 action = *data & NODE_ACTION_MASK;
-			int node_count = *data & NODE_COUNT_MASK;
+			u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK;
+			u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK;
 
 			data++;
 
 			for (i = 0; i < node_count; i++) {
-				u32 phandle = *data++;
-				u32 drc_index;
+				__be32 phandle = *data++;
+				__be32 drc_index;
 
 				switch (action) {
 				case DELETE_DT_NODE:
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index c9df40b..c9c875d 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -211,7 +211,7 @@
 
 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 {									    \
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 82c1989..6c79f1b 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/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 @@
 		return -EFAULT;
 	if (addr == MCOUNT_ADDR) {
 		/* Initial code replacement */
-#ifdef CC_USING_HOTPATCH
-		/* 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_orig_insn(&orig);
 		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 @@
 		 * 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;
-		orig.disp = KPROBE_ON_FTRACE_CALL;
-		new.disp = KPROBE_ON_FTRACE_NOP;
+		ftrace_generate_kprobe_call_insn(&orig);
+		ftrace_generate_kprobe_nop_insn(&new);
 	} else {
 		/* Replace ftrace call with a nop. */
 		ftrace_generate_call_insn(&orig, rec->ip);
@@ -111,7 +141,7 @@
 
 	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 @@
 		 * 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;
-		orig.disp = KPROBE_ON_FTRACE_NOP;
-		new.disp = KPROBE_ON_FTRACE_CALL;
+		ftrace_generate_kprobe_nop_insn(&orig);
+		ftrace_generate_kprobe_call_insn(&new);
 	} else {
 		/* Replace nop with an ftrace call. */
 		ftrace_generate_nop_insn(&orig);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index c3f8d15..e6a1578 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1415,7 +1415,7 @@
 
 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 @@
 		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)
diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S
index 6b09fdf..ca62946 100644
--- a/arch/s390/kernel/swsusp_asm64.S
+++ b/arch/s390/kernel/swsusp_asm64.S
@@ -177,6 +177,17 @@
 	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:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f6579cf..19e17bd 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -165,7 +165,6 @@
 	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:
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 96ac69c..efb00ec 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -86,6 +86,9 @@
 	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
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index 4f6725f..f5b6537 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -2957,6 +2957,17 @@
 				   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 @@
 #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
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 9b672be..50d4840 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -407,16 +407,16 @@
 {
 }
 
-#define ioread8(X)			readb(X)
-#define ioread16(X)			readw(X)
-#define ioread16be(X)			__raw_readw(X)
-#define ioread32(X)			readl(X)
-#define ioread32be(X)			__raw_readl(X)
-#define iowrite8(val,X)			writeb(val,X)
-#define iowrite16(val,X)		writew(val,X)
-#define iowrite16be(val,X)		__raw_writew(val,X)
-#define iowrite32(val,X)		writel(val,X)
-#define iowrite32be(val,X)		__raw_writel(val,X)
+#define ioread8			readb
+#define ioread16		readw
+#define ioread16be		__raw_readw
+#define ioread32		readl
+#define ioread32be		__raw_readl
+#define iowrite8		writeb
+#define iowrite16		writew
+#define iowrite16be		__raw_writew
+#define iowrite32		writel
+#define iowrite32be		__raw_writel
 
 /* Create a virtual mapping cookie for an IO port range */
 void __iomem *ioport_map(unsigned long port, unsigned int nr);
diff --git a/arch/sparc/include/asm/starfire.h b/arch/sparc/include/asm/starfire.h
index c100dc2..176fa0a 100644
--- a/arch/sparc/include/asm/starfire.h
+++ b/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);
 
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 88d322b..07cc49e5 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -98,11 +98,7 @@
 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);
diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index 5c55145..662500f 100644
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@@ -48,6 +48,7 @@
 	{ .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);
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index caedf83..afbaba5 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -837,3 +837,19 @@
 	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)
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index 7e967c8..eb978c7 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -217,6 +217,31 @@
 	.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 @@
 			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 @@
 		pcr_ops = &n5_pcr_ops;
 		break;
 
+	case SUN4V_CHIP_SPARC_M7:
+		pcr_ops = &m7_pcr_ops;
+		break;
+
 	default:
 		ret = -ENODEV;
 		break;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 46a5e45..86eebfa 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -792,6 +792,42 @@
 	.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 @@
 	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 @@
 		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]);
-		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);
+		sparc_pmu_start(cp, PERF_EF_RELOAD);
 	}
 out:
 	for (i = 0; i < cpuc->n_events; i++) {
@@ -1101,7 +1132,6 @@
 	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 @@
 		}
 	}
 
-	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
@@ -1361,7 +1390,6 @@
 	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 @@
 
 	ret = 0;
 out:
-	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
@@ -1667,6 +1694,10 @@
 		sparc_pmu = &niagara4_pmu;
 		return true;
 	}
+	if (!strcmp(sparc_pmu_type, "sparc-m7")) {
+		sparc_pmu = &sparc_m7_pmu;
+		return true;
+	}
 	return false;
 }
 
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 0be7bf9..46a5964 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -287,6 +287,8 @@
 			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 @@
 		       (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));
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index da6f1a7..61139d9 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1406,11 +1406,32 @@
 	scheduler_ipi();
 }
 
-/* This is a nop because we capture all other cpus
- * anyways when making the PROM active.
- */
+static void stop_this_cpu(void *dummy)
+{
+	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);
 }
 
 /**
diff --git a/arch/sparc/kernel/starfire.c b/arch/sparc/kernel/starfire.c
index 82281a5..167fdfd 100644
--- a/arch/sparc/kernel/starfire.c
+++ b/arch/sparc/kernel/starfire.c
@@ -28,11 +28,6 @@
 		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
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index c85403d..30e7ddb 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -333,7 +333,7 @@
 	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,
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index a27651e..0e69974 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2427,6 +2427,8 @@
 		}
 		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 @@
 	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 @@
 	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();
diff --git a/arch/sparc/lib/memmove.S b/arch/sparc/lib/memmove.S
index b7f6334..857ad4f 100644
--- a/arch/sparc/lib/memmove.S
+++ b/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 @@
 	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)
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3ea267c..4ca0d6b 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2820,7 +2820,7 @@
 
 	return 0;
 }
-device_initcall(report_memory);
+arch_initcall(report_memory);
 
 #ifdef CONFIG_SMP
 #define do_flush_tlb_kernel_range	smp_flush_tlb_kernel_range
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 7083c16..bb13763 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/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 @@
 	return slots_fetch_random();
 }
 
-static void add_kaslr_setup_data(struct boot_params *params, __u8 enabled)
-{
-	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 char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size)
@@ -335,17 +306,14 @@
 #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,
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 5903089..a950864 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -401,8 +401,7 @@
 	 * 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,
+	output = choose_kernel_location(input_data, input_len, output,
 					output_len > run_size ? output_len
 							      : run_size);
 
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index ee3576b..04477d6 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -57,8 +57,7 @@
 
 #if CONFIG_RANDOMIZE_BASE
 /* aslr.c */
-unsigned char *choose_kernel_location(struct boot_params *params,
-				      unsigned char *input,
+unsigned char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size);
@@ -66,8 +65,7 @@
 bool has_cpuflag(int flag);
 #else
 static inline
-unsigned char *choose_kernel_location(struct boot_params *params,
-				      unsigned char *input,
+unsigned char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size)
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 947c6bf..54f60ab 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1155,7 +1155,7 @@
 		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 @@
 		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;
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 0dbc082..72ba21a 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -370,7 +370,7 @@
 	preempt_disable();
 	tsk->thread.fpu_counter = 0;
 	__drop_fpu(tsk);
-	clear_used_math();
+	clear_stopped_child_used_math(tsk);
 	preempt_enable();
 }
 
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 95e11f7..f97fbe3 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -51,8 +51,6 @@
 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;
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index fa1195d..164e3f8 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,6 +93,8 @@
 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);
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 44e6dd7..225b098 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/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
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 3d525c6..803b684 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1338,6 +1338,26 @@
 }
 
 /*
+ * 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 @@
 	 */
 	early_acpi_process_madt();
 
+	/*
+	 * Hardware-reduced ACPI mode initialization:
+	 */
+	acpi_reduced_hw_init();
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index c2fd21f..017149c 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -37,10 +37,12 @@
 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);
-	id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U);
+	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+		rdmsrl(MSR_FAM10H_NODE_ID, value);
+		id |= (value << 2) & 0xff00;
+	}
 
 	return id;
 }
@@ -155,10 +157,18 @@
 
 static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 {
-	if (c->phys_proc_id != node) {
-		c->phys_proc_id = node;
-		per_cpu(cpu_llc_id, smp_processor_id()) = node;
+	u64 val;
+	u32 nodes = 1;
+
+	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)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1d74d16..2babb39 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -364,12 +364,21 @@
  * 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 @@
 
 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 @@
 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)
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 9bbb9b3..d1ac80b 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -47,13 +47,21 @@
 
 #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
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 98dc931..0a2421c 100644
--- a/arch/x86/kernel/setup.c
+++ b/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 @@
 }
 #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 @@
 		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 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 (relocation range: 0x%lx-0x%lx)\n",
-			 (unsigned long)&_text - __START_KERNEL,
-			 __START_KERNEL,
-			 __START_KERNEL_map,
-			 MODULES_VADDR-1);
-	else
-		pr_emerg("Kernel Offset: disabled\n");
+	pr_emerg("Kernel Offset: 0x%lx from 0x%lx "
+		 "(relocation range: 0x%lx-0x%lx)\n",
+		 (unsigned long)&_text - __START_KERNEL, __START_KERNEL,
+		 __START_KERNEL_map, MODULES_VADDR-1);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9d2073e..4ff5d16 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -384,7 +384,7 @@
 		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 @@
 	 * 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! */
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 34f66e5..cdc6cf9 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -379,7 +379,7 @@
 		 * 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 @@
 		 */
 		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();
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index cc31f7c..9541ba3 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -507,6 +507,7 @@
 		return -EOPNOTSUPP;
 
 	if (len != 1) {
+		memset(val, 0, len);
 		pr_pic_unimpl("non byte read\n");
 		return 0;
 	}
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index b1947e0..46d4449 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -422,6 +422,7 @@
 			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 @@
 		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);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index bd4e34d..4ee827d 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -833,8 +833,7 @@
 
 static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
 {
-	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
-	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
+	if (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;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f7b20b4..ae4f6d3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2168,7 +2168,10 @@
 {
 	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 @@
 	if (enable_ept) {
 		/* nested EPT: emulate EPT also to L1 */
 		vmx->nested.nested_vmx_secondary_ctls_high |=
-			SECONDARY_EXEC_ENABLE_EPT |
-			SECONDARY_EXEC_UNRESTRICTED_GUEST;
+			SECONDARY_EXEC_ENABLE_EPT;
 		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 @@
 	} 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 @@
 	}
 
 	if (cpu_has_vmx_msr_bitmap() &&
-	    exec_control & CPU_BASED_USE_MSR_BITMAPS &&
-	    nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) {
-		vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_nested));
+	    exec_control & CPU_BASED_USE_MSR_BITMAPS) {
+		nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
+		/* MSR_BITMAP will be set by following vmx_set_efer. */
 	} else
 		exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bd7a70b..32bf19e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2744,7 +2744,6 @@
 	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:
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 3d2612b..2fb3847 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -513,31 +513,6 @@
 	}
 }
 
-/*
- * 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 @@
 
 	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 @@
 	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)
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index efb8493..852aa4c 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -234,10 +234,10 @@
 
 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;
 	}
 }
 
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index e71b3db..5dc6ca5 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1256,9 +1256,22 @@
 	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;
diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/vdso/vdso32/sigreturn.S
index 31776d0..d7ec4e2 100644
--- a/arch/x86/vdso/vdso32/sigreturn.S
+++ b/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:
diff --git a/block/blk-merge.c b/block/blk-merge.c
index fc1ff3b..fd3fee8 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -592,7 +592,7 @@
 	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;
 	}
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index d53a764..be3290c 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -278,9 +278,11 @@
 		/*
 		 * We're out of tags on this hardware queue, kick any
 		 * pending IO submits before going to sleep waiting for
-		 * some to complete.
+		 * some to complete. Note that hctx can be NULL here for
+		 * reserved tag allocation.
 		 */
-		blk_mq_run_hw_queue(hctx, false);
+		if (hctx)
+			blk_mq_run_hw_queue(hctx, false);
 
 		/*
 		 * Retry tag allocation after running the hardware queue,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4f4bea2..b7b8933 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1938,7 +1938,7 @@
 	 */
 	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
 			    PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
-		goto err_map;
+		goto err_mq_usage;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
 	blk_queue_rq_timeout(q, 30000);
@@ -1981,7 +1981,7 @@
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 
 	if (blk_mq_init_hw_queues(q, set))
-		goto err_hw;
+		goto err_mq_usage;
 
 	mutex_lock(&all_q_mutex);
 	list_add_tail(&q->all_q_node, &all_q_list);
@@ -1993,7 +1993,7 @@
 
 	return q;
 
-err_hw:
+err_mq_usage:
 	blk_cleanup_queue(q);
 err_hctxs:
 	kfree(map);
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index e7f718d..b1def41 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -485,6 +485,14 @@
 	if (!pin || !dev->irq_managed || dev->irq <= 0)
 		return;
 
+	/* Keep IOAPIC pin configuration when suspending */
+	if (dev->dev.power.is_prepared)
+		return;
+#ifdef	CONFIG_PM
+	if (dev->dev.power.runtime_status == RPM_SUSPENDING)
+		return;
+#endif
+
 	entry = acpi_pci_irq_lookup(dev, pin);
 	if (!entry)
 		return;
@@ -505,6 +513,5 @@
 	if (gsi >= 0) {
 		acpi_unregister_gsi(gsi);
 		dev->irq_managed = 0;
-		dev->irq = 0;
 	}
 }
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 4c35f08..ef150eb 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4737,7 +4737,7 @@
 		return NULL;
 
 	/* libsas case */
-	if (!ap->scsi_host) {
+	if (ap->flags & ATA_FLAG_SAS_HOST) {
 		tag = ata_sas_allocate_tag(ap);
 		if (tag < 0)
 			return NULL;
@@ -4776,7 +4776,7 @@
 	tag = qc->tag;
 	if (likely(ata_tag_valid(tag))) {
 		qc->tag = ATA_TAG_POISON;
-		if (!ap->scsi_host)
+		if (ap->flags & ATA_FLAG_SAS_HOST)
 			ata_sas_free_tag(tag, ap);
 	}
 }
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index beb8b27..a13587b 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -243,4 +243,12 @@
 extern struct regcache_ops regcache_lzo_ops;
 extern struct regcache_ops regcache_flat_ops;
 
+static inline const char *regmap_name(const struct regmap *map)
+{
+	if (map->dev)
+		return dev_name(map->dev);
+
+	return map->name;
+}
+
 #endif
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index d453a2c..81751a4 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -307,7 +307,7 @@
 	if (pos == 0) {
 		memmove(blk + offset * map->cache_word_size,
 			blk, rbnode->blklen * map->cache_word_size);
-		bitmap_shift_right(present, present, offset, blklen);
+		bitmap_shift_left(present, present, offset, blklen);
 	}
 
 	/* update the rbnode block, its size and the base register */
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index f373c35..87db989 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -218,7 +218,7 @@
 		ret = map->cache_ops->read(map, reg, value);
 
 		if (ret == 0)
-			trace_regmap_reg_read_cache(map->dev, reg, *value);
+			trace_regmap_reg_read_cache(map, reg, *value);
 
 		return ret;
 	}
@@ -311,7 +311,7 @@
 	dev_dbg(map->dev, "Syncing %s cache\n",
 		map->cache_ops->name);
 	name = map->cache_ops->name;
-	trace_regcache_sync(map->dev, name, "start");
+	trace_regcache_sync(map, name, "start");
 
 	if (!map->cache_dirty)
 		goto out;
@@ -346,7 +346,7 @@
 
 	regmap_async_complete(map);
 
-	trace_regcache_sync(map->dev, name, "stop");
+	trace_regcache_sync(map, name, "stop");
 
 	return ret;
 }
@@ -381,7 +381,7 @@
 	name = map->cache_ops->name;
 	dev_dbg(map->dev, "Syncing %s cache from %d-%d\n", name, min, max);
 
-	trace_regcache_sync(map->dev, name, "start region");
+	trace_regcache_sync(map, name, "start region");
 
 	if (!map->cache_dirty)
 		goto out;
@@ -401,7 +401,7 @@
 
 	regmap_async_complete(map);
 
-	trace_regcache_sync(map->dev, name, "stop region");
+	trace_regcache_sync(map, name, "stop region");
 
 	return ret;
 }
@@ -428,7 +428,7 @@
 
 	map->lock(map->lock_arg);
 
-	trace_regcache_drop_region(map->dev, min, max);
+	trace_regcache_drop_region(map, min, max);
 
 	ret = map->cache_ops->drop(map, min, max);
 
@@ -455,7 +455,7 @@
 	map->lock(map->lock_arg);
 	WARN_ON(map->cache_bypass && enable);
 	map->cache_only = enable;
-	trace_regmap_cache_only(map->dev, enable);
+	trace_regmap_cache_only(map, enable);
 	map->unlock(map->lock_arg);
 }
 EXPORT_SYMBOL_GPL(regcache_cache_only);
@@ -493,7 +493,7 @@
 	map->lock(map->lock_arg);
 	WARN_ON(map->cache_only && enable);
 	map->cache_bypass = enable;
-	trace_regmap_cache_bypass(map->dev, enable);
+	trace_regmap_cache_bypass(map, enable);
 	map->unlock(map->lock_arg);
 }
 EXPORT_SYMBOL_GPL(regcache_cache_bypass);
@@ -608,7 +608,8 @@
 	for (i = start; i < end; i++) {
 		regtmp = block_base + (i * map->reg_stride);
 
-		if (!regcache_reg_present(cache_present, i))
+		if (!regcache_reg_present(cache_present, i) ||
+		    !regmap_writeable(map, regtmp))
 			continue;
 
 		val = regcache_get_val(map, block, i);
@@ -677,7 +678,8 @@
 	for (i = start; i < end; i++) {
 		regtmp = block_base + (i * map->reg_stride);
 
-		if (!regcache_reg_present(cache_present, i)) {
+		if (!regcache_reg_present(cache_present, i) ||
+		    !regmap_writeable(map, regtmp)) {
 			ret = regcache_sync_block_raw_flush(map, &data,
 							    base, regtmp);
 			if (ret != 0)
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 6299a50..a6c3f75 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -499,7 +499,8 @@
 		goto err_alloc;
 	}
 
-	ret = request_threaded_irq(irq, NULL, regmap_irq_thread, irq_flags,
+	ret = request_threaded_irq(irq, NULL, regmap_irq_thread,
+				   irq_flags | IRQF_ONESHOT,
 				   chip->name, d);
 	if (ret != 0) {
 		dev_err(map->dev, "Failed to request IRQ %d for %s: %d\n",
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index f99b098..dbfe6a6 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1281,7 +1281,7 @@
 	if (map->async && map->bus->async_write) {
 		struct regmap_async *async;
 
-		trace_regmap_async_write_start(map->dev, reg, val_len);
+		trace_regmap_async_write_start(map, reg, val_len);
 
 		spin_lock_irqsave(&map->async_lock, flags);
 		async = list_first_entry_or_null(&map->async_free,
@@ -1339,8 +1339,7 @@
 		return ret;
 	}
 
-	trace_regmap_hw_write_start(map->dev, reg,
-				    val_len / map->format.val_bytes);
+	trace_regmap_hw_write_start(map, reg, val_len / map->format.val_bytes);
 
 	/* If we're doing a single register write we can probably just
 	 * send the work_buf directly, otherwise try to do a gather
@@ -1372,8 +1371,7 @@
 		kfree(buf);
 	}
 
-	trace_regmap_hw_write_done(map->dev, reg,
-				   val_len / map->format.val_bytes);
+	trace_regmap_hw_write_done(map, reg, val_len / map->format.val_bytes);
 
 	return ret;
 }
@@ -1407,12 +1405,12 @@
 
 	map->format.format_write(map, reg, val);
 
-	trace_regmap_hw_write_start(map->dev, reg, 1);
+	trace_regmap_hw_write_start(map, reg, 1);
 
 	ret = map->bus->write(map->bus_context, map->work_buf,
 			      map->format.buf_size);
 
-	trace_regmap_hw_write_done(map->dev, reg, 1);
+	trace_regmap_hw_write_done(map, reg, 1);
 
 	return ret;
 }
@@ -1470,7 +1468,7 @@
 		dev_info(map->dev, "%x <= %x\n", reg, val);
 #endif
 
-	trace_regmap_reg_write(map->dev, reg, val);
+	trace_regmap_reg_write(map, reg, val);
 
 	return map->reg_write(context, reg, val);
 }
@@ -1773,7 +1771,7 @@
 	for (i = 0; i < num_regs; i++) {
 		int reg = regs[i].reg;
 		int val = regs[i].def;
-		trace_regmap_hw_write_start(map->dev, reg, 1);
+		trace_regmap_hw_write_start(map, reg, 1);
 		map->format.format_reg(u8, reg, map->reg_shift);
 		u8 += reg_bytes + pad_bytes;
 		map->format.format_val(u8, val, 0);
@@ -1788,7 +1786,7 @@
 
 	for (i = 0; i < num_regs; i++) {
 		int reg = regs[i].reg;
-		trace_regmap_hw_write_done(map->dev, reg, 1);
+		trace_regmap_hw_write_done(map, reg, 1);
 	}
 	return ret;
 }
@@ -2059,15 +2057,13 @@
 	 */
 	u8[0] |= map->read_flag_mask;
 
-	trace_regmap_hw_read_start(map->dev, reg,
-				   val_len / map->format.val_bytes);
+	trace_regmap_hw_read_start(map, reg, val_len / map->format.val_bytes);
 
 	ret = map->bus->read(map->bus_context, map->work_buf,
 			     map->format.reg_bytes + map->format.pad_bytes,
 			     val, val_len);
 
-	trace_regmap_hw_read_done(map->dev, reg,
-				  val_len / map->format.val_bytes);
+	trace_regmap_hw_read_done(map, reg, val_len / map->format.val_bytes);
 
 	return ret;
 }
@@ -2123,7 +2119,7 @@
 			dev_info(map->dev, "%x => %x\n", reg, *val);
 #endif
 
-		trace_regmap_reg_read(map->dev, reg, *val);
+		trace_regmap_reg_read(map, reg, *val);
 
 		if (!map->cache_bypass)
 			regcache_write(map, reg, *val);
@@ -2480,7 +2476,7 @@
 	struct regmap *map = async->map;
 	bool wake;
 
-	trace_regmap_async_io_complete(map->dev);
+	trace_regmap_async_io_complete(map);
 
 	spin_lock(&map->async_lock);
 	list_move(&async->list, &map->async_free);
@@ -2525,7 +2521,7 @@
 	if (!map->bus || !map->bus->async_write)
 		return 0;
 
-	trace_regmap_async_complete_start(map->dev);
+	trace_regmap_async_complete_start(map);
 
 	wait_event(map->async_waitq, regmap_async_is_done(map));
 
@@ -2534,7 +2530,7 @@
 	map->async_ret = 0;
 	spin_unlock_irqrestore(&map->async_lock, flags);
 
-	trace_regmap_async_complete_done(map->dev);
+	trace_regmap_async_complete_done(map);
 
 	return ret;
 }
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 4bc2a5c..a98c41f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -803,10 +803,6 @@
 		return -EINVAL;
 	}
 
-	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
-	if (!nbd_dev)
-		return -ENOMEM;
-
 	part_shift = 0;
 	if (max_part > 0) {
 		part_shift = fls(max_part);
@@ -828,6 +824,10 @@
 	if (nbds_max > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
 
+	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
+	if (!nbd_dev)
+		return -ENOMEM;
+
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = alloc_disk(1 << part_shift);
 		if (!disk)
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index ceb32dd..e23be20 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -3003,6 +3003,7 @@
 	}
 	get_device(dev->device);
 
+	INIT_LIST_HEAD(&dev->node);
 	INIT_WORK(&dev->probe_work, nvme_async_probe);
 	schedule_work(&dev->probe_work);
 	return 0;
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index fae2dbb..72d7028 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -142,6 +142,7 @@
 	 * notification
 	 */
 	struct work_struct control_work;
+	struct work_struct config_work;
 
 	struct list_head ports;
 
@@ -1837,10 +1838,21 @@
 
 	portdev = vdev->priv;
 
+	if (!use_multiport(portdev))
+		schedule_work(&portdev->config_work);
+}
+
+static void config_work_handler(struct work_struct *work)
+{
+	struct ports_device *portdev;
+
+	portdev = container_of(work, struct ports_device, control_work);
 	if (!use_multiport(portdev)) {
+		struct virtio_device *vdev;
 		struct port *port;
 		u16 rows, cols;
 
+		vdev = portdev->vdev;
 		virtio_cread(vdev, struct virtio_console_config, cols, &cols);
 		virtio_cread(vdev, struct virtio_console_config, rows, &rows);
 
@@ -2040,12 +2052,14 @@
 
 	virtio_device_ready(portdev->vdev);
 
+	INIT_WORK(&portdev->config_work, &config_work_handler);
+	INIT_WORK(&portdev->control_work, &control_work_handler);
+
 	if (multiport) {
 		unsigned int nr_added_bufs;
 
 		spin_lock_init(&portdev->c_ivq_lock);
 		spin_lock_init(&portdev->c_ovq_lock);
-		INIT_WORK(&portdev->control_work, &control_work_handler);
 
 		nr_added_bufs = fill_queue(portdev->c_ivq,
 					   &portdev->c_ivq_lock);
@@ -2113,6 +2127,8 @@
 	/* Finish up work that's lined up */
 	if (use_multiport(portdev))
 		cancel_work_sync(&portdev->control_work);
+	else
+		cancel_work_sync(&portdev->config_work);
 
 	list_for_each_entry_safe(port, port2, &portdev->ports, list)
 		unplug_port(port);
@@ -2164,6 +2180,7 @@
 
 	virtqueue_disable_cb(portdev->c_ivq);
 	cancel_work_sync(&portdev->control_work);
+	cancel_work_sync(&portdev->config_work);
 	/*
 	 * Once more: if control_work_handler() was running, it would
 	 * enable the cb as the last step.
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 68161f7..a0b036c 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -192,6 +192,7 @@
 config SH_TIMER_CMT
 	bool "Renesas CMT timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	default SYS_SUPPORTS_SH_CMT
 	help
 	  This enables build of a clocksource and clockevent driver for
@@ -201,6 +202,7 @@
 config SH_TIMER_MTU2
 	bool "Renesas MTU2 timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	default SYS_SUPPORTS_SH_MTU2
 	help
 	  This enables build of a clockevent driver for the Multi-Function
@@ -210,6 +212,7 @@
 config SH_TIMER_TMU
 	bool "Renesas TMU timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	default SYS_SUPPORTS_SH_TMU
 	help
 	  This enables build of a clocksource and clockevent driver for
diff --git a/drivers/clocksource/time-efm32.c b/drivers/clocksource/time-efm32.c
index bba62f9..ec57ba2 100644
--- a/drivers/clocksource/time-efm32.c
+++ b/drivers/clocksource/time-efm32.c
@@ -225,12 +225,12 @@
 	clock_event_ddata.base = base;
 	clock_event_ddata.periodic_top = DIV_ROUND_CLOSEST(rate, 1024 * HZ);
 
-	setup_irq(irq, &efm32_clock_event_irq);
-
 	clockevents_config_and_register(&clock_event_ddata.evtdev,
 					DIV_ROUND_CLOSEST(rate, 1024),
 					0xf, 0xffff);
 
+	setup_irq(irq, &efm32_clock_event_irq);
+
 	return 0;
 
 err_get_irq:
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index 0226844..58597fb 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -17,7 +17,6 @@
 #include <linux/irq.h>
 #include <linux/irqreturn.h>
 #include <linux/reset.h>
-#include <linux/sched_clock.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -137,11 +136,6 @@
 	.dev_id = &sun5i_clockevent,
 };
 
-static u64 sun5i_timer_sched_read(void)
-{
-	return ~readl(timer_base + TIMER_CNTVAL_LO_REG(1));
-}
-
 static void __init sun5i_timer_init(struct device_node *node)
 {
 	struct reset_control *rstc;
@@ -172,16 +166,11 @@
 	writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
 	       timer_base + TIMER_CTL_REG(1));
 
-	sched_clock_register(sun5i_timer_sched_read, 32, rate);
 	clocksource_mmio_init(timer_base + TIMER_CNTVAL_LO_REG(1), node->name,
 			      rate, 340, 32, clocksource_mmio_readl_down);
 
 	ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
 
-	ret = setup_irq(irq, &sun5i_timer_irq);
-	if (ret)
-		pr_warn("failed to setup irq %d\n", irq);
-
 	/* Enable timer0 interrupt */
 	val = readl(timer_base + TIMER_IRQ_EN_REG);
 	writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG);
@@ -191,6 +180,10 @@
 
 	clockevents_config_and_register(&sun5i_clockevent, rate,
 					TIMER_SYNC_TICKS, 0xffffffff);
+
+	ret = setup_irq(irq, &sun5i_timer_irq);
+	if (ret)
+		pr_warn("failed to setup irq %d\n", irq);
 }
 CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer",
 		       sun5i_timer_init);
diff --git a/drivers/cpuidle/cpuidle-mvebu-v7.c b/drivers/cpuidle/cpuidle-mvebu-v7.c
index 38e6861..980151f 100644
--- a/drivers/cpuidle/cpuidle-mvebu-v7.c
+++ b/drivers/cpuidle/cpuidle-mvebu-v7.c
@@ -37,11 +37,11 @@
 		deepidle = true;
 
 	ret = mvebu_v7_cpu_suspend(deepidle);
+	cpu_pm_exit();
+
 	if (ret)
 		return ret;
 
-	cpu_pm_exit();
-
 	return index;
 }
 
@@ -50,17 +50,17 @@
 	.states[0]		= ARM_CPUIDLE_WFI_STATE,
 	.states[1]		= {
 		.enter			= mvebu_v7_enter_idle,
-		.exit_latency		= 10,
+		.exit_latency		= 100,
 		.power_usage		= 50,
-		.target_residency	= 100,
+		.target_residency	= 1000,
 		.name			= "MV CPU IDLE",
 		.desc			= "CPU power down",
 	},
 	.states[2]		= {
 		.enter			= mvebu_v7_enter_idle,
-		.exit_latency		= 100,
+		.exit_latency		= 1000,
 		.power_usage		= 5,
-		.target_residency	= 1000,
+		.target_residency	= 10000,
 		.flags			= MVEBU_V7_FLAG_DEEP_IDLE,
 		.name			= "MV CPU DEEP IDLE",
 		.desc			= "CPU and L2 Fabric power down",
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 4a5fd24..83aa55d 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -97,6 +97,12 @@
 
 #define DRIVER_NAME	"pl08xdmac"
 
+#define PL80X_DMA_BUSWIDTHS \
+	BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) | \
+	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)
+
 static struct amba_driver pl08x_amba_driver;
 struct pl08x_driver_data;
 
@@ -2070,6 +2076,10 @@
 	pl08x->memcpy.device_pause = pl08x_pause;
 	pl08x->memcpy.device_resume = pl08x_resume;
 	pl08x->memcpy.device_terminate_all = pl08x_terminate_all;
+	pl08x->memcpy.src_addr_widths = PL80X_DMA_BUSWIDTHS;
+	pl08x->memcpy.dst_addr_widths = PL80X_DMA_BUSWIDTHS;
+	pl08x->memcpy.directions = BIT(DMA_MEM_TO_MEM);
+	pl08x->memcpy.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
 
 	/* Initialize slave engine */
 	dma_cap_set(DMA_SLAVE, pl08x->slave.cap_mask);
@@ -2086,6 +2096,10 @@
 	pl08x->slave.device_pause = pl08x_pause;
 	pl08x->slave.device_resume = pl08x_resume;
 	pl08x->slave.device_terminate_all = pl08x_terminate_all;
+	pl08x->slave.src_addr_widths = PL80X_DMA_BUSWIDTHS;
+	pl08x->slave.dst_addr_widths = PL80X_DMA_BUSWIDTHS;
+	pl08x->slave.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	pl08x->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
 
 	/* Get the platform data */
 	pl08x->pd = dev_get_platdata(&adev->dev);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 1e1a4c5..0b4fc6f 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -238,93 +238,126 @@
 }
 
 /*
- * atc_get_current_descriptors -
- * locate the descriptor which equal to physical address in DSCR
- * @atchan: the channel we want to start
- * @dscr_addr: physical descriptor address in DSCR
+ * atc_get_desc_by_cookie - get the descriptor of a cookie
+ * @atchan: the DMA channel
+ * @cookie: the cookie to get the descriptor for
  */
-static struct at_desc *atc_get_current_descriptors(struct at_dma_chan *atchan,
-							u32 dscr_addr)
+static struct at_desc *atc_get_desc_by_cookie(struct at_dma_chan *atchan,
+						dma_cookie_t cookie)
 {
-	struct at_desc  *desc, *_desc, *child, *desc_cur = NULL;
+	struct at_desc *desc, *_desc;
+
+	list_for_each_entry_safe(desc, _desc, &atchan->queue, desc_node) {
+		if (desc->txd.cookie == cookie)
+			return desc;
+	}
 
 	list_for_each_entry_safe(desc, _desc, &atchan->active_list, desc_node) {
-		if (desc->lli.dscr == dscr_addr) {
-			desc_cur = desc;
-			break;
-		}
-
-		list_for_each_entry(child, &desc->tx_list, desc_node) {
-			if (child->lli.dscr == dscr_addr) {
-				desc_cur = child;
-				break;
-			}
-		}
+		if (desc->txd.cookie == cookie)
+			return desc;
 	}
 
-	return desc_cur;
+	return NULL;
 }
 
-/*
- * atc_get_bytes_left -
- * Get the number of bytes residue in dma buffer,
- * @chan: the channel we want to start
+/**
+ * atc_calc_bytes_left - calculates the number of bytes left according to the
+ * value read from CTRLA.
+ *
+ * @current_len: the number of bytes left before reading CTRLA
+ * @ctrla: the value of CTRLA
+ * @desc: the descriptor containing the transfer width
  */
-static int atc_get_bytes_left(struct dma_chan *chan)
+static inline int atc_calc_bytes_left(int current_len, u32 ctrla,
+					struct at_desc *desc)
+{
+	return current_len - ((ctrla & ATC_BTSIZE_MAX) << desc->tx_width);
+}
+
+/**
+ * atc_calc_bytes_left_from_reg - calculates the number of bytes left according
+ * to the current value of CTRLA.
+ *
+ * @current_len: the number of bytes left before reading CTRLA
+ * @atchan: the channel to read CTRLA for
+ * @desc: the descriptor containing the transfer width
+ */
+static inline int atc_calc_bytes_left_from_reg(int current_len,
+			struct at_dma_chan *atchan, struct at_desc *desc)
+{
+	u32 ctrla = channel_readl(atchan, CTRLA);
+
+	return atc_calc_bytes_left(current_len, ctrla, desc);
+}
+
+/**
+ * atc_get_bytes_left - get the number of bytes residue for a cookie
+ * @chan: DMA channel
+ * @cookie: transaction identifier to check status of
+ */
+static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 {
 	struct at_dma_chan      *atchan = to_at_dma_chan(chan);
-	struct at_dma           *atdma = to_at_dma(chan->device);
-	int	chan_id = atchan->chan_common.chan_id;
 	struct at_desc *desc_first = atc_first_active(atchan);
-	struct at_desc *desc_cur;
-	int ret = 0, count = 0;
+	struct at_desc *desc;
+	int ret;
+	u32 ctrla, dscr;
 
 	/*
-	 * Initialize necessary values in the first time.
-	 * remain_desc record remain desc length.
+	 * If the cookie doesn't match to the currently running transfer then
+	 * we can return the total length of the associated DMA transfer,
+	 * because it is still queued.
 	 */
-	if (atchan->remain_desc == 0)
-		/* First descriptor embedds the transaction length */
-		atchan->remain_desc = desc_first->len;
+	desc = atc_get_desc_by_cookie(atchan, cookie);
+	if (desc == NULL)
+		return -EINVAL;
+	else if (desc != desc_first)
+		return desc->total_len;
 
-	/*
-	 * This happens when current descriptor transfer complete.
-	 * The residual buffer size should reduce current descriptor length.
-	 */
-	if (unlikely(test_bit(ATC_IS_BTC, &atchan->status))) {
-		clear_bit(ATC_IS_BTC, &atchan->status);
-		desc_cur = atc_get_current_descriptors(atchan,
-						channel_readl(atchan, DSCR));
-		if (!desc_cur) {
-			ret = -EINVAL;
-			goto out;
-		}
+	/* cookie matches to the currently running transfer */
+	ret = desc_first->total_len;
 
-		count = (desc_cur->lli.ctrla & ATC_BTSIZE_MAX)
-			<< desc_first->tx_width;
-		if (atchan->remain_desc < count) {
-			ret = -EINVAL;
-			goto out;
-		}
+	if (desc_first->lli.dscr) {
+		/* hardware linked list transfer */
 
-		atchan->remain_desc -= count;
-		ret = atchan->remain_desc;
-	} else {
 		/*
-		 * Get residual bytes when current
-		 * descriptor transfer in progress.
+		 * Calculate the residue by removing the length of the child
+		 * descriptors already transferred from the total length.
+		 * To get the current child descriptor we can use the value of
+		 * the channel's DSCR register and compare it against the value
+		 * of the hardware linked list structure of each child
+		 * descriptor.
 		 */
-		count = (channel_readl(atchan, CTRLA) & ATC_BTSIZE_MAX)
-				<< (desc_first->tx_width);
-		ret = atchan->remain_desc - count;
-	}
-	/*
-	 * Check fifo empty.
-	 */
-	if (!(dma_readl(atdma, CHSR) & AT_DMA_EMPT(chan_id)))
-		atc_issue_pending(chan);
 
-out:
+		ctrla = channel_readl(atchan, CTRLA);
+		rmb(); /* ensure CTRLA is read before DSCR */
+		dscr = channel_readl(atchan, DSCR);
+
+		/* for the first descriptor we can be more accurate */
+		if (desc_first->lli.dscr == dscr)
+			return atc_calc_bytes_left(ret, ctrla, desc_first);
+
+		ret -= desc_first->len;
+		list_for_each_entry(desc, &desc_first->tx_list, desc_node) {
+			if (desc->lli.dscr == dscr)
+				break;
+
+			ret -= desc->len;
+		}
+
+		/*
+		 * For the last descriptor in the chain we can calculate
+		 * the remaining bytes using the channel's register.
+		 * Note that the transfer width of the first and last
+		 * descriptor may differ.
+		 */
+		if (!desc->lli.dscr)
+			ret = atc_calc_bytes_left_from_reg(ret, atchan, desc);
+	} else {
+		/* single transfer */
+		ret = atc_calc_bytes_left_from_reg(ret, atchan, desc_first);
+	}
+
 	return ret;
 }
 
@@ -539,8 +572,6 @@
 					/* Give information to tasklet */
 					set_bit(ATC_IS_ERROR, &atchan->status);
 				}
-				if (pending & AT_DMA_BTC(i))
-					set_bit(ATC_IS_BTC, &atchan->status);
 				tasklet_schedule(&atchan->tasklet);
 				ret = IRQ_HANDLED;
 			}
@@ -653,14 +684,18 @@
 		desc->lli.ctrlb = ctrlb;
 
 		desc->txd.cookie = 0;
+		desc->len = xfer_count << src_width;
 
 		atc_desc_chain(&first, &prev, desc);
 	}
 
 	/* First descriptor of the chain embedds additional information */
 	first->txd.cookie = -EBUSY;
-	first->len = len;
+	first->total_len = len;
+
+	/* set transfer width for the calculation of the residue */
 	first->tx_width = src_width;
+	prev->tx_width = src_width;
 
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
@@ -752,6 +787,7 @@
 					| ATC_SRC_WIDTH(mem_width)
 					| len >> mem_width;
 			desc->lli.ctrlb = ctrlb;
+			desc->len = len;
 
 			atc_desc_chain(&first, &prev, desc);
 			total_len += len;
@@ -792,6 +828,7 @@
 					| ATC_DST_WIDTH(mem_width)
 					| len >> reg_width;
 			desc->lli.ctrlb = ctrlb;
+			desc->len = len;
 
 			atc_desc_chain(&first, &prev, desc);
 			total_len += len;
@@ -806,8 +843,11 @@
 
 	/* First descriptor of the chain embedds additional information */
 	first->txd.cookie = -EBUSY;
-	first->len = total_len;
+	first->total_len = total_len;
+
+	/* set transfer width for the calculation of the residue */
 	first->tx_width = reg_width;
+	prev->tx_width = reg_width;
 
 	/* first link descriptor of list is responsible of flags */
 	first->txd.flags = flags; /* client is in control of this ack */
@@ -872,6 +912,7 @@
 				| ATC_FC_MEM2PER
 				| ATC_SIF(atchan->mem_if)
 				| ATC_DIF(atchan->per_if);
+		desc->len = period_len;
 		break;
 
 	case DMA_DEV_TO_MEM:
@@ -883,6 +924,7 @@
 				| ATC_FC_PER2MEM
 				| ATC_SIF(atchan->per_if)
 				| ATC_DIF(atchan->mem_if);
+		desc->len = period_len;
 		break;
 
 	default:
@@ -964,7 +1006,7 @@
 
 	/* First descriptor of the chain embedds additional information */
 	first->txd.cookie = -EBUSY;
-	first->len = buf_len;
+	first->total_len = buf_len;
 	first->tx_width = reg_width;
 
 	return &first->txd;
@@ -1118,7 +1160,7 @@
 	spin_lock_irqsave(&atchan->lock, flags);
 
 	/*  Get number of bytes left in the active transactions */
-	bytes = atc_get_bytes_left(chan);
+	bytes = atc_get_bytes_left(chan, cookie);
 
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
@@ -1214,7 +1256,6 @@
 
 	spin_lock_irqsave(&atchan->lock, flags);
 	atchan->descs_allocated = i;
-	atchan->remain_desc = 0;
 	list_splice(&tmp_list, &atchan->free_list);
 	dma_cookie_init(chan);
 	spin_unlock_irqrestore(&atchan->lock, flags);
@@ -1257,7 +1298,6 @@
 	list_splice_init(&atchan->free_list, &list);
 	atchan->descs_allocated = 0;
 	atchan->status = 0;
-	atchan->remain_desc = 0;
 
 	dev_vdbg(chan2dev(chan), "free_chan_resources: done\n");
 }
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index d6bba6c..2727ca5 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -181,8 +181,9 @@
  * @at_lli: hardware lli structure
  * @txd: support for the async_tx api
  * @desc_node: node on the channed descriptors list
- * @len: total transaction bytecount
+ * @len: descriptor byte count
  * @tx_width: transfer width
+ * @total_len: total transaction byte count
  */
 struct at_desc {
 	/* FIRST values the hardware uses */
@@ -194,6 +195,7 @@
 	struct list_head		desc_node;
 	size_t				len;
 	u32				tx_width;
+	size_t				total_len;
 };
 
 static inline struct at_desc *
@@ -213,7 +215,6 @@
 enum atc_status {
 	ATC_IS_ERROR = 0,
 	ATC_IS_PAUSED = 1,
-	ATC_IS_BTC = 2,
 	ATC_IS_CYCLIC = 24,
 };
 
@@ -231,7 +232,6 @@
  * @save_cfg: configuration register that is saved on suspend/resume cycle
  * @save_dscr: for cyclic operations, preserve next descriptor address in
  *             the cyclic list on suspend/resume cycle
- * @remain_desc: to save remain desc length
  * @dma_sconfig: configuration for slave transfers, passed via
  * .device_config
  * @lock: serializes enqueue/dequeue operations to descriptors lists
@@ -251,7 +251,6 @@
 	struct tasklet_struct	tasklet;
 	u32			save_cfg;
 	u32			save_dscr;
-	u32			remain_desc;
 	struct dma_slave_config dma_sconfig;
 
 	spinlock_t		lock;
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index 6565a36..b2c3ae0 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -26,6 +26,8 @@
 
 #include "internal.h"
 
+#define DRV_NAME	"dw_dmac"
+
 static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
 					struct of_dma *ofdma)
 {
@@ -284,7 +286,7 @@
 	.remove		= dw_remove,
 	.shutdown       = dw_shutdown,
 	.driver = {
-		.name	= "dw_dmac",
+		.name	= DRV_NAME,
 		.pm	= &dw_dev_pm_ops,
 		.of_match_table = of_match_ptr(dw_dma_of_id_table),
 		.acpi_match_table = ACPI_PTR(dw_dma_acpi_id_table),
@@ -305,3 +307,4 @@
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller platform driver");
+MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 18c0a13..66a0efb 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -531,6 +531,10 @@
 		dev_err(sdma->dev, "Timeout waiting for CH0 ready\n");
 	}
 
+	/* Set bits of CONFIG register with dynamic context switching */
+	if (readl(sdma->regs + SDMA_H_CONFIG) == 0)
+		writel_relaxed(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG);
+
 	return ret ? 0 : -ETIMEDOUT;
 }
 
@@ -1394,9 +1398,6 @@
 
 	writel_relaxed(ccb_phys, sdma->regs + SDMA_H_C0PTR);
 
-	/* Set bits of CONFIG register with given context switching mode */
-	writel_relaxed(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG);
-
 	/* Initializes channel's priorities */
 	sdma_set_channel_priority(&sdma->channel[0], 7);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index d717430..69af73f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -649,6 +649,7 @@
 	pr_debug("     sdma queue id: %d\n", q->properties.sdma_queue_id);
 	pr_debug("     sdma engine id: %d\n", q->properties.sdma_engine_id);
 
+	init_sdma_vm(dqm, q, qpd);
 	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval != 0) {
@@ -656,7 +657,14 @@
 		return retval;
 	}
 
-	init_sdma_vm(dqm, q, qpd);
+	retval = mqd->load_mqd(mqd, q->mqd, 0,
+				0, NULL);
+	if (retval != 0) {
+		deallocate_sdma_queue(dqm, q->sdma_id);
+		mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+		return retval;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index e415a2a..c7d298e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -44,7 +44,7 @@
 	BUG_ON(!kq || !dev);
 	BUG_ON(type != KFD_QUEUE_TYPE_DIQ && type != KFD_QUEUE_TYPE_HIQ);
 
-	pr_debug("kfd: In func %s initializing queue type %d size %d\n",
+	pr_debug("amdkfd: In func %s initializing queue type %d size %d\n",
 			__func__, KFD_QUEUE_TYPE_HIQ, queue_size);
 
 	nop.opcode = IT_NOP;
@@ -69,12 +69,16 @@
 
 	prop.doorbell_ptr = kfd_get_kernel_doorbell(dev, &prop.doorbell_off);
 
-	if (prop.doorbell_ptr == NULL)
+	if (prop.doorbell_ptr == NULL) {
+		pr_err("amdkfd: error init doorbell");
 		goto err_get_kernel_doorbell;
+	}
 
 	retval = kfd_gtt_sa_allocate(dev, queue_size, &kq->pq);
-	if (retval != 0)
+	if (retval != 0) {
+		pr_err("amdkfd: error init pq queues size (%d)\n", queue_size);
 		goto err_pq_allocate_vidmem;
+	}
 
 	kq->pq_kernel_addr = kq->pq->cpu_ptr;
 	kq->pq_gpu_addr = kq->pq->gpu_addr;
@@ -165,10 +169,8 @@
 err_eop_allocate_vidmem:
 	kfd_gtt_sa_free(dev, kq->pq);
 err_pq_allocate_vidmem:
-	pr_err("kfd: error init pq\n");
 	kfd_release_kernel_doorbell(dev, prop.doorbell_ptr);
 err_get_kernel_doorbell:
-	pr_err("kfd: error init doorbell");
 	return false;
 
 }
@@ -187,6 +189,8 @@
 	else if (kq->queue->properties.type == KFD_QUEUE_TYPE_DIQ)
 		kfd_gtt_sa_free(kq->dev, kq->fence_mem_obj);
 
+	kq->mqd->uninit_mqd(kq->mqd, kq->queue->mqd, kq->queue->mqd_mem_obj);
+
 	kfd_gtt_sa_free(kq->dev, kq->rptr_mem);
 	kfd_gtt_sa_free(kq->dev, kq->wptr_mem);
 	kq->ops_asic_specific.uninitialize(kq);
@@ -211,7 +215,7 @@
 	queue_address = (unsigned int *)kq->pq_kernel_addr;
 	queue_size_dwords = kq->queue->properties.queue_size / sizeof(uint32_t);
 
-	pr_debug("kfd: In func %s\nrptr: %d\nwptr: %d\nqueue_address 0x%p\n",
+	pr_debug("amdkfd: In func %s\nrptr: %d\nwptr: %d\nqueue_address 0x%p\n",
 			__func__, rptr, wptr, queue_address);
 
 	available_size = (rptr - 1 - wptr + queue_size_dwords) %
@@ -296,7 +300,7 @@
 	}
 
 	if (kq->ops.initialize(kq, dev, type, KFD_KERNEL_QUEUE_SIZE) == false) {
-		pr_err("kfd: failed to init kernel queue\n");
+		pr_err("amdkfd: failed to init kernel queue\n");
 		kfree(kq);
 		return NULL;
 	}
@@ -319,7 +323,7 @@
 
 	BUG_ON(!dev);
 
-	pr_err("kfd: starting kernel queue test\n");
+	pr_err("amdkfd: starting kernel queue test\n");
 
 	kq = kernel_queue_init(dev, KFD_QUEUE_TYPE_HIQ);
 	BUG_ON(!kq);
@@ -330,7 +334,7 @@
 		buffer[i] = kq->nop_packet;
 	kq->ops.submit_packet(kq);
 
-	pr_err("kfd: ending kernel queue test\n");
+	pr_err("amdkfd: ending kernel queue test\n");
 }
 
 
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index a5e7461..0a67803 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -50,7 +50,7 @@
 
 config DRM_EXYNOS_DP
 	bool "EXYNOS DRM DP driver support"
-	depends on (DRM_EXYNOS_FIMD || DRM_EXYNOS7DECON) && ARCH_EXYNOS && (DRM_PTN3460=n || DRM_PTN3460=y || DRM_PTN3460=DRM_EXYNOS)
+	depends on (DRM_EXYNOS_FIMD || DRM_EXYNOS7_DECON) && ARCH_EXYNOS && (DRM_PTN3460=n || DRM_PTN3460=y || DRM_PTN3460=DRM_EXYNOS)
 	default DRM_EXYNOS
 	select DRM_PANEL
 	help
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 63f02e2..9700461 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -888,8 +888,8 @@
 	of_node_put(i80_if_timings);
 
 	ctx->regs = of_iomap(dev->of_node, 0);
-	if (IS_ERR(ctx->regs)) {
-		ret = PTR_ERR(ctx->regs);
+	if (!ctx->regs) {
+		ret = -ENOMEM;
 		goto err_del_component;
 	}
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.c b/drivers/gpu/drm/exynos/exynos_drm_connector.c
deleted file mode 100644
index ba9b3d5..0000000
--- a/drivers/gpu/drm/exynos/exynos_drm_connector.c
+++ /dev/null
@@ -1,245 +0,0 @@
-/*
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- * Authors:
- *	Inki Dae <inki.dae@samsung.com>
- *	Joonyoung Shim <jy0922.shim@samsung.com>
- *	Seung-Woo Kim <sw0312.kim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <drm/drmP.h>
-#include <drm/drm_crtc_helper.h>
-
-#include <drm/exynos_drm.h>
-#include "exynos_drm_drv.h"
-#include "exynos_drm_encoder.h"
-#include "exynos_drm_connector.h"
-
-#define to_exynos_connector(x)	container_of(x, struct exynos_drm_connector,\
-				drm_connector)
-
-struct exynos_drm_connector {
-	struct drm_connector		drm_connector;
-	uint32_t			encoder_id;
-	struct exynos_drm_display	*display;
-};
-
-static int exynos_drm_connector_get_modes(struct drm_connector *connector)
-{
-	struct exynos_drm_connector *exynos_connector =
-					to_exynos_connector(connector);
-	struct exynos_drm_display *display = exynos_connector->display;
-	struct edid *edid = NULL;
-	unsigned int count = 0;
-	int ret;
-
-	/*
-	 * if get_edid() exists then get_edid() callback of hdmi side
-	 * is called to get edid data through i2c interface else
-	 * get timing from the FIMD driver(display controller).
-	 *
-	 * P.S. in case of lcd panel, count is always 1 if success
-	 * because lcd panel has only one mode.
-	 */
-	if (display->ops->get_edid) {
-		edid = display->ops->get_edid(display, connector);
-		if (IS_ERR_OR_NULL(edid)) {
-			ret = PTR_ERR(edid);
-			edid = NULL;
-			DRM_ERROR("Panel operation get_edid failed %d\n", ret);
-			goto out;
-		}
-
-		count = drm_add_edid_modes(connector, edid);
-		if (!count) {
-			DRM_ERROR("Add edid modes failed %d\n", count);
-			goto out;
-		}
-
-		drm_mode_connector_update_edid_property(connector, edid);
-	} else {
-		struct exynos_drm_panel_info *panel;
-		struct drm_display_mode *mode = drm_mode_create(connector->dev);
-		if (!mode) {
-			DRM_ERROR("failed to create a new display mode.\n");
-			return 0;
-		}
-
-		if (display->ops->get_panel)
-			panel = display->ops->get_panel(display);
-		else {
-			drm_mode_destroy(connector->dev, mode);
-			return 0;
-		}
-
-		drm_display_mode_from_videomode(&panel->vm, mode);
-		mode->width_mm = panel->width_mm;
-		mode->height_mm = panel->height_mm;
-		connector->display_info.width_mm = mode->width_mm;
-		connector->display_info.height_mm = mode->height_mm;
-
-		mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
-		drm_mode_set_name(mode);
-		drm_mode_probed_add(connector, mode);
-
-		count = 1;
-	}
-
-out:
-	kfree(edid);
-	return count;
-}
-
-static int exynos_drm_connector_mode_valid(struct drm_connector *connector,
-					    struct drm_display_mode *mode)
-{
-	struct exynos_drm_connector *exynos_connector =
-					to_exynos_connector(connector);
-	struct exynos_drm_display *display = exynos_connector->display;
-	int ret = MODE_BAD;
-
-	DRM_DEBUG_KMS("%s\n", __FILE__);
-
-	if (display->ops->check_mode)
-		if (!display->ops->check_mode(display, mode))
-			ret = MODE_OK;
-
-	return ret;
-}
-
-static struct drm_encoder *exynos_drm_best_encoder(
-		struct drm_connector *connector)
-{
-	struct drm_device *dev = connector->dev;
-	struct exynos_drm_connector *exynos_connector =
-					to_exynos_connector(connector);
-	return drm_encoder_find(dev, exynos_connector->encoder_id);
-}
-
-static struct drm_connector_helper_funcs exynos_connector_helper_funcs = {
-	.get_modes	= exynos_drm_connector_get_modes,
-	.mode_valid	= exynos_drm_connector_mode_valid,
-	.best_encoder	= exynos_drm_best_encoder,
-};
-
-static int exynos_drm_connector_fill_modes(struct drm_connector *connector,
-				unsigned int max_width, unsigned int max_height)
-{
-	struct exynos_drm_connector *exynos_connector =
-					to_exynos_connector(connector);
-	struct exynos_drm_display *display = exynos_connector->display;
-	unsigned int width, height;
-
-	width = max_width;
-	height = max_height;
-
-	/*
-	 * if specific driver want to find desired_mode using maxmum
-	 * resolution then get max width and height from that driver.
-	 */
-	if (display->ops->get_max_resol)
-		display->ops->get_max_resol(display, &width, &height);
-
-	return drm_helper_probe_single_connector_modes(connector, width,
-							height);
-}
-
-/* get detection status of display device. */
-static enum drm_connector_status
-exynos_drm_connector_detect(struct drm_connector *connector, bool force)
-{
-	struct exynos_drm_connector *exynos_connector =
-					to_exynos_connector(connector);
-	struct exynos_drm_display *display = exynos_connector->display;
-	enum drm_connector_status status = connector_status_disconnected;
-
-	if (display->ops->is_connected) {
-		if (display->ops->is_connected(display))
-			status = connector_status_connected;
-		else
-			status = connector_status_disconnected;
-	}
-
-	return status;
-}
-
-static void exynos_drm_connector_destroy(struct drm_connector *connector)
-{
-	struct exynos_drm_connector *exynos_connector =
-		to_exynos_connector(connector);
-
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-	kfree(exynos_connector);
-}
-
-static struct drm_connector_funcs exynos_connector_funcs = {
-	.dpms		= drm_helper_connector_dpms,
-	.fill_modes	= exynos_drm_connector_fill_modes,
-	.detect		= exynos_drm_connector_detect,
-	.destroy	= exynos_drm_connector_destroy,
-};
-
-struct drm_connector *exynos_drm_connector_create(struct drm_device *dev,
-						   struct drm_encoder *encoder)
-{
-	struct exynos_drm_connector *exynos_connector;
-	struct exynos_drm_display *display = exynos_drm_get_display(encoder);
-	struct drm_connector *connector;
-	int type;
-	int err;
-
-	exynos_connector = kzalloc(sizeof(*exynos_connector), GFP_KERNEL);
-	if (!exynos_connector)
-		return NULL;
-
-	connector = &exynos_connector->drm_connector;
-
-	switch (display->type) {
-	case EXYNOS_DISPLAY_TYPE_HDMI:
-		type = DRM_MODE_CONNECTOR_HDMIA;
-		connector->interlace_allowed = true;
-		connector->polled = DRM_CONNECTOR_POLL_HPD;
-		break;
-	case EXYNOS_DISPLAY_TYPE_VIDI:
-		type = DRM_MODE_CONNECTOR_VIRTUAL;
-		connector->polled = DRM_CONNECTOR_POLL_HPD;
-		break;
-	default:
-		type = DRM_MODE_CONNECTOR_Unknown;
-		break;
-	}
-
-	drm_connector_init(dev, connector, &exynos_connector_funcs, type);
-	drm_connector_helper_add(connector, &exynos_connector_helper_funcs);
-
-	err = drm_connector_register(connector);
-	if (err)
-		goto err_connector;
-
-	exynos_connector->encoder_id = encoder->base.id;
-	exynos_connector->display = display;
-	connector->dpms = DRM_MODE_DPMS_OFF;
-	connector->encoder = encoder;
-
-	err = drm_mode_connector_attach_encoder(connector, encoder);
-	if (err) {
-		DRM_ERROR("failed to attach a connector to a encoder\n");
-		goto err_sysfs;
-	}
-
-	DRM_DEBUG_KMS("connector has been created\n");
-
-	return connector;
-
-err_sysfs:
-	drm_connector_unregister(connector);
-err_connector:
-	drm_connector_cleanup(connector);
-	kfree(exynos_connector);
-	return NULL;
-}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.h b/drivers/gpu/drm/exynos/exynos_drm_connector.h
deleted file mode 100644
index 4eb20d7..0000000
--- a/drivers/gpu/drm/exynos/exynos_drm_connector.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- * Authors:
- *	Inki Dae <inki.dae@samsung.com>
- *	Joonyoung Shim <jy0922.shim@samsung.com>
- *	Seung-Woo Kim <sw0312.kim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef _EXYNOS_DRM_CONNECTOR_H_
-#define _EXYNOS_DRM_CONNECTOR_H_
-
-struct drm_connector *exynos_drm_connector_create(struct drm_device *dev,
-						   struct drm_encoder *encoder);
-
-#endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 925fc69..c300e22 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -284,14 +284,9 @@
 	}
 }
 
-static int fimd_ctx_initialize(struct fimd_context *ctx,
+static int fimd_iommu_attach_devices(struct fimd_context *ctx,
 			struct drm_device *drm_dev)
 {
-	struct exynos_drm_private *priv;
-	priv = drm_dev->dev_private;
-
-	ctx->drm_dev = drm_dev;
-	ctx->pipe = priv->pipe++;
 
 	/* attach this sub driver to iommu mapping if supported. */
 	if (is_drm_iommu_supported(ctx->drm_dev)) {
@@ -313,7 +308,7 @@
 	return 0;
 }
 
-static void fimd_ctx_remove(struct fimd_context *ctx)
+static void fimd_iommu_detach_devices(struct fimd_context *ctx)
 {
 	/* detach this sub driver from iommu mapping if supported. */
 	if (is_drm_iommu_supported(ctx->drm_dev))
@@ -1056,25 +1051,23 @@
 {
 	struct fimd_context *ctx = dev_get_drvdata(dev);
 	struct drm_device *drm_dev = data;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
 	int ret;
 
-	ret = fimd_ctx_initialize(ctx, drm_dev);
-	if (ret) {
-		DRM_ERROR("fimd_ctx_initialize failed.\n");
-		return ret;
-	}
+	ctx->drm_dev = drm_dev;
+	ctx->pipe = priv->pipe++;
 
 	ctx->crtc = exynos_drm_crtc_create(drm_dev, ctx->pipe,
 					   EXYNOS_DISPLAY_TYPE_LCD,
 					   &fimd_crtc_ops, ctx);
-	if (IS_ERR(ctx->crtc)) {
-		fimd_ctx_remove(ctx);
-		return PTR_ERR(ctx->crtc);
-	}
 
 	if (ctx->display)
 		exynos_drm_create_enc_conn(drm_dev, ctx->display);
 
+	ret = fimd_iommu_attach_devices(ctx, drm_dev);
+	if (ret)
+		return ret;
+
 	return 0;
 
 }
@@ -1086,10 +1079,10 @@
 
 	fimd_dpms(ctx->crtc, DRM_MODE_DPMS_OFF);
 
+	fimd_iommu_detach_devices(ctx);
+
 	if (ctx->display)
 		exynos_dpi_remove(ctx->display);
-
-	fimd_ctx_remove(ctx);
 }
 
 static const struct component_ops fimd_component_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index a561687..8ad5b72 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -175,7 +175,7 @@
 	struct exynos_drm_plane *exynos_plane = to_exynos_plane(plane);
 	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(plane->crtc);
 
-	if (exynos_crtc->ops->win_disable)
+	if (exynos_crtc && exynos_crtc->ops->win_disable)
 		exynos_crtc->ops->win_disable(exynos_crtc,
 					      exynos_plane->zpos);
 
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index d3ebaf2..a69002e 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -28,6 +28,7 @@
 	  i915_gem_execbuffer.o \
 	  i915_gem_gtt.o \
 	  i915_gem.o \
+	  i915_gem_shrinker.o \
 	  i915_gem_stolen.o \
 	  i915_gem_tiling.o \
 	  i915_gem_userptr.o \
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 1a52d6a..007c7d7 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1200,6 +1200,9 @@
 
 		seq_printf(m, "Max overclocked frequency: %dMHz\n",
 			   intel_gpu_freq(dev_priv, dev_priv->rps.max_freq));
+
+		seq_printf(m, "Idle freq: %d MHz\n",
+			   intel_gpu_freq(dev_priv, dev_priv->rps.idle_freq));
 	} else if (IS_VALLEYVIEW(dev)) {
 		u32 freq_sts;
 
@@ -1214,6 +1217,9 @@
 		seq_printf(m, "min GPU freq: %d MHz\n",
 			   intel_gpu_freq(dev_priv, dev_priv->rps.min_freq));
 
+		seq_printf(m, "idle GPU freq: %d MHz\n",
+			   intel_gpu_freq(dev_priv, dev_priv->rps.idle_freq));
+
 		seq_printf(m,
 			   "efficient (RPe) frequency: %d MHz\n",
 			   intel_gpu_freq(dev_priv, dev_priv->rps.efficient_freq));
@@ -2308,7 +2314,7 @@
 	u8 crc[6];
 
 	drm_modeset_lock_all(dev);
-	for_each_intel_encoder(dev, connector) {
+	for_each_intel_connector(dev, connector) {
 
 		if (connector->base.dpms != DRM_MODE_DPMS_ON)
 			continue;
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index d49ed68..68e0c85 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1199,7 +1199,7 @@
 	DRM_IOCTL_DEF_DRV(I915_OVERLAY_PUT_IMAGE, intel_overlay_put_image, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_OVERLAY_ATTRS, intel_overlay_attrs, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_SET_SPRITE_COLORKEY, intel_sprite_set_colorkey, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
-	DRM_IOCTL_DEF_DRV(I915_GET_SPRITE_COLORKEY, intel_sprite_get_colorkey, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
+	DRM_IOCTL_DEF_DRV(I915_GET_SPRITE_COLORKEY, drm_noop, DRM_MASTER|DRM_CONTROL_ALLOW|DRM_UNLOCKED),
 	DRM_IOCTL_DEF_DRV(I915_GEM_WAIT, i915_gem_wait_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_CREATE, i915_gem_context_create_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8ba7e1b..e326ac9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -56,7 +56,7 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20150313"
+#define DRIVER_DATE		"20150327"
 
 #undef WARN_ON
 /* Many gcc seem to no see through this and fall over :( */
@@ -427,6 +427,8 @@
 	u32 forcewake;
 	u32 error; /* gen6+ */
 	u32 err_int; /* gen7 */
+	u32 fault_data0; /* gen8, gen9 */
+	u32 fault_data1; /* gen8, gen9 */
 	u32 done_reg;
 	u32 gac_eco;
 	u32 gam_ecochk;
@@ -544,7 +546,7 @@
 	 * Returns true on success, false on failure.
 	 */
 	bool (*find_dpll)(const struct intel_limit *limit,
-			  struct intel_crtc *crtc,
+			  struct intel_crtc_state *crtc_state,
 			  int target, int refclk,
 			  struct dpll *match_clock,
 			  struct dpll *best_clock);
@@ -553,7 +555,7 @@
 				 struct drm_crtc *crtc,
 				 uint32_t sprite_width, uint32_t sprite_height,
 				 int pixel_size, bool enable, bool scaled);
-	void (*modeset_global_resources)(struct drm_device *dev);
+	void (*modeset_global_resources)(struct drm_atomic_state *state);
 	/* Returns the active state of the crtc, and if the crtc is active,
 	 * fills out the pipe-config with the hw state. */
 	bool (*get_pipe_config)(struct intel_crtc *,
@@ -1025,13 +1027,12 @@
 	u8 max_freq_softlimit;	/* Max frequency permitted by the driver */
 	u8 max_freq;		/* Maximum frequency, RP0 if not overclocking */
 	u8 min_freq;		/* AKA RPn. Minimum frequency */
+	u8 idle_freq;		/* Frequency to request when we are idle */
 	u8 efficient_freq;	/* AKA RPe. Pre-determined balanced frequency */
 	u8 rp1_freq;		/* "less than" RP0 power/freqency */
 	u8 rp0_freq;		/* Non-overclocked max frequency. */
 	u32 cz_freq;
 
-	u32 ei_interrupt_count;
-
 	int last_adj;
 	enum { LOW_POWER, BETWEEN, HIGH_POWER } power;
 
@@ -2442,7 +2443,6 @@
 struct i915_params {
 	int modeset;
 	int panel_ignore_lid;
-	unsigned int powersave;
 	int semaphores;
 	unsigned int lvds_downclock;
 	int lvds_channel_mode;
@@ -2462,6 +2462,7 @@
 	bool enable_hangcheck;
 	bool fastboot;
 	bool prefault_disable;
+	bool load_detect_test;
 	bool reset;
 	bool disable_display;
 	bool disable_vtd_wa;
@@ -2601,12 +2602,6 @@
 int i915_gem_wait_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 void i915_gem_load(struct drm_device *dev);
-unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
-			      long target,
-			      unsigned flags);
-#define I915_SHRINK_PURGEABLE 0x1
-#define I915_SHRINK_UNBOUND 0x2
-#define I915_SHRINK_BOUND 0x4
 void *i915_gem_object_alloc(struct drm_device *dev);
 void i915_gem_object_free(struct drm_i915_gem_object *obj);
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
@@ -2623,20 +2618,16 @@
 #define PIN_GLOBAL 0x4
 #define PIN_OFFSET_BIAS 0x8
 #define PIN_OFFSET_MASK (~4095)
-int __must_check i915_gem_object_pin_view(struct drm_i915_gem_object *obj,
-					  struct i915_address_space *vm,
-					  uint32_t alignment,
-					  uint64_t flags,
-					  const struct i915_ggtt_view *view);
-static inline
-int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj,
-				     struct i915_address_space *vm,
-				     uint32_t alignment,
-				     uint64_t flags)
-{
-	return i915_gem_object_pin_view(obj, vm, alignment, flags,
-						&i915_ggtt_view_normal);
-}
+int __must_check
+i915_gem_object_pin(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm,
+		    uint32_t alignment,
+		    uint64_t flags);
+int __must_check
+i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
+			 const struct i915_ggtt_view *view,
+			 uint32_t alignment,
+			 uint64_t flags);
 
 int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 		  u32 flags);
@@ -2776,8 +2767,10 @@
 int __must_check
 i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     u32 alignment,
-				     struct intel_engine_cs *pipelined);
-void i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj);
+				     struct intel_engine_cs *pipelined,
+				     const struct i915_ggtt_view *view);
+void i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj,
+					      const struct i915_ggtt_view *view);
 int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj,
 				int align);
 int i915_gem_open(struct drm_device *dev, struct drm_file *file);
@@ -2800,60 +2793,46 @@
 
 void i915_gem_restore_fences(struct drm_device *dev);
 
-unsigned long i915_gem_obj_offset_view(struct drm_i915_gem_object *o,
-				       struct i915_address_space *vm,
-				       enum i915_ggtt_view_type view);
-static inline
-unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o,
-				  struct i915_address_space *vm)
+unsigned long
+i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o,
+			      const struct i915_ggtt_view *view);
+unsigned long
+i915_gem_obj_offset(struct drm_i915_gem_object *o,
+		    struct i915_address_space *vm);
+static inline unsigned long
+i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *o)
 {
-	return i915_gem_obj_offset_view(o, vm, I915_GGTT_VIEW_NORMAL);
+	return i915_gem_obj_ggtt_offset_view(o, &i915_ggtt_view_normal);
 }
+
 bool i915_gem_obj_bound_any(struct drm_i915_gem_object *o);
-bool i915_gem_obj_bound_view(struct drm_i915_gem_object *o,
-			     struct i915_address_space *vm,
-			     enum i915_ggtt_view_type view);
-static inline
+bool i915_gem_obj_ggtt_bound_view(struct drm_i915_gem_object *o,
+				  const struct i915_ggtt_view *view);
 bool i915_gem_obj_bound(struct drm_i915_gem_object *o,
-			struct i915_address_space *vm)
-{
-	return i915_gem_obj_bound_view(o, vm, I915_GGTT_VIEW_NORMAL);
-}
+			struct i915_address_space *vm);
 
 unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
 				struct i915_address_space *vm);
-struct i915_vma *i915_gem_obj_to_vma_view(struct drm_i915_gem_object *obj,
-					  struct i915_address_space *vm,
-					  const struct i915_ggtt_view *view);
-static inline
-struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
-				     struct i915_address_space *vm)
-{
-	return i915_gem_obj_to_vma_view(obj, vm, &i915_ggtt_view_normal);
-}
-
 struct i915_vma *
-i915_gem_obj_lookup_or_create_vma_view(struct drm_i915_gem_object *obj,
-				       struct i915_address_space *vm,
-				       const struct i915_ggtt_view *view);
+i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm);
+struct i915_vma *
+i915_gem_obj_to_ggtt_view(struct drm_i915_gem_object *obj,
+			  const struct i915_ggtt_view *view);
 
-static inline
 struct i915_vma *
 i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
-				  struct i915_address_space *vm)
-{
-	return i915_gem_obj_lookup_or_create_vma_view(obj, vm,
-						&i915_ggtt_view_normal);
-}
+				  struct i915_address_space *vm);
+struct i915_vma *
+i915_gem_obj_lookup_or_create_ggtt_vma(struct drm_i915_gem_object *obj,
+				       const struct i915_ggtt_view *view);
 
-struct i915_vma *i915_gem_obj_to_ggtt(struct drm_i915_gem_object *obj);
-static inline bool i915_gem_obj_is_pinned(struct drm_i915_gem_object *obj) {
-	struct i915_vma *vma;
-	list_for_each_entry(vma, &obj->vma_list, vma_link)
-		if (vma->pin_count > 0)
-			return true;
-	return false;
+static inline struct i915_vma *
+i915_gem_obj_to_ggtt(struct drm_i915_gem_object *obj)
+{
+	return i915_gem_obj_to_ggtt_view(obj, &i915_ggtt_view_normal);
 }
+bool i915_gem_obj_is_pinned(struct drm_i915_gem_object *obj);
 
 /* Some GGTT VM helpers */
 #define i915_obj_to_ggtt(obj) \
@@ -2876,13 +2855,7 @@
 
 static inline bool i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *obj)
 {
-	return i915_gem_obj_bound(obj, i915_obj_to_ggtt(obj));
-}
-
-static inline unsigned long
-i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *obj)
-{
-	return i915_gem_obj_offset(obj, i915_obj_to_ggtt(obj));
+	return i915_gem_obj_ggtt_bound_view(obj, &i915_ggtt_view_normal);
 }
 
 static inline unsigned long
@@ -2906,7 +2879,13 @@
 	return i915_vma_unbind(i915_gem_obj_to_ggtt(obj));
 }
 
-void i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj);
+void i915_gem_object_ggtt_unpin_view(struct drm_i915_gem_object *obj,
+				     const struct i915_ggtt_view *view);
+static inline void
+i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj)
+{
+	i915_gem_object_ggtt_unpin_view(obj, &i915_ggtt_view_normal);
+}
 
 /* i915_gem_context.c */
 int __must_check i915_gem_context_init(struct drm_device *dev);
@@ -2978,6 +2957,17 @@
 					       u32 gtt_offset,
 					       u32 size);
 
+/* i915_gem_shrinker.c */
+unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv,
+			      long target,
+			      unsigned flags);
+#define I915_SHRINK_PURGEABLE 0x1
+#define I915_SHRINK_UNBOUND 0x2
+#define I915_SHRINK_BOUND 0x4
+unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
+void i915_gem_shrinker_init(struct drm_i915_private *dev_priv);
+
+
 /* i915_gem_tiling.c */
 static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0fe313d..d07c0b1 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1,5 +1,5 @@
 /*
- * Copyright © 2008 Intel Corporation
+ * Copyright © 2008-2015 Intel Corporation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -32,7 +32,6 @@
 #include "i915_vgpu.h"
 #include "i915_trace.h"
 #include "intel_drv.h"
-#include <linux/oom.h>
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -53,15 +52,6 @@
 					 struct drm_i915_fence_reg *fence,
 					 bool enable);
 
-static unsigned long i915_gem_shrinker_count(struct shrinker *shrinker,
-					     struct shrink_control *sc);
-static unsigned long i915_gem_shrinker_scan(struct shrinker *shrinker,
-					    struct shrink_control *sc);
-static int i915_gem_shrinker_oom(struct notifier_block *nb,
-				 unsigned long event,
-				 void *ptr);
-static unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
-
 static bool cpu_cache_is_coherent(struct drm_device *dev,
 				  enum i915_cache_level level)
 {
@@ -1936,12 +1926,6 @@
 	return i915_gem_mmap_gtt(file, dev, args->handle, &args->offset);
 }
 
-static inline int
-i915_gem_object_is_purgeable(struct drm_i915_gem_object *obj)
-{
-	return obj->madv == I915_MADV_DONTNEED;
-}
-
 /* Immediately discard the backing storage */
 static void
 i915_gem_object_truncate(struct drm_i915_gem_object *obj)
@@ -2047,85 +2031,6 @@
 	return 0;
 }
 
-unsigned long
-i915_gem_shrink(struct drm_i915_private *dev_priv,
-		long target, unsigned flags)
-{
-	const struct {
-		struct list_head *list;
-		unsigned int bit;
-	} phases[] = {
-		{ &dev_priv->mm.unbound_list, I915_SHRINK_UNBOUND },
-		{ &dev_priv->mm.bound_list, I915_SHRINK_BOUND },
-		{ NULL, 0 },
-	}, *phase;
-	unsigned long count = 0;
-
-	/*
-	 * As we may completely rewrite the (un)bound list whilst unbinding
-	 * (due to retiring requests) we have to strictly process only
-	 * one element of the list at the time, and recheck the list
-	 * on every iteration.
-	 *
-	 * In particular, we must hold a reference whilst removing the
-	 * object as we may end up waiting for and/or retiring the objects.
-	 * This might release the final reference (held by the active list)
-	 * and result in the object being freed from under us. This is
-	 * similar to the precautions the eviction code must take whilst
-	 * removing objects.
-	 *
-	 * Also note that although these lists do not hold a reference to
-	 * the object we can safely grab one here: The final object
-	 * unreferencing and the bound_list are both protected by the
-	 * dev->struct_mutex and so we won't ever be able to observe an
-	 * object on the bound_list with a reference count equals 0.
-	 */
-	for (phase = phases; phase->list; phase++) {
-		struct list_head still_in_list;
-
-		if ((flags & phase->bit) == 0)
-			continue;
-
-		INIT_LIST_HEAD(&still_in_list);
-		while (count < target && !list_empty(phase->list)) {
-			struct drm_i915_gem_object *obj;
-			struct i915_vma *vma, *v;
-
-			obj = list_first_entry(phase->list,
-					       typeof(*obj), global_list);
-			list_move_tail(&obj->global_list, &still_in_list);
-
-			if (flags & I915_SHRINK_PURGEABLE &&
-			    !i915_gem_object_is_purgeable(obj))
-				continue;
-
-			drm_gem_object_reference(&obj->base);
-
-			/* For the unbound phase, this should be a no-op! */
-			list_for_each_entry_safe(vma, v,
-						 &obj->vma_list, vma_link)
-				if (i915_vma_unbind(vma))
-					break;
-
-			if (i915_gem_object_put_pages(obj) == 0)
-				count += obj->base.size >> PAGE_SHIFT;
-
-			drm_gem_object_unreference(&obj->base);
-		}
-		list_splice(&still_in_list, phase->list);
-	}
-
-	return count;
-}
-
-static unsigned long
-i915_gem_shrink_all(struct drm_i915_private *dev_priv)
-{
-	i915_gem_evict_everything(dev_priv->dev);
-	return i915_gem_shrink(dev_priv, LONG_MAX,
-			       I915_SHRINK_BOUND | I915_SHRINK_UNBOUND);
-}
-
 static int
 i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 {
@@ -2755,24 +2660,11 @@
 
 	WARN_ON(i915_verify_lists(ring->dev));
 
-	/* Move any buffers on the active list that are no longer referenced
-	 * by the ringbuffer to the flushing/inactive lists as appropriate,
-	 * before we free the context associated with the requests.
+	/* Retire requests first as we use it above for the early return.
+	 * If we retire requests last, we may use a later seqno and so clear
+	 * the requests lists without clearing the active list, leading to
+	 * confusion.
 	 */
-	while (!list_empty(&ring->active_list)) {
-		struct drm_i915_gem_object *obj;
-
-		obj = list_first_entry(&ring->active_list,
-				      struct drm_i915_gem_object,
-				      ring_list);
-
-		if (!i915_gem_request_completed(obj->last_read_req, true))
-			break;
-
-		i915_gem_object_move_to_inactive(obj);
-	}
-
-
 	while (!list_empty(&ring->request_list)) {
 		struct drm_i915_gem_request *request;
 
@@ -2795,6 +2687,23 @@
 		i915_gem_free_request(request);
 	}
 
+	/* Move any buffers on the active list that are no longer referenced
+	 * by the ringbuffer to the flushing/inactive lists as appropriate,
+	 * before we free the context associated with the requests.
+	 */
+	while (!list_empty(&ring->active_list)) {
+		struct drm_i915_gem_object *obj;
+
+		obj = list_first_entry(&ring->active_list,
+				      struct drm_i915_gem_object,
+				      ring_list);
+
+		if (!i915_gem_request_completed(obj->last_read_req, true))
+			break;
+
+		i915_gem_object_move_to_inactive(obj);
+	}
+
 	if (unlikely(ring->trace_irq_req &&
 		     i915_gem_request_completed(ring->trace_irq_req, true))) {
 		ring->irq_put(ring);
@@ -3518,9 +3427,9 @@
 static struct i915_vma *
 i915_gem_object_bind_to_vm(struct drm_i915_gem_object *obj,
 			   struct i915_address_space *vm,
+			   const struct i915_ggtt_view *ggtt_view,
 			   unsigned alignment,
-			   uint64_t flags,
-			   const struct i915_ggtt_view *view)
+			   uint64_t flags)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3532,6 +3441,9 @@
 	struct i915_vma *vma;
 	int ret;
 
+	if(WARN_ON(i915_is_ggtt(vm) != !!ggtt_view))
+		return ERR_PTR(-EINVAL);
+
 	fence_size = i915_gem_get_gtt_size(dev,
 					   obj->base.size,
 					   obj->tiling_mode);
@@ -3570,7 +3482,9 @@
 
 	i915_gem_object_pin_pages(obj);
 
-	vma = i915_gem_obj_lookup_or_create_vma_view(obj, vm, view);
+	vma = ggtt_view ? i915_gem_obj_lookup_or_create_ggtt_vma(obj, ggtt_view) :
+			  i915_gem_obj_lookup_or_create_vma(obj, vm);
+
 	if (IS_ERR(vma))
 		goto err_unpin;
 
@@ -3600,6 +3514,17 @@
 	if (ret)
 		goto err_remove_node;
 
+	/*  allocate before insert / bind */
+	if (vma->vm->allocate_va_range) {
+		trace_i915_va_alloc(vma->vm, vma->node.start, vma->node.size,
+				VM_TO_TRACE_NAME(vma->vm));
+		ret = vma->vm->allocate_va_range(vma->vm,
+						vma->node.start,
+						vma->node.size);
+		if (ret)
+			goto err_remove_node;
+	}
+
 	trace_i915_vma_bind(vma, flags);
 	ret = i915_vma_bind(vma, obj->cache_level,
 			    flags & PIN_GLOBAL ? GLOBAL_BIND : 0);
@@ -3952,7 +3877,8 @@
 int
 i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     u32 alignment,
-				     struct intel_engine_cs *pipelined)
+				     struct intel_engine_cs *pipelined,
+				     const struct i915_ggtt_view *view)
 {
 	u32 old_read_domains, old_write_domain;
 	bool was_pin_display;
@@ -3988,7 +3914,9 @@
 	 * (e.g. libkms for the bootup splash), we have to ensure that we
 	 * always use map_and_fenceable for all scanout buffers.
 	 */
-	ret = i915_gem_obj_ggtt_pin(obj, alignment, PIN_MAPPABLE);
+	ret = i915_gem_object_ggtt_pin(obj, view, alignment,
+				       view->type == I915_GGTT_VIEW_NORMAL ?
+				       PIN_MAPPABLE : 0);
 	if (ret)
 		goto err_unpin_display;
 
@@ -4016,9 +3944,11 @@
 }
 
 void
-i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj)
+i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj,
+					 const struct i915_ggtt_view *view)
 {
-	i915_gem_object_ggtt_unpin(obj);
+	i915_gem_object_ggtt_unpin_view(obj, view);
+
 	obj->pin_display = is_pin_display(obj);
 }
 
@@ -4167,12 +4097,12 @@
 	return false;
 }
 
-int
-i915_gem_object_pin_view(struct drm_i915_gem_object *obj,
-			 struct i915_address_space *vm,
-			 uint32_t alignment,
-			 uint64_t flags,
-			 const struct i915_ggtt_view *view)
+static int
+i915_gem_object_do_pin(struct drm_i915_gem_object *obj,
+		       struct i915_address_space *vm,
+		       const struct i915_ggtt_view *ggtt_view,
+		       uint32_t alignment,
+		       uint64_t flags)
 {
 	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
 	struct i915_vma *vma;
@@ -4188,17 +4118,29 @@
 	if (WARN_ON((flags & (PIN_MAPPABLE | PIN_GLOBAL)) == PIN_MAPPABLE))
 		return -EINVAL;
 
-	vma = i915_gem_obj_to_vma_view(obj, vm, view);
+	if (WARN_ON(i915_is_ggtt(vm) != !!ggtt_view))
+		return -EINVAL;
+
+	vma = ggtt_view ? i915_gem_obj_to_ggtt_view(obj, ggtt_view) :
+			  i915_gem_obj_to_vma(obj, vm);
+
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
 	if (vma) {
 		if (WARN_ON(vma->pin_count == DRM_I915_GEM_OBJECT_MAX_PIN_COUNT))
 			return -EBUSY;
 
 		if (i915_vma_misplaced(vma, alignment, flags)) {
+			unsigned long offset;
+			offset = ggtt_view ? i915_gem_obj_ggtt_offset_view(obj, ggtt_view) :
+					     i915_gem_obj_offset(obj, vm);
 			WARN(vma->pin_count,
-			     "bo is already pinned with incorrect alignment:"
+			     "bo is already pinned in %s with incorrect alignment:"
 			     " offset=%lx, req.alignment=%x, req.map_and_fenceable=%d,"
 			     " obj->map_and_fenceable=%d\n",
-			     i915_gem_obj_offset_view(obj, vm, view->type),
+			     ggtt_view ? "ggtt" : "ppgtt",
+			     offset,
 			     alignment,
 			     !!(flags & PIN_MAPPABLE),
 			     obj->map_and_fenceable);
@@ -4212,8 +4154,12 @@
 
 	bound = vma ? vma->bound : 0;
 	if (vma == NULL || !drm_mm_node_allocated(&vma->node)) {
-		vma = i915_gem_object_bind_to_vm(obj, vm, alignment,
-						 flags, view);
+		/* In true PPGTT, bind has possibly changed PDEs, which
+		 * means we must do a context switch before the GPU can
+		 * accurately read some of the VMAs.
+		 */
+		vma = i915_gem_object_bind_to_vm(obj, vm, ggtt_view, alignment,
+						 flags);
 		if (IS_ERR(vma))
 			return PTR_ERR(vma);
 	}
@@ -4254,16 +4200,41 @@
 	return 0;
 }
 
-void
-i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj)
+int
+i915_gem_object_pin(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm,
+		    uint32_t alignment,
+		    uint64_t flags)
 {
-	struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
+	return i915_gem_object_do_pin(obj, vm,
+				      i915_is_ggtt(vm) ? &i915_ggtt_view_normal : NULL,
+				      alignment, flags);
+}
+
+int
+i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
+			 const struct i915_ggtt_view *view,
+			 uint32_t alignment,
+			 uint64_t flags)
+{
+	if (WARN_ONCE(!view, "no view specified"))
+		return -EINVAL;
+
+	return i915_gem_object_do_pin(obj, i915_obj_to_ggtt(obj), view,
+				      alignment, flags | PIN_GLOBAL);
+}
+
+void
+i915_gem_object_ggtt_unpin_view(struct drm_i915_gem_object *obj,
+				const struct i915_ggtt_view *view)
+{
+	struct i915_vma *vma = i915_gem_obj_to_ggtt_view(obj, view);
 
 	BUG_ON(!vma);
-	BUG_ON(vma->pin_count == 0);
-	BUG_ON(!i915_gem_obj_ggtt_bound(obj));
+	WARN_ON(vma->pin_count == 0);
+	WARN_ON(!i915_gem_obj_ggtt_bound_view(obj, view));
 
-	if (--vma->pin_count == 0)
+	if (--vma->pin_count == 0 && view->type == I915_GGTT_VIEW_NORMAL)
 		obj->pin_mappable = false;
 }
 
@@ -4384,7 +4355,7 @@
 		obj->madv = args->madv;
 
 	/* if the object is no longer attached, discard its backing storage */
-	if (i915_gem_object_is_purgeable(obj) && obj->pages == NULL)
+	if (obj->madv == I915_MADV_DONTNEED && obj->pages == NULL)
 		i915_gem_object_truncate(obj);
 
 	args->retained = obj->madv != __I915_MADV_PURGED;
@@ -4559,15 +4530,33 @@
 	intel_runtime_pm_put(dev_priv);
 }
 
-struct i915_vma *i915_gem_obj_to_vma_view(struct drm_i915_gem_object *obj,
-					  struct i915_address_space *vm,
-					  const struct i915_ggtt_view *view)
+struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
+				     struct i915_address_space *vm)
 {
 	struct i915_vma *vma;
-	list_for_each_entry(vma, &obj->vma_list, vma_link)
-		if (vma->vm == vm && vma->ggtt_view.type == view->type)
+	list_for_each_entry(vma, &obj->vma_list, vma_link) {
+		if (i915_is_ggtt(vma->vm) &&
+		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
+			continue;
+		if (vma->vm == vm)
 			return vma;
+	}
+	return NULL;
+}
 
+struct i915_vma *i915_gem_obj_to_ggtt_view(struct drm_i915_gem_object *obj,
+					   const struct i915_ggtt_view *view)
+{
+	struct i915_address_space *ggtt = i915_obj_to_ggtt(obj);
+	struct i915_vma *vma;
+
+	if (WARN_ONCE(!view, "no view specified"))
+		return ERR_PTR(-EINVAL);
+
+	list_for_each_entry(vma, &obj->vma_list, vma_link)
+		if (vma->vm == ggtt &&
+		    i915_ggtt_view_equal(&vma->ggtt_view, view))
+			return vma;
 	return NULL;
 }
 
@@ -5006,13 +4995,7 @@
 
 	dev_priv->mm.interruptible = true;
 
-	dev_priv->mm.shrinker.scan_objects = i915_gem_shrinker_scan;
-	dev_priv->mm.shrinker.count_objects = i915_gem_shrinker_count;
-	dev_priv->mm.shrinker.seeks = DEFAULT_SEEKS;
-	register_shrinker(&dev_priv->mm.shrinker);
-
-	dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
-	register_oom_notifier(&dev_priv->mm.oom_notifier);
+	i915_gem_shrinker_init(dev_priv);
 
 	i915_gem_batch_pool_init(dev, &dev_priv->mm.batch_pool);
 
@@ -5104,81 +5087,10 @@
 	}
 }
 
-static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
-{
-	if (!mutex_is_locked(mutex))
-		return false;
-
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
-	return mutex->owner == task;
-#else
-	/* Since UP may be pre-empted, we cannot assume that we own the lock */
-	return false;
-#endif
-}
-
-static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
-{
-	if (!mutex_trylock(&dev->struct_mutex)) {
-		if (!mutex_is_locked_by(&dev->struct_mutex, current))
-			return false;
-
-		if (to_i915(dev)->mm.shrinker_no_lock_stealing)
-			return false;
-
-		*unlock = false;
-	} else
-		*unlock = true;
-
-	return true;
-}
-
-static int num_vma_bound(struct drm_i915_gem_object *obj)
-{
-	struct i915_vma *vma;
-	int count = 0;
-
-	list_for_each_entry(vma, &obj->vma_list, vma_link)
-		if (drm_mm_node_allocated(&vma->node))
-			count++;
-
-	return count;
-}
-
-static unsigned long
-i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
-{
-	struct drm_i915_private *dev_priv =
-		container_of(shrinker, struct drm_i915_private, mm.shrinker);
-	struct drm_device *dev = dev_priv->dev;
-	struct drm_i915_gem_object *obj;
-	unsigned long count;
-	bool unlock;
-
-	if (!i915_gem_shrinker_lock(dev, &unlock))
-		return 0;
-
-	count = 0;
-	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list)
-		if (obj->pages_pin_count == 0)
-			count += obj->base.size >> PAGE_SHIFT;
-
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if (!i915_gem_obj_is_pinned(obj) &&
-		    obj->pages_pin_count == num_vma_bound(obj))
-			count += obj->base.size >> PAGE_SHIFT;
-	}
-
-	if (unlock)
-		mutex_unlock(&dev->struct_mutex);
-
-	return count;
-}
-
 /* All the new VM stuff */
-unsigned long i915_gem_obj_offset_view(struct drm_i915_gem_object *o,
-				       struct i915_address_space *vm,
-				       enum i915_ggtt_view_type view)
+unsigned long
+i915_gem_obj_offset(struct drm_i915_gem_object *o,
+		    struct i915_address_space *vm)
 {
 	struct drm_i915_private *dev_priv = o->base.dev->dev_private;
 	struct i915_vma *vma;
@@ -5186,24 +5098,59 @@
 	WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base);
 
 	list_for_each_entry(vma, &o->vma_list, vma_link) {
-		if (vma->vm == vm && vma->ggtt_view.type == view)
+		if (i915_is_ggtt(vma->vm) &&
+		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
+			continue;
+		if (vma->vm == vm)
 			return vma->node.start;
-
 	}
+
 	WARN(1, "%s vma for this object not found.\n",
 	     i915_is_ggtt(vm) ? "global" : "ppgtt");
 	return -1;
 }
 
-bool i915_gem_obj_bound_view(struct drm_i915_gem_object *o,
-			     struct i915_address_space *vm,
-			     enum i915_ggtt_view_type view)
+unsigned long
+i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o,
+			      const struct i915_ggtt_view *view)
 {
+	struct i915_address_space *ggtt = i915_obj_to_ggtt(o);
 	struct i915_vma *vma;
 
 	list_for_each_entry(vma, &o->vma_list, vma_link)
-		if (vma->vm == vm &&
-		    vma->ggtt_view.type == view &&
+		if (vma->vm == ggtt &&
+		    i915_ggtt_view_equal(&vma->ggtt_view, view))
+			return vma->node.start;
+
+	WARN(1, "global vma for this object not found.\n");
+	return -1;
+}
+
+bool i915_gem_obj_bound(struct drm_i915_gem_object *o,
+			struct i915_address_space *vm)
+{
+	struct i915_vma *vma;
+
+	list_for_each_entry(vma, &o->vma_list, vma_link) {
+		if (i915_is_ggtt(vma->vm) &&
+		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
+			continue;
+		if (vma->vm == vm && drm_mm_node_allocated(&vma->node))
+			return true;
+	}
+
+	return false;
+}
+
+bool i915_gem_obj_ggtt_bound_view(struct drm_i915_gem_object *o,
+				  const struct i915_ggtt_view *view)
+{
+	struct i915_address_space *ggtt = i915_obj_to_ggtt(o);
+	struct i915_vma *vma;
+
+	list_for_each_entry(vma, &o->vma_list, vma_link)
+		if (vma->vm == ggtt &&
+		    i915_ggtt_view_equal(&vma->ggtt_view, view) &&
 		    drm_mm_node_allocated(&vma->node))
 			return true;
 
@@ -5231,118 +5178,26 @@
 
 	BUG_ON(list_empty(&o->vma_list));
 
-	list_for_each_entry(vma, &o->vma_list, vma_link)
+	list_for_each_entry(vma, &o->vma_list, vma_link) {
+		if (i915_is_ggtt(vma->vm) &&
+		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
+			continue;
 		if (vma->vm == vm)
 			return vma->node.size;
-
+	}
 	return 0;
 }
 
-static unsigned long
-i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
+bool i915_gem_obj_is_pinned(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv =
-		container_of(shrinker, struct drm_i915_private, mm.shrinker);
-	struct drm_device *dev = dev_priv->dev;
-	unsigned long freed;
-	bool unlock;
-
-	if (!i915_gem_shrinker_lock(dev, &unlock))
-		return SHRINK_STOP;
-
-	freed = i915_gem_shrink(dev_priv,
-				sc->nr_to_scan,
-				I915_SHRINK_BOUND |
-				I915_SHRINK_UNBOUND |
-				I915_SHRINK_PURGEABLE);
-	if (freed < sc->nr_to_scan)
-		freed += i915_gem_shrink(dev_priv,
-					 sc->nr_to_scan - freed,
-					 I915_SHRINK_BOUND |
-					 I915_SHRINK_UNBOUND);
-	if (unlock)
-		mutex_unlock(&dev->struct_mutex);
-
-	return freed;
-}
-
-static int
-i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
-{
-	struct drm_i915_private *dev_priv =
-		container_of(nb, struct drm_i915_private, mm.oom_notifier);
-	struct drm_device *dev = dev_priv->dev;
-	struct drm_i915_gem_object *obj;
-	unsigned long timeout = msecs_to_jiffies(5000) + 1;
-	unsigned long pinned, bound, unbound, freed_pages;
-	bool was_interruptible;
-	bool unlock;
-
-	while (!i915_gem_shrinker_lock(dev, &unlock) && --timeout) {
-		schedule_timeout_killable(1);
-		if (fatal_signal_pending(current))
-			return NOTIFY_DONE;
-	}
-	if (timeout == 0) {
-		pr_err("Unable to purge GPU memory due lock contention.\n");
-		return NOTIFY_DONE;
-	}
-
-	was_interruptible = dev_priv->mm.interruptible;
-	dev_priv->mm.interruptible = false;
-
-	freed_pages = i915_gem_shrink_all(dev_priv);
-
-	dev_priv->mm.interruptible = was_interruptible;
-
-	/* Because we may be allocating inside our own driver, we cannot
-	 * assert that there are no objects with pinned pages that are not
-	 * being pointed to by hardware.
-	 */
-	unbound = bound = pinned = 0;
-	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) {
-		if (!obj->base.filp) /* not backed by a freeable object */
-			continue;
-
-		if (obj->pages_pin_count)
-			pinned += obj->base.size;
-		else
-			unbound += obj->base.size;
-	}
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if (!obj->base.filp)
-			continue;
-
-		if (obj->pages_pin_count)
-			pinned += obj->base.size;
-		else
-			bound += obj->base.size;
-	}
-
-	if (unlock)
-		mutex_unlock(&dev->struct_mutex);
-
-	if (freed_pages || unbound || bound)
-		pr_info("Purging GPU memory, %lu bytes freed, %lu bytes still pinned.\n",
-			freed_pages << PAGE_SHIFT, pinned);
-	if (unbound || bound)
-		pr_err("%lu and %lu bytes still available in the "
-		       "bound and unbound GPU page lists.\n",
-		       bound, unbound);
-
-	*(unsigned long *)ptr += freed_pages;
-	return NOTIFY_DONE;
-}
-
-struct i915_vma *i915_gem_obj_to_ggtt(struct drm_i915_gem_object *obj)
-{
-	struct i915_address_space *ggtt = i915_obj_to_ggtt(obj);
 	struct i915_vma *vma;
-
-	list_for_each_entry(vma, &obj->vma_list, vma_link)
-		if (vma->vm == ggtt &&
-		    vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL)
-			return vma;
-
-	return NULL;
+	list_for_each_entry(vma, &obj->vma_list, vma_link) {
+		if (i915_is_ggtt(vma->vm) &&
+		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
+			continue;
+		if (vma->pin_count > 0)
+			return true;
+	}
+	return false;
 }
+
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 70346b0..f3e84c4 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -569,6 +569,66 @@
 	return ret;
 }
 
+static inline bool should_skip_switch(struct intel_engine_cs *ring,
+				      struct intel_context *from,
+				      struct intel_context *to)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+
+	if (to->remap_slice)
+		return false;
+
+	if (to->ppgtt) {
+		if (from == to && !test_bit(ring->id,
+				&to->ppgtt->pd_dirty_rings))
+			return true;
+	} else if (dev_priv->mm.aliasing_ppgtt) {
+		if (from == to && !test_bit(ring->id,
+				&dev_priv->mm.aliasing_ppgtt->pd_dirty_rings))
+			return true;
+	}
+
+	return false;
+}
+
+static bool
+needs_pd_load_pre(struct intel_engine_cs *ring, struct intel_context *to)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+
+	if (!to->ppgtt)
+		return false;
+
+	if (INTEL_INFO(ring->dev)->gen < 8)
+		return true;
+
+	if (ring != &dev_priv->ring[RCS])
+		return true;
+
+	return false;
+}
+
+static bool
+needs_pd_load_post(struct intel_engine_cs *ring, struct intel_context *to,
+		u32 hw_flags)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+
+	if (!to->ppgtt)
+		return false;
+
+	if (!IS_GEN8(ring->dev))
+		return false;
+
+	if (ring != &dev_priv->ring[RCS])
+		return false;
+
+	if (hw_flags & MI_RESTORE_INHIBIT)
+		return true;
+
+	return false;
+}
+
 static int do_switch(struct intel_engine_cs *ring,
 		     struct intel_context *to)
 {
@@ -584,7 +644,7 @@
 		BUG_ON(!i915_gem_obj_is_pinned(from->legacy_hw_ctx.rcs_state));
 	}
 
-	if (from == to && !to->remap_slice)
+	if (should_skip_switch(ring, from, to))
 		return 0;
 
 	/* Trying to pin first makes error handling easier. */
@@ -602,11 +662,18 @@
 	 */
 	from = ring->last_context;
 
-	if (to->ppgtt) {
+	if (needs_pd_load_pre(ring, to)) {
+		/* Older GENs and non render rings still want the load first,
+		 * "PP_DCLV followed by PP_DIR_BASE register through Load
+		 * Register Immediate commands in Ring Buffer before submitting
+		 * a context."*/
 		trace_switch_mm(ring, to);
 		ret = to->ppgtt->switch_mm(to->ppgtt, ring);
 		if (ret)
 			goto unpin_out;
+
+		/* Doing a PD load always reloads the page dirs */
+		clear_bit(ring->id, &to->ppgtt->pd_dirty_rings);
 	}
 
 	if (ring != &dev_priv->ring[RCS]) {
@@ -637,13 +704,41 @@
 			goto unpin_out;
 	}
 
-	if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to))
+	if (!to->legacy_hw_ctx.initialized) {
 		hw_flags |= MI_RESTORE_INHIBIT;
+		/* NB: If we inhibit the restore, the context is not allowed to
+		 * die because future work may end up depending on valid address
+		 * space. This means we must enforce that a page table load
+		 * occur when this occurs. */
+	} else if (to->ppgtt &&
+			test_and_clear_bit(ring->id, &to->ppgtt->pd_dirty_rings))
+		hw_flags |= MI_FORCE_RESTORE;
+
+	/* We should never emit switch_mm more than once */
+	WARN_ON(needs_pd_load_pre(ring, to) &&
+			needs_pd_load_post(ring, to, hw_flags));
 
 	ret = mi_set_context(ring, to, hw_flags);
 	if (ret)
 		goto unpin_out;
 
+	/* GEN8 does *not* require an explicit reload if the PDPs have been
+	 * setup, and we do not wish to move them.
+	 */
+	if (needs_pd_load_post(ring, to, hw_flags)) {
+		trace_switch_mm(ring, to);
+		ret = to->ppgtt->switch_mm(to->ppgtt, ring);
+		/* The hardware context switch is emitted, but we haven't
+		 * actually changed the state - so it's probably safe to bail
+		 * here. Still, let the user know something dangerous has
+		 * happened.
+		 */
+		if (ret) {
+			DRM_ERROR("Failed to change address space on context switch\n");
+			goto unpin_out;
+		}
+	}
+
 	for (i = 0; i < MAX_L3_SLICES; i++) {
 		if (!(to->remap_slice & (1<<i)))
 			continue;
@@ -681,7 +776,7 @@
 		i915_gem_context_unreference(from);
 	}
 
-	uninitialized = !to->legacy_hw_ctx.initialized && from == NULL;
+	uninitialized = !to->legacy_hw_ctx.initialized;
 	to->legacy_hw_ctx.initialized = true;
 
 done:
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index e3a49d9..d09e35e 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -63,6 +63,10 @@
  *
  * This function is used by the object/vma binding code.
  *
+ * Since this function is only used to free up virtual address space it only
+ * ignores pinned vmas, and not object where the backing storage itself is
+ * pinned. Hence obj->pages_pin_count does not protect against eviction.
+ *
  * To clarify: This is for freeing up virtual address space, not for freeing
  * memory in e.g. the shrinker.
  */
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index dc10bc4..a3190e79 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -251,7 +251,6 @@
 {
 	return (HAS_LLC(obj->base.dev) ||
 		obj->base.write_domain == I915_GEM_DOMAIN_CPU ||
-		!obj->map_and_fenceable ||
 		obj->cache_level != I915_CACHE_NONE);
 }
 
@@ -337,6 +336,51 @@
 	return 0;
 }
 
+static void
+clflush_write32(void *addr, uint32_t value)
+{
+	/* This is not a fast path, so KISS. */
+	drm_clflush_virt_range(addr, sizeof(uint32_t));
+	*(uint32_t *)addr = value;
+	drm_clflush_virt_range(addr, sizeof(uint32_t));
+}
+
+static int
+relocate_entry_clflush(struct drm_i915_gem_object *obj,
+		       struct drm_i915_gem_relocation_entry *reloc,
+		       uint64_t target_offset)
+{
+	struct drm_device *dev = obj->base.dev;
+	uint32_t page_offset = offset_in_page(reloc->offset);
+	uint64_t delta = (int)reloc->delta + target_offset;
+	char *vaddr;
+	int ret;
+
+	ret = i915_gem_object_set_to_gtt_domain(obj, true);
+	if (ret)
+		return ret;
+
+	vaddr = kmap_atomic(i915_gem_object_get_page(obj,
+				reloc->offset >> PAGE_SHIFT));
+	clflush_write32(vaddr + page_offset, lower_32_bits(delta));
+
+	if (INTEL_INFO(dev)->gen >= 8) {
+		page_offset = offset_in_page(page_offset + sizeof(uint32_t));
+
+		if (page_offset == 0) {
+			kunmap_atomic(vaddr);
+			vaddr = kmap_atomic(i915_gem_object_get_page(obj,
+			    (reloc->offset + sizeof(uint32_t)) >> PAGE_SHIFT));
+		}
+
+		clflush_write32(vaddr + page_offset, upper_32_bits(delta));
+	}
+
+	kunmap_atomic(vaddr);
+
+	return 0;
+}
+
 static int
 i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 				   struct eb_vmas *eb,
@@ -426,8 +470,14 @@
 
 	if (use_cpu_reloc(obj))
 		ret = relocate_entry_cpu(obj, reloc, target_offset);
-	else
+	else if (obj->map_and_fenceable)
 		ret = relocate_entry_gtt(obj, reloc, target_offset);
+	else if (cpu_has_clflush)
+		ret = relocate_entry_clflush(obj, reloc, target_offset);
+	else {
+		WARN_ONCE(1, "Impossible case in relocation handling\n");
+		ret = -ENODEV;
+	}
 
 	if (ret)
 		return ret;
@@ -525,6 +575,12 @@
 	return ret;
 }
 
+static bool only_mappable_for_reloc(unsigned int flags)
+{
+	return (flags & (EXEC_OBJECT_NEEDS_FENCE | __EXEC_OBJECT_NEEDS_MAP)) ==
+		__EXEC_OBJECT_NEEDS_MAP;
+}
+
 static int
 i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
 				struct intel_engine_cs *ring,
@@ -536,14 +592,21 @@
 	int ret;
 
 	flags = 0;
-	if (entry->flags & __EXEC_OBJECT_NEEDS_MAP)
-		flags |= PIN_GLOBAL | PIN_MAPPABLE;
-	if (entry->flags & EXEC_OBJECT_NEEDS_GTT)
-		flags |= PIN_GLOBAL;
-	if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS)
-		flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS;
+	if (!drm_mm_node_allocated(&vma->node)) {
+		if (entry->flags & __EXEC_OBJECT_NEEDS_MAP)
+			flags |= PIN_GLOBAL | PIN_MAPPABLE;
+		if (entry->flags & EXEC_OBJECT_NEEDS_GTT)
+			flags |= PIN_GLOBAL;
+		if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS)
+			flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS;
+	}
 
 	ret = i915_gem_object_pin(obj, vma->vm, entry->alignment, flags);
+	if ((ret == -ENOSPC  || ret == -E2BIG) &&
+	    only_mappable_for_reloc(entry->flags))
+		ret = i915_gem_object_pin(obj, vma->vm,
+					  entry->alignment,
+					  flags & ~(PIN_GLOBAL | PIN_MAPPABLE));
 	if (ret)
 		return ret;
 
@@ -605,13 +668,14 @@
 	    vma->node.start & (entry->alignment - 1))
 		return true;
 
-	if (entry->flags & __EXEC_OBJECT_NEEDS_MAP && !obj->map_and_fenceable)
-		return true;
-
 	if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS &&
 	    vma->node.start < BATCH_OFFSET_BIAS)
 		return true;
 
+	/* avoid costly ping-pong once a batch bo ended up non-mappable */
+	if (entry->flags & __EXEC_OBJECT_NEEDS_MAP && !obj->map_and_fenceable)
+		return !only_mappable_for_reloc(entry->flags);
+
 	return false;
 }
 
@@ -1187,6 +1251,13 @@
 	if (ret)
 		goto error;
 
+	if (ctx->ppgtt)
+		WARN(ctx->ppgtt->pd_dirty_rings & (1<<ring->id),
+			"%s didn't clear reload\n", ring->name);
+	else if (dev_priv->mm.aliasing_ppgtt)
+		WARN(dev_priv->mm.aliasing_ppgtt->pd_dirty_rings &
+			(1<<ring->id), "%s didn't clear reload\n", ring->name);
+
 	instp_mode = args->flags & I915_EXEC_CONSTANTS_MASK;
 	instp_mask = I915_EXEC_CONSTANTS_MASK;
 	switch (instp_mode) {
@@ -1476,7 +1547,7 @@
 		goto err;
 	}
 
-	if (i915_needs_cmd_parser(ring)) {
+	if (i915_needs_cmd_parser(ring) && args->batch_len) {
 		batch_obj = i915_gem_execbuffer_parse(ring,
 						      &shadow_exec_entry,
 						      eb,
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 2034f7c..0239fbf 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -67,8 +67,9 @@
  * i915_ggtt_view_type and struct i915_ggtt_view.
  *
  * A new flavour of core GEM functions which work with GGTT bound objects were
- * added with the _view suffix. They take the struct i915_ggtt_view parameter
- * encapsulating all metadata required to implement a view.
+ * added with the _ggtt_ infix, and sometimes with _view postfix to avoid
+ * renaming  in large amounts of code. They take the struct i915_ggtt_view
+ * parameter encapsulating all metadata required to implement a view.
  *
  * As a helper for callers which are only interested in the normal view,
  * globally const i915_ggtt_view_normal singleton instance exists. All old core
@@ -92,6 +93,9 @@
  */
 
 const struct i915_ggtt_view i915_ggtt_view_normal;
+const struct i915_ggtt_view i915_ggtt_view_rotated = {
+        .type = I915_GGTT_VIEW_ROTATED
+};
 
 static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv);
 static void chv_setup_private_ppat(struct drm_i915_private *dev_priv);
@@ -147,11 +151,11 @@
 			   u32 flags);
 static void ppgtt_unbind_vma(struct i915_vma *vma);
 
-static inline gen8_gtt_pte_t gen8_pte_encode(dma_addr_t addr,
-					     enum i915_cache_level level,
-					     bool valid)
+static inline gen8_pte_t gen8_pte_encode(dma_addr_t addr,
+					 enum i915_cache_level level,
+					 bool valid)
 {
-	gen8_gtt_pte_t pte = valid ? _PAGE_PRESENT | _PAGE_RW : 0;
+	gen8_pte_t pte = valid ? _PAGE_PRESENT | _PAGE_RW : 0;
 	pte |= addr;
 
 	switch (level) {
@@ -169,11 +173,11 @@
 	return pte;
 }
 
-static inline gen8_ppgtt_pde_t gen8_pde_encode(struct drm_device *dev,
-					     dma_addr_t addr,
-					     enum i915_cache_level level)
+static inline gen8_pde_t gen8_pde_encode(struct drm_device *dev,
+					  dma_addr_t addr,
+					  enum i915_cache_level level)
 {
-	gen8_ppgtt_pde_t pde = _PAGE_PRESENT | _PAGE_RW;
+	gen8_pde_t pde = _PAGE_PRESENT | _PAGE_RW;
 	pde |= addr;
 	if (level != I915_CACHE_NONE)
 		pde |= PPAT_CACHED_PDE_INDEX;
@@ -182,11 +186,11 @@
 	return pde;
 }
 
-static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level,
-				     bool valid, u32 unused)
+static gen6_pte_t snb_pte_encode(dma_addr_t addr,
+				 enum i915_cache_level level,
+				 bool valid, u32 unused)
 {
-	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
+	gen6_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
@@ -204,11 +208,11 @@
 	return pte;
 }
 
-static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level,
-				     bool valid, u32 unused)
+static gen6_pte_t ivb_pte_encode(dma_addr_t addr,
+				 enum i915_cache_level level,
+				 bool valid, u32 unused)
 {
-	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
+	gen6_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
@@ -228,11 +232,11 @@
 	return pte;
 }
 
-static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level,
-				     bool valid, u32 flags)
+static gen6_pte_t byt_pte_encode(dma_addr_t addr,
+				 enum i915_cache_level level,
+				 bool valid, u32 flags)
 {
-	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
+	gen6_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
 
 	if (!(flags & PTE_READ_ONLY))
@@ -244,11 +248,11 @@
 	return pte;
 }
 
-static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
-				     enum i915_cache_level level,
-				     bool valid, u32 unused)
+static gen6_pte_t hsw_pte_encode(dma_addr_t addr,
+				 enum i915_cache_level level,
+				 bool valid, u32 unused)
 {
-	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
+	gen6_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
 
 	if (level != I915_CACHE_NONE)
@@ -257,11 +261,11 @@
 	return pte;
 }
 
-static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
-				      enum i915_cache_level level,
-				      bool valid, u32 unused)
+static gen6_pte_t iris_pte_encode(dma_addr_t addr,
+				  enum i915_cache_level level,
+				  bool valid, u32 unused)
 {
-	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
+	gen6_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
 
 	switch (level) {
@@ -278,29 +282,91 @@
 	return pte;
 }
 
-static void unmap_and_free_pt(struct i915_page_table_entry *pt, struct drm_device *dev)
+#define i915_dma_unmap_single(px, dev) \
+	__i915_dma_unmap_single((px)->daddr, dev)
+
+static inline void __i915_dma_unmap_single(dma_addr_t daddr,
+					struct drm_device *dev)
+{
+	struct device *device = &dev->pdev->dev;
+
+	dma_unmap_page(device, daddr, 4096, PCI_DMA_BIDIRECTIONAL);
+}
+
+/**
+ * i915_dma_map_single() - Create a dma mapping for a page table/dir/etc.
+ * @px:	Page table/dir/etc to get a DMA map for
+ * @dev:	drm device
+ *
+ * Page table allocations are unified across all gens. They always require a
+ * single 4k allocation, as well as a DMA mapping. If we keep the structs
+ * symmetric here, the simple macro covers us for every page table type.
+ *
+ * Return: 0 if success.
+ */
+#define i915_dma_map_single(px, dev) \
+	i915_dma_map_page_single((px)->page, (dev), &(px)->daddr)
+
+static inline int i915_dma_map_page_single(struct page *page,
+					   struct drm_device *dev,
+					   dma_addr_t *daddr)
+{
+	struct device *device = &dev->pdev->dev;
+
+	*daddr = dma_map_page(device, page, 0, 4096, PCI_DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(device, *daddr))
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void unmap_and_free_pt(struct i915_page_table_entry *pt,
+			       struct drm_device *dev)
 {
 	if (WARN_ON(!pt->page))
 		return;
+
+	i915_dma_unmap_single(pt, dev);
 	__free_page(pt->page);
+	kfree(pt->used_ptes);
 	kfree(pt);
 }
 
 static struct i915_page_table_entry *alloc_pt_single(struct drm_device *dev)
 {
 	struct i915_page_table_entry *pt;
+	const size_t count = INTEL_INFO(dev)->gen >= 8 ?
+		GEN8_PTES : GEN6_PTES;
+	int ret = -ENOMEM;
 
 	pt = kzalloc(sizeof(*pt), GFP_KERNEL);
 	if (!pt)
 		return ERR_PTR(-ENOMEM);
 
-	pt->page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	if (!pt->page) {
-		kfree(pt);
-		return ERR_PTR(-ENOMEM);
-	}
+	pt->used_ptes = kcalloc(BITS_TO_LONGS(count), sizeof(*pt->used_ptes),
+				GFP_KERNEL);
+
+	if (!pt->used_ptes)
+		goto fail_bitmap;
+
+	pt->page = alloc_page(GFP_KERNEL);
+	if (!pt->page)
+		goto fail_page;
+
+	ret = i915_dma_map_single(pt, dev);
+	if (ret)
+		goto fail_dma;
 
 	return pt;
+
+fail_dma:
+	__free_page(pt->page);
+fail_page:
+	kfree(pt->used_ptes);
+fail_bitmap:
+	kfree(pt);
+
+	return ERR_PTR(ret);
 }
 
 /**
@@ -318,12 +384,12 @@
  * Return: 0 if allocation succeeded.
  */
 static int alloc_pt_range(struct i915_page_directory_entry *pd, uint16_t pde, size_t count,
-		  struct drm_device *dev)
+			  struct drm_device *dev)
 {
 	int i, ret;
 
 	/* 512 is the max page tables per page_directory on any platform. */
-	if (WARN_ON(pde + count > GEN6_PPGTT_PD_ENTRIES))
+	if (WARN_ON(pde + count > I915_PDES))
 		return -EINVAL;
 
 	for (i = pde; i < pde + count; i++) {
@@ -401,7 +467,7 @@
 	int i, ret;
 
 	/* bit of a hack to find the actual last used pd */
-	int used_pd = ppgtt->num_pd_entries / GEN8_PDES_PER_PAGE;
+	int used_pd = ppgtt->num_pd_entries / I915_PDES;
 
 	for (i = used_pd - 1; i >= 0; i--) {
 		dma_addr_t addr = ppgtt->pdp.page_directory[i]->daddr;
@@ -420,7 +486,7 @@
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
-	gen8_gtt_pte_t *pt_vaddr, scratch_pte;
+	gen8_pte_t *pt_vaddr, scratch_pte;
 	unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
 	unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
 	unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK;
@@ -451,8 +517,8 @@
 		page_table = pt->page;
 
 		last_pte = pte + num_entries;
-		if (last_pte > GEN8_PTES_PER_PAGE)
-			last_pte = GEN8_PTES_PER_PAGE;
+		if (last_pte > GEN8_PTES)
+			last_pte = GEN8_PTES;
 
 		pt_vaddr = kmap_atomic(page_table);
 
@@ -466,7 +532,7 @@
 		kunmap_atomic(pt_vaddr);
 
 		pte = 0;
-		if (++pde == GEN8_PDES_PER_PAGE) {
+		if (++pde == I915_PDES) {
 			pdpe++;
 			pde = 0;
 		}
@@ -480,7 +546,7 @@
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
-	gen8_gtt_pte_t *pt_vaddr;
+	gen8_pte_t *pt_vaddr;
 	unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
 	unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
 	unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK;
@@ -503,12 +569,12 @@
 		pt_vaddr[pte] =
 			gen8_pte_encode(sg_page_iter_dma_address(&sg_iter),
 					cache_level, true);
-		if (++pte == GEN8_PTES_PER_PAGE) {
+		if (++pte == GEN8_PTES) {
 			if (!HAS_LLC(ppgtt->base.dev))
 				drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
 			kunmap_atomic(pt_vaddr);
 			pt_vaddr = NULL;
-			if (++pde == GEN8_PDES_PER_PAGE) {
+			if (++pde == I915_PDES) {
 				pdpe++;
 				pde = 0;
 			}
@@ -529,7 +595,7 @@
 	if (!pd->page)
 		return;
 
-	for (i = 0; i < GEN8_PDES_PER_PAGE; i++) {
+	for (i = 0; i < I915_PDES; i++) {
 		if (WARN_ON(!pd->page_table[i]))
 			continue;
 
@@ -565,7 +631,7 @@
 		pci_unmap_page(hwdev, ppgtt->pdp.page_directory[i]->daddr, PAGE_SIZE,
 			       PCI_DMA_BIDIRECTIONAL);
 
-		for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
+		for (j = 0; j < I915_PDES; j++) {
 			struct i915_page_directory_entry *pd = ppgtt->pdp.page_directory[i];
 			struct i915_page_table_entry *pt;
 			dma_addr_t addr;
@@ -598,7 +664,7 @@
 
 	for (i = 0; i < ppgtt->num_pd_pages; i++) {
 		ret = alloc_pt_range(ppgtt->pdp.page_directory[i],
-				     0, GEN8_PDES_PER_PAGE, ppgtt->base.dev);
+				     0, I915_PDES, ppgtt->base.dev);
 		if (ret)
 			goto unwind_out;
 	}
@@ -648,7 +714,7 @@
 	if (ret)
 		goto err_out;
 
-	ppgtt->num_pd_entries = max_pdp * GEN8_PDES_PER_PAGE;
+	ppgtt->num_pd_entries = max_pdp * I915_PDES;
 
 	return 0;
 
@@ -697,7 +763,7 @@
 	return 0;
 }
 
-/**
+/*
  * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
  * with a net effect resembling a 2-level page table in normal x86 terms. Each
  * PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
@@ -710,7 +776,7 @@
 static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
 {
 	const int max_pdp = DIV_ROUND_UP(size, 1 << 30);
-	const int min_pt_pages = GEN8_PDES_PER_PAGE * max_pdp;
+	const int min_pt_pages = I915_PDES * max_pdp;
 	int i, j, ret;
 
 	if (size % (1<<30))
@@ -733,7 +799,7 @@
 		if (ret)
 			goto bail;
 
-		for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
+		for (j = 0; j < I915_PDES; j++) {
 			ret = gen8_ppgtt_setup_page_tables(ppgtt, i, j);
 			if (ret)
 				goto bail;
@@ -750,9 +816,9 @@
 	 */
 	for (i = 0; i < GEN8_LEGACY_PDPES; i++) {
 		struct i915_page_directory_entry *pd = ppgtt->pdp.page_directory[i];
-		gen8_ppgtt_pde_t *pd_vaddr;
+		gen8_pde_t *pd_vaddr;
 		pd_vaddr = kmap_atomic(ppgtt->pdp.page_directory[i]->page);
-		for (j = 0; j < GEN8_PDES_PER_PAGE; j++) {
+		for (j = 0; j < I915_PDES; j++) {
 			struct i915_page_table_entry *pt = pd->page_table[j];
 			dma_addr_t addr = pt->daddr;
 			pd_vaddr[j] = gen8_pde_encode(ppgtt->base.dev, addr,
@@ -770,11 +836,11 @@
 	ppgtt->base.start = 0;
 
 	/* This is the area that we advertise as usable for the caller */
-	ppgtt->base.total = max_pdp * GEN8_PDES_PER_PAGE * GEN8_PTES_PER_PAGE * PAGE_SIZE;
+	ppgtt->base.total = max_pdp * I915_PDES * GEN8_PTES * PAGE_SIZE;
 
 	/* Set all ptes to a valid scratch page. Also above requested space */
 	ppgtt->base.clear_range(&ppgtt->base, 0,
-				ppgtt->num_pd_pages * GEN8_PTES_PER_PAGE * PAGE_SIZE,
+				ppgtt->num_pd_pages * GEN8_PTES * PAGE_SIZE,
 				true);
 
 	DRM_DEBUG_DRIVER("Allocated %d pages for page directories (%d wasted)\n",
@@ -794,22 +860,22 @@
 {
 	struct drm_i915_private *dev_priv = ppgtt->base.dev->dev_private;
 	struct i915_address_space *vm = &ppgtt->base;
-	gen6_gtt_pte_t __iomem *pd_addr;
-	gen6_gtt_pte_t scratch_pte;
+	gen6_pte_t __iomem *pd_addr;
+	gen6_pte_t scratch_pte;
 	uint32_t pd_entry;
 	int pte, pde;
 
 	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true, 0);
 
-	pd_addr = (gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm +
-		ppgtt->pd.pd_offset / sizeof(gen6_gtt_pte_t);
+	pd_addr = (gen6_pte_t __iomem *)dev_priv->gtt.gsm +
+		ppgtt->pd.pd_offset / sizeof(gen6_pte_t);
 
 	seq_printf(m, "  VM %p (pd_offset %x-%x):\n", vm,
 		   ppgtt->pd.pd_offset,
 		   ppgtt->pd.pd_offset + ppgtt->num_pd_entries);
 	for (pde = 0; pde < ppgtt->num_pd_entries; pde++) {
 		u32 expected;
-		gen6_gtt_pte_t *pt_vaddr;
+		gen6_pte_t *pt_vaddr;
 		dma_addr_t pt_addr = ppgtt->pd.page_table[pde]->daddr;
 		pd_entry = readl(pd_addr + pde);
 		expected = (GEN6_PDE_ADDR_ENCODE(pt_addr) | GEN6_PDE_VALID);
@@ -822,9 +888,9 @@
 		seq_printf(m, "\tPDE: %x\n", pd_entry);
 
 		pt_vaddr = kmap_atomic(ppgtt->pd.page_table[pde]->page);
-		for (pte = 0; pte < I915_PPGTT_PT_ENTRIES; pte+=4) {
+		for (pte = 0; pte < GEN6_PTES; pte+=4) {
 			unsigned long va =
-				(pde * PAGE_SIZE * I915_PPGTT_PT_ENTRIES) +
+				(pde * PAGE_SIZE * GEN6_PTES) +
 				(pte * PAGE_SIZE);
 			int i;
 			bool found = false;
@@ -847,26 +913,36 @@
 	}
 }
 
-static void gen6_write_pdes(struct i915_hw_ppgtt *ppgtt)
+/* Write pde (index) from the page directory @pd to the page table @pt */
+static void gen6_write_pde(struct i915_page_directory_entry *pd,
+			    const int pde, struct i915_page_table_entry *pt)
 {
-	struct drm_i915_private *dev_priv = ppgtt->base.dev->dev_private;
-	gen6_gtt_pte_t __iomem *pd_addr;
-	uint32_t pd_entry;
-	int i;
+	/* Caller needs to make sure the write completes if necessary */
+	struct i915_hw_ppgtt *ppgtt =
+		container_of(pd, struct i915_hw_ppgtt, pd);
+	u32 pd_entry;
 
-	WARN_ON(ppgtt->pd.pd_offset & 0x3f);
-	pd_addr = (gen6_gtt_pte_t __iomem*)dev_priv->gtt.gsm +
-		ppgtt->pd.pd_offset / sizeof(gen6_gtt_pte_t);
-	for (i = 0; i < ppgtt->num_pd_entries; i++) {
-		dma_addr_t pt_addr;
+	pd_entry = GEN6_PDE_ADDR_ENCODE(pt->daddr);
+	pd_entry |= GEN6_PDE_VALID;
 
-		pt_addr = ppgtt->pd.page_table[i]->daddr;
-		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
-		pd_entry |= GEN6_PDE_VALID;
+	writel(pd_entry, ppgtt->pd_addr + pde);
+}
 
-		writel(pd_entry, pd_addr + i);
-	}
-	readl(pd_addr);
+/* Write all the page tables found in the ppgtt structure to incrementing page
+ * directories. */
+static void gen6_write_page_range(struct drm_i915_private *dev_priv,
+				  struct i915_page_directory_entry *pd,
+				  uint32_t start, uint32_t length)
+{
+	struct i915_page_table_entry *pt;
+	uint32_t pde, temp;
+
+	gen6_for_each_pde(pt, pd, start, length, temp, pde)
+		gen6_write_pde(pd, pde, pt);
+
+	/* Make sure write is complete before other code can use this page
+	 * table. Also require for WC mapped PTEs */
+	readl(dev_priv->gtt.gsm);
 }
 
 static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt)
@@ -1022,19 +1098,19 @@
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
-	gen6_gtt_pte_t *pt_vaddr, scratch_pte;
+	gen6_pte_t *pt_vaddr, scratch_pte;
 	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned num_entries = length >> PAGE_SHIFT;
-	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
-	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
+	unsigned act_pt = first_entry / GEN6_PTES;
+	unsigned first_pte = first_entry % GEN6_PTES;
 	unsigned last_pte, i;
 
 	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true, 0);
 
 	while (num_entries) {
 		last_pte = first_pte + num_entries;
-		if (last_pte > I915_PPGTT_PT_ENTRIES)
-			last_pte = I915_PPGTT_PT_ENTRIES;
+		if (last_pte > GEN6_PTES)
+			last_pte = GEN6_PTES;
 
 		pt_vaddr = kmap_atomic(ppgtt->pd.page_table[act_pt]->page);
 
@@ -1056,10 +1132,10 @@
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
-	gen6_gtt_pte_t *pt_vaddr;
+	gen6_pte_t *pt_vaddr;
 	unsigned first_entry = start >> PAGE_SHIFT;
-	unsigned act_pt = first_entry / I915_PPGTT_PT_ENTRIES;
-	unsigned act_pte = first_entry % I915_PPGTT_PT_ENTRIES;
+	unsigned act_pt = first_entry / GEN6_PTES;
+	unsigned act_pte = first_entry % GEN6_PTES;
 	struct sg_page_iter sg_iter;
 
 	pt_vaddr = NULL;
@@ -1071,7 +1147,7 @@
 			vm->pte_encode(sg_page_iter_dma_address(&sg_iter),
 				       cache_level, true, flags);
 
-		if (++act_pte == I915_PPGTT_PT_ENTRIES) {
+		if (++act_pte == GEN6_PTES) {
 			kunmap_atomic(pt_vaddr);
 			pt_vaddr = NULL;
 			act_pt++;
@@ -1082,23 +1158,133 @@
 		kunmap_atomic(pt_vaddr);
 }
 
-static void gen6_ppgtt_unmap_pages(struct i915_hw_ppgtt *ppgtt)
+/* PDE TLBs are a pain invalidate pre GEN8. It requires a context reload. If we
+ * are switching between contexts with the same LRCA, we also must do a force
+ * restore.
+ */
+static inline void mark_tlbs_dirty(struct i915_hw_ppgtt *ppgtt)
 {
+	/* If current vm != vm, */
+	ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->base.dev)->ring_mask;
+}
+
+static void gen6_initialize_pt(struct i915_address_space *vm,
+		struct i915_page_table_entry *pt)
+{
+	gen6_pte_t *pt_vaddr, scratch_pte;
 	int i;
 
-	for (i = 0; i < ppgtt->num_pd_entries; i++)
-		pci_unmap_page(ppgtt->base.dev->pdev,
-			       ppgtt->pd.page_table[i]->daddr,
-			       4096, PCI_DMA_BIDIRECTIONAL);
+	WARN_ON(vm->scratch.addr == 0);
+
+	scratch_pte = vm->pte_encode(vm->scratch.addr,
+			I915_CACHE_LLC, true, 0);
+
+	pt_vaddr = kmap_atomic(pt->page);
+
+	for (i = 0; i < GEN6_PTES; i++)
+		pt_vaddr[i] = scratch_pte;
+
+	kunmap_atomic(pt_vaddr);
+}
+
+static int gen6_alloc_va_range(struct i915_address_space *vm,
+			       uint64_t start, uint64_t length)
+{
+	DECLARE_BITMAP(new_page_tables, I915_PDES);
+	struct drm_device *dev = vm->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_hw_ppgtt *ppgtt =
+				container_of(vm, struct i915_hw_ppgtt, base);
+	struct i915_page_table_entry *pt;
+	const uint32_t start_save = start, length_save = length;
+	uint32_t pde, temp;
+	int ret;
+
+	WARN_ON(upper_32_bits(start));
+
+	bitmap_zero(new_page_tables, I915_PDES);
+
+	/* The allocation is done in two stages so that we can bail out with
+	 * minimal amount of pain. The first stage finds new page tables that
+	 * need allocation. The second stage marks use ptes within the page
+	 * tables.
+	 */
+	gen6_for_each_pde(pt, &ppgtt->pd, start, length, temp, pde) {
+		if (pt != ppgtt->scratch_pt) {
+			WARN_ON(bitmap_empty(pt->used_ptes, GEN6_PTES));
+			continue;
+		}
+
+		/* We've already allocated a page table */
+		WARN_ON(!bitmap_empty(pt->used_ptes, GEN6_PTES));
+
+		pt = alloc_pt_single(dev);
+		if (IS_ERR(pt)) {
+			ret = PTR_ERR(pt);
+			goto unwind_out;
+		}
+
+		gen6_initialize_pt(vm, pt);
+
+		ppgtt->pd.page_table[pde] = pt;
+		set_bit(pde, new_page_tables);
+		trace_i915_page_table_entry_alloc(vm, pde, start, GEN6_PDE_SHIFT);
+	}
+
+	start = start_save;
+	length = length_save;
+
+	gen6_for_each_pde(pt, &ppgtt->pd, start, length, temp, pde) {
+		DECLARE_BITMAP(tmp_bitmap, GEN6_PTES);
+
+		bitmap_zero(tmp_bitmap, GEN6_PTES);
+		bitmap_set(tmp_bitmap, gen6_pte_index(start),
+			   gen6_pte_count(start, length));
+
+		if (test_and_clear_bit(pde, new_page_tables))
+			gen6_write_pde(&ppgtt->pd, pde, pt);
+
+		trace_i915_page_table_entry_map(vm, pde, pt,
+					 gen6_pte_index(start),
+					 gen6_pte_count(start, length),
+					 GEN6_PTES);
+		bitmap_or(pt->used_ptes, tmp_bitmap, pt->used_ptes,
+				GEN6_PTES);
+	}
+
+	WARN_ON(!bitmap_empty(new_page_tables, I915_PDES));
+
+	/* Make sure write is complete before other code can use this page
+	 * table. Also require for WC mapped PTEs */
+	readl(dev_priv->gtt.gsm);
+
+	mark_tlbs_dirty(ppgtt);
+	return 0;
+
+unwind_out:
+	for_each_set_bit(pde, new_page_tables, I915_PDES) {
+		struct i915_page_table_entry *pt = ppgtt->pd.page_table[pde];
+
+		ppgtt->pd.page_table[pde] = ppgtt->scratch_pt;
+		unmap_and_free_pt(pt, vm->dev);
+	}
+
+	mark_tlbs_dirty(ppgtt);
+	return ret;
 }
 
 static void gen6_ppgtt_free(struct i915_hw_ppgtt *ppgtt)
 {
 	int i;
 
-	for (i = 0; i < ppgtt->num_pd_entries; i++)
-		unmap_and_free_pt(ppgtt->pd.page_table[i], ppgtt->base.dev);
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		struct i915_page_table_entry *pt = ppgtt->pd.page_table[i];
 
+		if (pt != ppgtt->scratch_pt)
+			unmap_and_free_pt(ppgtt->pd.page_table[i], ppgtt->base.dev);
+	}
+
+	unmap_and_free_pt(ppgtt->scratch_pt, ppgtt->base.dev);
 	unmap_and_free_pd(&ppgtt->pd);
 }
 
@@ -1109,7 +1295,6 @@
 
 	drm_mm_remove_node(&ppgtt->node);
 
-	gen6_ppgtt_unmap_pages(ppgtt);
 	gen6_ppgtt_free(ppgtt);
 }
 
@@ -1125,6 +1310,12 @@
 	 * size. We allocate at the top of the GTT to avoid fragmentation.
 	 */
 	BUG_ON(!drm_mm_initialized(&dev_priv->gtt.base.mm));
+	ppgtt->scratch_pt = alloc_pt_single(ppgtt->base.dev);
+	if (IS_ERR(ppgtt->scratch_pt))
+		return PTR_ERR(ppgtt->scratch_pt);
+
+	gen6_initialize_pt(&ppgtt->base, ppgtt->scratch_pt);
+
 alloc:
 	ret = drm_mm_insert_node_in_range_generic(&dev_priv->gtt.base.mm,
 						  &ppgtt->node, GEN6_PD_SIZE,
@@ -1138,66 +1329,43 @@
 					       0, dev_priv->gtt.base.total,
 					       0);
 		if (ret)
-			return ret;
+			goto err_out;
 
 		retried = true;
 		goto alloc;
 	}
 
 	if (ret)
-		return ret;
+		goto err_out;
+
 
 	if (ppgtt->node.start < dev_priv->gtt.mappable_end)
 		DRM_DEBUG("Forced to use aperture for PDEs\n");
 
-	ppgtt->num_pd_entries = GEN6_PPGTT_PD_ENTRIES;
+	ppgtt->num_pd_entries = I915_PDES;
 	return 0;
+
+err_out:
+	unmap_and_free_pt(ppgtt->scratch_pt, ppgtt->base.dev);
+	return ret;
 }
 
 static int gen6_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt)
 {
-	int ret;
-
-	ret = gen6_ppgtt_allocate_page_directories(ppgtt);
-	if (ret)
-		return ret;
-
-	ret = alloc_pt_range(&ppgtt->pd, 0, ppgtt->num_pd_entries,
-			ppgtt->base.dev);
-
-	if (ret) {
-		drm_mm_remove_node(&ppgtt->node);
-		return ret;
-	}
-
-	return 0;
+	return gen6_ppgtt_allocate_page_directories(ppgtt);
 }
 
-static int gen6_ppgtt_setup_page_tables(struct i915_hw_ppgtt *ppgtt)
+static void gen6_scratch_va_range(struct i915_hw_ppgtt *ppgtt,
+				  uint64_t start, uint64_t length)
 {
-	struct drm_device *dev = ppgtt->base.dev;
-	int i;
+	struct i915_page_table_entry *unused;
+	uint32_t pde, temp;
 
-	for (i = 0; i < ppgtt->num_pd_entries; i++) {
-		struct page *page;
-		dma_addr_t pt_addr;
-
-		page = ppgtt->pd.page_table[i]->page;
-		pt_addr = pci_map_page(dev->pdev, page, 0, 4096,
-				       PCI_DMA_BIDIRECTIONAL);
-
-		if (pci_dma_mapping_error(dev->pdev, pt_addr)) {
-			gen6_ppgtt_unmap_pages(ppgtt);
-			return -EIO;
-		}
-
-		ppgtt->pd.page_table[i]->daddr = pt_addr;
-	}
-
-	return 0;
+	gen6_for_each_pde(unused, &ppgtt->pd, start, length, temp, pde)
+		ppgtt->pd.page_table[pde] = ppgtt->scratch_pt;
 }
 
-static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
+static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt, bool aliasing)
 {
 	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1220,36 +1388,50 @@
 	if (ret)
 		return ret;
 
-	ret = gen6_ppgtt_setup_page_tables(ppgtt);
-	if (ret) {
-		gen6_ppgtt_free(ppgtt);
-		return ret;
+	if (aliasing) {
+		/* preallocate all pts */
+		ret = alloc_pt_range(&ppgtt->pd, 0, ppgtt->num_pd_entries,
+				ppgtt->base.dev);
+
+		if (ret) {
+			gen6_ppgtt_cleanup(&ppgtt->base);
+			return ret;
+		}
 	}
 
+	ppgtt->base.allocate_va_range = gen6_alloc_va_range;
 	ppgtt->base.clear_range = gen6_ppgtt_clear_range;
 	ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
 	ppgtt->base.cleanup = gen6_ppgtt_cleanup;
 	ppgtt->base.start = 0;
-	ppgtt->base.total = ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES * PAGE_SIZE;
+	ppgtt->base.total = ppgtt->num_pd_entries * GEN6_PTES * PAGE_SIZE;
 	ppgtt->debug_dump = gen6_dump_ppgtt;
 
 	ppgtt->pd.pd_offset =
-		ppgtt->node.start / PAGE_SIZE * sizeof(gen6_gtt_pte_t);
+		ppgtt->node.start / PAGE_SIZE * sizeof(gen6_pte_t);
 
-	ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);
+	ppgtt->pd_addr = (gen6_pte_t __iomem *)dev_priv->gtt.gsm +
+		ppgtt->pd.pd_offset / sizeof(gen6_pte_t);
+
+	if (aliasing)
+		ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true);
+	else
+		gen6_scratch_va_range(ppgtt, 0, ppgtt->base.total);
+
+	gen6_write_page_range(dev_priv, &ppgtt->pd, 0, ppgtt->base.total);
 
 	DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
 			 ppgtt->node.size >> 20,
 			 ppgtt->node.start / PAGE_SIZE);
 
-	gen6_write_pdes(ppgtt);
 	DRM_DEBUG("Adding PPGTT at offset %x\n",
 		  ppgtt->pd.pd_offset << 10);
 
 	return 0;
 }
 
-static int __hw_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
+static int __hw_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt,
+		bool aliasing)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -1257,7 +1439,7 @@
 	ppgtt->base.scratch = dev_priv->gtt.base.scratch;
 
 	if (INTEL_INFO(dev)->gen < 8)
-		return gen6_ppgtt_init(ppgtt);
+		return gen6_ppgtt_init(ppgtt, aliasing);
 	else
 		return gen8_ppgtt_init(ppgtt, dev_priv->gtt.base.total);
 }
@@ -1266,7 +1448,7 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret = 0;
 
-	ret = __hw_ppgtt_init(dev, ppgtt);
+	ret = __hw_ppgtt_init(dev, ppgtt, false);
 	if (ret == 0) {
 		kref_init(&ppgtt->ref);
 		drm_mm_init(&ppgtt->base.mm, ppgtt->base.start,
@@ -1513,15 +1695,20 @@
 		return;
 	}
 
-	list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
-		/* TODO: Perhaps it shouldn't be gen6 specific */
-		if (i915_is_ggtt(vm)) {
-			if (dev_priv->mm.aliasing_ppgtt)
-				gen6_write_pdes(dev_priv->mm.aliasing_ppgtt);
-			continue;
-		}
+	if (USES_PPGTT(dev)) {
+		list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
+			/* TODO: Perhaps it shouldn't be gen6 specific */
 
-		gen6_write_pdes(container_of(vm, struct i915_hw_ppgtt, base));
+			struct i915_hw_ppgtt *ppgtt =
+					container_of(vm, struct i915_hw_ppgtt,
+						     base);
+
+			if (i915_is_ggtt(vm))
+				ppgtt = dev_priv->mm.aliasing_ppgtt;
+
+			gen6_write_page_range(dev_priv, &ppgtt->pd,
+					      0, ppgtt->base.total);
+		}
 	}
 
 	i915_ggtt_flush(dev_priv);
@@ -1540,7 +1727,7 @@
 	return 0;
 }
 
-static inline void gen8_set_pte(void __iomem *addr, gen8_gtt_pte_t pte)
+static inline void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
 {
 #ifdef writeq
 	writeq(pte, addr);
@@ -1557,8 +1744,8 @@
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	unsigned first_entry = start >> PAGE_SHIFT;
-	gen8_gtt_pte_t __iomem *gtt_entries =
-		(gen8_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
+	gen8_pte_t __iomem *gtt_entries =
+		(gen8_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
 	int i = 0;
 	struct sg_page_iter sg_iter;
 	dma_addr_t addr = 0; /* shut up gcc */
@@ -1603,8 +1790,8 @@
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	unsigned first_entry = start >> PAGE_SHIFT;
-	gen6_gtt_pte_t __iomem *gtt_entries =
-		(gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
+	gen6_pte_t __iomem *gtt_entries =
+		(gen6_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
 	int i = 0;
 	struct sg_page_iter sg_iter;
 	dma_addr_t addr = 0;
@@ -1642,8 +1829,8 @@
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned num_entries = length >> PAGE_SHIFT;
-	gen8_gtt_pte_t scratch_pte, __iomem *gtt_base =
-		(gen8_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
+	gen8_pte_t scratch_pte, __iomem *gtt_base =
+		(gen8_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
 	const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
 	int i;
 
@@ -1668,8 +1855,8 @@
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned num_entries = length >> PAGE_SHIFT;
-	gen6_gtt_pte_t scratch_pte, __iomem *gtt_base =
-		(gen6_gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
+	gen6_pte_t scratch_pte, __iomem *gtt_base =
+		(gen6_pte_t __iomem *) dev_priv->gtt.gsm + first_entry;
 	const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry;
 	int i;
 
@@ -1726,11 +1913,15 @@
 	struct drm_device *dev = vma->vm->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj = vma->obj;
+	struct sg_table *pages = obj->pages;
 
 	/* Currently applicable only to VLV */
 	if (obj->gt_ro)
 		flags |= PTE_READ_ONLY;
 
+	if (i915_is_ggtt(vma->vm))
+		pages = vma->ggtt_view.pages;
+
 	/* If there is no aliasing PPGTT, or the caller needs a global mapping,
 	 * or we have a global mapping already but the cacheability flags have
 	 * changed, set the global PTEs.
@@ -1745,7 +1936,7 @@
 	if (!dev_priv->mm.aliasing_ppgtt || flags & GLOBAL_BIND) {
 		if (!(vma->bound & GLOBAL_BIND) ||
 		    (cache_level != obj->cache_level)) {
-			vma->vm->insert_entries(vma->vm, vma->ggtt_view.pages,
+			vma->vm->insert_entries(vma->vm, pages,
 						vma->node.start,
 						cache_level, flags);
 			vma->bound |= GLOBAL_BIND;
@@ -1756,8 +1947,7 @@
 	    (!(vma->bound & LOCAL_BIND) ||
 	     (cache_level != obj->cache_level))) {
 		struct i915_hw_ppgtt *appgtt = dev_priv->mm.aliasing_ppgtt;
-		appgtt->base.insert_entries(&appgtt->base,
-					    vma->ggtt_view.pages,
+		appgtt->base.insert_entries(&appgtt->base, pages,
 					    vma->node.start,
 					    cache_level, flags);
 		vma->bound |= LOCAL_BIND;
@@ -1893,9 +2083,11 @@
 		if (!ppgtt)
 			return -ENOMEM;
 
-		ret = __hw_ppgtt_init(dev, ppgtt);
-		if (ret != 0)
+		ret = __hw_ppgtt_init(dev, ppgtt, true);
+		if (ret) {
+			kfree(ppgtt);
 			return ret;
+		}
 
 		dev_priv->mm.aliasing_ppgtt = ppgtt;
 	}
@@ -2181,7 +2373,7 @@
 		gtt_size = gen8_get_total_gtt_size(snb_gmch_ctl);
 	}
 
-	*gtt_total = (gtt_size / sizeof(gen8_gtt_pte_t)) << PAGE_SHIFT;
+	*gtt_total = (gtt_size / sizeof(gen8_pte_t)) << PAGE_SHIFT;
 
 	if (IS_CHERRYVIEW(dev))
 		chv_setup_private_ppat(dev_priv);
@@ -2226,7 +2418,7 @@
 	*stolen = gen6_get_stolen_size(snb_gmch_ctl);
 
 	gtt_size = gen6_get_total_gtt_size(snb_gmch_ctl);
-	*gtt_total = (gtt_size / sizeof(gen6_gtt_pte_t)) << PAGE_SHIFT;
+	*gtt_total = (gtt_size / sizeof(gen6_pte_t)) << PAGE_SHIFT;
 
 	ret = ggtt_probe_common(dev, gtt_size);
 
@@ -2331,11 +2523,16 @@
 	return 0;
 }
 
-static struct i915_vma *__i915_gem_vma_create(struct drm_i915_gem_object *obj,
-					      struct i915_address_space *vm,
-					      const struct i915_ggtt_view *view)
+static struct i915_vma *
+__i915_gem_vma_create(struct drm_i915_gem_object *obj,
+		      struct i915_address_space *vm,
+		      const struct i915_ggtt_view *ggtt_view)
 {
-	struct i915_vma *vma = kzalloc(sizeof(*vma), GFP_KERNEL);
+	struct i915_vma *vma;
+
+	if (WARN_ON(i915_is_ggtt(vm) != !!ggtt_view))
+		return ERR_PTR(-EINVAL);
+	vma = kzalloc(sizeof(*vma), GFP_KERNEL);
 	if (vma == NULL)
 		return ERR_PTR(-ENOMEM);
 
@@ -2344,10 +2541,11 @@
 	INIT_LIST_HEAD(&vma->exec_list);
 	vma->vm = vm;
 	vma->obj = obj;
-	vma->ggtt_view = *view;
 
 	if (INTEL_INFO(vm->dev)->gen >= 6) {
 		if (i915_is_ggtt(vm)) {
+			vma->ggtt_view = *ggtt_view;
+
 			vma->unbind_vma = ggtt_unbind_vma;
 			vma->bind_vma = ggtt_bind_vma;
 		} else {
@@ -2356,6 +2554,7 @@
 		}
 	} else {
 		BUG_ON(!i915_is_ggtt(vm));
+		vma->ggtt_view = *ggtt_view;
 		vma->unbind_vma = i915_ggtt_unbind_vma;
 		vma->bind_vma = i915_ggtt_bind_vma;
 	}
@@ -2368,38 +2567,170 @@
 }
 
 struct i915_vma *
-i915_gem_obj_lookup_or_create_vma_view(struct drm_i915_gem_object *obj,
-				       struct i915_address_space *vm,
-				       const struct i915_ggtt_view *view)
+i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
+				  struct i915_address_space *vm)
 {
 	struct i915_vma *vma;
 
-	vma = i915_gem_obj_to_vma_view(obj, vm, view);
+	vma = i915_gem_obj_to_vma(obj, vm);
 	if (!vma)
-		vma = __i915_gem_vma_create(obj, vm, view);
+		vma = __i915_gem_vma_create(obj, vm,
+					    i915_is_ggtt(vm) ? &i915_ggtt_view_normal : NULL);
 
 	return vma;
 }
 
-static inline
-int i915_get_vma_pages(struct i915_vma *vma)
+struct i915_vma *
+i915_gem_obj_lookup_or_create_ggtt_vma(struct drm_i915_gem_object *obj,
+				       const struct i915_ggtt_view *view)
 {
+	struct i915_address_space *ggtt = i915_obj_to_ggtt(obj);
+	struct i915_vma *vma;
+
+	if (WARN_ON(!view))
+		return ERR_PTR(-EINVAL);
+
+	vma = i915_gem_obj_to_ggtt_view(obj, view);
+
+	if (IS_ERR(vma))
+		return vma;
+
+	if (!vma)
+		vma = __i915_gem_vma_create(obj, ggtt, view);
+
+	return vma;
+
+}
+
+static void
+rotate_pages(dma_addr_t *in, unsigned int width, unsigned int height,
+	     struct sg_table *st)
+{
+	unsigned int column, row;
+	unsigned int src_idx;
+	struct scatterlist *sg = st->sgl;
+
+	st->nents = 0;
+
+	for (column = 0; column < width; column++) {
+		src_idx = width * (height - 1) + column;
+		for (row = 0; row < height; row++) {
+			st->nents++;
+			/* We don't need the pages, but need to initialize
+			 * the entries so the sg list can be happily traversed.
+			 * The only thing we need are DMA addresses.
+			 */
+			sg_set_page(sg, NULL, PAGE_SIZE, 0);
+			sg_dma_address(sg) = in[src_idx];
+			sg_dma_len(sg) = PAGE_SIZE;
+			sg = sg_next(sg);
+			src_idx -= width;
+		}
+	}
+}
+
+static struct sg_table *
+intel_rotate_fb_obj_pages(struct i915_ggtt_view *ggtt_view,
+			  struct drm_i915_gem_object *obj)
+{
+	struct drm_device *dev = obj->base.dev;
+	struct intel_rotation_info *rot_info = &ggtt_view->rotation_info;
+	unsigned long size, pages, rot_pages;
+	struct sg_page_iter sg_iter;
+	unsigned long i;
+	dma_addr_t *page_addr_list;
+	struct sg_table *st;
+	unsigned int tile_pitch, tile_height;
+	unsigned int width_pages, height_pages;
+	int ret = -ENOMEM;
+
+	pages = obj->base.size / PAGE_SIZE;
+
+	/* Calculate tiling geometry. */
+	tile_height = intel_tile_height(dev, rot_info->pixel_format,
+					rot_info->fb_modifier);
+	tile_pitch = PAGE_SIZE / tile_height;
+	width_pages = DIV_ROUND_UP(rot_info->pitch, tile_pitch);
+	height_pages = DIV_ROUND_UP(rot_info->height, tile_height);
+	rot_pages = width_pages * height_pages;
+	size = rot_pages * PAGE_SIZE;
+
+	/* Allocate a temporary list of source pages for random access. */
+	page_addr_list = drm_malloc_ab(pages, sizeof(dma_addr_t));
+	if (!page_addr_list)
+		return ERR_PTR(ret);
+
+	/* Allocate target SG list. */
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		goto err_st_alloc;
+
+	ret = sg_alloc_table(st, rot_pages, GFP_KERNEL);
+	if (ret)
+		goto err_sg_alloc;
+
+	/* Populate source page list from the object. */
+	i = 0;
+	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
+		page_addr_list[i] = sg_page_iter_dma_address(&sg_iter);
+		i++;
+	}
+
+	/* Rotate the pages. */
+	rotate_pages(page_addr_list, width_pages, height_pages, st);
+
+	DRM_DEBUG_KMS(
+		      "Created rotated page mapping for object size %lu (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %lu pages).\n",
+		      size, rot_info->pitch, rot_info->height,
+		      rot_info->pixel_format, width_pages, height_pages,
+		      rot_pages);
+
+	drm_free_large(page_addr_list);
+
+	return st;
+
+err_sg_alloc:
+	kfree(st);
+err_st_alloc:
+	drm_free_large(page_addr_list);
+
+	DRM_DEBUG_KMS(
+		      "Failed to create rotated mapping for object size %lu! (%d) (pitch=%u, height=%u, pixel_format=0x%x, %ux%u tiles, %lu pages)\n",
+		      size, ret, rot_info->pitch, rot_info->height,
+		      rot_info->pixel_format, width_pages, height_pages,
+		      rot_pages);
+	return ERR_PTR(ret);
+}
+
+static inline int
+i915_get_ggtt_vma_pages(struct i915_vma *vma)
+{
+	int ret = 0;
+
 	if (vma->ggtt_view.pages)
 		return 0;
 
 	if (vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL)
 		vma->ggtt_view.pages = vma->obj->pages;
+	else if (vma->ggtt_view.type == I915_GGTT_VIEW_ROTATED)
+		vma->ggtt_view.pages =
+			intel_rotate_fb_obj_pages(&vma->ggtt_view, vma->obj);
 	else
 		WARN_ONCE(1, "GGTT view %u not implemented!\n",
 			  vma->ggtt_view.type);
 
 	if (!vma->ggtt_view.pages) {
-		DRM_ERROR("Failed to get pages for VMA view type %u!\n",
+		DRM_ERROR("Failed to get pages for GGTT view type %u!\n",
 			  vma->ggtt_view.type);
-		return -EINVAL;
+		ret = -EINVAL;
+	} else if (IS_ERR(vma->ggtt_view.pages)) {
+		ret = PTR_ERR(vma->ggtt_view.pages);
+		vma->ggtt_view.pages = NULL;
+		DRM_ERROR("Failed to get pages for VMA view type %u (%d)!\n",
+			  vma->ggtt_view.type, ret);
 	}
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -2415,10 +2746,12 @@
 int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 		  u32 flags)
 {
-	int ret = i915_get_vma_pages(vma);
+	if (i915_is_ggtt(vma->vm)) {
+		int ret = i915_get_ggtt_vma_pages(vma);
 
-	if (ret)
-		return ret;
+		if (ret)
+			return ret;
+	}
 
 	vma->bind_vma(vma, cache_level, flags);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index c9e93f5..fc03c99 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -36,13 +36,13 @@
 
 struct drm_i915_file_private;
 
-typedef uint32_t gen6_gtt_pte_t;
-typedef uint64_t gen8_gtt_pte_t;
-typedef gen8_gtt_pte_t gen8_ppgtt_pde_t;
+typedef uint32_t gen6_pte_t;
+typedef uint64_t gen8_pte_t;
+typedef uint64_t gen8_pde_t;
 
 #define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT)
 
-#define I915_PPGTT_PT_ENTRIES		(PAGE_SIZE / sizeof(gen6_gtt_pte_t))
+
 /* gen6-hsw has bit 11-4 for physical addr bit 39-32 */
 #define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
 #define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
@@ -51,9 +51,16 @@
 #define GEN6_PTE_UNCACHED		(1 << 1)
 #define GEN6_PTE_VALID			(1 << 0)
 
-#define GEN6_PPGTT_PD_ENTRIES		512
-#define GEN6_PD_SIZE			(GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE)
+#define I915_PTES(pte_len)		(PAGE_SIZE / (pte_len))
+#define I915_PTE_MASK(pte_len)		(I915_PTES(pte_len) - 1)
+#define I915_PDES			512
+#define I915_PDE_MASK			(I915_PDES - 1)
+#define NUM_PTE(pde_shift)     (1 << (pde_shift - PAGE_SHIFT))
+
+#define GEN6_PTES			I915_PTES(sizeof(gen6_pte_t))
+#define GEN6_PD_SIZE		        (I915_PDES * PAGE_SIZE)
 #define GEN6_PD_ALIGN			(PAGE_SIZE * 16)
+#define GEN6_PDE_SHIFT			22
 #define GEN6_PDE_VALID			(1 << 0)
 
 #define GEN7_PTE_CACHE_L3_LLC		(3 << 1)
@@ -89,8 +96,7 @@
 #define GEN8_PTE_SHIFT			12
 #define GEN8_PTE_MASK			0x1ff
 #define GEN8_LEGACY_PDPES		4
-#define GEN8_PTES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_gtt_pte_t))
-#define GEN8_PDES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_ppgtt_pde_t))
+#define GEN8_PTES			I915_PTES(sizeof(gen8_pte_t))
 
 #define PPAT_UNCACHED_INDEX		(_PAGE_PWT | _PAGE_PCD)
 #define PPAT_CACHED_PDE_INDEX		0 /* WB LLC */
@@ -111,15 +117,28 @@
 
 enum i915_ggtt_view_type {
 	I915_GGTT_VIEW_NORMAL = 0,
+	I915_GGTT_VIEW_ROTATED
+};
+
+struct intel_rotation_info {
+	unsigned int height;
+	unsigned int pitch;
+	uint32_t pixel_format;
+	uint64_t fb_modifier;
 };
 
 struct i915_ggtt_view {
 	enum i915_ggtt_view_type type;
 
 	struct sg_table *pages;
+
+	union {
+		struct intel_rotation_info rotation_info;
+	};
 };
 
 extern const struct i915_ggtt_view i915_ggtt_view_normal;
+extern const struct i915_ggtt_view i915_ggtt_view_rotated;
 
 enum i915_cache_level;
 
@@ -190,6 +209,8 @@
 struct i915_page_table_entry {
 	struct page *page;
 	dma_addr_t daddr;
+
+	unsigned long *used_ptes;
 };
 
 struct i915_page_directory_entry {
@@ -199,7 +220,7 @@
 		dma_addr_t daddr;
 	};
 
-	struct i915_page_table_entry *page_table[GEN6_PPGTT_PD_ENTRIES]; /* PDEs */
+	struct i915_page_table_entry *page_table[I915_PDES]; /* PDEs */
 };
 
 struct i915_page_directory_pointer_entry {
@@ -243,9 +264,12 @@
 	struct list_head inactive_list;
 
 	/* FIXME: Need a more generic return type */
-	gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
-				     enum i915_cache_level level,
-				     bool valid, u32 flags); /* Create a valid PTE */
+	gen6_pte_t (*pte_encode)(dma_addr_t addr,
+				 enum i915_cache_level level,
+				 bool valid, u32 flags); /* Create a valid PTE */
+	int (*allocate_va_range)(struct i915_address_space *vm,
+				 uint64_t start,
+				 uint64_t length);
 	void (*clear_range)(struct i915_address_space *vm,
 			    uint64_t start,
 			    uint64_t length,
@@ -289,6 +313,7 @@
 	struct i915_address_space base;
 	struct kref ref;
 	struct drm_mm_node node;
+	unsigned long pd_dirty_rings;
 	unsigned num_pd_entries;
 	unsigned num_pd_pages; /* gen8+ */
 	union {
@@ -296,14 +321,82 @@
 		struct i915_page_directory_entry pd;
 	};
 
+	struct i915_page_table_entry *scratch_pt;
+
 	struct drm_i915_file_private *file_priv;
 
+	gen6_pte_t __iomem *pd_addr;
+
 	int (*enable)(struct i915_hw_ppgtt *ppgtt);
 	int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
 			 struct intel_engine_cs *ring);
 	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
 };
 
+/* For each pde iterates over every pde between from start until start + length.
+ * If start, and start+length are not perfectly divisible, the macro will round
+ * down, and up as needed. The macro modifies pde, start, and length. Dev is
+ * only used to differentiate shift values. Temp is temp.  On gen6/7, start = 0,
+ * and length = 2G effectively iterates over every PDE in the system.
+ *
+ * XXX: temp is not actually needed, but it saves doing the ALIGN operation.
+ */
+#define gen6_for_each_pde(pt, pd, start, length, temp, iter) \
+	for (iter = gen6_pde_index(start); \
+	     pt = (pd)->page_table[iter], length > 0 && iter < I915_PDES; \
+	     iter++, \
+	     temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT) - start, \
+	     temp = min_t(unsigned, temp, length), \
+	     start += temp, length -= temp)
+
+static inline uint32_t i915_pte_index(uint64_t address, uint32_t pde_shift)
+{
+	const uint32_t mask = NUM_PTE(pde_shift) - 1;
+
+	return (address >> PAGE_SHIFT) & mask;
+}
+
+/* Helper to counts the number of PTEs within the given length. This count
+ * does not cross a page table boundary, so the max value would be
+ * GEN6_PTES for GEN6, and GEN8_PTES for GEN8.
+*/
+static inline uint32_t i915_pte_count(uint64_t addr, size_t length,
+				      uint32_t pde_shift)
+{
+	const uint64_t mask = ~((1 << pde_shift) - 1);
+	uint64_t end;
+
+	WARN_ON(length == 0);
+	WARN_ON(offset_in_page(addr|length));
+
+	end = addr + length;
+
+	if ((addr & mask) != (end & mask))
+		return NUM_PTE(pde_shift) - i915_pte_index(addr, pde_shift);
+
+	return i915_pte_index(end, pde_shift) - i915_pte_index(addr, pde_shift);
+}
+
+static inline uint32_t i915_pde_index(uint64_t addr, uint32_t shift)
+{
+	return (addr >> shift) & I915_PDE_MASK;
+}
+
+static inline uint32_t gen6_pte_index(uint32_t addr)
+{
+	return i915_pte_index(addr, GEN6_PDE_SHIFT);
+}
+
+static inline size_t gen6_pte_count(uint32_t addr, uint32_t length)
+{
+	return i915_pte_count(addr, length, GEN6_PDE_SHIFT);
+}
+
+static inline uint32_t gen6_pde_index(uint32_t addr)
+{
+	return i915_pde_index(addr, GEN6_PDE_SHIFT);
+}
+
 int i915_gem_gtt_init(struct drm_device *dev);
 void i915_gem_init_global_gtt(struct drm_device *dev);
 void i915_global_gtt_cleanup(struct drm_device *dev);
@@ -332,4 +425,14 @@
 int __must_check i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj);
 void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj);
 
+static inline bool
+i915_ggtt_view_equal(const struct i915_ggtt_view *a,
+                     const struct i915_ggtt_view *b)
+{
+	if (WARN_ON(!a || !b))
+		return false;
+
+	return a->type == b->type;
+}
+
 #endif
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
new file mode 100644
index 0000000..f7929e7
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -0,0 +1,335 @@
+/*
+ * Copyright © 2008-2015 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#include <linux/oom.h>
+#include <linux/shmem_fs.h>
+#include <linux/slab.h>
+#include <linux/swap.h>
+#include <linux/pci.h>
+#include <linux/dma-buf.h>
+#include <drm/drmP.h>
+#include <drm/i915_drm.h>
+
+#include "i915_drv.h"
+#include "i915_trace.h"
+
+static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
+{
+	if (!mutex_is_locked(mutex))
+		return false;
+
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
+	return mutex->owner == task;
+#else
+	/* Since UP may be pre-empted, we cannot assume that we own the lock */
+	return false;
+#endif
+}
+
+/**
+ * i915_gem_shrink - Shrink buffer object caches
+ * @dev_priv: i915 device
+ * @target: amount of memory to make available, in pages
+ * @flags: control flags for selecting cache types
+ *
+ * This function is the main interface to the shrinker. It will try to release
+ * up to @target pages of main memory backing storage from buffer objects.
+ * Selection of the specific caches can be done with @flags. This is e.g. useful
+ * when purgeable objects should be removed from caches preferentially.
+ *
+ * Note that it's not guaranteed that released amount is actually available as
+ * free system memory - the pages might still be in-used to due to other reasons
+ * (like cpu mmaps) or the mm core has reused them before we could grab them.
+ * Therefore code that needs to explicitly shrink buffer objects caches (e.g. to
+ * avoid deadlocks in memory reclaim) must fall back to i915_gem_shrink_all().
+ *
+ * Also note that any kind of pinning (both per-vma address space pins and
+ * backing storage pins at the buffer object level) result in the shrinker code
+ * having to skip the object.
+ *
+ * Returns:
+ * The number of pages of backing storage actually released.
+ */
+unsigned long
+i915_gem_shrink(struct drm_i915_private *dev_priv,
+		long target, unsigned flags)
+{
+	const struct {
+		struct list_head *list;
+		unsigned int bit;
+	} phases[] = {
+		{ &dev_priv->mm.unbound_list, I915_SHRINK_UNBOUND },
+		{ &dev_priv->mm.bound_list, I915_SHRINK_BOUND },
+		{ NULL, 0 },
+	}, *phase;
+	unsigned long count = 0;
+
+	/*
+	 * As we may completely rewrite the (un)bound list whilst unbinding
+	 * (due to retiring requests) we have to strictly process only
+	 * one element of the list at the time, and recheck the list
+	 * on every iteration.
+	 *
+	 * In particular, we must hold a reference whilst removing the
+	 * object as we may end up waiting for and/or retiring the objects.
+	 * This might release the final reference (held by the active list)
+	 * and result in the object being freed from under us. This is
+	 * similar to the precautions the eviction code must take whilst
+	 * removing objects.
+	 *
+	 * Also note that although these lists do not hold a reference to
+	 * the object we can safely grab one here: The final object
+	 * unreferencing and the bound_list are both protected by the
+	 * dev->struct_mutex and so we won't ever be able to observe an
+	 * object on the bound_list with a reference count equals 0.
+	 */
+	for (phase = phases; phase->list; phase++) {
+		struct list_head still_in_list;
+
+		if ((flags & phase->bit) == 0)
+			continue;
+
+		INIT_LIST_HEAD(&still_in_list);
+		while (count < target && !list_empty(phase->list)) {
+			struct drm_i915_gem_object *obj;
+			struct i915_vma *vma, *v;
+
+			obj = list_first_entry(phase->list,
+					       typeof(*obj), global_list);
+			list_move_tail(&obj->global_list, &still_in_list);
+
+			if (flags & I915_SHRINK_PURGEABLE &&
+			    obj->madv != I915_MADV_DONTNEED)
+				continue;
+
+			drm_gem_object_reference(&obj->base);
+
+			/* For the unbound phase, this should be a no-op! */
+			list_for_each_entry_safe(vma, v,
+						 &obj->vma_list, vma_link)
+				if (i915_vma_unbind(vma))
+					break;
+
+			if (i915_gem_object_put_pages(obj) == 0)
+				count += obj->base.size >> PAGE_SHIFT;
+
+			drm_gem_object_unreference(&obj->base);
+		}
+		list_splice(&still_in_list, phase->list);
+	}
+
+	return count;
+}
+
+/**
+ * i915_gem_shrink - Shrink buffer object caches completely
+ * @dev_priv: i915 device
+ *
+ * This is a simple wraper around i915_gem_shrink() to aggressively shrink all
+ * caches completely. It also first waits for and retires all outstanding
+ * requests to also be able to release backing storage for active objects.
+ *
+ * This should only be used in code to intentionally quiescent the gpu or as a
+ * last-ditch effort when memory seems to have run out.
+ *
+ * Returns:
+ * The number of pages of backing storage actually released.
+ */
+unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
+{
+	i915_gem_evict_everything(dev_priv->dev);
+	return i915_gem_shrink(dev_priv, LONG_MAX,
+			       I915_SHRINK_BOUND | I915_SHRINK_UNBOUND);
+}
+
+static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
+{
+	if (!mutex_trylock(&dev->struct_mutex)) {
+		if (!mutex_is_locked_by(&dev->struct_mutex, current))
+			return false;
+
+		if (to_i915(dev)->mm.shrinker_no_lock_stealing)
+			return false;
+
+		*unlock = false;
+	} else
+		*unlock = true;
+
+	return true;
+}
+
+static int num_vma_bound(struct drm_i915_gem_object *obj)
+{
+	struct i915_vma *vma;
+	int count = 0;
+
+	list_for_each_entry(vma, &obj->vma_list, vma_link)
+		if (drm_mm_node_allocated(&vma->node))
+			count++;
+
+	return count;
+}
+
+static unsigned long
+i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(shrinker, struct drm_i915_private, mm.shrinker);
+	struct drm_device *dev = dev_priv->dev;
+	struct drm_i915_gem_object *obj;
+	unsigned long count;
+	bool unlock;
+
+	if (!i915_gem_shrinker_lock(dev, &unlock))
+		return 0;
+
+	count = 0;
+	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list)
+		if (obj->pages_pin_count == 0)
+			count += obj->base.size >> PAGE_SHIFT;
+
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
+		if (!i915_gem_obj_is_pinned(obj) &&
+		    obj->pages_pin_count == num_vma_bound(obj))
+			count += obj->base.size >> PAGE_SHIFT;
+	}
+
+	if (unlock)
+		mutex_unlock(&dev->struct_mutex);
+
+	return count;
+}
+
+static unsigned long
+i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(shrinker, struct drm_i915_private, mm.shrinker);
+	struct drm_device *dev = dev_priv->dev;
+	unsigned long freed;
+	bool unlock;
+
+	if (!i915_gem_shrinker_lock(dev, &unlock))
+		return SHRINK_STOP;
+
+	freed = i915_gem_shrink(dev_priv,
+				sc->nr_to_scan,
+				I915_SHRINK_BOUND |
+				I915_SHRINK_UNBOUND |
+				I915_SHRINK_PURGEABLE);
+	if (freed < sc->nr_to_scan)
+		freed += i915_gem_shrink(dev_priv,
+					 sc->nr_to_scan - freed,
+					 I915_SHRINK_BOUND |
+					 I915_SHRINK_UNBOUND);
+	if (unlock)
+		mutex_unlock(&dev->struct_mutex);
+
+	return freed;
+}
+
+static int
+i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(nb, struct drm_i915_private, mm.oom_notifier);
+	struct drm_device *dev = dev_priv->dev;
+	struct drm_i915_gem_object *obj;
+	unsigned long timeout = msecs_to_jiffies(5000) + 1;
+	unsigned long pinned, bound, unbound, freed_pages;
+	bool was_interruptible;
+	bool unlock;
+
+	while (!i915_gem_shrinker_lock(dev, &unlock) && --timeout) {
+		schedule_timeout_killable(1);
+		if (fatal_signal_pending(current))
+			return NOTIFY_DONE;
+	}
+	if (timeout == 0) {
+		pr_err("Unable to purge GPU memory due lock contention.\n");
+		return NOTIFY_DONE;
+	}
+
+	was_interruptible = dev_priv->mm.interruptible;
+	dev_priv->mm.interruptible = false;
+
+	freed_pages = i915_gem_shrink_all(dev_priv);
+
+	dev_priv->mm.interruptible = was_interruptible;
+
+	/* Because we may be allocating inside our own driver, we cannot
+	 * assert that there are no objects with pinned pages that are not
+	 * being pointed to by hardware.
+	 */
+	unbound = bound = pinned = 0;
+	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) {
+		if (!obj->base.filp) /* not backed by a freeable object */
+			continue;
+
+		if (obj->pages_pin_count)
+			pinned += obj->base.size;
+		else
+			unbound += obj->base.size;
+	}
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
+		if (!obj->base.filp)
+			continue;
+
+		if (obj->pages_pin_count)
+			pinned += obj->base.size;
+		else
+			bound += obj->base.size;
+	}
+
+	if (unlock)
+		mutex_unlock(&dev->struct_mutex);
+
+	if (freed_pages || unbound || bound)
+		pr_info("Purging GPU memory, %lu bytes freed, %lu bytes still pinned.\n",
+			freed_pages << PAGE_SHIFT, pinned);
+	if (unbound || bound)
+		pr_err("%lu and %lu bytes still available in the "
+		       "bound and unbound GPU page lists.\n",
+		       bound, unbound);
+
+	*(unsigned long *)ptr += freed_pages;
+	return NOTIFY_DONE;
+}
+
+/**
+ * i915_gem_shrinker_init - Initialize i915 shrinker
+ * @dev_priv: i915 device
+ *
+ * This function registers and sets up the i915 shrinker and OOM handler.
+ */
+void i915_gem_shrinker_init(struct drm_i915_private *dev_priv)
+{
+	dev_priv->mm.shrinker.scan_objects = i915_gem_shrinker_scan;
+	dev_priv->mm.shrinker.count_objects = i915_gem_shrinker_count;
+	dev_priv->mm.shrinker.seeks = DEFAULT_SEEKS;
+	register_shrinker(&dev_priv->mm.shrinker);
+
+	dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
+	register_oom_notifier(&dev_priv->mm.oom_notifier);
+}
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index a982849..1d4e60d 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -386,6 +386,11 @@
 
 	if (INTEL_INFO(dev)->gen >= 6) {
 		err_printf(m, "ERROR: 0x%08x\n", error->error);
+
+		if (INTEL_INFO(dev)->gen >= 8)
+			err_printf(m, "FAULT_TLB_DATA: 0x%08x 0x%08x\n",
+				   error->fault_data1, error->fault_data0);
+
 		err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
 	}
 
@@ -555,7 +560,14 @@
 	}
 
 	i915_error_object_free(error->semaphore_obj);
+
+	for (i = 0; i < error->vm_count; i++)
+		kfree(error->active_bo[i]);
+
 	kfree(error->active_bo);
+	kfree(error->active_bo_count);
+	kfree(error->pinned_bo);
+	kfree(error->pinned_bo_count);
 	kfree(error->overlay);
 	kfree(error->display);
 	kfree(error);
@@ -1164,6 +1176,11 @@
 	if (IS_GEN7(dev))
 		error->err_int = I915_READ(GEN7_ERR_INT);
 
+	if (INTEL_INFO(dev)->gen >= 8) {
+		error->fault_data0 = I915_READ(GEN8_FAULT_TLB_DATA0);
+		error->fault_data1 = I915_READ(GEN8_FAULT_TLB_DATA1);
+	}
+
 	if (IS_GEN6(dev)) {
 		error->forcewake = I915_READ(FORCEWAKE);
 		error->gab_ctl = I915_READ(GAB_CTL);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 49ad5fb..14ecb4d 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -277,6 +277,7 @@
 	I915_WRITE(reg, dev_priv->pm_rps_events);
 	I915_WRITE(reg, dev_priv->pm_rps_events);
 	POSTING_READ(reg);
+	dev_priv->rps.pm_iir = 0;
 	spin_unlock_irq(&dev_priv->irq_lock);
 }
 
@@ -330,12 +331,10 @@
 	__gen6_disable_pm_irq(dev_priv, dev_priv->pm_rps_events);
 	I915_WRITE(gen6_pm_ier(dev_priv), I915_READ(gen6_pm_ier(dev_priv)) &
 				~dev_priv->pm_rps_events);
-	I915_WRITE(gen6_pm_iir(dev_priv), dev_priv->pm_rps_events);
-	I915_WRITE(gen6_pm_iir(dev_priv), dev_priv->pm_rps_events);
-
-	dev_priv->rps.pm_iir = 0;
 
 	spin_unlock_irq(&dev_priv->irq_lock);
+
+	synchronize_irq(dev->irq);
 }
 
 /**
@@ -997,129 +996,73 @@
 	wake_up_all(&ring->irq_queue);
 }
 
-static u32 vlv_c0_residency(struct drm_i915_private *dev_priv,
-			    struct intel_rps_ei *rps_ei)
+static void vlv_c0_read(struct drm_i915_private *dev_priv,
+			struct intel_rps_ei *ei)
 {
-	u32 cz_ts, cz_freq_khz;
-	u32 render_count, media_count;
-	u32 elapsed_render, elapsed_media, elapsed_time;
-	u32 residency = 0;
-
-	cz_ts = vlv_punit_read(dev_priv, PUNIT_REG_CZ_TIMESTAMP);
-	cz_freq_khz = DIV_ROUND_CLOSEST(dev_priv->mem_freq * 1000, 4);
-
-	render_count = I915_READ(VLV_RENDER_C0_COUNT_REG);
-	media_count = I915_READ(VLV_MEDIA_C0_COUNT_REG);
-
-	if (rps_ei->cz_clock == 0) {
-		rps_ei->cz_clock = cz_ts;
-		rps_ei->render_c0 = render_count;
-		rps_ei->media_c0 = media_count;
-
-		return dev_priv->rps.cur_freq;
-	}
-
-	elapsed_time = cz_ts - rps_ei->cz_clock;
-	rps_ei->cz_clock = cz_ts;
-
-	elapsed_render = render_count - rps_ei->render_c0;
-	rps_ei->render_c0 = render_count;
-
-	elapsed_media = media_count - rps_ei->media_c0;
-	rps_ei->media_c0 = media_count;
-
-	/* Convert all the counters into common unit of milli sec */
-	elapsed_time /= VLV_CZ_CLOCK_TO_MILLI_SEC;
-	elapsed_render /=  cz_freq_khz;
-	elapsed_media /= cz_freq_khz;
-
-	/*
-	 * Calculate overall C0 residency percentage
-	 * only if elapsed time is non zero
-	 */
-	if (elapsed_time) {
-		residency =
-			((max(elapsed_render, elapsed_media) * 100)
-				/ elapsed_time);
-	}
-
-	return residency;
+	ei->cz_clock = vlv_punit_read(dev_priv, PUNIT_REG_CZ_TIMESTAMP);
+	ei->render_c0 = I915_READ(VLV_RENDER_C0_COUNT);
+	ei->media_c0 = I915_READ(VLV_MEDIA_C0_COUNT);
 }
 
-/**
- * vlv_calc_delay_from_C0_counters - Increase/Decrease freq based on GPU
- * busy-ness calculated from C0 counters of render & media power wells
- * @dev_priv: DRM device private
- *
- */
-static int vlv_calc_delay_from_C0_counters(struct drm_i915_private *dev_priv)
+static bool vlv_c0_above(struct drm_i915_private *dev_priv,
+			 const struct intel_rps_ei *old,
+			 const struct intel_rps_ei *now,
+			 int threshold)
 {
-	u32 residency_C0_up = 0, residency_C0_down = 0;
-	int new_delay, adj;
+	u64 time, c0;
 
-	dev_priv->rps.ei_interrupt_count++;
+	if (old->cz_clock == 0)
+		return false;
 
-	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+	time = now->cz_clock - old->cz_clock;
+	time *= threshold * dev_priv->mem_freq;
 
-
-	if (dev_priv->rps.up_ei.cz_clock == 0) {
-		vlv_c0_residency(dev_priv, &dev_priv->rps.up_ei);
-		vlv_c0_residency(dev_priv, &dev_priv->rps.down_ei);
-		return dev_priv->rps.cur_freq;
-	}
-
-
-	/*
-	 * To down throttle, C0 residency should be less than down threshold
-	 * for continous EI intervals. So calculate down EI counters
-	 * once in VLV_INT_COUNT_FOR_DOWN_EI
+	/* Workload can be split between render + media, e.g. SwapBuffers
+	 * being blitted in X after being rendered in mesa. To account for
+	 * this we need to combine both engines into our activity counter.
 	 */
-	if (dev_priv->rps.ei_interrupt_count == VLV_INT_COUNT_FOR_DOWN_EI) {
+	c0 = now->render_c0 - old->render_c0;
+	c0 += now->media_c0 - old->media_c0;
+	c0 *= 100 * VLV_CZ_CLOCK_TO_MILLI_SEC * 4 / 1000;
 
-		dev_priv->rps.ei_interrupt_count = 0;
+	return c0 >= time;
+}
 
-		residency_C0_down = vlv_c0_residency(dev_priv,
-						     &dev_priv->rps.down_ei);
-	} else {
-		residency_C0_up = vlv_c0_residency(dev_priv,
-						   &dev_priv->rps.up_ei);
+void gen6_rps_reset_ei(struct drm_i915_private *dev_priv)
+{
+	vlv_c0_read(dev_priv, &dev_priv->rps.down_ei);
+	dev_priv->rps.up_ei = dev_priv->rps.down_ei;
+}
+
+static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir)
+{
+	struct intel_rps_ei now;
+	u32 events = 0;
+
+	if ((pm_iir & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED)) == 0)
+		return 0;
+
+	vlv_c0_read(dev_priv, &now);
+	if (now.cz_clock == 0)
+		return 0;
+
+	if (pm_iir & GEN6_PM_RP_DOWN_EI_EXPIRED) {
+		if (!vlv_c0_above(dev_priv,
+				  &dev_priv->rps.down_ei, &now,
+				  VLV_RP_DOWN_EI_THRESHOLD))
+			events |= GEN6_PM_RP_DOWN_THRESHOLD;
+		dev_priv->rps.down_ei = now;
 	}
 
-	new_delay = dev_priv->rps.cur_freq;
-
-	adj = dev_priv->rps.last_adj;
-	/* C0 residency is greater than UP threshold. Increase Frequency */
-	if (residency_C0_up >= VLV_RP_UP_EI_THRESHOLD) {
-		if (adj > 0)
-			adj *= 2;
-		else
-			adj = 1;
-
-		if (dev_priv->rps.cur_freq < dev_priv->rps.max_freq_softlimit)
-			new_delay = dev_priv->rps.cur_freq + adj;
-
-		/*
-		 * For better performance, jump directly
-		 * to RPe if we're below it.
-		 */
-		if (new_delay < dev_priv->rps.efficient_freq)
-			new_delay = dev_priv->rps.efficient_freq;
-
-	} else if (!dev_priv->rps.ei_interrupt_count &&
-			(residency_C0_down < VLV_RP_DOWN_EI_THRESHOLD)) {
-		if (adj < 0)
-			adj *= 2;
-		else
-			adj = -1;
-		/*
-		 * This means, C0 residency is less than down threshold over
-		 * a period of VLV_INT_COUNT_FOR_DOWN_EI. So, reduce the freq
-		 */
-		if (dev_priv->rps.cur_freq > dev_priv->rps.min_freq_softlimit)
-			new_delay = dev_priv->rps.cur_freq + adj;
+	if (pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) {
+		if (vlv_c0_above(dev_priv,
+				 &dev_priv->rps.up_ei, &now,
+				 VLV_RP_UP_EI_THRESHOLD))
+			events |= GEN6_PM_RP_UP_THRESHOLD;
+		dev_priv->rps.up_ei = now;
 	}
 
-	return new_delay;
+	return events;
 }
 
 static void gen6_pm_rps_work(struct work_struct *work)
@@ -1149,6 +1092,8 @@
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 
+	pm_iir |= vlv_wa_c0_ei(dev_priv, pm_iir);
+
 	adj = dev_priv->rps.last_adj;
 	if (pm_iir & GEN6_PM_RP_UP_THRESHOLD) {
 		if (adj > 0)
@@ -1171,8 +1116,6 @@
 		else
 			new_delay = dev_priv->rps.min_freq_softlimit;
 		adj = 0;
-	} else if (pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) {
-		new_delay = vlv_calc_delay_from_C0_counters(dev_priv);
 	} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
 		if (adj < 0)
 			adj *= 2;
@@ -4299,7 +4242,7 @@
 	/* Let's track the enabled rps events */
 	if (IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
 		/* WaGsvRC0ResidencyMethod:vlv */
-		dev_priv->pm_rps_events = GEN6_PM_RP_UP_EI_EXPIRED;
+		dev_priv->pm_rps_events = GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED;
 	else
 		dev_priv->pm_rps_events = GEN6_PM_RPS_EVENTS;
 
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index e2d20ff..bb64415 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -27,7 +27,6 @@
 struct i915_params i915 __read_mostly = {
 	.modeset = -1,
 	.panel_ignore_lid = 1,
-	.powersave = 1,
 	.semaphores = -1,
 	.lvds_downclock = 0,
 	.lvds_channel_mode = 0,
@@ -44,6 +43,7 @@
 	.enable_ips = 1,
 	.fastboot = 0,
 	.prefault_disable = 0,
+	.load_detect_test = 0,
 	.reset = true,
 	.invert_brightness = 0,
 	.disable_display = 0,
@@ -65,10 +65,6 @@
 	"Override lid status (0=autodetect, 1=autodetect disabled [default], "
 	"-1=force lid closed, -2=force lid open)");
 
-module_param_named(powersave, i915.powersave, int, 0600);
-MODULE_PARM_DESC(powersave,
-	"Enable powersavings, fbc, downclocking, etc. (default: true)");
-
 module_param_named_unsafe(semaphores, i915.semaphores, int, 0400);
 MODULE_PARM_DESC(semaphores,
 	"Use semaphores for inter-ring sync "
@@ -144,11 +140,16 @@
 MODULE_PARM_DESC(fastboot,
 	"Try to skip unnecessary mode sets at boot time (default: false)");
 
-module_param_named(prefault_disable, i915.prefault_disable, bool, 0600);
+module_param_named_unsafe(prefault_disable, i915.prefault_disable, bool, 0600);
 MODULE_PARM_DESC(prefault_disable,
 	"Disable page prefaulting for pread/pwrite/reloc (default:false). "
 	"For developers only.");
 
+module_param_named_unsafe(load_detect_test, i915.load_detect_test, bool, 0600);
+MODULE_PARM_DESC(load_detect_test,
+	"Force-enable the VGA load detect code for testing (default:false). "
+	"For developers only.");
+
 module_param_named(invert_brightness, i915.invert_brightness, int, 0600);
 MODULE_PARM_DESC(invert_brightness,
 	"Invert backlight brightness "
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index cc8ebab..b522eb6 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -673,7 +673,6 @@
 #define VLV_CZ_CLOCK_TO_MILLI_SEC		100000
 #define VLV_RP_UP_EI_THRESHOLD			90
 #define VLV_RP_DOWN_EI_THRESHOLD		70
-#define VLV_INT_COUNT_FOR_DOWN_EI		5
 
 /* vlv2 north clock has */
 #define CCK_FUSE_REG				0x8
@@ -1307,6 +1306,9 @@
 #define   ERR_INT_FIFO_UNDERRUN_A	(1<<0)
 #define   ERR_INT_FIFO_UNDERRUN(pipe)	(1<<(pipe*3))
 
+#define GEN8_FAULT_TLB_DATA0		0x04b10
+#define GEN8_FAULT_TLB_DATA1		0x04b14
+
 #define FPGA_DBG		0x42300
 #define   FPGA_DBG_RM_NOCLAIM	(1<<31)
 
@@ -6220,8 +6222,8 @@
 
 #define GEN6_GT_GFX_RC6p			0x13810C
 #define GEN6_GT_GFX_RC6pp			0x138110
-#define VLV_RENDER_C0_COUNT_REG		0x138118
-#define VLV_MEDIA_C0_COUNT_REG			0x13811C
+#define VLV_RENDER_C0_COUNT			0x138118
+#define VLV_MEDIA_C0_COUNT			0x13811C
 
 #define GEN6_PCODE_MAILBOX			0x138124
 #define   GEN6_PCODE_READY			(1<<31)
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index f004d3d..b3070a4 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -156,6 +156,105 @@
 		      __entry->obj, __entry->offset, __entry->size, __entry->vm)
 );
 
+#define VM_TO_TRACE_NAME(vm) \
+	(i915_is_ggtt(vm) ? "G" : \
+		      "P")
+
+DECLARE_EVENT_CLASS(i915_va,
+	TP_PROTO(struct i915_address_space *vm, u64 start, u64 length, const char *name),
+	TP_ARGS(vm, start, length, name),
+
+	TP_STRUCT__entry(
+		__field(struct i915_address_space *, vm)
+		__field(u64, start)
+		__field(u64, end)
+		__string(name, name)
+	),
+
+	TP_fast_assign(
+		__entry->vm = vm;
+		__entry->start = start;
+		__entry->end = start + length - 1;
+		__assign_str(name, name);
+	),
+
+	TP_printk("vm=%p (%s), 0x%llx-0x%llx",
+		  __entry->vm, __get_str(name),  __entry->start, __entry->end)
+);
+
+DEFINE_EVENT(i915_va, i915_va_alloc,
+	     TP_PROTO(struct i915_address_space *vm, u64 start, u64 length, const char *name),
+	     TP_ARGS(vm, start, length, name)
+);
+
+DECLARE_EVENT_CLASS(i915_page_table_entry,
+	TP_PROTO(struct i915_address_space *vm, u32 pde, u64 start, u64 pde_shift),
+	TP_ARGS(vm, pde, start, pde_shift),
+
+	TP_STRUCT__entry(
+		__field(struct i915_address_space *, vm)
+		__field(u32, pde)
+		__field(u64, start)
+		__field(u64, end)
+	),
+
+	TP_fast_assign(
+		__entry->vm = vm;
+		__entry->pde = pde;
+		__entry->start = start;
+		__entry->end = ((start + (1ULL << pde_shift)) & ~((1ULL << pde_shift)-1)) - 1;
+	),
+
+	TP_printk("vm=%p, pde=%d (0x%llx-0x%llx)",
+		  __entry->vm, __entry->pde, __entry->start, __entry->end)
+);
+
+DEFINE_EVENT(i915_page_table_entry, i915_page_table_entry_alloc,
+	     TP_PROTO(struct i915_address_space *vm, u32 pde, u64 start, u64 pde_shift),
+	     TP_ARGS(vm, pde, start, pde_shift)
+);
+
+/* Avoid extra math because we only support two sizes. The format is defined by
+ * bitmap_scnprintf. Each 32 bits is 8 HEX digits followed by comma */
+#define TRACE_PT_SIZE(bits) \
+	((((bits) == 1024) ? 288 : 144) + 1)
+
+DECLARE_EVENT_CLASS(i915_page_table_entry_update,
+	TP_PROTO(struct i915_address_space *vm, u32 pde,
+		 struct i915_page_table_entry *pt, u32 first, u32 count, u32 bits),
+	TP_ARGS(vm, pde, pt, first, count, bits),
+
+	TP_STRUCT__entry(
+		__field(struct i915_address_space *, vm)
+		__field(u32, pde)
+		__field(u32, first)
+		__field(u32, last)
+		__dynamic_array(char, cur_ptes, TRACE_PT_SIZE(bits))
+	),
+
+	TP_fast_assign(
+		__entry->vm = vm;
+		__entry->pde = pde;
+		__entry->first = first;
+		__entry->last = first + count - 1;
+		scnprintf(__get_str(cur_ptes),
+			  TRACE_PT_SIZE(bits),
+			  "%*pb",
+			  bits,
+			  pt->used_ptes);
+	),
+
+	TP_printk("vm=%p, pde=%d, updating %u:%u\t%s",
+		  __entry->vm, __entry->pde, __entry->last, __entry->first,
+		  __get_str(cur_ptes))
+);
+
+DEFINE_EVENT(i915_page_table_entry_update, i915_page_table_entry_map,
+	TP_PROTO(struct i915_address_space *vm, u32 pde,
+		 struct i915_page_table_entry *pt, u32 first, u32 count, u32 bits),
+	TP_ARGS(vm, pde, pt, first, count, bits)
+);
+
 TRACE_EVENT(i915_gem_object_change_domain,
 	    TP_PROTO(struct drm_i915_gem_object *obj, u32 old_read, u32 old_write),
 	    TP_ARGS(obj, old_read, old_write),
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index e66e17a..6095a99 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -690,7 +690,7 @@
 	 * broken monitor (without edid) to work behind a broken kvm (that fails
 	 * to have the right resistors for HP detection) needs to fix this up.
 	 * For now just bail out. */
-	if (I915_HAS_HOTPLUG(dev)) {
+	if (I915_HAS_HOTPLUG(dev) && !i915.load_detect_test) {
 		status = connector_status_disconnected;
 		goto out;
 	}
@@ -706,9 +706,11 @@
 	if (intel_get_load_detect_pipe(connector, NULL, &tmp, &ctx)) {
 		if (intel_crt_detect_ddc(connector))
 			status = connector_status_connected;
-		else
+		else if (INTEL_INFO(dev)->gen < 4)
 			status = intel_crt_load_detect(crt);
-		intel_release_load_detect_pipe(connector, &tmp);
+		else
+			status = connector_status_unknown;
+		intel_release_load_detect_pipe(connector, &tmp, &ctx);
 	} else
 		status = connector_status_unknown;
 
@@ -794,6 +796,7 @@
 	.destroy = intel_crt_destroy,
 	.set_property = intel_crt_set_property,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 	.atomic_get_property = intel_connector_atomic_get_property,
 };
 
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 8aee7d7..47b9307d 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -492,17 +492,23 @@
 }
 
 static struct intel_encoder *
-intel_ddi_get_crtc_new_encoder(struct intel_crtc *crtc)
+intel_ddi_get_crtc_new_encoder(struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc->base.dev;
-	struct intel_encoder *intel_encoder, *ret = NULL;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_encoder *ret = NULL;
+	struct drm_atomic_state *state;
 	int num_encoders = 0;
+	int i;
 
-	for_each_intel_encoder(dev, intel_encoder) {
-		if (intel_encoder->new_crtc == crtc) {
-			ret = intel_encoder;
-			num_encoders++;
-		}
+	state = crtc_state->base.state;
+
+	for (i = 0; i < state->num_connector; i++) {
+		if (!state->connectors[i] ||
+		    state->connector_states[i]->crtc != crtc_state->base.crtc)
+			continue;
+
+		ret = to_intel_encoder(state->connector_states[i]->best_encoder);
+		num_encoders++;
 	}
 
 	WARN(num_encoders != 1, "%d encoders on crtc for pipe %c\n", num_encoders,
@@ -1216,7 +1222,7 @@
 {
 	struct drm_device *dev = intel_crtc->base.dev;
 	struct intel_encoder *intel_encoder =
-		intel_ddi_get_crtc_new_encoder(intel_crtc);
+		intel_ddi_get_crtc_new_encoder(crtc_state);
 	int clock = crtc_state->port_clock;
 
 	if (IS_SKYLAKE(dev))
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 90b460c..75955fe 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -83,7 +83,8 @@
 				   struct intel_crtc_state *pipe_config);
 
 static int intel_set_mode(struct drm_crtc *crtc, struct drm_display_mode *mode,
-			  int x, int y, struct drm_framebuffer *old_fb);
+			  int x, int y, struct drm_framebuffer *old_fb,
+			  struct drm_atomic_state *state);
 static int intel_framebuffer_init(struct drm_device *dev,
 				  struct intel_framebuffer *ifb,
 				  struct drm_mode_fb_cmd2 *mode_cmd,
@@ -430,25 +431,41 @@
  * intel_pipe_has_type() but looking at encoder->new_crtc instead of
  * encoder->crtc.
  */
-static bool intel_pipe_will_have_type(struct intel_crtc *crtc, int type)
+static bool intel_pipe_will_have_type(const struct intel_crtc_state *crtc_state,
+				      int type)
 {
-	struct drm_device *dev = crtc->base.dev;
+	struct drm_atomic_state *state = crtc_state->base.state;
+	struct drm_connector_state *connector_state;
 	struct intel_encoder *encoder;
+	int i, num_connectors = 0;
 
-	for_each_intel_encoder(dev, encoder)
-		if (encoder->new_crtc == crtc && encoder->type == type)
+	for (i = 0; i < state->num_connector; i++) {
+		if (!state->connectors[i])
+			continue;
+
+		connector_state = state->connector_states[i];
+		if (connector_state->crtc != crtc_state->base.crtc)
+			continue;
+
+		num_connectors++;
+
+		encoder = to_intel_encoder(connector_state->best_encoder);
+		if (encoder->type == type)
 			return true;
+	}
+
+	WARN_ON(num_connectors == 0);
 
 	return false;
 }
 
-static const intel_limit_t *intel_ironlake_limit(struct intel_crtc *crtc,
-						int refclk)
+static const intel_limit_t *
+intel_ironlake_limit(struct intel_crtc_state *crtc_state, int refclk)
 {
-	struct drm_device *dev = crtc->base.dev;
+	struct drm_device *dev = crtc_state->base.crtc->dev;
 	const intel_limit_t *limit;
 
-	if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS)) {
+	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		if (intel_is_dual_link_lvds(dev)) {
 			if (refclk == 100000)
 				limit = &intel_limits_ironlake_dual_lvds_100m;
@@ -466,20 +483,21 @@
 	return limit;
 }
 
-static const intel_limit_t *intel_g4x_limit(struct intel_crtc *crtc)
+static const intel_limit_t *
+intel_g4x_limit(struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc->base.dev;
+	struct drm_device *dev = crtc_state->base.crtc->dev;
 	const intel_limit_t *limit;
 
-	if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS)) {
+	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		if (intel_is_dual_link_lvds(dev))
 			limit = &intel_limits_g4x_dual_channel_lvds;
 		else
 			limit = &intel_limits_g4x_single_channel_lvds;
-	} else if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_HDMI) ||
-		   intel_pipe_will_have_type(crtc, INTEL_OUTPUT_ANALOG)) {
+	} else if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_HDMI) ||
+		   intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_ANALOG)) {
 		limit = &intel_limits_g4x_hdmi;
-	} else if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_SDVO)) {
+	} else if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_SDVO)) {
 		limit = &intel_limits_g4x_sdvo;
 	} else /* The option is for other outputs */
 		limit = &intel_limits_i9xx_sdvo;
@@ -487,17 +505,18 @@
 	return limit;
 }
 
-static const intel_limit_t *intel_limit(struct intel_crtc *crtc, int refclk)
+static const intel_limit_t *
+intel_limit(struct intel_crtc_state *crtc_state, int refclk)
 {
-	struct drm_device *dev = crtc->base.dev;
+	struct drm_device *dev = crtc_state->base.crtc->dev;
 	const intel_limit_t *limit;
 
 	if (HAS_PCH_SPLIT(dev))
-		limit = intel_ironlake_limit(crtc, refclk);
+		limit = intel_ironlake_limit(crtc_state, refclk);
 	else if (IS_G4X(dev)) {
-		limit = intel_g4x_limit(crtc);
+		limit = intel_g4x_limit(crtc_state);
 	} else if (IS_PINEVIEW(dev)) {
-		if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS))
+		if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS))
 			limit = &intel_limits_pineview_lvds;
 		else
 			limit = &intel_limits_pineview_sdvo;
@@ -506,14 +525,14 @@
 	} else if (IS_VALLEYVIEW(dev)) {
 		limit = &intel_limits_vlv;
 	} else if (!IS_GEN2(dev)) {
-		if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS))
+		if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS))
 			limit = &intel_limits_i9xx_lvds;
 		else
 			limit = &intel_limits_i9xx_sdvo;
 	} else {
-		if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS))
+		if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS))
 			limit = &intel_limits_i8xx_lvds;
-		else if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_DVO))
+		else if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_DVO))
 			limit = &intel_limits_i8xx_dvo;
 		else
 			limit = &intel_limits_i8xx_dac;
@@ -600,15 +619,17 @@
 }
 
 static bool
-i9xx_find_best_dpll(const intel_limit_t *limit, struct intel_crtc *crtc,
+i9xx_find_best_dpll(const intel_limit_t *limit,
+		    struct intel_crtc_state *crtc_state,
 		    int target, int refclk, intel_clock_t *match_clock,
 		    intel_clock_t *best_clock)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	intel_clock_t clock;
 	int err = target;
 
-	if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS)) {
+	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		/*
 		 * For LVDS just rely on its current settings for dual-channel.
 		 * We haven't figured out how to reliably set up different
@@ -661,15 +682,17 @@
 }
 
 static bool
-pnv_find_best_dpll(const intel_limit_t *limit, struct intel_crtc *crtc,
+pnv_find_best_dpll(const intel_limit_t *limit,
+		   struct intel_crtc_state *crtc_state,
 		   int target, int refclk, intel_clock_t *match_clock,
 		   intel_clock_t *best_clock)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	intel_clock_t clock;
 	int err = target;
 
-	if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS)) {
+	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		/*
 		 * For LVDS just rely on its current settings for dual-channel.
 		 * We haven't figured out how to reliably set up different
@@ -720,10 +743,12 @@
 }
 
 static bool
-g4x_find_best_dpll(const intel_limit_t *limit, struct intel_crtc *crtc,
+g4x_find_best_dpll(const intel_limit_t *limit,
+		   struct intel_crtc_state *crtc_state,
 		   int target, int refclk, intel_clock_t *match_clock,
 		   intel_clock_t *best_clock)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	intel_clock_t clock;
 	int max_n;
@@ -732,7 +757,7 @@
 	int err_most = (target >> 8) + (target >> 9);
 	found = false;
 
-	if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS)) {
+	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		if (intel_is_dual_link_lvds(dev))
 			clock.p2 = limit->p2.p2_fast;
 		else
@@ -776,11 +801,53 @@
 	return found;
 }
 
+/*
+ * Check if the calculated PLL configuration is more optimal compared to the
+ * best configuration and error found so far. Return the calculated error.
+ */
+static bool vlv_PLL_is_optimal(struct drm_device *dev, int target_freq,
+			       const intel_clock_t *calculated_clock,
+			       const intel_clock_t *best_clock,
+			       unsigned int best_error_ppm,
+			       unsigned int *error_ppm)
+{
+	/*
+	 * For CHV ignore the error and consider only the P value.
+	 * Prefer a bigger P value based on HW requirements.
+	 */
+	if (IS_CHERRYVIEW(dev)) {
+		*error_ppm = 0;
+
+		return calculated_clock->p > best_clock->p;
+	}
+
+	if (WARN_ON_ONCE(!target_freq))
+		return false;
+
+	*error_ppm = div_u64(1000000ULL *
+				abs(target_freq - calculated_clock->dot),
+			     target_freq);
+	/*
+	 * Prefer a better P value over a better (smaller) error if the error
+	 * is small. Ensure this preference for future configurations too by
+	 * setting the error to 0.
+	 */
+	if (*error_ppm < 100 && calculated_clock->p > best_clock->p) {
+		*error_ppm = 0;
+
+		return true;
+	}
+
+	return *error_ppm + 10 < best_error_ppm;
+}
+
 static bool
-vlv_find_best_dpll(const intel_limit_t *limit, struct intel_crtc *crtc,
+vlv_find_best_dpll(const intel_limit_t *limit,
+		   struct intel_crtc_state *crtc_state,
 		   int target, int refclk, intel_clock_t *match_clock,
 		   intel_clock_t *best_clock)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	intel_clock_t clock;
 	unsigned int bestppm = 1000000;
@@ -800,7 +867,7 @@
 				clock.p = clock.p1 * clock.p2;
 				/* based on hardware requirement, prefer bigger m1,m2 values */
 				for (clock.m1 = limit->m1.min; clock.m1 <= limit->m1.max; clock.m1++) {
-					unsigned int ppm, diff;
+					unsigned int ppm;
 
 					clock.m2 = DIV_ROUND_CLOSEST(target * clock.p * clock.n,
 								     refclk * clock.m1);
@@ -811,20 +878,15 @@
 								&clock))
 						continue;
 
-					diff = abs(clock.dot - target);
-					ppm = div_u64(1000000ULL * diff, target);
+					if (!vlv_PLL_is_optimal(dev, target,
+								&clock,
+								best_clock,
+								bestppm, &ppm))
+						continue;
 
-					if (ppm < 100 && clock.p > best_clock->p) {
-						bestppm = 0;
-						*best_clock = clock;
-						found = true;
-					}
-
-					if (bestppm >= 10 && ppm < bestppm - 10) {
-						bestppm = ppm;
-						*best_clock = clock;
-						found = true;
-					}
+					*best_clock = clock;
+					bestppm = ppm;
+					found = true;
 				}
 			}
 		}
@@ -834,16 +896,20 @@
 }
 
 static bool
-chv_find_best_dpll(const intel_limit_t *limit, struct intel_crtc *crtc,
+chv_find_best_dpll(const intel_limit_t *limit,
+		   struct intel_crtc_state *crtc_state,
 		   int target, int refclk, intel_clock_t *match_clock,
 		   intel_clock_t *best_clock)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
+	unsigned int best_error_ppm;
 	intel_clock_t clock;
 	uint64_t m2;
 	int found = false;
 
 	memset(best_clock, 0, sizeof(*best_clock));
+	best_error_ppm = 1000000;
 
 	/*
 	 * Based on hardware doc, the n always set to 1, and m1 always
@@ -857,6 +923,7 @@
 		for (clock.p2 = limit->p2.p2_fast;
 				clock.p2 >= limit->p2.p2_slow;
 				clock.p2 -= clock.p2 > 10 ? 2 : 1) {
+			unsigned int error_ppm;
 
 			clock.p = clock.p1 * clock.p2;
 
@@ -873,12 +940,13 @@
 			if (!intel_PLL_is_valid(dev, limit, &clock))
 				continue;
 
-			/* based on hardware requirement, prefer bigger p
-			 */
-			if (clock.p > best_clock->p) {
-				*best_clock = clock;
-				found = true;
-			}
+			if (!vlv_PLL_is_optimal(dev, target, &clock, best_clock,
+						best_error_ppm, &error_ppm))
+				continue;
+
+			*best_clock = clock;
+			best_error_ppm = error_ppm;
+			found = true;
 		}
 	}
 
@@ -2194,13 +2262,12 @@
 	return false;
 }
 
-int
-intel_fb_align_height(struct drm_device *dev, int height,
-		      uint32_t pixel_format,
-		      uint64_t fb_format_modifier)
+unsigned int
+intel_tile_height(struct drm_device *dev, uint32_t pixel_format,
+		  uint64_t fb_format_modifier)
 {
-	int tile_height;
-	uint32_t bits_per_pixel;
+	unsigned int tile_height;
+	uint32_t pixel_bytes;
 
 	switch (fb_format_modifier) {
 	case DRM_FORMAT_MOD_NONE:
@@ -2213,20 +2280,20 @@
 		tile_height = 32;
 		break;
 	case I915_FORMAT_MOD_Yf_TILED:
-		bits_per_pixel = drm_format_plane_cpp(pixel_format, 0) * 8;
-		switch (bits_per_pixel) {
+		pixel_bytes = drm_format_plane_cpp(pixel_format, 0);
+		switch (pixel_bytes) {
 		default:
-		case 8:
+		case 1:
 			tile_height = 64;
 			break;
-		case 16:
-		case 32:
+		case 2:
+		case 4:
 			tile_height = 32;
 			break;
-		case 64:
+		case 8:
 			tile_height = 16;
 			break;
-		case 128:
+		case 16:
 			WARN_ONCE(1,
 				  "128-bit pixels are not supported for display!");
 			tile_height = 16;
@@ -2239,17 +2306,58 @@
 		break;
 	}
 
-	return ALIGN(height, tile_height);
+	return tile_height;
+}
+
+unsigned int
+intel_fb_align_height(struct drm_device *dev, unsigned int height,
+		      uint32_t pixel_format, uint64_t fb_format_modifier)
+{
+	return ALIGN(height, intel_tile_height(dev, pixel_format,
+					       fb_format_modifier));
+}
+
+static int
+intel_fill_fb_ggtt_view(struct i915_ggtt_view *view, struct drm_framebuffer *fb,
+			const struct drm_plane_state *plane_state)
+{
+	struct intel_rotation_info *info = &view->rotation_info;
+
+	*view = i915_ggtt_view_normal;
+
+	if (!plane_state)
+		return 0;
+
+	if (!intel_rotation_90_or_270(plane_state->rotation))
+		return 0;
+
+	*view = i915_ggtt_view_rotated;
+
+	info->height = fb->height;
+	info->pixel_format = fb->pixel_format;
+	info->pitch = fb->pitches[0];
+	info->fb_modifier = fb->modifier[0];
+
+	if (!(info->fb_modifier == I915_FORMAT_MOD_Y_TILED ||
+	      info->fb_modifier == I915_FORMAT_MOD_Yf_TILED)) {
+		DRM_DEBUG_KMS(
+			      "Y or Yf tiling is needed for 90/270 rotation!\n");
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 int
 intel_pin_and_fence_fb_obj(struct drm_plane *plane,
 			   struct drm_framebuffer *fb,
+			   const struct drm_plane_state *plane_state,
 			   struct intel_engine_cs *pipelined)
 {
 	struct drm_device *dev = fb->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	struct i915_ggtt_view view;
 	u32 alignment;
 	int ret;
 
@@ -2286,6 +2394,10 @@
 		return -EINVAL;
 	}
 
+	ret = intel_fill_fb_ggtt_view(&view, fb, plane_state);
+	if (ret)
+		return ret;
+
 	/* Note that the w/a also requires 64 PTE of padding following the
 	 * bo. We currently fill all unused PTE with the shadow page and so
 	 * we should always have valid PTE following the scanout preventing
@@ -2304,7 +2416,8 @@
 	intel_runtime_pm_get(dev_priv);
 
 	dev_priv->mm.interruptible = false;
-	ret = i915_gem_object_pin_to_display_plane(obj, alignment, pipelined);
+	ret = i915_gem_object_pin_to_display_plane(obj, alignment, pipelined,
+						   &view);
 	if (ret)
 		goto err_interruptible;
 
@@ -2324,19 +2437,27 @@
 	return 0;
 
 err_unpin:
-	i915_gem_object_unpin_from_display_plane(obj);
+	i915_gem_object_unpin_from_display_plane(obj, &view);
 err_interruptible:
 	dev_priv->mm.interruptible = true;
 	intel_runtime_pm_put(dev_priv);
 	return ret;
 }
 
-static void intel_unpin_fb_obj(struct drm_i915_gem_object *obj)
+static void intel_unpin_fb_obj(struct drm_framebuffer *fb,
+			       const struct drm_plane_state *plane_state)
 {
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	struct i915_ggtt_view view;
+	int ret;
+
 	WARN_ON(!mutex_is_locked(&obj->base.dev->struct_mutex));
 
+	ret = intel_fill_fb_ggtt_view(&view, fb, plane_state);
+	WARN_ONCE(ret, "Couldn't get view from plane state!");
+
 	i915_gem_object_unpin_fence(obj);
-	i915_gem_object_unpin_from_display_plane(obj);
+	i915_gem_object_unpin_from_display_plane(obj, &view);
 }
 
 /* Computes the linear offset to the base tile and adjusts x, y. bytes per pixel
@@ -2414,8 +2535,8 @@
 }
 
 static bool
-intel_alloc_plane_obj(struct intel_crtc *crtc,
-		      struct intel_initial_plane_config *plane_config)
+intel_alloc_initial_plane_obj(struct intel_crtc *crtc,
+			      struct intel_initial_plane_config *plane_config)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_gem_object *obj = NULL;
@@ -2449,17 +2570,14 @@
 	mode_cmd.flags = DRM_MODE_FB_MODIFIERS;
 
 	mutex_lock(&dev->struct_mutex);
-
 	if (intel_framebuffer_init(dev, to_intel_framebuffer(fb),
 				   &mode_cmd, obj)) {
 		DRM_DEBUG_KMS("intel fb init failed\n");
 		goto out_unref_obj;
 	}
-
-	obj->frontbuffer_bits = INTEL_FRONTBUFFER_PRIMARY(crtc->pipe);
 	mutex_unlock(&dev->struct_mutex);
 
-	DRM_DEBUG_KMS("plane fb obj %p\n", obj);
+	DRM_DEBUG_KMS("initial plane fb obj %p\n", obj);
 	return true;
 
 out_unref_obj:
@@ -2483,26 +2601,23 @@
 }
 
 static void
-intel_find_plane_obj(struct intel_crtc *intel_crtc,
-		     struct intel_initial_plane_config *plane_config)
+intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
+			     struct intel_initial_plane_config *plane_config)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *c;
 	struct intel_crtc *i;
 	struct drm_i915_gem_object *obj;
+	struct drm_plane *primary = intel_crtc->base.primary;
+	struct drm_framebuffer *fb;
 
 	if (!plane_config->fb)
 		return;
 
-	if (intel_alloc_plane_obj(intel_crtc, plane_config)) {
-		struct drm_plane *primary = intel_crtc->base.primary;
-
-		primary->fb = &plane_config->fb->base;
-		primary->state->crtc = &intel_crtc->base;
-		update_state_fb(primary);
-
-		return;
+	if (intel_alloc_initial_plane_obj(intel_crtc, plane_config)) {
+		fb = &plane_config->fb->base;
+		goto valid_fb;
 	}
 
 	kfree(plane_config->fb);
@@ -2520,24 +2635,29 @@
 		if (!i->active)
 			continue;
 
-		obj = intel_fb_obj(c->primary->fb);
-		if (obj == NULL)
+		fb = c->primary->fb;
+		if (!fb)
 			continue;
 
+		obj = intel_fb_obj(fb);
 		if (i915_gem_obj_ggtt_offset(obj) == plane_config->base) {
-			struct drm_plane *primary = intel_crtc->base.primary;
-
-			if (obj->tiling_mode != I915_TILING_NONE)
-				dev_priv->preserve_bios_swizzle = true;
-
-			drm_framebuffer_reference(c->primary->fb);
-			primary->fb = c->primary->fb;
-			primary->state->crtc = &intel_crtc->base;
-			update_state_fb(intel_crtc->base.primary);
-			obj->frontbuffer_bits |= INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe);
-			break;
+			drm_framebuffer_reference(fb);
+			goto valid_fb;
 		}
 	}
+
+	return;
+
+valid_fb:
+	obj = intel_fb_obj(fb);
+	if (obj->tiling_mode != I915_TILING_NONE)
+		dev_priv->preserve_bios_swizzle = true;
+
+	primary->fb = fb;
+	primary->state->crtc = &intel_crtc->base;
+	primary->crtc = &intel_crtc->base;
+	update_state_fb(primary);
+	obj->frontbuffer_bits |= INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe);
 }
 
 static void i9xx_update_primary_plane(struct drm_crtc *crtc,
@@ -2805,6 +2925,17 @@
 	}
 }
 
+unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane,
+				     struct drm_i915_gem_object *obj)
+{
+	const struct i915_ggtt_view *view = &i915_ggtt_view_normal;
+
+	if (intel_rotation_90_or_270(intel_plane->base.state->rotation))
+		view = &i915_ggtt_view_rotated;
+
+	return i915_gem_obj_ggtt_offset_view(obj, view);
+}
+
 static void skylake_update_primary_plane(struct drm_crtc *crtc,
 					 struct drm_framebuffer *fb,
 					 int x, int y)
@@ -2815,6 +2946,7 @@
 	struct drm_i915_gem_object *obj;
 	int pipe = intel_crtc->pipe;
 	u32 plane_ctl, stride_div;
+	unsigned long surf_addr;
 
 	if (!intel_crtc->primary_enabled) {
 		I915_WRITE(PLANE_CTL(pipe, 0), 0);
@@ -2881,16 +3013,16 @@
 	obj = intel_fb_obj(fb);
 	stride_div = intel_fb_stride_alignment(dev, fb->modifier[0],
 					       fb->pixel_format);
+	surf_addr = intel_plane_obj_offset(to_intel_plane(crtc->primary), obj);
 
 	I915_WRITE(PLANE_CTL(pipe, 0), plane_ctl);
-
 	I915_WRITE(PLANE_POS(pipe, 0), 0);
 	I915_WRITE(PLANE_OFFSET(pipe, 0), (y << 16) | x);
 	I915_WRITE(PLANE_SIZE(pipe, 0),
 		   (intel_crtc->config->pipe_src_h - 1) << 16 |
 		   (intel_crtc->config->pipe_src_w - 1));
 	I915_WRITE(PLANE_STRIDE(pipe, 0), fb->pitches[0] / stride_div);
-	I915_WRITE(PLANE_SURF(pipe, 0), i915_gem_obj_ggtt_offset(obj));
+	I915_WRITE(PLANE_SURF(pipe, 0), surf_addr);
 
 	POSTING_READ(PLANE_SURF(pipe, 0));
 }
@@ -4824,8 +4956,9 @@
 	return mask;
 }
 
-static void modeset_update_crtc_power_domains(struct drm_device *dev)
+static void modeset_update_crtc_power_domains(struct drm_atomic_state *state)
 {
+	struct drm_device *dev = state->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long pipe_domains[I915_MAX_PIPES] = { 0, };
 	struct intel_crtc *crtc;
@@ -4847,7 +4980,7 @@
 	}
 
 	if (dev_priv->display.modeset_global_resources)
-		dev_priv->display.modeset_global_resources(dev);
+		dev_priv->display.modeset_global_resources(state);
 
 	for_each_intel_crtc(dev, crtc) {
 		enum intel_display_power_domain domain;
@@ -5095,8 +5228,9 @@
 	WARN_ON(I915_READ(GCI_CONTROL) & PFI_CREDIT_RESEND);
 }
 
-static void valleyview_modeset_global_resources(struct drm_device *dev)
+static void valleyview_modeset_global_resources(struct drm_atomic_state *state)
 {
+	struct drm_device *dev = state->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int max_pixclk = intel_mode_max_pixclk(dev_priv);
 	int req_cdclk = valleyview_calc_cdclk(dev_priv, max_pixclk);
@@ -5687,7 +5821,7 @@
 	 * - LVDS dual channel mode
 	 * - Double wide pipe
 	 */
-	if ((intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS) &&
+	if ((intel_pipe_will_have_type(pipe_config, INTEL_OUTPUT_LVDS) &&
 	     intel_is_dual_link_lvds(dev)) || pipe_config->double_wide)
 		pipe_config->pipe_src_w &= ~1;
 
@@ -5866,15 +6000,18 @@
 		&& !(dev_priv->quirks & QUIRK_LVDS_SSC_DISABLE);
 }
 
-static int i9xx_get_refclk(struct intel_crtc *crtc, int num_connectors)
+static int i9xx_get_refclk(const struct intel_crtc_state *crtc_state,
+			   int num_connectors)
 {
-	struct drm_device *dev = crtc->base.dev;
+	struct drm_device *dev = crtc_state->base.crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int refclk;
 
+	WARN_ON(!crtc_state->base.state);
+
 	if (IS_VALLEYVIEW(dev)) {
 		refclk = 100000;
-	} else if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS) &&
+	} else if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS) &&
 	    intel_panel_use_ssc(dev_priv) && num_connectors < 2) {
 		refclk = dev_priv->vbt.lvds_ssc_freq;
 		DRM_DEBUG_KMS("using SSC reference clock of %d kHz\n", refclk);
@@ -5917,8 +6054,8 @@
 	crtc_state->dpll_hw_state.fp0 = fp;
 
 	crtc->lowfreq_avail = false;
-	if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS) &&
-	    reduced_clock && i915.powersave) {
+	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS) &&
+	    reduced_clock) {
 		crtc_state->dpll_hw_state.fp1 = fp2;
 		crtc->lowfreq_avail = true;
 	} else {
@@ -6275,6 +6412,7 @@
 	struct intel_crtc *crtc =
 		to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe));
 	struct intel_crtc_state pipe_config = {
+		.base.crtc = &crtc->base,
 		.pixel_multiplier = 1,
 		.dpll = *dpll,
 	};
@@ -6319,12 +6457,12 @@
 
 	i9xx_update_pll_dividers(crtc, crtc_state, reduced_clock);
 
-	is_sdvo = intel_pipe_will_have_type(crtc, INTEL_OUTPUT_SDVO) ||
-		intel_pipe_will_have_type(crtc, INTEL_OUTPUT_HDMI);
+	is_sdvo = intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_SDVO) ||
+		intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_HDMI);
 
 	dpll = DPLL_VGA_MODE_DIS;
 
-	if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS))
+	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS))
 		dpll |= DPLLB_MODE_LVDS;
 	else
 		dpll |= DPLLB_MODE_DAC_SERIAL;
@@ -6367,7 +6505,7 @@
 
 	if (crtc_state->sdvo_tv_clock)
 		dpll |= PLL_REF_INPUT_TVCLKINBC;
-	else if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS) &&
+	else if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS) &&
 		 intel_panel_use_ssc(dev_priv) && num_connectors < 2)
 		dpll |= PLLB_REF_INPUT_SPREADSPECTRUMIN;
 	else
@@ -6397,7 +6535,7 @@
 
 	dpll = DPLL_VGA_MODE_DIS;
 
-	if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS)) {
+	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		dpll |= (1 << (clock->p1 - 1)) << DPLL_FPA01_P1_POST_DIV_SHIFT;
 	} else {
 		if (clock->p1 == 2)
@@ -6408,10 +6546,10 @@
 			dpll |= PLL_P2_DIVIDE_BY_4;
 	}
 
-	if (!IS_I830(dev) && intel_pipe_will_have_type(crtc, INTEL_OUTPUT_DVO))
+	if (!IS_I830(dev) && intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_DVO))
 		dpll |= DPLL_DVO_2X_MODE;
 
-	if (intel_pipe_will_have_type(crtc, INTEL_OUTPUT_LVDS) &&
+	if (intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS) &&
 		 intel_panel_use_ssc(dev_priv) && num_connectors < 2)
 		dpll |= PLLB_REF_INPUT_SPREADSPECTRUMIN;
 	else
@@ -6625,11 +6763,20 @@
 	bool is_lvds = false, is_dsi = false;
 	struct intel_encoder *encoder;
 	const intel_limit_t *limit;
+	struct drm_atomic_state *state = crtc_state->base.state;
+	struct drm_connector_state *connector_state;
+	int i;
 
-	for_each_intel_encoder(dev, encoder) {
-		if (encoder->new_crtc != crtc)
+	for (i = 0; i < state->num_connector; i++) {
+		if (!state->connectors[i])
 			continue;
 
+		connector_state = state->connector_states[i];
+		if (connector_state->crtc != &crtc->base)
+			continue;
+
+		encoder = to_intel_encoder(connector_state->best_encoder);
+
 		switch (encoder->type) {
 		case INTEL_OUTPUT_LVDS:
 			is_lvds = true;
@@ -6648,7 +6795,7 @@
 		return 0;
 
 	if (!crtc_state->clock_set) {
-		refclk = i9xx_get_refclk(crtc, num_connectors);
+		refclk = i9xx_get_refclk(crtc_state, num_connectors);
 
 		/*
 		 * Returns a set of divisors for the desired target clock with
@@ -6656,8 +6803,8 @@
 		 * the clock equation: reflck * (5 * (m1 + 2) + (m2 + 2)) / (n +
 		 * 2) / p1 / p2.
 		 */
-		limit = intel_limit(crtc, refclk);
-		ok = dev_priv->display.find_dpll(limit, crtc,
+		limit = intel_limit(crtc_state, refclk);
+		ok = dev_priv->display.find_dpll(limit, crtc_state,
 						 crtc_state->port_clock,
 						 refclk, NULL, &clock);
 		if (!ok) {
@@ -6673,7 +6820,7 @@
 			 * we will disable the LVDS downclock feature.
 			 */
 			has_reduced_clock =
-				dev_priv->display.find_dpll(limit, crtc,
+				dev_priv->display.find_dpll(limit, crtc_state,
 							    dev_priv->lvds_downclock,
 							    refclk, &clock,
 							    &reduced_clock);
@@ -6772,7 +6919,7 @@
 	u32 val, base, offset;
 	int pipe = crtc->pipe, plane = crtc->plane;
 	int fourcc, pixel_format;
-	int aligned_height;
+	unsigned int aligned_height;
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 
@@ -7303,18 +7450,26 @@
 		lpt_init_pch_refclk(dev);
 }
 
-static int ironlake_get_refclk(struct drm_crtc *crtc)
+static int ironlake_get_refclk(struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc->dev;
+	struct drm_device *dev = crtc_state->base.crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_atomic_state *state = crtc_state->base.state;
+	struct drm_connector_state *connector_state;
 	struct intel_encoder *encoder;
-	int num_connectors = 0;
+	int num_connectors = 0, i;
 	bool is_lvds = false;
 
-	for_each_intel_encoder(dev, encoder) {
-		if (encoder->new_crtc != to_intel_crtc(crtc))
+	for (i = 0; i < state->num_connector; i++) {
+		if (!state->connectors[i])
 			continue;
 
+		connector_state = state->connector_states[i];
+		if (connector_state->crtc != crtc_state->base.crtc)
+			continue;
+
+		encoder = to_intel_encoder(connector_state->best_encoder);
+
 		switch (encoder->type) {
 		case INTEL_OUTPUT_LVDS:
 			is_lvds = true;
@@ -7501,22 +7656,21 @@
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int refclk;
 	const intel_limit_t *limit;
 	bool ret, is_lvds = false;
 
-	is_lvds = intel_pipe_will_have_type(intel_crtc, INTEL_OUTPUT_LVDS);
+	is_lvds = intel_pipe_will_have_type(crtc_state, INTEL_OUTPUT_LVDS);
 
-	refclk = ironlake_get_refclk(crtc);
+	refclk = ironlake_get_refclk(crtc_state);
 
 	/*
 	 * Returns a set of divisors for the desired target clock with the given
 	 * refclk, or FALSE.  The returned values represent the clock equation:
 	 * reflck * (5 * (m1 + 2) + (m2 + 2)) / (n + 2) / p1 / p2.
 	 */
-	limit = intel_limit(intel_crtc, refclk);
-	ret = dev_priv->display.find_dpll(limit, intel_crtc,
+	limit = intel_limit(crtc_state, refclk);
+	ret = dev_priv->display.find_dpll(limit, crtc_state,
 					  crtc_state->port_clock,
 					  refclk, NULL, clock);
 	if (!ret)
@@ -7530,7 +7684,7 @@
 		 * downclock feature.
 		*/
 		*has_reduced_clock =
-			dev_priv->display.find_dpll(limit, intel_crtc,
+			dev_priv->display.find_dpll(limit, crtc_state,
 						    dev_priv->lvds_downclock,
 						    refclk, clock,
 						    reduced_clock);
@@ -7563,16 +7717,24 @@
 	struct drm_crtc *crtc = &intel_crtc->base;
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_encoder *intel_encoder;
+	struct drm_atomic_state *state = crtc_state->base.state;
+	struct drm_connector_state *connector_state;
+	struct intel_encoder *encoder;
 	uint32_t dpll;
-	int factor, num_connectors = 0;
+	int factor, num_connectors = 0, i;
 	bool is_lvds = false, is_sdvo = false;
 
-	for_each_intel_encoder(dev, intel_encoder) {
-		if (intel_encoder->new_crtc != to_intel_crtc(crtc))
+	for (i = 0; i < state->num_connector; i++) {
+		if (!state->connectors[i])
 			continue;
 
-		switch (intel_encoder->type) {
+		connector_state = state->connector_states[i];
+		if (connector_state->crtc != crtc_state->base.crtc)
+			continue;
+
+		encoder = to_intel_encoder(connector_state->best_encoder);
+
+		switch (encoder->type) {
 		case INTEL_OUTPUT_LVDS:
 			is_lvds = true;
 			break;
@@ -7701,7 +7863,7 @@
 		}
 	}
 
-	if (is_lvds && has_reduced_clock && i915.powersave)
+	if (is_lvds && has_reduced_clock)
 		crtc->lowfreq_avail = true;
 	else
 		crtc->lowfreq_avail = false;
@@ -7810,7 +7972,7 @@
 	u32 val, base, offset, stride_mult, tiling;
 	int pipe = crtc->pipe;
 	int fourcc, pixel_format;
-	int aligned_height;
+	unsigned int aligned_height;
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 
@@ -7918,7 +8080,7 @@
 	u32 val, base, offset;
 	int pipe = crtc->pipe;
 	int fourcc, pixel_format;
-	int aligned_height;
+	unsigned int aligned_height;
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 
@@ -8802,6 +8964,8 @@
 	struct drm_device *dev = encoder->dev;
 	struct drm_framebuffer *fb;
 	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_atomic_state *state = NULL;
+	struct drm_connector_state *connector_state;
 	int ret, i = -1;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s], [ENCODER:%d:%s]\n",
@@ -8883,6 +9047,21 @@
 	old->load_detect_temp = true;
 	old->release_fb = NULL;
 
+	state = drm_atomic_state_alloc(dev);
+	if (!state)
+		return false;
+
+	state->acquire_ctx = ctx;
+
+	connector_state = drm_atomic_get_connector_state(state, connector);
+	if (IS_ERR(connector_state)) {
+		ret = PTR_ERR(connector_state);
+		goto fail;
+	}
+
+	connector_state->crtc = crtc;
+	connector_state->best_encoder = &intel_encoder->base;
+
 	if (!mode)
 		mode = &load_detect_mode;
 
@@ -8905,7 +9084,7 @@
 		goto fail;
 	}
 
-	if (intel_set_mode(crtc, mode, 0, 0, fb)) {
+	if (intel_set_mode(crtc, mode, 0, 0, fb, state)) {
 		DRM_DEBUG_KMS("failed to set mode on load-detect pipe\n");
 		if (old->release_fb)
 			old->release_fb->funcs->destroy(old->release_fb);
@@ -8924,6 +9103,11 @@
 	else
 		intel_crtc->new_config = NULL;
 fail_unlock:
+	if (state) {
+		drm_atomic_state_free(state);
+		state = NULL;
+	}
+
 	if (ret == -EDEADLK) {
 		drm_modeset_backoff(ctx);
 		goto retry;
@@ -8933,24 +9117,44 @@
 }
 
 void intel_release_load_detect_pipe(struct drm_connector *connector,
-				    struct intel_load_detect_pipe *old)
+				    struct intel_load_detect_pipe *old,
+				    struct drm_modeset_acquire_ctx *ctx)
 {
+	struct drm_device *dev = connector->dev;
 	struct intel_encoder *intel_encoder =
 		intel_attached_encoder(connector);
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_crtc *crtc = encoder->crtc;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct drm_atomic_state *state;
+	struct drm_connector_state *connector_state;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s], [ENCODER:%d:%s]\n",
 		      connector->base.id, connector->name,
 		      encoder->base.id, encoder->name);
 
 	if (old->load_detect_temp) {
+		state = drm_atomic_state_alloc(dev);
+		if (!state)
+			goto fail;
+
+		state->acquire_ctx = ctx;
+
+		connector_state = drm_atomic_get_connector_state(state, connector);
+		if (IS_ERR(connector_state))
+			goto fail;
+
 		to_intel_connector(connector)->new_encoder = NULL;
 		intel_encoder->new_crtc = NULL;
 		intel_crtc->new_enabled = false;
 		intel_crtc->new_config = NULL;
-		intel_set_mode(crtc, NULL, 0, 0, NULL);
+
+		connector_state->best_encoder = NULL;
+		connector_state->crtc = NULL;
+
+		intel_set_mode(crtc, NULL, 0, 0, NULL, state);
+
+		drm_atomic_state_free(state);
 
 		if (old->release_fb) {
 			drm_framebuffer_unregister_private(old->release_fb);
@@ -8963,6 +9167,11 @@
 	/* Switch crtc and encoder back off if necessary */
 	if (old->dpms_mode != DRM_MODE_DPMS_ON)
 		connector->funcs->dpms(connector, old->dpms_mode);
+
+	return;
+fail:
+	DRM_DEBUG_KMS("Couldn't release load detect pipe.\n");
+	drm_atomic_state_free(state);
 }
 
 static int i9xx_pll_refclk(struct drm_device *dev,
@@ -9201,6 +9410,8 @@
 
 	intel_runtime_pm_get(dev_priv);
 	i915_update_gfx_val(dev_priv);
+	if (INTEL_INFO(dev)->gen >= 6)
+		gen6_rps_busy(dev_priv);
 	dev_priv->mm.busy = true;
 }
 
@@ -9214,9 +9425,6 @@
 
 	dev_priv->mm.busy = false;
 
-	if (!i915.powersave)
-		goto out;
-
 	for_each_crtc(dev, crtc) {
 		if (!crtc->primary->fb)
 			continue;
@@ -9227,7 +9435,6 @@
 	if (INTEL_INFO(dev)->gen >= 6)
 		gen6_rps_idle(dev->dev_private);
 
-out:
 	intel_runtime_pm_put(dev_priv);
 }
 
@@ -9269,7 +9476,7 @@
 	enum pipe pipe = to_intel_crtc(work->crtc)->pipe;
 
 	mutex_lock(&dev->struct_mutex);
-	intel_unpin_fb_obj(intel_fb_obj(work->old_fb));
+	intel_unpin_fb_obj(work->old_fb, work->crtc->primary->state);
 	drm_gem_object_unreference(&work->pending_flip_obj->base);
 
 	intel_fbc_update(dev);
@@ -9977,12 +10184,13 @@
 		ring = &dev_priv->ring[RCS];
 	}
 
-	ret = intel_pin_and_fence_fb_obj(crtc->primary, fb, ring);
+	ret = intel_pin_and_fence_fb_obj(crtc->primary, fb,
+					 crtc->primary->state, ring);
 	if (ret)
 		goto cleanup_pending;
 
-	work->gtt_offset =
-		i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset;
+	work->gtt_offset = intel_plane_obj_offset(to_intel_plane(primary), obj)
+						  + intel_crtc->dspaddr_offset;
 
 	if (use_mmio_flip(ring, obj)) {
 		ret = intel_queue_mmio_flip(dev, crtc, fb, obj, ring,
@@ -10017,7 +10225,7 @@
 	return 0;
 
 cleanup_unpin:
-	intel_unpin_fb_obj(obj);
+	intel_unpin_fb_obj(fb, crtc->primary->state);
 cleanup_pending:
 	atomic_dec(&intel_crtc->unpin_work_count);
 	mutex_unlock(&dev->struct_mutex);
@@ -10087,6 +10295,27 @@
 	}
 }
 
+/* Transitional helper to copy current connector/encoder state to
+ * connector->state. This is needed so that code that is partially
+ * converted to atomic does the right thing.
+ */
+static void intel_modeset_update_connector_atomic_state(struct drm_device *dev)
+{
+	struct intel_connector *connector;
+
+	for_each_intel_connector(dev, connector) {
+		if (connector->base.encoder) {
+			connector->base.state->best_encoder =
+				connector->base.encoder;
+			connector->base.state->crtc =
+				connector->base.encoder->crtc;
+		} else {
+			connector->base.state->best_encoder = NULL;
+			connector->base.state->crtc = NULL;
+		}
+	}
+}
+
 /**
  * intel_modeset_commit_output_state
  *
@@ -10110,6 +10339,8 @@
 		crtc->base.state->enable = crtc->new_enabled;
 		crtc->base.enabled = crtc->new_enabled;
 	}
+
+	intel_modeset_update_connector_atomic_state(dev);
 }
 
 static void
@@ -10144,8 +10375,9 @@
 			  struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
+	struct drm_atomic_state *state;
 	struct intel_connector *connector;
-	int bpp;
+	int bpp, i;
 
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_C8:
@@ -10185,10 +10417,15 @@
 
 	pipe_config->pipe_bpp = bpp;
 
+	state = pipe_config->base.state;
+
 	/* Clamp display bpp to EDID value */
-	for_each_intel_connector(dev, connector) {
-		if (!connector->new_encoder ||
-		    connector->new_encoder->new_crtc != crtc)
+	for (i = 0; i < state->num_connector; i++) {
+		if (!state->connectors[i])
+			continue;
+
+		connector = to_intel_connector(state->connectors[i]);
+		if (state->connector_states[i]->crtc != &crtc->base)
 			continue;
 
 		connected_sink_compute_bpp(connector, pipe_config);
@@ -10344,15 +10581,30 @@
 	return true;
 }
 
+static void
+clear_intel_crtc_state(struct intel_crtc_state *crtc_state)
+{
+	struct drm_crtc_state tmp_state;
+
+	/* Clear only the intel specific part of the crtc state */
+	tmp_state = crtc_state->base;
+	memset(crtc_state, 0, sizeof *crtc_state);
+	crtc_state->base = tmp_state;
+}
+
 static struct intel_crtc_state *
 intel_modeset_pipe_config(struct drm_crtc *crtc,
 			  struct drm_framebuffer *fb,
-			  struct drm_display_mode *mode)
+			  struct drm_display_mode *mode,
+			  struct drm_atomic_state *state)
 {
 	struct drm_device *dev = crtc->dev;
 	struct intel_encoder *encoder;
+	struct intel_connector *connector;
+	struct drm_connector_state *connector_state;
 	struct intel_crtc_state *pipe_config;
 	int plane_bpp, ret = -EINVAL;
+	int i;
 	bool retry = true;
 
 	if (!check_encoder_cloning(to_intel_crtc(crtc))) {
@@ -10365,9 +10617,11 @@
 		return ERR_PTR(-EINVAL);
 	}
 
-	pipe_config = kzalloc(sizeof(*pipe_config), GFP_KERNEL);
-	if (!pipe_config)
-		return ERR_PTR(-ENOMEM);
+	pipe_config = intel_atomic_get_crtc_state(state, to_intel_crtc(crtc));
+	if (IS_ERR(pipe_config))
+		return pipe_config;
+
+	clear_intel_crtc_state(pipe_config);
 
 	pipe_config->base.crtc = crtc;
 	drm_mode_copy(&pipe_config->base.adjusted_mode, mode);
@@ -10424,11 +10678,17 @@
 	 * adjust it according to limitations or connector properties, and also
 	 * a chance to reject the mode entirely.
 	 */
-	for_each_intel_encoder(dev, encoder) {
-
-		if (&encoder->new_crtc->base != crtc)
+	for (i = 0; i < state->num_connector; i++) {
+		connector = to_intel_connector(state->connectors[i]);
+		if (!connector)
 			continue;
 
+		connector_state = state->connector_states[i];
+		if (connector_state->crtc != crtc)
+			continue;
+
+		encoder = to_intel_encoder(connector_state->best_encoder);
+
 		if (!(encoder->compute_config(encoder, pipe_config))) {
 			DRM_DEBUG_KMS("Encoder config failure\n");
 			goto fail;
@@ -10464,7 +10724,6 @@
 
 	return pipe_config;
 fail:
-	kfree(pipe_config);
 	return ERR_PTR(ret);
 }
 
@@ -11143,17 +11402,30 @@
 intel_modeset_compute_config(struct drm_crtc *crtc,
 			     struct drm_display_mode *mode,
 			     struct drm_framebuffer *fb,
+			     struct drm_atomic_state *state,
 			     unsigned *modeset_pipes,
 			     unsigned *prepare_pipes,
 			     unsigned *disable_pipes)
 {
+	struct drm_device *dev = crtc->dev;
 	struct intel_crtc_state *pipe_config = NULL;
+	struct intel_crtc *intel_crtc;
+	int ret = 0;
+
+	ret = drm_atomic_add_affected_connectors(state, crtc);
+	if (ret)
+		return ERR_PTR(ret);
 
 	intel_modeset_affected_pipes(crtc, modeset_pipes,
 				     prepare_pipes, disable_pipes);
 
-	if ((*modeset_pipes) == 0)
-		goto out;
+	for_each_intel_crtc_masked(dev, *disable_pipes, intel_crtc) {
+		pipe_config = intel_atomic_get_crtc_state(state, intel_crtc);
+		if (IS_ERR(pipe_config))
+			return pipe_config;
+
+		pipe_config->base.enable = false;
+	}
 
 	/*
 	 * Note this needs changes when we start tracking multiple modes
@@ -11161,15 +11433,21 @@
 	 * (i.e. one pipe_config for each crtc) rather than just the one
 	 * for this crtc.
 	 */
-	pipe_config = intel_modeset_pipe_config(crtc, fb, mode);
-	if (IS_ERR(pipe_config)) {
-		goto out;
-	}
-	intel_dump_pipe_config(to_intel_crtc(crtc), pipe_config,
-			       "[modeset]");
+	for_each_intel_crtc_masked(dev, *modeset_pipes, intel_crtc) {
+		/* FIXME: For now we still expect modeset_pipes has at most
+		 * one bit set. */
+		if (WARN_ON(&intel_crtc->base != crtc))
+			continue;
 
-out:
-	return pipe_config;
+		pipe_config = intel_modeset_pipe_config(crtc, fb, mode, state);
+		if (IS_ERR(pipe_config))
+			return pipe_config;
+
+		intel_dump_pipe_config(to_intel_crtc(crtc), pipe_config,
+				       "[modeset]");
+	}
+
+	return intel_atomic_get_crtc_state(state, to_intel_crtc(crtc));;
 }
 
 static int __intel_set_mode_setup_plls(struct drm_device *dev,
@@ -11213,6 +11491,7 @@
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_display_mode *saved_mode;
+	struct intel_crtc_state *crtc_state_copy = NULL;
 	struct intel_crtc *intel_crtc;
 	int ret = 0;
 
@@ -11220,6 +11499,12 @@
 	if (!saved_mode)
 		return -ENOMEM;
 
+	crtc_state_copy = kmalloc(sizeof(*crtc_state_copy), GFP_KERNEL);
+	if (!crtc_state_copy) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
 	*saved_mode = crtc->mode;
 
 	if (modeset_pipes)
@@ -11277,7 +11562,7 @@
 	 * update the the output configuration. */
 	intel_modeset_update_state(dev, prepare_pipes);
 
-	modeset_update_crtc_power_domains(dev);
+	modeset_update_crtc_power_domains(pipe_config->base.state);
 
 	/* Set up the DPLL and any encoders state that needs to adjust or depend
 	 * on the DPLL.
@@ -11306,6 +11591,22 @@
 	if (ret && crtc->state->enable)
 		crtc->mode = *saved_mode;
 
+	if (ret == 0 && pipe_config) {
+		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+
+		/* The pipe_config will be freed with the atomic state, so
+		 * make a copy. */
+		memcpy(crtc_state_copy, intel_crtc->config,
+		       sizeof *crtc_state_copy);
+		intel_crtc->config = crtc_state_copy;
+		intel_crtc->base.state = &crtc_state_copy->base;
+
+		if (modeset_pipes)
+			intel_crtc->new_config = intel_crtc->config;
+	} else {
+		kfree(crtc_state_copy);
+	}
+
 	kfree(saved_mode);
 	return ret;
 }
@@ -11331,27 +11632,81 @@
 
 static int intel_set_mode(struct drm_crtc *crtc,
 			  struct drm_display_mode *mode,
-			  int x, int y, struct drm_framebuffer *fb)
+			  int x, int y, struct drm_framebuffer *fb,
+			  struct drm_atomic_state *state)
 {
 	struct intel_crtc_state *pipe_config;
 	unsigned modeset_pipes, prepare_pipes, disable_pipes;
+	int ret = 0;
 
-	pipe_config = intel_modeset_compute_config(crtc, mode, fb,
+	pipe_config = intel_modeset_compute_config(crtc, mode, fb, state,
 						   &modeset_pipes,
 						   &prepare_pipes,
 						   &disable_pipes);
 
-	if (IS_ERR(pipe_config))
-		return PTR_ERR(pipe_config);
+	if (IS_ERR(pipe_config)) {
+		ret = PTR_ERR(pipe_config);
+		goto out;
+	}
 
-	return intel_set_mode_pipes(crtc, mode, x, y, fb, pipe_config,
-				    modeset_pipes, prepare_pipes,
-				    disable_pipes);
+	ret = intel_set_mode_pipes(crtc, mode, x, y, fb, pipe_config,
+				   modeset_pipes, prepare_pipes,
+				   disable_pipes);
+	if (ret)
+		goto out;
+
+out:
+	return ret;
 }
 
 void intel_crtc_restore_mode(struct drm_crtc *crtc)
 {
-	intel_set_mode(crtc, &crtc->mode, crtc->x, crtc->y, crtc->primary->fb);
+	struct drm_device *dev = crtc->dev;
+	struct drm_atomic_state *state;
+	struct intel_encoder *encoder;
+	struct intel_connector *connector;
+	struct drm_connector_state *connector_state;
+
+	state = drm_atomic_state_alloc(dev);
+	if (!state) {
+		DRM_DEBUG_KMS("[CRTC:%d] mode restore failed, out of memory",
+			      crtc->base.id);
+		return;
+	}
+
+	state->acquire_ctx = dev->mode_config.acquire_ctx;
+
+	/* The force restore path in the HW readout code relies on the staged
+	 * config still keeping the user requested config while the actual
+	 * state has been overwritten by the configuration read from HW. We
+	 * need to copy the staged config to the atomic state, otherwise the
+	 * mode set will just reapply the state the HW is already in. */
+	for_each_intel_encoder(dev, encoder) {
+		if (&encoder->new_crtc->base != crtc)
+			continue;
+
+		for_each_intel_connector(dev, connector) {
+			if (connector->new_encoder != encoder)
+				continue;
+
+			connector_state = drm_atomic_get_connector_state(state, &connector->base);
+			if (IS_ERR(connector_state)) {
+				DRM_DEBUG_KMS("Failed to add [CONNECTOR:%d:%s] to state: %ld\n",
+					      connector->base.base.id,
+					      connector->base.name,
+					      PTR_ERR(connector_state));
+				continue;
+			}
+
+			connector_state->crtc = crtc;
+			connector_state->best_encoder = &encoder->base;
+		}
+	}
+
+	intel_set_mode(crtc, &crtc->mode, crtc->x, crtc->y, crtc->primary->fb,
+		       state);
+
+	drm_atomic_state_free(state);
 }
 
 #undef for_each_intel_crtc_masked
@@ -11520,9 +11875,11 @@
 static int
 intel_modeset_stage_output_state(struct drm_device *dev,
 				 struct drm_mode_set *set,
-				 struct intel_set_config *config)
+				 struct intel_set_config *config,
+				 struct drm_atomic_state *state)
 {
 	struct intel_connector *connector;
+	struct drm_connector_state *connector_state;
 	struct intel_encoder *encoder;
 	struct intel_crtc *crtc;
 	int ro;
@@ -11586,6 +11943,14 @@
 		}
 		connector->new_encoder->new_crtc = to_intel_crtc(new_crtc);
 
+		connector_state =
+			drm_atomic_get_connector_state(state, &connector->base);
+		if (IS_ERR(connector_state))
+			return PTR_ERR(connector_state);
+
+		connector_state->crtc = new_crtc;
+		connector_state->best_encoder = &connector->new_encoder->base;
+
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [CRTC:%d]\n",
 			connector->base.base.id,
 			connector->base.name,
@@ -11618,9 +11983,17 @@
 	}
 	/* Now we've also updated encoder->new_crtc for all encoders. */
 	for_each_intel_connector(dev, connector) {
-		if (connector->new_encoder)
+		connector_state =
+			drm_atomic_get_connector_state(state, &connector->base);
+		if (IS_ERR(connector_state))
+			return PTR_ERR(connector_state);
+
+		if (connector->new_encoder) {
 			if (connector->new_encoder != connector->encoder)
 				connector->encoder = connector->new_encoder;
+		} else {
+			connector_state->crtc = NULL;
+		}
 	}
 	for_each_intel_crtc(dev, crtc) {
 		crtc->new_enabled = false;
@@ -11676,6 +12049,7 @@
 {
 	struct drm_device *dev;
 	struct drm_mode_set save_set;
+	struct drm_atomic_state *state = NULL;
 	struct intel_set_config *config;
 	struct intel_crtc_state *pipe_config;
 	unsigned modeset_pipes, prepare_pipes, disable_pipes;
@@ -11720,12 +12094,20 @@
 	 * such cases. */
 	intel_set_config_compute_mode_changes(set, config);
 
-	ret = intel_modeset_stage_output_state(dev, set, config);
+	state = drm_atomic_state_alloc(dev);
+	if (!state) {
+		ret = -ENOMEM;
+		goto out_config;
+	}
+
+	state->acquire_ctx = dev->mode_config.acquire_ctx;
+
+	ret = intel_modeset_stage_output_state(dev, set, config, state);
 	if (ret)
 		goto fail;
 
 	pipe_config = intel_modeset_compute_config(set->crtc, set->mode,
-						   set->fb,
+						   set->fb, state,
 						   &modeset_pipes,
 						   &prepare_pipes,
 						   &disable_pipes);
@@ -11745,10 +12127,6 @@
 		 */
 	}
 
-	/* set_mode will free it in the mode_changed case */
-	if (!config->mode_changed)
-		kfree(pipe_config);
-
 	intel_update_pipe_size(to_intel_crtc(set->crtc));
 
 	if (config->mode_changed) {
@@ -11794,6 +12172,8 @@
 fail:
 		intel_set_config_restore_state(dev, config);
 
+		drm_atomic_state_clear(state);
+
 		/*
 		 * HACK: if the pipe was on, but we didn't have a framebuffer,
 		 * force the pipe off to avoid oopsing in the modeset code
@@ -11806,11 +12186,15 @@
 		/* Try to restore the config */
 		if (config->mode_changed &&
 		    intel_set_mode(save_set.crtc, save_set.mode,
-				   save_set.x, save_set.y, save_set.fb))
+				   save_set.x, save_set.y, save_set.fb,
+				   state))
 			DRM_ERROR("failed to restore config after modeset failure\n");
 	}
 
 out_config:
+	if (state)
+		drm_atomic_state_free(state);
+
 	intel_set_config_free(config);
 	return ret;
 }
@@ -11925,6 +12309,28 @@
 }
 
 /**
+ * intel_wm_need_update - Check whether watermarks need updating
+ * @plane: drm plane
+ * @state: new plane state
+ *
+ * Check current plane state versus the new one to determine whether
+ * watermarks need to be recalculated.
+ *
+ * Returns true or false.
+ */
+bool intel_wm_need_update(struct drm_plane *plane,
+			  struct drm_plane_state *state)
+{
+	/* Update watermarks on tiling changes. */
+	if (!plane->state->fb || !state->fb ||
+	    plane->state->fb->modifier[0] != state->fb->modifier[0] ||
+	    plane->state->rotation != state->rotation)
+		return true;
+
+	return false;
+}
+
+/**
  * intel_prepare_plane_fb - Prepare fb for usage on plane
  * @plane: drm plane to prepare for
  * @fb: framebuffer to prepare for presentation
@@ -11973,7 +12379,7 @@
 		if (ret)
 			DRM_DEBUG_KMS("failed to attach phys object\n");
 	} else {
-		ret = intel_pin_and_fence_fb_obj(plane, fb, NULL);
+		ret = intel_pin_and_fence_fb_obj(plane, fb, new_state, NULL);
 	}
 
 	if (ret == 0)
@@ -12005,7 +12411,7 @@
 	if (plane->type != DRM_PLANE_TYPE_CURSOR ||
 	    !INTEL_INFO(dev)->cursor_needs_physical) {
 		mutex_lock(&dev->struct_mutex);
-		intel_unpin_fb_obj(obj);
+		intel_unpin_fb_obj(fb, old_state);
 		mutex_unlock(&dev->struct_mutex);
 	}
 }
@@ -12070,10 +12476,7 @@
 
 		intel_crtc->atomic.update_fbc = true;
 
-		/* Update watermarks on tiling changes. */
-		if (!plane->state->fb || !state->base.fb ||
-		    plane->state->fb->modifier[0] !=
-		    state->base.fb->modifier[0])
+		if (intel_wm_need_update(plane, &state->base))
 			intel_crtc->atomic.update_wm = true;
 	}
 
@@ -12089,8 +12492,6 @@
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc;
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
-	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct drm_rect *src = &state->src;
 
 	crtc = crtc ? crtc : plane->crtc;
@@ -12100,8 +12501,6 @@
 	crtc->x = src->x1 >> 16;
 	crtc->y = src->y1 >> 16;
 
-	intel_plane->obj = obj;
-
 	if (intel_crtc->active) {
 		if (state->visible) {
 			/* FIXME: kill this fastboot hack */
@@ -12365,7 +12764,6 @@
 	struct drm_crtc *crtc = state->base.crtc;
 	struct drm_device *dev = plane->dev;
 	struct intel_crtc *intel_crtc;
-	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct drm_i915_gem_object *obj = intel_fb_obj(state->base.fb);
 	uint32_t addr;
 
@@ -12376,8 +12774,6 @@
 	crtc->cursor_x = state->base.crtc_x;
 	crtc->cursor_y = state->base.crtc_y;
 
-	intel_plane->obj = obj;
-
 	if (intel_crtc->cursor_bo == obj)
 		goto update;
 
@@ -12758,19 +13154,21 @@
 	 * testing/debug of the plane operations (and only when a specific
 	 * kernel module option is given), that shouldn't really matter.
 	 *
+	 * We are also relying on these states to convert the legacy mode set
+	 * to use a drm_atomic_state struct. The states are kept consistent
+	 * with actual state, so that it is safe to rely on that instead of
+	 * the staged config.
+	 *
 	 * Once atomic support for crtc's + connectors lands, this loop should
 	 * be removed since we'll be setting up real connector state, which
 	 * will contain Intel-specific properties.
 	 */
-	if (drm_core_check_feature(dev, DRIVER_ATOMIC)) {
-		list_for_each_entry(connector,
-				    &dev->mode_config.connector_list,
-				    head) {
-			if (!WARN_ON(connector->state)) {
-				connector->state =
-					kzalloc(sizeof(*connector->state),
-						GFP_KERNEL);
-			}
+	list_for_each_entry(connector,
+			    &dev->mode_config.connector_list,
+			    head) {
+		if (!WARN_ON(connector->state)) {
+			connector->state = kzalloc(sizeof(*connector->state),
+						   GFP_KERNEL);
 		}
 	}
 
@@ -12849,7 +13247,7 @@
 				  struct drm_mode_fb_cmd2 *mode_cmd,
 				  struct drm_i915_gem_object *obj)
 {
-	int aligned_height;
+	unsigned int aligned_height;
 	int ret;
 	u32 pitch_limit, stride_alignment;
 
@@ -12885,8 +13283,8 @@
 	case I915_FORMAT_MOD_X_TILED:
 		break;
 	default:
-		DRM_ERROR("Unsupported fb modifier 0x%llx!\n",
-				mode_cmd->modifier[0]);
+		DRM_DEBUG("Unsupported fb modifier 0x%llx!\n",
+			  mode_cmd->modifier[0]);
 		return -EINVAL;
 	}
 
@@ -13453,7 +13851,7 @@
 			 * If the fb is shared between multiple heads, we'll
 			 * just get the first one.
 			 */
-			intel_find_plane_obj(crtc, &crtc->plane_config);
+			intel_find_initial_plane_obj(crtc, &crtc->plane_config);
 		}
 	}
 }
@@ -13479,7 +13877,7 @@
 		return;
 
 	if (intel_get_load_detect_pipe(crt, NULL, &load_detect_temp, ctx))
-		intel_release_load_detect_pipe(crt, &load_detect_temp);
+		intel_release_load_detect_pipe(crt, &load_detect_temp, ctx);
 }
 
 static bool
@@ -13823,6 +14221,8 @@
 				       "[setup_hw_state]");
 	}
 
+	intel_modeset_update_connector_atomic_state(dev);
+
 	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
 		struct intel_shared_dpll *pll = &dev_priv->shared_dplls[i];
 
@@ -13851,8 +14251,7 @@
 			struct drm_crtc *crtc =
 				dev_priv->pipe_to_crtc_mapping[pipe];
 
-			intel_set_mode(crtc, &crtc->mode, crtc->x, crtc->y,
-				       crtc->primary->fb);
+			intel_crtc_restore_mode(crtc);
 		}
 	} else {
 		intel_modeset_update_staged_output_state(dev);
@@ -13898,6 +14297,7 @@
 
 		if (intel_pin_and_fence_fb_obj(c->primary,
 					       c->primary->fb,
+					       c->primary->state,
 					       NULL)) {
 			DRM_ERROR("failed to pin boot fb on pipe %d\n",
 				  to_intel_crtc(c)->pipe);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index ca60060..b70e635 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -85,10 +85,12 @@
 		{ .p1 = 2, .p2 = 1, .n = 1, .m1 = 2, .m2 = 0x6c00000 } }
 };
 /* Skylake supports following rates */
-static const uint32_t gen9_rates[] = { 162000, 216000, 270000, 324000,
-					432000, 540000 };
-
-static const uint32_t default_rates[] = { 162000, 270000, 540000 };
+static const int gen9_rates[] = { 162000, 216000, 270000,
+				  324000, 432000, 540000 };
+static const int chv_rates[] = { 162000, 202500, 210000, 216000,
+				 243000, 270000, 324000, 405000,
+				 420000, 432000, 540000 };
+static const int default_rates[] = { 162000, 270000, 540000 };
 
 /**
  * is_edp - is the given port attached to an eDP panel (either CPU or PCH)
@@ -123,26 +125,15 @@
 static void vlv_steal_power_sequencer(struct drm_device *dev,
 				      enum pipe pipe);
 
-int
-intel_dp_max_link_bw(struct intel_dp *intel_dp)
+static int
+intel_dp_max_link_bw(struct intel_dp  *intel_dp)
 {
 	int max_link_bw = intel_dp->dpcd[DP_MAX_LINK_RATE];
-	struct drm_device *dev = intel_dp->attached_connector->base.dev;
 
 	switch (max_link_bw) {
 	case DP_LINK_BW_1_62:
 	case DP_LINK_BW_2_7:
-		break;
-	case DP_LINK_BW_5_4: /* 1.2 capable displays may advertise higher bw */
-		if (IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0)
-			/* WaDisableHBR2:skl */
-			max_link_bw = DP_LINK_BW_2_7;
-		else if (((IS_HASWELL(dev) && !IS_HSW_ULX(dev)) ||
-		     INTEL_INFO(dev)->gen >= 8) &&
-		    intel_dp->dpcd[DP_DPCD_REV] >= 0x12)
-			max_link_bw = DP_LINK_BW_5_4;
-		else
-			max_link_bw = DP_LINK_BW_2_7;
+	case DP_LINK_BW_5_4:
 		break;
 	default:
 		WARN(1, "invalid max DP link bw val %x, using 1.62Gbps\n",
@@ -218,7 +209,7 @@
 		target_clock = fixed_mode->clock;
 	}
 
-	max_link_clock = drm_dp_bw_code_to_link_rate(intel_dp_max_link_bw(intel_dp));
+	max_link_clock = intel_dp_max_link_rate(intel_dp);
 	max_lanes = intel_dp_max_lane_count(intel_dp);
 
 	max_rate = intel_dp_max_data_rate(max_link_clock, max_lanes);
@@ -951,8 +942,9 @@
 	size_t txsize, rxsize;
 	int ret;
 
-	txbuf[0] = msg->request << 4;
-	txbuf[1] = msg->address >> 8;
+	txbuf[0] = (msg->request << 4) |
+		((msg->address >> 16) & 0xf);
+	txbuf[1] = (msg->address >> 8) & 0xff;
 	txbuf[2] = msg->address & 0xff;
 	txbuf[3] = msg->size - 1;
 
@@ -960,7 +952,7 @@
 	case DP_AUX_NATIVE_WRITE:
 	case DP_AUX_I2C_WRITE:
 		txsize = msg->size ? HEADER_SIZE + msg->size : BARE_ADDRESS_SIZE;
-		rxsize = 1;
+		rxsize = 2; /* 0 or 1 data bytes */
 
 		if (WARN_ON(txsize > 20))
 			return -E2BIG;
@@ -971,8 +963,13 @@
 		if (ret > 0) {
 			msg->reply = rxbuf[0] >> 4;
 
-			/* Return payload size. */
-			ret = msg->size;
+			if (ret > 1) {
+				/* Number of bytes written in a short write. */
+				ret = clamp_t(int, rxbuf[1], 0, msg->size);
+			} else {
+				/* Return payload size. */
+				ret = msg->size;
+			}
 		}
 		break;
 
@@ -1142,49 +1139,39 @@
 }
 
 static int
-intel_read_sink_rates(struct intel_dp *intel_dp, uint32_t *sink_rates)
+intel_dp_sink_rates(struct intel_dp *intel_dp, const int **sink_rates)
 {
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	int i = 0;
-	uint16_t val;
-
-	if (INTEL_INFO(dev)->gen >= 9 && intel_dp->supported_rates[0]) {
-		/*
-		 * Receiver supports only main-link rate selection by
-		 * link rate table method, so read link rates from
-		 * supported_link_rates
-		 */
-		for (i = 0; i < DP_MAX_SUPPORTED_RATES; ++i) {
-			val = le16_to_cpu(intel_dp->supported_rates[i]);
-			if (val == 0)
-				break;
-
-			sink_rates[i] = val * 200;
-		}
-
-		if (i <= 0)
-			DRM_ERROR("No rates in SUPPORTED_LINK_RATES");
+	if (intel_dp->num_sink_rates) {
+		*sink_rates = intel_dp->sink_rates;
+		return intel_dp->num_sink_rates;
 	}
-	return i;
+
+	*sink_rates = default_rates;
+
+	return (intel_dp_max_link_bw(intel_dp) >> 3) + 1;
 }
 
 static int
-intel_read_source_rates(struct intel_dp *intel_dp, uint32_t *source_rates)
+intel_dp_source_rates(struct drm_device *dev, const int **source_rates)
 {
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
-	int i;
-	int max_default_rate;
-
-	if (INTEL_INFO(dev)->gen >= 9 && intel_dp->supported_rates[0]) {
-		for (i = 0; i < ARRAY_SIZE(gen9_rates); ++i)
-			source_rates[i] = gen9_rates[i];
-	} else {
-		/* Index of the max_link_bw supported + 1 */
-		max_default_rate = (intel_dp_max_link_bw(intel_dp) >> 3) + 1;
-		for (i = 0; i < max_default_rate; ++i)
-			source_rates[i] = default_rates[i];
+	if (INTEL_INFO(dev)->gen >= 9) {
+		*source_rates = gen9_rates;
+		return ARRAY_SIZE(gen9_rates);
+	} else if (IS_CHERRYVIEW(dev)) {
+		*source_rates = chv_rates;
+		return ARRAY_SIZE(chv_rates);
 	}
-	return i;
+
+	*source_rates = default_rates;
+
+	if (IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0)
+		/* WaDisableHBR2:skl */
+		return (DP_LINK_BW_2_7 >> 3) + 1;
+	else if (INTEL_INFO(dev)->gen >= 8 ||
+	    (IS_HASWELL(dev) && !IS_HSW_ULX(dev)))
+		return (DP_LINK_BW_5_4 >> 3) + 1;
+	else
+		return (DP_LINK_BW_2_7 >> 3) + 1;
 }
 
 static void
@@ -1220,22 +1207,17 @@
 	}
 }
 
-static int intel_supported_rates(const uint32_t *source_rates, int source_len,
-const uint32_t *sink_rates, int sink_len, uint32_t *supported_rates)
+static int intersect_rates(const int *source_rates, int source_len,
+			   const int *sink_rates, int sink_len,
+			   int *common_rates)
 {
 	int i = 0, j = 0, k = 0;
 
-	/* For panels with edp version less than 1.4 */
-	if (sink_len == 0) {
-		for (i = 0; i < source_len; ++i)
-			supported_rates[i] = source_rates[i];
-		return source_len;
-	}
-
-	/* For edp1.4 panels, find the common rates between source and sink */
 	while (i < source_len && j < sink_len) {
 		if (source_rates[i] == sink_rates[j]) {
-			supported_rates[k] = source_rates[i];
+			if (WARN_ON(k >= DP_MAX_SUPPORTED_RATES))
+				return k;
+			common_rates[k] = source_rates[i];
 			++k;
 			++i;
 			++j;
@@ -1248,7 +1230,62 @@
 	return k;
 }
 
-static int rate_to_index(uint32_t find, const uint32_t *rates)
+static int intel_dp_common_rates(struct intel_dp *intel_dp,
+				 int *common_rates)
+{
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	const int *source_rates, *sink_rates;
+	int source_len, sink_len;
+
+	sink_len = intel_dp_sink_rates(intel_dp, &sink_rates);
+	source_len = intel_dp_source_rates(dev, &source_rates);
+
+	return intersect_rates(source_rates, source_len,
+			       sink_rates, sink_len,
+			       common_rates);
+}
+
+static void snprintf_int_array(char *str, size_t len,
+			       const int *array, int nelem)
+{
+	int i;
+
+	str[0] = '\0';
+
+	for (i = 0; i < nelem; i++) {
+		int r = snprintf(str, len, "%d,", array[i]);
+		if (r >= len)
+			return;
+		str += r;
+		len -= r;
+	}
+}
+
+static void intel_dp_print_rates(struct intel_dp *intel_dp)
+{
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	const int *source_rates, *sink_rates;
+	int source_len, sink_len, common_len;
+	int common_rates[DP_MAX_SUPPORTED_RATES];
+	char str[128]; /* FIXME: too big for stack? */
+
+	if ((drm_debug & DRM_UT_KMS) == 0)
+		return;
+
+	source_len = intel_dp_source_rates(dev, &source_rates);
+	snprintf_int_array(str, sizeof(str), source_rates, source_len);
+	DRM_DEBUG_KMS("source rates: %s\n", str);
+
+	sink_len = intel_dp_sink_rates(intel_dp, &sink_rates);
+	snprintf_int_array(str, sizeof(str), sink_rates, sink_len);
+	DRM_DEBUG_KMS("sink rates: %s\n", str);
+
+	common_len = intel_dp_common_rates(intel_dp, common_rates);
+	snprintf_int_array(str, sizeof(str), common_rates, common_len);
+	DRM_DEBUG_KMS("common rates: %s\n", str);
+}
+
+static int rate_to_index(int find, const int *rates)
 {
 	int i = 0;
 
@@ -1259,6 +1296,24 @@
 	return i;
 }
 
+int
+intel_dp_max_link_rate(struct intel_dp *intel_dp)
+{
+	int rates[DP_MAX_SUPPORTED_RATES] = {};
+	int len;
+
+	len = intel_dp_common_rates(intel_dp, rates);
+	if (WARN_ON(len <= 0))
+		return 162000;
+
+	return rates[rate_to_index(0, rates) - 1];
+}
+
+int intel_dp_rate_select(struct intel_dp *intel_dp, int rate)
+{
+	return rate_to_index(rate, intel_dp->sink_rates);
+}
+
 bool
 intel_dp_compute_config(struct intel_encoder *encoder,
 			struct intel_crtc_state *pipe_config)
@@ -1268,7 +1323,7 @@
 	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	enum port port = dp_to_dig_port(intel_dp)->port;
-	struct intel_crtc *intel_crtc = encoder->new_crtc;
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 	int lane_count, clock;
 	int min_lane_count = 1;
@@ -1278,22 +1333,15 @@
 	int max_clock;
 	int bpp, mode_rate;
 	int link_avail, link_clock;
-	uint32_t sink_rates[8];
-	uint32_t supported_rates[8] = {0};
-	uint32_t source_rates[8];
-	int source_len, sink_len, supported_len;
+	int common_rates[DP_MAX_SUPPORTED_RATES] = {};
+	int common_len;
 
-	sink_len = intel_read_sink_rates(intel_dp, sink_rates);
-
-	source_len = intel_read_source_rates(intel_dp, source_rates);
-
-	supported_len = intel_supported_rates(source_rates, source_len,
-				sink_rates, sink_len, supported_rates);
+	common_len = intel_dp_common_rates(intel_dp, common_rates);
 
 	/* No common link rates between source and sink */
-	WARN_ON(supported_len <= 0);
+	WARN_ON(common_len <= 0);
 
-	max_clock = supported_len - 1;
+	max_clock = common_len - 1;
 
 	if (HAS_PCH_SPLIT(dev) && !HAS_DDI(dev) && port != PORT_A)
 		pipe_config->has_pch_encoder = true;
@@ -1318,7 +1366,7 @@
 
 	DRM_DEBUG_KMS("DP link computation with max lane count %i "
 		      "max bw %d pixel clock %iKHz\n",
-		      max_lane_count, supported_rates[max_clock],
+		      max_lane_count, common_rates[max_clock],
 		      adjusted_mode->crtc_clock);
 
 	/* Walk through all bpp values. Luckily they're all nicely spaced with 2
@@ -1351,7 +1399,7 @@
 				lane_count <= max_lane_count;
 				lane_count <<= 1) {
 
-				link_clock = supported_rates[clock];
+				link_clock = common_rates[clock];
 				link_avail = intel_dp_max_data_rate(link_clock,
 								    lane_count);
 
@@ -1382,17 +1430,18 @@
 
 	intel_dp->lane_count = lane_count;
 
-	intel_dp->link_bw =
-		drm_dp_link_rate_to_bw_code(supported_rates[clock]);
-
-	if (INTEL_INFO(dev)->gen >= 9 && intel_dp->supported_rates[0]) {
-		intel_dp->rate_select =
-			rate_to_index(supported_rates[clock], sink_rates);
+	if (intel_dp->num_sink_rates) {
 		intel_dp->link_bw = 0;
+		intel_dp->rate_select =
+			intel_dp_rate_select(intel_dp, common_rates[clock]);
+	} else {
+		intel_dp->link_bw =
+			drm_dp_link_rate_to_bw_code(common_rates[clock]);
+		intel_dp->rate_select = 0;
 	}
 
 	pipe_config->pipe_bpp = bpp;
-	pipe_config->port_clock = supported_rates[clock];
+	pipe_config->port_clock = common_rates[clock];
 
 	DRM_DEBUG_KMS("DP link bw %02x lane count %d clock %d bpp %d\n",
 		      intel_dp->link_bw, intel_dp->lane_count,
@@ -1415,7 +1464,7 @@
 	}
 
 	if (IS_SKYLAKE(dev) && is_edp(intel_dp))
-		skl_edp_set_pll_config(pipe_config, supported_rates[clock]);
+		skl_edp_set_pll_config(pipe_config, common_rates[clock]);
 	else if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		hsw_dp_set_ddi_pll_sel(pipe_config, intel_dp->link_bw);
 	else
@@ -3502,7 +3551,7 @@
 	if (drm_dp_enhanced_frame_cap(intel_dp->dpcd))
 		link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
 	drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2);
-	if (INTEL_INFO(dev)->gen >= 9 && intel_dp->supported_rates[0])
+	if (intel_dp->num_sink_rates)
 		drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET,
 				&intel_dp->rate_select, 1);
 
@@ -3754,11 +3803,27 @@
 	    (intel_dp->dpcd[DP_EDP_CONFIGURATION_CAP] &	DP_DPCD_DISPLAY_CONTROL_CAPABLE) &&
 	    (intel_dp_dpcd_read_wake(&intel_dp->aux, DP_EDP_DPCD_REV, &rev, 1) == 1) &&
 	    (rev >= 0x03)) { /* eDp v1.4 or higher */
+		__le16 sink_rates[DP_MAX_SUPPORTED_RATES];
+		int i;
+
 		intel_dp_dpcd_read_wake(&intel_dp->aux,
 				DP_SUPPORTED_LINK_RATES,
-				intel_dp->supported_rates,
-				sizeof(intel_dp->supported_rates));
+				sink_rates,
+				sizeof(sink_rates));
+
+		for (i = 0; i < ARRAY_SIZE(sink_rates); i++) {
+			int val = le16_to_cpu(sink_rates[i]);
+
+			if (val == 0)
+				break;
+
+			intel_dp->sink_rates[i] = val * 200;
+		}
+		intel_dp->num_sink_rates = i;
 	}
+
+	intel_dp_print_rates(intel_dp);
+
 	if (!(intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] &
 	      DP_DWN_STRM_PORT_PRESENT))
 		return true; /* native DP sink */
@@ -4548,6 +4613,7 @@
 	.atomic_get_property = intel_connector_atomic_get_property,
 	.destroy = intel_dp_connector_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 };
 
 static const struct drm_connector_helper_funcs intel_dp_connector_helper_funcs = {
@@ -4934,7 +5000,7 @@
 
 	dig_port = dp_to_dig_port(intel_dp);
 	encoder = &dig_port->base;
-	intel_crtc = encoder->new_crtc;
+	intel_crtc = to_intel_crtc(encoder->base.crtc);
 
 	if (!intel_crtc) {
 		DRM_DEBUG_KMS("DRRS: intel_crtc not initialized\n");
@@ -5272,8 +5338,6 @@
 	struct edid *edid;
 	enum pipe pipe = INVALID_PIPE;
 
-	dev_priv->drrs.type = DRRS_NOT_SUPPORTED;
-
 	if (!is_edp(intel_dp))
 		return true;
 
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index be12492..5329c85 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -36,11 +36,11 @@
 	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
-	struct drm_device *dev = encoder->base.dev;
-	int bpp;
-	int lane_count, slots;
+	struct drm_atomic_state *state;
+	int bpp, i;
+	int lane_count, slots, rate;
 	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	struct intel_connector *found = NULL, *intel_connector;
+	struct intel_connector *found = NULL;
 	int mst_pbn;
 
 	pipe_config->dp_encoder_is_mst = true;
@@ -52,15 +52,30 @@
 	 * seem to suggest we should do otherwise.
 	 */
 	lane_count = drm_dp_max_lane_count(intel_dp->dpcd);
-	intel_dp->link_bw = intel_dp_max_link_bw(intel_dp);
+
+	rate = intel_dp_max_link_rate(intel_dp);
+
+	if (intel_dp->num_sink_rates) {
+		intel_dp->link_bw = 0;
+		intel_dp->rate_select = intel_dp_rate_select(intel_dp, rate);
+	} else {
+		intel_dp->link_bw = drm_dp_link_rate_to_bw_code(rate);
+		intel_dp->rate_select = 0;
+	}
+
 	intel_dp->lane_count = lane_count;
 
 	pipe_config->pipe_bpp = 24;
-	pipe_config->port_clock = drm_dp_bw_code_to_link_rate(intel_dp->link_bw);
+	pipe_config->port_clock = rate;
 
-	for_each_intel_connector(dev, intel_connector) {
-		if (intel_connector->new_encoder == encoder) {
-			found = intel_connector;
+	state = pipe_config->base.state;
+
+	for (i = 0; i < state->num_connector; i++) {
+		if (!state->connectors[i])
+			continue;
+
+		if (state->connector_states[i]->best_encoder == &encoder->base) {
+			found = to_intel_connector(state->connectors[i]);
 			break;
 		}
 	}
@@ -317,6 +332,7 @@
 	.atomic_get_property = intel_connector_atomic_get_property,
 	.destroy = intel_dp_mst_connector_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 };
 
 static int intel_dp_mst_get_modes(struct drm_connector *connector)
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index c77128c..6036e3b 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -35,6 +35,7 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_dp_mst_helper.h>
 #include <drm/drm_rect.h>
+#include <drm/drm_atomic.h>
 
 #define DIV_ROUND_CLOSEST_ULL(ll, d)	\
 ({ unsigned long long _tmp = (ll)+(d)/2; do_div(_tmp, d); _tmp; })
@@ -56,8 +57,8 @@
 				ret__ = -ETIMEDOUT;			\
 			break;						\
 		}							\
-		if (W && drm_can_sleep())  {				\
-			msleep(W);					\
+		if ((W) && drm_can_sleep()) {				\
+			usleep_range((W)*1000, (W)*2000);		\
 		} else {						\
 			cpu_relax();					\
 		}							\
@@ -501,16 +502,19 @@
 	bool enabled;
 	bool scaled;
 	u64 tiling;
+	unsigned int rotation;
 };
 
 struct intel_plane {
 	struct drm_plane base;
 	int plane;
 	enum pipe pipe;
-	struct drm_i915_gem_object *obj;
 	bool can_scale;
 	int max_downscale;
 
+	/* FIXME convert to properties */
+	struct drm_intel_sprite_colorkey ckey;
+
 	/* Since we need to change the watermarks before/after
 	 * enabling/disabling the planes, we need to store the parameters here
 	 * as the other pieces of the struct may not reflect the values we want
@@ -527,7 +531,6 @@
 	void (*update_plane)(struct drm_plane *plane,
 			     struct drm_crtc *crtc,
 			     struct drm_framebuffer *fb,
-			     struct drm_i915_gem_object *obj,
 			     int crtc_x, int crtc_y,
 			     unsigned int crtc_w, unsigned int crtc_h,
 			     uint32_t x, uint32_t y,
@@ -538,10 +541,6 @@
 			   struct intel_plane_state *state);
 	void (*commit_plane)(struct drm_plane *plane,
 			     struct intel_plane_state *state);
-	int (*update_colorkey)(struct drm_plane *plane,
-			       struct drm_intel_sprite_colorkey *key);
-	void (*get_colorkey)(struct drm_plane *plane,
-			     struct drm_intel_sprite_colorkey *key);
 };
 
 struct intel_watermark_params {
@@ -564,6 +563,7 @@
 };
 
 #define to_intel_crtc(x) container_of(x, struct intel_crtc, base)
+#define to_intel_crtc_state(x) container_of(x, struct intel_crtc_state, base)
 #define to_intel_connector(x) container_of(x, struct intel_connector, base)
 #define to_intel_encoder(x) container_of(x, struct intel_encoder, base)
 #define to_intel_framebuffer(x) container_of(x, struct intel_framebuffer, base)
@@ -627,7 +627,9 @@
 	uint8_t dpcd[DP_RECEIVER_CAP_SIZE];
 	uint8_t psr_dpcd[EDP_PSR_RECEIVER_CAP_SIZE];
 	uint8_t downstream_ports[DP_MAX_DOWNSTREAM_PORTS];
-	__le16 supported_rates[DP_MAX_SUPPORTED_RATES];
+	/* sink rates as reported by DP_SUPPORTED_LINK_RATES */
+	uint8_t num_sink_rates;
+	int sink_rates[DP_MAX_SUPPORTED_RATES];
 	struct drm_dp_aux aux;
 	uint8_t train_set[4];
 	int panel_power_up_delay;
@@ -902,9 +904,10 @@
 	intel_frontbuffer_flush(dev, frontbuffer_bits);
 }
 
-int intel_fb_align_height(struct drm_device *dev, int height,
-			  uint32_t pixel_format,
-			  uint64_t fb_format_modifier);
+unsigned int intel_fb_align_height(struct drm_device *dev,
+				   unsigned int height,
+				   uint32_t pixel_format,
+				   uint64_t fb_format_modifier);
 void intel_fb_obj_flush(struct drm_i915_gem_object *obj, bool retire);
 
 u32 intel_fb_stride_alignment(struct drm_device *dev, uint64_t fb_modifier,
@@ -956,9 +959,11 @@
 				struct intel_load_detect_pipe *old,
 				struct drm_modeset_acquire_ctx *ctx);
 void intel_release_load_detect_pipe(struct drm_connector *connector,
-				    struct intel_load_detect_pipe *old);
+				    struct intel_load_detect_pipe *old,
+				    struct drm_modeset_acquire_ctx *ctx);
 int intel_pin_and_fence_fb_obj(struct drm_plane *plane,
 			       struct drm_framebuffer *fb,
+			       const struct drm_plane_state *plane_state,
 			       struct intel_engine_cs *pipelined);
 struct drm_framebuffer *
 __intel_framebuffer_create(struct drm_device *dev,
@@ -983,6 +988,19 @@
 				    struct drm_property *property,
 				    uint64_t val);
 
+unsigned int
+intel_tile_height(struct drm_device *dev, uint32_t pixel_format,
+		  uint64_t fb_format_modifier);
+
+static inline bool
+intel_rotation_90_or_270(unsigned int rotation)
+{
+	return rotation & (BIT(DRM_ROTATE_90) | BIT(DRM_ROTATE_270));
+}
+
+bool intel_wm_need_update(struct drm_plane *plane,
+			  struct drm_plane_state *state);
+
 /* shared dpll functions */
 struct intel_shared_dpll *intel_crtc_to_shared_dpll(struct intel_crtc *crtc);
 void assert_shared_dpll(struct drm_i915_private *dev_priv,
@@ -1037,6 +1055,9 @@
 void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc);
 void intel_modeset_preclose(struct drm_device *dev, struct drm_file *file);
 
+unsigned long intel_plane_obj_offset(struct intel_plane *intel_plane,
+				     struct drm_i915_gem_object *obj);
+
 /* intel_dp.c */
 void intel_dp_init(struct drm_device *dev, int output_reg, enum port port);
 bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
@@ -1060,7 +1081,8 @@
 void intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connector);
 void intel_dp_mst_suspend(struct drm_device *dev);
 void intel_dp_mst_resume(struct drm_device *dev);
-int intel_dp_max_link_bw(struct intel_dp *intel_dp);
+int intel_dp_max_link_rate(struct intel_dp *intel_dp);
+int intel_dp_rate_select(struct intel_dp *intel_dp, int rate);
 void intel_dp_hot_plug(struct intel_encoder *intel_encoder);
 void vlv_power_sequencer_reset(struct drm_i915_private *dev_priv);
 uint32_t intel_dp_pack_aux(const uint8_t *src, int src_bytes);
@@ -1239,6 +1261,8 @@
 void intel_suspend_gt_powersave(struct drm_device *dev);
 void intel_reset_gt_powersave(struct drm_device *dev);
 void gen6_update_ring_freq(struct drm_device *dev);
+void gen6_rps_busy(struct drm_i915_private *dev_priv);
+void gen6_rps_reset_ei(struct drm_i915_private *dev_priv);
 void gen6_rps_idle(struct drm_i915_private *dev_priv);
 void gen6_rps_boost(struct drm_i915_private *dev_priv);
 void ilk_wm_get_hw_state(struct drm_device *dev);
@@ -1258,8 +1282,6 @@
 int intel_plane_restore(struct drm_plane *plane);
 int intel_sprite_set_colorkey(struct drm_device *dev, void *data,
 			      struct drm_file *file_priv);
-int intel_sprite_get_colorkey(struct drm_device *dev, void *data,
-			      struct drm_file *file_priv);
 bool intel_pipe_update_start(struct intel_crtc *crtc,
 			     uint32_t *start_vbl_count);
 void intel_pipe_update_end(struct intel_crtc *crtc, u32 start_vbl_count);
@@ -1282,6 +1304,17 @@
 struct drm_crtc_state *intel_crtc_duplicate_state(struct drm_crtc *crtc);
 void intel_crtc_destroy_state(struct drm_crtc *crtc,
 			       struct drm_crtc_state *state);
+static inline struct intel_crtc_state *
+intel_atomic_get_crtc_state(struct drm_atomic_state *state,
+			    struct intel_crtc *crtc)
+{
+	struct drm_crtc_state *crtc_state;
+	crtc_state = drm_atomic_get_crtc_state(state, &crtc->base);
+	if (IS_ERR(crtc_state))
+		return ERR_PTR(PTR_ERR(crtc_state));
+
+	return to_intel_crtc_state(crtc_state);
+}
 
 /* intel_atomic_plane.c */
 struct intel_plane_state *intel_create_plane_state(struct drm_plane *plane);
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index c8c8b24..572251e 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -975,6 +975,7 @@
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.atomic_get_property = intel_connector_atomic_get_property,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 };
 
 void intel_dsi_init(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index d857951..4ccd6c3 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -393,6 +393,7 @@
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.atomic_get_property = intel_connector_atomic_get_property,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 };
 
 static const struct drm_connector_helper_funcs intel_dvo_connector_helper_funcs = {
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index 9fcf446..4165ce0 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -521,7 +521,7 @@
 		goto out_disable;
 	}
 
-	if (!i915.enable_fbc || !i915.powersave) {
+	if (!i915.enable_fbc) {
 		if (set_no_fbc_reason(dev_priv, FBC_MODULE_PARAM))
 			DRM_DEBUG_KMS("fbc disabled per module param\n");
 		goto out_disable;
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 757c0d2..4e7e7da 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -151,7 +151,7 @@
 	}
 
 	/* Flush everything out, we'll be doing GTT only from now on */
-	ret = intel_pin_and_fence_fb_obj(NULL, fb, NULL);
+	ret = intel_pin_and_fence_fb_obj(NULL, fb, NULL, NULL);
 	if (ret) {
 		DRM_ERROR("failed to pin obj: %d\n", ret);
 		goto out_fb;
diff --git a/drivers/gpu/drm/i915/intel_frontbuffer.c b/drivers/gpu/drm/i915/intel_frontbuffer.c
index 0a1bac8..a20cffb 100644
--- a/drivers/gpu/drm/i915/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/intel_frontbuffer.c
@@ -110,9 +110,6 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum pipe pipe;
 
-	if (!i915.powersave)
-		return;
-
 	for_each_pipe(dev_priv, pipe) {
 		if (!(frontbuffer_bits & INTEL_FRONTBUFFER_ALL_MASK(pipe)))
 			continue;
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 995c5b2..cacbafd 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -951,19 +951,30 @@
 	return MODE_OK;
 }
 
-static bool hdmi_12bpc_possible(struct intel_crtc *crtc)
+static bool hdmi_12bpc_possible(struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc->base.dev;
+	struct drm_device *dev = crtc_state->base.crtc->dev;
+	struct drm_atomic_state *state;
 	struct intel_encoder *encoder;
+	struct drm_connector_state *connector_state;
 	int count = 0, count_hdmi = 0;
+	int i;
 
 	if (HAS_GMCH_DISPLAY(dev))
 		return false;
 
-	for_each_intel_encoder(dev, encoder) {
-		if (encoder->new_crtc != crtc)
+	state = crtc_state->base.state;
+
+	for (i = 0; i < state->num_connector; i++) {
+		if (!state->connectors[i])
 			continue;
 
+		connector_state = state->connector_states[i];
+		if (connector_state->crtc != crtc_state->base.crtc)
+			continue;
+
+		encoder = to_intel_encoder(connector_state->best_encoder);
+
 		count_hdmi += encoder->type == INTEL_OUTPUT_HDMI;
 		count++;
 	}
@@ -1020,7 +1031,7 @@
 	 */
 	if (pipe_config->pipe_bpp > 8*3 && pipe_config->has_hdmi_sink &&
 	    clock_12bpc <= portclock_limit &&
-	    hdmi_12bpc_possible(encoder->new_crtc)) {
+	    hdmi_12bpc_possible(pipe_config)) {
 		DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
 		desired_bpp = 12*3;
 
@@ -1618,6 +1629,7 @@
 	.atomic_get_property = intel_connector_atomic_get_property,
 	.destroy = intel_hdmi_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 };
 
 static const struct drm_connector_helper_funcs intel_hdmi_connector_helper_funcs = {
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 24e8730..06d2da3 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -286,7 +286,7 @@
 	struct intel_connector *intel_connector =
 		&lvds_encoder->attached_connector->base;
 	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	struct intel_crtc *intel_crtc = lvds_encoder->base.new_crtc;
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
 	unsigned int lvds_bpp;
 
 	/* Should never happen!! */
@@ -535,6 +535,7 @@
 	.atomic_get_property = intel_connector_atomic_get_property,
 	.destroy = intel_lvds_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 };
 
 static const struct drm_encoder_funcs intel_lvds_enc_funcs = {
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 823d1d9..dd92122 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -720,7 +720,8 @@
 	if (ret != 0)
 		return ret;
 
-	ret = i915_gem_object_pin_to_display_plane(new_bo, 0, NULL);
+	ret = i915_gem_object_pin_to_display_plane(new_bo, 0, NULL,
+						   &i915_ggtt_view_normal);
 	if (ret != 0)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 288c9d2..fa4ccb3 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2840,6 +2840,7 @@
 		}
 		p->plane[0].horiz_pixels = intel_crtc->config->pipe_src_w;
 		p->plane[0].vert_pixels = intel_crtc->config->pipe_src_h;
+		p->plane[0].rotation = crtc->primary->state->rotation;
 
 		fb = crtc->cursor->state->fb;
 		if (fb) {
@@ -2897,7 +2898,21 @@
 
 	if (p_params->tiling == I915_FORMAT_MOD_Y_TILED ||
 	    p_params->tiling == I915_FORMAT_MOD_Yf_TILED) {
-		uint32_t y_tile_minimum = plane_blocks_per_line * 4;
+		uint32_t min_scanlines = 4;
+		uint32_t y_tile_minimum;
+		if (intel_rotation_90_or_270(p_params->rotation)) {
+			switch (p_params->bytes_per_pixel) {
+			case 1:
+				min_scanlines = 16;
+				break;
+			case 2:
+				min_scanlines = 8;
+				break;
+			case 8:
+				WARN(1, "Unsupported pixel depth for rotation");
+			}
+		}
+		y_tile_minimum = plane_blocks_per_line * min_scanlines;
 		selected_result = max(method2, y_tile_minimum);
 	} else {
 		if ((ddb_allocation / plane_blocks_per_line) >= 1)
@@ -3357,6 +3372,7 @@
 	 */
 	if (fb)
 		intel_plane->wm.tiling = fb->modifier[0];
+	intel_plane->wm.rotation = plane->state->rotation;
 
 	skl_update_wm(crtc);
 }
@@ -3855,9 +3871,9 @@
 		break;
 	}
 	/* Max/min bins are special */
-	if (val == dev_priv->rps.min_freq_softlimit)
+	if (val <= dev_priv->rps.min_freq_softlimit)
 		new_power = LOW_POWER;
-	if (val == dev_priv->rps.max_freq_softlimit)
+	if (val >= dev_priv->rps.max_freq_softlimit)
 		new_power = HIGH_POWER;
 	if (new_power == dev_priv->rps.power)
 		return;
@@ -3922,11 +3938,10 @@
 	u32 mask = 0;
 
 	if (val > dev_priv->rps.min_freq_softlimit)
-		mask |= GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT;
+		mask |= GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT;
 	if (val < dev_priv->rps.max_freq_softlimit)
-		mask |= GEN6_PM_RP_UP_THRESHOLD;
+		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_UP_THRESHOLD;
 
-	mask |= dev_priv->pm_rps_events & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED);
 	mask &= dev_priv->pm_rps_events;
 
 	return gen6_sanitize_rps_pm_mask(dev_priv, ~mask);
@@ -3940,8 +3955,8 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
-	WARN_ON(val > dev_priv->rps.max_freq_softlimit);
-	WARN_ON(val < dev_priv->rps.min_freq_softlimit);
+	WARN_ON(val > dev_priv->rps.max_freq);
+	WARN_ON(val < dev_priv->rps.min_freq);
 
 	/* min/max delay may still have been modified so be sure to
 	 * write the limits value.
@@ -3979,8 +3994,8 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
-	WARN_ON(val > dev_priv->rps.max_freq_softlimit);
-	WARN_ON(val < dev_priv->rps.min_freq_softlimit);
+	WARN_ON(val > dev_priv->rps.max_freq);
+	WARN_ON(val < dev_priv->rps.min_freq);
 
 	if (WARN_ONCE(IS_CHERRYVIEW(dev) && (val & 1),
 		      "Odd GPU freq value\n"))
@@ -4007,10 +4022,11 @@
 static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = dev_priv->dev;
+	u32 val = dev_priv->rps.idle_freq;
 
 	/* CHV and latest VLV don't need to force the gfx clock */
 	if (IS_CHERRYVIEW(dev) || dev->pdev->revision >= 0xd) {
-		valleyview_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
+		valleyview_set_rps(dev_priv->dev, val);
 		return;
 	}
 
@@ -4018,7 +4034,7 @@
 	 * When we are idle.  Drop to min voltage state.
 	 */
 
-	if (dev_priv->rps.cur_freq <= dev_priv->rps.min_freq_softlimit)
+	if (dev_priv->rps.cur_freq <= val)
 		return;
 
 	/* Mask turbo interrupt so that they will not come in between */
@@ -4027,10 +4043,9 @@
 
 	vlv_force_gfx_clock(dev_priv, true);
 
-	dev_priv->rps.cur_freq = dev_priv->rps.min_freq_softlimit;
+	dev_priv->rps.cur_freq = val;
 
-	vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ,
-					dev_priv->rps.min_freq_softlimit);
+	vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
 
 	if (wait_for(((vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS))
 				& GENFREQSTATUS) == 0, 100))
@@ -4038,8 +4053,19 @@
 
 	vlv_force_gfx_clock(dev_priv, false);
 
-	I915_WRITE(GEN6_PMINTRMSK,
-		   gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq));
+	I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
+}
+
+void gen6_rps_busy(struct drm_i915_private *dev_priv)
+{
+	mutex_lock(&dev_priv->rps.hw_lock);
+	if (dev_priv->rps.enabled) {
+		if (dev_priv->pm_rps_events & (GEN6_PM_RP_DOWN_EI_EXPIRED | GEN6_PM_RP_UP_EI_EXPIRED))
+			gen6_rps_reset_ei(dev_priv);
+		I915_WRITE(GEN6_PMINTRMSK,
+			   gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq));
+	}
+	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
 void gen6_rps_idle(struct drm_i915_private *dev_priv)
@@ -4051,17 +4077,23 @@
 		if (IS_VALLEYVIEW(dev))
 			vlv_set_rps_idle(dev_priv);
 		else
-			gen6_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
+			gen6_set_rps(dev_priv->dev, dev_priv->rps.idle_freq);
 		dev_priv->rps.last_adj = 0;
+		I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
 void gen6_rps_boost(struct drm_i915_private *dev_priv)
 {
+	u32 val;
+
 	mutex_lock(&dev_priv->rps.hw_lock);
-	if (dev_priv->rps.enabled) {
-		intel_set_rps(dev_priv->dev, dev_priv->rps.max_freq_softlimit);
+	val = dev_priv->rps.max_freq_softlimit;
+	if (dev_priv->rps.enabled &&
+	    dev_priv->mm.busy &&
+	    dev_priv->rps.cur_freq < val) {
+		intel_set_rps(dev_priv->dev, val);
 		dev_priv->rps.last_adj = 0;
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
@@ -4209,6 +4241,8 @@
 					dev_priv->rps.max_freq);
 	}
 
+	dev_priv->rps.idle_freq = dev_priv->rps.min_freq;
+
 	/* Preserve min/max settings in case of re-init */
 	if (dev_priv->rps.max_freq_softlimit == 0)
 		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
@@ -4375,7 +4409,7 @@
 	/* 6: Ring frequency + overclocking (our driver does this later */
 
 	dev_priv->rps.power = HIGH_POWER; /* force a reset */
-	gen6_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
+	gen6_set_rps(dev_priv->dev, dev_priv->rps.idle_freq);
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 }
@@ -4469,7 +4503,7 @@
 	}
 
 	dev_priv->rps.power = HIGH_POWER; /* force a reset */
-	gen6_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
+	gen6_set_rps(dev_priv->dev, dev_priv->rps.idle_freq);
 
 	rc6vids = 0;
 	ret = sandybridge_pcode_read(dev_priv, GEN6_PCODE_READ_RC6VIDS, &rc6vids);
@@ -4834,6 +4868,8 @@
 			 intel_gpu_freq(dev_priv, dev_priv->rps.min_freq),
 			 dev_priv->rps.min_freq);
 
+	dev_priv->rps.idle_freq = dev_priv->rps.min_freq;
+
 	/* Preserve min/max settings in case of re-init */
 	if (dev_priv->rps.max_freq_softlimit == 0)
 		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
@@ -4909,6 +4945,8 @@
 		   dev_priv->rps.min_freq) & 1,
 		  "Odd GPU freq values\n");
 
+	dev_priv->rps.idle_freq = dev_priv->rps.min_freq;
+
 	/* Preserve min/max settings in case of re-init */
 	if (dev_priv->rps.max_freq_softlimit == 0)
 		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
@@ -5686,6 +5724,13 @@
 		gen6_enable_rps(dev);
 		__gen6_update_ring_freq(dev);
 	}
+
+	WARN_ON(dev_priv->rps.max_freq < dev_priv->rps.min_freq);
+	WARN_ON(dev_priv->rps.idle_freq > dev_priv->rps.max_freq);
+
+	WARN_ON(dev_priv->rps.efficient_freq < dev_priv->rps.min_freq);
+	WARN_ON(dev_priv->rps.efficient_freq > dev_priv->rps.max_freq);
+
 	dev_priv->rps.enabled = true;
 
 	gen6_enable_rps_interrupts(dev);
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index b9f40c2..a8f9348 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -532,8 +532,6 @@
 		WARN_ON(!(val & EDP_PSR_ENABLE));
 
 		I915_WRITE(EDP_PSR_CTL(dev), val & ~EDP_PSR_ENABLE);
-
-		dev_priv->psr.active = false;
 	} else {
 		val = I915_READ(VLV_PSRCTL(pipe));
 
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 9e554c2..f5b7e1e 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -2194,6 +2194,7 @@
 	.atomic_get_property = intel_connector_atomic_get_property,
 	.destroy = intel_sdvo_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 };
 
 static const struct drm_connector_helper_funcs intel_sdvo_connector_helper_funcs = {
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index a828736..e9ff6fc 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -179,7 +179,7 @@
 static void
 skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc,
 		 struct drm_framebuffer *fb,
-		 struct drm_i915_gem_object *obj, int crtc_x, int crtc_y,
+		 int crtc_x, int crtc_y,
 		 unsigned int crtc_w, unsigned int crtc_h,
 		 uint32_t x, uint32_t y,
 		 uint32_t src_w, uint32_t src_h)
@@ -187,23 +187,16 @@
 	struct drm_device *dev = drm_plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(drm_plane);
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	const int pipe = intel_plane->pipe;
 	const int plane = intel_plane->plane + 1;
 	u32 plane_ctl, stride_div;
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+	const struct drm_intel_sprite_colorkey *key = &intel_plane->ckey;
+	unsigned long surf_addr;
 
-	plane_ctl = I915_READ(PLANE_CTL(pipe, plane));
-
-	/* Mask out pixel format bits in case we change it */
-	plane_ctl &= ~PLANE_CTL_FORMAT_MASK;
-	plane_ctl &= ~PLANE_CTL_ORDER_RGBX;
-	plane_ctl &= ~PLANE_CTL_YUV422_ORDER_MASK;
-	plane_ctl &= ~PLANE_CTL_TILED_MASK;
-	plane_ctl &= ~PLANE_CTL_ALPHA_MASK;
-	plane_ctl &= ~PLANE_CTL_ROTATE_MASK;
-
-	/* Trickle feed has to be enabled */
-	plane_ctl &= ~PLANE_CTL_TRICKLE_FEED_DISABLE;
+	plane_ctl = PLANE_CTL_ENABLE |
+		PLANE_CTL_PIPE_CSC_ENABLE;
 
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_RGB565:
@@ -264,9 +257,6 @@
 	if (drm_plane->state->rotation == BIT(DRM_ROTATE_180))
 		plane_ctl |= PLANE_CTL_ROTATE_180;
 
-	plane_ctl |= PLANE_CTL_ENABLE;
-	plane_ctl |= PLANE_CTL_PIPE_CSC_ENABLE;
-
 	intel_update_sprite_watermarks(drm_plane, crtc, src_w, src_h,
 				       pixel_size, true,
 				       src_w != crtc_w || src_h != crtc_h);
@@ -280,12 +270,25 @@
 	crtc_w--;
 	crtc_h--;
 
+	if (key->flags) {
+		I915_WRITE(PLANE_KEYVAL(pipe, plane), key->min_value);
+		I915_WRITE(PLANE_KEYMAX(pipe, plane), key->max_value);
+		I915_WRITE(PLANE_KEYMSK(pipe, plane), key->channel_mask);
+	}
+
+	if (key->flags & I915_SET_COLORKEY_DESTINATION)
+		plane_ctl |= PLANE_CTL_KEY_ENABLE_DESTINATION;
+	else if (key->flags & I915_SET_COLORKEY_SOURCE)
+		plane_ctl |= PLANE_CTL_KEY_ENABLE_SOURCE;
+
+	surf_addr = intel_plane_obj_offset(intel_plane, obj);
+
 	I915_WRITE(PLANE_OFFSET(pipe, plane), (y << 16) | x);
 	I915_WRITE(PLANE_STRIDE(pipe, plane), fb->pitches[0] / stride_div);
 	I915_WRITE(PLANE_POS(pipe, plane), (crtc_y << 16) | crtc_x);
 	I915_WRITE(PLANE_SIZE(pipe, plane), (crtc_h << 16) | crtc_w);
 	I915_WRITE(PLANE_CTL(pipe, plane), plane_ctl);
-	I915_WRITE(PLANE_SURF(pipe, plane), i915_gem_obj_ggtt_offset(obj));
+	I915_WRITE(PLANE_SURF(pipe, plane), surf_addr);
 	POSTING_READ(PLANE_SURF(pipe, plane));
 }
 
@@ -298,73 +301,15 @@
 	const int pipe = intel_plane->pipe;
 	const int plane = intel_plane->plane + 1;
 
-	I915_WRITE(PLANE_CTL(pipe, plane),
-		   I915_READ(PLANE_CTL(pipe, plane)) & ~PLANE_CTL_ENABLE);
+	I915_WRITE(PLANE_CTL(pipe, plane), 0);
 
 	/* Activate double buffered register update */
-	I915_WRITE(PLANE_CTL(pipe, plane), 0);
-	POSTING_READ(PLANE_CTL(pipe, plane));
+	I915_WRITE(PLANE_SURF(pipe, plane), 0);
+	POSTING_READ(PLANE_SURF(pipe, plane));
 
 	intel_update_sprite_watermarks(drm_plane, crtc, 0, 0, 0, false, false);
 }
 
-static int
-skl_update_colorkey(struct drm_plane *drm_plane,
-		    struct drm_intel_sprite_colorkey *key)
-{
-	struct drm_device *dev = drm_plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_plane *intel_plane = to_intel_plane(drm_plane);
-	const int pipe = intel_plane->pipe;
-	const int plane = intel_plane->plane;
-	u32 plane_ctl;
-
-	I915_WRITE(PLANE_KEYVAL(pipe, plane), key->min_value);
-	I915_WRITE(PLANE_KEYMAX(pipe, plane), key->max_value);
-	I915_WRITE(PLANE_KEYMSK(pipe, plane), key->channel_mask);
-
-	plane_ctl = I915_READ(PLANE_CTL(pipe, plane));
-	plane_ctl &= ~PLANE_CTL_KEY_ENABLE_MASK;
-	if (key->flags & I915_SET_COLORKEY_DESTINATION)
-		plane_ctl |= PLANE_CTL_KEY_ENABLE_DESTINATION;
-	else if (key->flags & I915_SET_COLORKEY_SOURCE)
-		plane_ctl |= PLANE_CTL_KEY_ENABLE_SOURCE;
-	I915_WRITE(PLANE_CTL(pipe, plane), plane_ctl);
-
-	POSTING_READ(PLANE_CTL(pipe, plane));
-
-	return 0;
-}
-
-static void
-skl_get_colorkey(struct drm_plane *drm_plane,
-		 struct drm_intel_sprite_colorkey *key)
-{
-	struct drm_device *dev = drm_plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_plane *intel_plane = to_intel_plane(drm_plane);
-	const int pipe = intel_plane->pipe;
-	const int plane = intel_plane->plane;
-	u32 plane_ctl;
-
-	key->min_value = I915_READ(PLANE_KEYVAL(pipe, plane));
-	key->max_value = I915_READ(PLANE_KEYMAX(pipe, plane));
-	key->channel_mask = I915_READ(PLANE_KEYMSK(pipe, plane));
-
-	plane_ctl = I915_READ(PLANE_CTL(pipe, plane));
-
-	switch (plane_ctl & PLANE_CTL_KEY_ENABLE_MASK) {
-	case PLANE_CTL_KEY_ENABLE_DESTINATION:
-		key->flags = I915_SET_COLORKEY_DESTINATION;
-		break;
-	case PLANE_CTL_KEY_ENABLE_SOURCE:
-		key->flags = I915_SET_COLORKEY_SOURCE;
-		break;
-	default:
-		key->flags = I915_SET_COLORKEY_NONE;
-	}
-}
-
 static void
 chv_update_csc(struct intel_plane *intel_plane, uint32_t format)
 {
@@ -407,7 +352,7 @@
 static void
 vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 		 struct drm_framebuffer *fb,
-		 struct drm_i915_gem_object *obj, int crtc_x, int crtc_y,
+		 int crtc_x, int crtc_y,
 		 unsigned int crtc_w, unsigned int crtc_h,
 		 uint32_t x, uint32_t y,
 		 uint32_t src_w, uint32_t src_h)
@@ -416,19 +361,15 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(dplane);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	int pipe = intel_plane->pipe;
 	int plane = intel_plane->plane;
 	u32 sprctl;
 	unsigned long sprsurf_offset, linear_offset;
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+	const struct drm_intel_sprite_colorkey *key = &intel_plane->ckey;
 
-	sprctl = I915_READ(SPCNTR(pipe, plane));
-
-	/* Mask out pixel format bits in case we change it */
-	sprctl &= ~SP_PIXFORMAT_MASK;
-	sprctl &= ~SP_YUV_BYTE_ORDER_MASK;
-	sprctl &= ~SP_TILED;
-	sprctl &= ~SP_ROTATE_180;
+	sprctl = SP_ENABLE;
 
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_YUYV:
@@ -482,8 +423,6 @@
 	if (obj->tiling_mode != I915_TILING_NONE)
 		sprctl |= SP_TILED;
 
-	sprctl |= SP_ENABLE;
-
 	intel_update_sprite_watermarks(dplane, crtc, src_w, src_h,
 				       pixel_size, true,
 				       src_w != crtc_w || src_h != crtc_h);
@@ -511,6 +450,15 @@
 
 	intel_update_primary_plane(intel_crtc);
 
+	if (key->flags) {
+		I915_WRITE(SPKEYMINVAL(pipe, plane), key->min_value);
+		I915_WRITE(SPKEYMAXVAL(pipe, plane), key->max_value);
+		I915_WRITE(SPKEYMSK(pipe, plane), key->channel_mask);
+	}
+
+	if (key->flags & I915_SET_COLORKEY_SOURCE)
+		sprctl |= SP_SOURCE_KEY;
+
 	if (IS_CHERRYVIEW(dev) && pipe == PIPE_B)
 		chv_update_csc(intel_plane, fb->pixel_format);
 
@@ -544,8 +492,8 @@
 
 	intel_update_primary_plane(intel_crtc);
 
-	I915_WRITE(SPCNTR(pipe, plane), I915_READ(SPCNTR(pipe, plane)) &
-		   ~SP_ENABLE);
+	I915_WRITE(SPCNTR(pipe, plane), 0);
+
 	/* Activate double buffered register update */
 	I915_WRITE(SPSURF(pipe, plane), 0);
 
@@ -554,61 +502,11 @@
 	intel_update_sprite_watermarks(dplane, crtc, 0, 0, 0, false, false);
 }
 
-static int
-vlv_update_colorkey(struct drm_plane *dplane,
-		    struct drm_intel_sprite_colorkey *key)
-{
-	struct drm_device *dev = dplane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_plane *intel_plane = to_intel_plane(dplane);
-	int pipe = intel_plane->pipe;
-	int plane = intel_plane->plane;
-	u32 sprctl;
-
-	if (key->flags & I915_SET_COLORKEY_DESTINATION)
-		return -EINVAL;
-
-	I915_WRITE(SPKEYMINVAL(pipe, plane), key->min_value);
-	I915_WRITE(SPKEYMAXVAL(pipe, plane), key->max_value);
-	I915_WRITE(SPKEYMSK(pipe, plane), key->channel_mask);
-
-	sprctl = I915_READ(SPCNTR(pipe, plane));
-	sprctl &= ~SP_SOURCE_KEY;
-	if (key->flags & I915_SET_COLORKEY_SOURCE)
-		sprctl |= SP_SOURCE_KEY;
-	I915_WRITE(SPCNTR(pipe, plane), sprctl);
-
-	POSTING_READ(SPKEYMSK(pipe, plane));
-
-	return 0;
-}
-
-static void
-vlv_get_colorkey(struct drm_plane *dplane,
-		 struct drm_intel_sprite_colorkey *key)
-{
-	struct drm_device *dev = dplane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_plane *intel_plane = to_intel_plane(dplane);
-	int pipe = intel_plane->pipe;
-	int plane = intel_plane->plane;
-	u32 sprctl;
-
-	key->min_value = I915_READ(SPKEYMINVAL(pipe, plane));
-	key->max_value = I915_READ(SPKEYMAXVAL(pipe, plane));
-	key->channel_mask = I915_READ(SPKEYMSK(pipe, plane));
-
-	sprctl = I915_READ(SPCNTR(pipe, plane));
-	if (sprctl & SP_SOURCE_KEY)
-		key->flags = I915_SET_COLORKEY_SOURCE;
-	else
-		key->flags = I915_SET_COLORKEY_NONE;
-}
 
 static void
 ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		 struct drm_framebuffer *fb,
-		 struct drm_i915_gem_object *obj, int crtc_x, int crtc_y,
+		 int crtc_x, int crtc_y,
 		 unsigned int crtc_w, unsigned int crtc_h,
 		 uint32_t x, uint32_t y,
 		 uint32_t src_w, uint32_t src_h)
@@ -617,19 +515,14 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_plane->pipe;
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
+	enum pipe pipe = intel_plane->pipe;
 	u32 sprctl, sprscale = 0;
 	unsigned long sprsurf_offset, linear_offset;
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+	const struct drm_intel_sprite_colorkey *key = &intel_plane->ckey;
 
-	sprctl = I915_READ(SPRCTL(pipe));
-
-	/* Mask out pixel format bits in case we change it */
-	sprctl &= ~SPRITE_PIXFORMAT_MASK;
-	sprctl &= ~SPRITE_RGB_ORDER_RGBX;
-	sprctl &= ~SPRITE_YUV_BYTE_ORDER_MASK;
-	sprctl &= ~SPRITE_TILED;
-	sprctl &= ~SPRITE_ROTATE_180;
+	sprctl = SPRITE_ENABLE;
 
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_XBGR8888:
@@ -668,8 +561,6 @@
 	else
 		sprctl |= SPRITE_TRICKLE_FEED_DISABLE;
 
-	sprctl |= SPRITE_ENABLE;
-
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		sprctl |= SPRITE_PIPE_CSC_ENABLE;
 
@@ -706,6 +597,17 @@
 
 	intel_update_primary_plane(intel_crtc);
 
+	if (key->flags) {
+		I915_WRITE(SPRKEYVAL(pipe), key->min_value);
+		I915_WRITE(SPRKEYMAX(pipe), key->max_value);
+		I915_WRITE(SPRKEYMSK(pipe), key->channel_mask);
+	}
+
+	if (key->flags & I915_SET_COLORKEY_DESTINATION)
+		sprctl |= SPRITE_DEST_KEY;
+	else if (key->flags & I915_SET_COLORKEY_SOURCE)
+		sprctl |= SPRITE_SOURCE_KEY;
+
 	I915_WRITE(SPRSTRIDE(pipe), fb->pitches[0]);
 	I915_WRITE(SPRPOS(pipe), (crtc_y << 16) | crtc_x);
 
@@ -747,73 +649,12 @@
 	I915_WRITE(SPRSURF(pipe), 0);
 
 	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
-
-	/*
-	 * Avoid underruns when disabling the sprite.
-	 * FIXME remove once watermark updates are done properly.
-	 */
-	intel_crtc->atomic.wait_vblank = true;
-	intel_crtc->atomic.update_sprite_watermarks |= (1 << drm_plane_index(plane));
-}
-
-static int
-ivb_update_colorkey(struct drm_plane *plane,
-		    struct drm_intel_sprite_colorkey *key)
-{
-	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_plane *intel_plane;
-	u32 sprctl;
-	int ret = 0;
-
-	intel_plane = to_intel_plane(plane);
-
-	I915_WRITE(SPRKEYVAL(intel_plane->pipe), key->min_value);
-	I915_WRITE(SPRKEYMAX(intel_plane->pipe), key->max_value);
-	I915_WRITE(SPRKEYMSK(intel_plane->pipe), key->channel_mask);
-
-	sprctl = I915_READ(SPRCTL(intel_plane->pipe));
-	sprctl &= ~(SPRITE_SOURCE_KEY | SPRITE_DEST_KEY);
-	if (key->flags & I915_SET_COLORKEY_DESTINATION)
-		sprctl |= SPRITE_DEST_KEY;
-	else if (key->flags & I915_SET_COLORKEY_SOURCE)
-		sprctl |= SPRITE_SOURCE_KEY;
-	I915_WRITE(SPRCTL(intel_plane->pipe), sprctl);
-
-	POSTING_READ(SPRKEYMSK(intel_plane->pipe));
-
-	return ret;
-}
-
-static void
-ivb_get_colorkey(struct drm_plane *plane, struct drm_intel_sprite_colorkey *key)
-{
-	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_plane *intel_plane;
-	u32 sprctl;
-
-	intel_plane = to_intel_plane(plane);
-
-	key->min_value = I915_READ(SPRKEYVAL(intel_plane->pipe));
-	key->max_value = I915_READ(SPRKEYMAX(intel_plane->pipe));
-	key->channel_mask = I915_READ(SPRKEYMSK(intel_plane->pipe));
-	key->flags = 0;
-
-	sprctl = I915_READ(SPRCTL(intel_plane->pipe));
-
-	if (sprctl & SPRITE_DEST_KEY)
-		key->flags = I915_SET_COLORKEY_DESTINATION;
-	else if (sprctl & SPRITE_SOURCE_KEY)
-		key->flags = I915_SET_COLORKEY_SOURCE;
-	else
-		key->flags = I915_SET_COLORKEY_NONE;
 }
 
 static void
 ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		 struct drm_framebuffer *fb,
-		 struct drm_i915_gem_object *obj, int crtc_x, int crtc_y,
+		 int crtc_x, int crtc_y,
 		 unsigned int crtc_w, unsigned int crtc_h,
 		 uint32_t x, uint32_t y,
 		 uint32_t src_w, uint32_t src_h)
@@ -822,19 +663,14 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	int pipe = intel_plane->pipe;
 	unsigned long dvssurf_offset, linear_offset;
 	u32 dvscntr, dvsscale;
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+	const struct drm_intel_sprite_colorkey *key = &intel_plane->ckey;
 
-	dvscntr = I915_READ(DVSCNTR(pipe));
-
-	/* Mask out pixel format bits in case we change it */
-	dvscntr &= ~DVS_PIXFORMAT_MASK;
-	dvscntr &= ~DVS_RGB_ORDER_XBGR;
-	dvscntr &= ~DVS_YUV_BYTE_ORDER_MASK;
-	dvscntr &= ~DVS_TILED;
-	dvscntr &= ~DVS_ROTATE_180;
+	dvscntr = DVS_ENABLE;
 
 	switch (fb->pixel_format) {
 	case DRM_FORMAT_XBGR8888:
@@ -870,7 +706,6 @@
 
 	if (IS_GEN6(dev))
 		dvscntr |= DVS_TRICKLE_FEED_DISABLE; /* must disable */
-	dvscntr |= DVS_ENABLE;
 
 	intel_update_sprite_watermarks(plane, crtc, src_w, src_h,
 				       pixel_size, true,
@@ -902,6 +737,17 @@
 
 	intel_update_primary_plane(intel_crtc);
 
+	if (key->flags) {
+		I915_WRITE(DVSKEYVAL(pipe), key->min_value);
+		I915_WRITE(DVSKEYMAX(pipe), key->max_value);
+		I915_WRITE(DVSKEYMSK(pipe), key->channel_mask);
+	}
+
+	if (key->flags & I915_SET_COLORKEY_DESTINATION)
+		dvscntr |= DVS_DEST_KEY;
+	else if (key->flags & I915_SET_COLORKEY_SOURCE)
+		dvscntr |= DVS_SOURCE_KEY;
+
 	I915_WRITE(DVSSTRIDE(pipe), fb->pitches[0]);
 	I915_WRITE(DVSPOS(pipe), (crtc_y << 16) | crtc_x);
 
@@ -930,20 +776,14 @@
 
 	intel_update_primary_plane(intel_crtc);
 
-	I915_WRITE(DVSCNTR(pipe), I915_READ(DVSCNTR(pipe)) & ~DVS_ENABLE);
+	I915_WRITE(DVSCNTR(pipe), 0);
 	/* Disable the scaler */
 	I915_WRITE(DVSSCALE(pipe), 0);
+
 	/* Flush double buffered register updates */
 	I915_WRITE(DVSSURF(pipe), 0);
 
 	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
-
-	/*
-	 * Avoid underruns when disabling the sprite.
-	 * FIXME remove once watermark updates are done properly.
-	 */
-	intel_crtc->atomic.wait_vblank = true;
-	intel_crtc->atomic.update_sprite_watermarks |= (1 << drm_plane_index(plane));
 }
 
 /**
@@ -1014,67 +854,9 @@
 	hsw_disable_ips(intel_crtc);
 }
 
-static int
-ilk_update_colorkey(struct drm_plane *plane,
-		    struct drm_intel_sprite_colorkey *key)
-{
-	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_plane *intel_plane;
-	u32 dvscntr;
-	int ret = 0;
-
-	intel_plane = to_intel_plane(plane);
-
-	I915_WRITE(DVSKEYVAL(intel_plane->pipe), key->min_value);
-	I915_WRITE(DVSKEYMAX(intel_plane->pipe), key->max_value);
-	I915_WRITE(DVSKEYMSK(intel_plane->pipe), key->channel_mask);
-
-	dvscntr = I915_READ(DVSCNTR(intel_plane->pipe));
-	dvscntr &= ~(DVS_SOURCE_KEY | DVS_DEST_KEY);
-	if (key->flags & I915_SET_COLORKEY_DESTINATION)
-		dvscntr |= DVS_DEST_KEY;
-	else if (key->flags & I915_SET_COLORKEY_SOURCE)
-		dvscntr |= DVS_SOURCE_KEY;
-	I915_WRITE(DVSCNTR(intel_plane->pipe), dvscntr);
-
-	POSTING_READ(DVSKEYMSK(intel_plane->pipe));
-
-	return ret;
-}
-
-static void
-ilk_get_colorkey(struct drm_plane *plane, struct drm_intel_sprite_colorkey *key)
-{
-	struct drm_device *dev = plane->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_plane *intel_plane;
-	u32 dvscntr;
-
-	intel_plane = to_intel_plane(plane);
-
-	key->min_value = I915_READ(DVSKEYVAL(intel_plane->pipe));
-	key->max_value = I915_READ(DVSKEYMAX(intel_plane->pipe));
-	key->channel_mask = I915_READ(DVSKEYMSK(intel_plane->pipe));
-	key->flags = 0;
-
-	dvscntr = I915_READ(DVSCNTR(intel_plane->pipe));
-
-	if (dvscntr & DVS_DEST_KEY)
-		key->flags = I915_SET_COLORKEY_DESTINATION;
-	else if (dvscntr & DVS_SOURCE_KEY)
-		key->flags = I915_SET_COLORKEY_SOURCE;
-	else
-		key->flags = I915_SET_COLORKEY_NONE;
-}
-
 static bool colorkey_enabled(struct intel_plane *intel_plane)
 {
-	struct drm_intel_sprite_colorkey key;
-
-	intel_plane->get_colorkey(&intel_plane->base, &key);
-
-	return key.flags != I915_SET_COLORKEY_NONE;
+	return intel_plane->ckey.flags != I915_SET_COLORKEY_NONE;
 }
 
 static int
@@ -1257,11 +1039,18 @@
 		if (!intel_crtc->primary_enabled && !state->hides_primary)
 			intel_crtc->atomic.post_enable_primary = true;
 
-		/* Update watermarks on tiling changes. */
-		if (!plane->state->fb || !state->base.fb ||
-		    plane->state->fb->modifier[0] !=
-		    state->base.fb->modifier[0])
+		if (intel_wm_need_update(plane, &state->base))
 			intel_crtc->atomic.update_wm = true;
+
+		if (!state->visible) {
+			/*
+			 * Avoid underruns when disabling the sprite.
+			 * FIXME remove once watermark updates are done properly.
+			 */
+			intel_crtc->atomic.wait_vblank = true;
+			intel_crtc->atomic.update_sprite_watermarks |=
+				(1 << drm_plane_index(plane));
+		}
 	}
 
 	return 0;
@@ -1275,7 +1064,6 @@
 	struct intel_crtc *intel_crtc;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct drm_framebuffer *fb = state->base.fb;
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	int crtc_x, crtc_y;
 	unsigned int crtc_w, crtc_h;
 	uint32_t src_x, src_y, src_w, src_h;
@@ -1283,8 +1071,7 @@
 	crtc = crtc ? crtc : plane->crtc;
 	intel_crtc = to_intel_crtc(crtc);
 
-	plane->fb = state->base.fb;
-	intel_plane->obj = obj;
+	plane->fb = fb;
 
 	if (intel_crtc->active) {
 		intel_crtc->primary_enabled = !state->hides_primary;
@@ -1298,7 +1085,7 @@
 			src_y = state->src.y1;
 			src_w = drm_rect_width(&state->src);
 			src_h = drm_rect_height(&state->src);
-			intel_plane->update_plane(plane, crtc, fb, obj,
+			intel_plane->update_plane(plane, crtc, fb,
 						  crtc_x, crtc_y, crtc_w, crtc_h,
 						  src_x, src_y, src_w, src_h);
 		} else {
@@ -1319,6 +1106,10 @@
 	if ((set->flags & (I915_SET_COLORKEY_DESTINATION | I915_SET_COLORKEY_SOURCE)) == (I915_SET_COLORKEY_DESTINATION | I915_SET_COLORKEY_SOURCE))
 		return -EINVAL;
 
+	if (IS_VALLEYVIEW(dev) &&
+	    set->flags & I915_SET_COLORKEY_DESTINATION)
+		return -EINVAL;
+
 	drm_modeset_lock_all(dev);
 
 	plane = drm_plane_find(dev, set->plane_id);
@@ -1328,31 +1119,15 @@
 	}
 
 	intel_plane = to_intel_plane(plane);
-	ret = intel_plane->update_colorkey(plane, set);
+	intel_plane->ckey = *set;
 
-out_unlock:
-	drm_modeset_unlock_all(dev);
-	return ret;
-}
-
-int intel_sprite_get_colorkey(struct drm_device *dev, void *data,
-			      struct drm_file *file_priv)
-{
-	struct drm_intel_sprite_colorkey *get = data;
-	struct drm_plane *plane;
-	struct intel_plane *intel_plane;
-	int ret = 0;
-
-	drm_modeset_lock_all(dev);
-
-	plane = drm_plane_find(dev, get->plane_id);
-	if (!plane) {
-		ret = -ENOENT;
-		goto out_unlock;
-	}
-
-	intel_plane = to_intel_plane(plane);
-	intel_plane->get_colorkey(plane, get);
+	/*
+	 * The only way this could fail would be due to
+	 * the current plane state being unsupportable already,
+	 * and we dont't consider that an error for the
+	 * colorkey ioctl. So just ignore any error.
+	 */
+	intel_plane_restore(plane);
 
 out_unlock:
 	drm_modeset_unlock_all(dev);
@@ -1445,8 +1220,6 @@
 		intel_plane->max_downscale = 16;
 		intel_plane->update_plane = ilk_update_plane;
 		intel_plane->disable_plane = ilk_disable_plane;
-		intel_plane->update_colorkey = ilk_update_colorkey;
-		intel_plane->get_colorkey = ilk_get_colorkey;
 
 		if (IS_GEN6(dev)) {
 			plane_formats = snb_plane_formats;
@@ -1470,16 +1243,12 @@
 		if (IS_VALLEYVIEW(dev)) {
 			intel_plane->update_plane = vlv_update_plane;
 			intel_plane->disable_plane = vlv_disable_plane;
-			intel_plane->update_colorkey = vlv_update_colorkey;
-			intel_plane->get_colorkey = vlv_get_colorkey;
 
 			plane_formats = vlv_plane_formats;
 			num_plane_formats = ARRAY_SIZE(vlv_plane_formats);
 		} else {
 			intel_plane->update_plane = ivb_update_plane;
 			intel_plane->disable_plane = ivb_disable_plane;
-			intel_plane->update_colorkey = ivb_update_colorkey;
-			intel_plane->get_colorkey = ivb_get_colorkey;
 
 			plane_formats = snb_plane_formats;
 			num_plane_formats = ARRAY_SIZE(snb_plane_formats);
@@ -1494,8 +1263,6 @@
 		intel_plane->max_downscale = 1;
 		intel_plane->update_plane = skl_update_plane;
 		intel_plane->disable_plane = skl_disable_plane;
-		intel_plane->update_colorkey = skl_update_colorkey;
-		intel_plane->get_colorkey = skl_get_colorkey;
 
 		plane_formats = skl_plane_formats;
 		num_plane_formats = ARRAY_SIZE(skl_plane_formats);
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 892d23c..bc1d9d7 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1332,7 +1332,7 @@
 
 		if (intel_get_load_detect_pipe(connector, &mode, &tmp, &ctx)) {
 			type = intel_tv_detect_type(intel_tv, connector);
-			intel_release_load_detect_pipe(connector, &tmp);
+			intel_release_load_detect_pipe(connector, &tmp, &ctx);
 			status = type < 0 ?
 				connector_status_disconnected :
 				connector_status_connected;
@@ -1516,6 +1516,7 @@
 	.atomic_get_property = intel_connector_atomic_get_property,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
 };
 
 static const struct drm_connector_helper_funcs intel_tv_connector_helper_funcs = {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 29bd539..6efa8f3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -340,11 +340,13 @@
 
 		/* switch mmio to cpu's native endianness */
 #ifndef __BIG_ENDIAN
-		if (ioread32_native(map + 0x000004) != 0x00000000)
+		if (ioread32_native(map + 0x000004) != 0x00000000) {
 #else
-		if (ioread32_native(map + 0x000004) == 0x00000000)
+		if (ioread32_native(map + 0x000004) == 0x00000000) {
 #endif
 			iowrite32_native(0x01000001, map + 0x000004);
+			ioread32_native(map);
+		}
 
 		/* read boot0 and strapping information */
 		boot0 = ioread32_native(map + 0x000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c
index 539561e..108d048 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/gm100.c
@@ -142,6 +142,49 @@
 		device->oclass[NVDEV_ENGINE_MSPPP  ] = &gf100_msppp_oclass;
 #endif
 		break;
+	case 0x126:
+		device->cname = "GM206";
+		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nvkm_bios_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  gk104_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  gm204_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_FUSE   ] = &gm107_fuse_oclass;
+#if 0
+		/* looks to be some non-trivial changes */
+		device->oclass[NVDEV_SUBDEV_CLK    ] = &gk104_clk_oclass;
+		/* priv ring says no to 0x10eb14 writes */
+		device->oclass[NVDEV_SUBDEV_THERM  ] = &gm107_therm_oclass;
+#endif
+		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
+		device->oclass[NVDEV_SUBDEV_DEVINIT] =  gm204_devinit_oclass;
+		device->oclass[NVDEV_SUBDEV_MC     ] =  gk20a_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_BUS    ] =  gf100_bus_oclass;
+		device->oclass[NVDEV_SUBDEV_TIMER  ] = &gk20a_timer_oclass;
+		device->oclass[NVDEV_SUBDEV_FB     ] =  gm107_fb_oclass;
+		device->oclass[NVDEV_SUBDEV_LTC    ] =  gm107_ltc_oclass;
+		device->oclass[NVDEV_SUBDEV_IBUS   ] = &gk104_ibus_oclass;
+		device->oclass[NVDEV_SUBDEV_INSTMEM] =  nv50_instmem_oclass;
+		device->oclass[NVDEV_SUBDEV_MMU    ] = &gf100_mmu_oclass;
+		device->oclass[NVDEV_SUBDEV_BAR    ] = &gf100_bar_oclass;
+		device->oclass[NVDEV_SUBDEV_PMU    ] =  gk208_pmu_oclass;
+#if 0
+		device->oclass[NVDEV_SUBDEV_VOLT   ] = &nv40_volt_oclass;
+#endif
+		device->oclass[NVDEV_ENGINE_DMAOBJ ] =  gf110_dmaeng_oclass;
+#if 0
+		device->oclass[NVDEV_ENGINE_FIFO   ] =  gk208_fifo_oclass;
+		device->oclass[NVDEV_ENGINE_SW     ] =  gf100_sw_oclass;
+		device->oclass[NVDEV_ENGINE_GR     ] =  gm107_gr_oclass;
+#endif
+		device->oclass[NVDEV_ENGINE_DISP   ] =  gm204_disp_oclass;
+#if 0
+		device->oclass[NVDEV_ENGINE_CE0    ] = &gm204_ce0_oclass;
+		device->oclass[NVDEV_ENGINE_CE1    ] = &gm204_ce1_oclass;
+		device->oclass[NVDEV_ENGINE_CE2    ] = &gm204_ce2_oclass;
+		device->oclass[NVDEV_ENGINE_MSVLD  ] = &gk104_msvld_oclass;
+		device->oclass[NVDEV_ENGINE_MSPDEC ] = &gk104_mspdec_oclass;
+		device->oclass[NVDEV_ENGINE_MSPPP  ] = &gf100_msppp_oclass;
+#endif
+		break;
 	default:
 		nv_fatal(device, "unknown Maxwell chipset\n");
 		return -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c
index b038b6e..043e429 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c
@@ -502,72 +502,57 @@
 {
 	struct nvkm_device *device = nv_device(subdev);
 	struct nv04_fifo_priv *priv = (void *)subdev;
-	uint32_t status, reassign;
-	int cnt = 0;
+	u32 mask = nv_rd32(priv, NV03_PFIFO_INTR_EN_0);
+	u32 stat = nv_rd32(priv, NV03_PFIFO_INTR_0) & mask;
+	u32 reassign, chid, get, sem;
 
 	reassign = nv_rd32(priv, NV03_PFIFO_CACHES) & 1;
-	while ((status = nv_rd32(priv, NV03_PFIFO_INTR_0)) && (cnt++ < 100)) {
-		uint32_t chid, get;
+	nv_wr32(priv, NV03_PFIFO_CACHES, 0);
 
-		nv_wr32(priv, NV03_PFIFO_CACHES, 0);
+	chid = nv_rd32(priv, NV03_PFIFO_CACHE1_PUSH1) & priv->base.max;
+	get  = nv_rd32(priv, NV03_PFIFO_CACHE1_GET);
 
-		chid = nv_rd32(priv, NV03_PFIFO_CACHE1_PUSH1) & priv->base.max;
-		get  = nv_rd32(priv, NV03_PFIFO_CACHE1_GET);
-
-		if (status & NV_PFIFO_INTR_CACHE_ERROR) {
-			nv04_fifo_cache_error(device, priv, chid, get);
-			status &= ~NV_PFIFO_INTR_CACHE_ERROR;
-		}
-
-		if (status & NV_PFIFO_INTR_DMA_PUSHER) {
-			nv04_fifo_dma_pusher(device, priv, chid);
-			status &= ~NV_PFIFO_INTR_DMA_PUSHER;
-		}
-
-		if (status & NV_PFIFO_INTR_SEMAPHORE) {
-			uint32_t sem;
-
-			status &= ~NV_PFIFO_INTR_SEMAPHORE;
-			nv_wr32(priv, NV03_PFIFO_INTR_0,
-				NV_PFIFO_INTR_SEMAPHORE);
-
-			sem = nv_rd32(priv, NV10_PFIFO_CACHE1_SEMAPHORE);
-			nv_wr32(priv, NV10_PFIFO_CACHE1_SEMAPHORE, sem | 0x1);
-
-			nv_wr32(priv, NV03_PFIFO_CACHE1_GET, get + 4);
-			nv_wr32(priv, NV04_PFIFO_CACHE1_PULL0, 1);
-		}
-
-		if (device->card_type == NV_50) {
-			if (status & 0x00000010) {
-				status &= ~0x00000010;
-				nv_wr32(priv, 0x002100, 0x00000010);
-			}
-
-			if (status & 0x40000000) {
-				nv_wr32(priv, 0x002100, 0x40000000);
-				nvkm_fifo_uevent(&priv->base);
-				status &= ~0x40000000;
-			}
-		}
-
-		if (status) {
-			nv_warn(priv, "unknown intr 0x%08x, ch %d\n",
-				status, chid);
-			nv_wr32(priv, NV03_PFIFO_INTR_0, status);
-			status = 0;
-		}
-
-		nv_wr32(priv, NV03_PFIFO_CACHES, reassign);
+	if (stat & NV_PFIFO_INTR_CACHE_ERROR) {
+		nv04_fifo_cache_error(device, priv, chid, get);
+		stat &= ~NV_PFIFO_INTR_CACHE_ERROR;
 	}
 
-	if (status) {
-		nv_error(priv, "still angry after %d spins, halt\n", cnt);
-		nv_wr32(priv, 0x002140, 0);
-		nv_wr32(priv, 0x000140, 0);
+	if (stat & NV_PFIFO_INTR_DMA_PUSHER) {
+		nv04_fifo_dma_pusher(device, priv, chid);
+		stat &= ~NV_PFIFO_INTR_DMA_PUSHER;
 	}
 
-	nv_wr32(priv, 0x000100, 0x00000100);
+	if (stat & NV_PFIFO_INTR_SEMAPHORE) {
+		stat &= ~NV_PFIFO_INTR_SEMAPHORE;
+		nv_wr32(priv, NV03_PFIFO_INTR_0, NV_PFIFO_INTR_SEMAPHORE);
+
+		sem = nv_rd32(priv, NV10_PFIFO_CACHE1_SEMAPHORE);
+		nv_wr32(priv, NV10_PFIFO_CACHE1_SEMAPHORE, sem | 0x1);
+
+		nv_wr32(priv, NV03_PFIFO_CACHE1_GET, get + 4);
+		nv_wr32(priv, NV04_PFIFO_CACHE1_PULL0, 1);
+	}
+
+	if (device->card_type == NV_50) {
+		if (stat & 0x00000010) {
+			stat &= ~0x00000010;
+			nv_wr32(priv, 0x002100, 0x00000010);
+		}
+
+		if (stat & 0x40000000) {
+			nv_wr32(priv, 0x002100, 0x40000000);
+			nvkm_fifo_uevent(&priv->base);
+			stat &= ~0x40000000;
+		}
+	}
+
+	if (stat) {
+		nv_warn(priv, "unknown intr 0x%08x\n", stat);
+		nv_mask(priv, NV03_PFIFO_INTR_EN_0, stat, 0x00000000);
+		nv_wr32(priv, NV03_PFIFO_INTR_0, stat);
+	}
+
+	nv_wr32(priv, NV03_PFIFO_CACHES, reassign);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
index 2e7ec38..57e2c5b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
@@ -1032,9 +1032,9 @@
 	const int s = 8;
 	const int b = mmio_vram(info, impl->bundle_size, (1 << s), access);
 	mmio_refn(info, 0x408004, 0x00000000, s, b);
-	mmio_refn(info, 0x408008, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x408008, 0x80000000 | (impl->bundle_size >> s));
 	mmio_refn(info, 0x418808, 0x00000000, s, b);
-	mmio_refn(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s));
 }
 
 void
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
index b52300d..5e9454b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk104.c
@@ -851,9 +851,9 @@
 	const int s = 8;
 	const int b = mmio_vram(info, impl->bundle_size, (1 << s), access);
 	mmio_refn(info, 0x408004, 0x00000000, s, b);
-	mmio_refn(info, 0x408008, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x408008, 0x80000000 | (impl->bundle_size >> s));
 	mmio_refn(info, 0x418808, 0x00000000, s, b);
-	mmio_refn(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x41880c, 0x80000000 | (impl->bundle_size >> s));
 	mmio_wr32(info, 0x4064c8, (state_limit << 16) | token_limit);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c
index 956f4dc..b2fae6e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm107.c
@@ -871,9 +871,9 @@
 	const int s = 8;
 	const int b = mmio_vram(info, impl->bundle_size, (1 << s), access);
 	mmio_refn(info, 0x408004, 0x00000000, s, b);
-	mmio_refn(info, 0x408008, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x408008, 0x80000000 | (impl->bundle_size >> s));
 	mmio_refn(info, 0x418e24, 0x00000000, s, b);
-	mmio_refn(info, 0x418e28, 0x80000000 | (impl->bundle_size >> s), 0, b);
+	mmio_wr32(info, 0x418e28, 0x80000000 | (impl->bundle_size >> s));
 	mmio_wr32(info, 0x4064c8, (state_limit << 16) | token_limit);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c
index d1a89b2..c4e1f08 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/i2c.c
@@ -74,7 +74,11 @@
 	u16 ent = dcb_i2c_entry(bios, idx, &ver, &len);
 	if (ent) {
 		if (ver >= 0x41) {
-			if (!(nv_ro32(bios, ent) & 0x80000000))
+			u32 ent_value = nv_ro32(bios, ent);
+			u8 i2c_port = (ent_value >> 27) & 0x1f;
+			u8 dpaux_port = (ent_value >> 22) & 0x1f;
+			/* value 0x1f means unused according to DCB 4.x spec */
+			if (i2c_port == 0x1f && dpaux_port == 0x1f)
 				info->type = DCB_I2C_UNUSED;
 			else
 				info->type = DCB_I2C_PMGR;
diff --git a/drivers/gpu/drm/radeon/radeon_kfd.c b/drivers/gpu/drm/radeon/radeon_kfd.c
index 4cdcaf8..3db2300 100644
--- a/drivers/gpu/drm/radeon/radeon_kfd.c
+++ b/drivers/gpu/drm/radeon/radeon_kfd.c
@@ -153,7 +153,7 @@
 			.compute_vmid_bitmap = 0xFF00,
 
 			.first_compute_pipe = 1,
-			.compute_pipe_count = 8 - 1,
+			.compute_pipe_count = 4 - 1,
 		};
 
 		radeon_doorbell_get_kfd_info(rdev,
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 43e0994..318165d 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -173,17 +173,6 @@
 		else
 			rbo->placements[i].lpfn = 0;
 	}
-
-	/*
-	 * Use two-ended allocation depending on the buffer size to
-	 * improve fragmentation quality.
-	 * 512kb was measured as the most optimal number.
-	 */
-	if (rbo->tbo.mem.size > 512 * 1024) {
-		for (i = 0; i < c; i++) {
-			rbo->placements[i].flags |= TTM_PL_FLAG_TOPDOWN;
-		}
-	}
 }
 
 int radeon_bo_create(struct radeon_device *rdev,
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 7c669c3..56ce8c2 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1959,6 +1959,7 @@
 	{ HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb65a) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE_BT) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE_PRO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TOPSEED, USB_DEVICE_ID_TOPSEED_CYBERLINK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TOPSEED2, USB_DEVICE_ID_TOPSEED2_RF_COMBO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TWINHAN, USB_DEVICE_ID_TWINHAN_IR_REMOTE) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 204312b..9c47867 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -586,6 +586,7 @@
 #define USB_VENDOR_ID_LOGITECH		0x046d
 #define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e
 #define USB_DEVICE_ID_LOGITECH_T651	0xb00c
+#define USB_DEVICE_ID_LOGITECH_C077	0xc007
 #define USB_DEVICE_ID_LOGITECH_RECEIVER	0xc101
 #define USB_DEVICE_ID_LOGITECH_HARMONY_FIRST  0xc110
 #define USB_DEVICE_ID_LOGITECH_HARMONY_LAST 0xc14f
@@ -898,6 +899,7 @@
 #define USB_VENDOR_ID_TIVO		0x150a
 #define USB_DEVICE_ID_TIVO_SLIDE_BT	0x1200
 #define USB_DEVICE_ID_TIVO_SLIDE	0x1201
+#define USB_DEVICE_ID_TIVO_SLIDE_PRO	0x1203
 
 #define USB_VENDOR_ID_TOPSEED		0x0766
 #define USB_DEVICE_ID_TOPSEED_CYBERLINK	0x0204
diff --git a/drivers/hid/hid-tivo.c b/drivers/hid/hid-tivo.c
index d790d8d..d986969 100644
--- a/drivers/hid/hid-tivo.c
+++ b/drivers/hid/hid-tivo.c
@@ -64,6 +64,7 @@
 	/* TiVo Slide Bluetooth remote, pairs with a Broadcom dongle */
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE_BT) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_TIVO, USB_DEVICE_ID_TIVO_SLIDE_PRO) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, tivo_devices);
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 9be99a67..a821277 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -78,6 +78,7 @@
 	{ USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP, HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 046351c..bbe32d6 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -551,9 +551,13 @@
 	   (features->type == CINTIQ && !(data[1] & 0x40)))
 		return 1;
 
-	if (features->quirks & WACOM_QUIRK_MULTI_INPUT)
+	if (wacom->shared) {
 		wacom->shared->stylus_in_proximity = true;
 
+		if (wacom->shared->touch_down)
+			return 1;
+	}
+
 	/* in Range while exiting */
 	if (((data[1] & 0xfe) == 0x20) && wacom->reporting_data) {
 		input_report_key(input, BTN_TOUCH, 0);
@@ -1043,27 +1047,28 @@
 	struct input_dev *input = wacom->input;
 	unsigned char *data = wacom->data;
 	int i;
-	int current_num_contacts = 0;
+	int current_num_contacts = data[61];
 	int contacts_to_send = 0;
 	int num_contacts_left = 4; /* maximum contacts per packet */
 	int byte_per_packet = WACOM_BYTES_PER_24HDT_PACKET;
 	int y_offset = 2;
+	static int contact_with_no_pen_down_count = 0;
 
 	if (wacom->features.type == WACOM_27QHDT) {
 		current_num_contacts = data[63];
 		num_contacts_left = 10;
 		byte_per_packet = WACOM_BYTES_PER_QHDTHID_PACKET;
 		y_offset = 0;
-	} else {
-		current_num_contacts = data[61];
 	}
 
 	/*
 	 * First packet resets the counter since only the first
 	 * packet in series will have non-zero current_num_contacts.
 	 */
-	if (current_num_contacts)
+	if (current_num_contacts) {
 		wacom->num_contacts_left = current_num_contacts;
+		contact_with_no_pen_down_count = 0;
+	}
 
 	contacts_to_send = min(num_contacts_left, wacom->num_contacts_left);
 
@@ -1096,15 +1101,16 @@
 				input_report_abs(input, ABS_MT_WIDTH_MINOR, min(w, h));
 				input_report_abs(input, ABS_MT_ORIENTATION, w > h);
 			}
+			contact_with_no_pen_down_count++;
 		}
 	}
 	input_mt_report_pointer_emulation(input, true);
 
 	wacom->num_contacts_left -= contacts_to_send;
-	if (wacom->num_contacts_left <= 0)
+	if (wacom->num_contacts_left <= 0) {
 		wacom->num_contacts_left = 0;
-
-	wacom->shared->touch_down = (wacom->num_contacts_left > 0);
+		wacom->shared->touch_down = (contact_with_no_pen_down_count > 0);
+	}
 	return 1;
 }
 
@@ -1116,6 +1122,7 @@
 	int current_num_contacts = data[2];
 	int contacts_to_send = 0;
 	int x_offset = 0;
+	static int contact_with_no_pen_down_count = 0;
 
 	/* MTTPC does not support Height and Width */
 	if (wacom->features.type == MTTPC || wacom->features.type == MTTPC_B)
@@ -1125,8 +1132,10 @@
 	 * First packet resets the counter since only the first
 	 * packet in series will have non-zero current_num_contacts.
 	 */
-	if (current_num_contacts)
+	if (current_num_contacts) {
 		wacom->num_contacts_left = current_num_contacts;
+		contact_with_no_pen_down_count = 0;
+	}
 
 	/* There are at most 5 contacts per packet */
 	contacts_to_send = min(5, wacom->num_contacts_left);
@@ -1147,15 +1156,16 @@
 			int y = get_unaligned_le16(&data[offset + x_offset + 9]);
 			input_report_abs(input, ABS_MT_POSITION_X, x);
 			input_report_abs(input, ABS_MT_POSITION_Y, y);
+			contact_with_no_pen_down_count++;
 		}
 	}
 	input_mt_report_pointer_emulation(input, true);
 
 	wacom->num_contacts_left -= contacts_to_send;
-	if (wacom->num_contacts_left < 0)
+	if (wacom->num_contacts_left <= 0) {
 		wacom->num_contacts_left = 0;
-
-	wacom->shared->touch_down = (wacom->num_contacts_left > 0);
+		wacom->shared->touch_down = (contact_with_no_pen_down_count > 0);
+	}
 	return 1;
 }
 
@@ -1193,29 +1203,25 @@
 {
 	unsigned char *data = wacom->data;
 	struct input_dev *input = wacom->input;
-	bool prox;
+	bool prox = !wacom->shared->stylus_in_proximity;
 	int x = 0, y = 0;
 
 	if (wacom->features.touch_max > 1 || len > WACOM_PKGLEN_TPC2FG)
 		return 0;
 
-	if (!wacom->shared->stylus_in_proximity) {
-		if (len == WACOM_PKGLEN_TPC1FG) {
-			prox = data[0] & 0x01;
-			x = get_unaligned_le16(&data[1]);
-			y = get_unaligned_le16(&data[3]);
-		} else if (len == WACOM_PKGLEN_TPC1FG_B) {
-			prox = data[2] & 0x01;
-			x = get_unaligned_le16(&data[3]);
-			y = get_unaligned_le16(&data[5]);
-		} else {
-			prox = data[1] & 0x01;
-			x = le16_to_cpup((__le16 *)&data[2]);
-			y = le16_to_cpup((__le16 *)&data[4]);
-		}
-	} else
-		/* force touch out when pen is in prox */
-		prox = 0;
+	if (len == WACOM_PKGLEN_TPC1FG) {
+		prox = prox && (data[0] & 0x01);
+		x = get_unaligned_le16(&data[1]);
+		y = get_unaligned_le16(&data[3]);
+	} else if (len == WACOM_PKGLEN_TPC1FG_B) {
+		prox = prox && (data[2] & 0x01);
+		x = get_unaligned_le16(&data[3]);
+		y = get_unaligned_le16(&data[5]);
+	} else {
+		prox = prox && (data[1] & 0x01);
+		x = le16_to_cpup((__le16 *)&data[2]);
+		y = le16_to_cpup((__le16 *)&data[4]);
+	}
 
 	if (prox) {
 		input_report_abs(input, ABS_X, x);
@@ -1613,6 +1619,7 @@
 	struct input_dev *pad_input = wacom->pad_input;
 	unsigned char *data = wacom->data;
 	int i;
+	int contact_with_no_pen_down_count = 0;
 
 	if (data[0] != 0x02)
 	    return 0;
@@ -1640,6 +1647,7 @@
 			}
 			input_report_abs(input, ABS_MT_POSITION_X, x);
 			input_report_abs(input, ABS_MT_POSITION_Y, y);
+			contact_with_no_pen_down_count++;
 		}
 	}
 
@@ -1649,11 +1657,12 @@
 	input_report_key(pad_input, BTN_FORWARD, (data[1] & 0x04) != 0);
 	input_report_key(pad_input, BTN_BACK, (data[1] & 0x02) != 0);
 	input_report_key(pad_input, BTN_RIGHT, (data[1] & 0x01) != 0);
+	wacom->shared->touch_down = (contact_with_no_pen_down_count > 0);
 
 	return 1;
 }
 
-static void wacom_bpt3_touch_msg(struct wacom_wac *wacom, unsigned char *data)
+static int wacom_bpt3_touch_msg(struct wacom_wac *wacom, unsigned char *data, int last_touch_count)
 {
 	struct wacom_features *features = &wacom->features;
 	struct input_dev *input = wacom->input;
@@ -1661,7 +1670,7 @@
 	int slot = input_mt_get_slot_by_key(input, data[0]);
 
 	if (slot < 0)
-		return;
+		return 0;
 
 	touch = touch && !wacom->shared->stylus_in_proximity;
 
@@ -1693,7 +1702,9 @@
 		input_report_abs(input, ABS_MT_POSITION_Y, y);
 		input_report_abs(input, ABS_MT_TOUCH_MAJOR, width);
 		input_report_abs(input, ABS_MT_TOUCH_MINOR, height);
+		last_touch_count++;
 	}
+	return last_touch_count;
 }
 
 static void wacom_bpt3_button_msg(struct wacom_wac *wacom, unsigned char *data)
@@ -1718,6 +1729,7 @@
 	unsigned char *data = wacom->data;
 	int count = data[1] & 0x07;
 	int i;
+	int contact_with_no_pen_down_count = 0;
 
 	if (data[0] != 0x02)
 	    return 0;
@@ -1728,12 +1740,15 @@
 		int msg_id = data[offset];
 
 		if (msg_id >= 2 && msg_id <= 17)
-			wacom_bpt3_touch_msg(wacom, data + offset);
+			contact_with_no_pen_down_count = 
+			    wacom_bpt3_touch_msg(wacom, data + offset,
+						 contact_with_no_pen_down_count);
 		else if (msg_id == 128)
 			wacom_bpt3_button_msg(wacom, data + offset);
 
 	}
 	input_mt_report_pointer_emulation(input, true);
+	wacom->shared->touch_down = (contact_with_no_pen_down_count > 0);
 
 	return 1;
 }
@@ -1759,6 +1774,9 @@
 		return 0;
 	}
 
+	if (wacom->shared->touch_down)
+		return 0;
+
 	prox = (data[1] & 0x20) == 0x20;
 
 	/*
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index 1793aea..6eb738c 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -1793,11 +1793,11 @@
 	tape->best_dsc_rw_freq = clamp_t(unsigned long, t, IDETAPE_DSC_RW_MIN,
 					 IDETAPE_DSC_RW_MAX);
 	printk(KERN_INFO "ide-tape: %s <-> %s: %dKBps, %d*%dkB buffer, "
-		"%lums tDSC%s\n",
+		"%ums tDSC%s\n",
 		drive->name, tape->name, *(u16 *)&tape->caps[14],
 		(*(u16 *)&tape->caps[16] * 512) / tape->buffer_size,
 		tape->buffer_size / 1024,
-		tape->best_dsc_rw_freq * 1000 / HZ,
+		jiffies_to_msecs(tape->best_dsc_rw_freq),
 		(drive->dev_flags & IDE_DFLAG_USING_DMA) ? ", DMA" : "");
 
 	ide_proc_register_driver(drive, tape->driver);
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index c761971..5904026 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -64,6 +64,14 @@
 #define GUID_TBL_BLK_NUM_ENTRIES 8
 #define GUID_TBL_BLK_SIZE (GUID_TBL_ENTRY_SIZE * GUID_TBL_BLK_NUM_ENTRIES)
 
+/* Counters should be saturate once they reach their maximum value */
+#define ASSIGN_32BIT_COUNTER(counter, value) do {\
+	if ((value) > U32_MAX)			 \
+		counter = cpu_to_be32(U32_MAX); \
+	else					 \
+		counter = cpu_to_be32(value);	 \
+} while (0)
+
 struct mlx4_mad_rcv_buf {
 	struct ib_grh grh;
 	u8 payload[256];
@@ -806,10 +814,14 @@
 static void edit_counter(struct mlx4_counter *cnt,
 					struct ib_pma_portcounters *pma_cnt)
 {
-	pma_cnt->port_xmit_data = cpu_to_be32((be64_to_cpu(cnt->tx_bytes)>>2));
-	pma_cnt->port_rcv_data  = cpu_to_be32((be64_to_cpu(cnt->rx_bytes)>>2));
-	pma_cnt->port_xmit_packets = cpu_to_be32(be64_to_cpu(cnt->tx_frames));
-	pma_cnt->port_rcv_packets  = cpu_to_be32(be64_to_cpu(cnt->rx_frames));
+	ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data,
+			     (be64_to_cpu(cnt->tx_bytes) >> 2));
+	ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data,
+			     (be64_to_cpu(cnt->rx_bytes) >> 2));
+	ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets,
+			     be64_to_cpu(cnt->tx_frames));
+	ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets,
+			     be64_to_cpu(cnt->rx_frames));
 }
 
 static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index ac6e2b7..b972c0b 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2697,8 +2697,12 @@
 	spin_lock_bh(&ibdev->iboe.lock);
 	for (i = 0; i < MLX4_MAX_PORTS; ++i) {
 		struct net_device *curr_netdev = ibdev->iboe.netdevs[i];
+		enum ib_port_state curr_port_state;
 
-		enum ib_port_state curr_port_state =
+		if (!curr_netdev)
+			continue;
+
+		curr_port_state =
 			(netif_running(curr_netdev) &&
 			 netif_carrier_ok(curr_netdev)) ?
 			IB_PORT_ACTIVE : IB_PORT_DOWN;
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index f2cceb6..dda6058 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -67,9 +67,6 @@
 #define X_MAX_POSITIVE 8176
 #define Y_MAX_POSITIVE 8176
 
-/* maximum ABS_MT_POSITION displacement (in mm) */
-#define DMAX 10
-
 /*****************************************************************************
  *	Stuff we need even when we do not want native Synaptics support
  ****************************************************************************/
@@ -123,32 +120,41 @@
 
 static bool cr48_profile_sensor;
 
+#define ANY_BOARD_ID 0
 struct min_max_quirk {
 	const char * const *pnp_ids;
+	struct {
+		unsigned long int min, max;
+	} board_id;
 	int x_min, x_max, y_min, y_max;
 };
 
 static const struct min_max_quirk min_max_pnpid_table[] = {
 	{
 		(const char * const []){"LEN0033", NULL},
+		{ANY_BOARD_ID, ANY_BOARD_ID},
 		1024, 5052, 2258, 4832
 	},
 	{
-		(const char * const []){"LEN0035", "LEN0042", NULL},
+		(const char * const []){"LEN0042", NULL},
+		{ANY_BOARD_ID, ANY_BOARD_ID},
 		1232, 5710, 1156, 4696
 	},
 	{
 		(const char * const []){"LEN0034", "LEN0036", "LEN0037",
 					"LEN0039", "LEN2002", "LEN2004",
 					NULL},
+		{ANY_BOARD_ID, 2961},
 		1024, 5112, 2024, 4832
 	},
 	{
 		(const char * const []){"LEN2001", NULL},
+		{ANY_BOARD_ID, ANY_BOARD_ID},
 		1024, 5022, 2508, 4832
 	},
 	{
 		(const char * const []){"LEN2006", NULL},
+		{ANY_BOARD_ID, ANY_BOARD_ID},
 		1264, 5675, 1171, 4688
 	},
 	{ }
@@ -175,9 +181,7 @@
 	"LEN0041",
 	"LEN0042", /* Yoga */
 	"LEN0045",
-	"LEN0046",
 	"LEN0047",
-	"LEN0048",
 	"LEN0049",
 	"LEN2000",
 	"LEN2001", /* Edge E431 */
@@ -235,18 +239,39 @@
 	return 0;
 }
 
+static int synaptics_more_extended_queries(struct psmouse *psmouse)
+{
+	struct synaptics_data *priv = psmouse->private;
+	unsigned char buf[3];
+
+	if (synaptics_send_cmd(psmouse, SYN_QUE_MEXT_CAPAB_10, buf))
+		return -1;
+
+	priv->ext_cap_10 = (buf[0]<<16) | (buf[1]<<8) | buf[2];
+
+	return 0;
+}
+
 /*
- * Read the board id from the touchpad
+ * Read the board id and the "More Extended Queries" from the touchpad
  * The board id is encoded in the "QUERY MODES" response
  */
-static int synaptics_board_id(struct psmouse *psmouse)
+static int synaptics_query_modes(struct psmouse *psmouse)
 {
 	struct synaptics_data *priv = psmouse->private;
 	unsigned char bid[3];
 
+	/* firmwares prior 7.5 have no board_id encoded */
+	if (SYN_ID_FULL(priv->identity) < 0x705)
+		return 0;
+
 	if (synaptics_send_cmd(psmouse, SYN_QUE_MODES, bid))
 		return -1;
 	priv->board_id = ((bid[0] & 0xfc) << 6) | bid[1];
+
+	if (SYN_MEXT_CAP_BIT(bid[0]))
+		return synaptics_more_extended_queries(psmouse);
+
 	return 0;
 }
 
@@ -346,7 +371,6 @@
 {
 	struct synaptics_data *priv = psmouse->private;
 	unsigned char resp[3];
-	int i;
 
 	if (SYN_ID_MAJOR(priv->identity) < 4)
 		return 0;
@@ -358,17 +382,6 @@
 		}
 	}
 
-	for (i = 0; min_max_pnpid_table[i].pnp_ids; i++) {
-		if (psmouse_matches_pnp_id(psmouse,
-					   min_max_pnpid_table[i].pnp_ids)) {
-			priv->x_min = min_max_pnpid_table[i].x_min;
-			priv->x_max = min_max_pnpid_table[i].x_max;
-			priv->y_min = min_max_pnpid_table[i].y_min;
-			priv->y_max = min_max_pnpid_table[i].y_max;
-			return 0;
-		}
-	}
-
 	if (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 5 &&
 	    SYN_CAP_MAX_DIMENSIONS(priv->ext_cap_0c)) {
 		if (synaptics_send_cmd(psmouse, SYN_QUE_EXT_MAX_COORDS, resp)) {
@@ -377,23 +390,69 @@
 		} else {
 			priv->x_max = (resp[0] << 5) | ((resp[1] & 0x0f) << 1);
 			priv->y_max = (resp[2] << 5) | ((resp[1] & 0xf0) >> 3);
+			psmouse_info(psmouse,
+				     "queried max coordinates: x [..%d], y [..%d]\n",
+				     priv->x_max, priv->y_max);
 		}
 	}
 
-	if (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 7 &&
-	    SYN_CAP_MIN_DIMENSIONS(priv->ext_cap_0c)) {
+	if (SYN_CAP_MIN_DIMENSIONS(priv->ext_cap_0c) &&
+	    (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 7 ||
+	     /*
+	      * Firmware v8.1 does not report proper number of extended
+	      * capabilities, but has been proven to report correct min
+	      * coordinates.
+	      */
+	     SYN_ID_FULL(priv->identity) == 0x801)) {
 		if (synaptics_send_cmd(psmouse, SYN_QUE_EXT_MIN_COORDS, resp)) {
 			psmouse_warn(psmouse,
 				     "device claims to have min coordinates query, but I'm not able to read it.\n");
 		} else {
 			priv->x_min = (resp[0] << 5) | ((resp[1] & 0x0f) << 1);
 			priv->y_min = (resp[2] << 5) | ((resp[1] & 0xf0) >> 3);
+			psmouse_info(psmouse,
+				     "queried min coordinates: x [%d..], y [%d..]\n",
+				     priv->x_min, priv->y_min);
 		}
 	}
 
 	return 0;
 }
 
+/*
+ * Apply quirk(s) if the hardware matches
+ */
+
+static void synaptics_apply_quirks(struct psmouse *psmouse)
+{
+	struct synaptics_data *priv = psmouse->private;
+	int i;
+
+	for (i = 0; min_max_pnpid_table[i].pnp_ids; i++) {
+		if (!psmouse_matches_pnp_id(psmouse,
+					    min_max_pnpid_table[i].pnp_ids))
+			continue;
+
+		if (min_max_pnpid_table[i].board_id.min != ANY_BOARD_ID &&
+		    priv->board_id < min_max_pnpid_table[i].board_id.min)
+			continue;
+
+		if (min_max_pnpid_table[i].board_id.max != ANY_BOARD_ID &&
+		    priv->board_id > min_max_pnpid_table[i].board_id.max)
+			continue;
+
+		priv->x_min = min_max_pnpid_table[i].x_min;
+		priv->x_max = min_max_pnpid_table[i].x_max;
+		priv->y_min = min_max_pnpid_table[i].y_min;
+		priv->y_max = min_max_pnpid_table[i].y_max;
+		psmouse_info(psmouse,
+			     "quirked min/max coordinates: x [%d..%d], y [%d..%d]\n",
+			     priv->x_min, priv->x_max,
+			     priv->y_min, priv->y_max);
+		break;
+	}
+}
+
 static int synaptics_query_hardware(struct psmouse *psmouse)
 {
 	if (synaptics_identify(psmouse))
@@ -402,13 +461,15 @@
 		return -1;
 	if (synaptics_firmware_id(psmouse))
 		return -1;
-	if (synaptics_board_id(psmouse))
+	if (synaptics_query_modes(psmouse))
 		return -1;
 	if (synaptics_capability(psmouse))
 		return -1;
 	if (synaptics_resolution(psmouse))
 		return -1;
 
+	synaptics_apply_quirks(psmouse);
+
 	return 0;
 }
 
@@ -516,18 +577,22 @@
 	return (buf[0] & 0xFC) == 0x84 && (buf[3] & 0xCC) == 0xC4;
 }
 
-static void synaptics_pass_pt_packet(struct serio *ptport, unsigned char *packet)
+static void synaptics_pass_pt_packet(struct psmouse *psmouse,
+				     struct serio *ptport,
+				     unsigned char *packet)
 {
+	struct synaptics_data *priv = psmouse->private;
 	struct psmouse *child = serio_get_drvdata(ptport);
 
 	if (child && child->state == PSMOUSE_ACTIVATED) {
-		serio_interrupt(ptport, packet[1], 0);
+		serio_interrupt(ptport, packet[1] | priv->pt_buttons, 0);
 		serio_interrupt(ptport, packet[4], 0);
 		serio_interrupt(ptport, packet[5], 0);
 		if (child->pktsize == 4)
 			serio_interrupt(ptport, packet[2], 0);
-	} else
+	} else {
 		serio_interrupt(ptport, packet[1], 0);
+	}
 }
 
 static void synaptics_pt_activate(struct psmouse *psmouse)
@@ -605,6 +670,18 @@
 	}
 }
 
+static void synaptics_parse_ext_buttons(const unsigned char buf[],
+					struct synaptics_data *priv,
+					struct synaptics_hw_state *hw)
+{
+	unsigned int ext_bits =
+		(SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) + 1) >> 1;
+	unsigned int ext_mask = GENMASK(ext_bits - 1, 0);
+
+	hw->ext_buttons = buf[4] & ext_mask;
+	hw->ext_buttons |= (buf[5] & ext_mask) << ext_bits;
+}
+
 static bool is_forcepad;
 
 static int synaptics_parse_hw_state(const unsigned char buf[],
@@ -691,28 +768,9 @@
 			hw->down = ((buf[0] ^ buf[3]) & 0x02) ? 1 : 0;
 		}
 
-		if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) &&
+		if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) > 0 &&
 		    ((buf[0] ^ buf[3]) & 0x02)) {
-			switch (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) & ~0x01) {
-			default:
-				/*
-				 * if nExtBtn is greater than 8 it should be
-				 * considered invalid and treated as 0
-				 */
-				break;
-			case 8:
-				hw->ext_buttons |= ((buf[5] & 0x08)) ? 0x80 : 0;
-				hw->ext_buttons |= ((buf[4] & 0x08)) ? 0x40 : 0;
-			case 6:
-				hw->ext_buttons |= ((buf[5] & 0x04)) ? 0x20 : 0;
-				hw->ext_buttons |= ((buf[4] & 0x04)) ? 0x10 : 0;
-			case 4:
-				hw->ext_buttons |= ((buf[5] & 0x02)) ? 0x08 : 0;
-				hw->ext_buttons |= ((buf[4] & 0x02)) ? 0x04 : 0;
-			case 2:
-				hw->ext_buttons |= ((buf[5] & 0x01)) ? 0x02 : 0;
-				hw->ext_buttons |= ((buf[4] & 0x01)) ? 0x01 : 0;
-			}
+			synaptics_parse_ext_buttons(buf, priv, hw);
 		}
 	} else {
 		hw->x = (((buf[1] & 0x1f) << 8) | buf[2]);
@@ -774,12 +832,54 @@
 	}
 }
 
+static void synaptics_report_ext_buttons(struct psmouse *psmouse,
+					 const struct synaptics_hw_state *hw)
+{
+	struct input_dev *dev = psmouse->dev;
+	struct synaptics_data *priv = psmouse->private;
+	int ext_bits = (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) + 1) >> 1;
+	char buf[6] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00};
+	int i;
+
+	if (!SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap))
+		return;
+
+	/* Bug in FW 8.1, buttons are reported only when ExtBit is 1 */
+	if (SYN_ID_FULL(priv->identity) == 0x801 &&
+	    !((psmouse->packet[0] ^ psmouse->packet[3]) & 0x02))
+		return;
+
+	if (!SYN_CAP_EXT_BUTTONS_STICK(priv->ext_cap_10)) {
+		for (i = 0; i < ext_bits; i++) {
+			input_report_key(dev, BTN_0 + 2 * i,
+				hw->ext_buttons & (1 << i));
+			input_report_key(dev, BTN_1 + 2 * i,
+				hw->ext_buttons & (1 << (i + ext_bits)));
+		}
+		return;
+	}
+
+	/*
+	 * This generation of touchpads has the trackstick buttons
+	 * physically wired to the touchpad. Re-route them through
+	 * the pass-through interface.
+	 */
+	if (!priv->pt_port)
+		return;
+
+	/* The trackstick expects at most 3 buttons */
+	priv->pt_buttons = SYN_CAP_EXT_BUTTON_STICK_L(hw->ext_buttons)      |
+			   SYN_CAP_EXT_BUTTON_STICK_R(hw->ext_buttons) << 1 |
+			   SYN_CAP_EXT_BUTTON_STICK_M(hw->ext_buttons) << 2;
+
+	synaptics_pass_pt_packet(psmouse, priv->pt_port, buf);
+}
+
 static void synaptics_report_buttons(struct psmouse *psmouse,
 				     const struct synaptics_hw_state *hw)
 {
 	struct input_dev *dev = psmouse->dev;
 	struct synaptics_data *priv = psmouse->private;
-	int i;
 
 	input_report_key(dev, BTN_LEFT, hw->left);
 	input_report_key(dev, BTN_RIGHT, hw->right);
@@ -792,8 +892,7 @@
 		input_report_key(dev, BTN_BACK, hw->down);
 	}
 
-	for (i = 0; i < SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap); i++)
-		input_report_key(dev, BTN_0 + i, hw->ext_buttons & (1 << i));
+	synaptics_report_ext_buttons(psmouse, hw);
 }
 
 static void synaptics_report_mt_data(struct psmouse *psmouse,
@@ -813,7 +912,7 @@
 		pos[i].y = synaptics_invert_y(hw[i]->y);
 	}
 
-	input_mt_assign_slots(dev, slot, pos, nsemi, DMAX * priv->x_res);
+	input_mt_assign_slots(dev, slot, pos, nsemi, 0);
 
 	for (i = 0; i < nsemi; i++) {
 		input_mt_slot(dev, slot[i]);
@@ -1014,7 +1113,8 @@
 		if (SYN_CAP_PASS_THROUGH(priv->capabilities) &&
 		    synaptics_is_pt_packet(psmouse->packet)) {
 			if (priv->pt_port)
-				synaptics_pass_pt_packet(priv->pt_port, psmouse->packet);
+				synaptics_pass_pt_packet(psmouse, priv->pt_port,
+							 psmouse->packet);
 		} else
 			synaptics_process_packet(psmouse);
 
@@ -1116,8 +1216,9 @@
 		__set_bit(BTN_BACK, dev->keybit);
 	}
 
-	for (i = 0; i < SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap); i++)
-		__set_bit(BTN_0 + i, dev->keybit);
+	if (!SYN_CAP_EXT_BUTTONS_STICK(priv->ext_cap_10))
+		for (i = 0; i < SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap); i++)
+			__set_bit(BTN_0 + i, dev->keybit);
 
 	__clear_bit(EV_REL, dev->evbit);
 	__clear_bit(REL_X, dev->relbit);
@@ -1125,7 +1226,8 @@
 
 	if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) {
 		__set_bit(INPUT_PROP_BUTTONPAD, dev->propbit);
-		if (psmouse_matches_pnp_id(psmouse, topbuttonpad_pnp_ids))
+		if (psmouse_matches_pnp_id(psmouse, topbuttonpad_pnp_ids) &&
+		    !SYN_CAP_EXT_BUTTONS_STICK(priv->ext_cap_10))
 			__set_bit(INPUT_PROP_TOPBUTTONPAD, dev->propbit);
 		/* Clickpads report only left button */
 		__clear_bit(BTN_RIGHT, dev->keybit);
diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h
index aedc329..ee4bd0d1 100644
--- a/drivers/input/mouse/synaptics.h
+++ b/drivers/input/mouse/synaptics.h
@@ -22,6 +22,7 @@
 #define SYN_QUE_EXT_CAPAB_0C		0x0c
 #define SYN_QUE_EXT_MAX_COORDS		0x0d
 #define SYN_QUE_EXT_MIN_COORDS		0x0f
+#define SYN_QUE_MEXT_CAPAB_10		0x10
 
 /* synatics modes */
 #define SYN_BIT_ABSOLUTE_MODE		(1 << 7)
@@ -53,6 +54,7 @@
 #define SYN_EXT_CAP_REQUESTS(c)		(((c) & 0x700000) >> 20)
 #define SYN_CAP_MULTI_BUTTON_NO(ec)	(((ec) & 0x00f000) >> 12)
 #define SYN_CAP_PRODUCT_ID(ec)		(((ec) & 0xff0000) >> 16)
+#define SYN_MEXT_CAP_BIT(m)		((m) & (1 << 1))
 
 /*
  * The following describes response for the 0x0c query.
@@ -89,6 +91,30 @@
 #define SYN_CAP_REDUCED_FILTERING(ex0c)	((ex0c) & 0x000400)
 #define SYN_CAP_IMAGE_SENSOR(ex0c)	((ex0c) & 0x000800)
 
+/*
+ * The following descibes response for the 0x10 query.
+ *
+ * byte	mask	name			meaning
+ * ----	----	-------			------------
+ * 1	0x01	ext buttons are stick	buttons exported in the extended
+ *					capability are actually meant to be used
+ *					by the tracktick (pass-through).
+ * 1	0x02	SecurePad		the touchpad is a SecurePad, so it
+ *					contains a built-in fingerprint reader.
+ * 1	0xe0	more ext count		how many more extented queries are
+ *					available after this one.
+ * 2	0xff	SecurePad width		the width of the SecurePad fingerprint
+ *					reader.
+ * 3	0xff	SecurePad height	the height of the SecurePad fingerprint
+ *					reader.
+ */
+#define SYN_CAP_EXT_BUTTONS_STICK(ex10)	((ex10) & 0x010000)
+#define SYN_CAP_SECUREPAD(ex10)		((ex10) & 0x020000)
+
+#define SYN_CAP_EXT_BUTTON_STICK_L(eb)	(!!((eb) & 0x01))
+#define SYN_CAP_EXT_BUTTON_STICK_M(eb)	(!!((eb) & 0x02))
+#define SYN_CAP_EXT_BUTTON_STICK_R(eb)	(!!((eb) & 0x04))
+
 /* synaptics modes query bits */
 #define SYN_MODE_ABSOLUTE(m)		((m) & (1 << 7))
 #define SYN_MODE_RATE(m)		((m) & (1 << 6))
@@ -143,6 +169,7 @@
 	unsigned long int capabilities;		/* Capabilities */
 	unsigned long int ext_cap;		/* Extended Capabilities */
 	unsigned long int ext_cap_0c;		/* Ext Caps from 0x0c query */
+	unsigned long int ext_cap_10;		/* Ext Caps from 0x10 query */
 	unsigned long int identity;		/* Identification */
 	unsigned int x_res, y_res;		/* X/Y resolution in units/mm */
 	unsigned int x_max, y_max;		/* Max coordinates (from FW) */
@@ -156,6 +183,7 @@
 	bool disable_gesture;			/* disable gestures */
 
 	struct serio *pt_port;			/* Pass-through serio port */
+	unsigned char pt_buttons;		/* Pass-through buttons */
 
 	/*
 	 * Last received Advanced Gesture Mode (AGM) packet. An AGM packet
diff --git a/drivers/isdn/icn/icn.c b/drivers/isdn/icn/icn.c
index 6a7447c..358a574 100644
--- a/drivers/isdn/icn/icn.c
+++ b/drivers/isdn/icn/icn.c
@@ -1609,7 +1609,7 @@
 	if (ints[0] > 1)
 		membase = (unsigned long)ints[2];
 	if (str && *str) {
-		strcpy(sid, str);
+		strlcpy(sid, str, sizeof(sid));
 		icn_id = sid;
 		if ((p = strchr(sid, ','))) {
 			*p++ = 0;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 37de017..74adcd2 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -289,9 +289,16 @@
 	struct request_queue *q = bdev_get_queue(where->bdev);
 	unsigned short logical_block_size = queue_logical_block_size(q);
 	sector_t num_sectors;
+	unsigned int uninitialized_var(special_cmd_max_sectors);
 
-	/* Reject unsupported discard requests */
-	if ((rw & REQ_DISCARD) && !blk_queue_discard(q)) {
+	/*
+	 * Reject unsupported discard and write same requests.
+	 */
+	if (rw & REQ_DISCARD)
+		special_cmd_max_sectors = q->limits.max_discard_sectors;
+	else if (rw & REQ_WRITE_SAME)
+		special_cmd_max_sectors = q->limits.max_write_same_sectors;
+	if ((rw & (REQ_DISCARD | REQ_WRITE_SAME)) && special_cmd_max_sectors == 0) {
 		dec_count(io, region, -EOPNOTSUPP);
 		return;
 	}
@@ -317,7 +324,7 @@
 		store_io_and_region_in_bio(bio, io, region);
 
 		if (rw & REQ_DISCARD) {
-			num_sectors = min_t(sector_t, q->limits.max_discard_sectors, remaining);
+			num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
 			bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
 			remaining -= num_sectors;
 		} else if (rw & REQ_WRITE_SAME) {
@@ -326,7 +333,7 @@
 			 */
 			dp->get_page(dp, &page, &len, &offset);
 			bio_add_page(bio, page, logical_block_size, offset);
-			num_sectors = min_t(sector_t, q->limits.max_write_same_sectors, remaining);
+			num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
 			bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
 
 			offset = 0;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 8b204ae2..f83a0f3 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -20,6 +20,8 @@
 #include <linux/log2.h>
 #include <linux/dm-kcopyd.h>
 
+#include "dm.h"
+
 #include "dm-exception-store.h"
 
 #define DM_MSG_PREFIX "snapshots"
@@ -291,12 +293,23 @@
 };
 
 /*
+ * This structure is allocated for each origin target
+ */
+struct dm_origin {
+	struct dm_dev *dev;
+	struct dm_target *ti;
+	unsigned split_boundary;
+	struct list_head hash_list;
+};
+
+/*
  * Size of the hash table for origin volumes. If we make this
  * the size of the minors list then it should be nearly perfect
  */
 #define ORIGIN_HASH_SIZE 256
 #define ORIGIN_MASK      0xFF
 static struct list_head *_origins;
+static struct list_head *_dm_origins;
 static struct rw_semaphore _origins_lock;
 
 static DECLARE_WAIT_QUEUE_HEAD(_pending_exceptions_done);
@@ -310,12 +323,22 @@
 	_origins = kmalloc(ORIGIN_HASH_SIZE * sizeof(struct list_head),
 			   GFP_KERNEL);
 	if (!_origins) {
-		DMERR("unable to allocate memory");
+		DMERR("unable to allocate memory for _origins");
 		return -ENOMEM;
 	}
-
 	for (i = 0; i < ORIGIN_HASH_SIZE; i++)
 		INIT_LIST_HEAD(_origins + i);
+
+	_dm_origins = kmalloc(ORIGIN_HASH_SIZE * sizeof(struct list_head),
+			      GFP_KERNEL);
+	if (!_dm_origins) {
+		DMERR("unable to allocate memory for _dm_origins");
+		kfree(_origins);
+		return -ENOMEM;
+	}
+	for (i = 0; i < ORIGIN_HASH_SIZE; i++)
+		INIT_LIST_HEAD(_dm_origins + i);
+
 	init_rwsem(&_origins_lock);
 
 	return 0;
@@ -324,6 +347,7 @@
 static void exit_origin_hash(void)
 {
 	kfree(_origins);
+	kfree(_dm_origins);
 }
 
 static unsigned origin_hash(struct block_device *bdev)
@@ -350,6 +374,30 @@
 	list_add_tail(&o->hash_list, sl);
 }
 
+static struct dm_origin *__lookup_dm_origin(struct block_device *origin)
+{
+	struct list_head *ol;
+	struct dm_origin *o;
+
+	ol = &_dm_origins[origin_hash(origin)];
+	list_for_each_entry (o, ol, hash_list)
+		if (bdev_equal(o->dev->bdev, origin))
+			return o;
+
+	return NULL;
+}
+
+static void __insert_dm_origin(struct dm_origin *o)
+{
+	struct list_head *sl = &_dm_origins[origin_hash(o->dev->bdev)];
+	list_add_tail(&o->hash_list, sl);
+}
+
+static void __remove_dm_origin(struct dm_origin *o)
+{
+	list_del(&o->hash_list);
+}
+
 /*
  * _origins_lock must be held when calling this function.
  * Returns number of snapshots registered using the supplied cow device, plus:
@@ -1840,9 +1888,40 @@
 static void snapshot_resume(struct dm_target *ti)
 {
 	struct dm_snapshot *s = ti->private;
-	struct dm_snapshot *snap_src = NULL, *snap_dest = NULL;
+	struct dm_snapshot *snap_src = NULL, *snap_dest = NULL, *snap_merging = NULL;
+	struct dm_origin *o;
+	struct mapped_device *origin_md = NULL;
+	bool must_restart_merging = false;
 
 	down_read(&_origins_lock);
+
+	o = __lookup_dm_origin(s->origin->bdev);
+	if (o)
+		origin_md = dm_table_get_md(o->ti->table);
+	if (!origin_md) {
+		(void) __find_snapshots_sharing_cow(s, NULL, NULL, &snap_merging);
+		if (snap_merging)
+			origin_md = dm_table_get_md(snap_merging->ti->table);
+	}
+	if (origin_md == dm_table_get_md(ti->table))
+		origin_md = NULL;
+	if (origin_md) {
+		if (dm_hold(origin_md))
+			origin_md = NULL;
+	}
+
+	up_read(&_origins_lock);
+
+	if (origin_md) {
+		dm_internal_suspend_fast(origin_md);
+		if (snap_merging && test_bit(RUNNING_MERGE, &snap_merging->state_bits)) {
+			must_restart_merging = true;
+			stop_merge(snap_merging);
+		}
+	}
+
+	down_read(&_origins_lock);
+
 	(void) __find_snapshots_sharing_cow(s, &snap_src, &snap_dest, NULL);
 	if (snap_src && snap_dest) {
 		down_write(&snap_src->lock);
@@ -1851,8 +1930,16 @@
 		up_write(&snap_dest->lock);
 		up_write(&snap_src->lock);
 	}
+
 	up_read(&_origins_lock);
 
+	if (origin_md) {
+		if (must_restart_merging)
+			start_merge(snap_merging);
+		dm_internal_resume_fast(origin_md);
+		dm_put(origin_md);
+	}
+
 	/* Now we have correct chunk size, reregister */
 	reregister_snapshot(s);
 
@@ -2133,11 +2220,6 @@
  * Origin: maps a linear range of a device, with hooks for snapshotting.
  */
 
-struct dm_origin {
-	struct dm_dev *dev;
-	unsigned split_boundary;
-};
-
 /*
  * Construct an origin mapping: <dev_path>
  * The context for an origin is merely a 'struct dm_dev *'
@@ -2166,6 +2248,7 @@
 		goto bad_open;
 	}
 
+	o->ti = ti;
 	ti->private = o;
 	ti->num_flush_bios = 1;
 
@@ -2180,6 +2263,7 @@
 static void origin_dtr(struct dm_target *ti)
 {
 	struct dm_origin *o = ti->private;
+
 	dm_put_device(ti, o->dev);
 	kfree(o);
 }
@@ -2216,6 +2300,19 @@
 	struct dm_origin *o = ti->private;
 
 	o->split_boundary = get_origin_minimum_chunksize(o->dev->bdev);
+
+	down_write(&_origins_lock);
+	__insert_dm_origin(o);
+	up_write(&_origins_lock);
+}
+
+static void origin_postsuspend(struct dm_target *ti)
+{
+	struct dm_origin *o = ti->private;
+
+	down_write(&_origins_lock);
+	__remove_dm_origin(o);
+	up_write(&_origins_lock);
 }
 
 static void origin_status(struct dm_target *ti, status_type_t type,
@@ -2258,12 +2355,13 @@
 
 static struct target_type origin_target = {
 	.name    = "snapshot-origin",
-	.version = {1, 8, 1},
+	.version = {1, 9, 0},
 	.module  = THIS_MODULE,
 	.ctr     = origin_ctr,
 	.dtr     = origin_dtr,
 	.map     = origin_map,
 	.resume  = origin_resume,
+	.postsuspend = origin_postsuspend,
 	.status  = origin_status,
 	.merge	 = origin_merge,
 	.iterate_devices = origin_iterate_devices,
@@ -2271,7 +2369,7 @@
 
 static struct target_type snapshot_target = {
 	.name    = "snapshot",
-	.version = {1, 12, 0},
+	.version = {1, 13, 0},
 	.module  = THIS_MODULE,
 	.ctr     = snapshot_ctr,
 	.dtr     = snapshot_dtr,
@@ -2285,7 +2383,7 @@
 
 static struct target_type merge_target = {
 	.name    = dm_snapshot_merge_target_name,
-	.version = {1, 2, 0},
+	.version = {1, 3, 0},
 	.module  = THIS_MODULE,
 	.ctr     = snapshot_ctr,
 	.dtr     = snapshot_dtr,
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 654773c..921aafd 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2358,17 +2358,6 @@
 		return DM_MAPIO_REMAPPED;
 
 	case -ENODATA:
-		if (get_pool_mode(tc->pool) == PM_READ_ONLY) {
-			/*
-			 * This block isn't provisioned, and we have no way
-			 * of doing so.
-			 */
-			handle_unserviceable_bio(tc->pool, bio);
-			cell_defer_no_holder(tc, virt_cell);
-			return DM_MAPIO_SUBMITTED;
-		}
-		/* fall through */
-
 	case -EWOULDBLOCK:
 		thin_defer_cell(tc, virt_cell);
 		return DM_MAPIO_SUBMITTED;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 73f2880..8001fe9 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -433,7 +433,6 @@
 
 	dm_get(md);
 	atomic_inc(&md->open_count);
-
 out:
 	spin_unlock(&_minor_lock);
 
@@ -442,16 +441,20 @@
 
 static void dm_blk_close(struct gendisk *disk, fmode_t mode)
 {
-	struct mapped_device *md = disk->private_data;
+	struct mapped_device *md;
 
 	spin_lock(&_minor_lock);
 
+	md = disk->private_data;
+	if (WARN_ON(!md))
+		goto out;
+
 	if (atomic_dec_and_test(&md->open_count) &&
 	    (test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
 		queue_work(deferred_remove_workqueue, &deferred_remove_work);
 
 	dm_put(md);
-
+out:
 	spin_unlock(&_minor_lock);
 }
 
@@ -2241,7 +2244,6 @@
 	int minor = MINOR(disk_devt(md->disk));
 
 	unlock_fs(md);
-	bdput(md->bdev);
 	destroy_workqueue(md->wq);
 
 	if (md->kworker_task)
@@ -2252,19 +2254,22 @@
 		mempool_destroy(md->rq_pool);
 	if (md->bs)
 		bioset_free(md->bs);
-	blk_integrity_unregister(md->disk);
-	del_gendisk(md->disk);
+
 	cleanup_srcu_struct(&md->io_barrier);
 	free_table_devices(&md->table_devices);
-	free_minor(minor);
+	dm_stats_cleanup(&md->stats);
 
 	spin_lock(&_minor_lock);
 	md->disk->private_data = NULL;
 	spin_unlock(&_minor_lock);
-
+	if (blk_get_integrity(md->disk))
+		blk_integrity_unregister(md->disk);
+	del_gendisk(md->disk);
 	put_disk(md->disk);
 	blk_cleanup_queue(md->queue);
-	dm_stats_cleanup(&md->stats);
+	bdput(md->bdev);
+	free_minor(minor);
+
 	module_put(THIS_MODULE);
 	kfree(md);
 }
@@ -2616,6 +2621,19 @@
 	BUG_ON(test_bit(DMF_FREEING, &md->flags));
 }
 
+int dm_hold(struct mapped_device *md)
+{
+	spin_lock(&_minor_lock);
+	if (test_bit(DMF_FREEING, &md->flags)) {
+		spin_unlock(&_minor_lock);
+		return -EBUSY;
+	}
+	dm_get(md);
+	spin_unlock(&_minor_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dm_hold);
+
 const char *dm_device_name(struct mapped_device *md)
 {
 	return md->name;
@@ -2629,8 +2647,9 @@
 
 	might_sleep();
 
-	spin_lock(&_minor_lock);
 	map = dm_get_live_table(md, &srcu_idx);
+
+	spin_lock(&_minor_lock);
 	idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md))));
 	set_bit(DMF_FREEING, &md->flags);
 	spin_unlock(&_minor_lock);
@@ -2638,10 +2657,16 @@
 	if (dm_request_based(md))
 		flush_kthread_worker(&md->kworker);
 
+	/*
+	 * Take suspend_lock so that presuspend and postsuspend methods
+	 * do not race with internal suspend.
+	 */
+	mutex_lock(&md->suspend_lock);
 	if (!dm_suspended_md(md)) {
 		dm_table_presuspend_targets(map);
 		dm_table_postsuspend_targets(map);
 	}
+	mutex_unlock(&md->suspend_lock);
 
 	/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
 	dm_put_live_table(md, srcu_idx);
@@ -3115,6 +3140,7 @@
 	flush_workqueue(md->wq);
 	dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
 }
+EXPORT_SYMBOL_GPL(dm_internal_suspend_fast);
 
 void dm_internal_resume_fast(struct mapped_device *md)
 {
@@ -3126,6 +3152,7 @@
 done:
 	mutex_unlock(&md->suspend_lock);
 }
+EXPORT_SYMBOL_GPL(dm_internal_resume_fast);
 
 /*-----------------------------------------------------------------
  * Event notification.
diff --git a/drivers/md/md.c b/drivers/md/md.c
index cadf9cc..717daad 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5080,7 +5080,8 @@
 	}
 	if (err) {
 		mddev_detach(mddev);
-		pers->free(mddev, mddev->private);
+		if (mddev->private)
+			pers->free(mddev, mddev->private);
 		module_put(pers->owner);
 		bitmap_destroy(mddev);
 		return err;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index a13f738..3ed9f42 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -467,8 +467,6 @@
 	dump_zones(mddev);
 
 	ret = md_integrity_register(mddev);
-	if (ret)
-		raid0_free(mddev, conf);
 
 	return ret;
 }
diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c
index f38ec42..5615522 100644
--- a/drivers/mfd/kempld-core.c
+++ b/drivers/mfd/kempld-core.c
@@ -739,7 +739,7 @@
 		for (id = kempld_dmi_table;
 		     id->matches[0].slot != DMI_NONE; id++)
 			if (strstr(id->ident, force_device_id))
-				if (id->callback && id->callback(id))
+				if (id->callback && !id->callback(id))
 					break;
 		if (id->matches[0].slot == DMI_NONE)
 			return -ENODEV;
diff --git a/drivers/mfd/rtsx_usb.c b/drivers/mfd/rtsx_usb.c
index ede5024..dbd907d 100644
--- a/drivers/mfd/rtsx_usb.c
+++ b/drivers/mfd/rtsx_usb.c
@@ -196,18 +196,27 @@
 int rtsx_usb_ep0_read_register(struct rtsx_ucr *ucr, u16 addr, u8 *data)
 {
 	u16 value;
+	u8 *buf;
+	int ret;
 
 	if (!data)
 		return -EINVAL;
-	*data = 0;
+
+	buf = kzalloc(sizeof(u8), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
 
 	addr |= EP0_READ_REG_CMD << EP0_OP_SHIFT;
 	value = swab16(addr);
 
-	return usb_control_msg(ucr->pusb_dev,
+	ret = usb_control_msg(ucr->pusb_dev,
 			usb_rcvctrlpipe(ucr->pusb_dev, 0), RTSX_USB_REQ_REG_OP,
 			USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-			value, 0, data, 1, 100);
+			value, 0, buf, 1, 100);
+	*data = *buf;
+
+	kfree(buf);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(rtsx_usb_ep0_read_register);
 
@@ -288,18 +297,27 @@
 int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status)
 {
 	int ret;
+	u16 *buf;
 
 	if (!status)
 		return -EINVAL;
 
-	if (polling_pipe == 0)
+	if (polling_pipe == 0) {
+		buf = kzalloc(sizeof(u16), GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+
 		ret = usb_control_msg(ucr->pusb_dev,
 				usb_rcvctrlpipe(ucr->pusb_dev, 0),
 				RTSX_USB_REQ_POLL,
 				USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-				0, 0, status, 2, 100);
-	else
+				0, 0, buf, 2, 100);
+		*status = *buf;
+
+		kfree(buf);
+	} else {
 		ret = rtsx_usb_get_status_with_bulk(ucr, status);
+	}
 
 	/* usb_control_msg may return positive when success */
 	if (ret < 0)
diff --git a/drivers/mmc/core/pwrseq_simple.c b/drivers/mmc/core/pwrseq_simple.c
index e9f1d8d..c53f14a 100644
--- a/drivers/mmc/core/pwrseq_simple.c
+++ b/drivers/mmc/core/pwrseq_simple.c
@@ -124,7 +124,7 @@
 		    PTR_ERR(pwrseq->reset_gpios[i]) != -ENOSYS) {
 			ret = PTR_ERR(pwrseq->reset_gpios[i]);
 
-			while (--i)
+			while (i--)
 				gpiod_put(pwrseq->reset_gpios[i]);
 
 			goto clk_put;
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index da4c792..16e34b3 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -425,9 +425,10 @@
 					ubi_warn(ubi, "corrupted VID header at PEB %d, LEB %d:%d",
 						 pnum, vol_id, lnum);
 					err = -EBADMSG;
-				} else
+				} else {
 					err = -EINVAL;
 					ubi_ro_mode(ubi);
+				}
 			}
 			goto out_free;
 		} else if (err == UBI_IO_BITFLIPS)
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 98d73aa..58808f6 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -131,7 +131,7 @@
 
 config CAN_XILINXCAN
 	tristate "Xilinx CAN"
-	depends on ARCH_ZYNQ || MICROBLAZE || COMPILE_TEST
+	depends on ARCH_ZYNQ || ARM64 || MICROBLAZE || COMPILE_TEST
 	depends on COMMON_CLK && HAS_IOMEM
 	---help---
 	  Xilinx CAN driver. This driver supports both soft AXI CAN IP and
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index a316fa4..e97a08c 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -14,6 +14,7 @@
  * Copyright (C) 2015 Valeo S.A.
  */
 
+#include <linux/spinlock.h>
 #include <linux/kernel.h>
 #include <linux/completion.h>
 #include <linux/module.h>
@@ -467,10 +468,11 @@
 struct kvaser_usb_net_priv {
 	struct can_priv can;
 
-	atomic_t active_tx_urbs;
-	struct usb_anchor tx_submitted;
+	spinlock_t tx_contexts_lock;
+	int active_tx_contexts;
 	struct kvaser_usb_tx_urb_context tx_contexts[MAX_TX_URBS];
 
+	struct usb_anchor tx_submitted;
 	struct completion start_comp, stop_comp;
 
 	struct kvaser_usb *dev;
@@ -694,6 +696,7 @@
 	struct kvaser_usb_net_priv *priv;
 	struct sk_buff *skb;
 	struct can_frame *cf;
+	unsigned long flags;
 	u8 channel, tid;
 
 	channel = msg->u.tx_acknowledge_header.channel;
@@ -737,12 +740,15 @@
 
 	stats->tx_packets++;
 	stats->tx_bytes += context->dlc;
+
+	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
+
 	can_get_echo_skb(priv->netdev, context->echo_index);
-
 	context->echo_index = MAX_TX_URBS;
-	atomic_dec(&priv->active_tx_urbs);
-
+	--priv->active_tx_contexts;
 	netif_wake_queue(priv->netdev);
+
+	spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
 }
 
 static void kvaser_usb_simple_msg_callback(struct urb *urb)
@@ -803,17 +809,6 @@
 	return 0;
 }
 
-static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv)
-{
-	int i;
-
-	usb_kill_anchored_urbs(&priv->tx_submitted);
-	atomic_set(&priv->active_tx_urbs, 0);
-
-	for (i = 0; i < MAX_TX_URBS; i++)
-		priv->tx_contexts[i].echo_index = MAX_TX_URBS;
-}
-
 static void kvaser_usb_rx_error_update_can_state(struct kvaser_usb_net_priv *priv,
 						 const struct kvaser_usb_error_summary *es,
 						 struct can_frame *cf)
@@ -1515,6 +1510,24 @@
 	return err;
 }
 
+static void kvaser_usb_reset_tx_urb_contexts(struct kvaser_usb_net_priv *priv)
+{
+	int i;
+
+	priv->active_tx_contexts = 0;
+	for (i = 0; i < MAX_TX_URBS; i++)
+		priv->tx_contexts[i].echo_index = MAX_TX_URBS;
+}
+
+/* This method might sleep. Do not call it in the atomic context
+ * of URB completions.
+ */
+static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv)
+{
+	usb_kill_anchored_urbs(&priv->tx_submitted);
+	kvaser_usb_reset_tx_urb_contexts(priv);
+}
+
 static void kvaser_usb_unlink_all_urbs(struct kvaser_usb *dev)
 {
 	int i;
@@ -1634,6 +1647,7 @@
 	struct kvaser_msg *msg;
 	int i, err, ret = NETDEV_TX_OK;
 	u8 *msg_tx_can_flags = NULL;		/* GCC */
+	unsigned long flags;
 
 	if (can_dropped_invalid_skb(netdev, skb))
 		return NETDEV_TX_OK;
@@ -1687,12 +1701,21 @@
 	if (cf->can_id & CAN_RTR_FLAG)
 		*msg_tx_can_flags |= MSG_FLAG_REMOTE_FRAME;
 
+	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
 	for (i = 0; i < ARRAY_SIZE(priv->tx_contexts); i++) {
 		if (priv->tx_contexts[i].echo_index == MAX_TX_URBS) {
 			context = &priv->tx_contexts[i];
+
+			context->echo_index = i;
+			can_put_echo_skb(skb, netdev, context->echo_index);
+			++priv->active_tx_contexts;
+			if (priv->active_tx_contexts >= MAX_TX_URBS)
+				netif_stop_queue(netdev);
+
 			break;
 		}
 	}
+	spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
 
 	/* This should never happen; it implies a flow control bug */
 	if (!context) {
@@ -1704,7 +1727,6 @@
 	}
 
 	context->priv = priv;
-	context->echo_index = i;
 	context->dlc = cf->can_dlc;
 
 	msg->u.tx_can.tid = context->echo_index;
@@ -1716,18 +1738,17 @@
 			  kvaser_usb_write_bulk_callback, context);
 	usb_anchor_urb(urb, &priv->tx_submitted);
 
-	can_put_echo_skb(skb, netdev, context->echo_index);
-
-	atomic_inc(&priv->active_tx_urbs);
-
-	if (atomic_read(&priv->active_tx_urbs) >= MAX_TX_URBS)
-		netif_stop_queue(netdev);
-
 	err = usb_submit_urb(urb, GFP_ATOMIC);
 	if (unlikely(err)) {
-		can_free_echo_skb(netdev, context->echo_index);
+		spin_lock_irqsave(&priv->tx_contexts_lock, flags);
 
-		atomic_dec(&priv->active_tx_urbs);
+		can_free_echo_skb(netdev, context->echo_index);
+		context->echo_index = MAX_TX_URBS;
+		--priv->active_tx_contexts;
+		netif_wake_queue(netdev);
+
+		spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
+
 		usb_unanchor_urb(urb);
 
 		stats->tx_dropped++;
@@ -1854,7 +1875,7 @@
 	struct kvaser_usb *dev = usb_get_intfdata(intf);
 	struct net_device *netdev;
 	struct kvaser_usb_net_priv *priv;
-	int i, err;
+	int err;
 
 	err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, channel);
 	if (err)
@@ -1868,19 +1889,17 @@
 
 	priv = netdev_priv(netdev);
 
+	init_usb_anchor(&priv->tx_submitted);
 	init_completion(&priv->start_comp);
 	init_completion(&priv->stop_comp);
 
-	init_usb_anchor(&priv->tx_submitted);
-	atomic_set(&priv->active_tx_urbs, 0);
-
-	for (i = 0; i < ARRAY_SIZE(priv->tx_contexts); i++)
-		priv->tx_contexts[i].echo_index = MAX_TX_URBS;
-
 	priv->dev = dev;
 	priv->netdev = netdev;
 	priv->channel = channel;
 
+	spin_lock_init(&priv->tx_contexts_lock);
+	kvaser_usb_reset_tx_urb_contexts(priv);
+
 	priv->can.state = CAN_STATE_STOPPED;
 	priv->can.clock.freq = CAN_USB_CLOCK;
 	priv->can.bittiming_const = &kvaser_usb_bittiming_const;
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index 11d6e65..15a8190 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1543,7 +1543,7 @@
 {
 	struct pcnet32_private *lp;
 	int i, media;
-	int fdx, mii, fset, dxsuflo;
+	int fdx, mii, fset, dxsuflo, sram;
 	int chip_version;
 	char *chipname;
 	struct net_device *dev;
@@ -1580,7 +1580,7 @@
 	}
 
 	/* initialize variables */
-	fdx = mii = fset = dxsuflo = 0;
+	fdx = mii = fset = dxsuflo = sram = 0;
 	chip_version = (chip_version >> 12) & 0xffff;
 
 	switch (chip_version) {
@@ -1613,6 +1613,7 @@
 		chipname = "PCnet/FAST III 79C973";	/* PCI */
 		fdx = 1;
 		mii = 1;
+		sram = 1;
 		break;
 	case 0x2626:
 		chipname = "PCnet/Home 79C978";	/* PCI */
@@ -1636,6 +1637,7 @@
 		chipname = "PCnet/FAST III 79C975";	/* PCI */
 		fdx = 1;
 		mii = 1;
+		sram = 1;
 		break;
 	case 0x2628:
 		chipname = "PCnet/PRO 79C976";
@@ -1664,6 +1666,31 @@
 		dxsuflo = 1;
 	}
 
+	/*
+	 * The Am79C973/Am79C975 controllers come with 12K of SRAM
+	 * which we can use for the Tx/Rx buffers but most importantly,
+	 * the use of SRAM allow us to use the BCR18:NOUFLO bit to avoid
+	 * Tx fifo underflows.
+	 */
+	if (sram) {
+		/*
+		 * The SRAM is being configured in two steps. First we
+		 * set the SRAM size in the BCR25:SRAM_SIZE bits. According
+		 * to the datasheet, each bit corresponds to a 512-byte
+		 * page so we can have at most 24 pages. The SRAM_SIZE
+		 * holds the value of the upper 8 bits of the 16-bit SRAM size.
+		 * The low 8-bits start at 0x00 and end at 0xff. So the
+		 * address range is from 0x0000 up to 0x17ff. Therefore,
+		 * the SRAM_SIZE is set to 0x17. The next step is to set
+		 * the BCR26:SRAM_BND midway through so the Tx and Rx
+		 * buffers can share the SRAM equally.
+		 */
+		a->write_bcr(ioaddr, 25, 0x17);
+		a->write_bcr(ioaddr, 26, 0xc);
+		/* And finally enable the NOUFLO bit */
+		a->write_bcr(ioaddr, 18, a->read_bcr(ioaddr, 18) | (1 << 11));
+	}
+
 	dev = alloc_etherdev(sizeof(*lp));
 	if (!dev) {
 		ret = -ENOMEM;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index bef750a..996e215 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12769,7 +12769,7 @@
 		NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 |
 		NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO |
 		NETIF_F_RXHASH | NETIF_F_HW_VLAN_CTAG_TX;
-	if (!CHIP_IS_E1x(bp)) {
+	if (!chip_is_e1x) {
 		dev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL |
 				    NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT;
 		dev->hw_enc_features =
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 853c389..1abdfa1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -1120,7 +1120,7 @@
 		}
 
 		/* Installed successfully, update the cached header too. */
-		memcpy(card_fw, fs_fw, sizeof(*card_fw));
+		*card_fw = *fs_fw;
 		card_fw_usable = 1;
 		*reset = 0;	/* already reset as part of load_fw */
 	}
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 3b42556..ed41559 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -589,7 +589,7 @@
 			       (unsigned int)tp->rx_ring[i].buffer1,
 			       (unsigned int)tp->rx_ring[i].buffer2,
 			       buf[0], buf[1], buf[2]);
-			for (j = 0; buf[j] != 0xee && j < 1600; j++)
+			for (j = 0; ((j < 1600) && buf[j] != 0xee); j++)
 				if (j < 100)
 					pr_cont(" %02x", buf[j]);
 			pr_cont(" j=%d\n", j);
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 27de37a..27b9fe9 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -354,6 +354,7 @@
 	u16 vlan_tag;
 	u32 tx_rate;
 	u32 plink_tracking;
+	u32 privileges;
 };
 
 enum vf_state {
@@ -423,6 +424,7 @@
 
 	u8 __iomem *csr;	/* CSR BAR used only for BE2/3 */
 	u8 __iomem *db;		/* Door Bell */
+	u8 __iomem *pcicfg;	/* On SH,BEx only. Shadow of PCI config space */
 
 	struct mutex mbox_lock; /* For serializing mbox cmds to BE card */
 	struct be_dma_mem mbox_mem;
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 36916cf..7f05f30 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1902,15 +1902,11 @@
 {
 	int num_eqs, i = 0;
 
-	if (lancer_chip(adapter) && num > 8) {
-		while (num) {
-			num_eqs = min(num, 8);
-			__be_cmd_modify_eqd(adapter, &set_eqd[i], num_eqs);
-			i += num_eqs;
-			num -= num_eqs;
-		}
-	} else {
-		__be_cmd_modify_eqd(adapter, set_eqd, num);
+	while (num) {
+		num_eqs = min(num, 8);
+		__be_cmd_modify_eqd(adapter, &set_eqd[i], num_eqs);
+		i += num_eqs;
+		num -= num_eqs;
 	}
 
 	return 0;
@@ -1918,7 +1914,7 @@
 
 /* Uses sycnhronous mcc */
 int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
-		       u32 num)
+		       u32 num, u32 domain)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_vlan_config *req;
@@ -1936,6 +1932,7 @@
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
 			       OPCODE_COMMON_NTWK_VLAN_CONFIG, sizeof(*req),
 			       wrb, NULL);
+	req->hdr.domain = domain;
 
 	req->interface_id = if_id;
 	req->untagged = BE_IF_FLAGS_UNTAGGED & be_if_cap_flags(adapter) ? 1 : 0;
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index db761e8e..a7634a3 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -2256,7 +2256,7 @@
 int be_cmd_get_fw_ver(struct be_adapter *adapter);
 int be_cmd_modify_eqd(struct be_adapter *adapter, struct be_set_eqd *, int num);
 int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
-		       u32 num);
+		       u32 num, u32 domain);
 int be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 status);
 int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc);
 int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 0a81685..e6b790f 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1171,7 +1171,7 @@
 	for_each_set_bit(i, adapter->vids, VLAN_N_VID)
 		vids[num++] = cpu_to_le16(i);
 
-	status = be_cmd_vlan_config(adapter, adapter->if_handle, vids, num);
+	status = be_cmd_vlan_config(adapter, adapter->if_handle, vids, num, 0);
 	if (status) {
 		dev_err(dev, "Setting HW VLAN filtering failed\n");
 		/* Set to VLAN promisc mode as setting VLAN filter failed */
@@ -1380,11 +1380,67 @@
 	return 0;
 }
 
+static int be_set_vf_tvt(struct be_adapter *adapter, int vf, u16 vlan)
+{
+	struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
+	u16 vids[BE_NUM_VLANS_SUPPORTED];
+	int vf_if_id = vf_cfg->if_handle;
+	int status;
+
+	/* Enable Transparent VLAN Tagging */
+	status = be_cmd_set_hsw_config(adapter, vlan, vf + 1, vf_if_id, 0);
+	if (status)
+		return status;
+
+	/* Clear pre-programmed VLAN filters on VF if any, if TVT is enabled */
+	vids[0] = 0;
+	status = be_cmd_vlan_config(adapter, vf_if_id, vids, 1, vf + 1);
+	if (!status)
+		dev_info(&adapter->pdev->dev,
+			 "Cleared guest VLANs on VF%d", vf);
+
+	/* After TVT is enabled, disallow VFs to program VLAN filters */
+	if (vf_cfg->privileges & BE_PRIV_FILTMGMT) {
+		status = be_cmd_set_fn_privileges(adapter, vf_cfg->privileges &
+						  ~BE_PRIV_FILTMGMT, vf + 1);
+		if (!status)
+			vf_cfg->privileges &= ~BE_PRIV_FILTMGMT;
+	}
+	return 0;
+}
+
+static int be_clear_vf_tvt(struct be_adapter *adapter, int vf)
+{
+	struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
+	struct device *dev = &adapter->pdev->dev;
+	int status;
+
+	/* Reset Transparent VLAN Tagging. */
+	status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID, vf + 1,
+				       vf_cfg->if_handle, 0);
+	if (status)
+		return status;
+
+	/* Allow VFs to program VLAN filtering */
+	if (!(vf_cfg->privileges & BE_PRIV_FILTMGMT)) {
+		status = be_cmd_set_fn_privileges(adapter, vf_cfg->privileges |
+						  BE_PRIV_FILTMGMT, vf + 1);
+		if (!status) {
+			vf_cfg->privileges |= BE_PRIV_FILTMGMT;
+			dev_info(dev, "VF%d: FILTMGMT priv enabled", vf);
+		}
+	}
+
+	dev_info(dev,
+		 "Disable/re-enable i/f in VM to clear Transparent VLAN tag");
+	return 0;
+}
+
 static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
-	int status = 0;
+	int status;
 
 	if (!sriov_enabled(adapter))
 		return -EPERM;
@@ -1394,24 +1450,19 @@
 
 	if (vlan || qos) {
 		vlan |= qos << VLAN_PRIO_SHIFT;
-		if (vf_cfg->vlan_tag != vlan)
-			status = be_cmd_set_hsw_config(adapter, vlan, vf + 1,
-						       vf_cfg->if_handle, 0);
+		status = be_set_vf_tvt(adapter, vf, vlan);
 	} else {
-		/* Reset Transparent Vlan Tagging. */
-		status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID,
-					       vf + 1, vf_cfg->if_handle, 0);
+		status = be_clear_vf_tvt(adapter, vf);
 	}
 
 	if (status) {
 		dev_err(&adapter->pdev->dev,
-			"VLAN %d config on VF %d failed : %#x\n", vlan,
-			vf, status);
+			"VLAN %d config on VF %d failed : %#x\n", vlan, vf,
+			status);
 		return be_cmd_status(status);
 	}
 
 	vf_cfg->vlan_tag = vlan;
-
 	return 0;
 }
 
@@ -2772,14 +2823,12 @@
 			}
 		}
 	} else {
-		pci_read_config_dword(adapter->pdev,
-				      PCICFG_UE_STATUS_LOW, &ue_lo);
-		pci_read_config_dword(adapter->pdev,
-				      PCICFG_UE_STATUS_HIGH, &ue_hi);
-		pci_read_config_dword(adapter->pdev,
-				      PCICFG_UE_STATUS_LOW_MASK, &ue_lo_mask);
-		pci_read_config_dword(adapter->pdev,
-				      PCICFG_UE_STATUS_HI_MASK, &ue_hi_mask);
+		ue_lo = ioread32(adapter->pcicfg + PCICFG_UE_STATUS_LOW);
+		ue_hi = ioread32(adapter->pcicfg + PCICFG_UE_STATUS_HIGH);
+		ue_lo_mask = ioread32(adapter->pcicfg +
+				      PCICFG_UE_STATUS_LOW_MASK);
+		ue_hi_mask = ioread32(adapter->pcicfg +
+				      PCICFG_UE_STATUS_HI_MASK);
 
 		ue_lo = (ue_lo & ~ue_lo_mask);
 		ue_hi = (ue_hi & ~ue_hi_mask);
@@ -3339,7 +3388,6 @@
 			u32 cap_flags, u32 vf)
 {
 	u32 en_flags;
-	int status;
 
 	en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
 		   BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |
@@ -3347,10 +3395,7 @@
 
 	en_flags &= cap_flags;
 
-	status = be_cmd_if_create(adapter, cap_flags, en_flags,
-				  if_handle, vf);
-
-	return status;
+	return be_cmd_if_create(adapter, cap_flags, en_flags, if_handle, vf);
 }
 
 static int be_vfs_if_create(struct be_adapter *adapter)
@@ -3368,8 +3413,13 @@
 		if (!BE3_chip(adapter)) {
 			status = be_cmd_get_profile_config(adapter, &res,
 							   vf + 1);
-			if (!status)
+			if (!status) {
 				cap_flags = res.if_cap_flags;
+				/* Prevent VFs from enabling VLAN promiscuous
+				 * mode
+				 */
+				cap_flags &= ~BE_IF_FLAGS_VLAN_PROMISCUOUS;
+			}
 		}
 
 		status = be_if_create(adapter, &vf_cfg->if_handle,
@@ -3403,7 +3453,6 @@
 	struct device *dev = &adapter->pdev->dev;
 	struct be_vf_cfg *vf_cfg;
 	int status, old_vfs, vf;
-	u32 privileges;
 
 	old_vfs = pci_num_vf(adapter->pdev);
 
@@ -3433,15 +3482,18 @@
 
 	for_all_vfs(adapter, vf_cfg, vf) {
 		/* Allow VFs to programs MAC/VLAN filters */
-		status = be_cmd_get_fn_privileges(adapter, &privileges, vf + 1);
-		if (!status && !(privileges & BE_PRIV_FILTMGMT)) {
+		status = be_cmd_get_fn_privileges(adapter, &vf_cfg->privileges,
+						  vf + 1);
+		if (!status && !(vf_cfg->privileges & BE_PRIV_FILTMGMT)) {
 			status = be_cmd_set_fn_privileges(adapter,
-							  privileges |
+							  vf_cfg->privileges |
 							  BE_PRIV_FILTMGMT,
 							  vf + 1);
-			if (!status)
+			if (!status) {
+				vf_cfg->privileges |= BE_PRIV_FILTMGMT;
 				dev_info(dev, "VF%d has FILTMGMT privilege\n",
 					 vf);
+			}
 		}
 
 		/* Allow full available bandwidth */
@@ -4820,24 +4872,37 @@
 
 static int be_map_pci_bars(struct be_adapter *adapter)
 {
+	struct pci_dev *pdev = adapter->pdev;
 	u8 __iomem *addr;
 
 	if (BEx_chip(adapter) && be_physfn(adapter)) {
-		adapter->csr = pci_iomap(adapter->pdev, 2, 0);
+		adapter->csr = pci_iomap(pdev, 2, 0);
 		if (!adapter->csr)
 			return -ENOMEM;
 	}
 
-	addr = pci_iomap(adapter->pdev, db_bar(adapter), 0);
+	addr = pci_iomap(pdev, db_bar(adapter), 0);
 	if (!addr)
 		goto pci_map_err;
 	adapter->db = addr;
 
+	if (skyhawk_chip(adapter) || BEx_chip(adapter)) {
+		if (be_physfn(adapter)) {
+			/* PCICFG is the 2nd BAR in BE2 */
+			addr = pci_iomap(pdev, BE2_chip(adapter) ? 1 : 0, 0);
+			if (!addr)
+				goto pci_map_err;
+			adapter->pcicfg = addr;
+		} else {
+			adapter->pcicfg = adapter->db + SRIOV_VF_PCICFG_OFFSET;
+		}
+	}
+
 	be_roce_map_pci_bars(adapter);
 	return 0;
 
 pci_map_err:
-	dev_err(&adapter->pdev->dev, "Error in mapping PCI BARs\n");
+	dev_err(&pdev->dev, "Error in mapping PCI BARs\n");
 	be_unmap_pci_bars(adapter);
 	return -ENOMEM;
 }
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 99492b7..78e1ce0 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1189,13 +1189,12 @@
 fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 {
 	struct	fec_enet_private *fep;
-	struct bufdesc *bdp, *bdp_t;
+	struct bufdesc *bdp;
 	unsigned short status;
 	struct	sk_buff	*skb;
 	struct fec_enet_priv_tx_q *txq;
 	struct netdev_queue *nq;
 	int	index = 0;
-	int	i, bdnum;
 	int	entries_free;
 
 	fep = netdev_priv(ndev);
@@ -1216,29 +1215,18 @@
 		if (bdp == txq->cur_tx)
 			break;
 
-		bdp_t = bdp;
-		bdnum = 1;
-		index = fec_enet_get_bd_index(txq->tx_bd_base, bdp_t, fep);
-		skb = txq->tx_skbuff[index];
-		while (!skb) {
-			bdp_t = fec_enet_get_nextdesc(bdp_t, fep, queue_id);
-			index = fec_enet_get_bd_index(txq->tx_bd_base, bdp_t, fep);
-			skb = txq->tx_skbuff[index];
-			bdnum++;
-		}
-		if (skb_shinfo(skb)->nr_frags &&
-		    (status = bdp_t->cbd_sc) & BD_ENET_TX_READY)
-			break;
+		index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep);
 
-		for (i = 0; i < bdnum; i++) {
-			if (!IS_TSO_HEADER(txq, bdp->cbd_bufaddr))
-				dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
-						 bdp->cbd_datlen, DMA_TO_DEVICE);
-			bdp->cbd_bufaddr = 0;
-			if (i < bdnum - 1)
-				bdp = fec_enet_get_nextdesc(bdp, fep, queue_id);
-		}
+		skb = txq->tx_skbuff[index];
 		txq->tx_skbuff[index] = NULL;
+		if (!IS_TSO_HEADER(txq, bdp->cbd_bufaddr))
+			dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
+					bdp->cbd_datlen, DMA_TO_DEVICE);
+		bdp->cbd_bufaddr = 0;
+		if (!skb) {
+			bdp = fec_enet_get_nextdesc(bdp, fep, queue_id);
+			continue;
+		}
 
 		/* Check for errors. */
 		if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC |
@@ -1479,8 +1467,7 @@
 
 			vlan_packet_rcvd = true;
 
-			skb_copy_to_linear_data_offset(skb, VLAN_HLEN,
-						       data, (2 * ETH_ALEN));
+			memmove(skb->data + VLAN_HLEN, data, ETH_ALEN * 2);
 			skb_pull(skb, VLAN_HLEN);
 		}
 
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 072426a..cd7675a 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1136,6 +1136,8 @@
 	ibmveth_replenish_task(adapter);
 
 	if (frames_processed < budget) {
+		napi_complete(napi);
+
 		/* We think we are done - reenable interrupts,
 		 * then check once more to make sure we are done.
 		 */
@@ -1144,8 +1146,6 @@
 
 		BUG_ON(lpar_rc != H_SUCCESS);
 
-		napi_complete(napi);
-
 		if (ibmveth_rxq_pending_buffer(adapter) &&
 		    napi_reschedule(napi)) {
 			lpar_rc = h_vio_signal(adapter->vdev->unit_address,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 2a210c4..ebce5bb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1698,8 +1698,6 @@
 	/* Schedule multicast task to populate multicast list */
 	queue_work(mdev->workqueue, &priv->rx_mode_task);
 
-	mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap);
-
 #ifdef CONFIG_MLX4_EN_VXLAN
 	if (priv->mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		vxlan_get_rx_port(dev);
@@ -2853,6 +2851,8 @@
 		queue_delayed_work(mdev->workqueue, &priv->service_task,
 				   SERVICE_TASK_DELAY);
 
+	mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap);
+
 	return 0;
 
 out:
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 2a8268e..ebbe244 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -453,7 +453,7 @@
 	unsigned long rx_chksum_none;
 	unsigned long rx_chksum_complete;
 	unsigned long tx_chksum_offload;
-#define NUM_PORT_STATS		9
+#define NUM_PORT_STATS		10
 };
 
 struct mlx4_en_perf_stats {
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 5d093dc..8678e39 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2248,10 +2248,9 @@
 	const struct of_device_id *match = NULL;
 	struct smc_local *lp;
 	struct net_device *ndev;
-	struct resource *res;
+	struct resource *res, *ires;
 	unsigned int __iomem *addr;
 	unsigned long irq_flags = SMC_IRQ_FLAGS;
-	unsigned long irq_resflags;
 	int ret;
 
 	ndev = alloc_etherdev(sizeof(struct smc_local));
@@ -2343,19 +2342,16 @@
 		goto out_free_netdev;
 	}
 
-	ndev->irq = platform_get_irq(pdev, 0);
-	if (ndev->irq <= 0) {
+	ires = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!ires) {
 		ret = -ENODEV;
 		goto out_release_io;
 	}
-	/*
-	 * If this platform does not specify any special irqflags, or if
-	 * the resource supplies a trigger, override the irqflags with
-	 * the trigger flags from the resource.
-	 */
-	irq_resflags = irqd_get_trigger_type(irq_get_irq_data(ndev->irq));
-	if (irq_flags == -1 || irq_resflags & IRQF_TRIGGER_MASK)
-		irq_flags = irq_resflags & IRQF_TRIGGER_MASK;
+
+	ndev->irq = ires->start;
+
+	if (irq_flags == -1 || ires->flags & IRQF_TRIGGER_MASK)
+		irq_flags = ires->flags & IRQF_TRIGGER_MASK;
 
 	ret = smc_request_attrib(pdev, ndev);
 	if (ret)
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index a495931..0e0fbb5 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -498,9 +498,9 @@
 	}
 
 	if (rx_count < budget) {
+		napi_complete(napi);
 		w5100_write(priv, W5100_IMR, IR_S0);
 		mmiowb();
-		napi_complete(napi);
 	}
 
 	return rx_count;
diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c
index 09322d9..4b31000 100644
--- a/drivers/net/ethernet/wiznet/w5300.c
+++ b/drivers/net/ethernet/wiznet/w5300.c
@@ -418,9 +418,9 @@
 	}
 
 	if (rx_count < budget) {
+		napi_complete(napi);
 		w5300_write(priv, W5300_IMR, IR_S0);
 		mmiowb();
-		napi_complete(napi);
 	}
 
 	return rx_count;
diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c
index 3eed708..1762ad3 100644
--- a/drivers/net/usb/cx82310_eth.c
+++ b/drivers/net/usb/cx82310_eth.c
@@ -46,8 +46,7 @@
 };
 
 #define CMD_PACKET_SIZE	64
-/* first command after power on can take around 8 seconds */
-#define CMD_TIMEOUT	15000
+#define CMD_TIMEOUT	100
 #define CMD_REPLY_RETRY 5
 
 #define CX82310_MTU	1514
@@ -78,8 +77,9 @@
 	ret = usb_bulk_msg(udev, usb_sndbulkpipe(udev, CMD_EP), buf,
 			   CMD_PACKET_SIZE, &actual_len, CMD_TIMEOUT);
 	if (ret < 0) {
-		dev_err(&dev->udev->dev, "send command %#x: error %d\n",
-			cmd, ret);
+		if (cmd != CMD_GET_LINK_STATUS)
+			dev_err(&dev->udev->dev, "send command %#x: error %d\n",
+				cmd, ret);
 		goto end;
 	}
 
@@ -90,8 +90,10 @@
 					   buf, CMD_PACKET_SIZE, &actual_len,
 					   CMD_TIMEOUT);
 			if (ret < 0) {
-				dev_err(&dev->udev->dev,
-					"reply receive error %d\n", ret);
+				if (cmd != CMD_GET_LINK_STATUS)
+					dev_err(&dev->udev->dev,
+						"reply receive error %d\n",
+						ret);
 				goto end;
 			}
 			if (actual_len > 0)
@@ -134,6 +136,8 @@
 	int ret;
 	char buf[15];
 	struct usb_device *udev = dev->udev;
+	u8 link[3];
+	int timeout = 50;
 
 	/* avoid ADSL modems - continue only if iProduct is "USB NET CARD" */
 	if (usb_string(udev, udev->descriptor.iProduct, buf, sizeof(buf)) > 0
@@ -160,6 +164,20 @@
 	if (!dev->partial_data)
 		return -ENOMEM;
 
+	/* wait for firmware to become ready (indicated by the link being up) */
+	while (--timeout) {
+		ret = cx82310_cmd(dev, CMD_GET_LINK_STATUS, true, NULL, 0,
+				  link, sizeof(link));
+		/* the command can time out during boot - it's not an error */
+		if (!ret && link[0] == 1 && link[2] == 1)
+			break;
+		msleep(500);
+	};
+	if (!timeout) {
+		dev_err(&udev->dev, "firmware not ready in time\n");
+		return -ETIMEDOUT;
+	}
+
 	/* enable ethernet mode (?) */
 	ret = cx82310_cmd(dev, CMD_ETHERNET_MODE, true, "\x01", 1, NULL, 0);
 	if (ret) {
@@ -300,9 +318,18 @@
 	.tx_fixup	= cx82310_tx_fixup,
 };
 
+#define USB_DEVICE_CLASS(vend, prod, cl, sc, pr) \
+	.match_flags = USB_DEVICE_ID_MATCH_DEVICE | \
+		       USB_DEVICE_ID_MATCH_DEV_INFO, \
+	.idVendor = (vend), \
+	.idProduct = (prod), \
+	.bDeviceClass = (cl), \
+	.bDeviceSubClass = (sc), \
+	.bDeviceProtocol = (pr)
+
 static const struct usb_device_id products[] = {
 	{
-		USB_DEVICE_AND_INTERFACE_INFO(0x0572, 0xcb01, 0xff, 0, 0),
+		USB_DEVICE_CLASS(0x0572, 0xcb01, 0xff, 0, 0),
 		.driver_info = (unsigned long) &cx82310_info
 	},
 	{ },
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index f1ff366..59b0e97 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1448,8 +1448,10 @@
 {
 	int i;
 
-	for (i = 0; i < vi->max_queue_pairs; i++)
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		napi_hash_del(&vi->rq[i].napi);
 		netif_napi_del(&vi->rq[i].napi);
+	}
 
 	kfree(vi->rq);
 	kfree(vi->sq);
@@ -1948,11 +1950,8 @@
 	cancel_delayed_work_sync(&vi->refill);
 
 	if (netif_running(vi->dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			napi_disable(&vi->rq[i].napi);
-			napi_hash_del(&vi->rq[i].napi);
-			netif_napi_del(&vi->rq[i].napi);
-		}
 	}
 
 	remove_vq_common(vi);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 1e0a775..f8528a4 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1218,7 +1218,7 @@
 			goto drop;
 
 		flags &= ~VXLAN_HF_RCO;
-		vni &= VXLAN_VID_MASK;
+		vni &= VXLAN_VNI_MASK;
 	}
 
 	/* For backwards compatibility, only allow reserved fields to be
@@ -1239,7 +1239,7 @@
 		flags &= ~VXLAN_GBP_USED_BITS;
 	}
 
-	if (flags || (vni & ~VXLAN_VID_MASK)) {
+	if (flags || vni & ~VXLAN_VNI_MASK) {
 		/* If there are any unprocessed flags remaining treat
 		 * this as a malformed packet. This behavior diverges from
 		 * VXLAN RFC (RFC7348) which stipulates that bits in reserved
diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c
index ccbdb05..75345c1 100644
--- a/drivers/net/wireless/b43/main.c
+++ b/drivers/net/wireless/b43/main.c
@@ -5370,6 +5370,7 @@
 	case 0x432a: /* BCM4321 */
 	case 0x432d: /* BCM4322 */
 	case 0x4352: /* BCM43222 */
+	case 0x435a: /* BCM43228 */
 	case 0x4333: /* BCM4331 */
 	case 0x43a2: /* BCM4360 */
 	case 0x43b3: /* BCM4352 */
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/vendor.c b/drivers/net/wireless/brcm80211/brcmfmac/vendor.c
index 50cdf70..8eff275 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/vendor.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/vendor.c
@@ -39,13 +39,22 @@
 	void *dcmd_buf = NULL, *wr_pointer;
 	u16 msglen, maxmsglen = PAGE_SIZE - 0x100;
 
-	brcmf_dbg(TRACE, "cmd %x set %d len %d\n", cmdhdr->cmd, cmdhdr->set,
-		  cmdhdr->len);
+	if (len < sizeof(*cmdhdr)) {
+		brcmf_err("vendor command too short: %d\n", len);
+		return -EINVAL;
+	}
 
 	vif = container_of(wdev, struct brcmf_cfg80211_vif, wdev);
 	ifp = vif->ifp;
 
-	len -= sizeof(struct brcmf_vndr_dcmd_hdr);
+	brcmf_dbg(TRACE, "ifidx=%d, cmd=%d\n", ifp->ifidx, cmdhdr->cmd);
+
+	if (cmdhdr->offset > len) {
+		brcmf_err("bad buffer offset %d > %d\n", cmdhdr->offset, len);
+		return -EINVAL;
+	}
+
+	len -= cmdhdr->offset;
 	ret_len = cmdhdr->len;
 	if (ret_len > 0 || len > 0) {
 		if (len > BRCMF_DCMD_MAXLEN) {
diff --git a/drivers/net/wireless/iwlwifi/iwl-1000.c b/drivers/net/wireless/iwlwifi/iwl-1000.c
index c3817fa..06f6cc0 100644
--- a/drivers/net/wireless/iwlwifi/iwl-1000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-1000.c
@@ -95,7 +95,8 @@
 	.nvm_calib_ver = EEPROM_1000_TX_POWER_VERSION,	\
 	.base_params = &iwl1000_base_params,			\
 	.eeprom_params = &iwl1000_eeprom_params,		\
-	.led_mode = IWL_LED_BLINK
+	.led_mode = IWL_LED_BLINK,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl1000_bgn_cfg = {
 	.name = "Intel(R) Centrino(R) Wireless-N 1000 BGN",
@@ -121,7 +122,8 @@
 	.base_params = &iwl1000_base_params,			\
 	.eeprom_params = &iwl1000_eeprom_params,		\
 	.led_mode = IWL_LED_RF_STATE,				\
-	.rx_with_siso_diversity = true
+	.rx_with_siso_diversity = true,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl100_bgn_cfg = {
 	.name = "Intel(R) Centrino(R) Wireless-N 100 BGN",
diff --git a/drivers/net/wireless/iwlwifi/iwl-2000.c b/drivers/net/wireless/iwlwifi/iwl-2000.c
index 21e5d08..890b95f 100644
--- a/drivers/net/wireless/iwlwifi/iwl-2000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-2000.c
@@ -123,7 +123,9 @@
 	.nvm_calib_ver = EEPROM_2000_TX_POWER_VERSION,		\
 	.base_params = &iwl2000_base_params,			\
 	.eeprom_params = &iwl20x0_eeprom_params,		\
-	.led_mode = IWL_LED_RF_STATE
+	.led_mode = IWL_LED_RF_STATE,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
+
 
 const struct iwl_cfg iwl2000_2bgn_cfg = {
 	.name = "Intel(R) Centrino(R) Wireless-N 2200 BGN",
@@ -149,7 +151,8 @@
 	.nvm_calib_ver = EEPROM_2000_TX_POWER_VERSION,	\
 	.base_params = &iwl2030_base_params,			\
 	.eeprom_params = &iwl20x0_eeprom_params,		\
-	.led_mode = IWL_LED_RF_STATE
+	.led_mode = IWL_LED_RF_STATE,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl2030_2bgn_cfg = {
 	.name = "Intel(R) Centrino(R) Wireless-N 2230 BGN",
@@ -170,7 +173,8 @@
 	.base_params = &iwl2000_base_params,			\
 	.eeprom_params = &iwl20x0_eeprom_params,		\
 	.led_mode = IWL_LED_RF_STATE,				\
-	.rx_with_siso_diversity = true
+	.rx_with_siso_diversity = true,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl105_bgn_cfg = {
 	.name = "Intel(R) Centrino(R) Wireless-N 105 BGN",
@@ -197,7 +201,8 @@
 	.base_params = &iwl2030_base_params,			\
 	.eeprom_params = &iwl20x0_eeprom_params,		\
 	.led_mode = IWL_LED_RF_STATE,				\
-	.rx_with_siso_diversity = true
+	.rx_with_siso_diversity = true,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl135_bgn_cfg = {
 	.name = "Intel(R) Centrino(R) Wireless-N 135 BGN",
diff --git a/drivers/net/wireless/iwlwifi/iwl-5000.c b/drivers/net/wireless/iwlwifi/iwl-5000.c
index 332bbed..724194e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-5000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-5000.c
@@ -93,7 +93,8 @@
 	.nvm_calib_ver = EEPROM_5000_TX_POWER_VERSION,	\
 	.base_params = &iwl5000_base_params,			\
 	.eeprom_params = &iwl5000_eeprom_params,		\
-	.led_mode = IWL_LED_BLINK
+	.led_mode = IWL_LED_BLINK,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl5300_agn_cfg = {
 	.name = "Intel(R) Ultimate N WiFi Link 5300 AGN",
@@ -158,7 +159,8 @@
 	.base_params = &iwl5000_base_params,			\
 	.eeprom_params = &iwl5000_eeprom_params,		\
 	.led_mode = IWL_LED_BLINK,				\
-	.internal_wimax_coex = true
+	.internal_wimax_coex = true,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl5150_agn_cfg = {
 	.name = "Intel(R) WiMAX/WiFi Link 5150 AGN",
diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c
index 8f2c3c8..21b2630 100644
--- a/drivers/net/wireless/iwlwifi/iwl-6000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-6000.c
@@ -145,7 +145,8 @@
 	.nvm_calib_ver = EEPROM_6005_TX_POWER_VERSION,	\
 	.base_params = &iwl6000_g2_base_params,			\
 	.eeprom_params = &iwl6000_eeprom_params,		\
-	.led_mode = IWL_LED_RF_STATE
+	.led_mode = IWL_LED_RF_STATE,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl6005_2agn_cfg = {
 	.name = "Intel(R) Centrino(R) Advanced-N 6205 AGN",
@@ -199,7 +200,8 @@
 	.nvm_calib_ver = EEPROM_6030_TX_POWER_VERSION,	\
 	.base_params = &iwl6000_g2_base_params,			\
 	.eeprom_params = &iwl6000_eeprom_params,		\
-	.led_mode = IWL_LED_RF_STATE
+	.led_mode = IWL_LED_RF_STATE,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl6030_2agn_cfg = {
 	.name = "Intel(R) Centrino(R) Advanced-N 6230 AGN",
@@ -235,7 +237,8 @@
 	.nvm_calib_ver = EEPROM_6030_TX_POWER_VERSION,	\
 	.base_params = &iwl6000_g2_base_params,			\
 	.eeprom_params = &iwl6000_eeprom_params,		\
-	.led_mode = IWL_LED_RF_STATE
+	.led_mode = IWL_LED_RF_STATE,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl6035_2agn_cfg = {
 	.name = "Intel(R) Centrino(R) Advanced-N 6235 AGN",
@@ -290,7 +293,8 @@
 	.nvm_calib_ver = EEPROM_6000_TX_POWER_VERSION,	\
 	.base_params = &iwl6000_base_params,			\
 	.eeprom_params = &iwl6000_eeprom_params,		\
-	.led_mode = IWL_LED_BLINK
+	.led_mode = IWL_LED_BLINK,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl6000i_2agn_cfg = {
 	.name = "Intel(R) Centrino(R) Advanced-N 6200 AGN",
@@ -322,7 +326,8 @@
 	.base_params = &iwl6050_base_params,			\
 	.eeprom_params = &iwl6000_eeprom_params,		\
 	.led_mode = IWL_LED_BLINK,				\
-	.internal_wimax_coex = true
+	.internal_wimax_coex = true,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl6050_2agn_cfg = {
 	.name = "Intel(R) Centrino(R) Advanced-N + WiMAX 6250 AGN",
@@ -347,7 +352,8 @@
 	.base_params = &iwl6050_base_params,			\
 	.eeprom_params = &iwl6000_eeprom_params,		\
 	.led_mode = IWL_LED_BLINK,				\
-	.internal_wimax_coex = true
+	.internal_wimax_coex = true,				\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K
 
 const struct iwl_cfg iwl6150_bgn_cfg = {
 	.name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BGN",
diff --git a/drivers/net/wireless/iwlwifi/mvm/coex.c b/drivers/net/wireless/iwlwifi/mvm/coex.c
index 1ec4d55..7810c41 100644
--- a/drivers/net/wireless/iwlwifi/mvm/coex.c
+++ b/drivers/net/wireless/iwlwifi/mvm/coex.c
@@ -793,7 +793,8 @@
 	if (!vif->bss_conf.assoc)
 		smps_mode = IEEE80211_SMPS_AUTOMATIC;
 
-	if (IWL_COEX_IS_RRC_ON(mvm->last_bt_notif.ttc_rrc_status,
+	if (mvmvif->phy_ctxt &&
+	    IWL_COEX_IS_RRC_ON(mvm->last_bt_notif.ttc_rrc_status,
 			       mvmvif->phy_ctxt->id))
 		smps_mode = IEEE80211_SMPS_AUTOMATIC;
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c b/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c
index d530ef3..542ee74 100644
--- a/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c
+++ b/drivers/net/wireless/iwlwifi/mvm/coex_legacy.c
@@ -832,7 +832,8 @@
 	if (!vif->bss_conf.assoc)
 		smps_mode = IEEE80211_SMPS_AUTOMATIC;
 
-	if (data->notif->rrc_enabled & BIT(mvmvif->phy_ctxt->id))
+	if (mvmvif->phy_ctxt &&
+	    data->notif->rrc_enabled & BIT(mvmvif->phy_ctxt->id))
 		smps_mode = IEEE80211_SMPS_AUTOMATIC;
 
 	IWL_DEBUG_COEX(data->mvm,
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index 1ff7ec0..09654e7 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -405,7 +405,10 @@
 		hw->wiphy->bands[IEEE80211_BAND_5GHZ] =
 			&mvm->nvm_data->bands[IEEE80211_BAND_5GHZ];
 
-		if (mvm->fw->ucode_capa.capa[0] & IWL_UCODE_TLV_CAPA_BEAMFORMER)
+		if ((mvm->fw->ucode_capa.capa[0] &
+		     IWL_UCODE_TLV_CAPA_BEAMFORMER) &&
+		    (mvm->fw->ucode_capa.api[0] &
+		     IWL_UCODE_TLV_API_LQ_SS_PARAMS))
 			hw->wiphy->bands[IEEE80211_BAND_5GHZ]->vht_cap.cap |=
 				IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE;
 	}
@@ -2215,7 +2218,19 @@
 
 	mutex_lock(&mvm->mutex);
 
-	iwl_mvm_cancel_scan(mvm);
+	/* Due to a race condition, it's possible that mac80211 asks
+	 * us to stop a hw_scan when it's already stopped.  This can
+	 * happen, for instance, if we stopped the scan ourselves,
+	 * called ieee80211_scan_completed() and the userspace called
+	 * cancel scan scan before ieee80211_scan_work() could run.
+	 * To handle that, simply return if the scan is not running.
+	*/
+	/* FIXME: for now, we ignore this race for UMAC scans, since
+	 * they don't set the scan_status.
+	 */
+	if ((mvm->scan_status == IWL_MVM_SCAN_OS) ||
+	    (mvm->fw->ucode_capa.capa[0] & IWL_UCODE_TLV_CAPA_UMAC_SCAN))
+		iwl_mvm_cancel_scan(mvm);
 
 	mutex_unlock(&mvm->mutex);
 }
@@ -2559,12 +2574,29 @@
 	int ret;
 
 	mutex_lock(&mvm->mutex);
+
+	/* Due to a race condition, it's possible that mac80211 asks
+	 * us to stop a sched_scan when it's already stopped.  This
+	 * can happen, for instance, if we stopped the scan ourselves,
+	 * called ieee80211_sched_scan_stopped() and the userspace called
+	 * stop sched scan scan before ieee80211_sched_scan_stopped_work()
+	 * could run.  To handle this, simply return if the scan is
+	 * not running.
+	*/
+	/* FIXME: for now, we ignore this race for UMAC scans, since
+	 * they don't set the scan_status.
+	 */
+	if (mvm->scan_status != IWL_MVM_SCAN_SCHED &&
+	    !(mvm->fw->ucode_capa.capa[0] & IWL_UCODE_TLV_CAPA_UMAC_SCAN)) {
+		mutex_unlock(&mvm->mutex);
+		return 0;
+	}
+
 	ret = iwl_mvm_scan_offload_stop(mvm, false);
 	mutex_unlock(&mvm->mutex);
 	iwl_mvm_wait_for_async_handlers(mvm);
 
 	return ret;
-
 }
 
 static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/iwlwifi/mvm/rs.c b/drivers/net/wireless/iwlwifi/mvm/rs.c
index 194bd1f..efa9688 100644
--- a/drivers/net/wireless/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/iwlwifi/mvm/rs.c
@@ -134,9 +134,12 @@
 #define MAX_NEXT_COLUMNS 7
 #define MAX_COLUMN_CHECKS 3
 
+struct rs_tx_column;
+
 typedef bool (*allow_column_func_t) (struct iwl_mvm *mvm,
 				     struct ieee80211_sta *sta,
-				     struct iwl_scale_tbl_info *tbl);
+				     struct iwl_scale_tbl_info *tbl,
+				     const struct rs_tx_column *next_col);
 
 struct rs_tx_column {
 	enum rs_column_mode mode;
@@ -147,13 +150,15 @@
 };
 
 static bool rs_ant_allow(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
-			 struct iwl_scale_tbl_info *tbl)
+			 struct iwl_scale_tbl_info *tbl,
+			 const struct rs_tx_column *next_col)
 {
-	return iwl_mvm_bt_coex_is_ant_avail(mvm, tbl->rate.ant);
+	return iwl_mvm_bt_coex_is_ant_avail(mvm, next_col->ant);
 }
 
 static bool rs_mimo_allow(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
-			  struct iwl_scale_tbl_info *tbl)
+			  struct iwl_scale_tbl_info *tbl,
+			  const struct rs_tx_column *next_col)
 {
 	if (!sta->ht_cap.ht_supported)
 		return false;
@@ -171,7 +176,8 @@
 }
 
 static bool rs_siso_allow(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
-			  struct iwl_scale_tbl_info *tbl)
+			  struct iwl_scale_tbl_info *tbl,
+			  const struct rs_tx_column *next_col)
 {
 	if (!sta->ht_cap.ht_supported)
 		return false;
@@ -180,7 +186,8 @@
 }
 
 static bool rs_sgi_allow(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
-			 struct iwl_scale_tbl_info *tbl)
+			 struct iwl_scale_tbl_info *tbl,
+			 const struct rs_tx_column *next_col)
 {
 	struct rs_rate *rate = &tbl->rate;
 	struct ieee80211_sta_ht_cap *ht_cap = &sta->ht_cap;
@@ -1590,7 +1597,7 @@
 
 		for (j = 0; j < MAX_COLUMN_CHECKS; j++) {
 			allow_func = next_col->checks[j];
-			if (allow_func && !allow_func(mvm, sta, tbl))
+			if (allow_func && !allow_func(mvm, sta, tbl, next_col))
 				break;
 		}
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index 7e9aa3c..c47c8051 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -1128,8 +1128,10 @@
 	if (mvm->scan_status == IWL_MVM_SCAN_NONE)
 		return 0;
 
-	if (iwl_mvm_is_radio_killed(mvm))
+	if (iwl_mvm_is_radio_killed(mvm)) {
+		ret = 0;
 		goto out;
+	}
 
 	if (mvm->scan_status != IWL_MVM_SCAN_SCHED &&
 	    (!(mvm->fw->ucode_capa.api[0] & IWL_UCODE_TLV_API_LMAC_SCAN) ||
@@ -1148,16 +1150,14 @@
 		IWL_DEBUG_SCAN(mvm, "Send stop %sscan failed %d\n",
 			       sched ? "offloaded " : "", ret);
 		iwl_remove_notification(&mvm->notif_wait, &wait_scan_done);
-		return ret;
+		goto out;
 	}
 
 	IWL_DEBUG_SCAN(mvm, "Successfully sent stop %sscan\n",
 		       sched ? "offloaded " : "");
 
 	ret = iwl_wait_notification(&mvm->notif_wait, &wait_scan_done, 1 * HZ);
-	if (ret)
-		return ret;
-
+out:
 	/*
 	 * Clear the scan status so the next scan requests will succeed. This
 	 * also ensures the Rx handler doesn't do anything, as the scan was
@@ -1167,7 +1167,6 @@
 	if (mvm->scan_status == IWL_MVM_SCAN_OS)
 		iwl_mvm_unref(mvm, IWL_MVM_REF_SCAN);
 
-out:
 	mvm->scan_status = IWL_MVM_SCAN_NONE;
 
 	if (notify) {
@@ -1177,7 +1176,7 @@
 			ieee80211_scan_completed(mvm->hw, true);
 	}
 
-	return 0;
+	return ret;
 }
 
 static void iwl_mvm_unified_scan_fill_tx_cmd(struct iwl_mvm *mvm,
diff --git a/drivers/net/wireless/iwlwifi/mvm/time-event.c b/drivers/net/wireless/iwlwifi/mvm/time-event.c
index 54fafbf..f8d6f30 100644
--- a/drivers/net/wireless/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/iwlwifi/mvm/time-event.c
@@ -750,8 +750,7 @@
 	 * request
 	 */
 	list_for_each_entry(te_data, &mvm->time_event_list, list) {
-		if (te_data->vif->type == NL80211_IFTYPE_P2P_DEVICE &&
-		    te_data->running) {
+		if (te_data->vif->type == NL80211_IFTYPE_P2P_DEVICE) {
 			mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif);
 			is_p2p = true;
 			goto remove_te;
@@ -766,10 +765,8 @@
 	 * request
 	 */
 	list_for_each_entry(te_data, &mvm->aux_roc_te_list, list) {
-		if (te_data->running) {
-			mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif);
-			goto remove_te;
-		}
+		mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif);
+		goto remove_te;
 	}
 
 remove_te:
diff --git a/drivers/net/wireless/rtlwifi/base.c b/drivers/net/wireless/rtlwifi/base.c
index 1d46774..074f716 100644
--- a/drivers/net/wireless/rtlwifi/base.c
+++ b/drivers/net/wireless/rtlwifi/base.c
@@ -1386,8 +1386,11 @@
 		}
 
 		return true;
-	} else if (0x86DD == ether_type) {
-		return true;
+	} else if (ETH_P_IPV6 == ether_type) {
+		/* TODO: Handle any IPv6 cases that need special handling.
+		 * For now, always return false
+		 */
+		goto end;
 	}
 
 end:
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index cab9f52..997cf09 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -96,6 +96,7 @@
 static void make_tx_response(struct xenvif_queue *queue,
 			     struct xen_netif_tx_request *txp,
 			     s8       st);
+static void push_tx_responses(struct xenvif_queue *queue);
 
 static inline int tx_work_todo(struct xenvif_queue *queue);
 
@@ -655,15 +656,10 @@
 	unsigned long flags;
 
 	do {
-		int notify;
-
 		spin_lock_irqsave(&queue->response_lock, flags);
 		make_tx_response(queue, txp, XEN_NETIF_RSP_ERROR);
-		RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify);
+		push_tx_responses(queue);
 		spin_unlock_irqrestore(&queue->response_lock, flags);
-		if (notify)
-			notify_remote_via_irq(queue->tx_irq);
-
 		if (cons == end)
 			break;
 		txp = RING_GET_REQUEST(&queue->tx, cons++);
@@ -1657,7 +1653,6 @@
 {
 	struct pending_tx_info *pending_tx_info;
 	pending_ring_idx_t index;
-	int notify;
 	unsigned long flags;
 
 	pending_tx_info = &queue->pending_tx_info[pending_idx];
@@ -1673,12 +1668,9 @@
 	index = pending_index(queue->pending_prod++);
 	queue->pending_ring[index] = pending_idx;
 
-	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify);
+	push_tx_responses(queue);
 
 	spin_unlock_irqrestore(&queue->response_lock, flags);
-
-	if (notify)
-		notify_remote_via_irq(queue->tx_irq);
 }
 
 
@@ -1699,6 +1691,15 @@
 	queue->tx.rsp_prod_pvt = ++i;
 }
 
+static void push_tx_responses(struct xenvif_queue *queue)
+{
+	int notify;
+
+	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify);
+	if (notify)
+		notify_remote_via_irq(queue->tx_irq);
+}
+
 static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue,
 					     u16      id,
 					     s8       st,
diff --git a/drivers/of/base.c b/drivers/of/base.c
index adb8764..8f165b1 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -715,13 +715,8 @@
 {
 	struct device_node *child;
 	int len;
-	const char *end;
 
-	end = strchr(path, ':');
-	if (!end)
-		end = strchrnul(path, '/');
-
-	len = end - path;
+	len = strcspn(path, "/:");
 	if (!len)
 		return NULL;
 
@@ -1893,10 +1888,8 @@
 			name = of_get_property(of_chosen, "linux,stdout-path", NULL);
 		if (IS_ENABLED(CONFIG_PPC) && !name)
 			name = of_get_property(of_aliases, "stdout", NULL);
-		if (name) {
+		if (name)
 			of_stdout = of_find_node_opts_by_path(name, &of_stdout_options);
-			add_preferred_console("stdout-path", 0, NULL);
-		}
 	}
 
 	if (!of_aliases)
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 0d77658..1a79806 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -290,7 +290,7 @@
 	struct device_node *p;
 	const __be32 *intspec, *tmp, *addr;
 	u32 intsize, intlen;
-	int i, res = -EINVAL;
+	int i, res;
 
 	pr_debug("of_irq_parse_one: dev=%s, index=%d\n", of_node_full_name(device), index);
 
@@ -323,15 +323,19 @@
 
 	/* Get size of interrupt specifier */
 	tmp = of_get_property(p, "#interrupt-cells", NULL);
-	if (tmp == NULL)
+	if (tmp == NULL) {
+		res = -EINVAL;
 		goto out;
+	}
 	intsize = be32_to_cpu(*tmp);
 
 	pr_debug(" intsize=%d intlen=%d\n", intsize, intlen);
 
 	/* Check index */
-	if ((index + 1) * intsize > intlen)
+	if ((index + 1) * intsize > intlen) {
+		res = -EINVAL;
 		goto out;
+	}
 
 	/* Copy intspec into irq structure */
 	intspec += index * intsize;
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index aba8946..52c45c7 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -97,6 +97,11 @@
 		 "option path test, subcase #1 failed\n");
 	of_node_put(np);
 
+	np = of_find_node_opts_by_path("/testcase-data/testcase-device1:test/option", &options);
+	selftest(np && !strcmp("test/option", options),
+		 "option path test, subcase #2 failed\n");
+	of_node_put(np);
+
 	np = of_find_node_opts_by_path("/testcase-data:testoption", NULL);
 	selftest(np, "NULL option path test failed\n");
 	of_node_put(np);
diff --git a/drivers/pcmcia/Kconfig b/drivers/pcmcia/Kconfig
index 3bb4925..45f67c6 100644
--- a/drivers/pcmcia/Kconfig
+++ b/drivers/pcmcia/Kconfig
@@ -69,8 +69,7 @@
 	tristate "CardBus yenta-compatible bridge support"
 	depends on PCI
 	select CARDBUS if !EXPERT
-	select PCCARD_NONSTATIC if PCMCIA != n && ISA
-	select PCCARD_PCI if PCMCIA !=n && !ISA
+	select PCCARD_NONSTATIC if PCMCIA != n
 	---help---
 	  This option enables support for CardBus host bridges.  Virtually
 	  all modern PCMCIA bridges are CardBus compatible.  A "bridge" is
@@ -110,8 +109,7 @@
 config PD6729
 	tristate "Cirrus PD6729 compatible bridge support"
 	depends on PCMCIA && PCI
-	select PCCARD_NONSTATIC if PCMCIA != n && ISA
-	select PCCARD_PCI if PCMCIA !=n && !ISA
+	select PCCARD_NONSTATIC
 	help
 	  This provides support for the Cirrus PD6729 PCI-to-PCMCIA bridge
 	  device, found in some older laptops and PCMCIA card readers.
@@ -119,8 +117,7 @@
 config I82092
 	tristate "i82092 compatible bridge support"
 	depends on PCMCIA && PCI
-	select PCCARD_NONSTATIC if PCMCIA != n && ISA
-	select PCCARD_PCI if PCMCIA !=n && !ISA
+	select PCCARD_NONSTATIC
 	help
 	  This provides support for the Intel I82092AA PCI-to-PCMCIA bridge device,
 	  found in some older laptops and more commonly in evaluation boards for the
@@ -291,9 +288,6 @@
 	  Say Y here to support the CompactFlash controller on the
 	  PA Semi Electra eval board.
 
-config PCCARD_PCI
-	bool
-
 config PCCARD_NONSTATIC
 	bool
 
diff --git a/drivers/pcmcia/Makefile b/drivers/pcmcia/Makefile
index f1a7ca0..27e94b3 100644
--- a/drivers/pcmcia/Makefile
+++ b/drivers/pcmcia/Makefile
@@ -12,7 +12,6 @@
 pcmcia_rsrc-y					+= rsrc_mgr.o
 pcmcia_rsrc-$(CONFIG_PCCARD_NONSTATIC)		+= rsrc_nonstatic.o
 pcmcia_rsrc-$(CONFIG_PCCARD_IODYN)		+= rsrc_iodyn.o
-pcmcia_rsrc-$(CONFIG_PCCARD_PCI)		+= rsrc_pci.o
 obj-$(CONFIG_PCCARD)				+= pcmcia_rsrc.o
 
 
diff --git a/drivers/pcmcia/rsrc_pci.c b/drivers/pcmcia/rsrc_pci.c
deleted file mode 100644
index 1f67b3b..0000000
--- a/drivers/pcmcia/rsrc_pci.c
+++ /dev/null
@@ -1,173 +0,0 @@
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/pci.h>
-
-#include <pcmcia/ss.h>
-#include <pcmcia/cistpl.h>
-#include "cs_internal.h"
-
-
-struct pcmcia_align_data {
-	unsigned long	mask;
-	unsigned long	offset;
-};
-
-static resource_size_t pcmcia_align(void *align_data,
-				const struct resource *res,
-				resource_size_t size, resource_size_t align)
-{
-	struct pcmcia_align_data *data = align_data;
-	resource_size_t start;
-
-	start = (res->start & ~data->mask) + data->offset;
-	if (start < res->start)
-		start += data->mask + 1;
-	return start;
-}
-
-static struct resource *find_io_region(struct pcmcia_socket *s,
-					unsigned long base, int num,
-					unsigned long align)
-{
-	struct resource *res = pcmcia_make_resource(0, num, IORESOURCE_IO,
-						dev_name(&s->dev));
-	struct pcmcia_align_data data;
-	int ret;
-
-	data.mask = align - 1;
-	data.offset = base & data.mask;
-
-	ret = pci_bus_alloc_resource(s->cb_dev->bus, res, num, 1,
-					     base, 0, pcmcia_align, &data);
-	if (ret != 0) {
-		kfree(res);
-		res = NULL;
-	}
-	return res;
-}
-
-static int res_pci_find_io(struct pcmcia_socket *s, unsigned int attr,
-			unsigned int *base, unsigned int num,
-			unsigned int align, struct resource **parent)
-{
-	int i, ret = 0;
-
-	/* Check for an already-allocated window that must conflict with
-	 * what was asked for.  It is a hack because it does not catch all
-	 * potential conflicts, just the most obvious ones.
-	 */
-	for (i = 0; i < MAX_IO_WIN; i++) {
-		if (!s->io[i].res)
-			continue;
-
-		if (!*base)
-			continue;
-
-		if ((s->io[i].res->start & (align-1)) == *base)
-			return -EBUSY;
-	}
-
-	for (i = 0; i < MAX_IO_WIN; i++) {
-		struct resource *res = s->io[i].res;
-		unsigned int try;
-
-		if (res && (res->flags & IORESOURCE_BITS) !=
-			(attr & IORESOURCE_BITS))
-			continue;
-
-		if (!res) {
-			if (align == 0)
-				align = 0x10000;
-
-			res = s->io[i].res = find_io_region(s, *base, num,
-								align);
-			if (!res)
-				return -EINVAL;
-
-			*base = res->start;
-			s->io[i].res->flags =
-				((res->flags & ~IORESOURCE_BITS) |
-					(attr & IORESOURCE_BITS));
-			s->io[i].InUse = num;
-			*parent = res;
-			return 0;
-		}
-
-		/* Try to extend top of window */
-		try = res->end + 1;
-		if ((*base == 0) || (*base == try)) {
-			ret = adjust_resource(s->io[i].res, res->start,
-					      resource_size(res) + num);
-			if (ret)
-				continue;
-			*base = try;
-			s->io[i].InUse += num;
-			*parent = res;
-			return 0;
-		}
-
-		/* Try to extend bottom of window */
-		try = res->start - num;
-		if ((*base == 0) || (*base == try)) {
-			ret = adjust_resource(s->io[i].res,
-					      res->start - num,
-					      resource_size(res) + num);
-			if (ret)
-				continue;
-			*base = try;
-			s->io[i].InUse += num;
-			*parent = res;
-			return 0;
-		}
-	}
-	return -EINVAL;
-}
-
-static struct resource *res_pci_find_mem(u_long base, u_long num,
-		u_long align, int low, struct pcmcia_socket *s)
-{
-	struct resource *res = pcmcia_make_resource(0, num, IORESOURCE_MEM,
-						dev_name(&s->dev));
-	struct pcmcia_align_data data;
-	unsigned long min;
-	int ret;
-
-	if (align < 0x20000)
-		align = 0x20000;
-	data.mask = align - 1;
-	data.offset = base & data.mask;
-
-	min = 0;
-	if (!low)
-		min = 0x100000UL;
-
-	ret = pci_bus_alloc_resource(s->cb_dev->bus,
-			res, num, 1, min, 0,
-			pcmcia_align, &data);
-
-	if (ret != 0) {
-		kfree(res);
-		res = NULL;
-	}
-	return res;
-}
-
-
-static int res_pci_init(struct pcmcia_socket *s)
-{
-	if (!s->cb_dev || !(s->features & SS_CAP_PAGE_REGS)) {
-		dev_err(&s->dev, "not supported by res_pci\n");
-		return -EOPNOTSUPP;
-	}
-	return 0;
-}
-
-struct pccard_resource_ops pccard_nonstatic_ops = {
-	.validate_mem = NULL,
-	.find_io = res_pci_find_io,
-	.find_mem = res_pci_find_mem,
-	.init = res_pci_init,
-	.exit = NULL,
-};
-EXPORT_SYMBOL(pccard_nonstatic_ops);
diff --git a/drivers/phy/phy-armada375-usb2.c b/drivers/phy/phy-armada375-usb2.c
index 7c99ca2..8ccc395 100644
--- a/drivers/phy/phy-armada375-usb2.c
+++ b/drivers/phy/phy-armada375-usb2.c
@@ -37,7 +37,7 @@
 	struct armada375_cluster_phy *cluster_phy;
 	u32 reg;
 
-	cluster_phy = dev_get_drvdata(phy->dev.parent);
+	cluster_phy = phy_get_drvdata(phy);
 	if (!cluster_phy)
 		return -ENODEV;
 
@@ -131,6 +131,7 @@
 	cluster_phy->reg = usb_cluster_base;
 
 	dev_set_drvdata(dev, cluster_phy);
+	phy_set_drvdata(phy, cluster_phy);
 
 	phy_provider = devm_of_phy_provider_register(&pdev->dev,
 						     armada375_usb_phy_xlate);
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index a12d353..3791838 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -52,7 +52,9 @@
 
 static int devm_phy_match(struct device *dev, void *res, void *match_data)
 {
-	return res == match_data;
+	struct phy **phy = res;
+
+	return *phy == match_data;
 }
 
 /**
@@ -223,6 +225,7 @@
 	ret = phy_pm_runtime_get_sync(phy);
 	if (ret < 0 && ret != -ENOTSUPP)
 		return ret;
+	ret = 0; /* Override possible ret == -ENOTSUPP */
 
 	mutex_lock(&phy->mutex);
 	if (phy->init_count == 0 && phy->ops->init) {
@@ -231,8 +234,6 @@
 			dev_err(&phy->dev, "phy init failed --> %d\n", ret);
 			goto out;
 		}
-	} else {
-		ret = 0; /* Override possible ret == -ENOTSUPP */
 	}
 	++phy->init_count;
 
@@ -253,6 +254,7 @@
 	ret = phy_pm_runtime_get_sync(phy);
 	if (ret < 0 && ret != -ENOTSUPP)
 		return ret;
+	ret = 0; /* Override possible ret == -ENOTSUPP */
 
 	mutex_lock(&phy->mutex);
 	if (phy->init_count == 1 && phy->ops->exit) {
@@ -287,6 +289,7 @@
 	ret = phy_pm_runtime_get_sync(phy);
 	if (ret < 0 && ret != -ENOTSUPP)
 		return ret;
+	ret = 0; /* Override possible ret == -ENOTSUPP */
 
 	mutex_lock(&phy->mutex);
 	if (phy->power_count == 0 && phy->ops->power_on) {
@@ -295,8 +298,6 @@
 			dev_err(&phy->dev, "phy poweron failed --> %d\n", ret);
 			goto out;
 		}
-	} else {
-		ret = 0; /* Override possible ret == -ENOTSUPP */
 	}
 	++phy->power_count;
 	mutex_unlock(&phy->mutex);
diff --git a/drivers/phy/phy-exynos-dp-video.c b/drivers/phy/phy-exynos-dp-video.c
index f86cbe6..179cbf9 100644
--- a/drivers/phy/phy-exynos-dp-video.c
+++ b/drivers/phy/phy-exynos-dp-video.c
@@ -30,28 +30,13 @@
 	const struct exynos_dp_video_phy_drvdata *drvdata;
 };
 
-static void exynos_dp_video_phy_pwr_isol(struct exynos_dp_video_phy *state,
-							unsigned int on)
-{
-	unsigned int val;
-
-	if (IS_ERR(state->regs))
-		return;
-
-	val = on ? 0 : EXYNOS5_PHY_ENABLE;
-
-	regmap_update_bits(state->regs, state->drvdata->phy_ctrl_offset,
-			   EXYNOS5_PHY_ENABLE, val);
-}
-
 static int exynos_dp_video_phy_power_on(struct phy *phy)
 {
 	struct exynos_dp_video_phy *state = phy_get_drvdata(phy);
 
 	/* Disable power isolation on DP-PHY */
-	exynos_dp_video_phy_pwr_isol(state, 0);
-
-	return 0;
+	return regmap_update_bits(state->regs, state->drvdata->phy_ctrl_offset,
+				  EXYNOS5_PHY_ENABLE, EXYNOS5_PHY_ENABLE);
 }
 
 static int exynos_dp_video_phy_power_off(struct phy *phy)
@@ -59,9 +44,8 @@
 	struct exynos_dp_video_phy *state = phy_get_drvdata(phy);
 
 	/* Enable power isolation on DP-PHY */
-	exynos_dp_video_phy_pwr_isol(state, 1);
-
-	return 0;
+	return regmap_update_bits(state->regs, state->drvdata->phy_ctrl_offset,
+				  EXYNOS5_PHY_ENABLE, 0);
 }
 
 static struct phy_ops exynos_dp_video_phy_ops = {
diff --git a/drivers/phy/phy-exynos-mipi-video.c b/drivers/phy/phy-exynos-mipi-video.c
index f017b2f..df7519a 100644
--- a/drivers/phy/phy-exynos-mipi-video.c
+++ b/drivers/phy/phy-exynos-mipi-video.c
@@ -43,7 +43,6 @@
 	} phys[EXYNOS_MIPI_PHYS_NUM];
 	spinlock_t slock;
 	void __iomem *regs;
-	struct mutex mutex;
 	struct regmap *regmap;
 };
 
@@ -59,8 +58,9 @@
 	else
 		reset = EXYNOS4_MIPI_PHY_SRESETN;
 
-	if (state->regmap) {
-		mutex_lock(&state->mutex);
+	spin_lock(&state->slock);
+
+	if (!IS_ERR(state->regmap)) {
 		regmap_read(state->regmap, offset, &val);
 		if (on)
 			val |= reset;
@@ -72,11 +72,9 @@
 		else if (!(val & EXYNOS4_MIPI_PHY_RESET_MASK))
 			val &= ~EXYNOS4_MIPI_PHY_ENABLE;
 		regmap_write(state->regmap, offset, val);
-		mutex_unlock(&state->mutex);
 	} else {
 		addr = state->regs + EXYNOS_MIPI_PHY_CONTROL(id / 2);
 
-		spin_lock(&state->slock);
 		val = readl(addr);
 		if (on)
 			val |= reset;
@@ -90,9 +88,9 @@
 			val &= ~EXYNOS4_MIPI_PHY_ENABLE;
 
 		writel(val, addr);
-		spin_unlock(&state->slock);
 	}
 
+	spin_unlock(&state->slock);
 	return 0;
 }
 
@@ -158,7 +156,6 @@
 
 	dev_set_drvdata(dev, state);
 	spin_lock_init(&state->slock);
-	mutex_init(&state->mutex);
 
 	for (i = 0; i < EXYNOS_MIPI_PHYS_NUM; i++) {
 		struct phy *phy = devm_phy_create(dev, NULL,
diff --git a/drivers/phy/phy-exynos4210-usb2.c b/drivers/phy/phy-exynos4210-usb2.c
index 236a52a..f30bbb0 100644
--- a/drivers/phy/phy-exynos4210-usb2.c
+++ b/drivers/phy/phy-exynos4210-usb2.c
@@ -250,7 +250,6 @@
 		.power_on	= exynos4210_power_on,
 		.power_off	= exynos4210_power_off,
 	},
-	{},
 };
 
 const struct samsung_usb2_phy_config exynos4210_usb2_phy_config = {
diff --git a/drivers/phy/phy-exynos4x12-usb2.c b/drivers/phy/phy-exynos4x12-usb2.c
index 0b9de88..765da90 100644
--- a/drivers/phy/phy-exynos4x12-usb2.c
+++ b/drivers/phy/phy-exynos4x12-usb2.c
@@ -361,7 +361,6 @@
 		.power_on	= exynos4x12_power_on,
 		.power_off	= exynos4x12_power_off,
 	},
-	{},
 };
 
 const struct samsung_usb2_phy_config exynos3250_usb2_phy_config = {
diff --git a/drivers/phy/phy-exynos5-usbdrd.c b/drivers/phy/phy-exynos5-usbdrd.c
index 0437401..e2a0be7 100644
--- a/drivers/phy/phy-exynos5-usbdrd.c
+++ b/drivers/phy/phy-exynos5-usbdrd.c
@@ -531,7 +531,7 @@
 {
 	struct exynos5_usbdrd_phy *phy_drd = dev_get_drvdata(dev);
 
-	if (WARN_ON(args->args[0] > EXYNOS5_DRDPHYS_NUM))
+	if (WARN_ON(args->args[0] >= EXYNOS5_DRDPHYS_NUM))
 		return ERR_PTR(-ENODEV);
 
 	return phy_drd->phys[args->args[0]].phy;
diff --git a/drivers/phy/phy-exynos5250-usb2.c b/drivers/phy/phy-exynos5250-usb2.c
index 1c139aa..2ed1735 100644
--- a/drivers/phy/phy-exynos5250-usb2.c
+++ b/drivers/phy/phy-exynos5250-usb2.c
@@ -391,7 +391,6 @@
 		.power_on	= exynos5250_power_on,
 		.power_off	= exynos5250_power_off,
 	},
-	{},
 };
 
 const struct samsung_usb2_phy_config exynos5250_usb2_phy_config = {
diff --git a/drivers/phy/phy-hix5hd2-sata.c b/drivers/phy/phy-hix5hd2-sata.c
index 34915b4..d6b2265 100644
--- a/drivers/phy/phy-hix5hd2-sata.c
+++ b/drivers/phy/phy-hix5hd2-sata.c
@@ -147,6 +147,9 @@
 		return -ENOMEM;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
+
 	priv->base = devm_ioremap(dev, res->start, resource_size(res));
 	if (!priv->base)
 		return -ENOMEM;
diff --git a/drivers/phy/phy-miphy28lp.c b/drivers/phy/phy-miphy28lp.c
index 9b2848e..9334352 100644
--- a/drivers/phy/phy-miphy28lp.c
+++ b/drivers/phy/phy-miphy28lp.c
@@ -228,6 +228,7 @@
 	struct regmap *regmap;
 	struct mutex miphy_mutex;
 	struct miphy28lp_phy **phys;
+	int nphys;
 };
 
 struct miphy_initval {
@@ -1116,7 +1117,7 @@
 		return ERR_PTR(-EINVAL);
 	}
 
-	for (index = 0; index < of_get_child_count(dev->of_node); index++)
+	for (index = 0; index < miphy_dev->nphys; index++)
 		if (phynode == miphy_dev->phys[index]->phy->dev.of_node) {
 			miphy_phy = miphy_dev->phys[index];
 			break;
@@ -1138,6 +1139,7 @@
 
 static struct phy_ops miphy28lp_ops = {
 	.init = miphy28lp_init,
+	.owner = THIS_MODULE,
 };
 
 static int miphy28lp_probe_resets(struct device_node *node,
@@ -1200,16 +1202,15 @@
 	struct miphy28lp_dev *miphy_dev;
 	struct phy_provider *provider;
 	struct phy *phy;
-	int chancount, port = 0;
-	int ret;
+	int ret, port = 0;
 
 	miphy_dev = devm_kzalloc(&pdev->dev, sizeof(*miphy_dev), GFP_KERNEL);
 	if (!miphy_dev)
 		return -ENOMEM;
 
-	chancount = of_get_child_count(np);
-	miphy_dev->phys = devm_kzalloc(&pdev->dev, sizeof(phy) * chancount,
-				       GFP_KERNEL);
+	miphy_dev->nphys = of_get_child_count(np);
+	miphy_dev->phys = devm_kcalloc(&pdev->dev, miphy_dev->nphys,
+				       sizeof(*miphy_dev->phys), GFP_KERNEL);
 	if (!miphy_dev->phys)
 		return -ENOMEM;
 
diff --git a/drivers/phy/phy-miphy365x.c b/drivers/phy/phy-miphy365x.c
index 6c80154..51b459d 100644
--- a/drivers/phy/phy-miphy365x.c
+++ b/drivers/phy/phy-miphy365x.c
@@ -150,6 +150,7 @@
 	struct regmap *regmap;
 	struct mutex miphy_mutex;
 	struct miphy365x_phy **phys;
+	int nphys;
 };
 
 /*
@@ -485,7 +486,7 @@
 		return ERR_PTR(-EINVAL);
 	}
 
-	for (index = 0; index < of_get_child_count(dev->of_node); index++)
+	for (index = 0; index < miphy_dev->nphys; index++)
 		if (phynode == miphy_dev->phys[index]->phy->dev.of_node) {
 			miphy_phy = miphy_dev->phys[index];
 			break;
@@ -541,16 +542,15 @@
 	struct miphy365x_dev *miphy_dev;
 	struct phy_provider *provider;
 	struct phy *phy;
-	int chancount, port = 0;
-	int ret;
+	int ret, port = 0;
 
 	miphy_dev = devm_kzalloc(&pdev->dev, sizeof(*miphy_dev), GFP_KERNEL);
 	if (!miphy_dev)
 		return -ENOMEM;
 
-	chancount = of_get_child_count(np);
-	miphy_dev->phys = devm_kzalloc(&pdev->dev, sizeof(phy) * chancount,
-				       GFP_KERNEL);
+	miphy_dev->nphys = of_get_child_count(np);
+	miphy_dev->phys = devm_kcalloc(&pdev->dev, miphy_dev->nphys,
+				       sizeof(*miphy_dev->phys), GFP_KERNEL);
 	if (!miphy_dev->phys)
 		return -ENOMEM;
 
diff --git a/drivers/phy/phy-omap-control.c b/drivers/phy/phy-omap-control.c
index efe724f..93252e0 100644
--- a/drivers/phy/phy-omap-control.c
+++ b/drivers/phy/phy-omap-control.c
@@ -360,7 +360,7 @@
 }
 module_exit(omap_control_phy_exit);
 
-MODULE_ALIAS("platform: omap_control_phy");
+MODULE_ALIAS("platform:omap_control_phy");
 MODULE_AUTHOR("Texas Instruments Inc.");
 MODULE_DESCRIPTION("OMAP Control Module PHY Driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c
index 6f4aef3..4757e76 100644
--- a/drivers/phy/phy-omap-usb2.c
+++ b/drivers/phy/phy-omap-usb2.c
@@ -296,10 +296,11 @@
 			dev_warn(&pdev->dev,
 				 "found usb_otg_ss_refclk960m, please fix DTS\n");
 		}
-	} else {
-		clk_prepare(phy->optclk);
 	}
 
+	if (!IS_ERR(phy->optclk))
+		clk_prepare(phy->optclk);
+
 	usb_add_phy_dev(&phy->phy);
 
 	return 0;
@@ -383,7 +384,7 @@
 
 module_platform_driver(omap_usb2_driver);
 
-MODULE_ALIAS("platform: omap_usb2");
+MODULE_ALIAS("platform:omap_usb2");
 MODULE_AUTHOR("Texas Instruments Inc.");
 MODULE_DESCRIPTION("OMAP USB2 phy driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/phy/phy-rockchip-usb.c b/drivers/phy/phy-rockchip-usb.c
index 22011c3..7d4c336 100644
--- a/drivers/phy/phy-rockchip-usb.c
+++ b/drivers/phy/phy-rockchip-usb.c
@@ -61,8 +61,6 @@
 		return ret;
 
 	clk_disable_unprepare(phy->clk);
-	if (ret)
-		return ret;
 
 	return 0;
 }
@@ -78,8 +76,10 @@
 
 	/* Power up usb phy analog blocks by set siddq 0 */
 	ret = rockchip_usb_phy_power(phy, 0);
-	if (ret)
+	if (ret) {
+		clk_disable_unprepare(phy->clk);
 		return ret;
+	}
 
 	return 0;
 }
diff --git a/drivers/phy/phy-ti-pipe3.c b/drivers/phy/phy-ti-pipe3.c
index 95c88f9..2ba610b 100644
--- a/drivers/phy/phy-ti-pipe3.c
+++ b/drivers/phy/phy-ti-pipe3.c
@@ -165,15 +165,11 @@
 		cpu_relax();
 		val = ti_pipe3_readl(phy->pll_ctrl_base, PLL_STATUS);
 		if (val & PLL_LOCK)
-			break;
+			return 0;
 	} while (!time_after(jiffies, timeout));
 
-	if (!(val & PLL_LOCK)) {
-		dev_err(phy->dev, "DPLL failed to lock\n");
-		return -EBUSY;
-	}
-
-	return 0;
+	dev_err(phy->dev, "DPLL failed to lock\n");
+	return -EBUSY;
 }
 
 static int ti_pipe3_dpll_program(struct ti_pipe3 *phy)
@@ -608,7 +604,7 @@
 
 module_platform_driver(ti_pipe3_driver);
 
-MODULE_ALIAS("platform: ti_pipe3");
+MODULE_ALIAS("platform:ti_pipe3");
 MODULE_AUTHOR("Texas Instruments Inc.");
 MODULE_DESCRIPTION("TI PIPE3 phy driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c
index 8e87f54..bc42d6a 100644
--- a/drivers/phy/phy-twl4030-usb.c
+++ b/drivers/phy/phy-twl4030-usb.c
@@ -666,7 +666,6 @@
 	twl->dev		= &pdev->dev;
 	twl->irq		= platform_get_irq(pdev, 0);
 	twl->vbus_supplied	= false;
-	twl->linkstat		= -EINVAL;
 	twl->linkstat		= OMAP_MUSB_UNKNOWN;
 
 	twl->phy.dev		= twl->dev;
diff --git a/drivers/phy/phy-xgene.c b/drivers/phy/phy-xgene.c
index 29214a3..2263cd0 100644
--- a/drivers/phy/phy-xgene.c
+++ b/drivers/phy/phy-xgene.c
@@ -1704,7 +1704,6 @@
 	for (i = 0; i < MAX_LANE; i++)
 		ctx->sata_param.speed[i] = 2; /* Default to Gen3 */
 
-	ctx->dev = &pdev->dev;
 	platform_set_drvdata(pdev, ctx);
 
 	ctx->phy = devm_phy_create(ctx->dev, NULL, &xgene_phy_ops);
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 5afe03e..2062c22 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -66,6 +66,10 @@
 #define BYT_DIR_MASK		(BIT(1) | BIT(2))
 #define BYT_TRIG_MASK		(BIT(26) | BIT(25) | BIT(24))
 
+#define BYT_CONF0_RESTORE_MASK	(BYT_DIRECT_IRQ_EN | BYT_TRIG_MASK | \
+				 BYT_PIN_MUX)
+#define BYT_VAL_RESTORE_MASK	(BYT_DIR_MASK | BYT_LEVEL)
+
 #define BYT_NGPIO_SCORE		102
 #define BYT_NGPIO_NCORE		28
 #define BYT_NGPIO_SUS		44
@@ -134,12 +138,18 @@
 	},
 };
 
+struct byt_gpio_pin_context {
+	u32 conf0;
+	u32 val;
+};
+
 struct byt_gpio {
 	struct gpio_chip		chip;
 	struct platform_device		*pdev;
 	spinlock_t			lock;
 	void __iomem			*reg_base;
 	struct pinctrl_gpio_range	*range;
+	struct byt_gpio_pin_context	*saved_context;
 };
 
 #define to_byt_gpio(c)	container_of(c, struct byt_gpio, chip)
@@ -158,40 +168,62 @@
 	return vg->reg_base + reg_offset + reg;
 }
 
-static bool is_special_pin(struct byt_gpio *vg, unsigned offset)
+static void byt_gpio_clear_triggering(struct byt_gpio *vg, unsigned offset)
+{
+	void __iomem *reg = byt_gpio_reg(&vg->chip, offset, BYT_CONF0_REG);
+	unsigned long flags;
+	u32 value;
+
+	spin_lock_irqsave(&vg->lock, flags);
+	value = readl(reg);
+	value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL);
+	writel(value, reg);
+	spin_unlock_irqrestore(&vg->lock, flags);
+}
+
+static u32 byt_get_gpio_mux(struct byt_gpio *vg, unsigned offset)
 {
 	/* SCORE pin 92-93 */
 	if (!strcmp(vg->range->name, BYT_SCORE_ACPI_UID) &&
 		offset >= 92 && offset <= 93)
-		return true;
+		return 1;
 
 	/* SUS pin 11-21 */
 	if (!strcmp(vg->range->name, BYT_SUS_ACPI_UID) &&
 		offset >= 11 && offset <= 21)
-		return true;
+		return 1;
 
-	return false;
+	return 0;
 }
 
 static int byt_gpio_request(struct gpio_chip *chip, unsigned offset)
 {
 	struct byt_gpio *vg = to_byt_gpio(chip);
 	void __iomem *reg = byt_gpio_reg(chip, offset, BYT_CONF0_REG);
-	u32 value;
-	bool special;
+	u32 value, gpio_mux;
 
 	/*
 	 * In most cases, func pin mux 000 means GPIO function.
 	 * But, some pins may have func pin mux 001 represents
-	 * GPIO function. Only allow user to export pin with
-	 * func pin mux preset as GPIO function by BIOS/FW.
+	 * GPIO function.
+	 *
+	 * Because there are devices out there where some pins were not
+	 * configured correctly we allow changing the mux value from
+	 * request (but print out warning about that).
 	 */
 	value = readl(reg) & BYT_PIN_MUX;
-	special = is_special_pin(vg, offset);
-	if ((special && value != 1) || (!special && value)) {
-		dev_err(&vg->pdev->dev,
-			"pin %u cannot be used as GPIO.\n", offset);
-		return -EINVAL;
+	gpio_mux = byt_get_gpio_mux(vg, offset);
+	if (WARN_ON(gpio_mux != value)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&vg->lock, flags);
+		value = readl(reg) & ~BYT_PIN_MUX;
+		value |= gpio_mux;
+		writel(value, reg);
+		spin_unlock_irqrestore(&vg->lock, flags);
+
+		dev_warn(&vg->pdev->dev,
+			 "pin %u forcibly re-configured as GPIO\n", offset);
 	}
 
 	pm_runtime_get(&vg->pdev->dev);
@@ -202,14 +234,8 @@
 static void byt_gpio_free(struct gpio_chip *chip, unsigned offset)
 {
 	struct byt_gpio *vg = to_byt_gpio(chip);
-	void __iomem *reg = byt_gpio_reg(&vg->chip, offset, BYT_CONF0_REG);
-	u32 value;
 
-	/* clear interrupt triggering */
-	value = readl(reg);
-	value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL);
-	writel(value, reg);
-
+	byt_gpio_clear_triggering(vg, offset);
 	pm_runtime_put(&vg->pdev->dev);
 }
 
@@ -236,23 +262,13 @@
 	value &= ~(BYT_DIRECT_IRQ_EN | BYT_TRIG_POS | BYT_TRIG_NEG |
 		   BYT_TRIG_LVL);
 
-	switch (type) {
-	case IRQ_TYPE_LEVEL_HIGH:
-		value |= BYT_TRIG_LVL;
-	case IRQ_TYPE_EDGE_RISING:
-		value |= BYT_TRIG_POS;
-		break;
-	case IRQ_TYPE_LEVEL_LOW:
-		value |= BYT_TRIG_LVL;
-	case IRQ_TYPE_EDGE_FALLING:
-		value |= BYT_TRIG_NEG;
-		break;
-	case IRQ_TYPE_EDGE_BOTH:
-		value |= (BYT_TRIG_NEG | BYT_TRIG_POS);
-		break;
-	}
 	writel(value, reg);
 
+	if (type & IRQ_TYPE_EDGE_BOTH)
+		__irq_set_handler_locked(d->irq, handle_edge_irq);
+	else if (type & IRQ_TYPE_LEVEL_MASK)
+		__irq_set_handler_locked(d->irq, handle_level_irq);
+
 	spin_unlock_irqrestore(&vg->lock, flags);
 
 	return 0;
@@ -410,58 +426,80 @@
 	struct irq_data *data = irq_desc_get_irq_data(desc);
 	struct byt_gpio *vg = to_byt_gpio(irq_desc_get_handler_data(desc));
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
-	u32 base, pin, mask;
+	u32 base, pin;
 	void __iomem *reg;
-	u32 pending;
+	unsigned long pending;
 	unsigned virq;
-	int looplimit = 0;
 
 	/* check from GPIO controller which pin triggered the interrupt */
 	for (base = 0; base < vg->chip.ngpio; base += 32) {
-
 		reg = byt_gpio_reg(&vg->chip, base, BYT_INT_STAT_REG);
-
-		while ((pending = readl(reg))) {
-			pin = __ffs(pending);
-			mask = BIT(pin);
-			/* Clear before handling so we can't lose an edge */
-			writel(mask, reg);
-
+		pending = readl(reg);
+		for_each_set_bit(pin, &pending, 32) {
 			virq = irq_find_mapping(vg->chip.irqdomain, base + pin);
 			generic_handle_irq(virq);
-
-			/* In case bios or user sets triggering incorretly a pin
-			 * might remain in "interrupt triggered" state.
-			 */
-			if (looplimit++ > 32) {
-				dev_err(&vg->pdev->dev,
-					"Gpio %d interrupt flood, disabling\n",
-					base + pin);
-
-				reg = byt_gpio_reg(&vg->chip, base + pin,
-						   BYT_CONF0_REG);
-				mask = readl(reg);
-				mask &= ~(BYT_TRIG_NEG | BYT_TRIG_POS |
-					  BYT_TRIG_LVL);
-				writel(mask, reg);
-				mask = readl(reg); /* flush */
-				break;
-			}
 		}
 	}
 	chip->irq_eoi(data);
 }
 
+static void byt_irq_ack(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct byt_gpio *vg = to_byt_gpio(gc);
+	unsigned offset = irqd_to_hwirq(d);
+	void __iomem *reg;
+
+	reg = byt_gpio_reg(&vg->chip, offset, BYT_INT_STAT_REG);
+	writel(BIT(offset % 32), reg);
+}
+
 static void byt_irq_unmask(struct irq_data *d)
 {
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct byt_gpio *vg = to_byt_gpio(gc);
+	unsigned offset = irqd_to_hwirq(d);
+	unsigned long flags;
+	void __iomem *reg;
+	u32 value;
+
+	spin_lock_irqsave(&vg->lock, flags);
+
+	reg = byt_gpio_reg(&vg->chip, offset, BYT_CONF0_REG);
+	value = readl(reg);
+
+	switch (irqd_get_trigger_type(d)) {
+	case IRQ_TYPE_LEVEL_HIGH:
+		value |= BYT_TRIG_LVL;
+	case IRQ_TYPE_EDGE_RISING:
+		value |= BYT_TRIG_POS;
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		value |= BYT_TRIG_LVL;
+	case IRQ_TYPE_EDGE_FALLING:
+		value |= BYT_TRIG_NEG;
+		break;
+	case IRQ_TYPE_EDGE_BOTH:
+		value |= (BYT_TRIG_NEG | BYT_TRIG_POS);
+		break;
+	}
+
+	writel(value, reg);
+
+	spin_unlock_irqrestore(&vg->lock, flags);
 }
 
 static void byt_irq_mask(struct irq_data *d)
 {
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct byt_gpio *vg = to_byt_gpio(gc);
+
+	byt_gpio_clear_triggering(vg, irqd_to_hwirq(d));
 }
 
 static struct irq_chip byt_irqchip = {
 	.name = "BYT-GPIO",
+	.irq_ack = byt_irq_ack,
 	.irq_mask = byt_irq_mask,
 	.irq_unmask = byt_irq_unmask,
 	.irq_set_type = byt_irq_type,
@@ -472,6 +510,21 @@
 {
 	void __iomem *reg;
 	u32 base, value;
+	int i;
+
+	/*
+	 * Clear interrupt triggers for all pins that are GPIOs and
+	 * do not use direct IRQ mode. This will prevent spurious
+	 * interrupts from misconfigured pins.
+	 */
+	for (i = 0; i < vg->chip.ngpio; i++) {
+		value = readl(byt_gpio_reg(&vg->chip, i, BYT_CONF0_REG));
+		if ((value & BYT_PIN_MUX) == byt_get_gpio_mux(vg, i) &&
+		    !(value & BYT_DIRECT_IRQ_EN)) {
+			byt_gpio_clear_triggering(vg, i);
+			dev_dbg(&vg->pdev->dev, "disabling GPIO %d\n", i);
+		}
+	}
 
 	/* clear interrupt status trigger registers */
 	for (base = 0; base < vg->chip.ngpio; base += 32) {
@@ -541,6 +594,11 @@
 	gc->can_sleep = false;
 	gc->dev = dev;
 
+#ifdef CONFIG_PM_SLEEP
+	vg->saved_context = devm_kcalloc(&pdev->dev, gc->ngpio,
+				       sizeof(*vg->saved_context), GFP_KERNEL);
+#endif
+
 	ret = gpiochip_add(gc);
 	if (ret) {
 		dev_err(&pdev->dev, "failed adding byt-gpio chip\n");
@@ -569,6 +627,69 @@
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int byt_gpio_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct byt_gpio *vg = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < vg->chip.ngpio; i++) {
+		void __iomem *reg;
+		u32 value;
+
+		reg = byt_gpio_reg(&vg->chip, i, BYT_CONF0_REG);
+		value = readl(reg) & BYT_CONF0_RESTORE_MASK;
+		vg->saved_context[i].conf0 = value;
+
+		reg = byt_gpio_reg(&vg->chip, i, BYT_VAL_REG);
+		value = readl(reg) & BYT_VAL_RESTORE_MASK;
+		vg->saved_context[i].val = value;
+	}
+
+	return 0;
+}
+
+static int byt_gpio_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct byt_gpio *vg = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < vg->chip.ngpio; i++) {
+		void __iomem *reg;
+		u32 value;
+
+		reg = byt_gpio_reg(&vg->chip, i, BYT_CONF0_REG);
+		value = readl(reg);
+		if ((value & BYT_CONF0_RESTORE_MASK) !=
+		     vg->saved_context[i].conf0) {
+			value &= ~BYT_CONF0_RESTORE_MASK;
+			value |= vg->saved_context[i].conf0;
+			writel(value, reg);
+			dev_info(dev, "restored pin %d conf0 %#08x", i, value);
+		}
+
+		reg = byt_gpio_reg(&vg->chip, i, BYT_VAL_REG);
+		value = readl(reg);
+		if ((value & BYT_VAL_RESTORE_MASK) !=
+		     vg->saved_context[i].val) {
+			u32 v;
+
+			v = value & ~BYT_VAL_RESTORE_MASK;
+			v |= vg->saved_context[i].val;
+			if (v != value) {
+				writel(v, reg);
+				dev_dbg(dev, "restored pin %d val %#08x\n",
+					i, v);
+			}
+		}
+	}
+
+	return 0;
+}
+#endif
+
 static int byt_gpio_runtime_suspend(struct device *dev)
 {
 	return 0;
@@ -580,8 +701,9 @@
 }
 
 static const struct dev_pm_ops byt_gpio_pm_ops = {
-	.runtime_suspend = byt_gpio_runtime_suspend,
-	.runtime_resume = byt_gpio_runtime_resume,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(byt_gpio_suspend, byt_gpio_resume)
+	SET_RUNTIME_PM_OPS(byt_gpio_runtime_suspend, byt_gpio_runtime_resume,
+			   NULL)
 };
 
 static const struct acpi_device_id byt_gpio_acpi_match[] = {
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 3034fd0..82f691e 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1226,6 +1226,7 @@
 static int chv_gpio_direction_output(struct gpio_chip *chip, unsigned offset,
 				     int value)
 {
+	chv_gpio_set(chip, offset, value);
 	return pinctrl_gpio_direction_output(chip->base + offset);
 }
 
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index f4cd0b9..a481406 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -1477,28 +1477,25 @@
 	/* the interrupt is already cleared before by reading ISR */
 }
 
-static unsigned int gpio_irq_startup(struct irq_data *d)
+static int gpio_irq_request_res(struct irq_data *d)
 {
 	struct at91_gpio_chip *at91_gpio = irq_data_get_irq_chip_data(d);
 	unsigned	pin = d->hwirq;
 	int ret;
 
 	ret = gpiochip_lock_as_irq(&at91_gpio->chip, pin);
-	if (ret) {
+	if (ret)
 		dev_err(at91_gpio->chip.dev, "unable to lock pind %lu IRQ\n",
 			d->hwirq);
-		return ret;
-	}
-	gpio_irq_unmask(d);
-	return 0;
+
+	return ret;
 }
 
-static void gpio_irq_shutdown(struct irq_data *d)
+static void gpio_irq_release_res(struct irq_data *d)
 {
 	struct at91_gpio_chip *at91_gpio = irq_data_get_irq_chip_data(d);
 	unsigned	pin = d->hwirq;
 
-	gpio_irq_mask(d);
 	gpiochip_unlock_as_irq(&at91_gpio->chip, pin);
 }
 
@@ -1577,8 +1574,8 @@
 static struct irq_chip gpio_irqchip = {
 	.name		= "GPIO",
 	.irq_ack	= gpio_irq_ack,
-	.irq_startup	= gpio_irq_startup,
-	.irq_shutdown	= gpio_irq_shutdown,
+	.irq_request_resources = gpio_irq_request_res,
+	.irq_release_resources = gpio_irq_release_res,
 	.irq_disable	= gpio_irq_mask,
 	.irq_mask	= gpio_irq_mask,
 	.irq_unmask	= gpio_irq_unmask,
diff --git a/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c b/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c
index 24c5d88..3c68a8e 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sun4i-a10.c
@@ -1011,6 +1011,7 @@
 	.pins = sun4i_a10_pins,
 	.npins = ARRAY_SIZE(sun4i_a10_pins),
 	.irq_banks = 1,
+	.irq_read_needs_mux = true,
 };
 
 static int sun4i_a10_pinctrl_probe(struct platform_device *pdev)
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 3d07443..f8e171b 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 
 #include "../core.h"
+#include "../../gpio/gpiolib.h"
 #include "pinctrl-sunxi.h"
 
 static struct irq_chip sunxi_pinctrl_edge_irq_chip;
@@ -464,10 +465,19 @@
 static int sunxi_pinctrl_gpio_get(struct gpio_chip *chip, unsigned offset)
 {
 	struct sunxi_pinctrl *pctl = dev_get_drvdata(chip->dev);
-
 	u32 reg = sunxi_data_reg(offset);
 	u8 index = sunxi_data_offset(offset);
-	u32 val = (readl(pctl->membase + reg) >> index) & DATA_PINS_MASK;
+	u32 set_mux = pctl->desc->irq_read_needs_mux &&
+			test_bit(FLAG_USED_AS_IRQ, &chip->desc[offset].flags);
+	u32 val;
+
+	if (set_mux)
+		sunxi_pmx_set(pctl->pctl_dev, offset, SUN4I_FUNC_INPUT);
+
+	val = (readl(pctl->membase + reg) >> index) & DATA_PINS_MASK;
+
+	if (set_mux)
+		sunxi_pmx_set(pctl->pctl_dev, offset, SUN4I_FUNC_IRQ);
 
 	return val;
 }
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
index 5a51523..e248e81 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h
@@ -77,6 +77,9 @@
 #define IRQ_LEVEL_LOW		0x03
 #define IRQ_EDGE_BOTH		0x04
 
+#define SUN4I_FUNC_INPUT	0
+#define SUN4I_FUNC_IRQ		6
+
 struct sunxi_desc_function {
 	const char	*name;
 	u8		muxval;
@@ -94,6 +97,7 @@
 	int				npins;
 	unsigned			pin_base;
 	unsigned			irq_banks;
+	bool				irq_read_needs_mux;
 };
 
 struct sunxi_pinctrl_function {
diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c
index 97b5e4e..63d4033 100644
--- a/drivers/powercap/intel_rapl.c
+++ b/drivers/powercap/intel_rapl.c
@@ -73,7 +73,7 @@
 
 #define TIME_WINDOW_MAX_MSEC 40000
 #define TIME_WINDOW_MIN_MSEC 250
-
+#define ENERGY_UNIT_SCALE    1000 /* scale from driver unit to powercap unit */
 enum unit_type {
 	ARBITRARY_UNIT, /* no translation */
 	POWER_UNIT,
@@ -158,6 +158,7 @@
 	struct rapl_power_limit rpl[NR_POWER_LIMITS];
 	u64 attr_map; /* track capabilities */
 	unsigned int state;
+	unsigned int domain_energy_unit;
 	int package_id;
 };
 #define power_zone_to_rapl_domain(_zone) \
@@ -190,6 +191,7 @@
 	void (*set_floor_freq)(struct rapl_domain *rd, bool mode);
 	u64 (*compute_time_window)(struct rapl_package *rp, u64 val,
 				bool to_raw);
+	unsigned int dram_domain_energy_unit;
 };
 static struct rapl_defaults *rapl_defaults;
 
@@ -227,7 +229,8 @@
 static int rapl_write_data_raw(struct rapl_domain *rd,
 			enum rapl_primitives prim,
 			unsigned long long value);
-static u64 rapl_unit_xlate(int package, enum unit_type type, u64 value,
+static u64 rapl_unit_xlate(struct rapl_domain *rd, int package,
+			enum unit_type type, u64 value,
 			int to_raw);
 static void package_power_limit_irq_save(int package_id);
 
@@ -305,7 +308,9 @@
 
 static int get_max_energy_counter(struct powercap_zone *pcd_dev, u64 *energy)
 {
-	*energy = rapl_unit_xlate(0, ENERGY_UNIT, ENERGY_STATUS_MASK, 0);
+	struct rapl_domain *rd = power_zone_to_rapl_domain(pcd_dev);
+
+	*energy = rapl_unit_xlate(rd, 0, ENERGY_UNIT, ENERGY_STATUS_MASK, 0);
 	return 0;
 }
 
@@ -639,6 +644,11 @@
 			rd->msrs[4] = MSR_DRAM_POWER_INFO;
 			rd->rpl[0].prim_id = PL1_ENABLE;
 			rd->rpl[0].name = pl1_name;
+			rd->domain_energy_unit =
+				rapl_defaults->dram_domain_energy_unit;
+			if (rd->domain_energy_unit)
+				pr_info("DRAM domain energy unit %dpj\n",
+					rd->domain_energy_unit);
 			break;
 		}
 		if (mask) {
@@ -648,11 +658,13 @@
 	}
 }
 
-static u64 rapl_unit_xlate(int package, enum unit_type type, u64 value,
+static u64 rapl_unit_xlate(struct rapl_domain *rd, int package,
+			enum unit_type type, u64 value,
 			int to_raw)
 {
 	u64 units = 1;
 	struct rapl_package *rp;
+	u64 scale = 1;
 
 	rp = find_package_by_id(package);
 	if (!rp)
@@ -663,7 +675,12 @@
 		units = rp->power_unit;
 		break;
 	case ENERGY_UNIT:
-		units = rp->energy_unit;
+		scale = ENERGY_UNIT_SCALE;
+		/* per domain unit takes precedence */
+		if (rd && rd->domain_energy_unit)
+			units = rd->domain_energy_unit;
+		else
+			units = rp->energy_unit;
 		break;
 	case TIME_UNIT:
 		return rapl_defaults->compute_time_window(rp, value, to_raw);
@@ -673,11 +690,11 @@
 	};
 
 	if (to_raw)
-		return div64_u64(value, units);
+		return div64_u64(value, units) * scale;
 
 	value *= units;
 
-	return value;
+	return div64_u64(value, scale);
 }
 
 /* in the order of enum rapl_primitives */
@@ -773,7 +790,7 @@
 	final = value & rp->mask;
 	final = final >> rp->shift;
 	if (xlate)
-		*data = rapl_unit_xlate(rd->package_id, rp->unit, final, 0);
+		*data = rapl_unit_xlate(rd, rd->package_id, rp->unit, final, 0);
 	else
 		*data = final;
 
@@ -799,7 +816,7 @@
 			"failed to read msr 0x%x on cpu %d\n", msr, cpu);
 		return -EIO;
 	}
-	value = rapl_unit_xlate(rd->package_id, rp->unit, value, 1);
+	value = rapl_unit_xlate(rd, rd->package_id, rp->unit, value, 1);
 	msr_val &= ~rp->mask;
 	msr_val |= value << rp->shift;
 	if (wrmsrl_safe_on_cpu(cpu, msr, msr_val)) {
@@ -818,7 +835,7 @@
  * calculate units differ on different CPUs.
  * We convert the units to below format based on CPUs.
  * i.e.
- * energy unit: microJoules : Represented in microJoules by default
+ * energy unit: picoJoules  : Represented in picoJoules by default
  * power unit : microWatts  : Represented in milliWatts by default
  * time unit  : microseconds: Represented in seconds by default
  */
@@ -834,7 +851,7 @@
 	}
 
 	value = (msr_val & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET;
-	rp->energy_unit = 1000000 / (1 << value);
+	rp->energy_unit = ENERGY_UNIT_SCALE * 1000000 / (1 << value);
 
 	value = (msr_val & POWER_UNIT_MASK) >> POWER_UNIT_OFFSET;
 	rp->power_unit = 1000000 / (1 << value);
@@ -842,7 +859,7 @@
 	value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET;
 	rp->time_unit = 1000000 / (1 << value);
 
-	pr_debug("Core CPU package %d energy=%duJ, time=%dus, power=%duW\n",
+	pr_debug("Core CPU package %d energy=%dpJ, time=%dus, power=%duW\n",
 		rp->id, rp->energy_unit, rp->time_unit, rp->power_unit);
 
 	return 0;
@@ -859,7 +876,7 @@
 		return -ENODEV;
 	}
 	value = (msr_val & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET;
-	rp->energy_unit = 1 << value;
+	rp->energy_unit = ENERGY_UNIT_SCALE * 1 << value;
 
 	value = (msr_val & POWER_UNIT_MASK) >> POWER_UNIT_OFFSET;
 	rp->power_unit = (1 << value) * 1000;
@@ -867,7 +884,7 @@
 	value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET;
 	rp->time_unit = 1000000 / (1 << value);
 
-	pr_debug("Atom package %d energy=%duJ, time=%dus, power=%duW\n",
+	pr_debug("Atom package %d energy=%dpJ, time=%dus, power=%duW\n",
 		rp->id, rp->energy_unit, rp->time_unit, rp->power_unit);
 
 	return 0;
@@ -1017,6 +1034,13 @@
 	.compute_time_window = rapl_compute_time_window_core,
 };
 
+static const struct rapl_defaults rapl_defaults_hsw_server = {
+	.check_unit = rapl_check_unit_core,
+	.set_floor_freq = set_floor_freq_default,
+	.compute_time_window = rapl_compute_time_window_core,
+	.dram_domain_energy_unit = 15300,
+};
+
 static const struct rapl_defaults rapl_defaults_atom = {
 	.check_unit = rapl_check_unit_atom,
 	.set_floor_freq = set_floor_freq_atom,
@@ -1037,7 +1061,7 @@
 	RAPL_CPU(0x3a, rapl_defaults_core),/* Ivy Bridge */
 	RAPL_CPU(0x3c, rapl_defaults_core),/* Haswell */
 	RAPL_CPU(0x3d, rapl_defaults_core),/* Broadwell */
-	RAPL_CPU(0x3f, rapl_defaults_core),/* Haswell */
+	RAPL_CPU(0x3f, rapl_defaults_hsw_server),/* Haswell servers */
 	RAPL_CPU(0x45, rapl_defaults_core),/* Haswell ULT */
 	RAPL_CPU(0x4C, rapl_defaults_atom),/* Braswell */
 	RAPL_CPU(0x4A, rapl_defaults_atom),/* Tangier */
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 1245dca..a4a8a6d 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1839,10 +1839,12 @@
 	}
 
 	if (rdev->ena_pin) {
-		ret = regulator_ena_gpio_ctrl(rdev, true);
-		if (ret < 0)
-			return ret;
-		rdev->ena_gpio_state = 1;
+		if (!rdev->ena_gpio_state) {
+			ret = regulator_ena_gpio_ctrl(rdev, true);
+			if (ret < 0)
+				return ret;
+			rdev->ena_gpio_state = 1;
+		}
 	} else if (rdev->desc->ops->enable) {
 		ret = rdev->desc->ops->enable(rdev);
 		if (ret < 0)
@@ -1939,10 +1941,12 @@
 	trace_regulator_disable(rdev_get_name(rdev));
 
 	if (rdev->ena_pin) {
-		ret = regulator_ena_gpio_ctrl(rdev, false);
-		if (ret < 0)
-			return ret;
-		rdev->ena_gpio_state = 0;
+		if (rdev->ena_gpio_state) {
+			ret = regulator_ena_gpio_ctrl(rdev, false);
+			if (ret < 0)
+				return ret;
+			rdev->ena_gpio_state = 0;
+		}
 
 	} else if (rdev->desc->ops->disable) {
 		ret = rdev->desc->ops->disable(rdev);
@@ -3626,12 +3630,6 @@
 				 config->ena_gpio, ret);
 			goto wash;
 		}
-
-		if (config->ena_gpio_flags & GPIOF_OUT_INIT_HIGH)
-			rdev->ena_gpio_state = 1;
-
-		if (config->ena_gpio_invert)
-			rdev->ena_gpio_state = !rdev->ena_gpio_state;
 	}
 
 	/* set regulator constraints */
@@ -3800,9 +3798,11 @@
 	list_for_each_entry(rdev, &regulator_list, list) {
 		mutex_lock(&rdev->mutex);
 		if (rdev->use_count > 0  || rdev->constraints->always_on) {
-			error = _regulator_do_enable(rdev);
-			if (error)
-				ret = error;
+			if (!_regulator_is_enabled(rdev)) {
+				error = _regulator_do_enable(rdev);
+				if (error)
+					ret = error;
+			}
 		} else {
 			if (!have_full_constraints())
 				goto unlock;
diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c
index 9205f43..1819831 100644
--- a/drivers/regulator/palmas-regulator.c
+++ b/drivers/regulator/palmas-regulator.c
@@ -1572,6 +1572,10 @@
 	if (!pmic)
 		return -ENOMEM;
 
+	if (of_device_is_compatible(node, "ti,tps659038-pmic"))
+		palmas_generic_regs_info[PALMAS_REG_REGEN2].ctrl_addr =
+							TPS659038_REGEN2_CTRL;
+
 	pmic->dev = &pdev->dev;
 	pmic->palmas = palmas;
 	palmas->pmic = pmic;
diff --git a/drivers/regulator/tps65910-regulator.c b/drivers/regulator/tps65910-regulator.c
index e2cffe0..fb991ec 100644
--- a/drivers/regulator/tps65910-regulator.c
+++ b/drivers/regulator/tps65910-regulator.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/err.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c
index 92f6af6..73354ee 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -951,6 +951,7 @@
 	void *bufs_va;
 	int err = 0, i;
 	size_t total_buf_space;
+	bool notify;
 
 	vrp = kzalloc(sizeof(*vrp), GFP_KERNEL);
 	if (!vrp)
@@ -1030,8 +1031,22 @@
 		}
 	}
 
+	/*
+	 * Prepare to kick but don't notify yet - we can't do this before
+	 * device is ready.
+	 */
+	notify = virtqueue_kick_prepare(vrp->rvq);
+
+	/* From this point on, we can notify and get callbacks. */
+	virtio_device_ready(vdev);
+
 	/* tell the remote processor it can start sending messages */
-	virtqueue_kick(vrp->rvq);
+	/*
+	 * this might be concurrent with callbacks, but we are only
+	 * doing notify, not a full kick here, so that's ok.
+	 */
+	if (notify)
+		virtqueue_notify(vrp->rvq);
 
 	dev_info(&vdev->dev, "rpmsg host is online\n");
 
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index b4f7744..b283a1a 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -324,7 +324,7 @@
 
 		ret = IRQ_HANDLED;
 	}
-	spin_lock(&suspended_lock);
+	spin_unlock(&suspended_lock);
 
 	return ret;
 }
diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c
index e2436d1..3a6fd3a 100644
--- a/drivers/rtc/rtc-mrst.c
+++ b/drivers/rtc/rtc-mrst.c
@@ -413,8 +413,8 @@
 	mrst->dev = NULL;
 }
 
-#ifdef	CONFIG_PM
-static int mrst_suspend(struct device *dev, pm_message_t mesg)
+#ifdef CONFIG_PM_SLEEP
+static int mrst_suspend(struct device *dev)
 {
 	struct mrst_rtc	*mrst = dev_get_drvdata(dev);
 	unsigned char	tmp;
@@ -453,7 +453,7 @@
  */
 static inline int mrst_poweroff(struct device *dev)
 {
-	return mrst_suspend(dev, PMSG_HIBERNATE);
+	return mrst_suspend(dev);
 }
 
 static int mrst_resume(struct device *dev)
@@ -490,9 +490,11 @@
 	return 0;
 }
 
+static SIMPLE_DEV_PM_OPS(mrst_pm_ops, mrst_suspend, mrst_resume);
+#define MRST_PM_OPS (&mrst_pm_ops)
+
 #else
-#define	mrst_suspend	NULL
-#define	mrst_resume	NULL
+#define MRST_PM_OPS NULL
 
 static inline int mrst_poweroff(struct device *dev)
 {
@@ -529,9 +531,8 @@
 	.remove		= vrtc_mrst_platform_remove,
 	.shutdown	= vrtc_mrst_platform_shutdown,
 	.driver = {
-		.name		= (char *) driver_name,
-		.suspend	= mrst_suspend,
-		.resume		= mrst_resume,
+		.name	= driver_name,
+		.pm	= MRST_PM_OPS,
 	}
 };
 
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 9219953..d9afc51 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -6815,7 +6815,8 @@
 };
 
 static struct ata_port_info sata_port_info = {
-	.flags		= ATA_FLAG_SATA | ATA_FLAG_PIO_DMA,
+	.flags		= ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
+			  ATA_FLAG_SAS_HOST,
 	.pio_mask	= ATA_PIO4_ONLY,
 	.mwdma_mask	= ATA_MWDMA2,
 	.udma_mask	= ATA_UDMA6,
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 932d9cc..9c706d8 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -547,7 +547,8 @@
 };
 
 static struct ata_port_info sata_port_info = {
-	.flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ,
+	.flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ |
+		 ATA_FLAG_SAS_HOST,
 	.pio_mask = ATA_PIO4,
 	.mwdma_mask = ATA_MWDMA2,
 	.udma_mask = ATA_UDMA6,
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 99f43b7..ab4879e 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1596,7 +1596,7 @@
 	/*
 	 * Finally register the new FC Nexus with TCM
 	 */
-	__transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess);
+	transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 3ce39d1..4f8c798 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -108,7 +108,8 @@
 {
 	struct dw_spi *dws = arg;
 
-	if (test_and_clear_bit(TX_BUSY, &dws->dma_chan_busy) & BIT(RX_BUSY))
+	clear_bit(TX_BUSY, &dws->dma_chan_busy);
+	if (test_bit(RX_BUSY, &dws->dma_chan_busy))
 		return;
 	dw_spi_xfer_done(dws);
 }
@@ -156,7 +157,8 @@
 {
 	struct dw_spi *dws = arg;
 
-	if (test_and_clear_bit(RX_BUSY, &dws->dma_chan_busy) & BIT(TX_BUSY))
+	clear_bit(RX_BUSY, &dws->dma_chan_busy);
+	if (test_bit(TX_BUSY, &dws->dma_chan_busy))
 		return;
 	dw_spi_xfer_done(dws);
 }
diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
index ff9cdbd..2b2c359 100644
--- a/drivers/spi/spi-qup.c
+++ b/drivers/spi/spi-qup.c
@@ -498,7 +498,7 @@
 	struct resource *res;
 	struct device *dev;
 	void __iomem *base;
-	u32 max_freq, iomode;
+	u32 max_freq, iomode, num_cs;
 	int ret, irq, size;
 
 	dev = &pdev->dev;
@@ -550,10 +550,11 @@
 	}
 
 	/* use num-cs unless not present or out of range */
-	if (of_property_read_u16(dev->of_node, "num-cs",
-			&master->num_chipselect) ||
-			(master->num_chipselect > SPI_NUM_CHIPSELECTS))
+	if (of_property_read_u32(dev->of_node, "num-cs", &num_cs) ||
+	    num_cs > SPI_NUM_CHIPSELECTS)
 		master->num_chipselect = SPI_NUM_CHIPSELECTS;
+	else
+		master->num_chipselect = num_cs;
 
 	master->bus_num = pdev->id;
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LOOP;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index c64a3e5..57a1950 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1105,13 +1105,14 @@
 				"failed to unprepare message: %d\n", ret);
 		}
 	}
+
+	trace_spi_message_done(mesg);
+
 	master->cur_msg_prepared = false;
 
 	mesg->state = NULL;
 	if (mesg->complete)
 		mesg->complete(mesg->context);
-
-	trace_spi_message_done(mesg);
 }
 EXPORT_SYMBOL_GPL(spi_finalize_current_message);
 
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index 4324282a..03b2a90 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -330,16 +330,6 @@
 	/* zonetype initial */
 	pDevice->byOriginalZonetype = pDevice->abyEEPROM[EEP_OFS_ZONETYPE];
 
-	/* Get RFType */
-	pDevice->byRFType = SROMbyReadEmbedded(pDevice->PortOffset, EEP_OFS_RFTYPE);
-
-	/* force change RevID for VT3253 emu */
-	if ((pDevice->byRFType & RF_EMU) != 0)
-			pDevice->byRevId = 0x80;
-
-	pDevice->byRFType &= RF_MASK;
-	pr_debug("pDevice->byRFType = %x\n", pDevice->byRFType);
-
 	if (!pDevice->bZoneRegExist)
 		pDevice->byZoneType = pDevice->abyEEPROM[EEP_OFS_ZONETYPE];
 
@@ -1187,12 +1177,14 @@
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	PSTxDesc head_td;
-	u32 dma_idx = TYPE_AC0DMA;
+	u32 dma_idx;
 	unsigned long flags;
 
 	spin_lock_irqsave(&priv->lock, flags);
 
-	if (!ieee80211_is_data(hdr->frame_control))
+	if (ieee80211_is_data(hdr->frame_control))
+		dma_idx = TYPE_AC0DMA;
+	else
 		dma_idx = TYPE_TXDMA0;
 
 	if (AVAIL_TD(priv, dma_idx) < 1) {
@@ -1206,6 +1198,9 @@
 
 	head_td->pTDInfo->skb = skb;
 
+	if (dma_idx == TYPE_AC0DMA)
+		head_td->pTDInfo->byFlags = TD_FLAGS_NETIF_SKB;
+
 	priv->iTDUsed[dma_idx]++;
 
 	/* Take ownership */
@@ -1234,13 +1229,10 @@
 
 	head_td->buff_addr = cpu_to_le32(head_td->pTDInfo->skb_dma);
 
-	if (dma_idx == TYPE_AC0DMA) {
-		head_td->pTDInfo->byFlags = TD_FLAGS_NETIF_SKB;
-
+	if (head_td->pTDInfo->byFlags & TD_FLAGS_NETIF_SKB)
 		MACvTransmitAC0(priv->PortOffset);
-	} else {
+	else
 		MACvTransmit0(priv->PortOffset);
-	}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 
@@ -1778,6 +1770,12 @@
 	MACvInitialize(priv->PortOffset);
 	MACvReadEtherAddress(priv->PortOffset, priv->abyCurrentNetAddr);
 
+	/* Get RFType */
+	priv->byRFType = SROMbyReadEmbedded(priv->PortOffset, EEP_OFS_RFTYPE);
+	priv->byRFType &= RF_MASK;
+
+	dev_dbg(&pcid->dev, "RF Type = %x\n", priv->byRFType);
+
 	device_get_options(priv);
 	device_set_options(priv);
 	/* Mask out the options cannot be set to the chip */
diff --git a/drivers/staging/vt6655/rf.c b/drivers/staging/vt6655/rf.c
index 941b2ad..7626f63 100644
--- a/drivers/staging/vt6655/rf.c
+++ b/drivers/staging/vt6655/rf.c
@@ -794,6 +794,7 @@
 		break;
 	case RATE_6M:
 	case RATE_9M:
+	case RATE_12M:
 	case RATE_18M:
 		byPwr = priv->abyOFDMPwrTbl[uCH];
 		if (priv->byRFType == RF_UW2452)
diff --git a/drivers/staging/vt6656/rf.c b/drivers/staging/vt6656/rf.c
index c42cde5..c4286cc 100644
--- a/drivers/staging/vt6656/rf.c
+++ b/drivers/staging/vt6656/rf.c
@@ -640,6 +640,7 @@
 		break;
 	case RATE_6M:
 	case RATE_9M:
+	case RATE_12M:
 	case RATE_18M:
 	case RATE_24M:
 	case RATE_36M:
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 50bad55..2accb6e 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -4256,11 +4256,17 @@
 	pr_debug("Closing iSCSI connection CID %hu on SID:"
 		" %u\n", conn->cid, sess->sid);
 	/*
-	 * Always up conn_logout_comp just in case the RX Thread is sleeping
-	 * and the logout response never got sent because the connection
-	 * failed.
+	 * Always up conn_logout_comp for the traditional TCP case just in case
+	 * the RX Thread in iscsi_target_rx_opcode() is sleeping and the logout
+	 * response never got sent because the connection failed.
+	 *
+	 * However for iser-target, isert_wait4logout() is using conn_logout_comp
+	 * to signal logout response TX interrupt completion.  Go ahead and skip
+	 * this for iser since isert_rx_opcode() does not wait on logout failure,
+	 * and to avoid iscsi_conn pointer dereference in iser-target code.
 	 */
-	complete(&conn->conn_logout_comp);
+	if (conn->conn_transport->transport_type == ISCSI_TCP)
+		complete(&conn->conn_logout_comp);
 
 	iscsi_release_thread_set(conn);
 
diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c
index 1c197ba..bdd8731 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.c
+++ b/drivers/target/iscsi/iscsi_target_erl0.c
@@ -22,7 +22,6 @@
 #include <target/target_core_fabric.h>
 
 #include <target/iscsi/iscsi_target_core.h>
-#include <target/iscsi/iscsi_transport.h>
 #include "iscsi_target_seq_pdu_list.h"
 #include "iscsi_target_tq.h"
 #include "iscsi_target_erl0.h"
@@ -940,8 +939,7 @@
 
 	if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) {
 		spin_unlock_bh(&conn->state_lock);
-		if (conn->conn_transport->transport_type == ISCSI_TCP)
-			iscsit_close_connection(conn);
+		iscsit_close_connection(conn);
 		return;
 	}
 
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 6b3c329..c36bd7c 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -953,11 +953,8 @@
 		transport_free_session(tl_nexus->se_sess);
 		goto out;
 	}
-	/*
-	 * Now, register the SAS I_T Nexus as active with the call to
-	 * transport_register_session()
-	 */
-	__transport_register_session(se_tpg, tl_nexus->se_sess->se_node_acl,
+	/* Now, register the SAS I_T Nexus as active. */
+	transport_register_session(se_tpg, tl_nexus->se_sess->se_node_acl,
 			tl_nexus->se_sess, tl_nexus);
 	tl_tpg->tl_nexus = tl_nexus;
 	pr_debug("TCM_Loop_ConfigFS: Established I_T Nexus to emulated"
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 58f49ff..79b4ec3 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -650,6 +650,18 @@
 	return aligned_max_sectors;
 }
 
+bool se_dev_check_wce(struct se_device *dev)
+{
+	bool wce = false;
+
+	if (dev->transport->get_write_cache)
+		wce = dev->transport->get_write_cache(dev);
+	else if (dev->dev_attrib.emulate_write_cache > 0)
+		wce = true;
+
+	return wce;
+}
+
 int se_dev_set_max_unmap_lba_count(
 	struct se_device *dev,
 	u32 max_unmap_lba_count)
@@ -767,6 +779,16 @@
 		pr_err("Illegal value %d\n", flag);
 		return -EINVAL;
 	}
+	if (flag &&
+	    dev->transport->get_write_cache) {
+		pr_err("emulate_fua_write not supported for this device\n");
+		return -EINVAL;
+	}
+	if (dev->export_count) {
+		pr_err("emulate_fua_write cannot be changed with active"
+		       " exports: %d\n", dev->export_count);
+		return -EINVAL;
+	}
 	dev->dev_attrib.emulate_fua_write = flag;
 	pr_debug("dev[%p]: SE Device Forced Unit Access WRITEs: %d\n",
 			dev, dev->dev_attrib.emulate_fua_write);
@@ -801,7 +823,11 @@
 		pr_err("emulate_write_cache not supported for this device\n");
 		return -EINVAL;
 	}
-
+	if (dev->export_count) {
+		pr_err("emulate_write_cache cannot be changed with active"
+		       " exports: %d\n", dev->export_count);
+		return -EINVAL;
+	}
 	dev->dev_attrib.emulate_write_cache = flag;
 	pr_debug("dev[%p]: SE Device WRITE_CACHE_EMULATION flag: %d\n",
 			dev, dev->dev_attrib.emulate_write_cache);
@@ -1534,8 +1560,6 @@
 	ret = dev->transport->configure_device(dev);
 	if (ret)
 		goto out;
-	dev->dev_flags |= DF_CONFIGURED;
-
 	/*
 	 * XXX: there is not much point to have two different values here..
 	 */
@@ -1597,6 +1621,8 @@
 	list_add_tail(&dev->g_dev_node, &g_device_list);
 	mutex_unlock(&g_device_mutex);
 
+	dev->dev_flags |= DF_CONFIGURED;
+
 	return 0;
 
 out_free_alua:
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 1045dcd..f6c954c 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -1121,7 +1121,7 @@
 	struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
 	struct scsi_device *sd = pdv->pdv_sd;
 
-	return sd->type;
+	return (sd) ? sd->type : TYPE_NO_LUN;
 }
 
 static sector_t pscsi_get_blocks(struct se_device *dev)
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 9a2f9d3..3e72974 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -708,8 +708,7 @@
 		}
 	}
 	if (cdb[1] & 0x8) {
-		if (!dev->dev_attrib.emulate_fua_write ||
-		    !dev->dev_attrib.emulate_write_cache) {
+		if (!dev->dev_attrib.emulate_fua_write || !se_dev_check_wce(dev)) {
 			pr_err("Got CDB: 0x%02x with FUA bit set, but device"
 			       " does not advertise support for FUA write\n",
 			       cdb[0]);
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 460e931..6c8bd6b 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -454,19 +454,6 @@
 }
 EXPORT_SYMBOL(spc_emulate_evpd_83);
 
-static bool
-spc_check_dev_wce(struct se_device *dev)
-{
-	bool wce = false;
-
-	if (dev->transport->get_write_cache)
-		wce = dev->transport->get_write_cache(dev);
-	else if (dev->dev_attrib.emulate_write_cache > 0)
-		wce = true;
-
-	return wce;
-}
-
 /* Extended INQUIRY Data VPD Page */
 static sense_reason_t
 spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf)
@@ -490,7 +477,7 @@
 	buf[5] = 0x07;
 
 	/* If WriteCache emulation is enabled, set V_SUP */
-	if (spc_check_dev_wce(dev))
+	if (se_dev_check_wce(dev))
 		buf[6] = 0x01;
 	/* If an LBA map is present set R_SUP */
 	spin_lock(&cmd->se_dev->t10_alua.lba_map_lock);
@@ -897,7 +884,7 @@
 	if (pc == 1)
 		goto out;
 
-	if (spc_check_dev_wce(dev))
+	if (se_dev_check_wce(dev))
 		p[2] = 0x04; /* Write Cache Enable */
 	p[12] = 0x20; /* Disabled Read Ahead */
 
@@ -1009,7 +996,7 @@
 	     (cmd->se_deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)))
 		spc_modesense_write_protect(&buf[length], type);
 
-	if ((spc_check_dev_wce(dev)) &&
+	if ((se_dev_check_wce(dev)) &&
 	    (dev->dev_attrib.emulate_fua_write > 0))
 		spc_modesense_dpofua(&buf[length], type);
 
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 0adc0f6..ac3cbab 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2389,6 +2389,10 @@
 	list_add_tail(&se_cmd->se_cmd_list, &se_sess->sess_cmd_list);
 out:
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+
+	if (ret && ack_kref)
+		target_put_sess_cmd(se_sess, se_cmd);
+
 	return ret;
 }
 EXPORT_SYMBOL(target_get_sess_cmd);
diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c
index 97b486c..583e755 100644
--- a/drivers/target/tcm_fc/tfc_io.c
+++ b/drivers/target/tcm_fc/tfc_io.c
@@ -359,7 +359,7 @@
 		ep = fc_seq_exch(seq);
 		if (ep) {
 			lport = ep->lp;
-			if (lport && (ep->xid <= lport->lro_xid))
+			if (lport && (ep->xid <= lport->lro_xid)) {
 				/*
 				 * "ddp_done" trigger invalidation of HW
 				 * specific DDP context
@@ -374,6 +374,7 @@
 				 * identified using ep->xid)
 				 */
 				cmd->was_ddp_setup = 0;
+			}
 		}
 	}
 }
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 2ab229d..6ae5b85 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -119,7 +119,10 @@
 			dw8250_force_idle(p);
 			writeb(value, p->membase + (UART_LCR << p->regshift));
 		}
-		dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+		/*
+		 * FIXME: this deadlocks if port->lock is already held
+		 * dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+		 */
 	}
 }
 
@@ -163,7 +166,10 @@
 			__raw_writeq(value & 0xff,
 				     p->membase + (UART_LCR << p->regshift));
 		}
-		dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+		/*
+		 * FIXME: this deadlocks if port->lock is already held
+		 * dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+		 */
 	}
 }
 #endif /* CONFIG_64BIT */
@@ -187,7 +193,10 @@
 			dw8250_force_idle(p);
 			writel(value, p->membase + (UART_LCR << p->regshift));
 		}
-		dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+		/*
+		 * FIXME: this deadlocks if port->lock is already held
+		 * dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+		 */
 	}
 }
 
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index ff45104..4bfb7ac 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -929,6 +929,13 @@
 	return retval;
 }
 
+static int otg_a_alt_hnp_support(struct ci_hdrc *ci)
+{
+	dev_warn(&ci->gadget.dev,
+		"connect the device to an alternate port if you want HNP\n");
+	return isr_setup_status_phase(ci);
+}
+
 /**
  * isr_setup_packet_handler: setup packet handler
  * @ci: UDC descriptor
@@ -1061,6 +1068,10 @@
 							ci);
 				}
 				break;
+			case USB_DEVICE_A_ALT_HNP_SUPPORT:
+				if (ci_otg_is_fsm_mode(ci))
+					err = otg_a_alt_hnp_support(ci);
+				break;
 			default:
 				goto delegate;
 			}
diff --git a/drivers/usb/common/usb-otg-fsm.c b/drivers/usb/common/usb-otg-fsm.c
index c6b35b7..61d538a 100644
--- a/drivers/usb/common/usb-otg-fsm.c
+++ b/drivers/usb/common/usb-otg-fsm.c
@@ -150,9 +150,9 @@
 		break;
 	case OTG_STATE_B_PERIPHERAL:
 		otg_chrg_vbus(fsm, 0);
-		otg_loc_conn(fsm, 1);
 		otg_loc_sof(fsm, 0);
 		otg_set_protocol(fsm, PROTO_GADGET);
+		otg_loc_conn(fsm, 1);
 		break;
 	case OTG_STATE_B_WAIT_ACON:
 		otg_chrg_vbus(fsm, 0);
@@ -213,10 +213,10 @@
 
 		break;
 	case OTG_STATE_A_PERIPHERAL:
-		otg_loc_conn(fsm, 1);
 		otg_loc_sof(fsm, 0);
 		otg_set_protocol(fsm, PROTO_GADGET);
 		otg_drv_vbus(fsm, 1);
+		otg_loc_conn(fsm, 1);
 		otg_add_timer(fsm, A_BIDL_ADIS);
 		break;
 	case OTG_STATE_A_WAIT_VFALL:
diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c
index 02e3e2d..6cf0478 100644
--- a/drivers/usb/dwc2/core_intr.c
+++ b/drivers/usb/dwc2/core_intr.c
@@ -377,6 +377,9 @@
 		dwc2_is_host_mode(hsotg) ? "Host" : "Device",
 		dwc2_op_state_str(hsotg));
 
+	if (hsotg->op_state == OTG_STATE_A_HOST)
+		dwc2_hcd_disconnect(hsotg);
+
 	/* Change to L3 (OFF) state */
 	hsotg->lx_state = DWC2_L3;
 
diff --git a/drivers/usb/gadget/function/f_loopback.c b/drivers/usb/gadget/function/f_loopback.c
index 298b461..39f49f1 100644
--- a/drivers/usb/gadget/function/f_loopback.c
+++ b/drivers/usb/gadget/function/f_loopback.c
@@ -289,8 +289,7 @@
 	struct usb_composite_dev	*cdev;
 
 	cdev = loop->function.config->cdev;
-	disable_endpoints(cdev, loop->in_ep, loop->out_ep, NULL, NULL, NULL,
-			NULL);
+	disable_endpoints(cdev, loop->in_ep, loop->out_ep, NULL, NULL);
 	VDBG(cdev, "%s disabled\n", loop->function.name);
 }
 
diff --git a/drivers/usb/gadget/function/f_sourcesink.c b/drivers/usb/gadget/function/f_sourcesink.c
index e3dae47..3a5ae99 100644
--- a/drivers/usb/gadget/function/f_sourcesink.c
+++ b/drivers/usb/gadget/function/f_sourcesink.c
@@ -23,15 +23,6 @@
 #include "gadget_chips.h"
 #include "u_f.h"
 
-#define USB_MS_TO_SS_INTERVAL(x) USB_MS_TO_HS_INTERVAL(x)
-
-enum eptype {
-	EP_CONTROL = 0,
-	EP_BULK,
-	EP_ISOC,
-	EP_INTERRUPT,
-};
-
 /*
  * SOURCE/SINK FUNCTION ... a primary testing vehicle for USB peripheral
  * controller drivers.
@@ -64,8 +55,6 @@
 	struct usb_ep		*out_ep;
 	struct usb_ep		*iso_in_ep;
 	struct usb_ep		*iso_out_ep;
-	struct usb_ep		*int_in_ep;
-	struct usb_ep		*int_out_ep;
 	int			cur_alt;
 };
 
@@ -79,10 +68,6 @@
 static unsigned isoc_maxpacket;
 static unsigned isoc_mult;
 static unsigned isoc_maxburst;
-static unsigned int_interval; /* In ms */
-static unsigned int_maxpacket;
-static unsigned int_mult;
-static unsigned int_maxburst;
 static unsigned buflen;
 
 /*-------------------------------------------------------------------------*/
@@ -107,16 +92,6 @@
 	/* .iInterface		= DYNAMIC */
 };
 
-static struct usb_interface_descriptor source_sink_intf_alt2 = {
-	.bLength =		USB_DT_INTERFACE_SIZE,
-	.bDescriptorType =	USB_DT_INTERFACE,
-
-	.bAlternateSetting =	2,
-	.bNumEndpoints =	2,
-	.bInterfaceClass =	USB_CLASS_VENDOR_SPEC,
-	/* .iInterface		= DYNAMIC */
-};
-
 /* full speed support: */
 
 static struct usb_endpoint_descriptor fs_source_desc = {
@@ -155,26 +130,6 @@
 	.bInterval =		4,
 };
 
-static struct usb_endpoint_descriptor fs_int_source_desc = {
-	.bLength =		USB_DT_ENDPOINT_SIZE,
-	.bDescriptorType =	USB_DT_ENDPOINT,
-
-	.bEndpointAddress =	USB_DIR_IN,
-	.bmAttributes =		USB_ENDPOINT_XFER_INT,
-	.wMaxPacketSize =	cpu_to_le16(64),
-	.bInterval =		GZERO_INT_INTERVAL,
-};
-
-static struct usb_endpoint_descriptor fs_int_sink_desc = {
-	.bLength =		USB_DT_ENDPOINT_SIZE,
-	.bDescriptorType =	USB_DT_ENDPOINT,
-
-	.bEndpointAddress =	USB_DIR_OUT,
-	.bmAttributes =		USB_ENDPOINT_XFER_INT,
-	.wMaxPacketSize =	cpu_to_le16(64),
-	.bInterval =		GZERO_INT_INTERVAL,
-};
-
 static struct usb_descriptor_header *fs_source_sink_descs[] = {
 	(struct usb_descriptor_header *) &source_sink_intf_alt0,
 	(struct usb_descriptor_header *) &fs_sink_desc,
@@ -185,10 +140,6 @@
 	(struct usb_descriptor_header *) &fs_source_desc,
 	(struct usb_descriptor_header *) &fs_iso_sink_desc,
 	(struct usb_descriptor_header *) &fs_iso_source_desc,
-	(struct usb_descriptor_header *) &source_sink_intf_alt2,
-#define FS_ALT_IFC_2_OFFSET	8
-	(struct usb_descriptor_header *) &fs_int_sink_desc,
-	(struct usb_descriptor_header *) &fs_int_source_desc,
 	NULL,
 };
 
@@ -228,24 +179,6 @@
 	.bInterval =		4,
 };
 
-static struct usb_endpoint_descriptor hs_int_source_desc = {
-	.bLength =		USB_DT_ENDPOINT_SIZE,
-	.bDescriptorType =	USB_DT_ENDPOINT,
-
-	.bmAttributes =		USB_ENDPOINT_XFER_INT,
-	.wMaxPacketSize =	cpu_to_le16(1024),
-	.bInterval =		USB_MS_TO_HS_INTERVAL(GZERO_INT_INTERVAL),
-};
-
-static struct usb_endpoint_descriptor hs_int_sink_desc = {
-	.bLength =		USB_DT_ENDPOINT_SIZE,
-	.bDescriptorType =	USB_DT_ENDPOINT,
-
-	.bmAttributes =		USB_ENDPOINT_XFER_INT,
-	.wMaxPacketSize =	cpu_to_le16(1024),
-	.bInterval =		USB_MS_TO_HS_INTERVAL(GZERO_INT_INTERVAL),
-};
-
 static struct usb_descriptor_header *hs_source_sink_descs[] = {
 	(struct usb_descriptor_header *) &source_sink_intf_alt0,
 	(struct usb_descriptor_header *) &hs_source_desc,
@@ -256,10 +189,6 @@
 	(struct usb_descriptor_header *) &hs_sink_desc,
 	(struct usb_descriptor_header *) &hs_iso_source_desc,
 	(struct usb_descriptor_header *) &hs_iso_sink_desc,
-	(struct usb_descriptor_header *) &source_sink_intf_alt2,
-#define HS_ALT_IFC_2_OFFSET	8
-	(struct usb_descriptor_header *) &hs_int_source_desc,
-	(struct usb_descriptor_header *) &hs_int_sink_desc,
 	NULL,
 };
 
@@ -335,42 +264,6 @@
 	.wBytesPerInterval =	cpu_to_le16(1024),
 };
 
-static struct usb_endpoint_descriptor ss_int_source_desc = {
-	.bLength =		USB_DT_ENDPOINT_SIZE,
-	.bDescriptorType =	USB_DT_ENDPOINT,
-
-	.bmAttributes =		USB_ENDPOINT_XFER_INT,
-	.wMaxPacketSize =	cpu_to_le16(1024),
-	.bInterval =		USB_MS_TO_SS_INTERVAL(GZERO_INT_INTERVAL),
-};
-
-static struct usb_ss_ep_comp_descriptor ss_int_source_comp_desc = {
-	.bLength =		USB_DT_SS_EP_COMP_SIZE,
-	.bDescriptorType =	USB_DT_SS_ENDPOINT_COMP,
-
-	.bMaxBurst =		0,
-	.bmAttributes =		0,
-	.wBytesPerInterval =	cpu_to_le16(1024),
-};
-
-static struct usb_endpoint_descriptor ss_int_sink_desc = {
-	.bLength =		USB_DT_ENDPOINT_SIZE,
-	.bDescriptorType =	USB_DT_ENDPOINT,
-
-	.bmAttributes =		USB_ENDPOINT_XFER_INT,
-	.wMaxPacketSize =	cpu_to_le16(1024),
-	.bInterval =		USB_MS_TO_SS_INTERVAL(GZERO_INT_INTERVAL),
-};
-
-static struct usb_ss_ep_comp_descriptor ss_int_sink_comp_desc = {
-	.bLength =		USB_DT_SS_EP_COMP_SIZE,
-	.bDescriptorType =	USB_DT_SS_ENDPOINT_COMP,
-
-	.bMaxBurst =		0,
-	.bmAttributes =		0,
-	.wBytesPerInterval =	cpu_to_le16(1024),
-};
-
 static struct usb_descriptor_header *ss_source_sink_descs[] = {
 	(struct usb_descriptor_header *) &source_sink_intf_alt0,
 	(struct usb_descriptor_header *) &ss_source_desc,
@@ -387,12 +280,6 @@
 	(struct usb_descriptor_header *) &ss_iso_source_comp_desc,
 	(struct usb_descriptor_header *) &ss_iso_sink_desc,
 	(struct usb_descriptor_header *) &ss_iso_sink_comp_desc,
-	(struct usb_descriptor_header *) &source_sink_intf_alt2,
-#define SS_ALT_IFC_2_OFFSET	14
-	(struct usb_descriptor_header *) &ss_int_source_desc,
-	(struct usb_descriptor_header *) &ss_int_source_comp_desc,
-	(struct usb_descriptor_header *) &ss_int_sink_desc,
-	(struct usb_descriptor_header *) &ss_int_sink_comp_desc,
 	NULL,
 };
 
@@ -414,21 +301,6 @@
 };
 
 /*-------------------------------------------------------------------------*/
-static const char *get_ep_string(enum eptype ep_type)
-{
-	switch (ep_type) {
-	case EP_ISOC:
-		return "ISOC-";
-	case EP_INTERRUPT:
-		return "INTERRUPT-";
-	case EP_CONTROL:
-		return "CTRL-";
-	case EP_BULK:
-		return "BULK-";
-	default:
-		return "UNKNOWN-";
-	}
-}
 
 static inline struct usb_request *ss_alloc_ep_req(struct usb_ep *ep, int len)
 {
@@ -456,8 +328,7 @@
 
 void disable_endpoints(struct usb_composite_dev *cdev,
 		struct usb_ep *in, struct usb_ep *out,
-		struct usb_ep *iso_in, struct usb_ep *iso_out,
-		struct usb_ep *int_in, struct usb_ep *int_out)
+		struct usb_ep *iso_in, struct usb_ep *iso_out)
 {
 	disable_ep(cdev, in);
 	disable_ep(cdev, out);
@@ -465,10 +336,6 @@
 		disable_ep(cdev, iso_in);
 	if (iso_out)
 		disable_ep(cdev, iso_out);
-	if (int_in)
-		disable_ep(cdev, int_in);
-	if (int_out)
-		disable_ep(cdev, int_out);
 }
 
 static int
@@ -485,7 +352,6 @@
 		return id;
 	source_sink_intf_alt0.bInterfaceNumber = id;
 	source_sink_intf_alt1.bInterfaceNumber = id;
-	source_sink_intf_alt2.bInterfaceNumber = id;
 
 	/* allocate bulk endpoints */
 	ss->in_ep = usb_ep_autoconfig(cdev->gadget, &fs_source_desc);
@@ -546,55 +412,14 @@
 	if (isoc_maxpacket > 1024)
 		isoc_maxpacket = 1024;
 
-	/* sanity check the interrupt module parameters */
-	if (int_interval < 1)
-		int_interval = 1;
-	if (int_interval > 4096)
-		int_interval = 4096;
-	if (int_mult > 2)
-		int_mult = 2;
-	if (int_maxburst > 15)
-		int_maxburst = 15;
-
-	/* fill in the FS interrupt descriptors from the module parameters */
-	fs_int_source_desc.wMaxPacketSize = int_maxpacket > 64 ?
-						64 : int_maxpacket;
-	fs_int_source_desc.bInterval = int_interval > 255 ?
-						255 : int_interval;
-	fs_int_sink_desc.wMaxPacketSize = int_maxpacket > 64 ?
-						64 : int_maxpacket;
-	fs_int_sink_desc.bInterval = int_interval > 255 ?
-						255 : int_interval;
-
-	/* allocate int endpoints */
-	ss->int_in_ep = usb_ep_autoconfig(cdev->gadget, &fs_int_source_desc);
-	if (!ss->int_in_ep)
-		goto no_int;
-	ss->int_in_ep->driver_data = cdev;	/* claim */
-
-	ss->int_out_ep = usb_ep_autoconfig(cdev->gadget, &fs_int_sink_desc);
-	if (ss->int_out_ep) {
-		ss->int_out_ep->driver_data = cdev;	/* claim */
-	} else {
-		ss->int_in_ep->driver_data = NULL;
-		ss->int_in_ep = NULL;
-no_int:
-		fs_source_sink_descs[FS_ALT_IFC_2_OFFSET] = NULL;
-		hs_source_sink_descs[HS_ALT_IFC_2_OFFSET] = NULL;
-		ss_source_sink_descs[SS_ALT_IFC_2_OFFSET] = NULL;
-	}
-
-	if (int_maxpacket > 1024)
-		int_maxpacket = 1024;
-
 	/* support high speed hardware */
 	hs_source_desc.bEndpointAddress = fs_source_desc.bEndpointAddress;
 	hs_sink_desc.bEndpointAddress = fs_sink_desc.bEndpointAddress;
 
 	/*
-	 * Fill in the HS isoc and interrupt descriptors from the module
-	 * parameters. We assume that the user knows what they are doing and
-	 * won't give parameters that their UDC doesn't support.
+	 * Fill in the HS isoc descriptors from the module parameters.
+	 * We assume that the user knows what they are doing and won't
+	 * give parameters that their UDC doesn't support.
 	 */
 	hs_iso_source_desc.wMaxPacketSize = isoc_maxpacket;
 	hs_iso_source_desc.wMaxPacketSize |= isoc_mult << 11;
@@ -607,17 +432,6 @@
 	hs_iso_sink_desc.bInterval = isoc_interval;
 	hs_iso_sink_desc.bEndpointAddress = fs_iso_sink_desc.bEndpointAddress;
 
-	hs_int_source_desc.wMaxPacketSize = int_maxpacket;
-	hs_int_source_desc.wMaxPacketSize |= int_mult << 11;
-	hs_int_source_desc.bInterval = USB_MS_TO_HS_INTERVAL(int_interval);
-	hs_int_source_desc.bEndpointAddress =
-		fs_int_source_desc.bEndpointAddress;
-
-	hs_int_sink_desc.wMaxPacketSize = int_maxpacket;
-	hs_int_sink_desc.wMaxPacketSize |= int_mult << 11;
-	hs_int_sink_desc.bInterval = USB_MS_TO_HS_INTERVAL(int_interval);
-	hs_int_sink_desc.bEndpointAddress = fs_int_sink_desc.bEndpointAddress;
-
 	/* support super speed hardware */
 	ss_source_desc.bEndpointAddress =
 		fs_source_desc.bEndpointAddress;
@@ -625,9 +439,9 @@
 		fs_sink_desc.bEndpointAddress;
 
 	/*
-	 * Fill in the SS isoc and interrupt descriptors from the module
-	 * parameters. We assume that the user knows what they are doing and
-	 * won't give parameters that their UDC doesn't support.
+	 * Fill in the SS isoc descriptors from the module parameters.
+	 * We assume that the user knows what they are doing and won't
+	 * give parameters that their UDC doesn't support.
 	 */
 	ss_iso_source_desc.wMaxPacketSize = isoc_maxpacket;
 	ss_iso_source_desc.bInterval = isoc_interval;
@@ -646,37 +460,17 @@
 		isoc_maxpacket * (isoc_mult + 1) * (isoc_maxburst + 1);
 	ss_iso_sink_desc.bEndpointAddress = fs_iso_sink_desc.bEndpointAddress;
 
-	ss_int_source_desc.wMaxPacketSize = int_maxpacket;
-	ss_int_source_desc.bInterval = USB_MS_TO_SS_INTERVAL(int_interval);
-	ss_int_source_comp_desc.bmAttributes = int_mult;
-	ss_int_source_comp_desc.bMaxBurst = int_maxburst;
-	ss_int_source_comp_desc.wBytesPerInterval =
-		int_maxpacket * (int_mult + 1) * (int_maxburst + 1);
-	ss_int_source_desc.bEndpointAddress =
-		fs_int_source_desc.bEndpointAddress;
-
-	ss_int_sink_desc.wMaxPacketSize = int_maxpacket;
-	ss_int_sink_desc.bInterval = USB_MS_TO_SS_INTERVAL(int_interval);
-	ss_int_sink_comp_desc.bmAttributes = int_mult;
-	ss_int_sink_comp_desc.bMaxBurst = int_maxburst;
-	ss_int_sink_comp_desc.wBytesPerInterval =
-		int_maxpacket * (int_mult + 1) * (int_maxburst + 1);
-	ss_int_sink_desc.bEndpointAddress = fs_int_sink_desc.bEndpointAddress;
-
 	ret = usb_assign_descriptors(f, fs_source_sink_descs,
 			hs_source_sink_descs, ss_source_sink_descs);
 	if (ret)
 		return ret;
 
-	DBG(cdev, "%s speed %s: IN/%s, OUT/%s, ISO-IN/%s, ISO-OUT/%s, "
-			"INT-IN/%s, INT-OUT/%s\n",
+	DBG(cdev, "%s speed %s: IN/%s, OUT/%s, ISO-IN/%s, ISO-OUT/%s\n",
 	    (gadget_is_superspeed(c->cdev->gadget) ? "super" :
 	     (gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full")),
 			f->name, ss->in_ep->name, ss->out_ep->name,
 			ss->iso_in_ep ? ss->iso_in_ep->name : "<none>",
-			ss->iso_out_ep ? ss->iso_out_ep->name : "<none>",
-			ss->int_in_ep ? ss->int_in_ep->name : "<none>",
-			ss->int_out_ep ? ss->int_out_ep->name : "<none>");
+			ss->iso_out_ep ? ss->iso_out_ep->name : "<none>");
 	return 0;
 }
 
@@ -807,15 +601,14 @@
 }
 
 static int source_sink_start_ep(struct f_sourcesink *ss, bool is_in,
-		enum eptype ep_type, int speed)
+		bool is_iso, int speed)
 {
 	struct usb_ep		*ep;
 	struct usb_request	*req;
 	int			i, size, status;
 
 	for (i = 0; i < 8; i++) {
-		switch (ep_type) {
-		case EP_ISOC:
+		if (is_iso) {
 			switch (speed) {
 			case USB_SPEED_SUPER:
 				size = isoc_maxpacket * (isoc_mult + 1) *
@@ -831,28 +624,9 @@
 			}
 			ep = is_in ? ss->iso_in_ep : ss->iso_out_ep;
 			req = ss_alloc_ep_req(ep, size);
-			break;
-		case EP_INTERRUPT:
-			switch (speed) {
-			case USB_SPEED_SUPER:
-				size = int_maxpacket * (int_mult + 1) *
-						(int_maxburst + 1);
-				break;
-			case USB_SPEED_HIGH:
-				size = int_maxpacket * (int_mult + 1);
-				break;
-			default:
-				size = int_maxpacket > 1023 ?
-						1023 : int_maxpacket;
-				break;
-			}
-			ep = is_in ? ss->int_in_ep : ss->int_out_ep;
-			req = ss_alloc_ep_req(ep, size);
-			break;
-		default:
+		} else {
 			ep = is_in ? ss->in_ep : ss->out_ep;
 			req = ss_alloc_ep_req(ep, 0);
-			break;
 		}
 
 		if (!req)
@@ -870,12 +644,12 @@
 
 			cdev = ss->function.config->cdev;
 			ERROR(cdev, "start %s%s %s --> %d\n",
-				get_ep_string(ep_type), is_in ? "IN" : "OUT",
-				ep->name, status);
+			      is_iso ? "ISO-" : "", is_in ? "IN" : "OUT",
+			      ep->name, status);
 			free_ep_req(ep, req);
 		}
 
-		if (!(ep_type == EP_ISOC))
+		if (!is_iso)
 			break;
 	}
 
@@ -888,7 +662,7 @@
 
 	cdev = ss->function.config->cdev;
 	disable_endpoints(cdev, ss->in_ep, ss->out_ep, ss->iso_in_ep,
-			ss->iso_out_ep, ss->int_in_ep, ss->int_out_ep);
+			ss->iso_out_ep);
 	VDBG(cdev, "%s disabled\n", ss->function.name);
 }
 
@@ -900,62 +674,6 @@
 	int					speed = cdev->gadget->speed;
 	struct usb_ep				*ep;
 
-	if (alt == 2) {
-		/* Configure for periodic interrupt endpoint */
-		ep = ss->int_in_ep;
-		if (ep) {
-			result = config_ep_by_speed(cdev->gadget,
-					&(ss->function), ep);
-			if (result)
-				return result;
-
-			result = usb_ep_enable(ep);
-			if (result < 0)
-				return result;
-
-			ep->driver_data = ss;
-			result = source_sink_start_ep(ss, true, EP_INTERRUPT,
-					speed);
-			if (result < 0) {
-fail1:
-				ep = ss->int_in_ep;
-				if (ep) {
-					usb_ep_disable(ep);
-					ep->driver_data = NULL;
-				}
-				return result;
-			}
-		}
-
-		/*
-		 * one interrupt endpoint reads (sinks) anything OUT (from the
-		 * host)
-		 */
-		ep = ss->int_out_ep;
-		if (ep) {
-			result = config_ep_by_speed(cdev->gadget,
-					&(ss->function), ep);
-			if (result)
-				goto fail1;
-
-			result = usb_ep_enable(ep);
-			if (result < 0)
-				goto fail1;
-
-			ep->driver_data = ss;
-			result = source_sink_start_ep(ss, false, EP_INTERRUPT,
-					speed);
-			if (result < 0) {
-				ep = ss->int_out_ep;
-				usb_ep_disable(ep);
-				ep->driver_data = NULL;
-				goto fail1;
-			}
-		}
-
-		goto out;
-	}
-
 	/* one bulk endpoint writes (sources) zeroes IN (to the host) */
 	ep = ss->in_ep;
 	result = config_ep_by_speed(cdev->gadget, &(ss->function), ep);
@@ -966,7 +684,7 @@
 		return result;
 	ep->driver_data = ss;
 
-	result = source_sink_start_ep(ss, true, EP_BULK, speed);
+	result = source_sink_start_ep(ss, true, false, speed);
 	if (result < 0) {
 fail:
 		ep = ss->in_ep;
@@ -985,7 +703,7 @@
 		goto fail;
 	ep->driver_data = ss;
 
-	result = source_sink_start_ep(ss, false, EP_BULK, speed);
+	result = source_sink_start_ep(ss, false, false, speed);
 	if (result < 0) {
 fail2:
 		ep = ss->out_ep;
@@ -1008,7 +726,7 @@
 			goto fail2;
 		ep->driver_data = ss;
 
-		result = source_sink_start_ep(ss, true, EP_ISOC, speed);
+		result = source_sink_start_ep(ss, true, true, speed);
 		if (result < 0) {
 fail3:
 			ep = ss->iso_in_ep;
@@ -1031,14 +749,13 @@
 			goto fail3;
 		ep->driver_data = ss;
 
-		result = source_sink_start_ep(ss, false, EP_ISOC, speed);
+		result = source_sink_start_ep(ss, false, true, speed);
 		if (result < 0) {
 			usb_ep_disable(ep);
 			ep->driver_data = NULL;
 			goto fail3;
 		}
 	}
-
 out:
 	ss->cur_alt = alt;
 
@@ -1054,8 +771,6 @@
 
 	if (ss->in_ep->driver_data)
 		disable_source_sink(ss);
-	else if (alt == 2 && ss->int_in_ep->driver_data)
-		disable_source_sink(ss);
 	return enable_source_sink(cdev, ss, alt);
 }
 
@@ -1168,10 +883,6 @@
 	isoc_maxpacket = ss_opts->isoc_maxpacket;
 	isoc_mult = ss_opts->isoc_mult;
 	isoc_maxburst = ss_opts->isoc_maxburst;
-	int_interval = ss_opts->int_interval;
-	int_maxpacket = ss_opts->int_maxpacket;
-	int_mult = ss_opts->int_mult;
-	int_maxburst = ss_opts->int_maxburst;
 	buflen = ss_opts->bulk_buflen;
 
 	ss->function.name = "source/sink";
@@ -1468,182 +1179,6 @@
 			f_ss_opts_bulk_buflen_show,
 			f_ss_opts_bulk_buflen_store);
 
-static ssize_t f_ss_opts_int_interval_show(struct f_ss_opts *opts, char *page)
-{
-	int result;
-
-	mutex_lock(&opts->lock);
-	result = sprintf(page, "%u", opts->int_interval);
-	mutex_unlock(&opts->lock);
-
-	return result;
-}
-
-static ssize_t f_ss_opts_int_interval_store(struct f_ss_opts *opts,
-				       const char *page, size_t len)
-{
-	int ret;
-	u32 num;
-
-	mutex_lock(&opts->lock);
-	if (opts->refcnt) {
-		ret = -EBUSY;
-		goto end;
-	}
-
-	ret = kstrtou32(page, 0, &num);
-	if (ret)
-		goto end;
-
-	if (num > 4096) {
-		ret = -EINVAL;
-		goto end;
-	}
-
-	opts->int_interval = num;
-	ret = len;
-end:
-	mutex_unlock(&opts->lock);
-	return ret;
-}
-
-static struct f_ss_opts_attribute f_ss_opts_int_interval =
-	__CONFIGFS_ATTR(int_interval, S_IRUGO | S_IWUSR,
-			f_ss_opts_int_interval_show,
-			f_ss_opts_int_interval_store);
-
-static ssize_t f_ss_opts_int_maxpacket_show(struct f_ss_opts *opts, char *page)
-{
-	int result;
-
-	mutex_lock(&opts->lock);
-	result = sprintf(page, "%u", opts->int_maxpacket);
-	mutex_unlock(&opts->lock);
-
-	return result;
-}
-
-static ssize_t f_ss_opts_int_maxpacket_store(struct f_ss_opts *opts,
-				       const char *page, size_t len)
-{
-	int ret;
-	u16 num;
-
-	mutex_lock(&opts->lock);
-	if (opts->refcnt) {
-		ret = -EBUSY;
-		goto end;
-	}
-
-	ret = kstrtou16(page, 0, &num);
-	if (ret)
-		goto end;
-
-	if (num > 1024) {
-		ret = -EINVAL;
-		goto end;
-	}
-
-	opts->int_maxpacket = num;
-	ret = len;
-end:
-	mutex_unlock(&opts->lock);
-	return ret;
-}
-
-static struct f_ss_opts_attribute f_ss_opts_int_maxpacket =
-	__CONFIGFS_ATTR(int_maxpacket, S_IRUGO | S_IWUSR,
-			f_ss_opts_int_maxpacket_show,
-			f_ss_opts_int_maxpacket_store);
-
-static ssize_t f_ss_opts_int_mult_show(struct f_ss_opts *opts, char *page)
-{
-	int result;
-
-	mutex_lock(&opts->lock);
-	result = sprintf(page, "%u", opts->int_mult);
-	mutex_unlock(&opts->lock);
-
-	return result;
-}
-
-static ssize_t f_ss_opts_int_mult_store(struct f_ss_opts *opts,
-				       const char *page, size_t len)
-{
-	int ret;
-	u8 num;
-
-	mutex_lock(&opts->lock);
-	if (opts->refcnt) {
-		ret = -EBUSY;
-		goto end;
-	}
-
-	ret = kstrtou8(page, 0, &num);
-	if (ret)
-		goto end;
-
-	if (num > 2) {
-		ret = -EINVAL;
-		goto end;
-	}
-
-	opts->int_mult = num;
-	ret = len;
-end:
-	mutex_unlock(&opts->lock);
-	return ret;
-}
-
-static struct f_ss_opts_attribute f_ss_opts_int_mult =
-	__CONFIGFS_ATTR(int_mult, S_IRUGO | S_IWUSR,
-			f_ss_opts_int_mult_show,
-			f_ss_opts_int_mult_store);
-
-static ssize_t f_ss_opts_int_maxburst_show(struct f_ss_opts *opts, char *page)
-{
-	int result;
-
-	mutex_lock(&opts->lock);
-	result = sprintf(page, "%u", opts->int_maxburst);
-	mutex_unlock(&opts->lock);
-
-	return result;
-}
-
-static ssize_t f_ss_opts_int_maxburst_store(struct f_ss_opts *opts,
-				       const char *page, size_t len)
-{
-	int ret;
-	u8 num;
-
-	mutex_lock(&opts->lock);
-	if (opts->refcnt) {
-		ret = -EBUSY;
-		goto end;
-	}
-
-	ret = kstrtou8(page, 0, &num);
-	if (ret)
-		goto end;
-
-	if (num > 15) {
-		ret = -EINVAL;
-		goto end;
-	}
-
-	opts->int_maxburst = num;
-	ret = len;
-end:
-	mutex_unlock(&opts->lock);
-	return ret;
-}
-
-static struct f_ss_opts_attribute f_ss_opts_int_maxburst =
-	__CONFIGFS_ATTR(int_maxburst, S_IRUGO | S_IWUSR,
-			f_ss_opts_int_maxburst_show,
-			f_ss_opts_int_maxburst_store);
-
 static struct configfs_attribute *ss_attrs[] = {
 	&f_ss_opts_pattern.attr,
 	&f_ss_opts_isoc_interval.attr,
@@ -1651,10 +1186,6 @@
 	&f_ss_opts_isoc_mult.attr,
 	&f_ss_opts_isoc_maxburst.attr,
 	&f_ss_opts_bulk_buflen.attr,
-	&f_ss_opts_int_interval.attr,
-	&f_ss_opts_int_maxpacket.attr,
-	&f_ss_opts_int_mult.attr,
-	&f_ss_opts_int_maxburst.attr,
 	NULL,
 };
 
@@ -1684,8 +1215,6 @@
 	ss_opts->isoc_interval = GZERO_ISOC_INTERVAL;
 	ss_opts->isoc_maxpacket = GZERO_ISOC_MAXPACKET;
 	ss_opts->bulk_buflen = GZERO_BULK_BUFLEN;
-	ss_opts->int_interval = GZERO_INT_INTERVAL;
-	ss_opts->int_maxpacket = GZERO_INT_MAXPACKET;
 
 	config_group_init_type_name(&ss_opts->func_inst.group, "",
 				    &ss_func_type);
diff --git a/drivers/usb/gadget/function/g_zero.h b/drivers/usb/gadget/function/g_zero.h
index 2ce28b9d..15f1809 100644
--- a/drivers/usb/gadget/function/g_zero.h
+++ b/drivers/usb/gadget/function/g_zero.h
@@ -10,8 +10,6 @@
 #define GZERO_QLEN		32
 #define GZERO_ISOC_INTERVAL	4
 #define GZERO_ISOC_MAXPACKET	1024
-#define GZERO_INT_INTERVAL	1 /* Default interrupt interval = 1 ms */
-#define GZERO_INT_MAXPACKET	1024
 
 struct usb_zero_options {
 	unsigned pattern;
@@ -19,10 +17,6 @@
 	unsigned isoc_maxpacket;
 	unsigned isoc_mult;
 	unsigned isoc_maxburst;
-	unsigned int_interval; /* In ms */
-	unsigned int_maxpacket;
-	unsigned int_mult;
-	unsigned int_maxburst;
 	unsigned bulk_buflen;
 	unsigned qlen;
 };
@@ -34,10 +28,6 @@
 	unsigned isoc_maxpacket;
 	unsigned isoc_mult;
 	unsigned isoc_maxburst;
-	unsigned int_interval; /* In ms */
-	unsigned int_maxpacket;
-	unsigned int_mult;
-	unsigned int_maxburst;
 	unsigned bulk_buflen;
 
 	/*
@@ -72,7 +62,6 @@
 void free_ep_req(struct usb_ep *ep, struct usb_request *req);
 void disable_endpoints(struct usb_composite_dev *cdev,
 		struct usb_ep *in, struct usb_ep *out,
-		struct usb_ep *iso_in, struct usb_ep *iso_out,
-		struct usb_ep *int_in, struct usb_ep *int_out);
+		struct usb_ep *iso_in, struct usb_ep *iso_out);
 
 #endif /* __G_ZERO_H */
diff --git a/drivers/usb/gadget/legacy/tcm_usb_gadget.c b/drivers/usb/gadget/legacy/tcm_usb_gadget.c
index 3a49416..6e0a019 100644
--- a/drivers/usb/gadget/legacy/tcm_usb_gadget.c
+++ b/drivers/usb/gadget/legacy/tcm_usb_gadget.c
@@ -1740,10 +1740,9 @@
 		goto err_session;
 	}
 	/*
-	 * Now register the TCM vHost virtual I_T Nexus as active with the
-	 * call to __transport_register_session()
+	 * Now register the TCM vHost virtual I_T Nexus as active.
 	 */
-	__transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl,
+	transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl,
 			tv_nexus->tvn_se_sess, tv_nexus);
 	tpg->tpg_nexus = tv_nexus;
 	mutex_unlock(&tpg->tpg_mutex);
diff --git a/drivers/usb/gadget/legacy/zero.c b/drivers/usb/gadget/legacy/zero.c
index ff97ac93..5ee9515 100644
--- a/drivers/usb/gadget/legacy/zero.c
+++ b/drivers/usb/gadget/legacy/zero.c
@@ -68,8 +68,6 @@
 	.isoc_maxpacket = GZERO_ISOC_MAXPACKET,
 	.bulk_buflen = GZERO_BULK_BUFLEN,
 	.qlen = GZERO_QLEN,
-	.int_interval = GZERO_INT_INTERVAL,
-	.int_maxpacket = GZERO_INT_MAXPACKET,
 };
 
 /*-------------------------------------------------------------------------*/
@@ -268,21 +266,6 @@
 		S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(isoc_maxburst, "0 - 15 (ss only)");
 
-module_param_named(int_interval, gzero_options.int_interval, uint,
-		S_IRUGO|S_IWUSR);
-MODULE_PARM_DESC(int_interval, "1 - 16");
-
-module_param_named(int_maxpacket, gzero_options.int_maxpacket, uint,
-		S_IRUGO|S_IWUSR);
-MODULE_PARM_DESC(int_maxpacket, "0 - 1023 (fs), 0 - 1024 (hs/ss)");
-
-module_param_named(int_mult, gzero_options.int_mult, uint, S_IRUGO|S_IWUSR);
-MODULE_PARM_DESC(int_mult, "0 - 2 (hs/ss only)");
-
-module_param_named(int_maxburst, gzero_options.int_maxburst, uint,
-		S_IRUGO|S_IWUSR);
-MODULE_PARM_DESC(int_maxburst, "0 - 15 (ss only)");
-
 static struct usb_function *func_lb;
 static struct usb_function_instance *func_inst_lb;
 
@@ -318,10 +301,6 @@
 	ss_opts->isoc_maxpacket = gzero_options.isoc_maxpacket;
 	ss_opts->isoc_mult = gzero_options.isoc_mult;
 	ss_opts->isoc_maxburst = gzero_options.isoc_maxburst;
-	ss_opts->int_interval = gzero_options.int_interval;
-	ss_opts->int_maxpacket = gzero_options.int_maxpacket;
-	ss_opts->int_mult = gzero_options.int_mult;
-	ss_opts->int_maxburst = gzero_options.int_maxburst;
 	ss_opts->bulk_buflen = gzero_options.bulk_buflen;
 
 	func_ss = usb_get_function(func_inst_ss);
diff --git a/drivers/usb/host/ehci-atmel.c b/drivers/usb/host/ehci-atmel.c
index 663f790..be0964a 100644
--- a/drivers/usb/host/ehci-atmel.c
+++ b/drivers/usb/host/ehci-atmel.c
@@ -34,7 +34,6 @@
 
 struct atmel_ehci_priv {
 	struct clk *iclk;
-	struct clk *fclk;
 	struct clk *uclk;
 	bool clocked;
 };
@@ -51,12 +50,9 @@
 {
 	if (atmel_ehci->clocked)
 		return;
-	if (IS_ENABLED(CONFIG_COMMON_CLK)) {
-		clk_set_rate(atmel_ehci->uclk, 48000000);
-		clk_prepare_enable(atmel_ehci->uclk);
-	}
+
+	clk_prepare_enable(atmel_ehci->uclk);
 	clk_prepare_enable(atmel_ehci->iclk);
-	clk_prepare_enable(atmel_ehci->fclk);
 	atmel_ehci->clocked = true;
 }
 
@@ -64,10 +60,9 @@
 {
 	if (!atmel_ehci->clocked)
 		return;
-	clk_disable_unprepare(atmel_ehci->fclk);
+
 	clk_disable_unprepare(atmel_ehci->iclk);
-	if (IS_ENABLED(CONFIG_COMMON_CLK))
-		clk_disable_unprepare(atmel_ehci->uclk);
+	clk_disable_unprepare(atmel_ehci->uclk);
 	atmel_ehci->clocked = false;
 }
 
@@ -146,20 +141,13 @@
 		retval = -ENOENT;
 		goto fail_request_resource;
 	}
-	atmel_ehci->fclk = devm_clk_get(&pdev->dev, "uhpck");
-	if (IS_ERR(atmel_ehci->fclk)) {
-		dev_err(&pdev->dev, "Error getting function clock\n");
-		retval = -ENOENT;
+
+	atmel_ehci->uclk = devm_clk_get(&pdev->dev, "usb_clk");
+	if (IS_ERR(atmel_ehci->uclk)) {
+		dev_err(&pdev->dev, "failed to get uclk\n");
+		retval = PTR_ERR(atmel_ehci->uclk);
 		goto fail_request_resource;
 	}
-	if (IS_ENABLED(CONFIG_COMMON_CLK)) {
-		atmel_ehci->uclk = devm_clk_get(&pdev->dev, "usb_clk");
-		if (IS_ERR(atmel_ehci->uclk)) {
-			dev_err(&pdev->dev, "failed to get uclk\n");
-			retval = PTR_ERR(atmel_ehci->uclk);
-			goto fail_request_resource;
-		}
-	}
 
 	ehci = hcd_to_ehci(hcd);
 	/* registers start at offset 0x0 */
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 5fb66db..73485fa 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1729,7 +1729,7 @@
 	if (!command)
 		return;
 
-	ep->ep_state |= EP_HALTED | EP_RECENTLY_HALTED;
+	ep->ep_state |= EP_HALTED;
 	ep->stopped_stream = stream_id;
 
 	xhci_queue_reset_ep(xhci, command, slot_id, ep_index);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index b06d1a5..ec8ac16 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1338,12 +1338,6 @@
 		goto exit;
 	}
 
-	/* Reject urb if endpoint is in soft reset, queue must stay empty */
-	if (xhci->devs[slot_id]->eps[ep_index].ep_state & EP_CONFIG_PENDING) {
-		xhci_warn(xhci, "Can't enqueue URB while ep is in soft reset\n");
-		ret = -EINVAL;
-	}
-
 	if (usb_endpoint_xfer_isoc(&urb->ep->desc))
 		size = urb->number_of_packets;
 	else
@@ -2954,36 +2948,23 @@
 	}
 }
 
-/* Called after clearing a halted device. USB core should have sent the control
+/* Called when clearing halted device. The core should have sent the control
  * message to clear the device halt condition. The host side of the halt should
- * already be cleared with a reset endpoint command issued immediately when the
- * STALL tx event was received.
+ * already be cleared with a reset endpoint command issued when the STALL tx
+ * event was received.
+ *
+ * Context: in_interrupt
  */
 
 void xhci_endpoint_reset(struct usb_hcd *hcd,
 		struct usb_host_endpoint *ep)
 {
 	struct xhci_hcd *xhci;
-	struct usb_device *udev;
-	struct xhci_virt_device *virt_dev;
-	struct xhci_virt_ep *virt_ep;
-	struct xhci_input_control_ctx *ctrl_ctx;
-	struct xhci_command *command;
-	unsigned int ep_index, ep_state;
-	unsigned long flags;
-	u32 ep_flag;
 
 	xhci = hcd_to_xhci(hcd);
-	udev = (struct usb_device *) ep->hcpriv;
-	if (!ep->hcpriv)
-		return;
-	virt_dev = xhci->devs[udev->slot_id];
-	ep_index = xhci_get_endpoint_index(&ep->desc);
-	virt_ep = &virt_dev->eps[ep_index];
-	ep_state = virt_ep->ep_state;
 
 	/*
-	 * Implement the config ep command in xhci 4.6.8 additional note:
+	 * We might need to implement the config ep cmd in xhci 4.8.1 note:
 	 * The Reset Endpoint Command may only be issued to endpoints in the
 	 * Halted state. If software wishes reset the Data Toggle or Sequence
 	 * Number of an endpoint that isn't in the Halted state, then software
@@ -2991,72 +2972,9 @@
 	 * for the target endpoint. that is in the Stopped state.
 	 */
 
-	if (ep_state & SET_DEQ_PENDING || ep_state & EP_RECENTLY_HALTED) {
-		virt_ep->ep_state &= ~EP_RECENTLY_HALTED;
-		xhci_dbg(xhci, "ep recently halted, no toggle reset needed\n");
-		return;
-	}
-
-	/* Only interrupt and bulk ep's use Data toggle, USB2 spec 5.5.4-> */
-	if (usb_endpoint_xfer_control(&ep->desc) ||
-	    usb_endpoint_xfer_isoc(&ep->desc))
-		return;
-
-	ep_flag = xhci_get_endpoint_flag(&ep->desc);
-
-	if (ep_flag == SLOT_FLAG || ep_flag == EP0_FLAG)
-		return;
-
-	command = xhci_alloc_command(xhci, true, true, GFP_NOWAIT);
-	if (!command) {
-		xhci_err(xhci, "Could not allocate xHCI command structure.\n");
-		return;
-	}
-
-	spin_lock_irqsave(&xhci->lock, flags);
-
-	/* block ringing ep doorbell */
-	virt_ep->ep_state |= EP_CONFIG_PENDING;
-
-	/*
-	 * Make sure endpoint ring is empty before resetting the toggle/seq.
-	 * Driver is required to synchronously cancel all transfer request.
-	 *
-	 * xhci 4.6.6 says we can issue a configure endpoint command on a
-	 * running endpoint ring as long as it's idle (queue empty)
-	 */
-
-	if (!list_empty(&virt_ep->ring->td_list)) {
-		dev_err(&udev->dev, "EP not empty, refuse reset\n");
-		spin_unlock_irqrestore(&xhci->lock, flags);
-		goto cleanup;
-	}
-
-	xhci_dbg(xhci, "Reset toggle/seq for slot %d, ep_index: %d\n",
-		 udev->slot_id, ep_index);
-
-	ctrl_ctx = xhci_get_input_control_ctx(command->in_ctx);
-	if (!ctrl_ctx) {
-		xhci_err(xhci, "Could not get input context, bad type. virt_dev: %p, in_ctx %p\n",
-			 virt_dev, virt_dev->in_ctx);
-		spin_unlock_irqrestore(&xhci->lock, flags);
-		goto cleanup;
-	}
-	xhci_setup_input_ctx_for_config_ep(xhci, command->in_ctx,
-					   virt_dev->out_ctx, ctrl_ctx,
-					   ep_flag, ep_flag);
-	xhci_endpoint_copy(xhci, command->in_ctx, virt_dev->out_ctx, ep_index);
-
-	xhci_queue_configure_endpoint(xhci, command, command->in_ctx->dma,
-				     udev->slot_id, false);
-	xhci_ring_cmd_db(xhci);
-	spin_unlock_irqrestore(&xhci->lock, flags);
-
-	wait_for_completion(command->completion);
-
-cleanup:
-	virt_ep->ep_state &= ~EP_CONFIG_PENDING;
-	xhci_free_command(xhci, command);
+	/* For now just print debug to follow the situation */
+	xhci_dbg(xhci, "Endpoint 0x%x ep reset callback called\n",
+		 ep->desc.bEndpointAddress);
 }
 
 static int xhci_check_streams_endpoint(struct xhci_hcd *xhci,
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 265ab17..8e421b8 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -865,8 +865,6 @@
 #define EP_HAS_STREAMS		(1 << 4)
 /* Transitioning the endpoint to not using streams, don't enqueue URBs */
 #define EP_GETTING_NO_STREAMS	(1 << 5)
-#define EP_RECENTLY_HALTED	(1 << 6)
-#define EP_CONFIG_PENDING	(1 << 7)
 	/* ----  Related to URB cancellation ---- */
 	struct list_head	cancelled_td_list;
 	struct xhci_td		*stopped_td;
diff --git a/drivers/usb/isp1760/isp1760-core.c b/drivers/usb/isp1760/isp1760-core.c
index b982755..bfa402c 100644
--- a/drivers/usb/isp1760/isp1760-core.c
+++ b/drivers/usb/isp1760/isp1760-core.c
@@ -151,8 +151,7 @@
 	}
 
 	if (IS_ENABLED(CONFIG_USB_ISP1761_UDC) && !udc_disabled) {
-		ret = isp1760_udc_register(isp, irq, irqflags | IRQF_SHARED |
-					   IRQF_DISABLED);
+		ret = isp1760_udc_register(isp, irq, irqflags);
 		if (ret < 0) {
 			isp1760_hcd_unregister(&isp->hcd);
 			return ret;
diff --git a/drivers/usb/isp1760/isp1760-udc.c b/drivers/usb/isp1760/isp1760-udc.c
index 9612d79..f32c292 100644
--- a/drivers/usb/isp1760/isp1760-udc.c
+++ b/drivers/usb/isp1760/isp1760-udc.c
@@ -1191,6 +1191,7 @@
 			     struct usb_gadget_driver *driver)
 {
 	struct isp1760_udc *udc = gadget_to_udc(gadget);
+	unsigned long flags;
 
 	/* The hardware doesn't support low speed. */
 	if (driver->max_speed < USB_SPEED_FULL) {
@@ -1198,7 +1199,7 @@
 		return -EINVAL;
 	}
 
-	spin_lock(&udc->lock);
+	spin_lock_irqsave(&udc->lock, flags);
 
 	if (udc->driver) {
 		dev_err(udc->isp->dev, "UDC already has a gadget driver\n");
@@ -1208,7 +1209,7 @@
 
 	udc->driver = driver;
 
-	spin_unlock(&udc->lock);
+	spin_unlock_irqrestore(&udc->lock, flags);
 
 	dev_dbg(udc->isp->dev, "starting UDC with driver %s\n",
 		driver->function);
@@ -1232,6 +1233,7 @@
 static int isp1760_udc_stop(struct usb_gadget *gadget)
 {
 	struct isp1760_udc *udc = gadget_to_udc(gadget);
+	unsigned long flags;
 
 	dev_dbg(udc->isp->dev, "%s\n", __func__);
 
@@ -1239,9 +1241,9 @@
 
 	isp1760_udc_write(udc, DC_MODE, 0);
 
-	spin_lock(&udc->lock);
+	spin_lock_irqsave(&udc->lock, flags);
 	udc->driver = NULL;
-	spin_unlock(&udc->lock);
+	spin_unlock_irqrestore(&udc->lock, flags);
 
 	return 0;
 }
@@ -1411,7 +1413,7 @@
 		return -ENODEV;
 	}
 
-	if (chipid != 0x00011582) {
+	if (chipid != 0x00011582 && chipid != 0x00158210) {
 		dev_err(udc->isp->dev, "udc: invalid chip ID 0x%08x\n", chipid);
 		return -ENODEV;
 	}
@@ -1451,8 +1453,8 @@
 
 	sprintf(udc->irqname, "%s (udc)", devname);
 
-	ret = request_irq(irq, isp1760_udc_irq, IRQF_SHARED | IRQF_DISABLED |
-			  irqflags, udc->irqname, udc);
+	ret = request_irq(irq, isp1760_udc_irq, IRQF_SHARED | irqflags,
+			  udc->irqname, udc);
 	if (ret < 0)
 		goto error;
 
diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig
index 14e1628..39db8b6 100644
--- a/drivers/usb/musb/Kconfig
+++ b/drivers/usb/musb/Kconfig
@@ -79,7 +79,8 @@
 
 config USB_MUSB_OMAP2PLUS
 	tristate "OMAP2430 and onwards"
-	depends on ARCH_OMAP2PLUS && USB && OMAP_CONTROL_PHY
+	depends on ARCH_OMAP2PLUS && USB
+	depends on OMAP_CONTROL_PHY || !OMAP_CONTROL_PHY
 	select GENERIC_PHY
 
 config USB_MUSB_AM35X
diff --git a/drivers/usb/phy/phy-am335x-control.c b/drivers/usb/phy/phy-am335x-control.c
index 403fab7..7b3035f 100644
--- a/drivers/usb/phy/phy-am335x-control.c
+++ b/drivers/usb/phy/phy-am335x-control.c
@@ -126,6 +126,9 @@
 		return NULL;
 
 	dev = bus_find_device(&platform_bus_type, NULL, node, match);
+	if (!dev)
+		return NULL;
+
 	ctrl_usb = dev_get_drvdata(dev);
 	if (!ctrl_usb)
 		return NULL;
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 8257042..c85ea53 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -113,6 +113,13 @@
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_ATA_1X),
 
+/* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */
+UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999,
+		"Initio Corporation",
+		"",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
 /* Reported-by: Tom Arild Naess <tanaess@gmail.com> */
 UNUSUAL_DEV(0x152d, 0x0539, 0x0000, 0x9999,
 		"JMicron",
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 8d4f3f1..71df240 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1956,10 +1956,9 @@
 		goto out;
 	}
 	/*
-	 * Now register the TCM vhost virtual I_T Nexus as active with the
-	 * call to __transport_register_session()
+	 * Now register the TCM vhost virtual I_T Nexus as active.
 	 */
-	__transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl,
+	transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl,
 			tv_nexus->tvn_se_sess, tv_nexus);
 	tpg->tpg_nexus = tv_nexus;
 
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 0413157..6a356e3 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/balloon_compaction.h>
 #include <linux/oom.h>
+#include <linux/wait.h>
 
 /*
  * Balloon device works in 4K page units.  So each page is pointed to by
@@ -334,17 +335,25 @@
 static int balloon(void *_vballoon)
 {
 	struct virtio_balloon *vb = _vballoon;
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	set_freezable();
 	while (!kthread_should_stop()) {
 		s64 diff;
 
 		try_to_freeze();
-		wait_event_interruptible(vb->config_change,
-					 (diff = towards_target(vb)) != 0
-					 || vb->need_stats_update
-					 || kthread_should_stop()
-					 || freezing(current));
+
+		add_wait_queue(&vb->config_change, &wait);
+		for (;;) {
+			if ((diff = towards_target(vb)) != 0 ||
+			    vb->need_stats_update ||
+			    kthread_should_stop() ||
+			    freezing(current))
+				break;
+			wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+		}
+		remove_wait_queue(&vb->config_change, &wait);
+
 		if (vb->need_stats_update)
 			stats_handle_request(vb);
 		if (diff > 0)
@@ -499,6 +508,8 @@
 	if (err < 0)
 		goto out_oom_notify;
 
+	virtio_device_ready(vdev);
+
 	vb->thread = kthread_run(balloon, vb, "vballoon");
 	if (IS_ERR(vb->thread)) {
 		err = PTR_ERR(vb->thread);
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index cad5698..6010d7e 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -156,22 +156,95 @@
 		   void *buf, unsigned len)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
-	u8 *ptr = buf;
-	int i;
+	void __iomem *base = vm_dev->base + VIRTIO_MMIO_CONFIG;
+	u8 b;
+	__le16 w;
+	__le32 l;
 
-	for (i = 0; i < len; i++)
-		ptr[i] = readb(vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+	if (vm_dev->version == 1) {
+		u8 *ptr = buf;
+		int i;
+
+		for (i = 0; i < len; i++)
+			ptr[i] = readb(base + offset + i);
+		return;
+	}
+
+	switch (len) {
+	case 1:
+		b = readb(base + offset);
+		memcpy(buf, &b, sizeof b);
+		break;
+	case 2:
+		w = cpu_to_le16(readw(base + offset));
+		memcpy(buf, &w, sizeof w);
+		break;
+	case 4:
+		l = cpu_to_le32(readl(base + offset));
+		memcpy(buf, &l, sizeof l);
+		break;
+	case 8:
+		l = cpu_to_le32(readl(base + offset));
+		memcpy(buf, &l, sizeof l);
+		l = cpu_to_le32(ioread32(base + offset + sizeof l));
+		memcpy(buf + sizeof l, &l, sizeof l);
+		break;
+	default:
+		BUG();
+	}
 }
 
 static void vm_set(struct virtio_device *vdev, unsigned offset,
 		   const void *buf, unsigned len)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
-	const u8 *ptr = buf;
-	int i;
+	void __iomem *base = vm_dev->base + VIRTIO_MMIO_CONFIG;
+	u8 b;
+	__le16 w;
+	__le32 l;
 
-	for (i = 0; i < len; i++)
-		writeb(ptr[i], vm_dev->base + VIRTIO_MMIO_CONFIG + offset + i);
+	if (vm_dev->version == 1) {
+		const u8 *ptr = buf;
+		int i;
+
+		for (i = 0; i < len; i++)
+			writeb(ptr[i], base + offset + i);
+
+		return;
+	}
+
+	switch (len) {
+	case 1:
+		memcpy(&b, buf, sizeof b);
+		writeb(b, base + offset);
+		break;
+	case 2:
+		memcpy(&w, buf, sizeof w);
+		writew(le16_to_cpu(w), base + offset);
+		break;
+	case 4:
+		memcpy(&l, buf, sizeof l);
+		writel(le32_to_cpu(l), base + offset);
+		break;
+	case 8:
+		memcpy(&l, buf, sizeof l);
+		writel(le32_to_cpu(l), base + offset);
+		memcpy(&l, buf + sizeof l, sizeof l);
+		writel(le32_to_cpu(l), base + offset + sizeof l);
+		break;
+	default:
+		BUG();
+	}
+}
+
+static u32 vm_generation(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+
+	if (vm_dev->version == 1)
+		return 0;
+	else
+		return readl(vm_dev->base + VIRTIO_MMIO_CONFIG_GENERATION);
 }
 
 static u8 vm_get_status(struct virtio_device *vdev)
@@ -440,6 +513,7 @@
 static const struct virtio_config_ops virtio_mmio_config_ops = {
 	.get		= vm_get,
 	.set		= vm_set,
+	.generation	= vm_generation,
 	.get_status	= vm_get_status,
 	.set_status	= vm_set_status,
 	.reset		= vm_reset,
diff --git a/drivers/watchdog/imgpdc_wdt.c b/drivers/watchdog/imgpdc_wdt.c
index c8def68..0deaa4f 100644
--- a/drivers/watchdog/imgpdc_wdt.c
+++ b/drivers/watchdog/imgpdc_wdt.c
@@ -42,10 +42,10 @@
 #define PDC_WDT_MIN_TIMEOUT		1
 #define PDC_WDT_DEF_TIMEOUT		64
 
-static int heartbeat;
+static int heartbeat = PDC_WDT_DEF_TIMEOUT;
 module_param(heartbeat, int, 0);
-MODULE_PARM_DESC(heartbeat, "Watchdog heartbeats in seconds. "
-	"(default = " __MODULE_STRING(PDC_WDT_DEF_TIMEOUT) ")");
+MODULE_PARM_DESC(heartbeat, "Watchdog heartbeats in seconds "
+	"(default=" __MODULE_STRING(PDC_WDT_DEF_TIMEOUT) ")");
 
 static bool nowayout = WATCHDOG_NOWAYOUT;
 module_param(nowayout, bool, 0);
@@ -191,6 +191,7 @@
 	pdc_wdt->wdt_dev.ops = &pdc_wdt_ops;
 	pdc_wdt->wdt_dev.max_timeout = 1 << PDC_WDT_CONFIG_DELAY_MASK;
 	pdc_wdt->wdt_dev.parent = &pdev->dev;
+	watchdog_set_drvdata(&pdc_wdt->wdt_dev, pdc_wdt);
 
 	ret = watchdog_init_timeout(&pdc_wdt->wdt_dev, heartbeat, &pdev->dev);
 	if (ret < 0) {
@@ -232,7 +233,6 @@
 	watchdog_set_nowayout(&pdc_wdt->wdt_dev, nowayout);
 
 	platform_set_drvdata(pdev, pdc_wdt);
-	watchdog_set_drvdata(&pdc_wdt->wdt_dev, pdc_wdt);
 
 	ret = watchdog_register_device(&pdc_wdt->wdt_dev);
 	if (ret)
diff --git a/drivers/watchdog/mtk_wdt.c b/drivers/watchdog/mtk_wdt.c
index a87f6df..938b987 100644
--- a/drivers/watchdog/mtk_wdt.c
+++ b/drivers/watchdog/mtk_wdt.c
@@ -133,7 +133,7 @@
 	u32 reg;
 	struct mtk_wdt_dev *mtk_wdt = watchdog_get_drvdata(wdt_dev);
 	void __iomem *wdt_base = mtk_wdt->wdt_base;
-	u32 ret;
+	int ret;
 
 	ret = mtk_wdt_set_timeout(wdt_dev, wdt_dev->timeout);
 	if (ret < 0)
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 9faca6a..42bd55a 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -1659,11 +1659,8 @@
 			 name);
 		goto out;
 	}
-	/*
-	 * Now register the TCM pvscsi virtual I_T Nexus as active with the
-	 * call to __transport_register_session()
-	 */
-	__transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl,
+	/* Now register the TCM pvscsi virtual I_T Nexus as active. */
+	transport_register_session(se_tpg, tv_nexus->tvn_se_sess->se_node_acl,
 			tv_nexus->tvn_se_sess, tv_nexus);
 	tpg->tpg_nexus = tv_nexus;
 
diff --git a/fs/affs/file.c b/fs/affs/file.c
index d2468bf..a91795e 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -699,8 +699,10 @@
 	boff = tmp % bsize;
 	if (boff) {
 		bh = affs_bread_ino(inode, bidx, 0);
-		if (IS_ERR(bh))
-			return PTR_ERR(bh);
+		if (IS_ERR(bh)) {
+			written = PTR_ERR(bh);
+			goto err_first_bh;
+		}
 		tmp = min(bsize - boff, to - from);
 		BUG_ON(boff + tmp > bsize || tmp > bsize);
 		memcpy(AFFS_DATA(bh) + boff, data + from, tmp);
@@ -712,14 +714,16 @@
 		bidx++;
 	} else if (bidx) {
 		bh = affs_bread_ino(inode, bidx - 1, 0);
-		if (IS_ERR(bh))
-			return PTR_ERR(bh);
+		if (IS_ERR(bh)) {
+			written = PTR_ERR(bh);
+			goto err_first_bh;
+		}
 	}
 	while (from + bsize <= to) {
 		prev_bh = bh;
 		bh = affs_getemptyblk_ino(inode, bidx);
 		if (IS_ERR(bh))
-			goto out;
+			goto err_bh;
 		memcpy(AFFS_DATA(bh), data + from, bsize);
 		if (buffer_new(bh)) {
 			AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
@@ -751,7 +755,7 @@
 		prev_bh = bh;
 		bh = affs_bread_ino(inode, bidx, 1);
 		if (IS_ERR(bh))
-			goto out;
+			goto err_bh;
 		tmp = min(bsize, to - from);
 		BUG_ON(tmp > bsize);
 		memcpy(AFFS_DATA(bh), data + from, tmp);
@@ -790,12 +794,13 @@
 	if (tmp > inode->i_size)
 		inode->i_size = AFFS_I(inode)->mmu_private = tmp;
 
+err_first_bh:
 	unlock_page(page);
 	page_cache_release(page);
 
 	return written;
 
-out:
+err_bh:
 	bh = prev_bh;
 	if (!written)
 		written = PTR_ERR(bh);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 84c3b00..f9c89ca 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3387,6 +3387,8 @@
 
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 				    struct btrfs_root *root);
+int btrfs_setup_space_cache(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root);
 int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr);
 int btrfs_free_block_groups(struct btrfs_fs_info *info);
 int btrfs_read_block_groups(struct btrfs_root *root);
@@ -3909,6 +3911,9 @@
 				    loff_t actual_len, u64 *alloc_hint);
 int btrfs_inode_check_errors(struct inode *inode);
 extern const struct dentry_operations btrfs_dentry_operations;
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+void btrfs_test_inode_set_ops(struct inode *inode);
+#endif
 
 /* ioctl.c */
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f79f385..639f266 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3921,7 +3921,7 @@
 	}
 	if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
 			+ sizeof(struct btrfs_chunk)) {
-		printk(KERN_ERR "BTRFS: system chunk array too small %u < %lu\n",
+		printk(KERN_ERR "BTRFS: system chunk array too small %u < %zu\n",
 				btrfs_super_sys_array_size(sb),
 				sizeof(struct btrfs_disk_key)
 				+ sizeof(struct btrfs_chunk));
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 6f08045..8b353ad 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3325,6 +3325,32 @@
 	return ret;
 }
 
+int btrfs_setup_space_cache(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root)
+{
+	struct btrfs_block_group_cache *cache, *tmp;
+	struct btrfs_transaction *cur_trans = trans->transaction;
+	struct btrfs_path *path;
+
+	if (list_empty(&cur_trans->dirty_bgs) ||
+	    !btrfs_test_opt(root, SPACE_CACHE))
+		return 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	/* Could add new block groups, use _safe just in case */
+	list_for_each_entry_safe(cache, tmp, &cur_trans->dirty_bgs,
+				 dirty_list) {
+		if (cache->disk_cache_state == BTRFS_DC_CLEAR)
+			cache_save_setup(cache, trans, path);
+	}
+
+	btrfs_free_path(path);
+	return 0;
+}
+
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root)
 {
@@ -5110,7 +5136,11 @@
 	num_bytes = ALIGN(num_bytes, root->sectorsize);
 
 	spin_lock(&BTRFS_I(inode)->lock);
-	BTRFS_I(inode)->outstanding_extents++;
+	nr_extents = (unsigned)div64_u64(num_bytes +
+					 BTRFS_MAX_EXTENT_SIZE - 1,
+					 BTRFS_MAX_EXTENT_SIZE);
+	BTRFS_I(inode)->outstanding_extents += nr_extents;
+	nr_extents = 0;
 
 	if (BTRFS_I(inode)->outstanding_extents >
 	    BTRFS_I(inode)->reserved_extents)
@@ -5255,6 +5285,9 @@
 	if (dropped > 0)
 		to_free += btrfs_calc_trans_metadata_size(root, dropped);
 
+	if (btrfs_test_is_dummy_root(root))
+		return;
+
 	trace_btrfs_space_reservation(root->fs_info, "delalloc",
 				      btrfs_ino(inode), to_free, 0);
 	if (root->fs_info->quota_enabled) {
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c7233ff..d688cfe 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4968,6 +4968,12 @@
 
 		/* Should be safe to release our pages at this point */
 		btrfs_release_extent_buffer_page(eb);
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+		if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))) {
+			__free_extent_buffer(eb);
+			return 1;
+		}
+#endif
 		call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
 		return 1;
 	}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index da828cf..d2e732d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -108,6 +108,13 @@
 
 static int btrfs_dirty_inode(struct inode *inode);
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+void btrfs_test_inode_set_ops(struct inode *inode)
+{
+	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+}
+#endif
+
 static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
 				     struct inode *inode,  struct inode *dir,
 				     const struct qstr *qstr)
@@ -1542,30 +1549,17 @@
 		u64 new_size;
 
 		/*
-		 * We need the largest size of the remaining extent to see if we
-		 * need to add a new outstanding extent.  Think of the following
-		 * case
-		 *
-		 * [MEAX_EXTENT_SIZEx2 - 4k][4k]
-		 *
-		 * The new_size would just be 4k and we'd think we had enough
-		 * outstanding extents for this if we only took one side of the
-		 * split, same goes for the other direction.  We need to see if
-		 * the larger size still is the same amount of extents as the
-		 * original size, because if it is we need to add a new
-		 * outstanding extent.  But if we split up and the larger size
-		 * is less than the original then we are good to go since we've
-		 * already accounted for the extra extent in our original
-		 * accounting.
+		 * See the explanation in btrfs_merge_extent_hook, the same
+		 * applies here, just in reverse.
 		 */
 		new_size = orig->end - split + 1;
-		if ((split - orig->start) > new_size)
-			new_size = split - orig->start;
-
-		num_extents = div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+		num_extents = div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
 					BTRFS_MAX_EXTENT_SIZE);
-		if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
-			      BTRFS_MAX_EXTENT_SIZE) < num_extents)
+		new_size = split - orig->start;
+		num_extents += div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
+					BTRFS_MAX_EXTENT_SIZE);
+		if (div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+			      BTRFS_MAX_EXTENT_SIZE) >= num_extents)
 			return;
 	}
 
@@ -1591,8 +1585,10 @@
 	if (!(other->state & EXTENT_DELALLOC))
 		return;
 
-	old_size = other->end - other->start + 1;
-	new_size = old_size + (new->end - new->start + 1);
+	if (new->start > other->start)
+		new_size = new->end - other->start + 1;
+	else
+		new_size = other->end - new->start + 1;
 
 	/* we're not bigger than the max, unreserve the space and go */
 	if (new_size <= BTRFS_MAX_EXTENT_SIZE) {
@@ -1603,13 +1599,32 @@
 	}
 
 	/*
-	 * If we grew by another max_extent, just return, we want to keep that
-	 * reserved amount.
+	 * We have to add up either side to figure out how many extents were
+	 * accounted for before we merged into one big extent.  If the number of
+	 * extents we accounted for is <= the amount we need for the new range
+	 * then we can return, otherwise drop.  Think of it like this
+	 *
+	 * [ 4k][MAX_SIZE]
+	 *
+	 * So we've grown the extent by a MAX_SIZE extent, this would mean we
+	 * need 2 outstanding extents, on one side we have 1 and the other side
+	 * we have 1 so they are == and we can return.  But in this case
+	 *
+	 * [MAX_SIZE+4k][MAX_SIZE+4k]
+	 *
+	 * Each range on their own accounts for 2 extents, but merged together
+	 * they are only 3 extents worth of accounting, so we need to drop in
+	 * this case.
 	 */
+	old_size = other->end - other->start + 1;
 	num_extents = div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
 				BTRFS_MAX_EXTENT_SIZE);
+	old_size = new->end - new->start + 1;
+	num_extents += div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
+				 BTRFS_MAX_EXTENT_SIZE);
+
 	if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
-		      BTRFS_MAX_EXTENT_SIZE) > num_extents)
+		      BTRFS_MAX_EXTENT_SIZE) >= num_extents)
 		return;
 
 	spin_lock(&BTRFS_I(inode)->lock);
@@ -1686,6 +1701,10 @@
 			spin_unlock(&BTRFS_I(inode)->lock);
 		}
 
+		/* For sanity tests */
+		if (btrfs_test_is_dummy_root(root))
+			return;
+
 		__percpu_counter_add(&root->fs_info->delalloc_bytes, len,
 				     root->fs_info->delalloc_batch);
 		spin_lock(&BTRFS_I(inode)->lock);
@@ -1741,6 +1760,10 @@
 		    root != root->fs_info->tree_root)
 			btrfs_delalloc_release_metadata(inode, len);
 
+		/* For sanity tests. */
+		if (btrfs_test_is_dummy_root(root))
+			return;
+
 		if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
 		    && do_list && !(state->state & EXTENT_NORESERVE))
 			btrfs_free_reserved_data_space(inode, len);
@@ -7213,7 +7236,7 @@
 	u64 start = iblock << inode->i_blkbits;
 	u64 lockstart, lockend;
 	u64 len = bh_result->b_size;
-	u64 orig_len = len;
+	u64 *outstanding_extents = NULL;
 	int unlock_bits = EXTENT_LOCKED;
 	int ret = 0;
 
@@ -7225,6 +7248,16 @@
 	lockstart = start;
 	lockend = start + len - 1;
 
+	if (current->journal_info) {
+		/*
+		 * Need to pull our outstanding extents and set journal_info to NULL so
+		 * that anything that needs to check if there's a transction doesn't get
+		 * confused.
+		 */
+		outstanding_extents = current->journal_info;
+		current->journal_info = NULL;
+	}
+
 	/*
 	 * If this errors out it's because we couldn't invalidate pagecache for
 	 * this range and we need to fallback to buffered.
@@ -7348,11 +7381,20 @@
 		if (start + len > i_size_read(inode))
 			i_size_write(inode, start + len);
 
-		if (len < orig_len) {
+		/*
+		 * If we have an outstanding_extents count still set then we're
+		 * within our reservation, otherwise we need to adjust our inode
+		 * counter appropriately.
+		 */
+		if (*outstanding_extents) {
+			(*outstanding_extents)--;
+		} else {
 			spin_lock(&BTRFS_I(inode)->lock);
 			BTRFS_I(inode)->outstanding_extents++;
 			spin_unlock(&BTRFS_I(inode)->lock);
 		}
+
+		current->journal_info = outstanding_extents;
 		btrfs_free_reserved_data_space(inode, len);
 	}
 
@@ -7376,6 +7418,8 @@
 unlock_err:
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			 unlock_bits, 1, 0, &cached_state, GFP_NOFS);
+	if (outstanding_extents)
+		current->journal_info = outstanding_extents;
 	return ret;
 }
 
@@ -8075,6 +8119,7 @@
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	u64 outstanding_extents = 0;
 	size_t count = 0;
 	int flags = 0;
 	bool wakeup = true;
@@ -8112,6 +8157,16 @@
 		ret = btrfs_delalloc_reserve_space(inode, count);
 		if (ret)
 			goto out;
+		outstanding_extents = div64_u64(count +
+						BTRFS_MAX_EXTENT_SIZE - 1,
+						BTRFS_MAX_EXTENT_SIZE);
+
+		/*
+		 * We need to know how many extents we reserved so that we can
+		 * do the accounting properly if we go over the number we
+		 * originally calculated.  Abuse current->journal_info for this.
+		 */
+		current->journal_info = &outstanding_extents;
 	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 				     &BTRFS_I(inode)->runtime_flags)) {
 		inode_dio_done(inode);
@@ -8124,6 +8179,7 @@
 			iter, offset, btrfs_get_blocks_direct, NULL,
 			btrfs_submit_direct, flags);
 	if (rw & WRITE) {
+		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED)
 			btrfs_delalloc_release_space(inode, count);
 		else if (ret >= 0 && (size_t)ret < count)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 97159a8..058c79e 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1259,7 +1259,7 @@
 	if (oper1->seq < oper2->seq)
 		return -1;
 	if (oper1->seq > oper2->seq)
-		return -1;
+		return 1;
 	if (oper1->ref_root < oper2->ref_root)
 		return -1;
 	if (oper1->ref_root > oper2->ref_root)
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index a116b55..054fc0d 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -911,6 +911,197 @@
 	return ret;
 }
 
+static int test_extent_accounting(void)
+{
+	struct inode *inode = NULL;
+	struct btrfs_root *root = NULL;
+	int ret = -ENOMEM;
+
+	inode = btrfs_new_test_inode();
+	if (!inode) {
+		test_msg("Couldn't allocate inode\n");
+		return ret;
+	}
+
+	root = btrfs_alloc_dummy_root();
+	if (IS_ERR(root)) {
+		test_msg("Couldn't allocate root\n");
+		goto out;
+	}
+
+	root->fs_info = btrfs_alloc_dummy_fs_info();
+	if (!root->fs_info) {
+		test_msg("Couldn't allocate dummy fs info\n");
+		goto out;
+	}
+
+	BTRFS_I(inode)->root = root;
+	btrfs_test_inode_set_ops(inode);
+
+	/* [BTRFS_MAX_EXTENT_SIZE] */
+	BTRFS_I(inode)->outstanding_extents++;
+	ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1,
+					NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 1) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 1, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* [BTRFS_MAX_EXTENT_SIZE][4k] */
+	BTRFS_I(inode)->outstanding_extents++;
+	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE,
+					BTRFS_MAX_EXTENT_SIZE + 4095, NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 2) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 2, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* [BTRFS_MAX_EXTENT_SIZE/2][4K HOLE][the rest] */
+	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
+			       BTRFS_MAX_EXTENT_SIZE >> 1,
+			       (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+			       EXTENT_DELALLOC | EXTENT_DIRTY |
+			       EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0,
+			       NULL, GFP_NOFS);
+	if (ret) {
+		test_msg("clear_extent_bit returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 2) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 2, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* [BTRFS_MAX_EXTENT_SIZE][4K] */
+	BTRFS_I(inode)->outstanding_extents++;
+	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1,
+					(BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+					NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 2) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 2, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/*
+	 * [BTRFS_MAX_EXTENT_SIZE+4K][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4K]
+	 *
+	 * I'm artificially adding 2 to outstanding_extents because in the
+	 * buffered IO case we'd add things up as we go, but I don't feel like
+	 * doing that here, this isn't the interesting case we want to test.
+	 */
+	BTRFS_I(inode)->outstanding_extents += 2;
+	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + 8192,
+					(BTRFS_MAX_EXTENT_SIZE << 1) + 12287,
+					NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 4) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 4, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* [BTRFS_MAX_EXTENT_SIZE+4k][4k][BTRFS_MAX_EXTENT_SIZE+4k] */
+	BTRFS_I(inode)->outstanding_extents++;
+	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
+					BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 3) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 3, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* [BTRFS_MAX_EXTENT_SIZE+4k][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4k] */
+	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
+			       BTRFS_MAX_EXTENT_SIZE+4096,
+			       BTRFS_MAX_EXTENT_SIZE+8191,
+			       EXTENT_DIRTY | EXTENT_DELALLOC |
+			       EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
+			       NULL, GFP_NOFS);
+	if (ret) {
+		test_msg("clear_extent_bit returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 4) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 4, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/*
+	 * Refill the hole again just for good measure, because I thought it
+	 * might fail and I'd rather satisfy my paranoia at this point.
+	 */
+	BTRFS_I(inode)->outstanding_extents++;
+	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
+					BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+	if (ret) {
+		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents != 3) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 3, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+
+	/* Empty */
+	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
+			       EXTENT_DIRTY | EXTENT_DELALLOC |
+			       EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
+			       NULL, GFP_NOFS);
+	if (ret) {
+		test_msg("clear_extent_bit returned %d\n", ret);
+		goto out;
+	}
+	if (BTRFS_I(inode)->outstanding_extents) {
+		ret = -EINVAL;
+		test_msg("Miscount, wanted 0, got %u\n",
+			 BTRFS_I(inode)->outstanding_extents);
+		goto out;
+	}
+	ret = 0;
+out:
+	if (ret)
+		clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
+				 EXTENT_DIRTY | EXTENT_DELALLOC |
+				 EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
+				 NULL, GFP_NOFS);
+	iput(inode);
+	btrfs_free_dummy_root(root);
+	return ret;
+}
+
 int btrfs_test_inodes(void)
 {
 	int ret;
@@ -924,5 +1115,9 @@
 	if (ret)
 		return ret;
 	test_msg("Running hole first btrfs_get_extent test\n");
-	return test_hole_first();
+	ret = test_hole_first();
+	if (ret)
+		return ret;
+	test_msg("Running outstanding_extents tests\n");
+	return test_extent_accounting();
 }
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 88e51ad..8be4278 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1023,17 +1023,13 @@
 	u64 old_root_bytenr;
 	u64 old_root_used;
 	struct btrfs_root *tree_root = root->fs_info->tree_root;
-	bool extent_root = (root->objectid == BTRFS_EXTENT_TREE_OBJECTID);
 
 	old_root_used = btrfs_root_used(&root->root_item);
-	btrfs_write_dirty_block_groups(trans, root);
 
 	while (1) {
 		old_root_bytenr = btrfs_root_bytenr(&root->root_item);
 		if (old_root_bytenr == root->node->start &&
-		    old_root_used == btrfs_root_used(&root->root_item) &&
-		    (!extent_root ||
-		     list_empty(&trans->transaction->dirty_bgs)))
+		    old_root_used == btrfs_root_used(&root->root_item))
 			break;
 
 		btrfs_set_root_node(&root->root_item, root->node);
@@ -1044,14 +1040,6 @@
 			return ret;
 
 		old_root_used = btrfs_root_used(&root->root_item);
-		if (extent_root) {
-			ret = btrfs_write_dirty_block_groups(trans, root);
-			if (ret)
-				return ret;
-		}
-		ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
-		if (ret)
-			return ret;
 	}
 
 	return 0;
@@ -1068,6 +1056,7 @@
 					 struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct list_head *dirty_bgs = &trans->transaction->dirty_bgs;
 	struct list_head *next;
 	struct extent_buffer *eb;
 	int ret;
@@ -1095,11 +1084,15 @@
 	if (ret)
 		return ret;
 
+	ret = btrfs_setup_space_cache(trans, root);
+	if (ret)
+		return ret;
+
 	/* run_qgroups might have added some more refs */
 	ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
 	if (ret)
 		return ret;
-
+again:
 	while (!list_empty(&fs_info->dirty_cowonly_roots)) {
 		next = fs_info->dirty_cowonly_roots.next;
 		list_del_init(next);
@@ -1112,8 +1105,23 @@
 		ret = update_cowonly_root(trans, root);
 		if (ret)
 			return ret;
+		ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
+		if (ret)
+			return ret;
 	}
 
+	while (!list_empty(dirty_bgs)) {
+		ret = btrfs_write_dirty_block_groups(trans, root);
+		if (ret)
+			return ret;
+		ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
+		if (ret)
+			return ret;
+	}
+
+	if (!list_empty(&fs_info->dirty_cowonly_roots))
+		goto again;
+
 	list_add_tail(&fs_info->extent_root->dirty_list,
 		      &trans->transaction->switch_commits);
 	btrfs_after_dev_replace_commit(fs_info);
@@ -1811,6 +1819,9 @@
 
 		wait_for_commit(root, cur_trans);
 
+		if (unlikely(cur_trans->aborted))
+			ret = cur_trans->aborted;
+
 		btrfs_put_transaction(cur_trans);
 
 		return ret;
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ed19a7d..39706c5 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -890,8 +890,8 @@
 
 	newpage = buf->page;
 
-	if (WARN_ON(!PageUptodate(newpage)))
-		return -EIO;
+	if (!PageUptodate(newpage))
+		SetPageUptodate(newpage);
 
 	ClearPageMappedToDisk(newpage);
 
@@ -1353,6 +1353,17 @@
 	return err;
 }
 
+static int fuse_dev_open(struct inode *inode, struct file *file)
+{
+	/*
+	 * The fuse device's file's private_data is used to hold
+	 * the fuse_conn(ection) when it is mounted, and is used to
+	 * keep track of whether the file has been mounted already.
+	 */
+	file->private_data = NULL;
+	return 0;
+}
+
 static ssize_t fuse_dev_read(struct kiocb *iocb, const struct iovec *iov,
 			      unsigned long nr_segs, loff_t pos)
 {
@@ -1797,6 +1808,9 @@
 static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 		       unsigned int size, struct fuse_copy_state *cs)
 {
+	/* Don't try to move pages (yet) */
+	cs->move_pages = 0;
+
 	switch (code) {
 	case FUSE_NOTIFY_POLL:
 		return fuse_notify_poll(fc, size, cs);
@@ -2217,6 +2231,7 @@
 
 const struct file_operations fuse_dev_operations = {
 	.owner		= THIS_MODULE,
+	.open		= fuse_dev_open,
 	.llseek		= no_llseek,
 	.read		= do_sync_read,
 	.aio_read	= fuse_dev_read,
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index 6e560d5..754fdf8 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -131,13 +131,16 @@
 	hfs_bnode_write(node, entry, data_off + key_len, entry_len);
 	hfs_bnode_dump(node);
 
-	if (new_node) {
-		/* update parent key if we inserted a key
-		 * at the start of the first node
-		 */
-		if (!rec && new_node != node)
-			hfs_brec_update_parent(fd);
+	/*
+	 * update parent key if we inserted a key
+	 * at the start of the node and it is not the new node
+	 */
+	if (!rec && new_node != node) {
+		hfs_bnode_read_key(node, fd->search_key, data_off + size);
+		hfs_brec_update_parent(fd);
+	}
 
+	if (new_node) {
 		hfs_bnode_put(fd->bnode);
 		if (!new_node->parent) {
 			hfs_btree_inc_height(tree);
@@ -168,9 +171,6 @@
 		goto again;
 	}
 
-	if (!rec)
-		hfs_brec_update_parent(fd);
-
 	return 0;
 }
 
@@ -370,6 +370,8 @@
 	if (IS_ERR(parent))
 		return PTR_ERR(parent);
 	__hfs_brec_find(parent, fd, hfs_find_rec_by_key);
+	if (fd->record < 0)
+		return -ENOENT;
 	hfs_bnode_dump(parent);
 	rec = fd->record;
 
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index b684e8a..2bacb99 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -207,6 +207,7 @@
 		goto out_free;
 	}
 
+	of->event = atomic_read(&of->kn->attr.open->event);
 	ops = kernfs_ops(of->kn);
 	if (ops->read)
 		len = ops->read(of, buf, len, *ppos);
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 3c1bfa1..1028a06 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -587,8 +587,6 @@
 
 	rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str));
 
-	nfsd4_cb_layout_fail(ls);
-
 	printk(KERN_WARNING
 		"nfsd: client %s failed to respond to layout recall. "
 		"  Fencing..\n", addr_str);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index b90952f..5f0d199 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -529,8 +529,7 @@
 {
 	struct ovl_fs *ufs = sb->s_fs_info;
 
-	if (!(*flags & MS_RDONLY) &&
-	    (!ufs->upper_mnt || (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY)))
+	if (!(*flags & MS_RDONLY) && !ufs->upper_mnt)
 		return -EROFS;
 
 	return 0;
@@ -615,9 +614,19 @@
 			break;
 
 		default:
+			pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
 			return -EINVAL;
 		}
 	}
+
+	/* Workdir is useless in non-upper mount */
+	if (!config->upperdir && config->workdir) {
+		pr_info("overlayfs: option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
+			config->workdir);
+		kfree(config->workdir);
+		config->workdir = NULL;
+	}
+
 	return 0;
 }
 
@@ -837,7 +846,6 @@
 
 	sb->s_stack_depth = 0;
 	if (ufs->config.upperdir) {
-		/* FIXME: workdir is not needed for a R/O mount */
 		if (!ufs->config.workdir) {
 			pr_err("overlayfs: missing 'workdir'\n");
 			goto out_free_config;
@@ -847,6 +855,13 @@
 		if (err)
 			goto out_free_config;
 
+		/* Upper fs should not be r/o */
+		if (upperpath.mnt->mnt_sb->s_flags & MS_RDONLY) {
+			pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n");
+			err = -EINVAL;
+			goto out_put_upperpath;
+		}
+
 		err = ovl_mount_dir(ufs->config.workdir, &workpath);
 		if (err)
 			goto out_put_upperpath;
@@ -869,8 +884,14 @@
 
 	err = -EINVAL;
 	stacklen = ovl_split_lowerdirs(lowertmp);
-	if (stacklen > OVL_MAX_STACK)
+	if (stacklen > OVL_MAX_STACK) {
+		pr_err("overlayfs: too many lower directries, limit is %d\n",
+		       OVL_MAX_STACK);
 		goto out_free_lowertmp;
+	} else if (!ufs->config.upperdir && stacklen == 1) {
+		pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n");
+		goto out_free_lowertmp;
+	}
 
 	stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL);
 	if (!stack)
@@ -932,8 +953,8 @@
 		ufs->numlower++;
 	}
 
-	/* If the upper fs is r/o or nonexistent, we mark overlayfs r/o too */
-	if (!ufs->upper_mnt || (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY))
+	/* If the upper fs is nonexistent, we mark overlayfs r/o too */
+	if (!ufs->upper_mnt)
 		sb->s_flags |= MS_RDONLY;
 
 	sb->s_d_op = &ovl_dentry_operations;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 956b75d..6dee68d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1325,6 +1325,9 @@
 
 static int pagemap_open(struct inode *inode, struct file *file)
 {
+	/* do not disclose physical addresses: attack vector */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
 	pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
 			"to stop being page-shift some time soon. See the "
 			"linux/Documentation/vm/pagemap.txt for details.\n");
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 7c55dd5..66203b2 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -114,6 +114,7 @@
 	void	(*sync_lr_elrsr)(struct kvm_vcpu *, int, struct vgic_lr);
 	u64	(*get_elrsr)(const struct kvm_vcpu *vcpu);
 	u64	(*get_eisr)(const struct kvm_vcpu *vcpu);
+	void	(*clear_eisr)(struct kvm_vcpu *vcpu);
 	u32	(*get_interrupt_status)(const struct kvm_vcpu *vcpu);
 	void	(*enable_underflow)(struct kvm_vcpu *vcpu);
 	void	(*disable_underflow)(struct kvm_vcpu *vcpu);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 2646aed..fd23978 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -375,6 +375,7 @@
  */
 struct mapped_device *dm_get_md(dev_t dev);
 void dm_get(struct mapped_device *md);
+int dm_hold(struct mapped_device *md);
 void dm_put(struct mapped_device *md);
 
 /*
diff --git a/include/linux/libata.h b/include/linux/libata.h
index fc03efa..6b08cc1 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -232,6 +232,7 @@
 					      * led */
 	ATA_FLAG_NO_DIPM	= (1 << 23), /* host not happy with DIPM */
 	ATA_FLAG_LOWTAG		= (1 << 24), /* host wants lowest available tag */
+	ATA_FLAG_SAS_HOST	= (1 << 25), /* SAS host */
 
 	/* bits 24:31 of ap->flags are reserved for LLD specific flags */
 
diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h
index fb0390a..ee7b1ce 100644
--- a/include/linux/mfd/palmas.h
+++ b/include/linux/mfd/palmas.h
@@ -2999,6 +2999,9 @@
 #define PALMAS_GPADC_TRIM15					0x0E
 #define PALMAS_GPADC_TRIM16					0x0F
 
+/* TPS659038 regen2_ctrl offset iss different from palmas */
+#define TPS659038_REGEN2_CTRL					0x12
+
 /* TPS65917 Interrupt registers */
 
 /* Registers for function INTERRUPT */
diff --git a/include/linux/module.h b/include/linux/module.h
index 42999fe..b03485b 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -344,6 +344,10 @@
 	unsigned long *ftrace_callsites;
 #endif
 
+#ifdef CONFIG_LIVEPATCH
+	bool klp_alive;
+#endif
+
 #ifdef CONFIG_MODULE_UNLOAD
 	/* What modules depend on me? */
 	struct list_head source_list;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 429d179..dcf6ec2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -965,9 +965,12 @@
  *	Used to add FDB entries to dump requests. Implementers should add
  *	entries to skb and update idx with the number of entries.
  *
- * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh)
+ * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh,
+ *			     u16 flags)
  * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq,
  *			     struct net_device *dev, u32 filter_mask)
+ * int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh,
+ *			     u16 flags);
  *
  * int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier);
  *	Called to change device carrier. Soft-devices (like dummy, team, etc)
diff --git a/include/linux/pinctrl/consumer.h b/include/linux/pinctrl/consumer.h
index 72c0415d..18eccef 100644
--- a/include/linux/pinctrl/consumer.h
+++ b/include/linux/pinctrl/consumer.h
@@ -82,7 +82,7 @@
 
 static inline struct pinctrl * __must_check pinctrl_get(struct device *dev)
 {
-	return ERR_PTR(-ENOSYS);
+	return NULL;
 }
 
 static inline void pinctrl_put(struct pinctrl *p)
@@ -93,7 +93,7 @@
 							struct pinctrl *p,
 							const char *name)
 {
-	return ERR_PTR(-ENOSYS);
+	return NULL;
 }
 
 static inline int pinctrl_select_state(struct pinctrl *p,
@@ -104,7 +104,7 @@
 
 static inline struct pinctrl * __must_check devm_pinctrl_get(struct device *dev)
 {
-	return ERR_PTR(-ENOSYS);
+	return NULL;
 }
 
 static inline void devm_pinctrl_put(struct pinctrl *p)
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index d4ad5b5..045f709 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -316,7 +316,7 @@
  * @driver_data: private regulator data
  * @of_node: OpenFirmware node to parse for device tree bindings (may be
  *           NULL).
- * @regmap: regmap to use for core regmap helpers if dev_get_regulator() is
+ * @regmap: regmap to use for core regmap helpers if dev_get_regmap() is
  *          insufficient.
  * @ena_gpio_initialized: GPIO controlling regulator enable was properly
  *                        initialized, meaning that >= 0 is a valid gpio
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6d77432..a419b65 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1625,11 +1625,11 @@
 
 	/*
 	 * numa_faults_locality tracks if faults recorded during the last
-	 * scan window were remote/local. The task scan period is adapted
-	 * based on the locality of the faults with different weights
-	 * depending on whether they were shared or private faults
+	 * scan window were remote/local or failed to migrate. The task scan
+	 * period is adapted based on the locality of the faults with different
+	 * weights depending on whether they were shared or private faults
 	 */
-	unsigned long numa_faults_locality[2];
+	unsigned long numa_faults_locality[3];
 
 	unsigned long numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
@@ -1719,6 +1719,7 @@
 #define TNF_NO_GROUP	0x02
 #define TNF_SHARED	0x04
 #define TNF_FAULT_LOCAL	0x08
+#define TNF_MIGRATE_FAIL 0x10
 
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, int flags);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 30007af..f54d665 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -948,6 +948,13 @@
 	to->l4_hash = from->l4_hash;
 };
 
+static inline void skb_sender_cpu_clear(struct sk_buff *skb)
+{
+#ifdef CONFIG_XPS
+	skb->sender_cpu = 0;
+#endif
+}
+
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
 static inline unsigned char *skb_end_pointer(const struct sk_buff *skb)
 {
diff --git a/include/net/dst.h b/include/net/dst.h
index a8ae4e7..0fb99a2 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -481,6 +481,7 @@
 enum {
 	XFRM_LOOKUP_ICMP = 1 << 0,
 	XFRM_LOOKUP_QUEUE = 1 << 1,
+	XFRM_LOOKUP_KEEP_DST_REF = 1 << 2,
 };
 
 struct flowi;
diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h
index 534e1f2..57639fc 100644
--- a/include/net/netfilter/nf_log.h
+++ b/include/net/netfilter/nf_log.h
@@ -79,6 +79,16 @@
 		   const struct nf_loginfo *li,
 		   const char *fmt, ...);
 
+__printf(8, 9)
+void nf_log_trace(struct net *net,
+		  u_int8_t pf,
+		  unsigned int hooknum,
+		  const struct sk_buff *skb,
+		  const struct net_device *in,
+		  const struct net_device *out,
+		  const struct nf_loginfo *li,
+		  const char *fmt, ...);
+
 struct nf_log_buf;
 
 struct nf_log_buf *nf_log_buf_open(void);
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index eabd3a0..c73e7ab 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -91,6 +91,7 @@
 
 #define VXLAN_N_VID     (1u << 24)
 #define VXLAN_VID_MASK  (VXLAN_N_VID - 1)
+#define VXLAN_VNI_MASK  (VXLAN_VID_MASK << 8)
 #define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
 
 struct vxlan_metadata {
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index db81c65..d61be72 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -111,6 +111,7 @@
 void	target_core_setup_sub_cits(struct se_subsystem_api *);
 
 /* attribute helpers from target_core_device.c for backend drivers */
+bool	se_dev_check_wce(struct se_device *);
 int	se_dev_set_max_unmap_lba_count(struct se_device *, u32);
 int	se_dev_set_max_unmap_block_desc_count(struct se_device *, u32);
 int	se_dev_set_unmap_granularity(struct se_device *, u32);
diff --git a/include/trace/events/regmap.h b/include/trace/events/regmap.h
index 23d5615..22317d2 100644
--- a/include/trace/events/regmap.h
+++ b/include/trace/events/regmap.h
@@ -7,27 +7,26 @@
 #include <linux/ktime.h>
 #include <linux/tracepoint.h>
 
-struct device;
-struct regmap;
+#include "../../../drivers/base/regmap/internal.h"
 
 /*
  * Log register events
  */
 DECLARE_EVENT_CLASS(regmap_reg,
 
-	TP_PROTO(struct device *dev, unsigned int reg,
+	TP_PROTO(struct regmap *map, unsigned int reg,
 		 unsigned int val),
 
-	TP_ARGS(dev, reg, val),
+	TP_ARGS(map, reg, val),
 
 	TP_STRUCT__entry(
-		__string(	name,		dev_name(dev)	)
-		__field(	unsigned int,	reg		)
-		__field(	unsigned int,	val		)
+		__string(	name,		regmap_name(map)	)
+		__field(	unsigned int,	reg			)
+		__field(	unsigned int,	val			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 		__entry->reg = reg;
 		__entry->val = val;
 	),
@@ -39,45 +38,45 @@
 
 DEFINE_EVENT(regmap_reg, regmap_reg_write,
 
-	TP_PROTO(struct device *dev, unsigned int reg,
+	TP_PROTO(struct regmap *map, unsigned int reg,
 		 unsigned int val),
 
-	TP_ARGS(dev, reg, val)
+	TP_ARGS(map, reg, val)
 
 );
 
 DEFINE_EVENT(regmap_reg, regmap_reg_read,
 
-	TP_PROTO(struct device *dev, unsigned int reg,
+	TP_PROTO(struct regmap *map, unsigned int reg,
 		 unsigned int val),
 
-	TP_ARGS(dev, reg, val)
+	TP_ARGS(map, reg, val)
 
 );
 
 DEFINE_EVENT(regmap_reg, regmap_reg_read_cache,
 
-	TP_PROTO(struct device *dev, unsigned int reg,
+	TP_PROTO(struct regmap *map, unsigned int reg,
 		 unsigned int val),
 
-	TP_ARGS(dev, reg, val)
+	TP_ARGS(map, reg, val)
 
 );
 
 DECLARE_EVENT_CLASS(regmap_block,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count),
+	TP_ARGS(map, reg, count),
 
 	TP_STRUCT__entry(
-		__string(	name,		dev_name(dev)	)
-		__field(	unsigned int,	reg		)
-		__field(	int,		count		)
+		__string(	name,		regmap_name(map)	)
+		__field(	unsigned int,	reg			)
+		__field(	int,		count			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 		__entry->reg = reg;
 		__entry->count = count;
 	),
@@ -89,48 +88,48 @@
 
 DEFINE_EVENT(regmap_block, regmap_hw_read_start,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count)
+	TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_block, regmap_hw_read_done,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count)
+	TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_block, regmap_hw_write_start,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count)
+	TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_block, regmap_hw_write_done,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count)
+	TP_ARGS(map, reg, count)
 );
 
 TRACE_EVENT(regcache_sync,
 
-	TP_PROTO(struct device *dev, const char *type,
+	TP_PROTO(struct regmap *map, const char *type,
 		 const char *status),
 
-	TP_ARGS(dev, type, status),
+	TP_ARGS(map, type, status),
 
 	TP_STRUCT__entry(
-		__string(       name,           dev_name(dev)   )
-		__string(	status,		status		)
-		__string(	type,		type		)
-		__field(	int,		type		)
+		__string(       name,           regmap_name(map)	)
+		__string(	status,		status			)
+		__string(	type,		type			)
+		__field(	int,		type			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 		__assign_str(status, status);
 		__assign_str(type, type);
 	),
@@ -141,17 +140,17 @@
 
 DECLARE_EVENT_CLASS(regmap_bool,
 
-	TP_PROTO(struct device *dev, bool flag),
+	TP_PROTO(struct regmap *map, bool flag),
 
-	TP_ARGS(dev, flag),
+	TP_ARGS(map, flag),
 
 	TP_STRUCT__entry(
-		__string(	name,		dev_name(dev)	)
-		__field(	int,		flag		)
+		__string(	name,		regmap_name(map)	)
+		__field(	int,		flag			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 		__entry->flag = flag;
 	),
 
@@ -161,32 +160,32 @@
 
 DEFINE_EVENT(regmap_bool, regmap_cache_only,
 
-	TP_PROTO(struct device *dev, bool flag),
+	TP_PROTO(struct regmap *map, bool flag),
 
-	TP_ARGS(dev, flag)
+	TP_ARGS(map, flag)
 
 );
 
 DEFINE_EVENT(regmap_bool, regmap_cache_bypass,
 
-	TP_PROTO(struct device *dev, bool flag),
+	TP_PROTO(struct regmap *map, bool flag),
 
-	TP_ARGS(dev, flag)
+	TP_ARGS(map, flag)
 
 );
 
 DECLARE_EVENT_CLASS(regmap_async,
 
-	TP_PROTO(struct device *dev),
+	TP_PROTO(struct regmap *map),
 
-	TP_ARGS(dev),
+	TP_ARGS(map),
 
 	TP_STRUCT__entry(
-		__string(	name,		dev_name(dev)	)
+		__string(	name,		regmap_name(map)	)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 	),
 
 	TP_printk("%s", __get_str(name))
@@ -194,50 +193,50 @@
 
 DEFINE_EVENT(regmap_block, regmap_async_write_start,
 
-	TP_PROTO(struct device *dev, unsigned int reg, int count),
+	TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-	TP_ARGS(dev, reg, count)
+	TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_async, regmap_async_io_complete,
 
-	TP_PROTO(struct device *dev),
+	TP_PROTO(struct regmap *map),
 
-	TP_ARGS(dev)
+	TP_ARGS(map)
 
 );
 
 DEFINE_EVENT(regmap_async, regmap_async_complete_start,
 
-	TP_PROTO(struct device *dev),
+	TP_PROTO(struct regmap *map),
 
-	TP_ARGS(dev)
+	TP_ARGS(map)
 
 );
 
 DEFINE_EVENT(regmap_async, regmap_async_complete_done,
 
-	TP_PROTO(struct device *dev),
+	TP_PROTO(struct regmap *map),
 
-	TP_ARGS(dev)
+	TP_ARGS(map)
 
 );
 
 TRACE_EVENT(regcache_drop_region,
 
-	TP_PROTO(struct device *dev, unsigned int from,
+	TP_PROTO(struct regmap *map, unsigned int from,
 		 unsigned int to),
 
-	TP_ARGS(dev, from, to),
+	TP_ARGS(map, from, to),
 
 	TP_STRUCT__entry(
-		__string(       name,           dev_name(dev)   )
-		__field(	unsigned int,	from		)
-		__field(	unsigned int,	to		)
+		__string(       name,           regmap_name(map)	)
+		__field(	unsigned int,	from			)
+		__field(	unsigned int,	to			)
 	),
 
 	TP_fast_assign(
-		__assign_str(name, dev_name(dev));
+		__assign_str(name, regmap_name(map));
 		__entry->from = from;
 		__entry->to = to;
 	),
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 8d1be90..551b673 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -270,7 +270,7 @@
 #define DRM_IOCTL_I915_OVERLAY_PUT_IMAGE	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_OVERLAY_PUT_IMAGE, struct drm_intel_overlay_put_image)
 #define DRM_IOCTL_I915_OVERLAY_ATTRS	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_OVERLAY_ATTRS, struct drm_intel_overlay_attrs)
 #define DRM_IOCTL_I915_SET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_SET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
-#define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_SET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
+#define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
 #define DRM_IOCTL_I915_GEM_WAIT		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait)
 #define DRM_IOCTL_I915_GEM_CONTEXT_CREATE	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create)
 #define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy)
diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h
index 3c53eec..19c66fc 100644
--- a/include/uapi/linux/virtio_blk.h
+++ b/include/uapi/linux/virtio_blk.h
@@ -60,7 +60,7 @@
 	__u32 size_max;
 	/* The maximum number of segments (if VIRTIO_BLK_F_SEG_MAX) */
 	__u32 seg_max;
-	/* geometry the device (if VIRTIO_BLK_F_GEOMETRY) */
+	/* geometry of the device (if VIRTIO_BLK_F_GEOMETRY) */
 	struct virtio_blk_geometry {
 		__u16 cylinders;
 		__u8 heads;
@@ -119,7 +119,11 @@
 #define VIRTIO_BLK_T_BARRIER	0x80000000
 #endif /* !VIRTIO_BLK_NO_LEGACY */
 
-/* This is the first element of the read scatter-gather list. */
+/*
+ * This comes first in the read scatter-gather list.
+ * For legacy virtio, if VIRTIO_F_ANY_LAYOUT is not negotiated,
+ * this is the first element of the read scatter-gather list.
+ */
 struct virtio_blk_outhdr {
 	/* VIRTIO_BLK_T* */
 	__virtio32 type;
diff --git a/include/uapi/linux/virtio_scsi.h b/include/uapi/linux/virtio_scsi.h
index 42b9370..cc18ef8 100644
--- a/include/uapi/linux/virtio_scsi.h
+++ b/include/uapi/linux/virtio_scsi.h
@@ -29,8 +29,16 @@
 
 #include <linux/virtio_types.h>
 
-#define VIRTIO_SCSI_CDB_SIZE   32
-#define VIRTIO_SCSI_SENSE_SIZE 96
+/* Default values of the CDB and sense data size configuration fields */
+#define VIRTIO_SCSI_CDB_DEFAULT_SIZE   32
+#define VIRTIO_SCSI_SENSE_DEFAULT_SIZE 96
+
+#ifndef VIRTIO_SCSI_CDB_SIZE
+#define VIRTIO_SCSI_CDB_SIZE VIRTIO_SCSI_CDB_DEFAULT_SIZE
+#endif
+#ifndef VIRTIO_SCSI_SENSE_SIZE
+#define VIRTIO_SCSI_SENSE_SIZE VIRTIO_SCSI_SENSE_DEFAULT_SIZE
+#endif
 
 /* SCSI command request, followed by data-out */
 struct virtio_scsi_cmd_req {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f04daab..2fabc06 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3591,7 +3591,7 @@
 	ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING);
 	WARN_ON_ONCE(ctx->parent_ctx);
 	perf_remove_from_context(event, true);
-	mutex_unlock(&ctx->mutex);
+	perf_event_ctx_unlock(event, ctx);
 
 	_free_event(event);
 }
@@ -4574,6 +4574,13 @@
 {
 	struct perf_event *event = container_of(entry,
 			struct perf_event, pending);
+	int rctx;
+
+	rctx = perf_swevent_get_recursion_context();
+	/*
+	 * If we 'fail' here, that's OK, it means recursion is already disabled
+	 * and we won't recurse 'further'.
+	 */
 
 	if (event->pending_disable) {
 		event->pending_disable = 0;
@@ -4584,6 +4591,9 @@
 		event->pending_wakeup = 0;
 		perf_event_wakeup(event);
 	}
+
+	if (rctx >= 0)
+		perf_swevent_put_recursion_context(rctx);
 }
 
 /*
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index 01ca088..3f9f1d6 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -89,16 +89,28 @@
 /* sets obj->mod if object is not vmlinux and module is found */
 static void klp_find_object_module(struct klp_object *obj)
 {
+	struct module *mod;
+
 	if (!klp_is_module(obj))
 		return;
 
 	mutex_lock(&module_mutex);
 	/*
-	 * We don't need to take a reference on the module here because we have
-	 * the klp_mutex, which is also taken by the module notifier.  This
-	 * prevents any module from unloading until we release the klp_mutex.
+	 * We do not want to block removal of patched modules and therefore
+	 * we do not take a reference here. The patches are removed by
+	 * a going module handler instead.
 	 */
-	obj->mod = find_module(obj->name);
+	mod = find_module(obj->name);
+	/*
+	 * Do not mess work of the module coming and going notifiers.
+	 * Note that the patch might still be needed before the going handler
+	 * is called. Module functions can be called even in the GOING state
+	 * until mod->exit() finishes. This is especially important for
+	 * patches that modify semantic of the functions.
+	 */
+	if (mod && mod->klp_alive)
+		obj->mod = mod;
+
 	mutex_unlock(&module_mutex);
 }
 
@@ -767,6 +779,7 @@
 		return -EINVAL;
 
 	obj->state = KLP_DISABLED;
+	obj->mod = NULL;
 
 	klp_find_object_module(obj);
 
@@ -961,6 +974,15 @@
 
 	mutex_lock(&klp_mutex);
 
+	/*
+	 * Each module has to know that the notifier has been called.
+	 * We never know what module will get patched by a new patch.
+	 */
+	if (action == MODULE_STATE_COMING)
+		mod->klp_alive = true;
+	else /* MODULE_STATE_GOING */
+		mod->klp_alive = false;
+
 	list_for_each_entry(patch, &klp_patches, list) {
 		for (obj = patch->objs; obj->funcs; obj++) {
 			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 88d0d44..ba77ab5 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -633,7 +633,7 @@
 	if (!new_class->name)
 		return 0;
 
-	list_for_each_entry(class, &all_lock_classes, lock_entry) {
+	list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) {
 		if (new_class->key - new_class->subclass == class->key)
 			return class->name_version;
 		if (class->name && !strcmp(class->name, new_class->name))
@@ -700,10 +700,12 @@
 	hash_head = classhashentry(key);
 
 	/*
-	 * We can walk the hash lockfree, because the hash only
-	 * grows, and we are careful when adding entries to the end:
+	 * We do an RCU walk of the hash, see lockdep_free_key_range().
 	 */
-	list_for_each_entry(class, hash_head, hash_entry) {
+	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+		return NULL;
+
+	list_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key) {
 			/*
 			 * Huh! same key, different name? Did someone trample
@@ -728,7 +730,8 @@
 	struct lockdep_subclass_key *key;
 	struct list_head *hash_head;
 	struct lock_class *class;
-	unsigned long flags;
+
+	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
 
 	class = look_up_lock_class(lock, subclass);
 	if (likely(class))
@@ -750,28 +753,26 @@
 	key = lock->key->subkeys + subclass;
 	hash_head = classhashentry(key);
 
-	raw_local_irq_save(flags);
 	if (!graph_lock()) {
-		raw_local_irq_restore(flags);
 		return NULL;
 	}
 	/*
 	 * We have to do the hash-walk again, to avoid races
 	 * with another CPU:
 	 */
-	list_for_each_entry(class, hash_head, hash_entry)
+	list_for_each_entry_rcu(class, hash_head, hash_entry) {
 		if (class->key == key)
 			goto out_unlock_set;
+	}
+
 	/*
 	 * Allocate a new key from the static array, and add it to
 	 * the hash:
 	 */
 	if (nr_lock_classes >= MAX_LOCKDEP_KEYS) {
 		if (!debug_locks_off_graph_unlock()) {
-			raw_local_irq_restore(flags);
 			return NULL;
 		}
-		raw_local_irq_restore(flags);
 
 		print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!");
 		dump_stack();
@@ -798,7 +799,6 @@
 
 	if (verbose(class)) {
 		graph_unlock();
-		raw_local_irq_restore(flags);
 
 		printk("\nnew class %p: %s", class->key, class->name);
 		if (class->name_version > 1)
@@ -806,15 +806,12 @@
 		printk("\n");
 		dump_stack();
 
-		raw_local_irq_save(flags);
 		if (!graph_lock()) {
-			raw_local_irq_restore(flags);
 			return NULL;
 		}
 	}
 out_unlock_set:
 	graph_unlock();
-	raw_local_irq_restore(flags);
 
 out_set_class_cache:
 	if (!subclass || force)
@@ -870,11 +867,9 @@
 	entry->distance = distance;
 	entry->trace = *trace;
 	/*
-	 * Since we never remove from the dependency list, the list can
-	 * be walked lockless by other CPUs, it's only allocation
-	 * that must be protected by the spinlock. But this also means
-	 * we must make new entries visible only once writes to the
-	 * entry become visible - hence the RCU op:
+	 * Both allocation and removal are done under the graph lock; but
+	 * iteration is under RCU-sched; see look_up_lock_class() and
+	 * lockdep_free_key_range().
 	 */
 	list_add_tail_rcu(&entry->entry, head);
 
@@ -1025,7 +1020,9 @@
 		else
 			head = &lock->class->locks_before;
 
-		list_for_each_entry(entry, head, entry) {
+		DEBUG_LOCKS_WARN_ON(!irqs_disabled());
+
+		list_for_each_entry_rcu(entry, head, entry) {
 			if (!lock_accessed(entry)) {
 				unsigned int cq_depth;
 				mark_lock_accessed(entry, lock);
@@ -2022,7 +2019,7 @@
 	 * We can walk it lock-free, because entries only get added
 	 * to the hash:
 	 */
-	list_for_each_entry(chain, hash_head, entry) {
+	list_for_each_entry_rcu(chain, hash_head, entry) {
 		if (chain->chain_key == chain_key) {
 cache_hit:
 			debug_atomic_inc(chain_lookup_hits);
@@ -2996,8 +2993,18 @@
 	if (unlikely(!debug_locks))
 		return;
 
-	if (subclass)
+	if (subclass) {
+		unsigned long flags;
+
+		if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion))
+			return;
+
+		raw_local_irq_save(flags);
+		current->lockdep_recursion = 1;
 		register_lock_class(lock, subclass, 1);
+		current->lockdep_recursion = 0;
+		raw_local_irq_restore(flags);
+	}
 }
 EXPORT_SYMBOL_GPL(lockdep_init_map);
 
@@ -3887,9 +3894,17 @@
 	return addr >= start && addr < start + size;
 }
 
+/*
+ * Used in module.c to remove lock classes from memory that is going to be
+ * freed; and possibly re-used by other modules.
+ *
+ * We will have had one sync_sched() before getting here, so we're guaranteed
+ * nobody will look up these exact classes -- they're properly dead but still
+ * allocated.
+ */
 void lockdep_free_key_range(void *start, unsigned long size)
 {
-	struct lock_class *class, *next;
+	struct lock_class *class;
 	struct list_head *head;
 	unsigned long flags;
 	int i;
@@ -3905,7 +3920,7 @@
 		head = classhash_table + i;
 		if (list_empty(head))
 			continue;
-		list_for_each_entry_safe(class, next, head, hash_entry) {
+		list_for_each_entry_rcu(class, head, hash_entry) {
 			if (within(class->key, start, size))
 				zap_class(class);
 			else if (within(class->name, start, size))
@@ -3916,11 +3931,25 @@
 	if (locked)
 		graph_unlock();
 	raw_local_irq_restore(flags);
+
+	/*
+	 * Wait for any possible iterators from look_up_lock_class() to pass
+	 * before continuing to free the memory they refer to.
+	 *
+	 * sync_sched() is sufficient because the read-side is IRQ disable.
+	 */
+	synchronize_sched();
+
+	/*
+	 * XXX at this point we could return the resources to the pool;
+	 * instead we leak them. We would need to change to bitmap allocators
+	 * instead of the linear allocators we have now.
+	 */
 }
 
 void lockdep_reset_lock(struct lockdep_map *lock)
 {
-	struct lock_class *class, *next;
+	struct lock_class *class;
 	struct list_head *head;
 	unsigned long flags;
 	int i, j;
@@ -3948,7 +3977,7 @@
 		head = classhash_table + i;
 		if (list_empty(head))
 			continue;
-		list_for_each_entry_safe(class, next, head, hash_entry) {
+		list_for_each_entry_rcu(class, head, hash_entry) {
 			int match = 0;
 
 			for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
diff --git a/kernel/module.c b/kernel/module.c
index b3d634e..99fdf94 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1865,7 +1865,7 @@
 	kfree(mod->args);
 	percpu_modfree(mod);
 
-	/* Free lock-classes: */
+	/* Free lock-classes; relies on the preceding sync_rcu(). */
 	lockdep_free_key_range(mod->module_core, mod->core_size);
 
 	/* Finally, free the core (containing the module structure) */
@@ -3349,9 +3349,6 @@
 	module_bug_cleanup(mod);
 	mutex_unlock(&module_mutex);
 
-	/* Free lock-classes: */
-	lockdep_free_key_range(mod->module_core, mod->core_size);
-
 	/* we can't deallocate the module until we clear memory protection */
 	unset_module_init_ro_nx(mod);
 	unset_module_core_ro_nx(mod);
@@ -3375,6 +3372,9 @@
 	synchronize_rcu();
 	mutex_unlock(&module_mutex);
  free_module:
+	/* Free lock-classes; relies on the preceding sync_rcu() */
+	lockdep_free_key_range(mod->module_core, mod->core_size);
+
 	module_deallocate(mod, info);
  free_copy:
 	free_copy(info);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f0f831e..62671f5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3034,6 +3034,8 @@
 	} else {
 		if (dl_prio(oldprio))
 			p->dl.dl_boosted = 0;
+		if (rt_prio(oldprio))
+			p->rt.timeout = 0;
 		p->sched_class = &fair_sched_class;
 	}
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7ce18f3..bcfe320 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1609,9 +1609,11 @@
 	/*
 	 * If there were no record hinting faults then either the task is
 	 * completely idle or all activity is areas that are not of interest
-	 * to automatic numa balancing. Scan slower
+	 * to automatic numa balancing. Related to that, if there were failed
+	 * migration then it implies we are migrating too quickly or the local
+	 * node is overloaded. In either case, scan slower
 	 */
-	if (local + shared == 0) {
+	if (local + shared == 0 || p->numa_faults_locality[2]) {
 		p->numa_scan_period = min(p->numa_scan_period_max,
 			p->numa_scan_period << 1);
 
@@ -2080,6 +2082,8 @@
 
 	if (migrated)
 		p->numa_pages_migrated += pages;
+	if (flags & TNF_MIGRATE_FAIL)
+		p->numa_faults_locality[2] += pages;
 
 	p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages;
 	p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages;
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index eb682d5..6aac4be 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -49,6 +49,7 @@
  */
 static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 {
+	int bc_moved;
 	/*
 	 * We try to cancel the timer first. If the callback is on
 	 * flight on some other cpu then we let it handle it. If we
@@ -60,9 +61,15 @@
 	 * restart the timer because we are in the callback, but we
 	 * can set the expiry time and let the callback return
 	 * HRTIMER_RESTART.
+	 *
+	 * Since we are in the idle loop at this point and because
+	 * hrtimer_{start/cancel} functions call into tracing,
+	 * calls to these functions must be bound within RCU_NONIDLE.
 	 */
-	if (hrtimer_try_to_cancel(&bctimer) >= 0) {
-		hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+	RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ?
+		!hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) :
+			0);
+	if (bc_moved) {
 		/* Bind the "device" to the cpu */
 		bc->bound_on = smp_processor_id();
 	} else if (bc->bound_on == smp_processor_id()) {
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 7a85967..f0f5c5c 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -139,6 +139,9 @@
 			/* Error: request to write beyond destination buffer */
 			if (cpy > oend)
 				goto _output_error;
+			if ((ref + COPYLENGTH) > oend ||
+					(op + COPYLENGTH) > oend)
+				goto _output_error;
 			LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
 			while (op < cpy)
 				*op++ = *ref++;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 626e93d..6817b03 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1260,6 +1260,7 @@
 	int target_nid, last_cpupid = -1;
 	bool page_locked;
 	bool migrated = false;
+	bool was_writable;
 	int flags = 0;
 
 	/* A PROT_NONE fault should not end up here */
@@ -1291,17 +1292,8 @@
 		flags |= TNF_FAULT_LOCAL;
 	}
 
-	/*
-	 * Avoid grouping on DSO/COW pages in specific and RO pages
-	 * in general, RO pages shouldn't hurt as much anyway since
-	 * they can be in shared cache state.
-	 *
-	 * FIXME! This checks "pmd_dirty()" as an approximation of
-	 * "is this a read-only page", since checking "pmd_write()"
-	 * is even more broken. We haven't actually turned this into
-	 * a writable page, so pmd_write() will always be false.
-	 */
-	if (!pmd_dirty(pmd))
+	/* See similar comment in do_numa_page for explanation */
+	if (!(vma->vm_flags & VM_WRITE))
 		flags |= TNF_NO_GROUP;
 
 	/*
@@ -1358,12 +1350,17 @@
 	if (migrated) {
 		flags |= TNF_MIGRATED;
 		page_nid = target_nid;
-	}
+	} else
+		flags |= TNF_MIGRATE_FAIL;
 
 	goto out;
 clear_pmdnuma:
 	BUG_ON(!PageLocked(page));
+	was_writable = pmd_write(pmd);
 	pmd = pmd_modify(pmd, vma->vm_page_prot);
+	pmd = pmd_mkyoung(pmd);
+	if (was_writable)
+		pmd = pmd_mkwrite(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	update_mmu_cache_pmd(vma, addr, pmdp);
 	unlock_page(page);
@@ -1487,6 +1484,7 @@
 
 	if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
 		pmd_t entry;
+		bool preserve_write = prot_numa && pmd_write(*pmd);
 		ret = 1;
 
 		/*
@@ -1502,9 +1500,11 @@
 		if (!prot_numa || !pmd_protnone(*pmd)) {
 			entry = pmdp_get_and_clear_notify(mm, addr, pmd);
 			entry = pmd_modify(entry, newprot);
+			if (preserve_write)
+				entry = pmd_mkwrite(entry);
 			ret = HPAGE_PMD_NR;
 			set_pmd_at(mm, addr, pmd, entry);
-			BUG_ON(pmd_write(entry));
+			BUG_ON(!preserve_write && pmd_write(entry));
 		}
 		spin_unlock(ptl);
 	}
diff --git a/mm/memory.c b/mm/memory.c
index 411144f..97839f5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3035,6 +3035,7 @@
 	int last_cpupid;
 	int target_nid;
 	bool migrated = false;
+	bool was_writable = pte_write(pte);
 	int flags = 0;
 
 	/* A PROT_NONE fault should not end up here */
@@ -3059,6 +3060,8 @@
 	/* Make it present again */
 	pte = pte_modify(pte, vma->vm_page_prot);
 	pte = pte_mkyoung(pte);
+	if (was_writable)
+		pte = pte_mkwrite(pte);
 	set_pte_at(mm, addr, ptep, pte);
 	update_mmu_cache(vma, addr, ptep);
 
@@ -3069,16 +3072,14 @@
 	}
 
 	/*
-	 * Avoid grouping on DSO/COW pages in specific and RO pages
-	 * in general, RO pages shouldn't hurt as much anyway since
-	 * they can be in shared cache state.
-	 *
-	 * FIXME! This checks "pmd_dirty()" as an approximation of
-	 * "is this a read-only page", since checking "pmd_write()"
-	 * is even more broken. We haven't actually turned this into
-	 * a writable page, so pmd_write() will always be false.
+	 * Avoid grouping on RO pages in general. RO pages shouldn't hurt as
+	 * much anyway since they can be in shared cache state. This misses
+	 * the case where a mapping is writable but the process never writes
+	 * to it but pte_write gets cleared during protection updates and
+	 * pte_dirty has unpredictable behaviour between PTE scan updates,
+	 * background writeback, dirty balancing and application behaviour.
 	 */
-	if (!pte_dirty(pte))
+	if (!(vma->vm_flags & VM_WRITE))
 		flags |= TNF_NO_GROUP;
 
 	/*
@@ -3102,7 +3103,8 @@
 	if (migrated) {
 		page_nid = target_nid;
 		flags |= TNF_MIGRATED;
-	}
+	} else
+		flags |= TNF_MIGRATE_FAIL;
 
 out:
 	if (page_nid != -1)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9fab107..65842d6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1092,6 +1092,10 @@
 			return NULL;
 
 		arch_refresh_nodedata(nid, pgdat);
+	} else {
+		/* Reset the nr_zones and classzone_idx to 0 before reuse */
+		pgdat->nr_zones = 0;
+		pgdat->classzone_idx = 0;
 	}
 
 	/* we can use NODE_DATA(nid) from here */
@@ -1977,15 +1981,6 @@
 		if (is_vmalloc_addr(zone->wait_table))
 			vfree(zone->wait_table);
 	}
-
-	/*
-	 * Since there is no way to guarentee the address of pgdat/zone is not
-	 * on stack of any kernel threads or used by other kernel objects
-	 * without reference counting or other symchronizing method, do not
-	 * reset node_data and free pgdat here. Just reset it to 0 and reuse
-	 * the memory when the node is online again.
-	 */
-	memset(pgdat, 0, sizeof(*pgdat));
 }
 EXPORT_SYMBOL(try_offline_node);
 
diff --git a/mm/mmap.c b/mm/mmap.c
index da9990a..9ec50a3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -774,10 +774,8 @@
 
 			importer->anon_vma = exporter->anon_vma;
 			error = anon_vma_clone(importer, exporter);
-			if (error) {
-				importer->anon_vma = NULL;
+			if (error)
 				return error;
-			}
 		}
 	}
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 4472781..8858483 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -75,6 +75,7 @@
 		oldpte = *pte;
 		if (pte_present(oldpte)) {
 			pte_t ptent;
+			bool preserve_write = prot_numa && pte_write(oldpte);
 
 			/*
 			 * Avoid trapping faults against the zero or KSM
@@ -94,6 +95,8 @@
 
 			ptent = ptep_modify_prot_start(mm, addr, pte);
 			ptent = pte_modify(ptent, newprot);
+			if (preserve_write)
+				ptent = pte_mkwrite(ptent);
 
 			/* Avoid taking write faults for known dirty pages */
 			if (dirty_accountable && pte_dirty(ptent) &&
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 45e187b..644bcb6 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -857,8 +857,11 @@
 	 *                   bw * elapsed + write_bandwidth * (period - elapsed)
 	 * write_bandwidth = ---------------------------------------------------
 	 *                                          period
+	 *
+	 * @written may have decreased due to account_page_redirty().
+	 * Avoid underflowing @bw calculation.
 	 */
-	bw = written - bdi->written_stamp;
+	bw = written - min(written, bdi->written_stamp);
 	bw *= HZ;
 	if (unlikely(elapsed > period)) {
 		do_div(bw, elapsed);
@@ -922,7 +925,7 @@
 				    unsigned long now)
 {
 	static DEFINE_SPINLOCK(dirty_lock);
-	static unsigned long update_time;
+	static unsigned long update_time = INITIAL_JIFFIES;
 
 	/*
 	 * check locklessly first to optimize away locking for the most time
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 72f5ac3..755a42c 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -103,6 +103,7 @@
 
 			if (!is_migrate_isolate_page(buddy)) {
 				__isolate_free_page(page, order);
+				kernel_map_pages(page, (1 << order), 1);
 				set_page_refcounted(page);
 				isolated_page = page;
 			}
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 75c1f28..29f2f8b 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -265,8 +265,15 @@
 			vma = vma->vm_next;
 
 			err = walk_page_test(start, next, walk);
-			if (err > 0)
+			if (err > 0) {
+				/*
+				 * positive return values are purely for
+				 * controlling the pagewalk, so should never
+				 * be passed to the callers.
+				 */
+				err = 0;
 				continue;
+			}
 			if (err < 0)
 				break;
 		}
diff --git a/mm/rmap.c b/mm/rmap.c
index 5e3e090..c161a14 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -287,6 +287,13 @@
 	return 0;
 
  enomem_failure:
+	/*
+	 * dst->anon_vma is dropped here otherwise its degree can be incorrectly
+	 * decremented in unlink_anon_vmas().
+	 * We can safely do this because callers of anon_vma_clone() don't care
+	 * about dst->anon_vma if anon_vma_clone() failed.
+	 */
+	dst->anon_vma = NULL;
 	unlink_anon_vmas(dst);
 	return -ENOMEM;
 }
diff --git a/mm/slub.c b/mm/slub.c
index 6832c4e..82c4737 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2449,7 +2449,8 @@
 	do {
 		tid = this_cpu_read(s->cpu_slab->tid);
 		c = raw_cpu_ptr(s->cpu_slab);
-	} while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid));
+	} while (IS_ENABLED(CONFIG_PREEMPT) &&
+		 unlikely(tid != READ_ONCE(c->tid)));
 
 	/*
 	 * Irqless object alloc/free algorithm used here depends on sequence
@@ -2718,7 +2719,8 @@
 	do {
 		tid = this_cpu_read(s->cpu_slab->tid);
 		c = raw_cpu_ptr(s->cpu_slab);
-	} while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid));
+	} while (IS_ENABLED(CONFIG_PREEMPT) &&
+		 unlikely(tid != READ_ONCE(c->tid)));
 
 	/* Same with comment on barrier() in slab_alloc_node() */
 	barrier();
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index d8e376a..36a1a73 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -658,14 +658,30 @@
 static void p9_virtio_remove(struct virtio_device *vdev)
 {
 	struct virtio_chan *chan = vdev->priv;
-
-	if (chan->inuse)
-		p9_virtio_close(chan->client);
-	vdev->config->del_vqs(vdev);
+	unsigned long warning_time;
 
 	mutex_lock(&virtio_9p_lock);
+
+	/* Remove self from list so we don't get new users. */
 	list_del(&chan->chan_list);
+	warning_time = jiffies;
+
+	/* Wait for existing users to close. */
+	while (chan->inuse) {
+		mutex_unlock(&virtio_9p_lock);
+		msleep(250);
+		if (time_after(jiffies, warning_time + 10 * HZ)) {
+			dev_emerg(&vdev->dev,
+				  "p9_virtio_remove: waiting for device in use.\n");
+			warning_time = jiffies;
+		}
+		mutex_lock(&virtio_9p_lock);
+	}
+
 	mutex_unlock(&virtio_9p_lock);
+
+	vdev->config->del_vqs(vdev);
+
 	sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
 	kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
 	kfree(chan->tag);
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index b087d27..1849d96 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -563,6 +563,8 @@
 	 */
 	del_nbp(p);
 
+	dev_set_mtu(br->dev, br_min_mtu(br));
+
 	spin_lock_bh(&br->lock);
 	changed_addr = br_stp_recalculate_bridge_id(br);
 	spin_unlock_bh(&br->lock);
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 769b185..a6e2da0 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -281,7 +281,7 @@
 	int copylen;
 
 	ret = -EOPNOTSUPP;
-	if (m->msg_flags&MSG_OOB)
+	if (flags & MSG_OOB)
 		goto read_error;
 
 	skb = skb_recv_datagram(sk, flags, 0 , &ret);
diff --git a/net/compat.c b/net/compat.c
index 94d3d5e..f7bd286 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -49,6 +49,13 @@
 	    __get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
 	    __get_user(kmsg->msg_flags, &umsg->msg_flags))
 		return -EFAULT;
+
+	if (!uaddr)
+		kmsg->msg_namelen = 0;
+
+	if (kmsg->msg_namelen < 0)
+		return -EINVAL;
+
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
 		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 	kmsg->msg_control = compat_ptr(tmp3);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 25b4b5d..ee0608b 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2166,28 +2166,28 @@
 			}
 		}
 		err = rtnl_configure_link(dev, ifm);
-		if (err < 0) {
-			if (ops->newlink) {
-				LIST_HEAD(list_kill);
-
-				ops->dellink(dev, &list_kill);
-				unregister_netdevice_many(&list_kill);
-			} else {
-				unregister_netdevice(dev);
-			}
-			goto out;
-		}
-
+		if (err < 0)
+			goto out_unregister;
 		if (link_net) {
 			err = dev_change_net_namespace(dev, dest_net, ifname);
 			if (err < 0)
-				unregister_netdevice(dev);
+				goto out_unregister;
 		}
 out:
 		if (link_net)
 			put_net(link_net);
 		put_net(dest_net);
 		return err;
+out_unregister:
+		if (ops->newlink) {
+			LIST_HEAD(list_kill);
+
+			ops->dellink(dev, &list_kill);
+			unregister_netdevice_many(&list_kill);
+		} else {
+			unregister_netdevice(dev);
+		}
+		goto out;
 	}
 }
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f805078..8e4ac97 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3733,9 +3733,13 @@
 		     struct sock *sk, int tstype)
 {
 	struct sk_buff *skb;
-	bool tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
+	bool tsonly;
 
-	if (!sk || !skb_may_tx_timestamp(sk, tsonly))
+	if (!sk)
+		return;
+
+	tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
+	if (!skb_may_tx_timestamp(sk, tsonly))
 		return;
 
 	if (tsonly)
@@ -4173,7 +4177,7 @@
 	skb->ignore_df = 0;
 	skb_dst_drop(skb);
 	skb->mark = 0;
-	skb->sender_cpu = 0;
+	skb_sender_cpu_clear(skb);
 	skb_init_secmark(skb);
 	secpath_reset(skb);
 	nf_reset(skb);
diff --git a/net/core/sock.c b/net/core/sock.c
index 93c8b20..78e89eb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1655,6 +1655,10 @@
 }
 EXPORT_SYMBOL(sock_rfree);
 
+/*
+ * Buffer destructor for skbs that are not used directly in read or write
+ * path, e.g. for error handler skbs. Automatically called from kfree_skb.
+ */
 void sock_efree(struct sk_buff *skb)
 {
 	sock_put(skb->sk);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 4334248..8ce351f 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -25,6 +25,8 @@
 static int zero = 0;
 static int one = 1;
 static int ushort_max = USHRT_MAX;
+static int min_sndbuf = SOCK_MIN_SNDBUF;
+static int min_rcvbuf = SOCK_MIN_RCVBUF;
 
 static int net_msg_warn;	/* Unused, but still a sysctl */
 
@@ -237,7 +239,7 @@
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_sndbuf,
 	},
 	{
 		.procname	= "rmem_max",
@@ -245,7 +247,7 @@
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_rcvbuf,
 	},
 	{
 		.procname	= "wmem_default",
@@ -253,7 +255,7 @@
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_sndbuf,
 	},
 	{
 		.procname	= "rmem_default",
@@ -261,7 +263,7 @@
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
+		.extra1		= &min_rcvbuf,
 	},
 	{
 		.procname	= "dev_weight",
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 14d02ea..3e44b9b 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -268,6 +268,7 @@
 		release_sock(sk);
 		if (reqsk_queue_empty(&icsk->icsk_accept_queue))
 			timeo = schedule_timeout(timeo);
+		sched_annotate_sleep();
 		lock_sock(sk);
 		err = 0;
 		if (!reqsk_queue_empty(&icsk->icsk_accept_queue))
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 81751f1..592aff3 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -71,6 +71,20 @@
 	mutex_unlock(&inet_diag_table_mutex);
 }
 
+static size_t inet_sk_attr_size(void)
+{
+	return	  nla_total_size(sizeof(struct tcp_info))
+		+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
+		+ nla_total_size(1) /* INET_DIAG_TOS */
+		+ nla_total_size(1) /* INET_DIAG_TCLASS */
+		+ nla_total_size(sizeof(struct inet_diag_meminfo))
+		+ nla_total_size(sizeof(struct inet_diag_msg))
+		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
+		+ nla_total_size(TCP_CA_NAME_MAX)
+		+ nla_total_size(sizeof(struct tcpvegas_info))
+		+ 64;
+}
+
 int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			      struct sk_buff *skb, struct inet_diag_req_v2 *req,
 			      struct user_namespace *user_ns,		      	
@@ -326,9 +340,7 @@
 	if (err)
 		goto out;
 
-	rep = nlmsg_new(sizeof(struct inet_diag_msg) +
-			sizeof(struct inet_diag_meminfo) +
-			sizeof(struct tcp_info) + 64, GFP_KERNEL);
+	rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL);
 	if (!rep) {
 		err = -ENOMEM;
 		goto out;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 787b3c2..d9bc28a 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -67,6 +67,7 @@
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
+	skb_sender_cpu_clear(skb);
 	return dst_output(skb);
 }
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 99e810f..cf5e82f 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -272,9 +272,9 @@
 		    &chainname, &comment, &rulenum) != 0)
 			break;
 
-	nf_log_packet(net, AF_INET, hook, skb, in, out, &trace_loginfo,
-		      "TRACE: %s:%s:%s:%u ",
-		      tablename, chainname, comment, rulenum);
+	nf_log_trace(net, AF_INET, hook, skb, in, out, &trace_loginfo,
+		     "TRACE: %s:%s:%s:%u ",
+		     tablename, chainname, comment, rulenum);
 }
 #endif
 
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index d694088..62856e1 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -378,6 +378,12 @@
  */
 void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked)
 {
+	/* If credits accumulated at a higher w, apply them gently now. */
+	if (tp->snd_cwnd_cnt >= w) {
+		tp->snd_cwnd_cnt = 0;
+		tp->snd_cwnd++;
+	}
+
 	tp->snd_cwnd_cnt += acked;
 	if (tp->snd_cwnd_cnt >= w) {
 		u32 delta = tp->snd_cwnd_cnt / w;
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 4b276d1..06d3d66 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -306,8 +306,10 @@
 		}
 	}
 
-	if (ca->cnt == 0)			/* cannot be zero */
-		ca->cnt = 1;
+	/* The maximum rate of cwnd increase CUBIC allows is 1 packet per
+	 * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT.
+	 */
+	ca->cnt = max(ca->cnt, 2U);
 }
 
 static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a2a796c..1db253e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2773,15 +2773,11 @@
 	} else {
 		/* Socket is locked, keep trying until memory is available. */
 		for (;;) {
-			skb = alloc_skb_fclone(MAX_TCP_HEADER,
-					       sk->sk_allocation);
+			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
 			if (skb)
 				break;
 			yield();
 		}
-
-		/* Reserve space for headers and prepare control bits. */
-		skb_reserve(skb, MAX_TCP_HEADER);
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		tcp_init_nondata_skb(skb, tp->write_seq,
 				     TCPHDR_ACK | TCPHDR_FIN);
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index d5f6bd9..dab7381 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -63,6 +63,7 @@
 		return err;
 
 	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
+	skb->protocol = htons(ETH_P_IP);
 
 	return x->outer_mode->output2(x, skb);
 }
@@ -71,7 +72,6 @@
 int xfrm4_output_finish(struct sk_buff *skb)
 {
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-	skb->protocol = htons(ETH_P_IP);
 
 #ifdef CONFIG_NETFILTER
 	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index b4d5e1d..27ca796 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -104,6 +104,7 @@
 				goto again;
 			flp6->saddr = saddr;
 		}
+		err = rt->dst.error;
 		goto out;
 	}
 again:
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 0a04a37..7e80b61 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -318,6 +318,7 @@
 
 static inline int ip6_forward_finish(struct sk_buff *skb)
 {
+	skb_sender_cpu_clear(skb);
 	return dst_output(skb);
 }
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 266a264..ddd94ec 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -314,7 +314,7 @@
  *   Create tunnel matching given parameters.
  *
  * Return:
- *   created tunnel or NULL
+ *   created tunnel or error pointer
  **/
 
 static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
@@ -322,7 +322,7 @@
 	struct net_device *dev;
 	struct ip6_tnl *t;
 	char name[IFNAMSIZ];
-	int err;
+	int err = -ENOMEM;
 
 	if (p->name[0])
 		strlcpy(name, p->name, IFNAMSIZ);
@@ -348,7 +348,7 @@
 failed_free:
 	ip6_dev_free(dev);
 failed:
-	return NULL;
+	return ERR_PTR(err);
 }
 
 /**
@@ -362,7 +362,7 @@
  *   tunnel device is created and registered for use.
  *
  * Return:
- *   matching tunnel or NULL
+ *   matching tunnel or error pointer
  **/
 
 static struct ip6_tnl *ip6_tnl_locate(struct net *net,
@@ -380,13 +380,13 @@
 		if (ipv6_addr_equal(local, &t->parms.laddr) &&
 		    ipv6_addr_equal(remote, &t->parms.raddr)) {
 			if (create)
-				return NULL;
+				return ERR_PTR(-EEXIST);
 
 			return t;
 		}
 	}
 	if (!create)
-		return NULL;
+		return ERR_PTR(-ENODEV);
 	return ip6_tnl_create(net, p);
 }
 
@@ -1420,7 +1420,7 @@
 			}
 			ip6_tnl_parm_from_user(&p1, &p);
 			t = ip6_tnl_locate(net, &p1, 0);
-			if (t == NULL)
+			if (IS_ERR(t))
 				t = netdev_priv(dev);
 		} else {
 			memset(&p, 0, sizeof(p));
@@ -1445,7 +1445,7 @@
 		ip6_tnl_parm_from_user(&p1, &p);
 		t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL);
 		if (cmd == SIOCCHGTUNNEL) {
-			if (t != NULL) {
+			if (!IS_ERR(t)) {
 				if (t->dev != dev) {
 					err = -EEXIST;
 					break;
@@ -1457,14 +1457,15 @@
 			else
 				err = ip6_tnl_update(t, &p1);
 		}
-		if (t) {
+		if (!IS_ERR(t)) {
 			err = 0;
 			ip6_tnl_parm_to_user(&p, &t->parms);
 			if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
 				err = -EFAULT;
 
-		} else
-			err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
+		} else {
+			err = PTR_ERR(t);
+		}
 		break;
 	case SIOCDELTUNNEL:
 		err = -EPERM;
@@ -1478,7 +1479,7 @@
 			err = -ENOENT;
 			ip6_tnl_parm_from_user(&p1, &p);
 			t = ip6_tnl_locate(net, &p1, 0);
-			if (t == NULL)
+			if (IS_ERR(t))
 				break;
 			err = -EPERM;
 			if (t->dev == ip6n->fb_tnl_dev)
@@ -1672,12 +1673,13 @@
 			   struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net *net = dev_net(dev);
-	struct ip6_tnl *nt;
+	struct ip6_tnl *nt, *t;
 
 	nt = netdev_priv(dev);
 	ip6_tnl_netlink_parms(data, &nt->parms);
 
-	if (ip6_tnl_locate(net, &nt->parms, 0))
+	t = ip6_tnl_locate(net, &nt->parms, 0);
+	if (!IS_ERR(t))
 		return -EEXIST;
 
 	return ip6_tnl_create2(dev);
@@ -1697,8 +1699,7 @@
 	ip6_tnl_netlink_parms(data, &p);
 
 	t = ip6_tnl_locate(net, &p, 0);
-
-	if (t) {
+	if (!IS_ERR(t)) {
 		if (t->dev != dev)
 			return -EEXIST;
 	} else
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index e080fbb..bb00c6f 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -298,9 +298,9 @@
 		    &chainname, &comment, &rulenum) != 0)
 			break;
 
-	nf_log_packet(net, AF_INET6, hook, skb, in, out, &trace_loginfo,
-		      "TRACE: %s:%s:%s:%u ",
-		      tablename, chainname, comment, rulenum);
+	nf_log_trace(net, AF_INET6, hook, skb, in, out, &trace_loginfo,
+		     "TRACE: %s:%s:%s:%u ",
+		     tablename, chainname, comment, rulenum);
 }
 #endif
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index ab889bb..be2c0ba 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -112,11 +112,9 @@
 		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
 		fptr->nexthdr = nexthdr;
 		fptr->reserved = 0;
-		if (skb_shinfo(skb)->ip6_frag_id)
-			fptr->identification = skb_shinfo(skb)->ip6_frag_id;
-		else
-			ipv6_select_ident(fptr,
-					  (struct rt6_info *)skb_dst(skb));
+		if (!skb_shinfo(skb)->ip6_frag_id)
+			ipv6_proxy_select_ident(skb);
+		fptr->identification = skb_shinfo(skb)->ip6_frag_id;
 
 		/* Fragment the skb. ipv6 header and the remaining fields of the
 		 * fragment header are updated in ipv6_gso_segment()
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index ca3f29b..010f8bd 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -114,6 +114,7 @@
 		return err;
 
 	skb->ignore_df = 1;
+	skb->protocol = htons(ETH_P_IPV6);
 
 	return x->outer_mode->output2(x, skb);
 }
@@ -122,7 +123,6 @@
 int xfrm6_output_finish(struct sk_buff *skb)
 {
 	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
-	skb->protocol = htons(ETH_P_IPV6);
 
 #ifdef CONFIG_NETFILTER
 	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 48bf5a0..8d2d01b 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -200,6 +200,7 @@
 
 #if IS_ENABLED(CONFIG_IPV6_MIP6)
 		case IPPROTO_MH:
+			offset += ipv6_optlen(exthdr);
 			if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) {
 				struct ip6_mh *mh;
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 3afe368..8d53d65 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -58,13 +58,24 @@
 #define IEEE80211_UNSET_POWER_LEVEL	INT_MIN
 
 /*
- * Some APs experience problems when working with U-APSD. Decrease the
- * probability of that happening by using legacy mode for all ACs but VO.
- * The AP that caused us trouble was a Cisco 4410N. It ignores our
- * setting, and always treats non-VO ACs as legacy.
+ * Some APs experience problems when working with U-APSD. Decreasing the
+ * probability of that happening by using legacy mode for all ACs but VO isn't
+ * enough.
+ *
+ * Cisco 4410N originally forced us to enable VO by default only because it
+ * treated non-VO ACs as legacy.
+ *
+ * However some APs (notably Netgear R7000) silently reclassify packets to
+ * different ACs. Since u-APSD ACs require trigger frames for frame retrieval
+ * clients would never see some frames (e.g. ARP responses) or would fetch them
+ * accidentally after a long time.
+ *
+ * It makes little sense to enable u-APSD queues by default because it needs
+ * userspace applications to be aware of it to actually take advantage of the
+ * possible additional powersavings. Implicitly depending on driver autotrigger
+ * frame support doesn't make much sense.
  */
-#define IEEE80211_DEFAULT_UAPSD_QUEUES \
-	IEEE80211_WMM_IE_STA_QOSINFO_AC_VO
+#define IEEE80211_DEFAULT_UAPSD_QUEUES 0
 
 #define IEEE80211_DEFAULT_MAX_SP_LEN		\
 	IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL
@@ -453,6 +464,7 @@
 	unsigned int flags;
 
 	bool csa_waiting_bcn;
+	bool csa_ignored_same_chan;
 
 	bool beacon_crc_valid;
 	u32 beacon_crc;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 10ac632..142f66a 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1150,6 +1150,17 @@
 		return;
 	}
 
+	if (cfg80211_chandef_identical(&csa_ie.chandef,
+				       &sdata->vif.bss_conf.chandef)) {
+		if (ifmgd->csa_ignored_same_chan)
+			return;
+		sdata_info(sdata,
+			   "AP %pM tries to chanswitch to same channel, ignore\n",
+			   ifmgd->associated->bssid);
+		ifmgd->csa_ignored_same_chan = true;
+		return;
+	}
+
 	mutex_lock(&local->mtx);
 	mutex_lock(&local->chanctx_mtx);
 	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
@@ -1210,6 +1221,7 @@
 	sdata->vif.csa_active = true;
 	sdata->csa_chandef = csa_ie.chandef;
 	sdata->csa_block_tx = csa_ie.mode;
+	ifmgd->csa_ignored_same_chan = false;
 
 	if (sdata->csa_block_tx)
 		ieee80211_stop_vif_queues(local, sdata,
@@ -2090,6 +2102,7 @@
 
 	sdata->vif.csa_active = false;
 	ifmgd->csa_waiting_bcn = false;
+	ifmgd->csa_ignored_same_chan = false;
 	if (sdata->csa_block_tx) {
 		ieee80211_wake_vif_queues(local, sdata,
 					  IEEE80211_QUEUE_STOP_REASON_CSA);
@@ -3204,7 +3217,8 @@
 	(1ULL << WLAN_EID_CHANNEL_SWITCH) |
 	(1ULL << WLAN_EID_PWR_CONSTRAINT) |
 	(1ULL << WLAN_EID_HT_CAPABILITY) |
-	(1ULL << WLAN_EID_HT_OPERATION);
+	(1ULL << WLAN_EID_HT_OPERATION) |
+	(1ULL << WLAN_EID_EXT_CHANSWITCH_ANN);
 
 static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 				     struct ieee80211_mgmt *mgmt, size_t len,
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 1101563..944bdc0 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2214,6 +2214,9 @@
 	hdr = (struct ieee80211_hdr *) skb->data;
 	mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen);
 
+	if (ieee80211_drop_unencrypted(rx, hdr->frame_control))
+		return RX_DROP_MONITOR;
+
 	/* frame is in RMC, don't forward */
 	if (ieee80211_is_data(hdr->frame_control) &&
 	    is_multicast_ether_addr(hdr->addr1) &&
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 8428f4a..747bdcf 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3178,7 +3178,7 @@
 		wdev_iter = &sdata_iter->wdev;
 
 		if (sdata_iter == sdata ||
-		    rcu_access_pointer(sdata_iter->vif.chanctx_conf) == NULL ||
+		    !ieee80211_sdata_running(sdata_iter) ||
 		    local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype))
 			continue;
 
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 0d8448f..675d12c 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -212,6 +212,30 @@
 }
 EXPORT_SYMBOL(nf_log_packet);
 
+void nf_log_trace(struct net *net,
+		  u_int8_t pf,
+		  unsigned int hooknum,
+		  const struct sk_buff *skb,
+		  const struct net_device *in,
+		  const struct net_device *out,
+		  const struct nf_loginfo *loginfo, const char *fmt, ...)
+{
+	va_list args;
+	char prefix[NF_LOG_PREFIXLEN];
+	const struct nf_logger *logger;
+
+	rcu_read_lock();
+	logger = rcu_dereference(net->nf.nf_loggers[pf]);
+	if (logger) {
+		va_start(args, fmt);
+		vsnprintf(prefix, sizeof(prefix), fmt, args);
+		va_end(args);
+		logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(nf_log_trace);
+
 #define S_SIZE (1024 - (sizeof(unsigned int) + 1))
 
 struct nf_log_buf {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 6ab7779..ac1a952 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1225,7 +1225,10 @@
 
 	if (nla[NFTA_CHAIN_POLICY]) {
 		if ((chain != NULL &&
-		    !(chain->flags & NFT_BASE_CHAIN)) ||
+		    !(chain->flags & NFT_BASE_CHAIN)))
+			return -EOPNOTSUPP;
+
+		if (chain == NULL &&
 		    nla[NFTA_CHAIN_HOOK] == NULL)
 			return -EOPNOTSUPP;
 
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 3b90eb2..2d298dc 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -94,10 +94,10 @@
 {
 	struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
 
-	nf_log_packet(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in,
-		      pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ",
-		      chain->table->name, chain->name, comments[type],
-		      rulenum);
+	nf_log_trace(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in,
+		     pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ",
+		     chain->table->name, chain->name, comments[type],
+		     rulenum);
 }
 
 unsigned int
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index a5599fc..54330fb 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -77,6 +77,9 @@
 	if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM])
 		return -EINVAL;
 
+	/* Not all fields are initialized so first zero the tuple */
+	memset(tuple, 0, sizeof(struct nf_conntrack_tuple));
+
 	tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM]));
 	tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]);
 
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 213584c..65f3e2b 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -133,6 +133,9 @@
 		entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
 		break;
 	case AF_INET6:
+		if (proto)
+			entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
 		entry->e6.ipv6.proto = proto;
 		entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
 		break;
@@ -344,6 +347,9 @@
 		entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
 		break;
 	case AF_INET6:
+		if (proto)
+			entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
 		entry->e6.ipv6.proto = proto;
 		entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
 		break;
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index c82df0a..37c15e6 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -153,6 +153,8 @@
 				iter->err = err;
 				goto out;
 			}
+
+			continue;
 		}
 
 		if (iter->count < iter->skip)
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index ef8a926..50e1e5a 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -513,8 +513,8 @@
 {
 	const struct ip6t_ip6 *i = par->entryinfo;
 
-	if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP)
-	    && !(i->flags & IP6T_INV_PROTO))
+	if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) &&
+	    !(i->invflags & IP6T_INV_PROTO))
 		return 0;
 
 	pr_info("Can be used only in combination with "
diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c
index a817705..dba8d08 100644
--- a/net/rds/iw_rdma.c
+++ b/net/rds/iw_rdma.c
@@ -88,7 +88,9 @@
 			int *unpinned);
 static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr);
 
-static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id)
+static int rds_iw_get_device(struct sockaddr_in *src, struct sockaddr_in *dst,
+			     struct rds_iw_device **rds_iwdev,
+			     struct rdma_cm_id **cm_id)
 {
 	struct rds_iw_device *iwdev;
 	struct rds_iw_cm_id *i_cm_id;
@@ -112,15 +114,15 @@
 				src_addr->sin_port,
 				dst_addr->sin_addr.s_addr,
 				dst_addr->sin_port,
-				rs->rs_bound_addr,
-				rs->rs_bound_port,
-				rs->rs_conn_addr,
-				rs->rs_conn_port);
+				src->sin_addr.s_addr,
+				src->sin_port,
+				dst->sin_addr.s_addr,
+				dst->sin_port);
 #ifdef WORKING_TUPLE_DETECTION
-			if (src_addr->sin_addr.s_addr == rs->rs_bound_addr &&
-			    src_addr->sin_port == rs->rs_bound_port &&
-			    dst_addr->sin_addr.s_addr == rs->rs_conn_addr &&
-			    dst_addr->sin_port == rs->rs_conn_port) {
+			if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr &&
+			    src_addr->sin_port == src->sin_port &&
+			    dst_addr->sin_addr.s_addr == dst->sin_addr.s_addr &&
+			    dst_addr->sin_port == dst->sin_port) {
 #else
 			/* FIXME - needs to compare the local and remote
 			 * ipaddr/port tuple, but the ipaddr is the only
@@ -128,7 +130,7 @@
 			 * zero'ed.  It doesn't appear to be properly populated
 			 * during connection setup...
 			 */
-			if (src_addr->sin_addr.s_addr == rs->rs_bound_addr) {
+			if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr) {
 #endif
 				spin_unlock_irq(&iwdev->spinlock);
 				*rds_iwdev = iwdev;
@@ -180,19 +182,13 @@
 {
 	struct sockaddr_in *src_addr, *dst_addr;
 	struct rds_iw_device *rds_iwdev_old;
-	struct rds_sock rs;
 	struct rdma_cm_id *pcm_id;
 	int rc;
 
 	src_addr = (struct sockaddr_in *)&cm_id->route.addr.src_addr;
 	dst_addr = (struct sockaddr_in *)&cm_id->route.addr.dst_addr;
 
-	rs.rs_bound_addr = src_addr->sin_addr.s_addr;
-	rs.rs_bound_port = src_addr->sin_port;
-	rs.rs_conn_addr = dst_addr->sin_addr.s_addr;
-	rs.rs_conn_port = dst_addr->sin_port;
-
-	rc = rds_iw_get_device(&rs, &rds_iwdev_old, &pcm_id);
+	rc = rds_iw_get_device(src_addr, dst_addr, &rds_iwdev_old, &pcm_id);
 	if (rc)
 		rds_iw_remove_cm_id(rds_iwdev, cm_id);
 
@@ -598,9 +594,17 @@
 	struct rds_iw_device *rds_iwdev;
 	struct rds_iw_mr *ibmr = NULL;
 	struct rdma_cm_id *cm_id;
+	struct sockaddr_in src = {
+		.sin_addr.s_addr = rs->rs_bound_addr,
+		.sin_port = rs->rs_bound_port,
+	};
+	struct sockaddr_in dst = {
+		.sin_addr.s_addr = rs->rs_conn_addr,
+		.sin_port = rs->rs_conn_port,
+	};
 	int ret;
 
-	ret = rds_iw_get_device(rs, &rds_iwdev, &cm_id);
+	ret = rds_iw_get_device(&src, &dst, &rds_iwdev, &cm_id);
 	if (ret || !cm_id) {
 		ret = -ENODEV;
 		goto out;
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index 4575485..19a5606 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -87,7 +87,7 @@
 		if (!skb) {
 			/* nothing remains on the queue */
 			if (copied &&
-			    (msg->msg_flags & MSG_PEEK || timeo == 0))
+			    (flags & MSG_PEEK || timeo == 0))
 				goto out;
 
 			/* wait for a message to turn up */
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 82c5d7f..5f6288f 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -25,21 +25,41 @@
 		   struct tcf_result *res)
 {
 	struct tcf_bpf *b = a->priv;
-	int action;
-	int filter_res;
+	int action, filter_res;
 
 	spin_lock(&b->tcf_lock);
+
 	b->tcf_tm.lastuse = jiffies;
 	bstats_update(&b->tcf_bstats, skb);
-	action = b->tcf_action;
 
 	filter_res = BPF_PROG_RUN(b->filter, skb);
-	if (filter_res == 0) {
-		/* Return code 0 from the BPF program
-		 * is being interpreted as a drop here.
-		 */
-		action = TC_ACT_SHOT;
+
+	/* A BPF program may overwrite the default action opcode.
+	 * Similarly as in cls_bpf, if filter_res == -1 we use the
+	 * default action specified from tc.
+	 *
+	 * In case a different well-known TC_ACT opcode has been
+	 * returned, it will overwrite the default one.
+	 *
+	 * For everything else that is unkown, TC_ACT_UNSPEC is
+	 * returned.
+	 */
+	switch (filter_res) {
+	case TC_ACT_PIPE:
+	case TC_ACT_RECLASSIFY:
+	case TC_ACT_OK:
+		action = filter_res;
+		break;
+	case TC_ACT_SHOT:
+		action = filter_res;
 		b->tcf_qstats.drops++;
+		break;
+	case TC_ACT_UNSPEC:
+		action = b->tcf_action;
+		break;
+	default:
+		action = TC_ACT_UNSPEC;
+		break;
 	}
 
 	spin_unlock(&b->tcf_lock);
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 09487af..95fdf4e 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -78,8 +78,11 @@
 	struct tc_u_common	*tp_c;
 	int			refcnt;
 	unsigned int		divisor;
-	struct tc_u_knode __rcu	*ht[1];
 	struct rcu_head		rcu;
+	/* The 'ht' field MUST be the last field in structure to allow for
+	 * more entries allocated at end of structure.
+	 */
+	struct tc_u_knode __rcu	*ht[1];
 };
 
 struct tc_u_common {
diff --git a/net/socket.c b/net/socket.c
index bbedbfc..245330c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1702,6 +1702,8 @@
 
 	if (len > INT_MAX)
 		len = INT_MAX;
+	if (unlikely(!access_ok(VERIFY_READ, buff, len)))
+		return -EFAULT;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
 		goto out;
@@ -1760,6 +1762,8 @@
 
 	if (size > INT_MAX)
 		size = INT_MAX;
+	if (unlikely(!access_ok(VERIFY_WRITE, ubuf, size)))
+		return -EFAULT;
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
 		goto out;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index be25015..b6f84f6 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4400,6 +4400,16 @@
 	if (parse_station_flags(info, dev->ieee80211_ptr->iftype, &params))
 		return -EINVAL;
 
+	/* HT/VHT requires QoS, but if we don't have that just ignore HT/VHT
+	 * as userspace might just pass through the capabilities from the IEs
+	 * directly, rather than enforcing this restriction and returning an
+	 * error in this case.
+	 */
+	if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) {
+		params.ht_capa = NULL;
+		params.vht_capa = NULL;
+	}
+
 	/* When you run into this, adjust the code below for the new flag */
 	BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7);
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index cee479b..638af06 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2269,11 +2269,9 @@
 		 * have the xfrm_state's. We need to wait for KM to
 		 * negotiate new SA's or bail out with error.*/
 		if (net->xfrm.sysctl_larval_drop) {
-			dst_release(dst);
-			xfrm_pols_put(pols, drop_pols);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
-
-			return ERR_PTR(-EREMOTE);
+			err = -EREMOTE;
+			goto error;
 		}
 
 		err = -EAGAIN;
@@ -2324,7 +2322,8 @@
 error:
 	dst_release(dst);
 dropdst:
-	dst_release(dst_orig);
+	if (!(flags & XFRM_LOOKUP_KEEP_DST_REF))
+		dst_release(dst_orig);
 	xfrm_pols_put(pols, drop_pols);
 	return ERR_PTR(err);
 }
@@ -2338,7 +2337,8 @@
 				    struct sock *sk, int flags)
 {
 	struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk,
-					    flags | XFRM_LOOKUP_QUEUE);
+					    flags | XFRM_LOOKUP_QUEUE |
+					    XFRM_LOOKUP_KEEP_DST_REF);
 
 	if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE)
 		return make_blackhole(net, dst_orig->ops->family, dst_orig);
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 1684bcc..5fde343 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -152,7 +152,7 @@
 		goto out;
 
 	/* No partial writes. */
-	length = EINVAL;
+	length = -EINVAL;
 	if (*ppos != 0)
 		goto out;
 
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index fe18071..8ec5289 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -687,13 +687,30 @@
 	return val;
 }
 
+/* is this a stereo widget or a stereo-to-mono mix? */
+static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid, int dir)
+{
+	unsigned int wcaps = get_wcaps(codec, nid);
+	hda_nid_t conn;
+
+	if (wcaps & AC_WCAP_STEREO)
+		return true;
+	if (dir != HDA_INPUT || get_wcaps_type(wcaps) != AC_WID_AUD_MIX)
+		return false;
+	if (snd_hda_get_num_conns(codec, nid) != 1)
+		return false;
+	if (snd_hda_get_connections(codec, nid, &conn, 1) < 0)
+		return false;
+	return !!(get_wcaps(codec, conn) & AC_WCAP_STEREO);
+}
+
 /* initialize the amp value (only at the first time) */
 static void init_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx)
 {
 	unsigned int caps = query_amp_caps(codec, nid, dir);
 	int val = get_amp_val_to_activate(codec, nid, dir, caps, false);
 
-	if (get_wcaps(codec, nid) & AC_WCAP_STEREO)
+	if (is_stereo_amps(codec, nid, dir))
 		snd_hda_codec_amp_init_stereo(codec, nid, dir, idx, 0xff, val);
 	else
 		snd_hda_codec_amp_init(codec, nid, 0, dir, idx, 0xff, val);
@@ -703,7 +720,7 @@
 static int update_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx,
 		      unsigned int mask, unsigned int val)
 {
-	if (get_wcaps(codec, nid) & AC_WCAP_STEREO)
+	if (is_stereo_amps(codec, nid, dir))
 		return snd_hda_codec_amp_stereo(codec, nid, dir, idx,
 						mask, val);
 	else
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 4ca3d5d..a8a1e14 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1989,7 +1989,7 @@
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
 	/* Sunrise Point */
 	{ PCI_DEVICE(0x8086, 0xa170),
-	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
 	/* Sunrise Point-LP */
 	{ PCI_DEVICE(0x8086, 0x9d70),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
diff --git a/sound/pci/hda/hda_proc.c b/sound/pci/hda/hda_proc.c
index ce5a6da..05e19f7 100644
--- a/sound/pci/hda/hda_proc.c
+++ b/sound/pci/hda/hda_proc.c
@@ -134,13 +134,38 @@
 		    (caps & AC_AMPCAP_MUTE) >> AC_AMPCAP_MUTE_SHIFT);
 }
 
+/* is this a stereo widget or a stereo-to-mono mix? */
+static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid,
+			   int dir, unsigned int wcaps, int indices)
+{
+	hda_nid_t conn;
+
+	if (wcaps & AC_WCAP_STEREO)
+		return true;
+	/* check for a stereo-to-mono mix; it must be:
+	 * only a single connection, only for input, and only a mixer widget
+	 */
+	if (indices != 1 || dir != HDA_INPUT ||
+	    get_wcaps_type(wcaps) != AC_WID_AUD_MIX)
+		return false;
+
+	if (snd_hda_get_raw_connections(codec, nid, &conn, 1) < 0)
+		return false;
+	/* the connection source is a stereo? */
+	wcaps = snd_hda_param_read(codec, conn, AC_PAR_AUDIO_WIDGET_CAP);
+	return !!(wcaps & AC_WCAP_STEREO);
+}
+
 static void print_amp_vals(struct snd_info_buffer *buffer,
 			   struct hda_codec *codec, hda_nid_t nid,
-			   int dir, int stereo, int indices)
+			   int dir, unsigned int wcaps, int indices)
 {
 	unsigned int val;
+	bool stereo;
 	int i;
 
+	stereo = is_stereo_amps(codec, nid, dir, wcaps, indices);
+
 	dir = dir == HDA_OUTPUT ? AC_AMP_GET_OUTPUT : AC_AMP_GET_INPUT;
 	for (i = 0; i < indices; i++) {
 		snd_iprintf(buffer, " [");
@@ -757,12 +782,10 @@
 			    (codec->single_adc_amp &&
 			     wid_type == AC_WID_AUD_IN))
 				print_amp_vals(buffer, codec, nid, HDA_INPUT,
-					       wid_caps & AC_WCAP_STEREO,
-					       1);
+					       wid_caps, 1);
 			else
 				print_amp_vals(buffer, codec, nid, HDA_INPUT,
-					       wid_caps & AC_WCAP_STEREO,
-					       conn_len);
+					       wid_caps, conn_len);
 		}
 		if (wid_caps & AC_WCAP_OUT_AMP) {
 			snd_iprintf(buffer, "  Amp-Out caps: ");
@@ -771,11 +794,10 @@
 			if (wid_type == AC_WID_PIN &&
 			    codec->pin_amp_workaround)
 				print_amp_vals(buffer, codec, nid, HDA_OUTPUT,
-					       wid_caps & AC_WCAP_STEREO,
-					       conn_len);
+					       wid_caps, conn_len);
 			else
 				print_amp_vals(buffer, codec, nid, HDA_OUTPUT,
-					       wid_caps & AC_WCAP_STEREO, 1);
+					       wid_caps, 1);
 		}
 
 		switch (wid_type) {
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 526398a..7438213 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -396,7 +396,7 @@
 {
 	/* We currently only handle front, HP */
 	static hda_nid_t pins[] = {
-		0x0f, 0x10, 0x14, 0x15, 0
+		0x0f, 0x10, 0x14, 0x15, 0x17, 0
 	};
 	hda_nid_t *p;
 	for (p = pins; *p; p++)
@@ -5036,6 +5036,7 @@
 	SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x501e, "Thinkpad L440", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
 	SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
diff --git a/sound/soc/codecs/adav80x.c b/sound/soc/codecs/adav80x.c
index b67480f..4373ada 100644
--- a/sound/soc/codecs/adav80x.c
+++ b/sound/soc/codecs/adav80x.c
@@ -317,7 +317,7 @@
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec);
-	unsigned int deemph = ucontrol->value.enumerated.item[0];
+	unsigned int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
@@ -333,7 +333,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = adav80x->deemph;
+	ucontrol->value.integer.value[0] = adav80x->deemph;
 	return 0;
 };
 
diff --git a/sound/soc/codecs/ak4641.c b/sound/soc/codecs/ak4641.c
index 70861c7..81b54a2 100644
--- a/sound/soc/codecs/ak4641.c
+++ b/sound/soc/codecs/ak4641.c
@@ -76,7 +76,7 @@
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
@@ -92,7 +92,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = ak4641->deemph;
+	ucontrol->value.integer.value[0] = ak4641->deemph;
 	return 0;
 };
 
diff --git a/sound/soc/codecs/ak4671.c b/sound/soc/codecs/ak4671.c
index 632e89f..2a58b1d 100644
--- a/sound/soc/codecs/ak4671.c
+++ b/sound/soc/codecs/ak4671.c
@@ -343,25 +343,25 @@
 };
 
 static const struct snd_soc_dapm_route ak4671_intercon[] = {
-	{"DAC Left", "NULL", "PMPLL"},
-	{"DAC Right", "NULL", "PMPLL"},
-	{"ADC Left", "NULL", "PMPLL"},
-	{"ADC Right", "NULL", "PMPLL"},
+	{"DAC Left", NULL, "PMPLL"},
+	{"DAC Right", NULL, "PMPLL"},
+	{"ADC Left", NULL, "PMPLL"},
+	{"ADC Right", NULL, "PMPLL"},
 
 	/* Outputs */
-	{"LOUT1", "NULL", "LOUT1 Mixer"},
-	{"ROUT1", "NULL", "ROUT1 Mixer"},
-	{"LOUT2", "NULL", "LOUT2 Mix Amp"},
-	{"ROUT2", "NULL", "ROUT2 Mix Amp"},
-	{"LOUT3", "NULL", "LOUT3 Mixer"},
-	{"ROUT3", "NULL", "ROUT3 Mixer"},
+	{"LOUT1", NULL, "LOUT1 Mixer"},
+	{"ROUT1", NULL, "ROUT1 Mixer"},
+	{"LOUT2", NULL, "LOUT2 Mix Amp"},
+	{"ROUT2", NULL, "ROUT2 Mix Amp"},
+	{"LOUT3", NULL, "LOUT3 Mixer"},
+	{"ROUT3", NULL, "ROUT3 Mixer"},
 
 	{"LOUT1 Mixer", "DACL", "DAC Left"},
 	{"ROUT1 Mixer", "DACR", "DAC Right"},
 	{"LOUT2 Mixer", "DACHL", "DAC Left"},
 	{"ROUT2 Mixer", "DACHR", "DAC Right"},
-	{"LOUT2 Mix Amp", "NULL", "LOUT2 Mixer"},
-	{"ROUT2 Mix Amp", "NULL", "ROUT2 Mixer"},
+	{"LOUT2 Mix Amp", NULL, "LOUT2 Mixer"},
+	{"ROUT2 Mix Amp", NULL, "ROUT2 Mixer"},
 	{"LOUT3 Mixer", "DACSL", "DAC Left"},
 	{"ROUT3 Mixer", "DACSR", "DAC Right"},
 
@@ -381,18 +381,18 @@
 	{"LIN2", NULL, "Mic Bias"},
 	{"RIN2", NULL, "Mic Bias"},
 
-	{"ADC Left", "NULL", "LIN MUX"},
-	{"ADC Right", "NULL", "RIN MUX"},
+	{"ADC Left", NULL, "LIN MUX"},
+	{"ADC Right", NULL, "RIN MUX"},
 
 	/* Analog Loops */
-	{"LIN1 Mixing Circuit", "NULL", "LIN1"},
-	{"RIN1 Mixing Circuit", "NULL", "RIN1"},
-	{"LIN2 Mixing Circuit", "NULL", "LIN2"},
-	{"RIN2 Mixing Circuit", "NULL", "RIN2"},
-	{"LIN3 Mixing Circuit", "NULL", "LIN3"},
-	{"RIN3 Mixing Circuit", "NULL", "RIN3"},
-	{"LIN4 Mixing Circuit", "NULL", "LIN4"},
-	{"RIN4 Mixing Circuit", "NULL", "RIN4"},
+	{"LIN1 Mixing Circuit", NULL, "LIN1"},
+	{"RIN1 Mixing Circuit", NULL, "RIN1"},
+	{"LIN2 Mixing Circuit", NULL, "LIN2"},
+	{"RIN2 Mixing Circuit", NULL, "RIN2"},
+	{"LIN3 Mixing Circuit", NULL, "LIN3"},
+	{"RIN3 Mixing Circuit", NULL, "RIN3"},
+	{"LIN4 Mixing Circuit", NULL, "LIN4"},
+	{"RIN4 Mixing Circuit", NULL, "RIN4"},
 
 	{"LOUT1 Mixer", "LINL1", "LIN1 Mixing Circuit"},
 	{"ROUT1 Mixer", "RINR1", "RIN1 Mixing Circuit"},
diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c
index 79a4efc..7d3a6ac 100644
--- a/sound/soc/codecs/cs4271.c
+++ b/sound/soc/codecs/cs4271.c
@@ -286,7 +286,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = cs4271->deemph;
+	ucontrol->value.integer.value[0] = cs4271->deemph;
 	return 0;
 }
 
@@ -296,7 +296,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec);
 
-	cs4271->deemph = ucontrol->value.enumerated.item[0];
+	cs4271->deemph = ucontrol->value.integer.value[0];
 	return cs4271_set_deemph(codec);
 }
 
diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c
index ffe9617..911c26c 100644
--- a/sound/soc/codecs/da732x.c
+++ b/sound/soc/codecs/da732x.c
@@ -876,11 +876,11 @@
 
 static const struct snd_soc_dapm_route da732x_dapm_routes[] = {
 	/* Inputs */
-	{"AUX1L PGA", "NULL", "AUX1L"},
-	{"AUX1R PGA", "NULL", "AUX1R"},
+	{"AUX1L PGA", NULL, "AUX1L"},
+	{"AUX1R PGA", NULL, "AUX1R"},
 	{"MIC1 PGA", NULL, "MIC1"},
-	{"MIC2 PGA", "NULL", "MIC2"},
-	{"MIC3 PGA", "NULL", "MIC3"},
+	{"MIC2 PGA", NULL, "MIC2"},
+	{"MIC3 PGA", NULL, "MIC3"},
 
 	/* Capture Path */
 	{"ADC1 Left MUX", "MIC1", "MIC1 PGA"},
diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c
index f273251..c5f35a0 100644
--- a/sound/soc/codecs/es8328.c
+++ b/sound/soc/codecs/es8328.c
@@ -120,7 +120,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct es8328_priv *es8328 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = es8328->deemph;
+	ucontrol->value.integer.value[0] = es8328->deemph;
 	return 0;
 }
 
@@ -129,7 +129,7 @@
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct es8328_priv *es8328 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 	int ret;
 
 	if (deemph > 1)
diff --git a/sound/soc/codecs/pcm1681.c b/sound/soc/codecs/pcm1681.c
index a722a02..477e13d 100644
--- a/sound/soc/codecs/pcm1681.c
+++ b/sound/soc/codecs/pcm1681.c
@@ -118,7 +118,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = priv->deemph;
+	ucontrol->value.integer.value[0] = priv->deemph;
 
 	return 0;
 }
@@ -129,7 +129,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct pcm1681_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	priv->deemph = ucontrol->value.enumerated.item[0];
+	priv->deemph = ucontrol->value.integer.value[0];
 
 	return pcm1681_set_deemph(codec);
 }
diff --git a/sound/soc/codecs/rt286.c b/sound/soc/codecs/rt286.c
index f374840..9b541e5 100644
--- a/sound/soc/codecs/rt286.c
+++ b/sound/soc/codecs/rt286.c
@@ -1198,7 +1198,7 @@
 		.ident = "Dell Dino",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_BOARD_NAME, "0144P8")
+			DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9343")
 		}
 	},
 	{ }
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index e182e65..3593a14 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -1151,13 +1151,7 @@
 		/* Enable VDDC charge pump */
 		ana_pwr |= SGTL5000_VDDC_CHRGPMP_POWERUP;
 	} else if (vddio >= 3100 && vdda >= 3100) {
-		/*
-		 * if vddio and vddd > 3.1v,
-		 * charge pump should be clean before set ana_pwr
-		 */
-		snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
-				SGTL5000_VDDC_CHRGPMP_POWERUP, 0);
-
+		ana_pwr &= ~SGTL5000_VDDC_CHRGPMP_POWERUP;
 		/* VDDC use VDDIO rail */
 		lreg_ctrl |= SGTL5000_VDDC_ASSN_OVRD;
 		lreg_ctrl |= SGTL5000_VDDC_MAN_ASSN_VDDIO <<
diff --git a/sound/soc/codecs/sn95031.c b/sound/soc/codecs/sn95031.c
index 47b257e..82095d6c 100644
--- a/sound/soc/codecs/sn95031.c
+++ b/sound/soc/codecs/sn95031.c
@@ -538,8 +538,8 @@
 	/* speaker map */
 	{ "IHFOUTL", NULL, "Speaker Rail"},
 	{ "IHFOUTR", NULL, "Speaker Rail"},
-	{ "IHFOUTL", "NULL", "Speaker Left Playback"},
-	{ "IHFOUTR", "NULL", "Speaker Right Playback"},
+	{ "IHFOUTL", NULL, "Speaker Left Playback"},
+	{ "IHFOUTR", NULL, "Speaker Right Playback"},
 	{ "Speaker Left Playback", NULL, "Speaker Left Filter"},
 	{ "Speaker Right Playback", NULL, "Speaker Right Filter"},
 	{ "Speaker Left Filter", NULL, "IHFDAC Left"},
diff --git a/sound/soc/codecs/tas5086.c b/sound/soc/codecs/tas5086.c
index 249ef5c..32942be 100644
--- a/sound/soc/codecs/tas5086.c
+++ b/sound/soc/codecs/tas5086.c
@@ -281,7 +281,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = priv->deemph;
+	ucontrol->value.integer.value[0] = priv->deemph;
 
 	return 0;
 }
@@ -292,7 +292,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec);
 
-	priv->deemph = ucontrol->value.enumerated.item[0];
+	priv->deemph = ucontrol->value.integer.value[0];
 
 	return tas5086_set_deemph(codec);
 }
diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c
index 8d9de49..21d5402 100644
--- a/sound/soc/codecs/wm2000.c
+++ b/sound/soc/codecs/wm2000.c
@@ -610,7 +610,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
 
-	ucontrol->value.enumerated.item[0] = wm2000->anc_active;
+	ucontrol->value.integer.value[0] = wm2000->anc_active;
 
 	return 0;
 }
@@ -620,7 +620,7 @@
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
-	int anc_active = ucontrol->value.enumerated.item[0];
+	int anc_active = ucontrol->value.integer.value[0];
 	int ret;
 
 	if (anc_active > 1)
@@ -643,7 +643,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
 
-	ucontrol->value.enumerated.item[0] = wm2000->spk_ena;
+	ucontrol->value.integer.value[0] = wm2000->spk_ena;
 
 	return 0;
 }
@@ -653,7 +653,7 @@
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
-	int val = ucontrol->value.enumerated.item[0];
+	int val = ucontrol->value.integer.value[0];
 	int ret;
 
 	if (val > 1)
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index 098c143..c6d1053 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -125,7 +125,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8731->deemph;
+	ucontrol->value.integer.value[0] = wm8731->deemph;
 
 	return 0;
 }
@@ -135,7 +135,7 @@
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 	int ret = 0;
 
 	if (deemph > 1)
diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c
index dde462c..04b04f8 100644
--- a/sound/soc/codecs/wm8903.c
+++ b/sound/soc/codecs/wm8903.c
@@ -442,7 +442,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8903->deemph;
+	ucontrol->value.integer.value[0] = wm8903->deemph;
 
 	return 0;
 }
@@ -452,7 +452,7 @@
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 	int ret = 0;
 
 	if (deemph > 1)
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index d3b3f57..215e93c 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -525,7 +525,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8904->deemph;
+	ucontrol->value.integer.value[0] = wm8904->deemph;
 	return 0;
 }
 
@@ -534,7 +534,7 @@
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm8955.c b/sound/soc/codecs/wm8955.c
index 1ab2d46..00bec91 100644
--- a/sound/soc/codecs/wm8955.c
+++ b/sound/soc/codecs/wm8955.c
@@ -393,7 +393,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8955->deemph;
+	ucontrol->value.integer.value[0] = wm8955->deemph;
 	return 0;
 }
 
@@ -402,7 +402,7 @@
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index cf8fecf..3035d98 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -184,7 +184,7 @@
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec);
 
-	ucontrol->value.enumerated.item[0] = wm8960->deemph;
+	ucontrol->value.integer.value[0] = wm8960->deemph;
 	return 0;
 }
 
@@ -193,7 +193,7 @@
 {
 	struct snd_soc_codec *codec = snd_soc_kcontrol_codec(kcontrol);
 	struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec);
-	int deemph = ucontrol->value.enumerated.item[0];
+	int deemph = ucontrol->value.integer.value[0];
 
 	if (deemph > 1)
 		return -EINVAL;
diff --git a/sound/soc/codecs/wm9712.c b/sound/soc/codecs/wm9712.c
index 9517571..98c9525 100644
--- a/sound/soc/codecs/wm9712.c
+++ b/sound/soc/codecs/wm9712.c
@@ -180,7 +180,7 @@
 	struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol);
 	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(dapm);
 	struct wm9712_priv *wm9712 = snd_soc_codec_get_drvdata(codec);
-	unsigned int val = ucontrol->value.enumerated.item[0];
+	unsigned int val = ucontrol->value.integer.value[0];
 	struct soc_mixer_control *mc =
 		(struct soc_mixer_control *)kcontrol->private_value;
 	unsigned int mixer, mask, shift, old;
@@ -193,7 +193,7 @@
 
 	mutex_lock(&wm9712->lock);
 	old = wm9712->hp_mixer[mixer];
-	if (ucontrol->value.enumerated.item[0])
+	if (ucontrol->value.integer.value[0])
 		wm9712->hp_mixer[mixer] |= mask;
 	else
 		wm9712->hp_mixer[mixer] &= ~mask;
@@ -231,7 +231,7 @@
 	mixer = mc->shift >> 8;
 	shift = mc->shift & 0xff;
 
-	ucontrol->value.enumerated.item[0] =
+	ucontrol->value.integer.value[0] =
 		(wm9712->hp_mixer[mixer] >> shift) & 1;
 
 	return 0;
diff --git a/sound/soc/codecs/wm9713.c b/sound/soc/codecs/wm9713.c
index 6822291..7955295 100644
--- a/sound/soc/codecs/wm9713.c
+++ b/sound/soc/codecs/wm9713.c
@@ -255,7 +255,7 @@
 	struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol);
 	struct snd_soc_codec *codec = snd_soc_dapm_to_codec(dapm);
 	struct wm9713_priv *wm9713 = snd_soc_codec_get_drvdata(codec);
-	unsigned int val = ucontrol->value.enumerated.item[0];
+	unsigned int val = ucontrol->value.integer.value[0];
 	struct soc_mixer_control *mc =
 		(struct soc_mixer_control *)kcontrol->private_value;
 	unsigned int mixer, mask, shift, old;
@@ -268,7 +268,7 @@
 
 	mutex_lock(&wm9713->lock);
 	old = wm9713->hp_mixer[mixer];
-	if (ucontrol->value.enumerated.item[0])
+	if (ucontrol->value.integer.value[0])
 		wm9713->hp_mixer[mixer] |= mask;
 	else
 		wm9713->hp_mixer[mixer] &= ~mask;
@@ -306,7 +306,7 @@
 	mixer = mc->shift >> 8;
 	shift = mc->shift & 0xff;
 
-	ucontrol->value.enumerated.item[0] =
+	ucontrol->value.integer.value[0] =
 		(wm9713->hp_mixer[mixer] >> shift) & 1;
 
 	return 0;
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index b9fabbf..6b0c8f7 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -603,7 +603,7 @@
 	factor = (div2 + 1) * (7 * psr + 1) * 2;
 
 	for (i = 0; i < 255; i++) {
-		tmprate = freq * factor * (i + 2);
+		tmprate = freq * factor * (i + 1);
 
 		if (baudclk_is_used)
 			clkrate = clk_get_rate(ssi_private->baudclk);
@@ -1227,7 +1227,7 @@
 	ssi_private->dma_params_tx.addr = ssi_private->ssi_phys + CCSR_SSI_STX0;
 	ssi_private->dma_params_rx.addr = ssi_private->ssi_phys + CCSR_SSI_SRX0;
 
-	ret = !of_property_read_u32_array(np, "dmas", dmas, 4);
+	ret = of_property_read_u32_array(np, "dmas", dmas, 4);
 	if (ssi_private->use_dma && !ret && dmas[2] == IMX_DMATYPE_SSI_DUAL) {
 		ssi_private->use_dual_fifo = true;
 		/* When using dual fifo mode, we need to keep watermark
diff --git a/sound/soc/intel/sst-haswell-dsp.c b/sound/soc/intel/sst-haswell-dsp.c
index c42ffae..402b728 100644
--- a/sound/soc/intel/sst-haswell-dsp.c
+++ b/sound/soc/intel/sst-haswell-dsp.c
@@ -207,9 +207,6 @@
 		module = (void *)module + sizeof(*module) + module->mod_size;
 	}
 
-	/* allocate scratch mem regions */
-	sst_block_alloc_scratch(dsp);
-
 	return 0;
 }
 
diff --git a/sound/soc/intel/sst-haswell-ipc.c b/sound/soc/intel/sst-haswell-ipc.c
index 394af56..863a9ca 100644
--- a/sound/soc/intel/sst-haswell-ipc.c
+++ b/sound/soc/intel/sst-haswell-ipc.c
@@ -1732,6 +1732,7 @@
 int sst_hsw_dsp_load(struct sst_hsw *hsw)
 {
 	struct sst_dsp *dsp = hsw->dsp;
+	struct sst_fw *sst_fw, *t;
 	int ret;
 
 	dev_dbg(hsw->dev, "loading audio DSP....");
@@ -1748,12 +1749,17 @@
 		return ret;
 	}
 
-	ret = sst_fw_reload(hsw->sst_fw);
-	if (ret < 0) {
-		dev_err(hsw->dev, "error: SST FW reload failed\n");
-		sst_dsp_dma_put_channel(dsp);
-		return -ENOMEM;
+	list_for_each_entry_safe_reverse(sst_fw, t, &dsp->fw_list, list) {
+		ret = sst_fw_reload(sst_fw);
+		if (ret < 0) {
+			dev_err(hsw->dev, "error: SST FW reload failed\n");
+			sst_dsp_dma_put_channel(dsp);
+			return -ENOMEM;
+		}
 	}
+	ret = sst_block_alloc_scratch(hsw->dsp);
+	if (ret < 0)
+		return -EINVAL;
 
 	sst_dsp_dma_put_channel(dsp);
 	return 0;
@@ -1809,12 +1815,17 @@
 
 int sst_hsw_dsp_runtime_sleep(struct sst_hsw *hsw)
 {
-	sst_fw_unload(hsw->sst_fw);
-	sst_block_free_scratch(hsw->dsp);
+	struct sst_fw *sst_fw, *t;
+	struct sst_dsp *dsp = hsw->dsp;
+
+	list_for_each_entry_safe(sst_fw, t, &dsp->fw_list, list) {
+		sst_fw_unload(sst_fw);
+	}
+	sst_block_free_scratch(dsp);
 
 	hsw->boot_complete = false;
 
-	sst_dsp_sleep(hsw->dsp);
+	sst_dsp_sleep(dsp);
 
 	return 0;
 }
@@ -1943,6 +1954,11 @@
 		goto fw_err;
 	}
 
+	/* allocate scratch mem regions */
+	ret = sst_block_alloc_scratch(hsw->dsp);
+	if (ret < 0)
+		goto boot_err;
+
 	/* wait for DSP boot completion */
 	sst_dsp_boot(hsw->dsp);
 	ret = wait_event_timeout(hsw->boot_wait, hsw->boot_complete,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 30579ca..e5c9908 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -347,6 +347,8 @@
 	if (!buf)
 		return -ENOMEM;
 
+	mutex_lock(&client_mutex);
+
 	list_for_each_entry(codec, &codec_list, list) {
 		len = snprintf(buf + ret, PAGE_SIZE - ret, "%s\n",
 			       codec->component.name);
@@ -358,6 +360,8 @@
 		}
 	}
 
+	mutex_unlock(&client_mutex);
+
 	if (ret >= 0)
 		ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret);
 
@@ -382,6 +386,8 @@
 	if (!buf)
 		return -ENOMEM;
 
+	mutex_lock(&client_mutex);
+
 	list_for_each_entry(component, &component_list, list) {
 		list_for_each_entry(dai, &component->dai_list, list) {
 			len = snprintf(buf + ret, PAGE_SIZE - ret, "%s\n",
@@ -395,6 +401,8 @@
 		}
 	}
 
+	mutex_unlock(&client_mutex);
+
 	ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret);
 
 	kfree(buf);
@@ -418,6 +426,8 @@
 	if (!buf)
 		return -ENOMEM;
 
+	mutex_lock(&client_mutex);
+
 	list_for_each_entry(platform, &platform_list, list) {
 		len = snprintf(buf + ret, PAGE_SIZE - ret, "%s\n",
 			       platform->component.name);
@@ -429,6 +439,8 @@
 		}
 	}
 
+	mutex_unlock(&client_mutex);
+
 	ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret);
 
 	kfree(buf);
@@ -836,6 +848,8 @@
 {
 	struct snd_soc_component *component;
 
+	lockdep_assert_held(&client_mutex);
+
 	list_for_each_entry(component, &component_list, list) {
 		if (of_node) {
 			if (component->dev->of_node == of_node)
@@ -854,6 +868,8 @@
 	struct snd_soc_component *component;
 	struct snd_soc_dai *dai;
 
+	lockdep_assert_held(&client_mutex);
+
 	/* Find CPU DAI from registered DAIs*/
 	list_for_each_entry(component, &component_list, list) {
 		if (dlc->of_node && component->dev->of_node != dlc->of_node)
@@ -1508,6 +1524,7 @@
 	struct snd_soc_codec *codec;
 	int ret, i, order;
 
+	mutex_lock(&client_mutex);
 	mutex_lock_nested(&card->mutex, SND_SOC_CARD_CLASS_INIT);
 
 	/* bind DAIs */
@@ -1662,6 +1679,7 @@
 	card->instantiated = 1;
 	snd_soc_dapm_sync(&card->dapm);
 	mutex_unlock(&card->mutex);
+	mutex_unlock(&client_mutex);
 
 	return 0;
 
@@ -1680,6 +1698,7 @@
 
 base_error:
 	mutex_unlock(&card->mutex);
+	mutex_unlock(&client_mutex);
 
 	return ret;
 }
@@ -2713,13 +2732,6 @@
 	list_del(&component->list);
 }
 
-static void snd_soc_component_del(struct snd_soc_component *component)
-{
-	mutex_lock(&client_mutex);
-	snd_soc_component_del_unlocked(component);
-	mutex_unlock(&client_mutex);
-}
-
 int snd_soc_register_component(struct device *dev,
 			       const struct snd_soc_component_driver *cmpnt_drv,
 			       struct snd_soc_dai_driver *dai_drv,
@@ -2767,14 +2779,17 @@
 {
 	struct snd_soc_component *cmpnt;
 
+	mutex_lock(&client_mutex);
 	list_for_each_entry(cmpnt, &component_list, list) {
 		if (dev == cmpnt->dev && cmpnt->registered_as_component)
 			goto found;
 	}
+	mutex_unlock(&client_mutex);
 	return;
 
 found:
-	snd_soc_component_del(cmpnt);
+	snd_soc_component_del_unlocked(cmpnt);
+	mutex_unlock(&client_mutex);
 	snd_soc_component_cleanup(cmpnt);
 	kfree(cmpnt);
 }
@@ -2882,10 +2897,14 @@
 {
 	struct snd_soc_platform *platform;
 
+	mutex_lock(&client_mutex);
 	list_for_each_entry(platform, &platform_list, list) {
-		if (dev == platform->dev)
+		if (dev == platform->dev) {
+			mutex_unlock(&client_mutex);
 			return platform;
+		}
 	}
+	mutex_unlock(&client_mutex);
 
 	return NULL;
 }
@@ -3090,15 +3109,15 @@
 {
 	struct snd_soc_codec *codec;
 
+	mutex_lock(&client_mutex);
 	list_for_each_entry(codec, &codec_list, list) {
 		if (dev == codec->dev)
 			goto found;
 	}
+	mutex_unlock(&client_mutex);
 	return;
 
 found:
-
-	mutex_lock(&client_mutex);
 	list_del(&codec->list);
 	snd_soc_component_del_unlocked(&codec->component);
 	mutex_unlock(&client_mutex);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 61bf912..9d9db3b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -30,6 +30,8 @@
 
 static void ins__delete(struct ins_operands *ops)
 {
+	if (ops == NULL)
+		return;
 	zfree(&ops->source.raw);
 	zfree(&ops->source.name);
 	zfree(&ops->target.raw);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 4e51122..0db5713 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -22,6 +22,14 @@
 TARGETS_HOTPLUG = cpu-hotplug
 TARGETS_HOTPLUG += memory-hotplug
 
+# Clear LDFLAGS and MAKEFLAGS if called from main
+# Makefile to avoid test build failures when test
+# Makefile doesn't have explicit build rules.
+ifeq (1,$(MAKELEVEL))
+undefine LDFLAGS
+override MAKEFLAGS =
+endif
+
 all:
 	for TARGET in $(TARGETS); do \
 		make -C $$TARGET; \
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
index a0a7b5d..f9b9c7c 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -72,6 +72,8 @@
 {
 	if (!(lr_desc.state & LR_STATE_MASK))
 		vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr |= (1ULL << lr);
+	else
+		vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr &= ~(1ULL << lr);
 }
 
 static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu)
@@ -84,6 +86,11 @@
 	return vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
 }
 
+static void vgic_v2_clear_eisr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr = 0;
+}
+
 static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu)
 {
 	u32 misr = vcpu->arch.vgic_cpu.vgic_v2.vgic_misr;
@@ -148,6 +155,7 @@
 	.sync_lr_elrsr		= vgic_v2_sync_lr_elrsr,
 	.get_elrsr		= vgic_v2_get_elrsr,
 	.get_eisr		= vgic_v2_get_eisr,
+	.clear_eisr		= vgic_v2_clear_eisr,
 	.get_interrupt_status	= vgic_v2_get_interrupt_status,
 	.enable_underflow	= vgic_v2_enable_underflow,
 	.disable_underflow	= vgic_v2_disable_underflow,
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
index 3a62d8a..dff0602 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -104,6 +104,8 @@
 {
 	if (!(lr_desc.state & LR_STATE_MASK))
 		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
+	else
+		vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr &= ~(1U << lr);
 }
 
 static u64 vgic_v3_get_elrsr(const struct kvm_vcpu *vcpu)
@@ -116,6 +118,11 @@
 	return vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr;
 }
 
+static void vgic_v3_clear_eisr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr = 0;
+}
+
 static u32 vgic_v3_get_interrupt_status(const struct kvm_vcpu *vcpu)
 {
 	u32 misr = vcpu->arch.vgic_cpu.vgic_v3.vgic_misr;
@@ -192,6 +199,7 @@
 	.sync_lr_elrsr		= vgic_v3_sync_lr_elrsr,
 	.get_elrsr		= vgic_v3_get_elrsr,
 	.get_eisr		= vgic_v3_get_eisr,
+	.clear_eisr		= vgic_v3_clear_eisr,
 	.get_interrupt_status	= vgic_v3_get_interrupt_status,
 	.enable_underflow	= vgic_v3_enable_underflow,
 	.disable_underflow	= vgic_v3_disable_underflow,
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 0cc6ab6..c9f60f5 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -883,6 +883,11 @@
 	return vgic_ops->get_eisr(vcpu);
 }
 
+static inline void vgic_clear_eisr(struct kvm_vcpu *vcpu)
+{
+	vgic_ops->clear_eisr(vcpu);
+}
+
 static inline u32 vgic_get_interrupt_status(struct kvm_vcpu *vcpu)
 {
 	return vgic_ops->get_interrupt_status(vcpu);
@@ -922,6 +927,7 @@
 	vgic_set_lr(vcpu, lr_nr, vlr);
 	clear_bit(lr_nr, vgic_cpu->lr_used);
 	vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
+	vgic_sync_lr_elrsr(vcpu, lr_nr, vlr);
 }
 
 /*
@@ -978,6 +984,7 @@
 			BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
 			vlr.state |= LR_STATE_PENDING;
 			vgic_set_lr(vcpu, lr, vlr);
+			vgic_sync_lr_elrsr(vcpu, lr, vlr);
 			return true;
 		}
 	}
@@ -999,6 +1006,7 @@
 		vlr.state |= LR_EOI_INT;
 
 	vgic_set_lr(vcpu, lr, vlr);
+	vgic_sync_lr_elrsr(vcpu, lr, vlr);
 
 	return true;
 }
@@ -1136,6 +1144,14 @@
 	if (status & INT_STATUS_UNDERFLOW)
 		vgic_disable_underflow(vcpu);
 
+	/*
+	 * In the next iterations of the vcpu loop, if we sync the vgic state
+	 * after flushing it, but before entering the guest (this happens for
+	 * pending signals and vmid rollovers), then make sure we don't pick
+	 * up any old maintenance interrupts here.
+	 */
+	vgic_clear_eisr(vcpu);
+
 	return level_pending;
 }
 
@@ -1583,8 +1599,10 @@
 	 * emulation. So check this here again. KVM_CREATE_DEVICE does
 	 * the proper checks already.
 	 */
-	if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && !vgic->can_emulate_gicv2)
-		return -ENODEV;
+	if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && !vgic->can_emulate_gicv2) {
+		ret = -ENODEV;
+		goto out;
+	}
 
 	/*
 	 * Any time a vcpu is run, vcpu_load is called which tries to grab the
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a109370..cc6a25d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -471,7 +471,7 @@
 	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
 	r = -ENOMEM;
-	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+	kvm->memslots = kvm_kvzalloc(sizeof(struct kvm_memslots));
 	if (!kvm->memslots)
 		goto out_err_no_srcu;
 
@@ -522,7 +522,7 @@
 out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm->buses[i]);
-	kfree(kvm->memslots);
+	kvfree(kvm->memslots);
 	kvm_arch_free_vm(kvm);
 	return ERR_PTR(r);
 }
@@ -578,7 +578,7 @@
 	kvm_for_each_memslot(memslot, slots)
 		kvm_free_physmem_slot(kvm, memslot, NULL);
 
-	kfree(kvm->memslots);
+	kvfree(kvm->memslots);
 }
 
 static void kvm_destroy_devices(struct kvm *kvm)
@@ -871,10 +871,10 @@
 			goto out_free;
 	}
 
-	slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
-			GFP_KERNEL);
+	slots = kvm_kvzalloc(sizeof(struct kvm_memslots));
 	if (!slots)
 		goto out_free;
+	memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
 
 	if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
 		slot = id_to_memslot(slots, mem->slot);
@@ -917,7 +917,7 @@
 	kvm_arch_commit_memory_region(kvm, mem, &old, change);
 
 	kvm_free_physmem_slot(kvm, &old, &new);
-	kfree(old_memslots);
+	kvfree(old_memslots);
 
 	/*
 	 * IOMMU mapping:  New slots need to be mapped.  Old slots need to be
@@ -936,7 +936,7 @@
 	return 0;
 
 out_slots:
-	kfree(slots);
+	kvfree(slots);
 out_free:
 	kvm_free_physmem_slot(kvm, &new, &old);
 out:
@@ -2492,6 +2492,7 @@
 	case KVM_CAP_SIGNAL_MSI:
 #endif
 #ifdef CONFIG_HAVE_KVM_IRQFD
+	case KVM_CAP_IRQFD:
 	case KVM_CAP_IRQFD_RESAMPLE:
 #endif
 	case KVM_CAP_CHECK_EXTENSION_VM: