Merge git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next
diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt
index 31d1d65..c0d8788 100644
--- a/Documentation/IPMI.txt
+++ b/Documentation/IPMI.txt
@@ -587,7 +587,7 @@
 
   modprobe ipmi_watchdog timeout=<t> pretimeout=<t> action=<action type>
       preaction=<preaction type> preop=<preop type> start_now=x
-      nowayout=x ifnum_to_use=n
+      nowayout=x ifnum_to_use=n panic_wdt_timeout=<t>
 
 ifnum_to_use specifies which interface the watchdog timer should use.
 The default is -1, which means to pick the first one registered.
@@ -597,7 +597,9 @@
 occur (if pretimeout is zero, then pretimeout will not be enabled).  Note
 that the pretimeout is the time before the final timeout.  So if the
 timeout is 50 seconds and the pretimeout is 10 seconds, then the pretimeout
-will occur in 40 second (10 seconds before the timeout).
+will occur in 40 second (10 seconds before the timeout). The panic_wdt_timeout
+is the value of timeout which is set on kernel panic, in order to let actions
+such as kdump to occur during panic.
 
 The action may be "reset", "power_cycle", or "power_off", and
 specifies what to do when the timer times out, and defaults to
@@ -634,6 +636,7 @@
 	ipmi_watchdog.preop=<preop type>
 	ipmi_watchdog.start_now=x
 	ipmi_watchdog.nowayout=x
+	ipmi_watchdog.panic_wdt_timeout=<t>
 
 The options are the same as the module parameter options.
 
diff --git a/Documentation/arm/keystone/Overview.txt b/Documentation/arm/keystone/Overview.txt
index f17bc4c..400c0c2 100644
--- a/Documentation/arm/keystone/Overview.txt
+++ b/Documentation/arm/keystone/Overview.txt
@@ -49,24 +49,6 @@
 The device tree documentation for the keystone machines are located at
         Documentation/devicetree/bindings/arm/keystone/keystone.txt
 
-Known issues & workaround
--------------------------
-
-Some of the device drivers used on keystone are re-used from that from
-DaVinci and other TI SoCs. These device drivers may use clock APIs directly.
-Some of the keystone specific drivers such as netcp uses run time power
-management API instead to enable clock. As this API has limitations on
-keystone, following workaround is needed to boot Linux.
-
-   Add 'clk_ignore_unused' to the bootargs env variable in u-boot. Otherwise
-   clock frameworks will try to disable clocks that are unused and disable
-   the hardware. This is because netcp related power domain and clock
-   domains are enabled in u-boot as run time power management API currently
-   doesn't enable clocks for netcp due to a limitation. This workaround is
-   expected to be removed in the future when proper API support becomes
-   available. Until then, this work around is needed.
-
-
 Document Author
 ---------------
 Murali Karicheri <m-karicheri2@ti.com>
diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt
index 2f6c6ff..d8880ca 100644
--- a/Documentation/block/null_blk.txt
+++ b/Documentation/block/null_blk.txt
@@ -70,3 +70,6 @@
      parameter.
   1: The multi-queue block layer is instantiated with a hardware dispatch
      queue for each CPU node in the system.
+
+use_lightnvm=[0/1]: Default: 0
+  Register device with LightNVM. Requires blk-mq to be used.
diff --git a/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt b/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
index b38200d..0dfa60d 100644
--- a/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
@@ -1,7 +1,9 @@
 * Temperature Sensor ADC (TSADC) on rockchip SoCs
 
 Required properties:
-- compatible : "rockchip,rk3288-tsadc"
+- compatible : should be "rockchip,<name>-tsadc"
+   "rockchip,rk3288-tsadc": found on RK3288 SoCs
+   "rockchip,rk3368-tsadc": found on RK3368 SoCs
 - reg : physical base address of the controller and length of memory mapped
 	region.
 - interrupts : The interrupt number to the cpu. The interrupt specifier format
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index 6a4b1af..1bba38d 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -32,6 +32,7 @@
   * Intel Sunrise Point-LP (PCH)
   * Intel DNV (SOC)
   * Intel Broxton (SOC)
+  * Intel Lewisburg (PCH)
    Datasheets: Publicly available at the Intel website
 
 On Intel Patsburg and later chipsets, both the normal host SMBus controller
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index f8aae63..742f69d 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1583,9 +1583,6 @@
 		hwp_only
 			Only load intel_pstate on systems which support
 			hardware P state control (HWP) if available.
-		no_acpi
-			Don't use ACPI processor performance control objects
-			_PSS and _PPC specified limits.
 
 	intremap=	[X86-64, Intel-IOMMU]
 			on	enable Interrupt Remapping (default)
diff --git a/MAINTAINERS b/MAINTAINERS
index ea17512..dac7270 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -388,7 +388,7 @@
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org/
 S:	Orphan
-F:	drivers/net/wireless/adm8211.*
+F:	drivers/net/wireless/admtek/adm8211.*
 
 ADP1653 FLASH CONTROLLER DRIVER
 M:	Sakari Ailus <sakari.ailus@iki.fi>
@@ -1847,7 +1847,7 @@
 F:	drivers/net/wireless/ath/ath6kl/
 
 WILOCITY WIL6210 WIRELESS DRIVER
-M:	Vladimir Kondratiev <qca_vkondrat@qca.qualcomm.com>
+M:	Maya Erez <qca_merez@qca.qualcomm.com>
 L:	linux-wireless@vger.kernel.org
 L:	wil6210@qca.qualcomm.com
 S:	Supported
@@ -1931,7 +1931,7 @@
 F:	drivers/i2c/busses/i2c-at91.c
 
 ATMEL ISI DRIVER
-M:	Josh Wu <josh.wu@atmel.com>
+M:	Ludovic Desroches <ludovic.desroches@atmel.com>
 L:	linux-media@vger.kernel.org
 S:	Supported
 F:	drivers/media/platform/soc_camera/atmel-isi.c
@@ -1950,7 +1950,8 @@
 F:	drivers/net/ethernet/cadence/
 
 ATMEL NAND DRIVER
-M:	Josh Wu <josh.wu@atmel.com>
+M:	Wenyou Yang <wenyou.yang@atmel.com>
+M:	Josh Wu <rainyfeeling@outlook.com>
 L:	linux-mtd@lists.infradead.org
 S:	Supported
 F:	drivers/mtd/nand/atmel_nand*
@@ -1992,7 +1993,7 @@
 W:	http://www.thekelleys.org.uk/atmel
 W:	http://atmelwlandriver.sourceforge.net/
 S:	Maintained
-F:	drivers/net/wireless/atmel*
+F:	drivers/net/wireless/atmel/atmel*
 
 ATMEL MAXTOUCH DRIVER
 M:	Nick Dyer <nick.dyer@itdev.co.uk>
@@ -2081,7 +2082,7 @@
 L:	b43-dev@lists.infradead.org
 W:	http://wireless.kernel.org/en/users/Drivers/b43
 S:	Odd Fixes
-F:	drivers/net/wireless/b43/
+F:	drivers/net/wireless/broadcom/b43/
 
 B43LEGACY WIRELESS DRIVER
 M:	Larry Finger <Larry.Finger@lwfinger.net>
@@ -2089,7 +2090,7 @@
 L:	b43-dev@lists.infradead.org
 W:	http://wireless.kernel.org/en/users/Drivers/b43
 S:	Maintained
-F:	drivers/net/wireless/b43legacy/
+F:	drivers/net/wireless/broadcom/b43legacy/
 
 BACKLIGHT CLASS/SUBSYSTEM
 M:	Jingoo Han <jingoohan1@gmail.com>
@@ -2391,7 +2392,7 @@
 L:	linux-wireless@vger.kernel.org
 L:	brcm80211-dev-list@broadcom.com
 S:	Supported
-F:	drivers/net/wireless/brcm80211/
+F:	drivers/net/wireless/broadcom/brcm80211/
 
 BROADCOM BNX2FC 10 GIGABIT FCOE DRIVER
 M:	QLogic-Storage-Upstream@qlogic.com
@@ -2449,7 +2450,9 @@
 
 BROADCOM STB NAND FLASH DRIVER
 M:	Brian Norris <computersforpeace@gmail.com>
+M:	Kamal Dasu <kdasu.kdev@gmail.com>
 L:	linux-mtd@lists.infradead.org
+L:	bcm-kernel-feedback-list@broadcom.com
 S:	Maintained
 F:	drivers/mtd/nand/brcmnand/
 
@@ -2929,10 +2932,9 @@
 F:	drivers/platform/x86/compal-laptop.c
 
 CONEXANT ACCESSRUNNER USB DRIVER
-M:	Simon Arlott <cxacru@fire.lp0.eu>
 L:	accessrunner-general@lists.sourceforge.net
 W:	http://accessrunner.sourceforge.net/
-S:	Maintained
+S:	Orphan
 F:	drivers/usb/atm/cxacru.c
 
 CONFIGFS
@@ -3101,7 +3103,7 @@
 CW1200 WLAN driver
 M:	Solomon Peachy <pizza@shaftnet.org>
 S:	Maintained
-F:	drivers/net/wireless/cw1200/
+F:	drivers/net/wireless/st/cw1200/
 
 CX18 VIDEO4LINUX DRIVER
 M:	Andy Walls <awalls@md.metrocast.net>
@@ -4409,6 +4411,7 @@
 
 FPGA MANAGER FRAMEWORK
 M:	Alan Tull <atull@opensource.altera.com>
+R:	Moritz Fischer <moritz.fischer@ettus.com>
 S:	Maintained
 F:	drivers/fpga/
 F:	include/linux/fpga/fpga-mgr.h
@@ -5041,7 +5044,7 @@
 L:	linux-wireless@vger.kernel.org
 W:	http://hostap.epitest.fi/
 S:	Maintained
-F:	drivers/net/wireless/hostap/
+F:	drivers/net/wireless/intersil/hostap/
 
 HP COMPAQ TC1100 TABLET WMI EXTRAS DRIVER
 L:	platform-driver-x86@vger.kernel.org
@@ -5609,7 +5612,7 @@
 S:	Maintained
 F:	Documentation/networking/README.ipw2100
 F:	Documentation/networking/README.ipw2200
-F:	drivers/net/wireless/ipw2x00/
+F:	drivers/net/wireless/intel/ipw2x00/
 
 INTEL(R) TRACE HUB
 M:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
@@ -5643,7 +5646,7 @@
 M:	Stanislaw Gruszka <sgruszka@redhat.com>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
-F:	drivers/net/wireless/iwlegacy/
+F:	drivers/net/wireless/intel/iwlegacy/
 
 INTEL WIRELESS WIFI LINK (iwlwifi)
 M:	Johannes Berg <johannes.berg@intel.com>
@@ -5653,7 +5656,7 @@
 W:	http://intellinuxwireless.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/iwlwifi/iwlwifi.git
 S:	Supported
-F:	drivers/net/wireless/iwlwifi/
+F:	drivers/net/wireless/intel/iwlwifi/
 
 INTEL MANAGEMENT ENGINE (mei)
 M:	Tomas Winkler <tomas.winkler@intel.com>
@@ -6364,6 +6367,7 @@
 LIGHTNVM PLATFORM SUPPORT
 M:	Matias Bjorling <mb@lightnvm.io>
 W:	http://github/OpenChannelSSD
+L:	linux-block@vger.kernel.org
 S:	Maintained
 F:	drivers/lightnvm/
 F:	include/linux/lightnvm.h
@@ -6703,7 +6707,7 @@
 MARVELL LIBERTAS WIRELESS DRIVER
 L:	libertas-dev@lists.infradead.org
 S:	Orphan
-F:	drivers/net/wireless/libertas/
+F:	drivers/net/wireless/marvell/libertas/
 
 MARVELL MV643XX ETHERNET DRIVER
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
@@ -6723,13 +6727,13 @@
 M:	Nishant Sarmukadam <nishants@marvell.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-F:	drivers/net/wireless/mwifiex/
+F:	drivers/net/wireless/marvell/mwifiex/
 
 MARVELL MWL8K WIRELESS DRIVER
 M:	Lennert Buytenhek <buytenh@wantstofly.org>
 L:	linux-wireless@vger.kernel.org
 S:	Odd Fixes
-F:	drivers/net/wireless/mwl8k.c
+F:	drivers/net/wireless/marvell/mwl8k.c
 
 MARVELL SOC MMC/SD/SDIO CONTROLLER DRIVER
 M:	Nicolas Pitre <nico@fluxnic.net>
@@ -7902,6 +7906,18 @@
 F:	net/openvswitch/
 F:	include/uapi/linux/openvswitch.h
 
+OPERATING PERFORMANCE POINTS (OPP)
+M:	Viresh Kumar <vireshk@kernel.org>
+M:	Nishanth Menon <nm@ti.com>
+M:	Stephen Boyd <sboyd@codeaurora.org>
+L:	linux-pm@vger.kernel.org
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm.git
+F:	drivers/base/power/opp/
+F:	include/linux/pm_opp.h
+F:	Documentation/power/opp.txt
+F:	Documentation/devicetree/bindings/opp/
+
 OPL4 DRIVER
 M:	Clemens Ladisch <clemens@ladisch.de>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
@@ -7933,7 +7949,7 @@
 W:	http://wireless.kernel.org/en/users/Drivers/orinoco
 W:	http://www.nongnu.org/orinoco/
 S:	Orphan
-F:	drivers/net/wireless/orinoco/
+F:	drivers/net/wireless/intersil/orinoco/
 
 OSD LIBRARY and FILESYSTEM
 M:	Boaz Harrosh <ooo@electrozaur.com>
@@ -7959,7 +7975,7 @@
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org/en/users/Drivers/p54
 S:	Maintained
-F:	drivers/net/wireless/p54/
+F:	drivers/net/wireless/intersil/p54/
 
 PA SEMI ETHERNET DRIVER
 M:	Olof Johansson <olof@lixom.net>
@@ -8501,7 +8517,7 @@
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org/en/users/Drivers/p54
 S:	Obsolete
-F:	drivers/net/wireless/prism54/
+F:	drivers/net/wireless/intersil/prism54/
 
 PS3 NETWORK SUPPORT
 M:	Geoff Levand <geoff@infradead.org>
@@ -8804,7 +8820,7 @@
 M:	Helmut Schaa <helmut.schaa@googlemail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-F:	drivers/net/wireless/rt2x00/
+F:	drivers/net/wireless/ralink/rt2x00/
 
 RAMDISK RAM BLOCK DEVICE DRIVER
 M:	Jens Axboe <axboe@kernel.dk>
@@ -9038,7 +9054,7 @@
 W:	http://wireless.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
 S:	Orphan
-F:	drivers/net/wireless/rtl818x/rtl8180/
+F:	drivers/net/wireless/realtek/rtl818x/rtl8180/
 
 RTL8187 WIRELESS DRIVER
 M:	Herton Ronaldo Krzesinski <herton@canonical.com>
@@ -9048,7 +9064,7 @@
 W:	http://wireless.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
 S:	Maintained
-F:	drivers/net/wireless/rtl818x/rtl8187/
+F:	drivers/net/wireless/realtek/rtl818x/rtl8187/
 
 RTL8192CE WIRELESS DRIVER
 M:	Larry Finger <Larry.Finger@lwfinger.net>
@@ -9057,8 +9073,8 @@
 W:	http://wireless.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
 S:	Maintained
-F:	drivers/net/wireless/rtlwifi/
-F:	drivers/net/wireless/rtlwifi/rtl8192ce/
+F:	drivers/net/wireless/realtek/rtlwifi/
+F:	drivers/net/wireless/realtek/rtlwifi/rtl8192ce/
 
 RTL8XXXU WIRELESS DRIVER (rtl8xxxu)
 M:	Jes Sorensen <Jes.Sorensen@redhat.com>
@@ -9315,7 +9331,6 @@
 F:	include/linux/platform_data/i2c-designware.h
 
 SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
-M:	Seungwon Jeon <tgih.jun@samsung.com>
 M:	Jaehoon Chung <jh80.chung@samsung.com>
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
@@ -11255,7 +11270,7 @@
 L:	linux-wireless@vger.kernel.org
 W:	http://linux-lc100020.sourceforge.net
 S:	Orphan
-F:	drivers/net/wireless/zd1201.*
+F:	drivers/net/wireless/zydas/zd1201.*
 
 USB ZR364XX DRIVER
 M:	Antoine Jacquet <royale@zerezo.com>
@@ -11886,7 +11901,7 @@
 L:	linux-wireless@vger.kernel.org
 L:	zd1211-devs@lists.sourceforge.net (subscribers-only)
 S:	Maintained
-F:	drivers/net/wireless/zd1211rw/
+F:	drivers/net/wireless/zydas/zd1211rw/
 
 ZPOOL COMPRESSED PAGE STORAGE API
 M:	Dan Streetman <ddstreet@ieee.org>
diff --git a/Makefile b/Makefile
index 3a0234f..904a1d6 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index c92c0ef..f1ac981 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index cfac24e..323486d 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index 9922a11..66191cd 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index f761a7c..f68838e 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index dc6f74f..96bd1c2 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index 3fef0a2..fcae666 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index 5178483..b01b659 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
index ef35ef3..a07f20d 100644
--- a/arch/arc/configs/vdk_hs38_defconfig
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_CROSS_MEMORY_ATTACH is not set
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index 634509e..f36c047 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_CROSS_MEMORY_ATTACH is not set
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index ad481c2..258b0e5 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -37,6 +37,9 @@
 #define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | STATUS_AD_MASK | \
 					(ARCV2_IRQ_DEF_PRIO << 1))
 
+/* SLEEP needs default irq priority (<=) which can interrupt the doze */
+#define ISA_SLEEP_ARG		(0x10 | ARCV2_IRQ_DEF_PRIO)
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index d8c6081..c1d3645 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -43,6 +43,8 @@
 
 #define ISA_INIT_STATUS_BITS	STATUS_IE_MASK
 
+#define ISA_SLEEP_ARG		0x3
+
 #ifndef __ASSEMBLY__
 
 /******************************************************************
diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c
index c14a5be..5d446df 100644
--- a/arch/arc/kernel/ctx_sw.c
+++ b/arch/arc/kernel/ctx_sw.c
@@ -58,8 +58,6 @@
 		"st      sp, [r24]       \n\t"
 #endif
 
-		"sync   \n\t"
-
 		/*
 		 * setup _current_task with incoming tsk.
 		 * optionally, set r25 to that as well
diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S
index e248594..e6890b1 100644
--- a/arch/arc/kernel/ctx_sw_asm.S
+++ b/arch/arc/kernel/ctx_sw_asm.S
@@ -44,9 +44,6 @@
 	* don't need to do anything special to return it
 	*/
 
-	/* hardware memory barrier */
-	sync
-
 	/*
 	 * switch to new task, contained in r1
 	 * Temp reg r3 is required to get the ptr to store val
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 91d5a0f..a3f750e 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -44,11 +44,10 @@
 void arch_cpu_idle(void)
 {
 	/* sleep, but enable all interrupts before committing */
-	if (is_isa_arcompact()) {
-		__asm__("sleep 0x3");
-	} else {
-		__asm__("sleep 0x10");
-	}
+	__asm__ __volatile__(
+		"sleep %0	\n"
+		:
+		:"I"(ISA_SLEEP_ARG)); /* can't be "r" has to be embedded const */
 }
 
 asmlinkage void ret_from_fork(void);
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 93c6ea5..7352475 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -986,42 +986,13 @@
 							    (const u8 *)(fde +
 									 1) +
 							    *fde, ptrType);
-				if (pc >= endLoc)
+				if (pc >= endLoc) {
 					fde = NULL;
-			} else
-				fde = NULL;
-		}
-		if (fde == NULL) {
-			for (fde = table->address, tableSize = table->size;
-			     cie = NULL, tableSize > sizeof(*fde)
-			     && tableSize - sizeof(*fde) >= *fde;
-			     tableSize -= sizeof(*fde) + *fde,
-			     fde += 1 + *fde / sizeof(*fde)) {
-				cie = cie_for_fde(fde, table);
-				if (cie == &bad_cie) {
 					cie = NULL;
-					break;
 				}
-				if (cie == NULL
-				    || cie == &not_fde
-				    || (ptrType = fde_pointer_type(cie)) < 0)
-					continue;
-				ptr = (const u8 *)(fde + 2);
-				startLoc = read_pointer(&ptr,
-							(const u8 *)(fde + 1) +
-							*fde, ptrType);
-				if (!startLoc)
-					continue;
-				if (!(ptrType & DW_EH_PE_indirect))
-					ptrType &=
-					    DW_EH_PE_FORM | DW_EH_PE_signed;
-				endLoc =
-				    startLoc + read_pointer(&ptr,
-							    (const u8 *)(fde +
-									 1) +
-							    *fde, ptrType);
-				if (pc >= startLoc && pc < endLoc)
-					break;
+			} else {
+				fde = NULL;
+				cie = NULL;
 			}
 		}
 	}
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index 0ee7398..daf2bf5 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -619,10 +619,10 @@
 
 		int dirty = !test_and_set_bit(PG_dc_clean, &page->flags);
 		if (dirty) {
-			/* wback + inv dcache lines */
+			/* wback + inv dcache lines (K-mapping) */
 			__flush_dcache_page(paddr, paddr);
 
-			/* invalidate any existing icache lines */
+			/* invalidate any existing icache lines (U-mapping) */
 			if (vma->vm_flags & VM_EXEC)
 				__inv_icache_page(paddr, vaddr);
 		}
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0365cbb..34e1569 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -76,6 +76,8 @@
 	select IRQ_FORCED_THREADING
 	select MODULES_USE_ELF_REL
 	select NO_BOOTMEM
+	select OF_EARLY_FLATTREE if OF
+	select OF_RESERVED_MEM if OF
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
 	select PERF_USE_VMALLOC
@@ -1822,8 +1824,6 @@
 	bool "Flattened Device Tree support"
 	select IRQ_DOMAIN
 	select OF
-	select OF_EARLY_FLATTREE
-	select OF_RESERVED_MEM
 	help
 	  Include support for flattened device tree machine descriptions.
 
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index d9ba6b8..00352e7 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -604,6 +604,7 @@
 		reg = <0x6f>;
 		interrupts-extended = <&crossbar_mpu GIC_SPI 2 IRQ_TYPE_EDGE_RISING>,
 				      <&dra7_pmx_core 0x424>;
+		interrupt-names = "irq", "wakeup";
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&mcp79410_pins_default>;
diff --git a/arch/arm/boot/dts/animeo_ip.dts b/arch/arm/boot/dts/animeo_ip.dts
index 4e0ad3b..0962f2f 100644
--- a/arch/arm/boot/dts/animeo_ip.dts
+++ b/arch/arm/boot/dts/animeo_ip.dts
@@ -155,21 +155,21 @@
 			label = "keyswitch_in";
 			gpios = <&pioB 1 GPIO_ACTIVE_HIGH>;
 			linux,code = <28>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		error_in {
 			label = "error_in";
 			gpios = <&pioB 2 GPIO_ACTIVE_HIGH>;
 			linux,code = <29>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		btn {
 			label = "btn";
 			gpios = <&pioC 23 GPIO_ACTIVE_HIGH>;
 			linux,code = <31>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/at91-foxg20.dts b/arch/arm/boot/dts/at91-foxg20.dts
index f89598a..6bf873e 100644
--- a/arch/arm/boot/dts/at91-foxg20.dts
+++ b/arch/arm/boot/dts/at91-foxg20.dts
@@ -159,7 +159,7 @@
 			label = "Button";
 			gpios = <&pioC 4 GPIO_ACTIVE_LOW>;
 			linux,code = <0x103>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/at91-kizbox.dts b/arch/arm/boot/dts/at91-kizbox.dts
index bf18ece..229e989 100644
--- a/arch/arm/boot/dts/at91-kizbox.dts
+++ b/arch/arm/boot/dts/at91-kizbox.dts
@@ -24,15 +24,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <18432000>;
-		};
-
 		main_xtal {
 			clock-frequency = <18432000>;
 		};
@@ -94,14 +85,14 @@
 			label = "PB_RST";
 			gpios = <&pioB 30 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		user {
 			label = "PB_USER";
 			gpios = <&pioB 31 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x101>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-kizbox2.dts b/arch/arm/boot/dts/at91-kizbox2.dts
index f0b1563..50a1456 100644
--- a/arch/arm/boot/dts/at91-kizbox2.dts
+++ b/arch/arm/boot/dts/at91-kizbox2.dts
@@ -171,21 +171,21 @@
 			label = "PB_PROG";
 			gpios = <&pioE 27 GPIO_ACTIVE_LOW>;
 			linux,code = <0x102>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		reset {
 			label = "PB_RST";
 			gpios = <&pioE 29 GPIO_ACTIVE_LOW>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		user {
 			label = "PB_USER";
 			gpios = <&pioE 31 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x101>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-kizboxmini.dts b/arch/arm/boot/dts/at91-kizboxmini.dts
index 9f72b49..9682d10 100644
--- a/arch/arm/boot/dts/at91-kizboxmini.dts
+++ b/arch/arm/boot/dts/at91-kizboxmini.dts
@@ -98,14 +98,14 @@
 			label = "PB_PROG";
 			gpios = <&pioC 17 GPIO_ACTIVE_LOW>;
 			linux,code = <0x102>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		reset {
 			label = "PB_RST";
 			gpios = <&pioC 16 GPIO_ACTIVE_LOW>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-qil_a9260.dts b/arch/arm/boot/dts/at91-qil_a9260.dts
index a9aef53..4f2eebf 100644
--- a/arch/arm/boot/dts/at91-qil_a9260.dts
+++ b/arch/arm/boot/dts/at91-qil_a9260.dts
@@ -183,7 +183,7 @@
 			label = "user_pb";
 			gpios = <&pioB 10 GPIO_ACTIVE_LOW>;
 			linux,code = <28>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
index e07c2b2..ad6de73 100644
--- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
@@ -45,6 +45,7 @@
 /dts-v1/;
 #include "sama5d2.dtsi"
 #include "sama5d2-pinfunc.h"
+#include <dt-bindings/mfd/atmel-flexcom.h>
 
 / {
 	model = "Atmel SAMA5D2 Xplained";
@@ -59,15 +60,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -91,6 +83,22 @@
 			status = "okay";
 		};
 
+		sdmmc0: sdio-host@a0000000 {
+			bus-width = <8>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_sdmmc0_default>;
+			non-removable;
+			mmc-ddr-1_8v;
+			status = "okay";
+		};
+
+		sdmmc1: sdio-host@b0000000 {
+			bus-width = <4>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_sdmmc1_default>;
+			status = "okay"; /* conflict with qspi0 */
+		};
+
 		apb {
 			spi0: spi@f8000000 {
 				pinctrl-names = "default";
@@ -181,12 +189,49 @@
 				};
 			};
 
+			flx0: flexcom@f8034000 {
+				atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_USART>;
+				status = "disabled"; /* conflict with ISC_D2 & ISC_D3 data pins */
+
+				uart5: serial@200 {
+					compatible = "atmel,at91sam9260-usart";
+					reg = <0x200 0x200>;
+					interrupts = <19 IRQ_TYPE_LEVEL_HIGH 7>;
+					clocks = <&flx0_clk>;
+					clock-names = "usart";
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_flx0_default>;
+					atmel,fifo-size = <32>;
+					status = "okay";
+				};
+			};
+
 			uart3: serial@fc008000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_uart3_default>;
 				status = "okay";
 			};
 
+			flx4: flexcom@fc018000 {
+				atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_TWI>;
+				status = "okay";
+
+				i2c2: i2c@600 {
+					compatible = "atmel,sama5d2-i2c";
+					reg = <0x600 0x200>;
+					interrupts = <23 IRQ_TYPE_LEVEL_HIGH 7>;
+					dmas = <0>, <0>;
+					dma-names = "tx", "rx";
+					#address-cells = <1>;
+					#size-cells = <0>;
+					clocks = <&flx4_clk>;
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_flx4_default>;
+					atmel,fifo-size = <16>;
+					status = "okay";
+				};
+			};
+
 			i2c1: i2c@fc028000 {
 				dmas = <0>, <0>;
 				pinctrl-names = "default";
@@ -201,6 +246,18 @@
 			};
 
 			pinctrl@fc038000 {
+				pinctrl_flx0_default: flx0_default {
+					pinmux = <PIN_PB28__FLEXCOM0_IO0>,
+						 <PIN_PB29__FLEXCOM0_IO1>;
+					bias-disable;
+				};
+
+				pinctrl_flx4_default: flx4_default {
+					pinmux = <PIN_PD12__FLEXCOM4_IO0>,
+						 <PIN_PD13__FLEXCOM4_IO1>;
+					bias-disable;
+				};
+
 				pinctrl_i2c0_default: i2c0_default {
 					pinmux = <PIN_PD21__TWD0>,
 						 <PIN_PD22__TWCK0>;
@@ -227,6 +284,46 @@
 					bias-disable;
 				};
 
+				pinctrl_sdmmc0_default: sdmmc0_default {
+					cmd_data {
+						pinmux = <PIN_PA1__SDMMC0_CMD>,
+							 <PIN_PA2__SDMMC0_DAT0>,
+							 <PIN_PA3__SDMMC0_DAT1>,
+							 <PIN_PA4__SDMMC0_DAT2>,
+							 <PIN_PA5__SDMMC0_DAT3>,
+							 <PIN_PA6__SDMMC0_DAT4>,
+							 <PIN_PA7__SDMMC0_DAT5>,
+							 <PIN_PA8__SDMMC0_DAT6>,
+							 <PIN_PA9__SDMMC0_DAT7>;
+						bias-pull-up;
+					};
+
+					ck_cd_rstn_vddsel {
+						pinmux = <PIN_PA0__SDMMC0_CK>,
+							 <PIN_PA10__SDMMC0_RSTN>,
+							 <PIN_PA11__SDMMC0_VDDSEL>,
+							 <PIN_PA13__SDMMC0_CD>;
+						bias-disable;
+					};
+				};
+
+				pinctrl_sdmmc1_default: sdmmc1_default {
+					cmd_data {
+						pinmux = <PIN_PA28__SDMMC1_CMD>,
+							 <PIN_PA18__SDMMC1_DAT0>,
+							 <PIN_PA19__SDMMC1_DAT1>,
+							 <PIN_PA20__SDMMC1_DAT2>,
+							 <PIN_PA21__SDMMC1_DAT3>;
+						bias-pull-up;
+					};
+
+					conf-ck_cd {
+						pinmux = <PIN_PA22__SDMMC1_CK>,
+							 <PIN_PA30__SDMMC1_CD>;
+						bias-disable;
+					};
+				};
+
 				pinctrl_spi0_default: spi0_default {
 					pinmux = <PIN_PA14__SPI0_SPCK>,
 						 <PIN_PA15__SPI0_MOSI>,
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
index 8488ac5..ff888d2 100644
--- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -315,7 +315,7 @@
 			label = "PB_USER";
 			gpios = <&pioE 29 GPIO_ACTIVE_LOW>;
 			linux,code = <0x104>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
index 45371a1..131614f 100644
--- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
@@ -50,7 +50,6 @@
 	compatible = "atmel,sama5d4-xplained", "atmel,sama5d4", "atmel,sama5";
 
 	chosen {
-		bootargs = "ignore_loglevel earlyprintk";
 		stdout-path = "serial0:115200n8";
 	};
 
@@ -59,15 +58,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -235,7 +225,7 @@
 			label = "pb_user1";
 			gpios = <&pioE 8 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts
index 6d272c0..2d4a331 100644
--- a/arch/arm/boot/dts/at91-sama5d4ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d4ek.dts
@@ -50,7 +50,6 @@
 	compatible = "atmel,sama5d4ek", "atmel,sama5d4", "atmel,sama5";
 
 	chosen {
-		bootargs = "ignore_loglevel earlyprintk";
 		stdout-path = "serial0:115200n8";
 	};
 
@@ -59,15 +58,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -304,7 +294,7 @@
 			label = "pb_user1";
 			gpios = <&pioE 13 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91rm9200ek.dts b/arch/arm/boot/dts/at91rm9200ek.dts
index 8dab4b7..f90e1c2 100644
--- a/arch/arm/boot/dts/at91rm9200ek.dts
+++ b/arch/arm/boot/dts/at91rm9200ek.dts
@@ -21,15 +21,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <18432000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts
index 2e92ac0..55bd51f 100644
--- a/arch/arm/boot/dts/at91sam9261ek.dts
+++ b/arch/arm/boot/dts/at91sam9261ek.dts
@@ -22,15 +22,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <18432000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -149,7 +140,7 @@
 					ti,debounce-tol = /bits/ 16 <65535>;
 					ti,debounce-max = /bits/ 16 <1>;
 
-					linux,wakeup;
+					wakeup-source;
 				};
 			};
 
@@ -193,28 +184,28 @@
 			label = "button_0";
 			gpios = <&pioA 27 GPIO_ACTIVE_LOW>;
 			linux,code = <256>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		button_1 {
 			label = "button_1";
 			gpios = <&pioA 26 GPIO_ACTIVE_LOW>;
 			linux,code = <257>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		button_2 {
 			label = "button_2";
 			gpios = <&pioA 25 GPIO_ACTIVE_LOW>;
 			linux,code = <258>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		button_3 {
 			label = "button_3";
 			gpios = <&pioA 24 GPIO_ACTIVE_LOW>;
 			linux,code = <259>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts
index 2338127..59df9d7 100644
--- a/arch/arm/boot/dts/at91sam9263ek.dts
+++ b/arch/arm/boot/dts/at91sam9263ek.dts
@@ -22,15 +22,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <16367660>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -213,14 +204,14 @@
 			label = "left_click";
 			gpios = <&pioC 5 GPIO_ACTIVE_LOW>;
 			linux,code = <272>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		right_click {
 			label = "right_click";
 			gpios = <&pioC 4 GPIO_ACTIVE_LOW>;
 			linux,code = <273>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
index 57548a2..e9cc99b 100644
--- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
+++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
@@ -19,15 +19,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <18432000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -206,14 +197,14 @@
 			label = "Button 3";
 			gpios = <&pioA 30 GPIO_ACTIVE_LOW>;
 			linux,code = <0x103>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		btn4 {
 			label = "Button 4";
 			gpios = <&pioA 31 GPIO_ACTIVE_LOW>;
 			linux,code = <0x104>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts
index 9d16ef8..2400c99 100644
--- a/arch/arm/boot/dts/at91sam9m10g45ek.dts
+++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts
@@ -24,15 +24,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 		      clock-frequency = <32768>;
 		};
@@ -323,14 +314,14 @@
 			label = "left_click";
 			gpios = <&pioB 6 GPIO_ACTIVE_LOW>;
 			linux,code = <272>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		right_click {
 			label = "right_click";
 			gpios = <&pioB 7 GPIO_ACTIVE_LOW>;
 			linux,code = <273>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		left {
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index acf3451..ca4ddf8 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -23,15 +23,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <16000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -219,7 +210,7 @@
 			label = "Enter";
 			gpios = <&pioB 3 GPIO_ACTIVE_LOW>;
 			linux,code = <28>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9rlek.dts b/arch/arm/boot/dts/at91sam9rlek.dts
index 558c9f2..f10566f 100644
--- a/arch/arm/boot/dts/at91sam9rlek.dts
+++ b/arch/arm/boot/dts/at91sam9rlek.dts
@@ -22,15 +22,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -225,14 +216,14 @@
 			label = "right_click";
 			gpios = <&pioB 0 GPIO_ACTIVE_LOW>;
 			linux,code = <273>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		left_click {
 			label = "left_click";
 			gpios = <&pioB 1 GPIO_ACTIVE_LOW>;
 			linux,code = <272>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9x5cm.dtsi b/arch/arm/boot/dts/at91sam9x5cm.dtsi
index 26112eb..b098ad8 100644
--- a/arch/arm/boot/dts/at91sam9x5cm.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5cm.dtsi
@@ -13,17 +13,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-	};
-
-	clocks {
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index bc672fb..fe99231 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1459,8 +1459,8 @@
 			interrupt-names = "tx", "rx";
 			dmas = <&sdma_xbar 133>, <&sdma_xbar 132>;
 			dma-names = "tx", "rx";
-			clocks = <&mcasp3_ahclkx_mux>;
-			clock-names = "fck";
+			clocks = <&mcasp3_aux_gfclk_mux>, <&mcasp3_ahclkx_mux>;
+			clock-names = "fck", "ahclkx";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index feb9d34..f818ea4 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -486,7 +486,10 @@
 				compatible = "fsl,imx27-usb";
 				reg = <0x10024000 0x200>;
 				interrupts = <56>;
-				clocks = <&clks IMX27_CLK_USB_IPG_GATE>;
+				clocks = <&clks IMX27_CLK_USB_IPG_GATE>,
+					<&clks IMX27_CLK_USB_AHB_GATE>,
+					<&clks IMX27_CLK_USB_DIV>;
+				clock-names = "ipg", "ahb", "per";
 				fsl,usbmisc = <&usbmisc 0>;
 				status = "disabled";
 			};
@@ -495,7 +498,10 @@
 				compatible = "fsl,imx27-usb";
 				reg = <0x10024200 0x200>;
 				interrupts = <54>;
-				clocks = <&clks IMX27_CLK_USB_IPG_GATE>;
+				clocks = <&clks IMX27_CLK_USB_IPG_GATE>,
+					<&clks IMX27_CLK_USB_AHB_GATE>,
+					<&clks IMX27_CLK_USB_DIV>;
+				clock-names = "ipg", "ahb", "per";
 				fsl,usbmisc = <&usbmisc 1>;
 				dr_mode = "host";
 				status = "disabled";
@@ -505,7 +511,10 @@
 				compatible = "fsl,imx27-usb";
 				reg = <0x10024400 0x200>;
 				interrupts = <55>;
-				clocks = <&clks IMX27_CLK_USB_IPG_GATE>;
+				clocks = <&clks IMX27_CLK_USB_IPG_GATE>,
+					<&clks IMX27_CLK_USB_AHB_GATE>,
+					<&clks IMX27_CLK_USB_DIV>;
+				clock-names = "ipg", "ahb", "per";
 				fsl,usbmisc = <&usbmisc 2>;
 				dr_mode = "host";
 				status = "disabled";
@@ -515,7 +524,6 @@
 				#index-cells = <1>;
 				compatible = "fsl,imx27-usbmisc";
 				reg = <0x10024600 0x200>;
-				clocks = <&clks IMX27_CLK_USB_AHB_GATE>;
 			};
 
 			sahara2: sahara@10025000 {
diff --git a/arch/arm/boot/dts/k2l-netcp.dtsi b/arch/arm/boot/dts/k2l-netcp.dtsi
index 01aef23..5acbd0d 100644
--- a/arch/arm/boot/dts/k2l-netcp.dtsi
+++ b/arch/arm/boot/dts/k2l-netcp.dtsi
@@ -137,7 +137,7 @@
 	/* NetCP address range */
 	ranges = <0 0x26000000 0x1000000>;
 
-	clocks = <&papllclk>, <&clkcpgmac>, <&chipclk12>;
+	clocks = <&clkosr>, <&papllclk>, <&clkcpgmac>, <&chipclk12>;
 	dma-coherent;
 
 	ti,navigator-dmas = <&dma_gbe 0>,
diff --git a/arch/arm/boot/dts/kirkwood-ts219.dtsi b/arch/arm/boot/dts/kirkwood-ts219.dtsi
index c56ab6b..0e46560 100644
--- a/arch/arm/boot/dts/kirkwood-ts219.dtsi
+++ b/arch/arm/boot/dts/kirkwood-ts219.dtsi
@@ -40,7 +40,7 @@
 		};
 		poweroff@12100 {
 			compatible = "qnap,power-off";
-			reg = <0x12000 0x100>;
+			reg = <0x12100 0x100>;
 			clocks = <&gate_clk 7>;
 		};
 		spi@10600 {
diff --git a/arch/arm/boot/dts/rk3288-veyron-minnie.dts b/arch/arm/boot/dts/rk3288-veyron-minnie.dts
index 8fd8ef2..85f0373 100644
--- a/arch/arm/boot/dts/rk3288-veyron-minnie.dts
+++ b/arch/arm/boot/dts/rk3288-veyron-minnie.dts
@@ -86,6 +86,10 @@
 	};
 };
 
+&emmc {
+	/delete-property/mmc-hs200-1_8v;
+};
+
 &gpio_keys {
 	pinctrl-0 = <&pwr_key_l &ap_lid_int_l &volum_down_l &volum_up_l>;
 
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 6a79c9c..04ea209 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -452,8 +452,10 @@
 		clock-names = "tsadc", "apb_pclk";
 		resets = <&cru SRST_TSADC>;
 		reset-names = "tsadc-apb";
-		pinctrl-names = "default";
-		pinctrl-0 = <&otp_out>;
+		pinctrl-names = "init", "default", "sleep";
+		pinctrl-0 = <&otp_gpio>;
+		pinctrl-1 = <&otp_out>;
+		pinctrl-2 = <&otp_gpio>;
 		#thermal-sensor-cells = <1>;
 		rockchip,hw-tshut-temp = <95000>;
 		status = "disabled";
@@ -1395,6 +1397,10 @@
 		};
 
 		tsadc {
+			otp_gpio: otp-gpio {
+				rockchip,pins = <0 10 RK_FUNC_GPIO &pcfg_pull_none>;
+			};
+
 			otp_out: otp-out {
 				rockchip,pins = <0 10 RK_FUNC_1 &pcfg_pull_none>;
 			};
diff --git a/arch/arm/boot/dts/sama5d35ek.dts b/arch/arm/boot/dts/sama5d35ek.dts
index d9a9aca..e812f5c 100644
--- a/arch/arm/boot/dts/sama5d35ek.dts
+++ b/arch/arm/boot/dts/sama5d35ek.dts
@@ -49,7 +49,7 @@
 			label = "pb_user1";
 			gpios = <&pioE 27 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi
index 15bbaf6..2193637 100644
--- a/arch/arm/boot/dts/sama5d4.dtsi
+++ b/arch/arm/boot/dts/sama5d4.dtsi
@@ -1300,7 +1300,7 @@
 			};
 
 			watchdog@fc068640 {
-				compatible = "atmel,at91sam9260-wdt";
+				compatible = "atmel,sama5d4-wdt";
 				reg = <0xfc068640 0x10>;
 				clocks = <&clk32k>;
 				status = "disabled";
diff --git a/arch/arm/boot/dts/usb_a9260_common.dtsi b/arch/arm/boot/dts/usb_a9260_common.dtsi
index 12edafe..9beea89 100644
--- a/arch/arm/boot/dts/usb_a9260_common.dtsi
+++ b/arch/arm/boot/dts/usb_a9260_common.dtsi
@@ -115,7 +115,7 @@
 			label = "user_pb";
 			gpios = <&pioB 10 GPIO_ACTIVE_LOW>;
 			linux,code = <28>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/usb_a9263.dts b/arch/arm/boot/dts/usb_a9263.dts
index 68c0de3..8cc6edb 100644
--- a/arch/arm/boot/dts/usb_a9263.dts
+++ b/arch/arm/boot/dts/usb_a9263.dts
@@ -143,7 +143,7 @@
 			label = "user_pb";
 			gpios = <&pioB 10 GPIO_ACTIVE_LOW>;
 			linux,code = <28>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index 6736bae..0d5acc2 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -158,7 +158,7 @@
 				interrupts = <67 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks VF610_CLK_DSPI0>;
 				clock-names = "dspi";
-				spi-num-chipselects = <5>;
+				spi-num-chipselects = <6>;
 				status = "disabled";
 			};
 
@@ -170,7 +170,7 @@
 				interrupts = <68 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks VF610_CLK_DSPI1>;
 				clock-names = "dspi";
-				spi-num-chipselects = <5>;
+				spi-num-chipselects = <4>;
 				status = "disabled";
 			};
 
@@ -461,6 +461,8 @@
 				clock-names = "adc";
 				#io-channel-cells = <1>;
 				status = "disabled";
+				fsl,adck-max-frequency = <30000000>, <40000000>,
+							<20000000>;
 			};
 
 			esdhc0: esdhc@400b1000 {
@@ -472,8 +474,6 @@
 					<&clks VF610_CLK_ESDHC0>;
 				clock-names = "ipg", "ahb", "per";
 				status = "disabled";
-				fsl,adck-max-frequency = <30000000>, <40000000>,
-							<20000000>;
 			};
 
 			esdhc1: esdhc@400b2000 {
diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig
index 1b1e5ac..e4b1be6 100644
--- a/arch/arm/configs/at91_dt_defconfig
+++ b/arch/arm/configs/at91_dt_defconfig
@@ -125,7 +125,6 @@
 # CONFIG_HWMON is not set
 CONFIG_WATCHDOG=y
 CONFIG_AT91SAM9X_WATCHDOG=y
-CONFIG_SSB=m
 CONFIG_MFD_ATMEL_HLCDC=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig
index a0c57ac..63f7e6c 100644
--- a/arch/arm/configs/sama5_defconfig
+++ b/arch/arm/configs/sama5_defconfig
@@ -129,7 +129,6 @@
 CONFIG_POWER_SUPPLY=y
 CONFIG_POWER_RESET=y
 # CONFIG_HWMON is not set
-CONFIG_SSB=m
 CONFIG_MFD_ATMEL_FLEXCOM=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index be1d07d..1bd9510 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -40,6 +40,11 @@
 #define arch_trigger_all_cpu_backtrace(x) arch_trigger_all_cpu_backtrace(x)
 #endif
 
+static inline int nr_legacy_irqs(void)
+{
+	return NR_IRQS_LEGACY;
+}
+
 #endif
 
 #endif
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 7a2a32a..ede692f 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -416,6 +416,7 @@
 #define __NR_execveat			(__NR_SYSCALL_BASE+387)
 #define __NR_userfaultfd		(__NR_SYSCALL_BASE+388)
 #define __NR_membarrier			(__NR_SYSCALL_BASE+389)
+#define __NR_mlock2			(__NR_SYSCALL_BASE+390)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 6551d28..066f7f9 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -17,11 +17,6 @@
 #include <asm/mach/pci.h>
 
 static int debug_pci;
-static resource_size_t (*align_resource)(struct pci_dev *dev,
-		  const struct resource *res,
-		  resource_size_t start,
-		  resource_size_t size,
-		  resource_size_t align) = NULL;
 
 /*
  * We can't use pci_get_device() here since we are
@@ -461,7 +456,6 @@
 		sys->busnr   = busnr;
 		sys->swizzle = hw->swizzle;
 		sys->map_irq = hw->map_irq;
-		align_resource = hw->align_resource;
 		INIT_LIST_HEAD(&sys->resources);
 
 		if (hw->private_data)
@@ -470,6 +464,8 @@
 		ret = hw->setup(nr, sys);
 
 		if (ret > 0) {
+			struct pci_host_bridge *host_bridge;
+
 			ret = pcibios_init_resources(nr, sys);
 			if (ret)  {
 				kfree(sys);
@@ -491,6 +487,9 @@
 			busnr = sys->bus->busn_res.end + 1;
 
 			list_add(&sys->node, head);
+
+			host_bridge = pci_find_host_bridge(sys->bus);
+			host_bridge->align_resource = hw->align_resource;
 		} else {
 			kfree(sys);
 			if (ret < 0)
@@ -578,14 +577,18 @@
 {
 	struct pci_dev *dev = data;
 	resource_size_t start = res->start;
+	struct pci_host_bridge *host_bridge;
 
 	if (res->flags & IORESOURCE_IO && start & 0x300)
 		start = (start + 0x3ff) & ~0x3ff;
 
 	start = (start + align - 1) & ~(align - 1);
 
-	if (align_resource)
-		return align_resource(dev, res, start, size, align);
+	host_bridge = pci_find_host_bridge(dev->bus);
+
+	if (host_bridge->align_resource)
+		return host_bridge->align_resource(dev, res,
+				start, size, align);
 
 	return start;
 }
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index fde6c88..ac368bb 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -399,6 +399,7 @@
 		CALL(sys_execveat)
 		CALL(sys_userfaultfd)
 		CALL(sys_membarrier)
+		CALL(sys_mlock2)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index eab83b2..e06fd29 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -564,17 +564,12 @@
 			vcpu_sleep(vcpu);
 
 		/*
-		 * Disarming the background timer must be done in a
-		 * preemptible context, as this call may sleep.
-		 */
-		kvm_timer_flush_hwstate(vcpu);
-
-		/*
 		 * Preparing the interrupts to be injected also
 		 * involves poking the GIC, which must be done in a
 		 * non-preemptible context.
 		 */
 		preempt_disable();
+		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);
 
 		local_irq_disable();
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 6984342..7dace90 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -98,6 +98,11 @@
 	__kvm_flush_dcache_pud(pud);
 }
 
+static bool kvm_is_device_pfn(unsigned long pfn)
+{
+	return !pfn_valid(pfn);
+}
+
 /**
  * stage2_dissolve_pmd() - clear and flush huge PMD entry
  * @kvm:	pointer to kvm structure.
@@ -213,7 +218,7 @@
 			kvm_tlb_flush_vmid_ipa(kvm, addr);
 
 			/* No need to invalidate the cache for device mappings */
-			if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+			if (!kvm_is_device_pfn(__phys_to_pfn(addr)))
 				kvm_flush_dcache_pte(old_pte);
 
 			put_page(virt_to_page(pte));
@@ -305,8 +310,7 @@
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		if (!pte_none(*pte) &&
-		    (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+		if (!pte_none(*pte) && !kvm_is_device_pfn(__phys_to_pfn(addr)))
 			kvm_flush_dcache_pte(*pte);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
@@ -1037,11 +1041,6 @@
 	return kvm_vcpu_dabt_iswrite(vcpu);
 }
 
-static bool kvm_is_device_pfn(unsigned long pfn)
-{
-	return !pfn_valid(pfn);
-}
-
 /**
  * stage2_wp_ptes - write protect PMD range
  * @pmd:	pointer to pmd entry
diff --git a/arch/arm/mach-dove/include/mach/entry-macro.S b/arch/arm/mach-dove/include/mach/entry-macro.S
index 72d622b..df1d44b 100644
--- a/arch/arm/mach-dove/include/mach/entry-macro.S
+++ b/arch/arm/mach-dove/include/mach/entry-macro.S
@@ -18,13 +18,13 @@
 	@ check low interrupts
 	ldr	\irqstat, [\base, #IRQ_CAUSE_LOW_OFF]
 	ldr	\tmp, [\base, #IRQ_MASK_LOW_OFF]
-	mov	\irqnr, #31
+	mov	\irqnr, #32
 	ands	\irqstat, \irqstat, \tmp
 
 	@ if no low interrupts set, check high interrupts
 	ldreq	\irqstat, [\base, #IRQ_CAUSE_HIGH_OFF]
 	ldreq	\tmp, [\base, #IRQ_MASK_HIGH_OFF]
-	moveq	\irqnr, #63
+	moveq	\irqnr, #64
 	andeqs	\irqstat, \irqstat, \tmp
 
 	@ find first active interrupt source
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 8e7976a..cfc696b 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -177,6 +177,7 @@
 	.irq_unmask		= imx_gpc_irq_unmask,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_set_wake		= imx_gpc_irq_set_wake,
+	.irq_set_type           = irq_chip_set_type_parent,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= irq_chip_set_affinity_parent,
 #endif
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 5305ec7..79e1f87 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -143,9 +143,9 @@
 		 * Ensure that CPU power state is set to ON to avoid CPU
 		 * powerdomain transition on wfi
 		 */
-		clkdm_wakeup(cpu1_clkdm);
-		omap_set_pwrdm_state(cpu1_pwrdm, PWRDM_POWER_ON);
-		clkdm_allow_idle(cpu1_clkdm);
+		clkdm_wakeup_nolock(cpu1_clkdm);
+		pwrdm_set_next_pwrst(cpu1_pwrdm, PWRDM_POWER_ON);
+		clkdm_allow_idle_nolock(cpu1_clkdm);
 
 		if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD)) {
 			while (gic_dist_disabled()) {
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index cc8a987..48495ad 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -890,6 +890,36 @@
 	return ret;
 }
 
+static void _enable_optional_clocks(struct omap_hwmod *oh)
+{
+	struct omap_hwmod_opt_clk *oc;
+	int i;
+
+	pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name);
+
+	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+		if (oc->_clk) {
+			pr_debug("omap_hwmod: enable %s:%s\n", oc->role,
+				 __clk_get_name(oc->_clk));
+			clk_enable(oc->_clk);
+		}
+}
+
+static void _disable_optional_clocks(struct omap_hwmod *oh)
+{
+	struct omap_hwmod_opt_clk *oc;
+	int i;
+
+	pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name);
+
+	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+		if (oc->_clk) {
+			pr_debug("omap_hwmod: disable %s:%s\n", oc->role,
+				 __clk_get_name(oc->_clk));
+			clk_disable(oc->_clk);
+		}
+}
+
 /**
  * _enable_clocks - enable hwmod main clock and interface clocks
  * @oh: struct omap_hwmod *
@@ -917,6 +947,9 @@
 			clk_enable(os->_clk);
 	}
 
+	if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
+		_enable_optional_clocks(oh);
+
 	/* The opt clocks are controlled by the device driver. */
 
 	return 0;
@@ -948,41 +981,14 @@
 			clk_disable(os->_clk);
 	}
 
+	if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
+		_disable_optional_clocks(oh);
+
 	/* The opt clocks are controlled by the device driver. */
 
 	return 0;
 }
 
-static void _enable_optional_clocks(struct omap_hwmod *oh)
-{
-	struct omap_hwmod_opt_clk *oc;
-	int i;
-
-	pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name);
-
-	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
-		if (oc->_clk) {
-			pr_debug("omap_hwmod: enable %s:%s\n", oc->role,
-				 __clk_get_name(oc->_clk));
-			clk_enable(oc->_clk);
-		}
-}
-
-static void _disable_optional_clocks(struct omap_hwmod *oh)
-{
-	struct omap_hwmod_opt_clk *oc;
-	int i;
-
-	pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name);
-
-	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
-		if (oc->_clk) {
-			pr_debug("omap_hwmod: disable %s:%s\n", oc->role,
-				 __clk_get_name(oc->_clk));
-			clk_disable(oc->_clk);
-		}
-}
-
 /**
  * _omap4_enable_module - enable CLKCTRL modulemode on OMAP4
  * @oh: struct omap_hwmod *
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index ca6df1a..76bce11 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -523,6 +523,8 @@
  * HWMOD_RECONFIG_IO_CHAIN: omap_hwmod code needs to reconfigure wake-up 
  *     events by calling _reconfigure_io_chain() when a device is enabled
  *     or idled.
+ * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to
+ *     operate and they need to be handled at the same time as the main_clk.
  */
 #define HWMOD_SWSUP_SIDLE			(1 << 0)
 #define HWMOD_SWSUP_MSTANDBY			(1 << 1)
@@ -538,6 +540,7 @@
 #define HWMOD_FORCE_MSTANDBY			(1 << 11)
 #define HWMOD_SWSUP_SIDLE_ACT			(1 << 12)
 #define HWMOD_RECONFIG_IO_CHAIN			(1 << 13)
+#define HWMOD_OPT_CLKS_NEEDED			(1 << 14)
 
 /*
  * omap_hwmod._int_flags definitions
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 51d1ecb..ee4e044 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1298,6 +1298,44 @@
 };
 
 /*
+ * 'mcasp' class
+ *
+ */
+static struct omap_hwmod_class_sysconfig dra7xx_mcasp_sysc = {
+	.sysc_offs	= 0x0004,
+	.sysc_flags	= SYSC_HAS_SIDLEMODE,
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
+	.sysc_fields	= &omap_hwmod_sysc_type3,
+};
+
+static struct omap_hwmod_class dra7xx_mcasp_hwmod_class = {
+	.name	= "mcasp",
+	.sysc	= &dra7xx_mcasp_sysc,
+};
+
+/* mcasp3 */
+static struct omap_hwmod_opt_clk mcasp3_opt_clks[] = {
+	{ .role = "ahclkx", .clk = "mcasp3_ahclkx_mux" },
+};
+
+static struct omap_hwmod dra7xx_mcasp3_hwmod = {
+	.name		= "mcasp3",
+	.class		= &dra7xx_mcasp_hwmod_class,
+	.clkdm_name	= "l4per2_clkdm",
+	.main_clk	= "mcasp3_aux_gfclk_mux",
+	.flags		= HWMOD_OPT_CLKS_NEEDED,
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER2_MCASP3_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER2_MCASP3_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.opt_clks	= mcasp3_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(mcasp3_opt_clks),
+};
+
+/*
  * 'mmc' class
  *
  */
@@ -2566,6 +2604,22 @@
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
+/* l4_per2 -> mcasp3 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per2__mcasp3 = {
+	.master		= &dra7xx_l4_per2_hwmod,
+	.slave		= &dra7xx_mcasp3_hwmod,
+	.clk		= "l4_root_clk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l3_main_1 -> mcasp3 */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__mcasp3 = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_mcasp3_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
 /* l4_per1 -> elm */
 static struct omap_hwmod_ocp_if dra7xx_l4_per1__elm = {
 	.master		= &dra7xx_l4_per1_hwmod,
@@ -3308,6 +3362,8 @@
 	&dra7xx_l4_wkup__dcan1,
 	&dra7xx_l4_per2__dcan2,
 	&dra7xx_l4_per2__cpgmac0,
+	&dra7xx_l4_per2__mcasp3,
+	&dra7xx_l3_main_1__mcasp3,
 	&dra7xx_gmac__mdio,
 	&dra7xx_l4_cfg__dma_system,
 	&dra7xx_l3_main_1__dss,
diff --git a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
index b1288f5..6256052 100644
--- a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
@@ -144,6 +144,7 @@
 	.name		= "l4_ls",
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.class		= &l4_hwmod_class,
+	.flags		= HWMOD_NO_IDLEST,
 };
 
 /*
@@ -155,6 +156,7 @@
 	.name		= "l4_hs",
 	.clkdm_name	= "alwon_l3_med_clkdm",
 	.class		= &l4_hwmod_class,
+	.flags		= HWMOD_NO_IDLEST,
 };
 
 /* L3 slow -> L4 ls peripheral interface running at 125MHz */
@@ -850,6 +852,7 @@
 	.name		= "emac0",
 	.clkdm_name	= "alwon_ethernet_clkdm",
 	.class		= &dm816x_emac_hwmod_class,
+	.flags		= HWMOD_NO_IDLEST,
 };
 
 static struct omap_hwmod_ocp_if dm81xx_l4_hs__emac0 = {
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 1dfe346..5814477 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -24,9 +24,6 @@
 #include <linux/platform_data/iommu-omap.h>
 #include <linux/platform_data/wkup_m3.h>
 
-#include <asm/siginfo.h>
-#include <asm/signal.h>
-
 #include "common.h"
 #include "common-board-devices.h"
 #include "dss-common.h"
@@ -385,29 +382,6 @@
 }
 #endif /* CONFIG_ARCH_OMAP3 */
 
-#ifdef CONFIG_SOC_TI81XX
-static int fault_fixed_up;
-
-static int t410_abort_handler(unsigned long addr, unsigned int fsr,
-			      struct pt_regs *regs)
-{
-	if ((fsr == 0x406 || fsr == 0xc06) && !fault_fixed_up) {
-		pr_warn("External imprecise Data abort at addr=%#lx, fsr=%#x ignored.\n",
-			addr, fsr);
-		fault_fixed_up = 1;
-		return 0;
-	}
-
-	return 1;
-}
-
-static void __init t410_abort_init(void)
-{
-	hook_fault_code(16 + 6, t410_abort_handler, SIGBUS, BUS_OBJERR,
-			"imprecise external abort");
-}
-#endif
-
 #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5)
 static struct iommu_platform_data omap4_iommu_pdata = {
 	.reset_name = "mmu_cache",
@@ -536,9 +510,6 @@
 	{ "openpandora,omap3-pandora-600mhz", omap3_pandora_legacy_init, },
 	{ "openpandora,omap3-pandora-1ghz", omap3_pandora_legacy_init, },
 #endif
-#ifdef CONFIG_SOC_TI81XX
-	{ "hp,t410", t410_abort_init, },
-#endif
 #ifdef CONFIG_SOC_OMAP5
 	{ "ti,omap5-uevm", omap5_uevm_legacy_init, },
 #endif
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 87b98bf9..2dbd378 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -301,11 +301,11 @@
 	if (omap_irq_pending())
 		return;
 
-	trace_cpu_idle(1, smp_processor_id());
+	trace_cpu_idle_rcuidle(1, smp_processor_id());
 
 	omap_sram_idle();
 
-	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 #ifdef CONFIG_SUSPEND
diff --git a/arch/arm/mach-orion5x/include/mach/entry-macro.S b/arch/arm/mach-orion5x/include/mach/entry-macro.S
index 79eb502..73919a3 100644
--- a/arch/arm/mach-orion5x/include/mach/entry-macro.S
+++ b/arch/arm/mach-orion5x/include/mach/entry-macro.S
@@ -21,5 +21,5 @@
 	@ find cause bits that are unmasked
 	ands	\irqstat, \irqstat, \tmp	@ clear Z flag if any
 	clzne	\irqnr,	\irqstat		@ calc irqnr
-	rsbne	\irqnr, \irqnr, #31
+	rsbne	\irqnr, \irqnr, #32
 	.endm
diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c
index 13eba2b..8fbfb10 100644
--- a/arch/arm/mach-pxa/palm27x.c
+++ b/arch/arm/mach-pxa/palm27x.c
@@ -344,7 +344,7 @@
 {
 	palm_bl_power	= bl;
 	palm_lcd_power	= lcd;
-	pwm_add_lookup(palm27x_pwm_lookup, ARRAY_SIZE(palm27x_pwm_lookup));
+	pwm_add_table(palm27x_pwm_lookup, ARRAY_SIZE(palm27x_pwm_lookup));
 	platform_device_register(&palm27x_backlight);
 }
 #endif
diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c
index aebf6de..0b5c387 100644
--- a/arch/arm/mach-pxa/palmtc.c
+++ b/arch/arm/mach-pxa/palmtc.c
@@ -169,7 +169,7 @@
 #if defined(CONFIG_BACKLIGHT_PWM) || defined(CONFIG_BACKLIGHT_PWM_MODULE)
 static struct pwm_lookup palmtc_pwm_lookup[] = {
 	PWM_LOOKUP("pxa25x-pwm.1", 0, "pwm-backlight.0", NULL, PALMTC_PERIOD_NS,
-		   PWM_PERIOD_NORMAL),
+		   PWM_POLARITY_NORMAL),
 };
 
 static struct platform_pwm_backlight_data palmtc_backlight_data = {
diff --git a/arch/arm/mach-shmobile/setup-r8a7793.c b/arch/arm/mach-shmobile/setup-r8a7793.c
index 1d2825c..5fce87f 100644
--- a/arch/arm/mach-shmobile/setup-r8a7793.c
+++ b/arch/arm/mach-shmobile/setup-r8a7793.c
@@ -19,7 +19,7 @@
 #include "common.h"
 #include "rcar-gen2.h"
 
-static const char *r8a7793_boards_compat_dt[] __initconst = {
+static const char * const r8a7793_boards_compat_dt[] __initconst = {
 	"renesas,r8a7793",
 	NULL,
 };
diff --git a/arch/arm/mach-zx/Kconfig b/arch/arm/mach-zx/Kconfig
index 7fdc5bf..446334a 100644
--- a/arch/arm/mach-zx/Kconfig
+++ b/arch/arm/mach-zx/Kconfig
@@ -13,7 +13,7 @@
 	select ARM_GLOBAL_TIMER
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
-	select PM_GENERIC_DOMAINS
+	select PM_GENERIC_DOMAINS if PM
 	help
 	  Support for ZTE ZX296702 SoC which is a dual core CortexA9MP
 endif
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9ac16a4..871f217 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -49,7 +49,7 @@
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_BITREVERSE
 	select HAVE_ARCH_JUMP_LABEL
-	select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP
+	select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
@@ -316,6 +316,27 @@
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_834220
+	bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault"
+	depends on KVM
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 834220 on Cortex-A57 parts up to r1p2.
+
+	  Affected Cortex-A57 parts might report a Stage 2 translation
+	  fault as the result of a Stage 1 fault for load crossing a
+	  page boundary when there is a permission or device memory
+	  alignment fault at Stage 1 and a translation fault at Stage 2.
+
+	  The workaround is to verify that the Stage 1 translation
+	  doesn't generate a fault before handling the Stage 2 fault.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
 config ARM64_ERRATUM_845719
 	bool "Cortex-A53: 845719: a load might read incorrect data"
 	depends on COMPAT
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
index ce47792..f7bd9bf 100644
--- a/arch/arm64/crypto/aes-ce-cipher.c
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -237,7 +237,7 @@
 static struct crypto_alg aes_alg = {
 	.cra_name		= "aes",
 	.cra_driver_name	= "aes-ce",
-	.cra_priority		= 300,
+	.cra_priority		= 250,
 	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		= AES_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 624f967..9622eb4 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -64,27 +64,31 @@
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1;						\
+	union { typeof(*p) __val; char __c[1]; } __u;			\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("ldarb %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u8 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("ldarh %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u16 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("ldar %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u32 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("ldar %0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u64 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	}								\
-	___p1;								\
+	__u.__val;							\
 })
 
 #define read_barrier_depends()		do { } while(0)
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 7fbed69..eb8432b 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -23,7 +23,6 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
-#include <linux/ptrace.h>
 
 #define COMPAT_USER_HZ		100
 #ifdef __AARCH64EB__
@@ -234,7 +233,7 @@
 	return (u32)(unsigned long)uptr;
 }
 
-#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
+#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current)))
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 11d5bb0f..8f271b8 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -29,8 +29,9 @@
 #define ARM64_HAS_PAN				4
 #define ARM64_HAS_LSE_ATOMICS			5
 #define ARM64_WORKAROUND_CAVIUM_23154		6
+#define ARM64_WORKAROUND_834220			7
 
-#define ARM64_NCAPS				7
+#define ARM64_NCAPS				8
 
 #ifndef __ASSEMBLY__
 
@@ -46,8 +47,12 @@
 #define FTR_STRICT	true	/* SANITY check strict matching required */
 #define FTR_NONSTRICT	false	/* SANITY check ignored */
 
+#define FTR_SIGNED	true	/* Value should be treated as signed */
+#define FTR_UNSIGNED	false	/* Value should be treated as unsigned */
+
 struct arm64_ftr_bits {
-	bool		strict;	  /* CPU Sanity check: strict matching required ? */
+	bool		sign;	/* Value is signed ? */
+	bool		strict;	/* CPU Sanity check: strict matching required ? */
 	enum ftr_type	type;
 	u8		shift;
 	u8		width;
@@ -123,6 +128,18 @@
 	return cpuid_feature_extract_field_width(features, field, 4);
 }
 
+static inline unsigned int __attribute_const__
+cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width)
+{
+	return (u64)(features << (64 - width - field)) >> (64 - width);
+}
+
+static inline unsigned int __attribute_const__
+cpuid_feature_extract_unsigned_field(u64 features, int field)
+{
+	return cpuid_feature_extract_unsigned_field_width(features, field, 4);
+}
+
 static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
 {
 	return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
@@ -130,7 +147,9 @@
 
 static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val)
 {
-	return cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width);
+	return ftrp->sign ?
+		cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width) :
+		cpuid_feature_extract_unsigned_field_width(val, ftrp->shift, ftrp->width);
 }
 
 static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 54d0ead..61e08f3 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -18,7 +18,6 @@
 
 #ifdef __KERNEL__
 
-#include <linux/acpi.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
@@ -26,22 +25,16 @@
 #include <asm/xen/hypervisor.h>
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
-extern struct dma_map_ops *dma_ops;
 extern struct dma_map_ops dummy_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
-	if (unlikely(!dev))
-		return dma_ops;
-	else if (dev->archdata.dma_ops)
+	if (dev && dev->archdata.dma_ops)
 		return dev->archdata.dma_ops;
-	else if (acpi_disabled)
-		return dma_ops;
 
 	/*
-	 * When ACPI is enabled, if arch_set_dma_ops is not called,
-	 * we will disable device DMA capability by setting it
-	 * to dummy_dma_ops.
+	 * We expect no ISA devices, and all other DMA masters are expected to
+	 * have someone call arch_setup_dma_ops at device creation time.
 	 */
 	return &dummy_dma_ops;
 }
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index e54415e..9732908 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -138,16 +138,18 @@
 /* Determine number of BRP registers available. */
 static inline int get_num_brps(void)
 {
+	u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1);
 	return 1 +
-		cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+		cpuid_feature_extract_unsigned_field(dfr0,
 						ID_AA64DFR0_BRPS_SHIFT);
 }
 
 /* Determine number of WRP registers available. */
 static inline int get_num_wrps(void)
 {
+	u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1);
 	return 1 +
-		cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+		cpuid_feature_extract_unsigned_field(dfr0,
 						ID_AA64DFR0_WRPS_SHIFT);
 }
 
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 23eb450..8e8d306 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -7,4 +7,9 @@
 
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
+static inline int nr_legacy_irqs(void)
+{
+	return 0;
+}
+
 #endif
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 17e92f0..3ca894e 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -99,11 +99,13 @@
 	*vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT;
 }
 
+/*
+ * vcpu_reg should always be passed a register number coming from a
+ * read of ESR_EL2. Otherwise, it may give the wrong result on AArch32
+ * with banked registers.
+ */
 static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num)
 {
-	if (vcpu_mode_is_32bit(vcpu))
-		return vcpu_reg32(vcpu, reg_num);
-
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num];
 }
 
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index c0e8789..2416578 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -101,7 +101,7 @@
 #define destroy_context(mm)		do { } while(0)
 void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
 
-#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
+#define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
 /*
  * This is called when "tsk" is about to enter lazy TLB mode.
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 9819a94..7e074f9 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -81,6 +81,7 @@
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
+#define PAGE_KERNEL_ROX	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 24926f2..feb6b4e 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -75,6 +75,15 @@
 			   (1 << MIDR_VARIANT_SHIFT) | 2),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_834220
+	{
+	/* Cortex-A57 r0p0 - r1p2 */
+		.desc = "ARM erratum 834220",
+		.capability = ARM64_WORKAROUND_834220,
+		MIDR_RANGE(MIDR_CORTEX_A57, 0x00,
+			   (1 << MIDR_VARIANT_SHIFT) | 2),
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_845719
 	{
 	/* Cortex-A53 r0p[01234] */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index c8cf892..0669c63 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -44,8 +44,9 @@
 
 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 
-#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+#define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
 	{						\
+		.sign = SIGNED,				\
 		.strict = STRICT,			\
 		.type = TYPE,				\
 		.shift = SHIFT,				\
@@ -53,6 +54,14 @@
 		.safe_val = SAFE_VAL,			\
 	}
 
+/* Define a feature with signed values */
+#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+	__ARM64_FTR_BITS(FTR_SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL)
+
+/* Define a feature with unsigned value */
+#define U_ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+	__ARM64_FTR_BITS(FTR_UNSIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL)
+
 #define ARM64_FTR_END					\
 	{						\
 		.width = 0,				\
@@ -99,7 +108,7 @@
 	 * Differing PARange is fine as long as all peripherals and memory are mapped
 	 * within the minimum PARange of all CPUs
 	 */
-	ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -115,18 +124,18 @@
 };
 
 static struct arm64_ftr_bits ftr_ctr[] = {
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1),	/* RAO */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1),	/* RAO */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),	/* CWG */
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* ERG */
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1),	/* DminLine */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),	/* CWG */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* ERG */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1),	/* DminLine */
 	/*
 	 * Linux can handle differing I-cache policies. Userspace JITs will
 	 * make use of *minLine
 	 */
-	ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0),	/* L1Ip */
+	U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0),	/* L1Ip */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 10, 0),	/* RAZ */
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* IminLine */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* IminLine */
 	ARM64_FTR_END,
 };
 
@@ -144,12 +153,12 @@
 
 static struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
 	ARM64_FTR_END,
 };
 
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 706679d..212ae63 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -30,6 +30,7 @@
 #include <linux/seq_file.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/delay.h>
 
 /*
  * In case the boot CPU is hotpluggable, we record its initial state and
@@ -112,6 +113,10 @@
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
 
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   loops_per_jiffy / (500000UL/HZ),
+			   loops_per_jiffy / (5000UL/HZ) % 100);
+
 		/*
 		 * Dump out the common processor features in a single line.
 		 * Userspace should read the hwcaps with getauxval(AT_HWCAP)
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index de46b50..4eeb171 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -127,7 +127,11 @@
 	table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables;
 	config_tables = early_memremap(efi_to_phys(efi.systab->tables),
 				       table_size);
-
+	if (config_tables == NULL) {
+		pr_warn("Unable to map EFI config table array.\n");
+		retval = -ENOMEM;
+		goto out;
+	}
 	retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables,
 					 sizeof(efi_config_table_64_t), NULL);
 
@@ -209,6 +213,14 @@
 			 PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK)));
 	memmap.phys_map = params.mmap;
 	memmap.map = early_memremap(params.mmap, params.mmap_size);
+	if (memmap.map == NULL) {
+		/*
+		* If we are booting via UEFI, the UEFI memory map is the only
+		* description of memory we have, so there is little point in
+		* proceeding if we cannot access it.
+		*/
+		panic("Unable to map EFI memory map.\n");
+	}
 	memmap.map_end = memmap.map + params.mmap_size;
 	memmap.desc_size = params.desc_size;
 	memmap.desc_version = params.desc_ver;
@@ -224,8 +236,9 @@
 {
 	efi_memory_desc_t *md;
 
+	init_new_context(NULL, &efi_mm);
+
 	for_each_efi_memory_desc(&memmap, md) {
-		u64 paddr, npages, size;
 		pgprot_t prot;
 
 		if (!(md->attribute & EFI_MEMORY_RUNTIME))
@@ -233,11 +246,6 @@
 		if (md->virt_addr == 0)
 			return false;
 
-		paddr = md->phys_addr;
-		npages = md->num_pages;
-		memrange_efi_to_native(&paddr, &npages);
-		size = npages << PAGE_SHIFT;
-
 		pr_info("  EFI remap 0x%016llx => %p\n",
 			md->phys_addr, (void *)md->virt_addr);
 
@@ -254,7 +262,9 @@
 		else
 			prot = PAGE_KERNEL;
 
-		create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, prot);
+		create_pgd_mapping(&efi_mm, md->phys_addr, md->virt_addr,
+				   md->num_pages << EFI_PAGE_SHIFT, 
+				   __pgprot(pgprot_val(prot) | PTE_NG));
 	}
 	return true;
 }
@@ -270,12 +280,12 @@
 
 	if (!efi_enabled(EFI_BOOT)) {
 		pr_info("EFI services will not be available.\n");
-		return -1;
+		return 0;
 	}
 
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
-		return -1;
+		return 0;
 	}
 
 	pr_info("Remapping and enabling EFI services.\n");
@@ -285,7 +295,7 @@
 						   mapsize);
 	if (!memmap.map) {
 		pr_err("Failed to remap EFI memory map\n");
-		return -1;
+		return -ENOMEM;
 	}
 	memmap.map_end = memmap.map + mapsize;
 	efi.memmap = &memmap;
@@ -294,13 +304,13 @@
 						   sizeof(efi_system_table_t));
 	if (!efi.systab) {
 		pr_err("Failed to remap EFI System Table\n");
-		return -1;
+		return -ENOMEM;
 	}
 	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
 
 	if (!efi_virtmap_init()) {
 		pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n");
-		return -1;
+		return -ENOMEM;
 	}
 
 	/* Set up runtime services function pointers */
@@ -329,14 +339,7 @@
 
 static void efi_set_pgd(struct mm_struct *mm)
 {
-	if (mm == &init_mm)
-		cpu_set_reserved_ttbr0();
-	else
-		cpu_switch_mm(mm->pgd, mm);
-
-	local_flush_tlb_all();
-	if (icache_is_aivivt())
-		__local_flush_icache_all();
+	switch_mm(NULL, mm, NULL);
 }
 
 void efi_virtmap_load(void)
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index fce95e1..1095aa4 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -1,3 +1,4 @@
+#include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
 #include <asm/cacheflush.h>
@@ -71,6 +72,13 @@
 	local_dbg_save(flags);
 
 	/*
+	 * Function graph tracer state gets incosistent when the kernel
+	 * calls functions that never return (aka suspend finishers) hence
+	 * disable graph tracing during their execution.
+	 */
+	pause_graph_tracing();
+
+	/*
 	 * mm context saved on the stack, it will be restored when
 	 * the cpu comes out of reset through the identity mapped
 	 * page tables, so that the thread address space is properly
@@ -111,6 +119,8 @@
 			hw_breakpoint_restore(NULL);
 	}
 
+	unpause_graph_tracing();
+
 	/*
 	 * Restore pstate flags. OS lock and mdscr have been already
 	 * restored, so from this point onwards, debugging is fully
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 1599701..86c2898 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -864,6 +864,10 @@
 ENDPROC(__kvm_flush_vm_context)
 
 __kvm_hyp_panic:
+	// Stash PAR_EL1 before corrupting it in __restore_sysregs
+	mrs	x0, par_el1
+	push	x0, xzr
+
 	// Guess the context by looking at VTTBR:
 	// If zero, then we're already a host.
 	// Otherwise restore a minimal host context before panicing.
@@ -898,7 +902,7 @@
 	mrs	x3, esr_el2
 	mrs	x4, far_el2
 	mrs	x5, hpfar_el2
-	mrs	x6, par_el1
+	pop	x6, xzr		// active context PAR_EL1
 	mrs	x7, tpidr_el2
 
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
@@ -914,7 +918,7 @@
 ENDPROC(__kvm_hyp_panic)
 
 __hyp_panic_str:
-	.ascii	"HYP panic:\nPS:%08x PC:%p ESR:%p\nFAR:%p HPFAR:%p PAR:%p\nVCPU:%p\n\0"
+	.ascii	"HYP panic:\nPS:%08x PC:%016x ESR:%08x\nFAR:%016x HPFAR:%016x PAR:%016x\nVCPU:%p\n\0"
 
 	.align	2
 
@@ -1015,9 +1019,15 @@
 	b.ne	1f		// Not an abort we care about
 
 	/* This is an abort. Check for permission fault */
+alternative_if_not ARM64_WORKAROUND_834220
 	and	x2, x1, #ESR_ELx_FSC_TYPE
 	cmp	x2, #FSC_PERM
 	b.ne	1f		// Not a permission fault
+alternative_else
+	nop			// Use the permission fault path to
+	nop			// check for a valid S1 translation,
+	nop			// regardless of the ESR value.
+alternative_endif
 
 	/*
 	 * Check for Stage-1 page table walk, which is guaranteed
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 85c5715..648112e 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -48,7 +48,7 @@
 
 	/* Note: These now point to the banked copies */
 	*vcpu_spsr(vcpu) = new_spsr_value;
-	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
+	*vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
 	/* Branch to exception vector */
 	if (sctlr & (1 << 13))
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index f636a26..e87f53f 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -76,13 +76,28 @@
 		__flush_icache_all();
 }
 
-static int is_reserved_asid(u64 asid)
+static bool check_update_reserved_asid(u64 asid, u64 newasid)
 {
 	int cpu;
-	for_each_possible_cpu(cpu)
-		if (per_cpu(reserved_asids, cpu) == asid)
-			return 1;
-	return 0;
+	bool hit = false;
+
+	/*
+	 * Iterate over the set of reserved ASIDs looking for a match.
+	 * If we find one, then we can update our mm to use newasid
+	 * (i.e. the same ASID in the current generation) but we can't
+	 * exit the loop early, since we need to ensure that all copies
+	 * of the old ASID are updated to reflect the mm. Failure to do
+	 * so could result in us missing the reserved ASID in a future
+	 * generation.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(reserved_asids, cpu) == asid) {
+			hit = true;
+			per_cpu(reserved_asids, cpu) = newasid;
+		}
+	}
+
+	return hit;
 }
 
 static u64 new_context(struct mm_struct *mm, unsigned int cpu)
@@ -92,12 +107,14 @@
 	u64 generation = atomic64_read(&asid_generation);
 
 	if (asid != 0) {
+		u64 newasid = generation | (asid & ~ASID_MASK);
+
 		/*
 		 * If our current ASID was active during a rollover, we
 		 * can continue to use it and this was just a false alarm.
 		 */
-		if (is_reserved_asid(asid))
-			return generation | (asid & ~ASID_MASK);
+		if (check_update_reserved_asid(asid, newasid))
+			return newasid;
 
 		/*
 		 * We had a valid ASID in a previous life, so try to re-use
@@ -105,7 +122,7 @@
 		 */
 		asid &= ~ASID_MASK;
 		if (!__test_and_set_bit(asid, asid_map))
-			goto bump_gen;
+			return newasid;
 	}
 
 	/*
@@ -129,10 +146,7 @@
 set_asid:
 	__set_bit(asid, asid_map);
 	cur_idx = asid;
-
-bump_gen:
-	asid |= generation;
-	return asid;
+	return asid | generation;
 }
 
 void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 131a199..7963aa4 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/gfp.h>
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/genalloc.h>
@@ -28,9 +29,6 @@
 
 #include <asm/cacheflush.h>
 
-struct dma_map_ops *dma_ops;
-EXPORT_SYMBOL(dma_ops);
-
 static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
 				 bool coherent)
 {
@@ -515,13 +513,7 @@
 
 static int __init arm64_dma_init(void)
 {
-	int ret;
-
-	dma_ops = &swiotlb_dma_ops;
-
-	ret = atomic_pool_init();
-
-	return ret;
+	return atomic_pool_init();
 }
 arch_initcall(arm64_dma_init);
 
@@ -552,10 +544,14 @@
 {
 	bool coherent = is_device_dma_coherent(dev);
 	int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent);
+	size_t iosize = size;
 	void *addr;
 
 	if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n"))
 		return NULL;
+
+	size = PAGE_ALIGN(size);
+
 	/*
 	 * Some drivers rely on this, and we probably don't want the
 	 * possibility of stale kernel data being read by devices anyway.
@@ -566,7 +562,7 @@
 		struct page **pages;
 		pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
 
-		pages = iommu_dma_alloc(dev, size, gfp, ioprot,	handle,
+		pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle,
 					flush_page);
 		if (!pages)
 			return NULL;
@@ -574,7 +570,7 @@
 		addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
 					      __builtin_return_address(0));
 		if (!addr)
-			iommu_dma_free(dev, pages, size, handle);
+			iommu_dma_free(dev, pages, iosize, handle);
 	} else {
 		struct page *page;
 		/*
@@ -591,7 +587,7 @@
 		if (!addr)
 			return NULL;
 
-		*handle = iommu_dma_map_page(dev, page, 0, size, ioprot);
+		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
 		if (iommu_dma_mapping_error(dev, *handle)) {
 			if (coherent)
 				__free_pages(page, get_order(size));
@@ -606,6 +602,9 @@
 static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 			       dma_addr_t handle, struct dma_attrs *attrs)
 {
+	size_t iosize = size;
+
+	size = PAGE_ALIGN(size);
 	/*
 	 * @cpu_addr will be one of 3 things depending on how it was allocated:
 	 * - A remapped array of pages from iommu_dma_alloc(), for all
@@ -617,17 +616,17 @@
 	 * Hence how dodgy the below logic looks...
 	 */
 	if (__in_atomic_pool(cpu_addr, size)) {
-		iommu_dma_unmap_page(dev, handle, size, 0, NULL);
+		iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
 		__free_from_pool(cpu_addr, size);
 	} else if (is_vmalloc_addr(cpu_addr)){
 		struct vm_struct *area = find_vm_area(cpu_addr);
 
 		if (WARN_ON(!area || !area->pages))
 			return;
-		iommu_dma_free(dev, area->pages, size, &handle);
+		iommu_dma_free(dev, area->pages, iosize, &handle);
 		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
 	} else {
-		iommu_dma_unmap_page(dev, handle, size, 0, NULL);
+		iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
 		__free_pages(virt_to_page(cpu_addr), get_order(size));
 	}
 }
@@ -984,8 +983,8 @@
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			struct iommu_ops *iommu, bool coherent)
 {
-	if (!acpi_disabled && !dev->archdata.dma_ops)
-		dev->archdata.dma_ops = dma_ops;
+	if (!dev->archdata.dma_ops)
+		dev->archdata.dma_ops = &swiotlb_dma_ops;
 
 	dev->archdata.dma_coherent = coherent;
 	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 19211c4..92ddac1 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -393,16 +393,16 @@
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
-	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 8"			},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
-	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 12"			},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
 	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
-	{ do_bad,		SIGBUS,  0,		"asynchronous external abort"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
 	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
@@ -410,16 +410,16 @@
 	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
-	{ do_bad,		SIGBUS,  0,		"asynchronous parity error"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
 	{ do_bad,		SIGBUS,  BUS_ADRALN,	"alignment fault"		},
-	{ do_bad,		SIGBUS,  0,		"debug event"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 37"			},
@@ -433,21 +433,21 @@
 	{ do_bad,		SIGBUS,  0,		"unknown 45"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 46"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 47"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 48"			},
+	{ do_bad,		SIGBUS,  0,		"TLB conflict abort"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 49"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 50"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 51"			},
 	{ do_bad,		SIGBUS,  0,		"implementation fault (lockdown abort)" },
-	{ do_bad,		SIGBUS,  0,		"unknown 53"			},
+	{ do_bad,		SIGBUS,  0,		"implementation fault (unsupported exclusive)" },
 	{ do_bad,		SIGBUS,  0,		"unknown 54"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 55"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 56"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 57"			},
-	{ do_bad,		SIGBUS,  0,		"implementation fault (coprocessor abort)" },
+	{ do_bad,		SIGBUS,  0,		"unknown 58" 			},
 	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 61"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 62"			},
+	{ do_bad,		SIGBUS,  0,		"section domain fault"		},
+	{ do_bad,		SIGBUS,  0,		"page domain fault"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
 };
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index e3f563c..873e363 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -64,8 +64,12 @@
 
 static void __init *early_alloc(unsigned long sz)
 {
-	void *ptr = __va(memblock_alloc(sz, sz));
-	BUG_ON(!ptr);
+	phys_addr_t phys;
+	void *ptr;
+
+	phys = memblock_alloc(sz, sz);
+	BUG_ON(!phys);
+	ptr = __va(phys);
 	memset(ptr, 0, sz);
 	return ptr;
 }
@@ -81,55 +85,19 @@
 	do {
 		/*
 		 * Need to have the least restrictive permissions available
-		 * permissions will be fixed up later. Default the new page
-		 * range as contiguous ptes.
+		 * permissions will be fixed up later
 		 */
-		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC_CONT));
+		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
 		pfn++;
 	} while (pte++, i++, i < PTRS_PER_PTE);
 }
 
-/*
- * Given a PTE with the CONT bit set, determine where the CONT range
- * starts, and clear the entire range of PTE CONT bits.
- */
-static void clear_cont_pte_range(pte_t *pte, unsigned long addr)
-{
-	int i;
-
-	pte -= CONT_RANGE_OFFSET(addr);
-	for (i = 0; i < CONT_PTES; i++) {
-		set_pte(pte, pte_mknoncont(*pte));
-		pte++;
-	}
-	flush_tlb_all();
-}
-
-/*
- * Given a range of PTEs set the pfn and provided page protection flags
- */
-static void __populate_init_pte(pte_t *pte, unsigned long addr,
-				unsigned long end, phys_addr_t phys,
-				pgprot_t prot)
-{
-	unsigned long pfn = __phys_to_pfn(phys);
-
-	do {
-		/* clear all the bits except the pfn, then apply the prot */
-		set_pte(pte, pfn_pte(pfn, prot));
-		pte++;
-		pfn++;
-		addr += PAGE_SIZE;
-	} while (addr != end);
-}
-
 static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
-				  unsigned long end, phys_addr_t phys,
+				  unsigned long end, unsigned long pfn,
 				  pgprot_t prot,
 				  void *(*alloc)(unsigned long size))
 {
 	pte_t *pte;
-	unsigned long next;
 
 	if (pmd_none(*pmd) || pmd_sect(*pmd)) {
 		pte = alloc(PTRS_PER_PTE * sizeof(pte_t));
@@ -142,27 +110,9 @@
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		next = min(end, (addr + CONT_SIZE) & CONT_MASK);
-		if (((addr | next | phys) & ~CONT_MASK) == 0) {
-			/* a block of CONT_PTES  */
-			__populate_init_pte(pte, addr, next, phys,
-					    __pgprot(pgprot_val(prot) | PTE_CONT));
-		} else {
-			/*
-			 * If the range being split is already inside of a
-			 * contiguous range but this PTE isn't going to be
-			 * contiguous, then we want to unmark the adjacent
-			 * ranges, then update the portion of the range we
-			 * are interrested in.
-			 */
-			 clear_cont_pte_range(pte, addr);
-			 __populate_init_pte(pte, addr, next, phys, prot);
-		}
-
-		pte += (next - addr) >> PAGE_SHIFT;
-		phys += next - addr;
-		addr = next;
-	} while (addr != end);
+		set_pte(pte, pfn_pte(pfn, prot));
+		pfn++;
+	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
 static void split_pud(pud_t *old_pud, pmd_t *pmd)
@@ -223,7 +173,8 @@
 				}
 			}
 		} else {
-			alloc_init_pte(pmd, addr, next, phys, prot, alloc);
+			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
+				       prot, alloc);
 		}
 		phys += next - addr;
 	} while (pmd++, addr = next, addr != end);
@@ -362,8 +313,8 @@
 	 * for now. This will get more fine grained later once all memory
 	 * is mapped
 	 */
-	unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
-	unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
+	unsigned long kernel_x_start = round_down(__pa(_stext), SWAPPER_BLOCK_SIZE);
+	unsigned long kernel_x_end = round_up(__pa(__init_end), SWAPPER_BLOCK_SIZE);
 
 	if (end < kernel_x_start) {
 		create_mapping(start, __phys_to_virt(start),
@@ -451,18 +402,18 @@
 {
 #ifdef CONFIG_DEBUG_RODATA
 	/* now that we are actually fully mapped, make the start/end more fine grained */
-	if (!IS_ALIGNED((unsigned long)_stext, SECTION_SIZE)) {
+	if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) {
 		unsigned long aligned_start = round_down(__pa(_stext),
-							SECTION_SIZE);
+							 SWAPPER_BLOCK_SIZE);
 
 		create_mapping(aligned_start, __phys_to_virt(aligned_start),
 				__pa(_stext) - aligned_start,
 				PAGE_KERNEL);
 	}
 
-	if (!IS_ALIGNED((unsigned long)__init_end, SECTION_SIZE)) {
+	if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) {
 		unsigned long aligned_end = round_up(__pa(__init_end),
-							SECTION_SIZE);
+							  SWAPPER_BLOCK_SIZE);
 		create_mapping(__pa(__init_end), (unsigned long)__init_end,
 				aligned_end - __pa(__init_end),
 				PAGE_KERNEL);
@@ -475,7 +426,7 @@
 {
 	create_mapping_late(__pa(_stext), (unsigned long)_stext,
 				(unsigned long)_etext - (unsigned long)_stext,
-				PAGE_KERNEL_EXEC | PTE_RDONLY);
+				PAGE_KERNEL_ROX);
 
 }
 #endif
diff --git a/arch/m68k/coldfire/m54xx.c b/arch/m68k/coldfire/m54xx.c
index f7836c6..c32f767 100644
--- a/arch/m68k/coldfire/m54xx.c
+++ b/arch/m68k/coldfire/m54xx.c
@@ -98,7 +98,7 @@
 	memstart = PAGE_ALIGN(_ramstart);
 	min_low_pfn = PFN_DOWN(_rambase);
 	start_pfn = PFN_DOWN(memstart);
-	max_low_pfn = PFN_DOWN(_ramend);
+	max_pfn = max_low_pfn = PFN_DOWN(_ramend);
 	high_memory = (void *)_ramend;
 
 	m68k_virt_to_node_shift = fls(_ramend - _rambase - 1) - 6;
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 0793a7f..f9d96bf 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		375
+#define NR_syscalls		376
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 5e6fae6..36cf129 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -380,5 +380,6 @@
 #define __NR_sendmmsg		372
 #define __NR_userfaultfd	373
 #define __NR_membarrier		374
+#define __NR_mlock2		375
 
 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index 88c27d9..76b9113 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -238,11 +238,14 @@
 	 * Give all the memory to the bootmap allocator, tell it to put the
 	 * boot mem_map at the start of memory.
 	 */
+	min_low_pfn = PFN_DOWN(memory_start);
+	max_pfn = max_low_pfn = PFN_DOWN(memory_end);
+
 	bootmap_size = init_bootmem_node(
 			NODE_DATA(0),
-			memory_start >> PAGE_SHIFT, /* map goes here */
-			PAGE_OFFSET >> PAGE_SHIFT,	/* 0 on coldfire */
-			memory_end >> PAGE_SHIFT);
+			min_low_pfn,		/* map goes here */
+			PFN_DOWN(PAGE_OFFSET),
+			max_pfn);
 	/*
 	 * Free the usable memory, we have to make sure we do not free
 	 * the bootmem bitmap so we then reserve it after freeing it :-)
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 5dd0e80..282cd90 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -395,3 +395,4 @@
 	.long sys_sendmmsg
 	.long sys_userfaultfd
 	.long sys_membarrier
+	.long sys_mlock2		/* 375 */
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index b958916..8f37fdd 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -250,7 +250,7 @@
 	high_memory = phys_to_virt(max_addr);
 
 	min_low_pfn = availmem >> PAGE_SHIFT;
-	max_low_pfn = max_addr >> PAGE_SHIFT;
+	max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT;
 
 	for (i = 0; i < m68k_num_memory; i++) {
 		addr = m68k_memory[i].addr;
diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c
index a8b942b..2a5f43a 100644
--- a/arch/m68k/sun3/config.c
+++ b/arch/m68k/sun3/config.c
@@ -118,13 +118,13 @@
 	memory_end = memory_end & PAGE_MASK;
 
 	start_page = __pa(memory_start) >> PAGE_SHIFT;
-	num_pages = __pa(memory_end) >> PAGE_SHIFT;
+	max_pfn = num_pages = __pa(memory_end) >> PAGE_SHIFT;
 
 	high_memory = (void *)memory_end;
 	availmem = memory_start;
 
 	m68k_setup_node(0);
-	availmem += init_bootmem_node(NODE_DATA(0), start_page, 0, num_pages);
+	availmem += init_bootmem(start_page, num_pages);
 	availmem = (availmem + (PAGE_SIZE-1)) & PAGE_MASK;
 
 	free_bootmem(__pa(availmem), memory_end - (availmem));
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 1ba2120..8755d61 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -216,9 +216,9 @@
 					   AR71XX_RESET_SIZE);
 	ath79_pll_base = ioremap_nocache(AR71XX_PLL_BASE,
 					 AR71XX_PLL_SIZE);
+	ath79_detect_sys_type();
 	ath79_ddr_ctrl_init();
 
-	ath79_detect_sys_type();
 	if (mips_machtype != ATH79_MACH_GENERIC_OF)
 		detect_memory_region(0, ATH79_MEM_SIZE_MIN, ATH79_MEM_SIZE_MAX);
 
@@ -281,3 +281,8 @@
 	     "Generic",
 	     "Generic AR71XX/AR724X/AR913X based board",
 	     ath79_generic_init);
+
+MIPS_MACHINE(ATH79_MACH_GENERIC_OF,
+	     "DTB",
+	     "Generic AR71XX/AR724X/AR913X based board (DT)",
+	     NULL);
diff --git a/arch/mips/boot/dts/qca/ar9132.dtsi b/arch/mips/boot/dts/qca/ar9132.dtsi
index fb7734e..13d0439 100644
--- a/arch/mips/boot/dts/qca/ar9132.dtsi
+++ b/arch/mips/boot/dts/qca/ar9132.dtsi
@@ -107,7 +107,7 @@
 			miscintc: interrupt-controller@18060010 {
 				compatible = "qca,ar9132-misc-intc",
 					   "qca,ar7100-misc-intc";
-				reg = <0x18060010 0x4>;
+				reg = <0x18060010 0x8>;
 
 				interrupt-parent = <&cpuintc>;
 				interrupts = <6>;
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index ad1fccd..2046c02 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -200,8 +200,9 @@
 {
 	/* avoid <linux/mm.h> include hell */
 	extern unsigned long max_mapnr;
+	unsigned long pfn_offset = ARCH_PFN_OFFSET;
 
-	return pfn >= ARCH_PFN_OFFSET && pfn < max_mapnr;
+	return pfn >= pfn_offset && pfn < max_mapnr;
 }
 
 #elif defined(CONFIG_SPARSEMEM)
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index d5fa3ea..41b1b09 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1581,7 +1581,7 @@
 
 	base = (inst >> 21) & 0x1f;
 	op_inst = (inst >> 16) & 0x1f;
-	offset = inst & 0xffff;
+	offset = (int16_t)inst;
 	cache = (inst >> 16) & 0x3;
 	op = (inst >> 18) & 0x7;
 
diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
index 7bab3a4..7e22108 100644
--- a/arch/mips/kvm/locore.S
+++ b/arch/mips/kvm/locore.S
@@ -157,9 +157,11 @@
 
 FEXPORT(__kvm_mips_load_asid)
 	/* Set the ASID for the Guest Kernel */
-	INT_SLL	t0, t0, 1	/* with kseg0 @ 0x40000000, kernel */
-			        /* addresses shift to 0x80000000 */
-	bltz	t0, 1f		/* If kernel */
+	PTR_L	t0, VCPU_COP0(k1)
+	LONG_L	t0, COP0_STATUS(t0)
+	andi	t0, KSU_USER | ST0_ERL | ST0_EXL
+	xori	t0, KSU_USER
+	bnez	t0, 1f		/* If kernel */
 	 INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
 	INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID    /* else user */
 1:
@@ -474,9 +476,11 @@
 	mtc0	t0, CP0_EPC
 
 	/* Set the ASID for the Guest Kernel */
-	INT_SLL	t0, t0, 1	/* with kseg0 @ 0x40000000, kernel */
-				/* addresses shift to 0x80000000 */
-	bltz	t0, 1f		/* If kernel */
+	PTR_L	t0, VCPU_COP0(k1)
+	LONG_L	t0, COP0_STATUS(t0)
+	andi	t0, KSU_USER | ST0_ERL | ST0_EXL
+	xori	t0, KSU_USER
+	bnez	t0, 1f		/* If kernel */
 	 INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
 	INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID    /* else user */
 1:
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 49ff3bf..b9b803f 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -279,7 +279,7 @@
 
 	if (!gebase) {
 		err = -ENOMEM;
-		goto out_free_cpu;
+		goto out_uninit_cpu;
 	}
 	kvm_debug("Allocated %d bytes for KVM Exception Handlers @ %p\n",
 		  ALIGN(size, PAGE_SIZE), gebase);
@@ -343,6 +343,9 @@
 out_free_gebase:
 	kfree(gebase);
 
+out_uninit_cpu:
+	kvm_vcpu_uninit(vcpu);
+
 out_free_cpu:
 	kfree(vcpu);
 
diff --git a/arch/mips/pci/pci-rt2880.c b/arch/mips/pci/pci-rt2880.c
index 8a97802..dbbeccc 100644
--- a/arch/mips/pci/pci-rt2880.c
+++ b/arch/mips/pci/pci-rt2880.c
@@ -11,6 +11,7 @@
  *  by the Free Software Foundation.
  */
 
+#include <linux/delay.h>
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/io.h>
@@ -232,8 +233,7 @@
 	ioport_resource.end = RT2880_PCI_IO_BASE + RT2880_PCI_IO_SIZE - 1;
 
 	rt2880_pci_reg_write(0, RT2880_PCI_REG_PCICFG_ADDR);
-	for (i = 0; i < 0xfffff; i++)
-		;
+	udelay(1);
 
 	rt2880_pci_reg_write(0x79, RT2880_PCI_REG_ARBCTL);
 	rt2880_pci_reg_write(0x07FF0001, RT2880_PCI_REG_BAR0SETUP_ADDR);
diff --git a/arch/mips/pmcs-msp71xx/msp_setup.c b/arch/mips/pmcs-msp71xx/msp_setup.c
index 4f925e0..78b2ef4 100644
--- a/arch/mips/pmcs-msp71xx/msp_setup.c
+++ b/arch/mips/pmcs-msp71xx/msp_setup.c
@@ -10,6 +10,8 @@
  * option) any later version.
  */
 
+#include <linux/delay.h>
+
 #include <asm/bootinfo.h>
 #include <asm/cacheflush.h>
 #include <asm/idle.h>
@@ -77,7 +79,7 @@
 	 */
 
 	/* Wait a bit for the DDRC to settle */
-	for (i = 0; i < 100000000; i++);
+	mdelay(125);
 
 #if defined(CONFIG_PMC_MSP7120_GW)
 	/*
diff --git a/arch/mips/sni/reset.c b/arch/mips/sni/reset.c
index 244f942..db8f88b 100644
--- a/arch/mips/sni/reset.c
+++ b/arch/mips/sni/reset.c
@@ -3,6 +3,8 @@
  *
  *  Reset a SNI machine.
  */
+#include <linux/delay.h>
+
 #include <asm/io.h>
 #include <asm/reboot.h>
 #include <asm/sni.h>
@@ -32,9 +34,9 @@
 	for (;;) {
 		for (i = 0; i < 100; i++) {
 			kb_wait();
-			for (j = 0; j < 100000 ; j++)
-				/* nothing */;
+			udelay(50);
 			outb_p(0xfe, 0x64);	 /* pulse reset low */
+			udelay(50);
 		}
 	}
 }
diff --git a/arch/nios2/mm/cacheflush.c b/arch/nios2/mm/cacheflush.c
index 223cdcc..87bf88e 100644
--- a/arch/nios2/mm/cacheflush.c
+++ b/arch/nios2/mm/cacheflush.c
@@ -23,22 +23,6 @@
 	end += (cpuinfo.dcache_line_size - 1);
 	end &= ~(cpuinfo.dcache_line_size - 1);
 
-	for (addr = start; addr < end; addr += cpuinfo.dcache_line_size) {
-		__asm__ __volatile__ ("   flushda 0(%0)\n"
-					: /* Outputs */
-					: /* Inputs  */ "r"(addr)
-					/* : No clobber */);
-	}
-}
-
-static void __flush_dcache_all(unsigned long start, unsigned long end)
-{
-	unsigned long addr;
-
-	start &= ~(cpuinfo.dcache_line_size - 1);
-	end += (cpuinfo.dcache_line_size - 1);
-	end &= ~(cpuinfo.dcache_line_size - 1);
-
 	if (end > start + cpuinfo.dcache_size)
 		end = start + cpuinfo.dcache_size;
 
@@ -112,7 +96,7 @@
 
 void flush_cache_all(void)
 {
-	__flush_dcache_all(0, cpuinfo.dcache_size);
+	__flush_dcache(0, cpuinfo.dcache_size);
 	__flush_icache(0, cpuinfo.icache_size);
 }
 
@@ -182,7 +166,7 @@
 	 */
 	unsigned long start = (unsigned long)page_address(page);
 
-	__flush_dcache_all(start, start + PAGE_SIZE);
+	__flush_dcache(start, start + PAGE_SIZE);
 }
 
 void flush_dcache_page(struct page *page)
@@ -268,7 +252,7 @@
 {
 	flush_cache_page(vma, user_vaddr, page_to_pfn(page));
 	memcpy(dst, src, len);
-	__flush_dcache_all((unsigned long)src, (unsigned long)src + len);
+	__flush_dcache((unsigned long)src, (unsigned long)src + len);
 	if (vma->vm_flags & VM_EXEC)
 		__flush_icache((unsigned long)src, (unsigned long)src + len);
 }
@@ -279,7 +263,7 @@
 {
 	flush_cache_page(vma, user_vaddr, page_to_pfn(page));
 	memcpy(dst, src, len);
-	__flush_dcache_all((unsigned long)dst, (unsigned long)dst + len);
+	__flush_dcache((unsigned long)dst, (unsigned long)dst + len);
 	if (vma->vm_flags & VM_EXEC)
 		__flush_icache((unsigned long)dst, (unsigned long)dst + len);
 }
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index c365469..729f891 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -108,6 +108,9 @@
 	default 3 if 64BIT && PARISC_PAGE_SIZE_4KB
 	default 2
 
+config SYS_SUPPORTS_HUGETLBFS
+	def_bool y if PA20
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
new file mode 100644
index 0000000..7d56a9c
--- /dev/null
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -0,0 +1,85 @@
+#ifndef _ASM_PARISC64_HUGETLB_H
+#define _ASM_PARISC64_HUGETLB_H
+
+#include <asm/page.h>
+#include <asm-generic/hugetlb.h>
+
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pte);
+
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep);
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr,
+					 unsigned long len) {
+	return 0;
+}
+
+/*
+ * If the arch doesn't supply something else, assume that hugepage
+ * size aligned regions are ok without further preparation.
+ */
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
+{
+	if (len & ~HPAGE_MASK)
+		return -EINVAL;
+	if (addr & ~HPAGE_MASK)
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+					  unsigned long addr, unsigned long end,
+					  unsigned long floor,
+					  unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	pte_t old_pte = *ptep;
+	set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	int changed = !pte_same(*ptep, pte);
+	if (changed) {
+		set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+		flush_tlb_page(vma, addr);
+	}
+	return changed;
+}
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+}
+
+#endif /* _ASM_PARISC64_HUGETLB_H */
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index 60d5d17..80e742a 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -145,11 +145,22 @@
 #endif /* CONFIG_DISCONTIGMEM */
 
 #ifdef CONFIG_HUGETLB_PAGE
-#define HPAGE_SHIFT		22	/* 4MB (is this fixed?) */
+#define HPAGE_SHIFT		PMD_SHIFT /* fixed for transparent huge pages */
 #define HPAGE_SIZE      	((1UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+
+#if defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB)
+# define REAL_HPAGE_SHIFT	20 /* 20 = 1MB */
+# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_1M
+#elif !defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB)
+# define REAL_HPAGE_SHIFT	22 /* 22 = 4MB */
+# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_4M
+#else
+# define REAL_HPAGE_SHIFT	24 /* 24 = 16MB */
+# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_16M
 #endif
+#endif /* CONFIG_HUGETLB_PAGE */
 
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index 3edbb9f..f2fd327 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -35,7 +35,7 @@
 				        PxD_FLAG_VALID | 
 					PxD_FLAG_ATTACHED) 
 			+ (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT));
-		/* The first pmd entry also is marked with _PAGE_GATEWAY as
+		/* The first pmd entry also is marked with PxD_FLAG_ATTACHED as
 		 * a signal that this pmd may not be freed */
 		__pgd_val_set(*pgd, PxD_FLAG_ATTACHED);
 #endif
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index f93c4a4..d8534f9 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -83,7 +83,11 @@
 	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e))
 
 /* This is the size of the initially mapped kernel memory */
-#define KERNEL_INITIAL_ORDER	24	/* 0 to 1<<24 = 16MB */
+#ifdef CONFIG_64BIT
+#define KERNEL_INITIAL_ORDER	25	/* 1<<25 = 32MB */
+#else
+#define KERNEL_INITIAL_ORDER	24	/* 1<<24 = 16MB */
+#endif
 #define KERNEL_INITIAL_SIZE	(1 << KERNEL_INITIAL_ORDER)
 
 #if CONFIG_PGTABLE_LEVELS == 3
@@ -167,7 +171,7 @@
 #define _PAGE_NO_CACHE_BIT 24   /* (0x080) Uncached Page (U bit) */
 #define _PAGE_ACCESSED_BIT 23   /* (0x100) Software: Page Accessed */
 #define _PAGE_PRESENT_BIT  22   /* (0x200) Software: translation valid */
-/* bit 21 was formerly the FLUSH bit but is now unused */
+#define _PAGE_HPAGE_BIT    21   /* (0x400) Software: Huge Page */
 #define _PAGE_USER_BIT     20   /* (0x800) Software: User accessible page */
 
 /* N.B. The bits are defined in terms of a 32 bit word above, so the */
@@ -194,6 +198,7 @@
 #define _PAGE_NO_CACHE (1 << xlate_pabit(_PAGE_NO_CACHE_BIT))
 #define _PAGE_ACCESSED (1 << xlate_pabit(_PAGE_ACCESSED_BIT))
 #define _PAGE_PRESENT  (1 << xlate_pabit(_PAGE_PRESENT_BIT))
+#define _PAGE_HUGE     (1 << xlate_pabit(_PAGE_HPAGE_BIT))
 #define _PAGE_USER     (1 << xlate_pabit(_PAGE_USER_BIT))
 
 #define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE |  _PAGE_DIRTY | _PAGE_ACCESSED)
@@ -217,7 +222,7 @@
 #define PxD_FLAG_VALID    (1 << xlate_pabit(_PxD_VALID_BIT))
 #define PxD_FLAG_MASK     (0xf)
 #define PxD_FLAG_SHIFT    (4)
-#define PxD_VALUE_SHIFT   (8) /* (PAGE_SHIFT-PxD_FLAG_SHIFT) */
+#define PxD_VALUE_SHIFT   (PFN_PTE_SHIFT-PxD_FLAG_SHIFT)
 
 #ifndef __ASSEMBLY__
 
@@ -363,6 +368,18 @@
 static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 /*
+ * Huge pte definitions.
+ */
+#ifdef CONFIG_HUGETLB_PAGE
+#define pte_huge(pte)           (pte_val(pte) & _PAGE_HUGE)
+#define pte_mkhuge(pte)         (__pte(pte_val(pte) | _PAGE_HUGE))
+#else
+#define pte_huge(pte)           (0)
+#define pte_mkhuge(pte)         (pte)
+#endif
+
+
+/*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
  */
@@ -410,8 +427,9 @@
 /* Find an entry in the second-level page table.. */
 
 #if CONFIG_PGTABLE_LEVELS == 3
+#define pmd_index(addr)         (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
 #define pmd_offset(dir,address) \
-((pmd_t *) pgd_page_vaddr(*(dir)) + (((address)>>PMD_SHIFT) & (PTRS_PER_PMD-1)))
+((pmd_t *) pgd_page_vaddr(*(dir)) + pmd_index(address))
 #else
 #define pmd_offset(dir,addr) ((pmd_t *) dir)
 #endif
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 54adb60..7e759ec 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -192,33 +192,6 @@
  */
 typedef unsigned int elf_caddr_t;
 
-#define start_thread_som(regs, new_pc, new_sp) do {	\
-	unsigned long *sp = (unsigned long *)new_sp;	\
-	__u32 spaceid = (__u32)current->mm->context;	\
-	unsigned long pc = (unsigned long)new_pc;	\
-	/* offset pc for priv. level */			\
-	pc |= 3;					\
-							\
-	regs->iasq[0] = spaceid;			\
-	regs->iasq[1] = spaceid;			\
-	regs->iaoq[0] = pc;				\
-	regs->iaoq[1] = pc + 4;                         \
-	regs->sr[2] = LINUX_GATEWAY_SPACE;              \
-	regs->sr[3] = 0xffff;				\
-	regs->sr[4] = spaceid;				\
-	regs->sr[5] = spaceid;				\
-	regs->sr[6] = spaceid;				\
-	regs->sr[7] = spaceid;				\
-	regs->gr[ 0] = USER_PSW;                        \
-	regs->gr[30] = ((new_sp)+63)&~63;		\
-	regs->gr[31] = pc;				\
-							\
-	get_user(regs->gr[26],&sp[0]);			\
-	get_user(regs->gr[25],&sp[-1]); 		\
-	get_user(regs->gr[24],&sp[-2]); 		\
-	get_user(regs->gr[23],&sp[-3]); 		\
-} while(0)
-
 /* The ELF abi wants things done a "wee bit" differently than
  * som does.  Supporting this behavior here avoids
  * having our own version of create_elf_tables.
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index ecc3ae1..dd4d187 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -49,16 +49,6 @@
 #define MADV_DONTFORK	10		/* don't inherit across fork */
 #define MADV_DOFORK	11		/* do inherit across fork */
 
-/* The range 12-64 is reserved for page size specification. */
-#define MADV_4K_PAGES   12              /* Use 4K pages  */
-#define MADV_16K_PAGES  14              /* Use 16K pages */
-#define MADV_64K_PAGES  16              /* Use 64K pages */
-#define MADV_256K_PAGES 18              /* Use 256K pages */
-#define MADV_1M_PAGES   20              /* Use 1 Megabyte pages */
-#define MADV_4M_PAGES   22              /* Use 4 Megabyte pages */
-#define MADV_16M_PAGES  24              /* Use 16 Megabyte pages */
-#define MADV_64M_PAGES  26              /* Use 64 Megabyte pages */
-
 #define MADV_MERGEABLE   65		/* KSM may merge identical pages */
 #define MADV_UNMERGEABLE 66		/* KSM may not merge identical pages */
 
diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c
index 59001ce..d2f6257 100644
--- a/arch/parisc/kernel/asm-offsets.c
+++ b/arch/parisc/kernel/asm-offsets.c
@@ -290,6 +290,14 @@
 	DEFINE(ASM_PFN_PTE_SHIFT, PFN_PTE_SHIFT);
 	DEFINE(ASM_PT_INITIAL, PT_INITIAL);
 	BLANK();
+	/* HUGEPAGE_SIZE is only used in vmlinux.lds.S to align kernel text
+	 * and kernel data on physical huge pages */
+#ifdef CONFIG_HUGETLB_PAGE
+	DEFINE(HUGEPAGE_SIZE, 1UL << REAL_HPAGE_SHIFT);
+#else
+	DEFINE(HUGEPAGE_SIZE, PAGE_SIZE);
+#endif
+	BLANK();
 	DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip));
 	DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space));
 	DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr));
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index c5ef408..623496c 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -502,21 +502,38 @@
 	STREG		\pte,0(\ptp)
 	.endm
 
+	/* We have (depending on the page size):
+	 * - 38 to 52-bit Physical Page Number
+	 * - 12 to 26-bit page offset
+	 */
 	/* bitshift difference between a PFN (based on kernel's PAGE_SIZE)
 	 * to a CPU TLB 4k PFN (4k => 12 bits to shift) */
-	#define PAGE_ADD_SHIFT  (PAGE_SHIFT-12)
+	#define PAGE_ADD_SHIFT		(PAGE_SHIFT-12)
+	#define PAGE_ADD_HUGE_SHIFT	(REAL_HPAGE_SHIFT-12)
 
 	/* Drop prot bits and convert to page addr for iitlbt and idtlbt */
-	.macro		convert_for_tlb_insert20 pte
+	.macro		convert_for_tlb_insert20 pte,tmp
+#ifdef CONFIG_HUGETLB_PAGE
+	copy		\pte,\tmp
+	extrd,u		\tmp,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\
+				64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte
+
+	depdi		_PAGE_SIZE_ENCODING_DEFAULT,63,\
+				(63-58)+PAGE_ADD_SHIFT,\pte
+	extrd,u,*=	\tmp,_PAGE_HPAGE_BIT+32,1,%r0
+	depdi		_HUGE_PAGE_SIZE_ENCODING_DEFAULT,63,\
+				(63-58)+PAGE_ADD_HUGE_SHIFT,\pte
+#else /* Huge pages disabled */
 	extrd,u		\pte,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\
 				64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte
 	depdi		_PAGE_SIZE_ENCODING_DEFAULT,63,\
 				(63-58)+PAGE_ADD_SHIFT,\pte
+#endif
 	.endm
 
 	/* Convert the pte and prot to tlb insertion values.  How
 	 * this happens is quite subtle, read below */
-	.macro		make_insert_tlb	spc,pte,prot
+	.macro		make_insert_tlb	spc,pte,prot,tmp
 	space_to_prot   \spc \prot        /* create prot id from space */
 	/* The following is the real subtlety.  This is depositing
 	 * T <-> _PAGE_REFTRAP
@@ -553,7 +570,7 @@
 	depdi		1,12,1,\prot
 
 	/* Drop prot bits and convert to page addr for iitlbt and idtlbt */
-	convert_for_tlb_insert20 \pte
+	convert_for_tlb_insert20 \pte \tmp
 	.endm
 
 	/* Identical macro to make_insert_tlb above, except it
@@ -646,17 +663,12 @@
 
 
 	/*
-	 * Align fault_vector_20 on 4K boundary so that both
-	 * fault_vector_11 and fault_vector_20 are on the
-	 * same page. This is only necessary as long as we
-	 * write protect the kernel text, which we may stop
-	 * doing once we use large page translations to cover
-	 * the static part of the kernel address space.
+	 * Fault_vectors are architecturally required to be aligned on a 2K
+	 * boundary
 	 */
 
 	.text
-
-	.align 4096
+	.align 2048
 
 ENTRY(fault_vector_20)
 	/* First vector is invalid (0) */
@@ -1147,7 +1159,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20w
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 	
 	idtlbt          pte,prot
 
@@ -1173,7 +1185,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20w
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	idtlbt          pte,prot
 
@@ -1267,7 +1279,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	f_extend	pte,t1
 
@@ -1295,7 +1307,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	f_extend	pte,t1
 	
@@ -1404,7 +1416,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 	
 	iitlbt          pte,prot
 
@@ -1428,7 +1440,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20w
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	iitlbt          pte,prot
 
@@ -1514,7 +1526,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	f_extend	pte,t1
 
@@ -1534,7 +1546,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	f_extend	pte,t1
 
@@ -1566,7 +1578,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
 	update_dirty	ptp,pte,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 		
 	idtlbt          pte,prot
 
@@ -1610,7 +1622,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
 	update_dirty	ptp,pte,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	f_extend	pte,t1
 	
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index e7d6452..75aa0db 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -69,7 +69,7 @@
 	stw,ma          %arg2,4(%r1)
 	stw,ma          %arg3,4(%r1)
 
-	/* Initialize startup VM. Just map first 8/16 MB of memory */
+	/* Initialize startup VM. Just map first 16/32 MB of memory */
 	load32		PA(swapper_pg_dir),%r4
 	mtctl		%r4,%cr24	/* Initialize kernel root pointer */
 	mtctl		%r4,%cr25	/* Initialize user root pointer */
@@ -107,7 +107,7 @@
 	/* Now initialize the PTEs themselves.  We use RWX for
 	 * everything ... it will get remapped correctly later */
 	ldo		0+_PAGE_KERNEL_RWX(%r0),%r3 /* Hardwired 0 phys addr start */
-	ldi		(1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */
+	load32		(1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */
 	load32		PA(pg0),%r1
 
 $pgt_fill_loop:
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 72a3c65..f7ea626 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -130,7 +130,16 @@
 	printk(KERN_INFO "The 32-bit Kernel has started...\n");
 #endif
 
-	printk(KERN_INFO "Default page size is %dKB.\n", (int)(PAGE_SIZE / 1024));
+	printk(KERN_INFO "Kernel default page size is %d KB. Huge pages ",
+		(int)(PAGE_SIZE / 1024));
+#ifdef CONFIG_HUGETLB_PAGE
+	printk(KERN_CONT "enabled with %d MB physical and %d MB virtual size",
+		 1 << (REAL_HPAGE_SHIFT - 20), 1 << (HPAGE_SHIFT - 20));
+#else
+	printk(KERN_CONT "disabled");
+#endif
+	printk(KERN_CONT ".\n");
+
 
 	pdc_console_init();
 
@@ -377,6 +386,7 @@
 void start_parisc(void)
 {
 	extern void start_kernel(void);
+	extern void early_trap_init(void);
 
 	int ret, cpunum;
 	struct pdc_coproc_cfg coproc_cfg;
@@ -397,6 +407,8 @@
 		panic("must have an fpu to boot linux");
 	}
 
+	early_trap_init(); /* initialize checksum of fault_vector */
+
 	start_kernel();
 	// not reached
 }
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 0b8d26d..3fbd725 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -369,7 +369,7 @@
 	ldo	-16(%r30),%r29			/* Reference param save area */
 #endif
 	ldo	TASK_REGS(%r1),%r26
-	bl	do_syscall_trace_exit,%r2
+	BL	do_syscall_trace_exit,%r2
 	STREG   %r28,TASK_PT_GR28(%r1)          /* save return value now */
 	ldo     -THREAD_SZ_ALGN-FRAME_SIZE(%r30),%r1      /* get task ptr */
 	LDREG	TI_TASK(%r1), %r1
@@ -390,7 +390,7 @@
 #ifdef CONFIG_64BIT
 	ldo	-16(%r30),%r29			/* Reference param save area */
 #endif
-	bl	do_syscall_trace_exit,%r2
+	BL	do_syscall_trace_exit,%r2
 	ldo	TASK_REGS(%r1),%r26
 
 	ldil	L%syscall_exit_rfi,%r1
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index b99b39f..553b098 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -807,7 +807,7 @@
 }
 
 
-int __init check_ivt(void *iva)
+void __init initialize_ivt(const void *iva)
 {
 	extern u32 os_hpmc_size;
 	extern const u32 os_hpmc[];
@@ -818,8 +818,8 @@
 	u32 *hpmcp;
 	u32 length;
 
-	if (strcmp((char *)iva, "cows can fly"))
-		return -1;
+	if (strcmp((const char *)iva, "cows can fly"))
+		panic("IVT invalid");
 
 	ivap = (u32 *)iva;
 
@@ -839,28 +839,23 @@
 	    check += ivap[i];
 
 	ivap[5] = -check;
-
-	return 0;
 }
 	
+
+/* early_trap_init() is called before we set up kernel mappings and
+ * write-protect the kernel */
+void  __init early_trap_init(void)
+{
+	extern const void fault_vector_20;
+
 #ifndef CONFIG_64BIT
-extern const void fault_vector_11;
+	extern const void fault_vector_11;
+	initialize_ivt(&fault_vector_11);
 #endif
-extern const void fault_vector_20;
+
+	initialize_ivt(&fault_vector_20);
+}
 
 void __init trap_init(void)
 {
-	void *iva;
-
-	if (boot_cpu_data.cpu_type >= pcxu)
-		iva = (void *) &fault_vector_20;
-	else
-#ifdef CONFIG_64BIT
-		panic("Can't boot 64-bit OS on PA1.1 processor!");
-#else
-		iva = (void *) &fault_vector_11;
-#endif
-
-	if (check_ivt(iva))
-		panic("IVT invalid");
 }
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 0dacc5c..308f290 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -60,7 +60,7 @@
 		EXIT_DATA
 	}
 	PERCPU_SECTION(8)
-	. = ALIGN(PAGE_SIZE);
+	. = ALIGN(HUGEPAGE_SIZE);
 	__init_end = .;
 	/* freed after init ends here */
 
@@ -116,7 +116,7 @@
 	 * that we can properly leave these
 	 * as writable
 	 */
-	. = ALIGN(PAGE_SIZE);
+	. = ALIGN(HUGEPAGE_SIZE);
 	data_start = .;
 
 	EXCEPTION_TABLE(8)
@@ -135,8 +135,11 @@
 	_edata = .;
 
 	/* BSS */
-	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 8)
+	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE)
 
+	/* bootmap is allocated in setup_bootmem() directly behind bss. */
+
+	. = ALIGN(HUGEPAGE_SIZE);
 	_end = . ;
 
 	STABS_DEBUG
diff --git a/arch/parisc/mm/Makefile b/arch/parisc/mm/Makefile
index 758ceef..134393d 100644
--- a/arch/parisc/mm/Makefile
+++ b/arch/parisc/mm/Makefile
@@ -3,3 +3,4 @@
 #
 
 obj-y	 := init.o fault.o ioremap.o
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
new file mode 100644
index 0000000..f6fdc77
--- /dev/null
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -0,0 +1,161 @@
+/*
+ * PARISC64 Huge TLB page support.
+ *
+ * This parisc implementation is heavily based on the SPARC and x86 code.
+ *
+ * Copyright (C) 2015 Helge Deller <deller@gmx.de>
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/sysctl.h>
+
+#include <asm/mman.h>
+#include <asm/pgalloc.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
+
+
+unsigned long
+hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+		unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+	struct hstate *h = hstate_file(file);
+
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (flags & MAP_FIXED)
+		if (prepare_hugepage_range(file, addr, len))
+			return -EINVAL;
+
+	if (addr)
+		addr = ALIGN(addr, huge_page_size(h));
+
+	/* we need to make sure the colouring is OK */
+	return arch_get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
+
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte = NULL;
+
+	/* We must align the address, because our caller will run
+	 * set_huge_pte_at() on whatever we return, which writes out
+	 * all of the sub-ptes for the hugepage range.  So we have
+	 * to give it the first such sub-pte.
+	 */
+	addr &= HPAGE_MASK;
+
+	pgd = pgd_offset(mm, addr);
+	pud = pud_alloc(mm, pgd, addr);
+	if (pud) {
+		pmd = pmd_alloc(mm, pud, addr);
+		if (pmd)
+			pte = pte_alloc_map(mm, NULL, pmd, addr);
+	}
+	return pte;
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte = NULL;
+
+	addr &= HPAGE_MASK;
+
+	pgd = pgd_offset(mm, addr);
+	if (!pgd_none(*pgd)) {
+		pud = pud_offset(pgd, addr);
+		if (!pud_none(*pud)) {
+			pmd = pmd_offset(pud, addr);
+			if (!pmd_none(*pmd))
+				pte = pte_offset_map(pmd, addr);
+		}
+	}
+	return pte;
+}
+
+/* Purge data and instruction TLB entries.  Must be called holding
+ * the pa_tlb_lock.  The TLB purge instructions are slow on SMP
+ * machines since the purge must be broadcast to all CPUs.
+ */
+static inline void purge_tlb_entries_huge(struct mm_struct *mm, unsigned long addr)
+{
+	int i;
+
+	/* We may use multiple physical huge pages (e.g. 2x1 MB) to emulate
+	 * Linux standard huge pages (e.g. 2 MB) */
+	BUILD_BUG_ON(REAL_HPAGE_SHIFT > HPAGE_SHIFT);
+
+	addr &= HPAGE_MASK;
+	addr |= _HUGE_PAGE_SIZE_ENCODING_DEFAULT;
+
+	for (i = 0; i < (1 << (HPAGE_SHIFT-REAL_HPAGE_SHIFT)); i++) {
+		mtsp(mm->context, 1);
+		pdtlb(addr);
+		if (unlikely(split_tlb))
+			pitlb(addr);
+		addr += (1UL << REAL_HPAGE_SHIFT);
+	}
+}
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t entry)
+{
+	unsigned long addr_start;
+	int i;
+
+	addr &= HPAGE_MASK;
+	addr_start = addr;
+
+	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
+		/* Directly write pte entry.  We could call set_pte_at(mm, addr, ptep, entry)
+		 * instead, but then we get double locking on pa_tlb_lock. */
+		*ptep = entry;
+		ptep++;
+
+		/* Drop the PAGE_SIZE/non-huge tlb entry */
+		purge_tlb_entries(mm, addr);
+
+		addr += PAGE_SIZE;
+		pte_val(entry) += PAGE_SIZE;
+	}
+
+	purge_tlb_entries_huge(mm, addr_start);
+}
+
+
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep)
+{
+	pte_t entry;
+
+	entry = *ptep;
+	set_huge_pte_at(mm, addr, ptep, __pte(0));
+
+	return entry;
+}
+
+int pmd_huge(pmd_t pmd)
+{
+	return 0;
+}
+
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index c5fec48..1b366c4 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -409,15 +409,11 @@
 	unsigned long vaddr;
 	unsigned long ro_start;
 	unsigned long ro_end;
-	unsigned long fv_addr;
-	unsigned long gw_addr;
-	extern const unsigned long fault_vector_20;
-	extern void * const linux_gateway_page;
+	unsigned long kernel_end;
 
 	ro_start = __pa((unsigned long)_text);
 	ro_end   = __pa((unsigned long)&data_start);
-	fv_addr  = __pa((unsigned long)&fault_vector_20) & PAGE_MASK;
-	gw_addr  = __pa((unsigned long)&linux_gateway_page) & PAGE_MASK;
+	kernel_end  = __pa((unsigned long)&_end);
 
 	end_paddr = start_paddr + size;
 
@@ -475,24 +471,25 @@
 			for (tmp2 = start_pte; tmp2 < PTRS_PER_PTE; tmp2++, pg_table++) {
 				pte_t pte;
 
-				/*
-				 * Map the fault vector writable so we can
-				 * write the HPMC checksum.
-				 */
 				if (force)
 					pte =  __mk_pte(address, pgprot);
-				else if (parisc_text_address(vaddr) &&
-					 address != fv_addr)
+				else if (parisc_text_address(vaddr)) {
 					pte = __mk_pte(address, PAGE_KERNEL_EXEC);
+					if (address >= ro_start && address < kernel_end)
+						pte = pte_mkhuge(pte);
+				}
 				else
 #if defined(CONFIG_PARISC_PAGE_SIZE_4KB)
-				if (address >= ro_start && address < ro_end
-							&& address != fv_addr
-							&& address != gw_addr)
-					pte = __mk_pte(address, PAGE_KERNEL_RO);
-				else
+				if (address >= ro_start && address < ro_end) {
+					pte = __mk_pte(address, PAGE_KERNEL_EXEC);
+					pte = pte_mkhuge(pte);
+				} else
 #endif
+				{
 					pte = __mk_pte(address, pgprot);
+					if (address >= ro_start && address < kernel_end)
+						pte = pte_mkhuge(pte);
+				}
 
 				if (address >= end_paddr) {
 					if (force)
@@ -536,15 +533,12 @@
 
 	/* force the kernel to see the new TLB entries */
 	__flush_tlb_range(0, init_begin, init_end);
-	/* Attempt to catch anyone trying to execute code here
-	 * by filling the page with BRK insns.
-	 */
-	memset((void *)init_begin, 0x00, init_end - init_begin);
+
 	/* finally dump all the instructions which were cached, since the
 	 * pages are no-longer executable */
 	flush_icache_range(init_begin, init_end);
 	
-	free_initmem_default(-1);
+	free_initmem_default(POISON_FREE_INITMEM);
 
 	/* set up a new led state on systems shipped LED State panel */
 	pdc_chassis_send_status(PDC_CHASSIS_DIRECT_BCOMPLETE);
@@ -728,8 +722,8 @@
 		unsigned long size;
 
 		start_paddr = pmem_ranges[range].start_pfn << PAGE_SHIFT;
-		end_paddr = start_paddr + (pmem_ranges[range].pages << PAGE_SHIFT);
 		size = pmem_ranges[range].pages << PAGE_SHIFT;
+		end_paddr = start_paddr + size;
 
 		map_pages((unsigned long)__va(start_paddr), start_paddr,
 			  size, PAGE_KERNEL, 0);
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index a908ada..2220f7a 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -108,6 +108,7 @@
 #define MSR_TS_T	__MASK(MSR_TS_T_LG)	/*  Transaction Transactional */
 #define MSR_TS_MASK	(MSR_TS_T | MSR_TS_S)   /* Transaction State bits */
 #define MSR_TM_ACTIVE(x) (((x) & MSR_TS_MASK) != 0) /* Transaction active? */
+#define MSR_TM_RESV(x) (((x) & MSR_TS_MASK) == MSR_TS_MASK) /* Reserved */
 #define MSR_TM_TRANSACTIONAL(x)	(((x) & MSR_TS_MASK) == MSR_TS_T)
 #define MSR_TM_SUSPENDED(x)	(((x) & MSR_TS_MASK) == MSR_TS_S)
 
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index c9e26cb..f2b0b1b 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -382,3 +382,4 @@
 SYSCALL(shmdt)
 SYSCALL(shmget)
 COMPAT_SYS(shmctl)
+SYSCALL(mlock2)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 6d8f802..4b6b8ac 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define __NR_syscalls		378
+#define __NR_syscalls		379
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 81579e9..1effea5 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -400,5 +400,6 @@
 #define __NR_shmdt		375
 #define __NR_shmget		376
 #define __NR_shmctl		377
+#define __NR_mlock2		378
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 75b6676..646bf4d 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -551,6 +551,24 @@
 		msr_diff &= MSR_FP | MSR_VEC | MSR_VSX | MSR_FE0 | MSR_FE1;
 	}
 
+	/*
+	 * Use the current MSR TM suspended bit to track if we have
+	 * checkpointed state outstanding.
+	 * On signal delivery, we'd normally reclaim the checkpointed
+	 * state to obtain stack pointer (see:get_tm_stackpointer()).
+	 * This will then directly return to userspace without going
+	 * through __switch_to(). However, if the stack frame is bad,
+	 * we need to exit this thread which calls __switch_to() which
+	 * will again attempt to reclaim the already saved tm state.
+	 * Hence we need to check that we've not already reclaimed
+	 * this state.
+	 * We do this using the current MSR, rather tracking it in
+	 * some specific thread_struct bit, as it has the additional
+	 * benifit of checking for a potential TM bad thing exception.
+	 */
+	if (!MSR_TM_SUSPENDED(mfmsr()))
+		return;
+
 	tm_reclaim(thr, thr->regs->msr, cause);
 
 	/* Having done the reclaim, we now have the checkpointed
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 0dbee46..ef7c24e 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -875,6 +875,15 @@
 		return 1;
 #endif /* CONFIG_SPE */
 
+	/* Get the top half of the MSR from the user context */
+	if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR]))
+		return 1;
+	msr_hi <<= 32;
+	/* If TM bits are set to the reserved value, it's an invalid context */
+	if (MSR_TM_RESV(msr_hi))
+		return 1;
+	/* Pull in the MSR TM bits from the user context */
+	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr_hi & MSR_TS_MASK);
 	/* Now, recheckpoint.  This loads up all of the checkpointed (older)
 	 * registers, including FP and V[S]Rs.  After recheckpointing, the
 	 * transactional versions should be loaded.
@@ -884,11 +893,6 @@
 	current->thread.tm_texasr |= TEXASR_FS;
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
-	/* Get the top half of the MSR */
-	if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR]))
-		return 1;
-	/* Pull in MSR TM from user context */
-	regs->msr = (regs->msr & ~MSR_TS_MASK) | ((msr_hi<<32) & MSR_TS_MASK);
 
 	/* This loads the speculative FP/VEC state, if used */
 	if (msr & MSR_FP) {
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 20756df..c676ece 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -438,6 +438,10 @@
 
 	/* get MSR separately, transfer the LE bit if doing signal return */
 	err |= __get_user(msr, &sc->gp_regs[PT_MSR]);
+	/* Don't allow reserved mode. */
+	if (MSR_TM_RESV(msr))
+		return -EINVAL;
+
 	/* pull in MSR TM from user context */
 	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK);
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 373e323..6a75352 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1030,8 +1030,7 @@
 				   src_id, 0);
 
 	/* sending vcpu invalid */
-	if (src_id >= KVM_MAX_VCPUS ||
-	    kvm_get_vcpu(vcpu->kvm, src_id) == NULL)
+	if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL)
 		return -EINVAL;
 
 	if (sclp.has_sigpif)
@@ -1110,6 +1109,10 @@
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
 				   irq->u.emerg.code, 0);
 
+	/* sending vcpu invalid */
+	if (kvm_get_vcpu_by_id(vcpu->kvm, irq->u.emerg.code) == NULL)
+		return -EINVAL;
+
 	set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
 	set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
 	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8fe2f1c..8465892 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -342,12 +342,16 @@
 		r = 0;
 		break;
 	case KVM_CAP_S390_VECTOR_REGISTERS:
-		if (MACHINE_HAS_VX) {
+		mutex_lock(&kvm->lock);
+		if (atomic_read(&kvm->online_vcpus)) {
+			r = -EBUSY;
+		} else if (MACHINE_HAS_VX) {
 			set_kvm_facility(kvm->arch.model.fac->mask, 129);
 			set_kvm_facility(kvm->arch.model.fac->list, 129);
 			r = 0;
 		} else
 			r = -EINVAL;
+		mutex_unlock(&kvm->lock);
 		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
 			 r ? "(not available)" : "(success)");
 		break;
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 77191b8..d76b51c 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -660,7 +660,7 @@
 
 	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
-	if (!MACHINE_HAS_PFMF)
+	if (!test_kvm_facility(vcpu->kvm, 8))
 		return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index da690b6..77c22d6 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -291,12 +291,8 @@
 			   u16 cpu_addr, u32 parameter, u64 *status_reg)
 {
 	int rc;
-	struct kvm_vcpu *dst_vcpu;
+	struct kvm_vcpu *dst_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr);
 
-	if (cpu_addr >= KVM_MAX_VCPUS)
-		return SIGP_CC_NOT_OPERATIONAL;
-
-	dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
 	if (!dst_vcpu)
 		return SIGP_CC_NOT_OPERATIONAL;
 
@@ -478,7 +474,7 @@
 	trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr);
 
 	if (order_code == SIGP_EXTERNAL_CALL) {
-		dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+		dest_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr);
 		BUG_ON(dest_vcpu == NULL);
 
 		kvm_s390_vcpu_wakeup(dest_vcpu);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 9f39056..690b402 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -35,7 +35,7 @@
 #define MSR_IA32_PERFCTR0		0x000000c1
 #define MSR_IA32_PERFCTR1		0x000000c2
 #define MSR_FSB_FREQ			0x000000cd
-#define MSR_NHM_PLATFORM_INFO		0x000000ce
+#define MSR_PLATFORM_INFO		0x000000ce
 
 #define MSR_NHM_SNB_PKG_CST_CFG_CTL	0x000000e2
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
@@ -44,7 +44,6 @@
 #define SNB_C1_AUTO_UNDEMOTE		(1UL << 27)
 #define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
 
-#define MSR_PLATFORM_INFO		0x000000ce
 #define MSR_MTRRcap			0x000000fe
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4ddd780..c2b7522 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -273,10 +273,9 @@
 
 static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 {
-	unsigned long eflags;
+	unsigned long eflags = native_save_fl();
 
 	/* This should have been cleared long ago */
-	raw_local_save_flags(eflags);
 	BUG_ON(eflags & X86_EFLAGS_AC);
 
 	if (cpu_has(c, X86_FEATURE_SMAP)) {
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index ef29b74..31c6a60 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -385,20 +385,19 @@
  */
 void fpu__init_prepare_fx_sw_frame(void)
 {
-	int fsave_header_size = sizeof(struct fregs_state);
 	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
 
-	if (config_enabled(CONFIG_X86_32))
-		size += fsave_header_size;
-
 	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
 	fx_sw_reserved.extended_size = size;
 	fx_sw_reserved.xfeatures = xfeatures_mask;
 	fx_sw_reserved.xstate_size = xstate_size;
 
-	if (config_enabled(CONFIG_IA32_EMULATION)) {
+	if (config_enabled(CONFIG_IA32_EMULATION) ||
+	    config_enabled(CONFIG_X86_32)) {
+		int fsave_header_size = sizeof(struct fregs_state);
+
 		fx_sw_reserved_ia32 = fx_sw_reserved;
-		fx_sw_reserved_ia32.extended_size += fsave_header_size;
+		fx_sw_reserved_ia32.extended_size = size + fsave_header_size;
 	}
 }
 
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 6454f27..70fc312 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -694,7 +694,6 @@
 	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return NULL;
 
-	xsave = &current->thread.fpu.state.xsave;
 	/*
 	 * We should not ever be requesting features that we
 	 * have not enabled.  Remember that pcntxt_mask is
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index 94ea120..87e1762 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -278,6 +278,12 @@
 	/* save_mcount_regs fills in first two parameters */
 	save_mcount_regs
 
+	/*
+	 * When DYNAMIC_FTRACE is not defined, ARCH_SUPPORTS_FTRACE_OPS is not
+	 * set (see include/asm/ftrace.h and include/linux/ftrace.h).  Only the
+	 * ip and parent ip are used and the list function is called when
+	 * function tracing is enabled.
+	 */
 	call   *ftrace_trace_function
 
 	restore_mcount_regs
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 87acc52..af823a3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7394,11 +7394,6 @@
 
 	switch (type) {
 	case VMX_VPID_EXTENT_ALL_CONTEXT:
-		if (get_vmcs12(vcpu)->virtual_processor_id == 0) {
-			nested_vmx_failValid(vcpu,
-				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
-			return 1;
-		}
 		__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
 		nested_vmx_succeed(vcpu);
 		break;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 00462bd..eed3228 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2763,6 +2763,26 @@
 	return 0;
 }
 
+static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
+{
+	return (!lapic_in_kernel(vcpu) ||
+		kvm_apic_accept_pic_intr(vcpu));
+}
+
+/*
+ * if userspace requested an interrupt window, check that the
+ * interrupt window is open.
+ *
+ * No need to exit to userspace if we already have an interrupt queued.
+ */
+static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
+{
+	return kvm_arch_interrupt_allowed(vcpu) &&
+		!kvm_cpu_has_interrupt(vcpu) &&
+		!kvm_event_needs_reinjection(vcpu) &&
+		kvm_cpu_accept_dm_intr(vcpu);
+}
+
 static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 				    struct kvm_interrupt *irq)
 {
@@ -2786,6 +2806,7 @@
 		return -EEXIST;
 
 	vcpu->arch.pending_external_vector = irq->irq;
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	return 0;
 }
 
@@ -5910,23 +5931,10 @@
 	return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
 }
 
-/*
- * Check if userspace requested an interrupt window, and that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
 static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->run->request_interrupt_window || pic_in_kernel(vcpu->kvm))
-		return false;
-
-	if (kvm_cpu_has_interrupt(vcpu))
-		return false;
-
-	return (irqchip_split(vcpu->kvm)
-		? kvm_apic_accept_pic_intr(vcpu)
-		: kvm_arch_interrupt_allowed(vcpu));
+	return vcpu->run->request_interrupt_window &&
+		likely(!pic_in_kernel(vcpu->kvm));
 }
 
 static void post_kvm_run_save(struct kvm_vcpu *vcpu)
@@ -5937,17 +5945,9 @@
 	kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0;
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
-	if (!irqchip_in_kernel(vcpu->kvm))
-		kvm_run->ready_for_interrupt_injection =
-			kvm_arch_interrupt_allowed(vcpu) &&
-			!kvm_cpu_has_interrupt(vcpu) &&
-			!kvm_event_needs_reinjection(vcpu);
-	else if (!pic_in_kernel(vcpu->kvm))
-		kvm_run->ready_for_interrupt_injection =
-			kvm_apic_accept_pic_intr(vcpu) &&
-			!kvm_cpu_has_interrupt(vcpu);
-	else
-		kvm_run->ready_for_interrupt_injection = 1;
+	kvm_run->ready_for_interrupt_injection =
+		pic_in_kernel(vcpu->kvm) ||
+		kvm_vcpu_ready_for_interrupt_injection(vcpu);
 }
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
@@ -6360,8 +6360,10 @@
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
 	int r;
-	bool req_int_win = !lapic_in_kernel(vcpu) &&
-		vcpu->run->request_interrupt_window;
+	bool req_int_win =
+		dm_request_for_irq_injection(vcpu) &&
+		kvm_cpu_accept_dm_intr(vcpu);
+
 	bool req_immediate_exit = false;
 
 	if (vcpu->requests) {
@@ -6663,7 +6665,8 @@
 		if (kvm_cpu_has_pending_timer(vcpu))
 			kvm_inject_pending_timer_irqs(vcpu);
 
-		if (dm_request_for_irq_injection(vcpu)) {
+		if (dm_request_for_irq_injection(vcpu) &&
+			kvm_vcpu_ready_for_interrupt_injection(vcpu)) {
 			r = 0;
 			vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
 			++vcpu->stat.request_irq_exits;
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index b0ae85f..1202d5c 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -586,6 +586,29 @@
 }
 
 /*
+ * We only want to do a 4-byte get_user() on 32-bit.  Otherwise,
+ * we might run off the end of the bounds table if we are on
+ * a 64-bit kernel and try to get 8 bytes.
+ */
+int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
+		long __user *bd_entry_ptr)
+{
+	u32 bd_entry_32;
+	int ret;
+
+	if (is_64bit_mm(mm))
+		return get_user(*bd_entry_ret, bd_entry_ptr);
+
+	/*
+	 * Note that get_user() uses the type of the *pointer* to
+	 * establish the size of the get, not the destination.
+	 */
+	ret = get_user(bd_entry_32, (u32 __user *)bd_entry_ptr);
+	*bd_entry_ret = bd_entry_32;
+	return ret;
+}
+
+/*
  * Get the base of bounds tables pointed by specific bounds
  * directory entry.
  */
@@ -605,7 +628,7 @@
 		int need_write = 0;
 
 		pagefault_disable();
-		ret = get_user(bd_entry, bd_entry_ptr);
+		ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr);
 		pagefault_enable();
 		if (!ret)
 			break;
@@ -700,11 +723,23 @@
  */
 static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
 {
-	unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
-	if (is_64bit_mm(mm))
-		return virt_space / MPX_BD_NR_ENTRIES_64;
-	else
-		return virt_space / MPX_BD_NR_ENTRIES_32;
+	unsigned long long virt_space;
+	unsigned long long GB = (1ULL << 30);
+
+	/*
+	 * This covers 32-bit emulation as well as 32-bit kernels
+	 * running on 64-bit harware.
+	 */
+	if (!is_64bit_mm(mm))
+		return (4ULL * GB) / MPX_BD_NR_ENTRIES_32;
+
+	/*
+	 * 'x86_virt_bits' returns what the hardware is capable
+	 * of, and returns the full >32-bit adddress space when
+	 * running 32-bit kernels on 64-bit hardware.
+	 */
+	virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
+	return virt_space / MPX_BD_NR_ENTRIES_64;
 }
 
 /*
diff --git a/block/blk-merge.c b/block/blk-merge.c
index de5716d8..41a55ba 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -76,6 +76,9 @@
 	struct bio_vec bv, bvprv, *bvprvp = NULL;
 	struct bvec_iter iter;
 	unsigned seg_size = 0, nsegs = 0, sectors = 0;
+	unsigned front_seg_size = bio->bi_seg_front_size;
+	bool do_split = true;
+	struct bio *new = NULL;
 
 	bio_for_each_segment(bv, bio, iter) {
 		if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q))
@@ -98,7 +101,7 @@
 
 			seg_size += bv.bv_len;
 			bvprv = bv;
-			bvprvp = &bv;
+			bvprvp = &bvprv;
 			sectors += bv.bv_len >> 9;
 			continue;
 		}
@@ -108,16 +111,29 @@
 
 		nsegs++;
 		bvprv = bv;
-		bvprvp = &bv;
+		bvprvp = &bvprv;
 		seg_size = bv.bv_len;
 		sectors += bv.bv_len >> 9;
+
+		if (nsegs == 1 && seg_size > front_seg_size)
+			front_seg_size = seg_size;
 	}
 
-	*segs = nsegs;
-	return NULL;
+	do_split = false;
 split:
 	*segs = nsegs;
-	return bio_split(bio, sectors, GFP_NOIO, bs);
+
+	if (do_split) {
+		new = bio_split(bio, sectors, GFP_NOIO, bs);
+		if (new)
+			bio = new;
+	}
+
+	bio->bi_seg_front_size = front_seg_size;
+	if (seg_size > bio->bi_seg_back_size)
+		bio->bi_seg_back_size = seg_size;
+
+	return do_split ? new : NULL;
 }
 
 void blk_queue_split(struct request_queue *q, struct bio **bio,
@@ -412,6 +428,12 @@
 	if (sg)
 		sg_mark_end(sg);
 
+	/*
+	 * Something must have been wrong if the figured number of
+	 * segment is bigger than number of req's physical segments
+	 */
+	WARN_ON(nsegs > rq->nr_phys_segments);
+
 	return nsegs;
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3ae09de..6d6f8fe 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1291,15 +1291,16 @@
 		blk_mq_bio_to_request(rq, bio);
 
 		/*
-		 * we do limited pluging. If bio can be merged, do merge.
+		 * We do limited pluging. If the bio can be merged, do that.
 		 * Otherwise the existing request in the plug list will be
 		 * issued. So the plug list will have one request at most
 		 */
 		if (plug) {
 			/*
 			 * The plug list might get flushed before this. If that
-			 * happens, same_queue_rq is invalid and plug list is empty
-			 **/
+			 * happens, same_queue_rq is invalid and plug list is
+			 * empty
+			 */
 			if (same_queue_rq && !list_empty(&plug->mq_list)) {
 				old_rq = same_queue_rq;
 				list_del_init(&old_rq->queuelist);
@@ -1380,12 +1381,15 @@
 		blk_mq_bio_to_request(rq, bio);
 		if (!request_count)
 			trace_block_plug(q);
-		else if (request_count >= BLK_MAX_REQUEST_COUNT) {
+
+		blk_mq_put_ctx(data.ctx);
+
+		if (request_count >= BLK_MAX_REQUEST_COUNT) {
 			blk_flush_plug_list(plug, false);
 			trace_block_plug(q);
 		}
+
 		list_add_tail(&rq->queuelist, &plug->mq_list);
-		blk_mq_put_ctx(data.ctx);
 		return cookie;
 	}
 
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 246dfb1..aa40aa9 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -158,11 +158,13 @@
 {
 	if (blk_mark_rq_complete(req))
 		return;
-	blk_delete_timer(req);
-	if (req->q->mq_ops)
+
+	if (req->q->mq_ops) {
 		blk_mq_rq_timed_out(req, false);
-	else
+	} else {
+		blk_delete_timer(req);
 		blk_rq_timed_out(req);
+	}
 }
 EXPORT_SYMBOL_GPL(blk_abort_request);
 
diff --git a/block/blk.h b/block/blk.h
index da722eb..c43926d 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -72,8 +72,6 @@
 void __blk_queue_free_tags(struct request_queue *q);
 bool __blk_end_bidi_request(struct request *rq, int error,
 			    unsigned int nr_bytes, unsigned int bidi_bytes);
-int blk_queue_enter(struct request_queue *q, gfp_t gfp);
-void blk_queue_exit(struct request_queue *q);
 void blk_freeze_queue(struct request_queue *q);
 
 static inline void blk_queue_enter_live(struct request_queue *q)
diff --git a/block/noop-iosched.c b/block/noop-iosched.c
index 3de89d4..a163c48 100644
--- a/block/noop-iosched.c
+++ b/block/noop-iosched.c
@@ -21,10 +21,10 @@
 static int noop_dispatch(struct request_queue *q, int force)
 {
 	struct noop_data *nd = q->elevator->elevator_data;
+	struct request *rq;
 
-	if (!list_empty(&nd->queue)) {
-		struct request *rq;
-		rq = list_entry(nd->queue.next, struct request, queuelist);
+	rq = list_first_entry_or_null(&nd->queue, struct request, queuelist);
+	if (rq) {
 		list_del_init(&rq->queuelist);
 		elv_dispatch_sort(q, rq);
 		return 1;
@@ -46,7 +46,7 @@
 
 	if (rq->queuelist.prev == &nd->queue)
 		return NULL;
-	return list_entry(rq->queuelist.prev, struct request, queuelist);
+	return list_prev_entry(rq, queuelist);
 }
 
 static struct request *
@@ -56,7 +56,7 @@
 
 	if (rq->queuelist.next == &nd->queue)
 		return NULL;
-	return list_entry(rq->queuelist.next, struct request, queuelist);
+	return list_next_entry(rq, queuelist);
 }
 
 static int noop_init_queue(struct request_queue *q, struct elevator_type *e)
diff --git a/block/partitions/mac.c b/block/partitions/mac.c
index c2c48ec..621317a 100644
--- a/block/partitions/mac.c
+++ b/block/partitions/mac.c
@@ -32,7 +32,7 @@
 	Sector sect;
 	unsigned char *data;
 	int slot, blocks_in_map;
-	unsigned secsize;
+	unsigned secsize, datasize, partoffset;
 #ifdef CONFIG_PPC_PMAC
 	int found_root = 0;
 	int found_root_goodness = 0;
@@ -50,10 +50,14 @@
 	}
 	secsize = be16_to_cpu(md->block_size);
 	put_dev_sector(sect);
-	data = read_part_sector(state, secsize/512, &sect);
+	datasize = round_down(secsize, 512);
+	data = read_part_sector(state, datasize / 512, &sect);
 	if (!data)
 		return -1;
-	part = (struct mac_partition *) (data + secsize%512);
+	partoffset = secsize % 512;
+	if (partoffset + sizeof(*part) > datasize)
+		return -1;
+	part = (struct mac_partition *) (data + partoffset);
 	if (be16_to_cpu(part->signature) != MAC_PARTITION_MAGIC) {
 		put_dev_sector(sect);
 		return 0;		/* not a MacOS disk */
diff --git a/drivers/Makefile b/drivers/Makefile
index 73d0391..795d0ca 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -63,6 +63,7 @@
 obj-$(CONFIG_FB_INTEL)          += video/fbdev/intelfb/
 
 obj-$(CONFIG_PARPORT)		+= parport/
+obj-$(CONFIG_NVM)		+= lightnvm/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
 obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
@@ -70,7 +71,6 @@
 obj-y				+= macintosh/
 obj-$(CONFIG_IDE)		+= ide/
 obj-$(CONFIG_SCSI)		+= scsi/
-obj-$(CONFIG_NVM)		+= lightnvm/
 obj-y				+= nvme/
 obj-$(CONFIG_ATA)		+= ata/
 obj-$(CONFIG_TARGET_CORE)	+= target/
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 3c083d2..6730f96 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -304,7 +304,7 @@
 
 static int register_pcc_channel(int pcc_subspace_idx)
 {
-	struct acpi_pcct_subspace *cppc_ss;
+	struct acpi_pcct_hw_reduced *cppc_ss;
 	unsigned int len;
 
 	if (pcc_subspace_idx >= 0) {
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index f61a7c8..b420fb4 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1103,7 +1103,7 @@
 	}
 
 err_exit:
-	if (result && q)
+	if (result)
 		acpi_ec_delete_query(q);
 	if (data)
 		*data = value;
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index bf034f8..2fa8304 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -14,7 +14,6 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/dmi.h>
 #include "sbshc.h"
 
 #define PREFIX "ACPI: "
@@ -30,6 +29,7 @@
 	u8 query_bit;
 	smbus_alarm_callback callback;
 	void *context;
+	bool done;
 };
 
 static int acpi_smbus_hc_add(struct acpi_device *device);
@@ -88,8 +88,6 @@
 	ACPI_SMB_ALARM_DATA = 0x26,	/* 2 bytes alarm data */
 };
 
-static bool macbook;
-
 static inline int smb_hc_read(struct acpi_smb_hc *hc, u8 address, u8 *data)
 {
 	return ec_read(hc->offset + address, data);
@@ -100,27 +98,11 @@
 	return ec_write(hc->offset + address, data);
 }
 
-static inline int smb_check_done(struct acpi_smb_hc *hc)
-{
-	union acpi_smb_status status = {.raw = 0};
-	smb_hc_read(hc, ACPI_SMB_STATUS, &status.raw);
-	return status.fields.done && (status.fields.status == SMBUS_OK);
-}
-
 static int wait_transaction_complete(struct acpi_smb_hc *hc, int timeout)
 {
-	if (wait_event_timeout(hc->wait, smb_check_done(hc),
-			       msecs_to_jiffies(timeout)))
+	if (wait_event_timeout(hc->wait, hc->done, msecs_to_jiffies(timeout)))
 		return 0;
-	/*
-	 * After the timeout happens, OS will try to check the status of SMbus.
-	 * If the status is what OS expected, it will be regarded as the bogus
-	 * timeout.
-	 */
-	if (smb_check_done(hc))
-		return 0;
-	else
-		return -ETIME;
+	return -ETIME;
 }
 
 static int acpi_smbus_transaction(struct acpi_smb_hc *hc, u8 protocol,
@@ -135,8 +117,7 @@
 	}
 
 	mutex_lock(&hc->lock);
-	if (macbook)
-		udelay(5);
+	hc->done = false;
 	if (smb_hc_read(hc, ACPI_SMB_PROTOCOL, &temp))
 		goto end;
 	if (temp) {
@@ -235,8 +216,10 @@
 	if (smb_hc_read(hc, ACPI_SMB_STATUS, &status.raw))
 		return 0;
 	/* Check if it is only a completion notify */
-	if (status.fields.done)
+	if (status.fields.done && status.fields.status == SMBUS_OK) {
+		hc->done = true;
 		wake_up(&hc->wait);
+	}
 	if (!status.fields.alarm)
 		return 0;
 	mutex_lock(&hc->lock);
@@ -262,29 +245,12 @@
 			      acpi_handle handle, acpi_ec_query_func func,
 			      void *data);
 
-static int macbook_dmi_match(const struct dmi_system_id *d)
-{
-	pr_debug("Detected MacBook, enabling workaround\n");
-	macbook = true;
-	return 0;
-}
-
-static struct dmi_system_id acpi_smbus_dmi_table[] = {
-	{ macbook_dmi_match, "Apple MacBook", {
-	  DMI_MATCH(DMI_BOARD_VENDOR, "Apple"),
-	  DMI_MATCH(DMI_PRODUCT_NAME, "MacBook") },
-	},
-	{ },
-};
-
 static int acpi_smbus_hc_add(struct acpi_device *device)
 {
 	int status;
 	unsigned long long val;
 	struct acpi_smb_hc *hc;
 
-	dmi_check_system(acpi_smbus_dmi_table);
-
 	if (!device)
 		return -EINVAL;
 
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index eb6e674..0d77cd6 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -68,6 +68,9 @@
 	struct wake_irq *wirq;
 	int err;
 
+	if (irq < 0)
+		return -EINVAL;
+
 	wirq = kzalloc(sizeof(*wirq), GFP_KERNEL);
 	if (!wirq)
 		return -ENOMEM;
@@ -167,6 +170,9 @@
 	struct wake_irq *wirq;
 	int err;
 
+	if (irq < 0)
+		return -EINVAL;
+
 	wirq = kzalloc(sizeof(*wirq), GFP_KERNEL);
 	if (!wirq)
 		return -ENOMEM;
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index a28a562..3457ac8 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3810,7 +3810,6 @@
 	sector_t capacity;
 	unsigned int index = 0;
 	struct kobject *kobj;
-	unsigned char thd_name[16];
 
 	if (dd->disk)
 		goto skip_create_disk; /* hw init done, before rebuild */
@@ -3958,10 +3957,9 @@
 	}
 
 start_service_thread:
-	sprintf(thd_name, "mtip_svc_thd_%02d", index);
 	dd->mtip_svc_handler = kthread_create_on_node(mtip_service_thread,
-						dd, dd->numa_node, "%s",
-						thd_name);
+						dd, dd->numa_node,
+						"mtip_svc_thd_%02d", index);
 
 	if (IS_ERR(dd->mtip_svc_handler)) {
 		dev_err(&dd->pdev->dev, "service thread failed to start\n");
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 6255d1c..5c8ba54 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/blk-mq.h>
 #include <linux/hrtimer.h>
+#include <linux/lightnvm.h>
 
 struct nullb_cmd {
 	struct list_head list;
@@ -39,12 +40,14 @@
 
 	struct nullb_queue *queues;
 	unsigned int nr_queues;
+	char disk_name[DISK_NAME_LEN];
 };
 
 static LIST_HEAD(nullb_list);
 static struct mutex lock;
 static int null_major;
 static int nullb_indexes;
+static struct kmem_cache *ppa_cache;
 
 struct completion_queue {
 	struct llist_head list;
@@ -119,6 +122,10 @@
 module_param(nr_devices, int, S_IRUGO);
 MODULE_PARM_DESC(nr_devices, "Number of devices to register");
 
+static bool use_lightnvm;
+module_param(use_lightnvm, bool, S_IRUGO);
+MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device");
+
 static int irqmode = NULL_IRQ_SOFTIRQ;
 
 static int null_set_irqmode(const char *str, const struct kernel_param *kp)
@@ -427,15 +434,156 @@
 {
 	list_del_init(&nullb->list);
 
-	del_gendisk(nullb->disk);
+	if (use_lightnvm)
+		nvm_unregister(nullb->disk_name);
+	else
+		del_gendisk(nullb->disk);
 	blk_cleanup_queue(nullb->q);
 	if (queue_mode == NULL_Q_MQ)
 		blk_mq_free_tag_set(&nullb->tag_set);
-	put_disk(nullb->disk);
+	if (!use_lightnvm)
+		put_disk(nullb->disk);
 	cleanup_queues(nullb);
 	kfree(nullb);
 }
 
+#ifdef CONFIG_NVM
+
+static void null_lnvm_end_io(struct request *rq, int error)
+{
+	struct nvm_rq *rqd = rq->end_io_data;
+	struct nvm_dev *dev = rqd->dev;
+
+	dev->mt->end_io(rqd, error);
+
+	blk_put_request(rq);
+}
+
+static int null_lnvm_submit_io(struct request_queue *q, struct nvm_rq *rqd)
+{
+	struct request *rq;
+	struct bio *bio = rqd->bio;
+
+	rq = blk_mq_alloc_request(q, bio_rw(bio), GFP_KERNEL, 0);
+	if (IS_ERR(rq))
+		return -ENOMEM;
+
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	rq->__sector = bio->bi_iter.bi_sector;
+	rq->ioprio = bio_prio(bio);
+
+	if (bio_has_data(bio))
+		rq->nr_phys_segments = bio_phys_segments(q, bio);
+
+	rq->__data_len = bio->bi_iter.bi_size;
+	rq->bio = rq->biotail = bio;
+
+	rq->end_io_data = rqd;
+
+	blk_execute_rq_nowait(q, NULL, rq, 0, null_lnvm_end_io);
+
+	return 0;
+}
+
+static int null_lnvm_id(struct request_queue *q, struct nvm_id *id)
+{
+	sector_t size = gb * 1024 * 1024 * 1024ULL;
+	sector_t blksize;
+	struct nvm_id_group *grp;
+
+	id->ver_id = 0x1;
+	id->vmnt = 0;
+	id->cgrps = 1;
+	id->cap = 0x3;
+	id->dom = 0x1;
+
+	id->ppaf.blk_offset = 0;
+	id->ppaf.blk_len = 16;
+	id->ppaf.pg_offset = 16;
+	id->ppaf.pg_len = 16;
+	id->ppaf.sect_offset = 32;
+	id->ppaf.sect_len = 8;
+	id->ppaf.pln_offset = 40;
+	id->ppaf.pln_len = 8;
+	id->ppaf.lun_offset = 48;
+	id->ppaf.lun_len = 8;
+	id->ppaf.ch_offset = 56;
+	id->ppaf.ch_len = 8;
+
+	do_div(size, bs); /* convert size to pages */
+	do_div(size, 256); /* concert size to pgs pr blk */
+	grp = &id->groups[0];
+	grp->mtype = 0;
+	grp->fmtype = 0;
+	grp->num_ch = 1;
+	grp->num_pg = 256;
+	blksize = size;
+	do_div(size, (1 << 16));
+	grp->num_lun = size + 1;
+	do_div(blksize, grp->num_lun);
+	grp->num_blk = blksize;
+	grp->num_pln = 1;
+
+	grp->fpg_sz = bs;
+	grp->csecs = bs;
+	grp->trdt = 25000;
+	grp->trdm = 25000;
+	grp->tprt = 500000;
+	grp->tprm = 500000;
+	grp->tbet = 1500000;
+	grp->tbem = 1500000;
+	grp->mpos = 0x010101; /* single plane rwe */
+	grp->cpar = hw_queue_depth;
+
+	return 0;
+}
+
+static void *null_lnvm_create_dma_pool(struct request_queue *q, char *name)
+{
+	mempool_t *virtmem_pool;
+
+	virtmem_pool = mempool_create_slab_pool(64, ppa_cache);
+	if (!virtmem_pool) {
+		pr_err("null_blk: Unable to create virtual memory pool\n");
+		return NULL;
+	}
+
+	return virtmem_pool;
+}
+
+static void null_lnvm_destroy_dma_pool(void *pool)
+{
+	mempool_destroy(pool);
+}
+
+static void *null_lnvm_dev_dma_alloc(struct request_queue *q, void *pool,
+				gfp_t mem_flags, dma_addr_t *dma_handler)
+{
+	return mempool_alloc(pool, mem_flags);
+}
+
+static void null_lnvm_dev_dma_free(void *pool, void *entry,
+							dma_addr_t dma_handler)
+{
+	mempool_free(entry, pool);
+}
+
+static struct nvm_dev_ops null_lnvm_dev_ops = {
+	.identity		= null_lnvm_id,
+	.submit_io		= null_lnvm_submit_io,
+
+	.create_dma_pool	= null_lnvm_create_dma_pool,
+	.destroy_dma_pool	= null_lnvm_destroy_dma_pool,
+	.dev_dma_alloc		= null_lnvm_dev_dma_alloc,
+	.dev_dma_free		= null_lnvm_dev_dma_free,
+
+	/* Simulate nvme protocol restriction */
+	.max_phys_sect		= 64,
+};
+#else
+static struct nvm_dev_ops null_lnvm_dev_ops;
+#endif /* CONFIG_NVM */
+
 static int null_open(struct block_device *bdev, fmode_t mode)
 {
 	return 0;
@@ -575,11 +723,6 @@
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q);
 	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q);
 
-	disk = nullb->disk = alloc_disk_node(1, home_node);
-	if (!disk) {
-		rv = -ENOMEM;
-		goto out_cleanup_blk_queue;
-	}
 
 	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
@@ -589,6 +732,21 @@
 	blk_queue_logical_block_size(nullb->q, bs);
 	blk_queue_physical_block_size(nullb->q, bs);
 
+	sprintf(nullb->disk_name, "nullb%d", nullb->index);
+
+	if (use_lightnvm) {
+		rv = nvm_register(nullb->q, nullb->disk_name,
+							&null_lnvm_dev_ops);
+		if (rv)
+			goto out_cleanup_blk_queue;
+		goto done;
+	}
+
+	disk = nullb->disk = alloc_disk_node(1, home_node);
+	if (!disk) {
+		rv = -ENOMEM;
+		goto out_cleanup_lightnvm;
+	}
 	size = gb * 1024 * 1024 * 1024ULL;
 	set_capacity(disk, size >> 9);
 
@@ -598,10 +756,15 @@
 	disk->fops		= &null_fops;
 	disk->private_data	= nullb;
 	disk->queue		= nullb->q;
-	sprintf(disk->disk_name, "nullb%d", nullb->index);
+	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+
 	add_disk(disk);
+done:
 	return 0;
 
+out_cleanup_lightnvm:
+	if (use_lightnvm)
+		nvm_unregister(nullb->disk_name);
 out_cleanup_blk_queue:
 	blk_cleanup_queue(nullb->q);
 out_cleanup_tags:
@@ -625,6 +788,18 @@
 		bs = PAGE_SIZE;
 	}
 
+	if (use_lightnvm && bs != 4096) {
+		pr_warn("null_blk: LightNVM only supports 4k block size\n");
+		pr_warn("null_blk: defaults block size to 4k\n");
+		bs = 4096;
+	}
+
+	if (use_lightnvm && queue_mode != NULL_Q_MQ) {
+		pr_warn("null_blk: LightNVM only supported for blk-mq\n");
+		pr_warn("null_blk: defaults queue mode to blk-mq\n");
+		queue_mode = NULL_Q_MQ;
+	}
+
 	if (queue_mode == NULL_Q_MQ && use_per_node_hctx) {
 		if (submit_queues < nr_online_nodes) {
 			pr_warn("null_blk: submit_queues param is set to %u.",
@@ -655,15 +830,27 @@
 	if (null_major < 0)
 		return null_major;
 
+	if (use_lightnvm) {
+		ppa_cache = kmem_cache_create("ppa_cache", 64 * sizeof(u64),
+								0, 0, NULL);
+		if (!ppa_cache) {
+			pr_err("null_blk: unable to create ppa cache\n");
+			return -ENOMEM;
+		}
+	}
+
 	for (i = 0; i < nr_devices; i++) {
 		if (null_add_dev()) {
 			unregister_blkdev(null_major, "nullb");
-			return -EINVAL;
+			goto err_ppa;
 		}
 	}
 
 	pr_info("null: module loaded\n");
 	return 0;
+err_ppa:
+	kmem_cache_destroy(ppa_cache);
+	return -EINVAL;
 }
 
 static void __exit null_exit(void)
@@ -678,6 +865,8 @@
 		null_del_dev(nullb);
 	}
 	mutex_unlock(&lock);
+
+	kmem_cache_destroy(ppa_cache);
 }
 
 module_init(null_init);
diff --git a/drivers/bus/omap-ocp2scp.c b/drivers/bus/omap-ocp2scp.c
index 9f18569..bf500e0 100644
--- a/drivers/bus/omap-ocp2scp.c
+++ b/drivers/bus/omap-ocp2scp.c
@@ -117,7 +117,7 @@
 
 module_platform_driver(omap_ocp2scp_driver);
 
-MODULE_ALIAS("platform: omap-ocp2scp");
+MODULE_ALIAS("platform:omap-ocp2scp");
 MODULE_AUTHOR("Texas Instruments Inc.");
 MODULE_DESCRIPTION("OMAP OCP2SCP driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 654f6f3..55fe902 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -412,18 +412,42 @@
 	return rv;
 }
 
-static void start_check_enables(struct smi_info *smi_info)
+static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
+{
+	smi_info->last_timeout_jiffies = jiffies;
+	mod_timer(&smi_info->si_timer, new_val);
+	smi_info->timer_running = true;
+}
+
+/*
+ * Start a new message and (re)start the timer and thread.
+ */
+static void start_new_msg(struct smi_info *smi_info, unsigned char *msg,
+			  unsigned int size)
+{
+	smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
+
+	if (smi_info->thread)
+		wake_up_process(smi_info->thread);
+
+	smi_info->handlers->start_transaction(smi_info->si_sm, msg, size);
+}
+
+static void start_check_enables(struct smi_info *smi_info, bool start_timer)
 {
 	unsigned char msg[2];
 
 	msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
 	msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD;
 
-	smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
+	if (start_timer)
+		start_new_msg(smi_info, msg, 2);
+	else
+		smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
 	smi_info->si_state = SI_CHECKING_ENABLES;
 }
 
-static void start_clear_flags(struct smi_info *smi_info)
+static void start_clear_flags(struct smi_info *smi_info, bool start_timer)
 {
 	unsigned char msg[3];
 
@@ -432,7 +456,10 @@
 	msg[1] = IPMI_CLEAR_MSG_FLAGS_CMD;
 	msg[2] = WDT_PRE_TIMEOUT_INT;
 
-	smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3);
+	if (start_timer)
+		start_new_msg(smi_info, msg, 3);
+	else
+		smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3);
 	smi_info->si_state = SI_CLEARING_FLAGS;
 }
 
@@ -442,10 +469,8 @@
 	smi_info->curr_msg->data[1] = IPMI_GET_MSG_CMD;
 	smi_info->curr_msg->data_size = 2;
 
-	smi_info->handlers->start_transaction(
-		smi_info->si_sm,
-		smi_info->curr_msg->data,
-		smi_info->curr_msg->data_size);
+	start_new_msg(smi_info, smi_info->curr_msg->data,
+		      smi_info->curr_msg->data_size);
 	smi_info->si_state = SI_GETTING_MESSAGES;
 }
 
@@ -455,20 +480,11 @@
 	smi_info->curr_msg->data[1] = IPMI_READ_EVENT_MSG_BUFFER_CMD;
 	smi_info->curr_msg->data_size = 2;
 
-	smi_info->handlers->start_transaction(
-		smi_info->si_sm,
-		smi_info->curr_msg->data,
-		smi_info->curr_msg->data_size);
+	start_new_msg(smi_info, smi_info->curr_msg->data,
+		      smi_info->curr_msg->data_size);
 	smi_info->si_state = SI_GETTING_EVENTS;
 }
 
-static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
-{
-	smi_info->last_timeout_jiffies = jiffies;
-	mod_timer(&smi_info->si_timer, new_val);
-	smi_info->timer_running = true;
-}
-
 /*
  * When we have a situtaion where we run out of memory and cannot
  * allocate messages, we just leave them in the BMC and run the system
@@ -478,11 +494,11 @@
  * Note that we cannot just use disable_irq(), since the interrupt may
  * be shared.
  */
-static inline bool disable_si_irq(struct smi_info *smi_info)
+static inline bool disable_si_irq(struct smi_info *smi_info, bool start_timer)
 {
 	if ((smi_info->irq) && (!smi_info->interrupt_disabled)) {
 		smi_info->interrupt_disabled = true;
-		start_check_enables(smi_info);
+		start_check_enables(smi_info, start_timer);
 		return true;
 	}
 	return false;
@@ -492,7 +508,7 @@
 {
 	if ((smi_info->irq) && (smi_info->interrupt_disabled)) {
 		smi_info->interrupt_disabled = false;
-		start_check_enables(smi_info);
+		start_check_enables(smi_info, true);
 		return true;
 	}
 	return false;
@@ -510,7 +526,7 @@
 
 	msg = ipmi_alloc_smi_msg();
 	if (!msg) {
-		if (!disable_si_irq(smi_info))
+		if (!disable_si_irq(smi_info, true))
 			smi_info->si_state = SI_NORMAL;
 	} else if (enable_si_irq(smi_info)) {
 		ipmi_free_smi_msg(msg);
@@ -526,7 +542,7 @@
 		/* Watchdog pre-timeout */
 		smi_inc_stat(smi_info, watchdog_pretimeouts);
 
-		start_clear_flags(smi_info);
+		start_clear_flags(smi_info, true);
 		smi_info->msg_flags &= ~WDT_PRE_TIMEOUT_INT;
 		if (smi_info->intf)
 			ipmi_smi_watchdog_pretimeout(smi_info->intf);
@@ -879,8 +895,7 @@
 			msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
 			msg[1] = IPMI_GET_MSG_FLAGS_CMD;
 
-			smi_info->handlers->start_transaction(
-				smi_info->si_sm, msg, 2);
+			start_new_msg(smi_info, msg, 2);
 			smi_info->si_state = SI_GETTING_FLAGS;
 			goto restart;
 		}
@@ -910,7 +925,7 @@
 		 * disable and messages disabled.
 		 */
 		if (smi_info->supports_event_msg_buff || smi_info->irq) {
-			start_check_enables(smi_info);
+			start_check_enables(smi_info, true);
 		} else {
 			smi_info->curr_msg = alloc_msg_handle_irq(smi_info);
 			if (!smi_info->curr_msg)
@@ -920,6 +935,13 @@
 		}
 		goto restart;
 	}
+
+	if (si_sm_result == SI_SM_IDLE && smi_info->timer_running) {
+		/* Ok it if fails, the timer will just go off. */
+		if (del_timer(&smi_info->si_timer))
+			smi_info->timer_running = false;
+	}
+
  out:
 	return si_sm_result;
 }
@@ -2560,6 +2582,7 @@
 	  .data = (void *)(unsigned long) SI_BT },
 	{},
 };
+MODULE_DEVICE_TABLE(of, of_ipmi_match);
 
 static int of_ipmi_probe(struct platform_device *dev)
 {
@@ -2646,7 +2669,6 @@
 	}
 	return 0;
 }
-MODULE_DEVICE_TABLE(of, of_ipmi_match);
 #else
 #define of_ipmi_match NULL
 static int of_ipmi_probe(struct platform_device *dev)
@@ -3613,7 +3635,7 @@
 	 * Start clearing the flags before we enable interrupts or the
 	 * timer to avoid racing with the timer.
 	 */
-	start_clear_flags(new_smi);
+	start_clear_flags(new_smi, false);
 
 	/*
 	 * IRQ is defined to be set when non-zero.  req_events will
@@ -3908,7 +3930,7 @@
 		poll(to_clean);
 		schedule_timeout_uninterruptible(1);
 	}
-	disable_si_irq(to_clean);
+	disable_si_irq(to_clean, false);
 	while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) {
 		poll(to_clean);
 		schedule_timeout_uninterruptible(1);
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 0ac3bd1..096f0ce 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -153,6 +153,9 @@
 /* The pre-timeout is disabled by default. */
 static int pretimeout;
 
+/* Default timeout to set on panic */
+static int panic_wdt_timeout = 255;
+
 /* Default action is to reset the board on a timeout. */
 static unsigned char action_val = WDOG_TIMEOUT_RESET;
 
@@ -293,6 +296,9 @@
 module_param(pretimeout, timeout, 0644);
 MODULE_PARM_DESC(pretimeout, "Pretimeout value in seconds.");
 
+module_param(panic_wdt_timeout, timeout, 0644);
+MODULE_PARM_DESC(timeout, "Timeout value on kernel panic in seconds.");
+
 module_param_cb(action, &param_ops_str, action_op, 0644);
 MODULE_PARM_DESC(action, "Timeout action. One of: "
 		 "reset, none, power_cycle, power_off.");
@@ -1189,7 +1195,7 @@
 		/* Make sure we do this only once. */
 		panic_event_handled = 1;
 
-		timeout = 255;
+		timeout = panic_wdt_timeout;
 		pretimeout = 0;
 		panic_halt_ipmi_set_timeout();
 	}
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 71cfdf7..2eb5f0e 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -1,4 +1,5 @@
 menu "Clock Source drivers"
+	depends on !ARCH_USES_GETTIMEOFFSET
 
 config CLKSRC_OF
 	bool
diff --git a/drivers/clocksource/fsl_ftm_timer.c b/drivers/clocksource/fsl_ftm_timer.c
index 10202f1..517e1c7 100644
--- a/drivers/clocksource/fsl_ftm_timer.c
+++ b/drivers/clocksource/fsl_ftm_timer.c
@@ -203,7 +203,7 @@
 	int err;
 
 	ftm_writel(0x00, priv->clkevt_base + FTM_CNTIN);
-	ftm_writel(~0UL, priv->clkevt_base + FTM_MOD);
+	ftm_writel(~0u, priv->clkevt_base + FTM_MOD);
 
 	ftm_reset_counter(priv->clkevt_base);
 
@@ -230,7 +230,7 @@
 	int err;
 
 	ftm_writel(0x00, priv->clksrc_base + FTM_CNTIN);
-	ftm_writel(~0UL, priv->clksrc_base + FTM_MOD);
+	ftm_writel(~0u, priv->clksrc_base + FTM_MOD);
 
 	ftm_reset_counter(priv->clksrc_base);
 
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 1582c1c..235a1ba 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -84,6 +84,7 @@
 config ARM_MT8173_CPUFREQ
 	bool "Mediatek MT8173 CPUFreq support"
 	depends on ARCH_MEDIATEK && REGULATOR
+	depends on ARM64 || (ARM_CPU_TOPOLOGY && COMPILE_TEST)
 	depends on !CPU_THERMAL || THERMAL=y
 	select PM_OPP
 	help
@@ -201,7 +202,7 @@
 
 config ARM_SCPI_CPUFREQ
         tristate "SCPI based CPUfreq driver"
-	depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL
+	depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
         help
 	  This adds the CPUfreq driver support for ARM big.LITTLE platforms
 	  using SCPI protocol for CPU power management.
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index adbd1de..c59bdcb 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -5,7 +5,6 @@
 config X86_INTEL_PSTATE
        bool "Intel P state control"
        depends on X86
-       select ACPI_PROCESSOR if ACPI
        help
           This driver provides a P state for Intel core processors.
 	  The driver implements an internal governor and will become
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index e8cb334..7c0bdfb 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -98,10 +98,11 @@
 	policy->max = cpu->perf_caps.highest_perf;
 	policy->cpuinfo.min_freq = policy->min;
 	policy->cpuinfo.max_freq = policy->max;
+	policy->shared_type = cpu->shared_type;
 
 	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
 		cpumask_copy(policy->cpus, cpu->shared_cpu_map);
-	else {
+	else if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL) {
 		/* Support only SW_ANY for now. */
 		pr_debug("Unsupported CPU co-ord type\n");
 		return -EFAULT;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 7c48e73..a83c995 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1401,13 +1401,10 @@
 	}
 
 	cpumask_clear_cpu(cpu, policy->real_cpus);
-
-	if (cpumask_empty(policy->real_cpus)) {
-		cpufreq_policy_free(policy, true);
-		return;
-	}
-
 	remove_cpu_dev_symlink(policy, cpu);
+
+	if (cpumask_empty(policy->real_cpus))
+		cpufreq_policy_free(policy, true);
 }
 
 static void handle_update(struct work_struct *work)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2e31d09..4d07cbd 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -34,14 +34,10 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cpufeature.h>
 
-#if IS_ENABLED(CONFIG_ACPI)
-#include <acpi/processor.h>
-#endif
-
-#define BYT_RATIOS		0x66a
-#define BYT_VIDS		0x66b
-#define BYT_TURBO_RATIOS	0x66c
-#define BYT_TURBO_VIDS		0x66d
+#define ATOM_RATIOS		0x66a
+#define ATOM_VIDS		0x66b
+#define ATOM_TURBO_RATIOS	0x66c
+#define ATOM_TURBO_VIDS		0x66d
 
 #define FRAC_BITS 8
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
@@ -117,9 +113,6 @@
 	u64	prev_mperf;
 	u64	prev_tsc;
 	struct sample sample;
-#if IS_ENABLED(CONFIG_ACPI)
-	struct acpi_processor_performance acpi_perf_data;
-#endif
 };
 
 static struct cpudata **all_cpu_data;
@@ -150,7 +143,6 @@
 static struct pstate_adjust_policy pid_params;
 static struct pstate_funcs pstate_funcs;
 static int hwp_active;
-static int no_acpi_perf;
 
 struct perf_limits {
 	int no_turbo;
@@ -163,8 +155,6 @@
 	int max_sysfs_pct;
 	int min_policy_pct;
 	int min_sysfs_pct;
-	int max_perf_ctl;
-	int min_perf_ctl;
 };
 
 static struct perf_limits performance_limits = {
@@ -191,8 +181,6 @@
 	.max_sysfs_pct = 100,
 	.min_policy_pct = 0,
 	.min_sysfs_pct = 0,
-	.max_perf_ctl = 0,
-	.min_perf_ctl = 0,
 };
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
@@ -201,153 +189,6 @@
 static struct perf_limits *limits = &powersave_limits;
 #endif
 
-#if IS_ENABLED(CONFIG_ACPI)
-/*
- * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and
- * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and
- * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state
- * ratio, out of it only high 8 bits are used. For example 0x1700 is setting
- * target ratio 0x17. The _PSS control value stores in a format which can be
- * directly written to PERF_CTL MSR. But in intel_pstate driver this shift
- * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()).
- * This function converts the _PSS control value to intel pstate driver format
- * for comparison and assignment.
- */
-static int convert_to_native_pstate_format(struct cpudata *cpu, int index)
-{
-	return cpu->acpi_perf_data.states[index].control >> 8;
-}
-
-static int intel_pstate_init_perf_limits(struct cpufreq_policy *policy)
-{
-	struct cpudata *cpu;
-	int ret;
-	bool turbo_absent = false;
-	int max_pstate_index;
-	int min_pss_ctl, max_pss_ctl, turbo_pss_ctl;
-	int i;
-
-	cpu = all_cpu_data[policy->cpu];
-
-	pr_debug("intel_pstate: default limits 0x%x 0x%x 0x%x\n",
-		 cpu->pstate.min_pstate, cpu->pstate.max_pstate,
-		 cpu->pstate.turbo_pstate);
-
-	if (!cpu->acpi_perf_data.shared_cpu_map &&
-	    zalloc_cpumask_var_node(&cpu->acpi_perf_data.shared_cpu_map,
-				    GFP_KERNEL, cpu_to_node(policy->cpu))) {
-		return -ENOMEM;
-	}
-
-	ret = acpi_processor_register_performance(&cpu->acpi_perf_data,
-						  policy->cpu);
-	if (ret)
-		return ret;
-
-	/*
-	 * Check if the control value in _PSS is for PERF_CTL MSR, which should
-	 * guarantee that the states returned by it map to the states in our
-	 * list directly.
-	 */
-	if (cpu->acpi_perf_data.control_register.space_id !=
-						ACPI_ADR_SPACE_FIXED_HARDWARE)
-		return -EIO;
-
-	pr_debug("intel_pstate: CPU%u - ACPI _PSS perf data\n", policy->cpu);
-	for (i = 0; i < cpu->acpi_perf_data.state_count; i++)
-		pr_debug("     %cP%d: %u MHz, %u mW, 0x%x\n",
-			 (i == cpu->acpi_perf_data.state ? '*' : ' '), i,
-			 (u32) cpu->acpi_perf_data.states[i].core_frequency,
-			 (u32) cpu->acpi_perf_data.states[i].power,
-			 (u32) cpu->acpi_perf_data.states[i].control);
-
-	/*
-	 * If there is only one entry _PSS, simply ignore _PSS and continue as
-	 * usual without taking _PSS into account
-	 */
-	if (cpu->acpi_perf_data.state_count < 2)
-		return 0;
-
-	turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0);
-	min_pss_ctl = convert_to_native_pstate_format(cpu,
-					cpu->acpi_perf_data.state_count - 1);
-	/* Check if there is a turbo freq in _PSS */
-	if (turbo_pss_ctl <= cpu->pstate.max_pstate &&
-	    turbo_pss_ctl > cpu->pstate.min_pstate) {
-		pr_debug("intel_pstate: no turbo range exists in _PSS\n");
-		limits->no_turbo = limits->turbo_disabled = 1;
-		cpu->pstate.turbo_pstate = cpu->pstate.max_pstate;
-		turbo_absent = true;
-	}
-
-	/* Check if the max non turbo p state < Intel P state max */
-	max_pstate_index = turbo_absent ? 0 : 1;
-	max_pss_ctl = convert_to_native_pstate_format(cpu, max_pstate_index);
-	if (max_pss_ctl < cpu->pstate.max_pstate &&
-	    max_pss_ctl > cpu->pstate.min_pstate)
-		cpu->pstate.max_pstate = max_pss_ctl;
-
-	/* check If min perf > Intel P State min */
-	if (min_pss_ctl > cpu->pstate.min_pstate &&
-	    min_pss_ctl < cpu->pstate.max_pstate) {
-		cpu->pstate.min_pstate = min_pss_ctl;
-		policy->cpuinfo.min_freq = min_pss_ctl * cpu->pstate.scaling;
-	}
-
-	if (turbo_absent)
-		policy->cpuinfo.max_freq = cpu->pstate.max_pstate *
-						cpu->pstate.scaling;
-	else {
-		policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate *
-						cpu->pstate.scaling;
-		/*
-		 * The _PSS table doesn't contain whole turbo frequency range.
-		 * This just contains +1 MHZ above the max non turbo frequency,
-		 * with control value corresponding to max turbo ratio. But
-		 * when cpufreq set policy is called, it will call with this
-		 * max frequency, which will cause a reduced performance as
-		 * this driver uses real max turbo frequency as the max
-		 * frequeny. So correct this frequency in _PSS table to
-		 * correct max turbo frequency based on the turbo ratio.
-		 * Also need to convert to MHz as _PSS freq is in MHz.
-		 */
-		cpu->acpi_perf_data.states[0].core_frequency =
-						turbo_pss_ctl * 100;
-	}
-
-	pr_debug("intel_pstate: Updated limits using _PSS 0x%x 0x%x 0x%x\n",
-		 cpu->pstate.min_pstate, cpu->pstate.max_pstate,
-		 cpu->pstate.turbo_pstate);
-	pr_debug("intel_pstate: policy max_freq=%d Khz min_freq = %d KHz\n",
-		 policy->cpuinfo.max_freq, policy->cpuinfo.min_freq);
-
-	return 0;
-}
-
-static int intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
-{
-	struct cpudata *cpu;
-
-	if (!no_acpi_perf)
-		return 0;
-
-	cpu = all_cpu_data[policy->cpu];
-	acpi_processor_unregister_performance(policy->cpu);
-	return 0;
-}
-
-#else
-static int intel_pstate_init_perf_limits(struct cpufreq_policy *policy)
-{
-	return 0;
-}
-
-static int intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
-{
-	return 0;
-}
-#endif
-
 static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
 			     int deadband, int integral) {
 	pid->setpoint = setpoint;
@@ -687,31 +528,31 @@
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 }
 
-static int byt_get_min_pstate(void)
+static int atom_get_min_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_RATIOS, value);
+	rdmsrl(ATOM_RATIOS, value);
 	return (value >> 8) & 0x7F;
 }
 
-static int byt_get_max_pstate(void)
+static int atom_get_max_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_RATIOS, value);
+	rdmsrl(ATOM_RATIOS, value);
 	return (value >> 16) & 0x7F;
 }
 
-static int byt_get_turbo_pstate(void)
+static int atom_get_turbo_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_TURBO_RATIOS, value);
+	rdmsrl(ATOM_TURBO_RATIOS, value);
 	return value & 0x7F;
 }
 
-static void byt_set_pstate(struct cpudata *cpudata, int pstate)
+static void atom_set_pstate(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
 	int32_t vid_fp;
@@ -736,27 +577,42 @@
 	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
 }
 
-#define BYT_BCLK_FREQS 5
-static int byt_freq_table[BYT_BCLK_FREQS] = { 833, 1000, 1333, 1167, 800};
-
-static int byt_get_scaling(void)
+static int silvermont_get_scaling(void)
 {
 	u64 value;
 	int i;
+	/* Defined in Table 35-6 from SDM (Sept 2015) */
+	static int silvermont_freq_table[] = {
+		83300, 100000, 133300, 116700, 80000};
 
 	rdmsrl(MSR_FSB_FREQ, value);
-	i = value & 0x3;
+	i = value & 0x7;
+	WARN_ON(i > 4);
 
-	BUG_ON(i > BYT_BCLK_FREQS);
-
-	return byt_freq_table[i] * 100;
+	return silvermont_freq_table[i];
 }
 
-static void byt_get_vid(struct cpudata *cpudata)
+static int airmont_get_scaling(void)
+{
+	u64 value;
+	int i;
+	/* Defined in Table 35-10 from SDM (Sept 2015) */
+	static int airmont_freq_table[] = {
+		83300, 100000, 133300, 116700, 80000,
+		93300, 90000, 88900, 87500};
+
+	rdmsrl(MSR_FSB_FREQ, value);
+	i = value & 0xF;
+	WARN_ON(i > 8);
+
+	return airmont_freq_table[i];
+}
+
+static void atom_get_vid(struct cpudata *cpudata)
 {
 	u64 value;
 
-	rdmsrl(BYT_VIDS, value);
+	rdmsrl(ATOM_VIDS, value);
 	cpudata->vid.min = int_tofp((value >> 8) & 0x7f);
 	cpudata->vid.max = int_tofp((value >> 16) & 0x7f);
 	cpudata->vid.ratio = div_fp(
@@ -764,7 +620,7 @@
 		int_tofp(cpudata->pstate.max_pstate -
 			cpudata->pstate.min_pstate));
 
-	rdmsrl(BYT_TURBO_VIDS, value);
+	rdmsrl(ATOM_TURBO_VIDS, value);
 	cpudata->vid.turbo = value & 0x7f;
 }
 
@@ -885,7 +741,7 @@
 	},
 };
 
-static struct cpu_defaults byt_params = {
+static struct cpu_defaults silvermont_params = {
 	.pid_policy = {
 		.sample_rate_ms = 10,
 		.deadband = 0,
@@ -895,13 +751,33 @@
 		.i_gain_pct = 4,
 	},
 	.funcs = {
-		.get_max = byt_get_max_pstate,
-		.get_max_physical = byt_get_max_pstate,
-		.get_min = byt_get_min_pstate,
-		.get_turbo = byt_get_turbo_pstate,
-		.set = byt_set_pstate,
-		.get_scaling = byt_get_scaling,
-		.get_vid = byt_get_vid,
+		.get_max = atom_get_max_pstate,
+		.get_max_physical = atom_get_max_pstate,
+		.get_min = atom_get_min_pstate,
+		.get_turbo = atom_get_turbo_pstate,
+		.set = atom_set_pstate,
+		.get_scaling = silvermont_get_scaling,
+		.get_vid = atom_get_vid,
+	},
+};
+
+static struct cpu_defaults airmont_params = {
+	.pid_policy = {
+		.sample_rate_ms = 10,
+		.deadband = 0,
+		.setpoint = 60,
+		.p_gain_pct = 14,
+		.d_gain_pct = 0,
+		.i_gain_pct = 4,
+	},
+	.funcs = {
+		.get_max = atom_get_max_pstate,
+		.get_max_physical = atom_get_max_pstate,
+		.get_min = atom_get_min_pstate,
+		.get_turbo = atom_get_turbo_pstate,
+		.set = atom_set_pstate,
+		.get_scaling = airmont_get_scaling,
+		.get_vid = atom_get_vid,
 	},
 };
 
@@ -938,23 +814,12 @@
 	 * policy, or by cpu specific default values determined through
 	 * experimentation.
 	 */
-	if (limits->max_perf_ctl && limits->max_sysfs_pct >=
-						limits->max_policy_pct) {
-		*max = limits->max_perf_ctl;
-	} else {
-		max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf),
-					limits->max_perf));
-		*max = clamp_t(int, max_perf_adj, cpu->pstate.min_pstate,
-			       cpu->pstate.turbo_pstate);
-	}
+	max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits->max_perf));
+	*max = clamp_t(int, max_perf_adj,
+			cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
 
-	if (limits->min_perf_ctl) {
-		*min = limits->min_perf_ctl;
-	} else {
-		min_perf = fp_toint(mul_fp(int_tofp(max_perf),
-				    limits->min_perf));
-		*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
-	}
+	min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits->min_perf));
+	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
 static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate, bool force)
@@ -1153,7 +1018,7 @@
 static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x2a, core_params),
 	ICPU(0x2d, core_params),
-	ICPU(0x37, byt_params),
+	ICPU(0x37, silvermont_params),
 	ICPU(0x3a, core_params),
 	ICPU(0x3c, core_params),
 	ICPU(0x3d, core_params),
@@ -1162,7 +1027,7 @@
 	ICPU(0x45, core_params),
 	ICPU(0x46, core_params),
 	ICPU(0x47, core_params),
-	ICPU(0x4c, byt_params),
+	ICPU(0x4c, airmont_params),
 	ICPU(0x4e, core_params),
 	ICPU(0x4f, core_params),
 	ICPU(0x5e, core_params),
@@ -1229,12 +1094,6 @@
 
 static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 {
-#if IS_ENABLED(CONFIG_ACPI)
-	struct cpudata *cpu;
-	int i;
-#endif
-	pr_debug("intel_pstate: %s max %u policy->max %u\n", __func__,
-		 policy->cpuinfo.max_freq, policy->max);
 	if (!policy->cpuinfo.max_freq)
 		return -ENODEV;
 
@@ -1242,6 +1101,8 @@
 	    policy->max >= policy->cpuinfo.max_freq) {
 		pr_debug("intel_pstate: set performance\n");
 		limits = &performance_limits;
+		if (hwp_active)
+			intel_pstate_hwp_set();
 		return 0;
 	}
 
@@ -1249,7 +1110,8 @@
 	limits = &powersave_limits;
 	limits->min_policy_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
 	limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, 0 , 100);
-	limits->max_policy_pct = (policy->max * 100) / policy->cpuinfo.max_freq;
+	limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100,
+					      policy->cpuinfo.max_freq);
 	limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0 , 100);
 
 	/* Normalize user input to [min_policy_pct, max_policy_pct] */
@@ -1261,6 +1123,7 @@
 				   limits->max_sysfs_pct);
 	limits->max_perf_pct = max(limits->min_policy_pct,
 				   limits->max_perf_pct);
+	limits->max_perf = round_up(limits->max_perf, 8);
 
 	/* Make sure min_perf_pct <= max_perf_pct */
 	limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
@@ -1270,23 +1133,6 @@
 	limits->max_perf = div_fp(int_tofp(limits->max_perf_pct),
 				  int_tofp(100));
 
-#if IS_ENABLED(CONFIG_ACPI)
-	cpu = all_cpu_data[policy->cpu];
-	for (i = 0; i < cpu->acpi_perf_data.state_count; i++) {
-		int control;
-
-		control = convert_to_native_pstate_format(cpu, i);
-		if (control * cpu->pstate.scaling == policy->max)
-			limits->max_perf_ctl = control;
-		if (control * cpu->pstate.scaling == policy->min)
-			limits->min_perf_ctl = control;
-	}
-
-	pr_debug("intel_pstate: max %u policy_max %u perf_ctl [0x%x-0x%x]\n",
-		 policy->cpuinfo.max_freq, policy->max, limits->min_perf_ctl,
-		 limits->max_perf_ctl);
-#endif
-
 	if (hwp_active)
 		intel_pstate_hwp_set();
 
@@ -1341,30 +1187,18 @@
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	policy->cpuinfo.max_freq =
 		cpu->pstate.turbo_pstate * cpu->pstate.scaling;
-	if (!no_acpi_perf)
-		intel_pstate_init_perf_limits(policy);
-	/*
-	 * If there is no acpi perf data or error, we ignore and use Intel P
-	 * state calculated limits, So this is not fatal error.
-	 */
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	cpumask_set_cpu(policy->cpu, policy->cpus);
 
 	return 0;
 }
 
-static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
-{
-	return intel_pstate_exit_perf_limits(policy);
-}
-
 static struct cpufreq_driver intel_pstate_driver = {
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.verify		= intel_pstate_verify_policy,
 	.setpolicy	= intel_pstate_set_policy,
 	.get		= intel_pstate_get,
 	.init		= intel_pstate_cpu_init,
-	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_pstate_stop_cpu,
 	.name		= "intel_pstate",
 };
@@ -1406,6 +1240,7 @@
 }
 
 #if IS_ENABLED(CONFIG_ACPI)
+#include <acpi/processor.h>
 
 static bool intel_pstate_no_acpi_pss(void)
 {
@@ -1601,9 +1436,6 @@
 		force_load = 1;
 	if (!strcmp(str, "hwp_only"))
 		hwp_only = 1;
-	if (!strcmp(str, "no_acpi"))
-		no_acpi_perf = 1;
-
 	return 0;
 }
 early_param("intel_pstate", intel_pstate_setup);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 4e55239..53d22eb 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -729,8 +729,8 @@
 		return NULL;
 
 	dev_info(chan2dev(chan),
-		 "%s: src=0x%08x, dest=0x%08x, numf=%d, frame_size=%d, flags=0x%lx\n",
-		__func__, xt->src_start, xt->dst_start, xt->numf,
+		 "%s: src=%pad, dest=%pad, numf=%d, frame_size=%d, flags=0x%lx\n",
+		__func__, &xt->src_start, &xt->dst_start, xt->numf,
 		xt->frame_size, flags);
 
 	/*
@@ -824,8 +824,8 @@
 	u32			ctrla;
 	u32			ctrlb;
 
-	dev_vdbg(chan2dev(chan), "prep_dma_memcpy: d0x%x s0x%x l0x%zx f0x%lx\n",
-			dest, src, len, flags);
+	dev_vdbg(chan2dev(chan), "prep_dma_memcpy: d%pad s%pad l0x%zx f0x%lx\n",
+			&dest, &src, len, flags);
 
 	if (unlikely(!len)) {
 		dev_dbg(chan2dev(chan), "prep_dma_memcpy: length is zero!\n");
@@ -938,8 +938,8 @@
 	void __iomem		*vaddr;
 	dma_addr_t		paddr;
 
-	dev_vdbg(chan2dev(chan), "%s: d0x%x v0x%x l0x%zx f0x%lx\n", __func__,
-		dest, value, len, flags);
+	dev_vdbg(chan2dev(chan), "%s: d%pad v0x%x l0x%zx f0x%lx\n", __func__,
+		&dest, value, len, flags);
 
 	if (unlikely(!len)) {
 		dev_dbg(chan2dev(chan), "%s: length is zero!\n", __func__);
@@ -1022,8 +1022,8 @@
 		dma_addr_t dest = sg_dma_address(sg);
 		size_t len = sg_dma_len(sg);
 
-		dev_vdbg(chan2dev(chan), "%s: d0x%08x, l0x%zx\n",
-			 __func__, dest, len);
+		dev_vdbg(chan2dev(chan), "%s: d%pad, l0x%zx\n",
+			 __func__, &dest, len);
 
 		if (!is_dma_fill_aligned(chan->device, dest, 0, len)) {
 			dev_err(chan2dev(chan), "%s: buffer is not aligned\n",
@@ -1439,9 +1439,9 @@
 	unsigned int		periods = buf_len / period_len;
 	unsigned int		i;
 
-	dev_vdbg(chan2dev(chan), "prep_dma_cyclic: %s buf@0x%08x - %d (%d/%d)\n",
+	dev_vdbg(chan2dev(chan), "prep_dma_cyclic: %s buf@%pad - %d (%d/%d)\n",
 			direction == DMA_MEM_TO_DEV ? "TO DEVICE" : "FROM DEVICE",
-			buf_addr,
+			&buf_addr,
 			periods, buf_len, period_len);
 
 	if (unlikely(!atslave || !buf_len || !period_len)) {
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index d1cfc8c..7f58f06 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -385,9 +385,9 @@
 static void atc_dump_lli(struct at_dma_chan *atchan, struct at_lli *lli)
 {
 	dev_crit(chan2dev(&atchan->chan_common),
-		 "  desc: s0x%x d0x%x ctrl0x%x:0x%x l0x%x\n",
-		 lli->saddr, lli->daddr,
-		 lli->ctrla, lli->ctrlb, lli->dscr);
+		 "  desc: s%pad d%pad ctrl0x%x:0x%x l0x%pad\n",
+		 &lli->saddr, &lli->daddr,
+		 lli->ctrla, lli->ctrlb, &lli->dscr);
 }
 
 
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index b5e132d..7f039de 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -920,8 +920,8 @@
 	desc->lld.mbr_cfg = chan_cc;
 
 	dev_dbg(chan2dev(chan),
-		"%s: lld: mbr_sa=0x%08x, mbr_da=0x%08x, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
-		__func__, desc->lld.mbr_sa, desc->lld.mbr_da,
+		"%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
+		__func__, &desc->lld.mbr_sa, &desc->lld.mbr_da,
 		desc->lld.mbr_ubc, desc->lld.mbr_cfg);
 
 	/* Chain lld. */
@@ -953,8 +953,8 @@
 	if ((xt->numf > 1) && (xt->frame_size > 1))
 		return NULL;
 
-	dev_dbg(chan2dev(chan), "%s: src=0x%08x, dest=0x%08x, numf=%d, frame_size=%d, flags=0x%lx\n",
-		__func__, xt->src_start, xt->dst_start,	xt->numf,
+	dev_dbg(chan2dev(chan), "%s: src=%pad, dest=%pad, numf=%d, frame_size=%d, flags=0x%lx\n",
+		__func__, &xt->src_start, &xt->dst_start,	xt->numf,
 		xt->frame_size, flags);
 
 	src_addr = xt->src_start;
@@ -1179,8 +1179,8 @@
 	desc->lld.mbr_cfg = chan_cc;
 
 	dev_dbg(chan2dev(chan),
-		"%s: lld: mbr_da=0x%08x, mbr_ds=0x%08x, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
-		__func__, desc->lld.mbr_da, desc->lld.mbr_ds, desc->lld.mbr_ubc,
+		"%s: lld: mbr_da=%pad, mbr_ds=%pad, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
+		__func__, &desc->lld.mbr_da, &desc->lld.mbr_ds, desc->lld.mbr_ubc,
 		desc->lld.mbr_cfg);
 
 	return desc;
@@ -1193,8 +1193,8 @@
 	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
 	struct at_xdmac_desc	*desc;
 
-	dev_dbg(chan2dev(chan), "%s: dest=0x%08x, len=%d, pattern=0x%x, flags=0x%lx\n",
-		__func__, dest, len, value, flags);
+	dev_dbg(chan2dev(chan), "%s: dest=%pad, len=%d, pattern=0x%x, flags=0x%lx\n",
+		__func__, &dest, len, value, flags);
 
 	if (unlikely(!len))
 		return NULL;
@@ -1229,8 +1229,8 @@
 
 	/* Prepare descriptors. */
 	for_each_sg(sgl, sg, sg_len, i) {
-		dev_dbg(chan2dev(chan), "%s: dest=0x%08x, len=%d, pattern=0x%x, flags=0x%lx\n",
-			__func__, sg_dma_address(sg), sg_dma_len(sg),
+		dev_dbg(chan2dev(chan), "%s: dest=%pad, len=%d, pattern=0x%x, flags=0x%lx\n",
+			__func__, &sg_dma_address(sg), sg_dma_len(sg),
 			value, flags);
 		desc = at_xdmac_memset_create_desc(chan, atchan,
 						   sg_dma_address(sg),
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 6b03e4e..0675e26 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -107,7 +107,7 @@
 
 /* CCCFG register */
 #define GET_NUM_DMACH(x)	(x & 0x7) /* bits 0-2 */
-#define GET_NUM_QDMACH(x)	(x & 0x70 >> 4) /* bits 4-6 */
+#define GET_NUM_QDMACH(x)	((x & 0x70) >> 4) /* bits 4-6 */
 #define GET_NUM_PAENTRY(x)	((x & 0x7000) >> 12) /* bits 12-14 */
 #define GET_NUM_EVQUE(x)	((x & 0x70000) >> 16) /* bits 16-18 */
 #define GET_NUM_REGN(x)		((x & 0x300000) >> 20) /* bits 20-21 */
@@ -1565,7 +1565,7 @@
 	struct platform_device *tc_pdev;
 	int ret;
 
-	if (!tc)
+	if (!IS_ENABLED(CONFIG_OF) || !tc)
 		return;
 
 	tc_pdev = of_find_device_by_node(tc->node);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 7058d58..0f6fd42 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1462,7 +1462,7 @@
 
 #define EVENT_REMAP_CELLS 3
 
-static int __init sdma_event_remap(struct sdma_engine *sdma)
+static int sdma_event_remap(struct sdma_engine *sdma)
 {
 	struct device_node *np = sdma->dev->of_node;
 	struct device_node *gpr_np = of_parse_phandle(np, "gpr", 0);
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index ebd8a5f..f1bcc2a 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -679,8 +679,11 @@
 	struct usb_dmac *dmac = dev_get_drvdata(dev);
 	int i;
 
-	for (i = 0; i < dmac->n_channels; ++i)
+	for (i = 0; i < dmac->n_channels; ++i) {
+		if (!dmac->channels[i].iomem)
+			break;
 		usb_dmac_chan_halt(&dmac->channels[i]);
+	}
 
 	return 0;
 }
@@ -799,11 +802,10 @@
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret);
-		return ret;
+		goto error_pm;
 	}
 
 	ret = usb_dmac_init(dmac);
-	pm_runtime_put(&pdev->dev);
 
 	if (ret) {
 		dev_err(&pdev->dev, "failed to reset device\n");
@@ -851,10 +853,13 @@
 	if (ret < 0)
 		goto error;
 
+	pm_runtime_put(&pdev->dev);
 	return 0;
 
 error:
 	of_dma_controller_free(pdev->dev.of_node);
+	pm_runtime_put(&pdev->dev);
+error_pm:
 	pm_runtime_disable(&pdev->dev);
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 615ce6d..251b147 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -389,7 +389,6 @@
  * Fences.
  */
 struct amdgpu_fence_driver {
-	struct amdgpu_ring		*ring;
 	uint64_t			gpu_addr;
 	volatile uint32_t		*cpu_addr;
 	/* sync_seq is protected by ring emission lock */
@@ -398,7 +397,7 @@
 	bool				initialized;
 	struct amdgpu_irq_src		*irq_src;
 	unsigned			irq_type;
-	struct delayed_work             lockup_work;
+	struct timer_list		fallback_timer;
 	wait_queue_head_t		fence_queue;
 };
 
@@ -497,6 +496,7 @@
 
 /* bo virtual addresses in a specific vm */
 struct amdgpu_bo_va {
+	struct mutex		        mutex;
 	/* protected by bo being reserved */
 	struct list_head		bo_list;
 	struct fence		        *last_pt_update;
@@ -917,8 +917,8 @@
 #define AMDGPU_VM_FAULT_STOP_ALWAYS	2
 
 struct amdgpu_vm_pt {
-	struct amdgpu_bo		*bo;
-	uint64_t			addr;
+	struct amdgpu_bo	*bo;
+	uint64_t		addr;
 };
 
 struct amdgpu_vm_id {
@@ -926,13 +926,9 @@
 	uint64_t		pd_gpu_addr;
 	/* last flushed PD/PT update */
 	struct fence	        *flushed_updates;
-	/* last use of vmid */
-	struct fence		*last_id_use;
 };
 
 struct amdgpu_vm {
-	struct mutex		mutex;
-
 	struct rb_root		va;
 
 	/* protecting invalidated */
@@ -957,24 +953,70 @@
 
 	/* for id and flush management per ring */
 	struct amdgpu_vm_id	ids[AMDGPU_MAX_RINGS];
+	/* for interval tree */
+	spinlock_t		it_lock;
 };
 
 struct amdgpu_vm_manager {
-	struct fence			*active[AMDGPU_NUM_VM];
-	uint32_t			max_pfn;
+	struct {
+		struct fence	*active;
+		atomic_long_t	owner;
+	} ids[AMDGPU_NUM_VM];
+
+	uint32_t				max_pfn;
 	/* number of VMIDs */
-	unsigned			nvm;
+	unsigned				nvm;
 	/* vram base address for page table entry  */
-	u64				vram_base_offset;
+	u64					vram_base_offset;
 	/* is vm enabled? */
-	bool				enabled;
-	/* for hw to save the PD addr on suspend/resume */
-	uint32_t			saved_table_addr[AMDGPU_NUM_VM];
+	bool					enabled;
 	/* vm pte handling */
 	const struct amdgpu_vm_pte_funcs        *vm_pte_funcs;
 	struct amdgpu_ring                      *vm_pte_funcs_ring;
 };
 
+void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
+int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm);
+void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
+struct amdgpu_bo_list_entry *amdgpu_vm_get_bos(struct amdgpu_device *adev,
+					       struct amdgpu_vm *vm,
+					       struct list_head *head);
+int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
+		      struct amdgpu_sync *sync);
+void amdgpu_vm_flush(struct amdgpu_ring *ring,
+		     struct amdgpu_vm *vm,
+		     struct fence *updates);
+void amdgpu_vm_fence(struct amdgpu_device *adev,
+		     struct amdgpu_vm *vm,
+		     struct fence *fence);
+uint64_t amdgpu_vm_map_gart(struct amdgpu_device *adev, uint64_t addr);
+int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
+				    struct amdgpu_vm *vm);
+int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
+			  struct amdgpu_vm *vm);
+int amdgpu_vm_clear_invalids(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+			     struct amdgpu_sync *sync);
+int amdgpu_vm_bo_update(struct amdgpu_device *adev,
+			struct amdgpu_bo_va *bo_va,
+			struct ttm_mem_reg *mem);
+void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
+			     struct amdgpu_bo *bo);
+struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
+				       struct amdgpu_bo *bo);
+struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
+				      struct amdgpu_vm *vm,
+				      struct amdgpu_bo *bo);
+int amdgpu_vm_bo_map(struct amdgpu_device *adev,
+		     struct amdgpu_bo_va *bo_va,
+		     uint64_t addr, uint64_t offset,
+		     uint64_t size, uint32_t flags);
+int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
+		       struct amdgpu_bo_va *bo_va,
+		       uint64_t addr);
+void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
+		      struct amdgpu_bo_va *bo_va);
+int amdgpu_vm_free_job(struct amdgpu_job *job);
+
 /*
  * context related structures
  */
@@ -1211,6 +1253,7 @@
 	/* relocations */
 	struct amdgpu_bo_list_entry	*vm_bos;
 	struct list_head	validated;
+	struct fence		*fence;
 
 	struct amdgpu_ib	*ibs;
 	uint32_t		num_ibs;
@@ -1226,7 +1269,7 @@
 	struct amdgpu_device	*adev;
 	struct amdgpu_ib	*ibs;
 	uint32_t		num_ibs;
-	struct mutex            job_lock;
+	void			*owner;
 	struct amdgpu_user_fence uf;
 	int (*free_job)(struct amdgpu_job *job);
 };
@@ -2257,11 +2300,6 @@
 bool amdgpu_card_posted(struct amdgpu_device *adev);
 void amdgpu_update_display_priority(struct amdgpu_device *adev);
 bool amdgpu_boot_test_post_card(struct amdgpu_device *adev);
-struct amdgpu_cs_parser *amdgpu_cs_parser_create(struct amdgpu_device *adev,
-						 struct drm_file *filp,
-						 struct amdgpu_ctx *ctx,
-						 struct amdgpu_ib *ibs,
-						 uint32_t num_ibs);
 
 int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data);
 int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
@@ -2319,49 +2357,6 @@
 			     unsigned long arg);
 
 /*
- * vm
- */
-int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm);
-void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
-struct amdgpu_bo_list_entry *amdgpu_vm_get_bos(struct amdgpu_device *adev,
-					  struct amdgpu_vm *vm,
-					  struct list_head *head);
-int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
-		      struct amdgpu_sync *sync);
-void amdgpu_vm_flush(struct amdgpu_ring *ring,
-		     struct amdgpu_vm *vm,
-		     struct fence *updates);
-void amdgpu_vm_fence(struct amdgpu_device *adev,
-		     struct amdgpu_vm *vm,
-		     struct amdgpu_fence *fence);
-uint64_t amdgpu_vm_map_gart(struct amdgpu_device *adev, uint64_t addr);
-int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
-				    struct amdgpu_vm *vm);
-int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
-				struct amdgpu_vm *vm);
-int amdgpu_vm_clear_invalids(struct amdgpu_device *adev,
-				struct amdgpu_vm *vm, struct amdgpu_sync *sync);
-int amdgpu_vm_bo_update(struct amdgpu_device *adev,
-			struct amdgpu_bo_va *bo_va,
-			struct ttm_mem_reg *mem);
-void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
-			     struct amdgpu_bo *bo);
-struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
-				       struct amdgpu_bo *bo);
-struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
-				      struct amdgpu_vm *vm,
-				      struct amdgpu_bo *bo);
-int amdgpu_vm_bo_map(struct amdgpu_device *adev,
-		     struct amdgpu_bo_va *bo_va,
-		     uint64_t addr, uint64_t offset,
-		     uint64_t size, uint32_t flags);
-int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
-		       struct amdgpu_bo_va *bo_va,
-		       uint64_t addr);
-void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
-		      struct amdgpu_bo_va *bo_va);
-int amdgpu_vm_free_job(struct amdgpu_job *job);
-/*
  * functions used by amdgpu_encoder.c
  */
 struct amdgpu_afmt_acr {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index dfc4d02..1d44d50 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -127,30 +127,6 @@
 	return 0;
 }
 
-struct amdgpu_cs_parser *amdgpu_cs_parser_create(struct amdgpu_device *adev,
-                                               struct drm_file *filp,
-                                               struct amdgpu_ctx *ctx,
-                                               struct amdgpu_ib *ibs,
-                                               uint32_t num_ibs)
-{
-	struct amdgpu_cs_parser *parser;
-	int i;
-
-	parser = kzalloc(sizeof(struct amdgpu_cs_parser), GFP_KERNEL);
-	if (!parser)
-		return NULL;
-
-	parser->adev = adev;
-	parser->filp = filp;
-	parser->ctx = ctx;
-	parser->ibs = ibs;
-	parser->num_ibs = num_ibs;
-	for (i = 0; i < num_ibs; i++)
-		ibs[i].ctx = ctx;
-
-	return parser;
-}
-
 int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 {
 	union drm_amdgpu_cs *cs = data;
@@ -463,8 +439,18 @@
 	return (int)la->robj->tbo.num_pages - (int)lb->robj->tbo.num_pages;
 }
 
-static void amdgpu_cs_parser_fini_early(struct amdgpu_cs_parser *parser, int error, bool backoff)
+/**
+ * cs_parser_fini() - clean parser states
+ * @parser:	parser structure holding parsing context.
+ * @error:	error number
+ *
+ * If error is set than unvalidate buffer, otherwise just free memory
+ * used by parsing context.
+ **/
+static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bool backoff)
 {
+	unsigned i;
+
 	if (!error) {
 		/* Sort the buffer list from the smallest to largest buffer,
 		 * which affects the order of buffers in the LRU list.
@@ -479,17 +465,14 @@
 		list_sort(NULL, &parser->validated, cmp_size_smaller_first);
 
 		ttm_eu_fence_buffer_objects(&parser->ticket,
-				&parser->validated,
-				&parser->ibs[parser->num_ibs-1].fence->base);
+					    &parser->validated,
+					    parser->fence);
 	} else if (backoff) {
 		ttm_eu_backoff_reservation(&parser->ticket,
 					   &parser->validated);
 	}
-}
+	fence_put(parser->fence);
 
-static void amdgpu_cs_parser_fini_late(struct amdgpu_cs_parser *parser)
-{
-	unsigned i;
 	if (parser->ctx)
 		amdgpu_ctx_put(parser->ctx);
 	if (parser->bo_list)
@@ -499,31 +482,12 @@
 	for (i = 0; i < parser->nchunks; i++)
 		drm_free_large(parser->chunks[i].kdata);
 	kfree(parser->chunks);
-	if (!amdgpu_enable_scheduler)
-	{
-		if (parser->ibs)
-			for (i = 0; i < parser->num_ibs; i++)
-				amdgpu_ib_free(parser->adev, &parser->ibs[i]);
-		kfree(parser->ibs);
-		if (parser->uf.bo)
-			drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base);
-	}
-
-	kfree(parser);
-}
-
-/**
- * cs_parser_fini() - clean parser states
- * @parser:	parser structure holding parsing context.
- * @error:	error number
- *
- * If error is set than unvalidate buffer, otherwise just free memory
- * used by parsing context.
- **/
-static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bool backoff)
-{
-       amdgpu_cs_parser_fini_early(parser, error, backoff);
-       amdgpu_cs_parser_fini_late(parser);
+	if (parser->ibs)
+		for (i = 0; i < parser->num_ibs; i++)
+			amdgpu_ib_free(parser->adev, &parser->ibs[i]);
+	kfree(parser->ibs);
+	if (parser->uf.bo)
+		drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base);
 }
 
 static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p,
@@ -610,15 +574,9 @@
 	}
 
 	r = amdgpu_bo_vm_update_pte(parser, vm);
-	if (r) {
-		goto out;
-	}
-	amdgpu_cs_sync_rings(parser);
-	if (!amdgpu_enable_scheduler)
-		r = amdgpu_ib_schedule(adev, parser->num_ibs, parser->ibs,
-				       parser->filp);
+	if (!r)
+		amdgpu_cs_sync_rings(parser);
 
-out:
 	return r;
 }
 
@@ -826,38 +784,35 @@
 {
 	struct amdgpu_device *adev = dev->dev_private;
 	union drm_amdgpu_cs *cs = data;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
-	struct amdgpu_vm *vm = &fpriv->vm;
-	struct amdgpu_cs_parser *parser;
+	struct amdgpu_cs_parser parser = {};
 	bool reserved_buffers = false;
 	int i, r;
 
 	if (!adev->accel_working)
 		return -EBUSY;
 
-	parser = amdgpu_cs_parser_create(adev, filp, NULL, NULL, 0);
-	if (!parser)
-		return -ENOMEM;
-	r = amdgpu_cs_parser_init(parser, data);
+	parser.adev = adev;
+	parser.filp = filp;
+
+	r = amdgpu_cs_parser_init(&parser, data);
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
-		amdgpu_cs_parser_fini(parser, r, false);
+		amdgpu_cs_parser_fini(&parser, r, false);
 		r = amdgpu_cs_handle_lockup(adev, r);
 		return r;
 	}
-	mutex_lock(&vm->mutex);
-	r = amdgpu_cs_parser_relocs(parser);
+	r = amdgpu_cs_parser_relocs(&parser);
 	if (r == -ENOMEM)
 		DRM_ERROR("Not enough memory for command submission!\n");
 	else if (r && r != -ERESTARTSYS)
 		DRM_ERROR("Failed to process the buffer list %d!\n", r);
 	else if (!r) {
 		reserved_buffers = true;
-		r = amdgpu_cs_ib_fill(adev, parser);
+		r = amdgpu_cs_ib_fill(adev, &parser);
 	}
 
 	if (!r) {
-		r = amdgpu_cs_dependencies(adev, parser);
+		r = amdgpu_cs_dependencies(adev, &parser);
 		if (r)
 			DRM_ERROR("Failed in the dependencies handling %d!\n", r);
 	}
@@ -865,63 +820,71 @@
 	if (r)
 		goto out;
 
-	for (i = 0; i < parser->num_ibs; i++)
-		trace_amdgpu_cs(parser, i);
+	for (i = 0; i < parser.num_ibs; i++)
+		trace_amdgpu_cs(&parser, i);
 
-	r = amdgpu_cs_ib_vm_chunk(adev, parser);
+	r = amdgpu_cs_ib_vm_chunk(adev, &parser);
 	if (r)
 		goto out;
 
-	if (amdgpu_enable_scheduler && parser->num_ibs) {
+	if (amdgpu_enable_scheduler && parser.num_ibs) {
+		struct amdgpu_ring * ring = parser.ibs->ring;
+		struct amd_sched_fence *fence;
 		struct amdgpu_job *job;
-		struct amdgpu_ring * ring =  parser->ibs->ring;
+
 		job = kzalloc(sizeof(struct amdgpu_job), GFP_KERNEL);
 		if (!job) {
 			r = -ENOMEM;
 			goto out;
 		}
+
 		job->base.sched = &ring->sched;
-		job->base.s_entity = &parser->ctx->rings[ring->idx].entity;
-		job->adev = parser->adev;
-		job->ibs = parser->ibs;
-		job->num_ibs = parser->num_ibs;
-		job->base.owner = parser->filp;
-		mutex_init(&job->job_lock);
+		job->base.s_entity = &parser.ctx->rings[ring->idx].entity;
+		job->adev = parser.adev;
+		job->owner = parser.filp;
+		job->free_job = amdgpu_cs_free_job;
+
+		job->ibs = parser.ibs;
+		job->num_ibs = parser.num_ibs;
+		parser.ibs = NULL;
+		parser.num_ibs = 0;
+
 		if (job->ibs[job->num_ibs - 1].user) {
-			memcpy(&job->uf,  &parser->uf,
-			       sizeof(struct amdgpu_user_fence));
+			job->uf = parser.uf;
 			job->ibs[job->num_ibs - 1].user = &job->uf;
+			parser.uf.bo = NULL;
 		}
 
-		job->free_job = amdgpu_cs_free_job;
-		mutex_lock(&job->job_lock);
-		r = amd_sched_entity_push_job(&job->base);
-		if (r) {
-			mutex_unlock(&job->job_lock);
+		fence = amd_sched_fence_create(job->base.s_entity,
+					       parser.filp);
+		if (!fence) {
+			r = -ENOMEM;
 			amdgpu_cs_free_job(job);
 			kfree(job);
 			goto out;
 		}
-		cs->out.handle =
-			amdgpu_ctx_add_fence(parser->ctx, ring,
-					     &job->base.s_fence->base);
-		parser->ibs[parser->num_ibs - 1].sequence = cs->out.handle;
+		job->base.s_fence = fence;
+		parser.fence = fence_get(&fence->base);
 
-		list_sort(NULL, &parser->validated, cmp_size_smaller_first);
-		ttm_eu_fence_buffer_objects(&parser->ticket,
-				&parser->validated,
-				&job->base.s_fence->base);
+		cs->out.handle = amdgpu_ctx_add_fence(parser.ctx, ring,
+						      &fence->base);
+		job->ibs[job->num_ibs - 1].sequence = cs->out.handle;
 
-		mutex_unlock(&job->job_lock);
-		amdgpu_cs_parser_fini_late(parser);
-		mutex_unlock(&vm->mutex);
-		return 0;
+		trace_amdgpu_cs_ioctl(job);
+		amd_sched_entity_push_job(&job->base);
+
+	} else {
+		struct amdgpu_fence *fence;
+
+		r = amdgpu_ib_schedule(adev, parser.num_ibs, parser.ibs,
+				       parser.filp);
+		fence = parser.ibs[parser.num_ibs - 1].fence;
+		parser.fence = fence_get(&fence->base);
+		cs->out.handle = parser.ibs[parser.num_ibs - 1].sequence;
 	}
 
-	cs->out.handle = parser->ibs[parser->num_ibs - 1].sequence;
 out:
-	amdgpu_cs_parser_fini(parser, r, reserved_buffers);
-	mutex_unlock(&vm->mutex);
+	amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
 	r = amdgpu_cs_handle_lockup(adev, r);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 257d722..3671f9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -47,6 +47,9 @@
  * that the the relevant GPU caches have been flushed.
  */
 
+static struct kmem_cache *amdgpu_fence_slab;
+static atomic_t amdgpu_fence_slab_ref = ATOMIC_INIT(0);
+
 /**
  * amdgpu_fence_write - write a fence value
  *
@@ -85,24 +88,6 @@
 }
 
 /**
- * amdgpu_fence_schedule_check - schedule lockup check
- *
- * @ring: pointer to struct amdgpu_ring
- *
- * Queues a delayed work item to check for lockups.
- */
-static void amdgpu_fence_schedule_check(struct amdgpu_ring *ring)
-{
-	/*
-	 * Do not reset the timer here with mod_delayed_work,
-	 * this can livelock in an interaction with TTM delayed destroy.
-	 */
-	queue_delayed_work(system_power_efficient_wq,
-		&ring->fence_drv.lockup_work,
-		AMDGPU_FENCE_JIFFIES_TIMEOUT);
-}
-
-/**
  * amdgpu_fence_emit - emit a fence on the requested ring
  *
  * @ring: ring the fence is associated with
@@ -118,7 +103,7 @@
 	struct amdgpu_device *adev = ring->adev;
 
 	/* we are protected by the ring emission mutex */
-	*fence = kmalloc(sizeof(struct amdgpu_fence), GFP_KERNEL);
+	*fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_KERNEL);
 	if ((*fence) == NULL) {
 		return -ENOMEM;
 	}
@@ -132,11 +117,23 @@
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       (*fence)->seq,
 			       AMDGPU_FENCE_FLAG_INT);
-	trace_amdgpu_fence_emit(ring->adev->ddev, ring->idx, (*fence)->seq);
 	return 0;
 }
 
 /**
+ * amdgpu_fence_schedule_fallback - schedule fallback check
+ *
+ * @ring: pointer to struct amdgpu_ring
+ *
+ * Start a timer as fallback to our interrupts.
+ */
+static void amdgpu_fence_schedule_fallback(struct amdgpu_ring *ring)
+{
+	mod_timer(&ring->fence_drv.fallback_timer,
+		  jiffies + AMDGPU_FENCE_JIFFIES_TIMEOUT);
+}
+
+/**
  * amdgpu_fence_activity - check for fence activity
  *
  * @ring: pointer to struct amdgpu_ring
@@ -202,33 +199,12 @@
 	} while (atomic64_xchg(&ring->fence_drv.last_seq, seq) > seq);
 
 	if (seq < last_emitted)
-		amdgpu_fence_schedule_check(ring);
+		amdgpu_fence_schedule_fallback(ring);
 
 	return wake;
 }
 
 /**
- * amdgpu_fence_check_lockup - check for hardware lockup
- *
- * @work: delayed work item
- *
- * Checks for fence activity and if there is none probe
- * the hardware if a lockup occured.
- */
-static void amdgpu_fence_check_lockup(struct work_struct *work)
-{
-	struct amdgpu_fence_driver *fence_drv;
-	struct amdgpu_ring *ring;
-
-	fence_drv = container_of(work, struct amdgpu_fence_driver,
-				lockup_work.work);
-	ring = fence_drv->ring;
-
-	if (amdgpu_fence_activity(ring))
-		wake_up_all(&ring->fence_drv.fence_queue);
-}
-
-/**
  * amdgpu_fence_process - process a fence
  *
  * @adev: amdgpu_device pointer
@@ -244,6 +220,20 @@
 }
 
 /**
+ * amdgpu_fence_fallback - fallback for hardware interrupts
+ *
+ * @work: delayed work item
+ *
+ * Checks for fence activity.
+ */
+static void amdgpu_fence_fallback(unsigned long arg)
+{
+	struct amdgpu_ring *ring = (void *)arg;
+
+	amdgpu_fence_process(ring);
+}
+
+/**
  * amdgpu_fence_seq_signaled - check if a fence sequence number has signaled
  *
  * @ring: ring the fence is associated with
@@ -290,7 +280,7 @@
 	if (atomic64_read(&ring->fence_drv.last_seq) >= seq)
 		return 0;
 
-	amdgpu_fence_schedule_check(ring);
+	amdgpu_fence_schedule_fallback(ring);
 	wait_event(ring->fence_drv.fence_queue, (
 		   (signaled = amdgpu_fence_seq_signaled(ring, seq))));
 
@@ -491,9 +481,8 @@
 	atomic64_set(&ring->fence_drv.last_seq, 0);
 	ring->fence_drv.initialized = false;
 
-	INIT_DELAYED_WORK(&ring->fence_drv.lockup_work,
-			amdgpu_fence_check_lockup);
-	ring->fence_drv.ring = ring;
+	setup_timer(&ring->fence_drv.fallback_timer, amdgpu_fence_fallback,
+		    (unsigned long)ring);
 
 	init_waitqueue_head(&ring->fence_drv.fence_queue);
 
@@ -536,6 +525,13 @@
  */
 int amdgpu_fence_driver_init(struct amdgpu_device *adev)
 {
+	if (atomic_inc_return(&amdgpu_fence_slab_ref) == 1) {
+		amdgpu_fence_slab = kmem_cache_create(
+			"amdgpu_fence", sizeof(struct amdgpu_fence), 0,
+			SLAB_HWCACHE_ALIGN, NULL);
+		if (!amdgpu_fence_slab)
+			return -ENOMEM;
+	}
 	if (amdgpu_debugfs_fence_init(adev))
 		dev_err(adev->dev, "fence debugfs file creation failed\n");
 
@@ -554,9 +550,12 @@
 {
 	int i, r;
 
+	if (atomic_dec_and_test(&amdgpu_fence_slab_ref))
+		kmem_cache_destroy(amdgpu_fence_slab);
 	mutex_lock(&adev->ring_lock);
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
+
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 		r = amdgpu_fence_wait_empty(ring);
@@ -568,6 +567,7 @@
 		amdgpu_irq_put(adev, ring->fence_drv.irq_src,
 			       ring->fence_drv.irq_type);
 		amd_sched_fini(&ring->sched);
+		del_timer_sync(&ring->fence_drv.fallback_timer);
 		ring->fence_drv.initialized = false;
 	}
 	mutex_unlock(&adev->ring_lock);
@@ -751,18 +751,25 @@
 	fence->fence_wake.func = amdgpu_fence_check_signaled;
 	__add_wait_queue(&ring->fence_drv.fence_queue, &fence->fence_wake);
 	fence_get(f);
-	amdgpu_fence_schedule_check(ring);
+	if (!timer_pending(&ring->fence_drv.fallback_timer))
+		amdgpu_fence_schedule_fallback(ring);
 	FENCE_TRACE(&fence->base, "armed on ring %i!\n", ring->idx);
 	return true;
 }
 
+static void amdgpu_fence_release(struct fence *f)
+{
+	struct amdgpu_fence *fence = to_amdgpu_fence(f);
+	kmem_cache_free(amdgpu_fence_slab, fence);
+}
+
 const struct fence_ops amdgpu_fence_ops = {
 	.get_driver_name = amdgpu_fence_get_driver_name,
 	.get_timeline_name = amdgpu_fence_get_timeline_name,
 	.enable_signaling = amdgpu_fence_enable_signaling,
 	.signaled = amdgpu_fence_is_signaled,
 	.wait = fence_default_wait,
-	.release = NULL,
+	.release = amdgpu_fence_release,
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 0873328..fc32fc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -115,12 +115,9 @@
 	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_va *bo_va;
 	int r;
-	mutex_lock(&vm->mutex);
 	r = amdgpu_bo_reserve(rbo, false);
-	if (r) {
-		mutex_unlock(&vm->mutex);
+	if (r)
 		return r;
-	}
 
 	bo_va = amdgpu_vm_bo_find(vm, rbo);
 	if (!bo_va) {
@@ -129,7 +126,6 @@
 		++bo_va->ref_count;
 	}
 	amdgpu_bo_unreserve(rbo);
-	mutex_unlock(&vm->mutex);
 	return 0;
 }
 
@@ -142,10 +138,8 @@
 	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_va *bo_va;
 	int r;
-	mutex_lock(&vm->mutex);
 	r = amdgpu_bo_reserve(rbo, true);
 	if (r) {
-		mutex_unlock(&vm->mutex);
 		dev_err(adev->dev, "leaking bo va because "
 			"we fail to reserve bo (%d)\n", r);
 		return;
@@ -157,7 +151,6 @@
 		}
 	}
 	amdgpu_bo_unreserve(rbo);
-	mutex_unlock(&vm->mutex);
 }
 
 static int amdgpu_gem_handle_lockup(struct amdgpu_device *adev, int r)
@@ -483,6 +476,9 @@
 		if (domain == AMDGPU_GEM_DOMAIN_CPU)
 			goto error_unreserve;
 	}
+	r = amdgpu_vm_update_page_directory(adev, bo_va->vm);
+	if (r)
+		goto error_unreserve;
 
 	r = amdgpu_vm_clear_freed(adev, bo_va->vm);
 	if (r)
@@ -512,6 +508,9 @@
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	struct amdgpu_bo *rbo;
 	struct amdgpu_bo_va *bo_va;
+	struct ttm_validate_buffer tv, tv_pd;
+	struct ww_acquire_ctx ticket;
+	struct list_head list, duplicates;
 	uint32_t invalid_flags, va_flags = 0;
 	int r = 0;
 
@@ -547,19 +546,28 @@
 	gobj = drm_gem_object_lookup(dev, filp, args->handle);
 	if (gobj == NULL)
 		return -ENOENT;
-	mutex_lock(&fpriv->vm.mutex);
 	rbo = gem_to_amdgpu_bo(gobj);
-	r = amdgpu_bo_reserve(rbo, false);
+	INIT_LIST_HEAD(&list);
+	INIT_LIST_HEAD(&duplicates);
+	tv.bo = &rbo->tbo;
+	tv.shared = true;
+	list_add(&tv.head, &list);
+
+	if (args->operation == AMDGPU_VA_OP_MAP) {
+		tv_pd.bo = &fpriv->vm.page_directory->tbo;
+		tv_pd.shared = true;
+		list_add(&tv_pd.head, &list);
+	}
+	r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates);
 	if (r) {
-		mutex_unlock(&fpriv->vm.mutex);
 		drm_gem_object_unreference_unlocked(gobj);
 		return r;
 	}
 
 	bo_va = amdgpu_vm_bo_find(&fpriv->vm, rbo);
 	if (!bo_va) {
-		amdgpu_bo_unreserve(rbo);
-		mutex_unlock(&fpriv->vm.mutex);
+		ttm_eu_backoff_reservation(&ticket, &list);
+		drm_gem_object_unreference_unlocked(gobj);
 		return -ENOENT;
 	}
 
@@ -581,10 +589,10 @@
 	default:
 		break;
 	}
-
+	ttm_eu_backoff_reservation(&ticket, &list);
 	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE))
 		amdgpu_gem_va_update_vm(adev, bo_va, args->operation);
-	mutex_unlock(&fpriv->vm.mutex);
+
 	drm_gem_object_unreference_unlocked(gobj);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index e659877..9e25eda 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -62,7 +62,7 @@
 	int r;
 
 	if (size) {
-		r = amdgpu_sa_bo_new(adev, &adev->ring_tmp_bo,
+		r = amdgpu_sa_bo_new(&adev->ring_tmp_bo,
 				      &ib->sa_bo, size, 256);
 		if (r) {
 			dev_err(adev->dev, "failed to get a new IB (%d)\n", r);
@@ -216,7 +216,7 @@
 	}
 
 	if (ib->vm)
-		amdgpu_vm_fence(adev, ib->vm, ib->fence);
+		amdgpu_vm_fence(adev, ib->vm, &ib->fence->base);
 
 	amdgpu_ring_unlock_commit(ring);
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 3c2ff45..ea756e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -189,10 +189,9 @@
 				      struct amdgpu_sa_manager *sa_manager);
 int amdgpu_sa_bo_manager_suspend(struct amdgpu_device *adev,
 					struct amdgpu_sa_manager *sa_manager);
-int amdgpu_sa_bo_new(struct amdgpu_device *adev,
-			    struct amdgpu_sa_manager *sa_manager,
-			    struct amdgpu_sa_bo **sa_bo,
-			    unsigned size, unsigned align);
+int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
+		     struct amdgpu_sa_bo **sa_bo,
+		     unsigned size, unsigned align);
 void amdgpu_sa_bo_free(struct amdgpu_device *adev,
 			      struct amdgpu_sa_bo **sa_bo,
 			      struct fence *fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 0212b31..8b88edb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -311,8 +311,7 @@
 	return false;
 }
 
-int amdgpu_sa_bo_new(struct amdgpu_device *adev,
-		     struct amdgpu_sa_manager *sa_manager,
+int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
 		     struct amdgpu_sa_bo **sa_bo,
 		     unsigned size, unsigned align)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
index dcf4a8a..438c052 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -26,6 +26,7 @@
 #include <linux/sched.h>
 #include <drm/drmP.h>
 #include "amdgpu.h"
+#include "amdgpu_trace.h"
 
 static struct fence *amdgpu_sched_dependency(struct amd_sched_job *sched_job)
 {
@@ -44,11 +45,8 @@
 		return NULL;
 	}
 	job = to_amdgpu_job(sched_job);
-	mutex_lock(&job->job_lock);
-	r = amdgpu_ib_schedule(job->adev,
-			       job->num_ibs,
-			       job->ibs,
-			       job->base.owner);
+	trace_amdgpu_sched_run_job(job);
+	r = amdgpu_ib_schedule(job->adev, job->num_ibs, job->ibs, job->owner);
 	if (r) {
 		DRM_ERROR("Error scheduling IBs (%d)\n", r);
 		goto err;
@@ -61,8 +59,6 @@
 	if (job->free_job)
 		job->free_job(job);
 
-	mutex_unlock(&job->job_lock);
-	fence_put(&job->base.s_fence->base);
 	kfree(job);
 	return fence ? &fence->base : NULL;
 }
@@ -88,21 +84,19 @@
 			return -ENOMEM;
 		job->base.sched = &ring->sched;
 		job->base.s_entity = &adev->kernel_ctx.rings[ring->idx].entity;
+		job->base.s_fence = amd_sched_fence_create(job->base.s_entity, owner);
+		if (!job->base.s_fence) {
+			kfree(job);
+			return -ENOMEM;
+		}
+		*f = fence_get(&job->base.s_fence->base);
+
 		job->adev = adev;
 		job->ibs = ibs;
 		job->num_ibs = num_ibs;
-		job->base.owner = owner;
-		mutex_init(&job->job_lock);
+		job->owner = owner;
 		job->free_job = free_job;
-		mutex_lock(&job->job_lock);
-		r = amd_sched_entity_push_job(&job->base);
-		if (r) {
-			mutex_unlock(&job->job_lock);
-			kfree(job);
-			return r;
-		}
-		*f = fence_get(&job->base.s_fence->base);
-		mutex_unlock(&job->job_lock);
+		amd_sched_entity_push_job(&job->base);
 	} else {
 		r = amdgpu_ib_schedule(adev, num_ibs, ibs, owner);
 		if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c
index ff3ca52..1caaf20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c
@@ -40,7 +40,7 @@
 	if (*semaphore == NULL) {
 		return -ENOMEM;
 	}
-	r = amdgpu_sa_bo_new(adev, &adev->ring_tmp_bo,
+	r = amdgpu_sa_bo_new(&adev->ring_tmp_bo,
 			     &(*semaphore)->sa_bo, 8, 8);
 	if (r) {
 		kfree(*semaphore);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index a6697fd..dd005c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -302,8 +302,14 @@
 			return -EINVAL;
 		}
 
-		if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores ||
-		    (count >= AMDGPU_NUM_SYNCS)) {
+		if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores) {
+			r = fence_wait(&fence->base, true);
+			if (r)
+				return r;
+			continue;
+		}
+
+		if (count >= AMDGPU_NUM_SYNCS) {
 			/* not enough room, wait manually */
 			r = fence_wait(&fence->base, false);
 			if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 76ecbaf..8f9834ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -48,6 +48,57 @@
 		      __entry->fences)
 );
 
+TRACE_EVENT(amdgpu_cs_ioctl,
+	    TP_PROTO(struct amdgpu_job *job),
+	    TP_ARGS(job),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_device *, adev)
+			     __field(struct amd_sched_job *, sched_job)
+			     __field(struct amdgpu_ib *, ib)
+			     __field(struct fence *, fence)
+			     __field(char *, ring_name)
+			     __field(u32, num_ibs)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->adev = job->adev;
+			   __entry->sched_job = &job->base;
+			   __entry->ib = job->ibs;
+			   __entry->fence = &job->base.s_fence->base;
+			   __entry->ring_name = job->ibs[0].ring->name;
+			   __entry->num_ibs = job->num_ibs;
+			   ),
+	    TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u",
+		      __entry->adev, __entry->sched_job, __entry->ib,
+		      __entry->fence, __entry->ring_name, __entry->num_ibs)
+);
+
+TRACE_EVENT(amdgpu_sched_run_job,
+	    TP_PROTO(struct amdgpu_job *job),
+	    TP_ARGS(job),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_device *, adev)
+			     __field(struct amd_sched_job *, sched_job)
+			     __field(struct amdgpu_ib *, ib)
+			     __field(struct fence *, fence)
+			     __field(char *, ring_name)
+			     __field(u32, num_ibs)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->adev = job->adev;
+			   __entry->sched_job = &job->base;
+			   __entry->ib = job->ibs;
+			   __entry->fence = &job->base.s_fence->base;
+			   __entry->ring_name = job->ibs[0].ring->name;
+			   __entry->num_ibs = job->num_ibs;
+			   ),
+	    TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u",
+		      __entry->adev, __entry->sched_job, __entry->ib,
+		      __entry->fence, __entry->ring_name, __entry->num_ibs)
+);
+
+
 TRACE_EVENT(amdgpu_vm_grab_id,
 	    TP_PROTO(unsigned vmid, int ring),
 	    TP_ARGS(vmid, ring),
@@ -196,49 +247,6 @@
 	    TP_printk("list=%p, bo=%p", __entry->list, __entry->bo)
 );
 
-DECLARE_EVENT_CLASS(amdgpu_fence_request,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno),
-
-	    TP_STRUCT__entry(
-			     __field(u32, dev)
-			     __field(int, ring)
-			     __field(u32, seqno)
-			     ),
-
-	    TP_fast_assign(
-			   __entry->dev = dev->primary->index;
-			   __entry->ring = ring;
-			   __entry->seqno = seqno;
-			   ),
-
-	    TP_printk("dev=%u, ring=%d, seqno=%u",
-		      __entry->dev, __entry->ring, __entry->seqno)
-);
-
-DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_emit,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno)
-);
-
-DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_wait_begin,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno)
-);
-
-DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_wait_end,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno)
-);
-
 DECLARE_EVENT_CLASS(amdgpu_semaphore_request,
 
 	    TP_PROTO(int ring, struct amdgpu_semaphore *sem),
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 81bb8e9..d4bac5f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1073,10 +1073,10 @@
 	ret = drm_mm_dump_table(m, mm);
 	spin_unlock(&glob->lru_lock);
 	if (ttm_pl == TTM_PL_VRAM)
-		seq_printf(m, "man size:%llu pages, ram usage:%luMB, vis usage:%luMB\n",
+		seq_printf(m, "man size:%llu pages, ram usage:%lluMB, vis usage:%lluMB\n",
 			   adev->mman.bdev.man[ttm_pl].size,
-			   atomic64_read(&adev->vram_usage) >> 20,
-			   atomic64_read(&adev->vram_vis_usage) >> 20);
+			   (u64)atomic64_read(&adev->vram_usage) >> 20,
+			   (u64)atomic64_read(&adev->vram_vis_usage) >> 20);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 03f0c3b..a745eee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -392,7 +392,10 @@
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session cmd */
 	ib->ptr[ib->length_dw++] = handle;
 
-	ib->ptr[ib->length_dw++] = 0x00000030; /* len */
+	if ((ring->adev->vce.fw_version >> 24) >= 52)
+		ib->ptr[ib->length_dw++] = 0x00000040; /* len */
+	else
+		ib->ptr[ib->length_dw++] = 0x00000030; /* len */
 	ib->ptr[ib->length_dw++] = 0x01000001; /* create cmd */
 	ib->ptr[ib->length_dw++] = 0x00000000;
 	ib->ptr[ib->length_dw++] = 0x00000042;
@@ -404,6 +407,12 @@
 	ib->ptr[ib->length_dw++] = 0x00000100;
 	ib->ptr[ib->length_dw++] = 0x0000000c;
 	ib->ptr[ib->length_dw++] = 0x00000000;
+	if ((ring->adev->vce.fw_version >> 24) >= 52) {
+		ib->ptr[ib->length_dw++] = 0x00000000;
+		ib->ptr[ib->length_dw++] = 0x00000000;
+		ib->ptr[ib->length_dw++] = 0x00000000;
+		ib->ptr[ib->length_dw++] = 0x00000000;
+	}
 
 	ib->ptr[ib->length_dw++] = 0x00000014; /* len */
 	ib->ptr[ib->length_dw++] = 0x05000005; /* feedback buffer */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 633a32a..ae037e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -143,10 +143,15 @@
 	unsigned i;
 
 	/* check if the id is still valid */
-	if (vm_id->id && vm_id->last_id_use &&
-	    vm_id->last_id_use == adev->vm_manager.active[vm_id->id]) {
-		trace_amdgpu_vm_grab_id(vm_id->id, ring->idx);
-		return 0;
+	if (vm_id->id) {
+		unsigned id = vm_id->id;
+		long owner;
+
+		owner = atomic_long_read(&adev->vm_manager.ids[id].owner);
+		if (owner == (long)vm) {
+			trace_amdgpu_vm_grab_id(vm_id->id, ring->idx);
+			return 0;
+		}
 	}
 
 	/* we definately need to flush */
@@ -154,7 +159,7 @@
 
 	/* skip over VMID 0, since it is the system VM */
 	for (i = 1; i < adev->vm_manager.nvm; ++i) {
-		struct fence *fence = adev->vm_manager.active[i];
+		struct fence *fence = adev->vm_manager.ids[i].active;
 		struct amdgpu_ring *fring;
 
 		if (fence == NULL) {
@@ -176,7 +181,7 @@
 		if (choices[i]) {
 			struct fence *fence;
 
-			fence  = adev->vm_manager.active[choices[i]];
+			fence  = adev->vm_manager.ids[choices[i]].active;
 			vm_id->id = choices[i];
 
 			trace_amdgpu_vm_grab_id(choices[i], ring->idx);
@@ -207,24 +212,21 @@
 	uint64_t pd_addr = amdgpu_bo_gpu_offset(vm->page_directory);
 	struct amdgpu_vm_id *vm_id = &vm->ids[ring->idx];
 	struct fence *flushed_updates = vm_id->flushed_updates;
-	bool is_earlier = false;
+	bool is_later;
 
-	if (flushed_updates && updates) {
-		BUG_ON(flushed_updates->context != updates->context);
-		is_earlier = (updates->seqno - flushed_updates->seqno <=
-			      INT_MAX) ? true : false;
-	}
+	if (!flushed_updates)
+		is_later = true;
+	else if (!updates)
+		is_later = false;
+	else
+		is_later = fence_is_later(updates, flushed_updates);
 
-	if (pd_addr != vm_id->pd_gpu_addr || !flushed_updates ||
-	    is_earlier) {
-
+	if (pd_addr != vm_id->pd_gpu_addr || is_later) {
 		trace_amdgpu_vm_flush(pd_addr, ring->idx, vm_id->id);
-		if (is_earlier) {
+		if (is_later) {
 			vm_id->flushed_updates = fence_get(updates);
 			fence_put(flushed_updates);
 		}
-		if (!flushed_updates)
-			vm_id->flushed_updates = fence_get(updates);
 		vm_id->pd_gpu_addr = pd_addr;
 		amdgpu_ring_emit_vm_flush(ring, vm_id->id, vm_id->pd_gpu_addr);
 	}
@@ -244,16 +246,14 @@
  */
 void amdgpu_vm_fence(struct amdgpu_device *adev,
 		     struct amdgpu_vm *vm,
-		     struct amdgpu_fence *fence)
+		     struct fence *fence)
 {
-	unsigned ridx = fence->ring->idx;
-	unsigned vm_id = vm->ids[ridx].id;
+	struct amdgpu_ring *ring = amdgpu_ring_from_fence(fence);
+	unsigned vm_id = vm->ids[ring->idx].id;
 
-	fence_put(adev->vm_manager.active[vm_id]);
-	adev->vm_manager.active[vm_id] = fence_get(&fence->base);
-
-	fence_put(vm->ids[ridx].last_id_use);
-	vm->ids[ridx].last_id_use = fence_get(&fence->base);
+	fence_put(adev->vm_manager.ids[vm_id].active);
+	adev->vm_manager.ids[vm_id].active = fence_get(fence);
+	atomic_long_set(&adev->vm_manager.ids[vm_id].owner, (long)vm);
 }
 
 /**
@@ -332,6 +332,8 @@
  *
  * @adev: amdgpu_device pointer
  * @bo: bo to clear
+ *
+ * need to reserve bo first before calling it.
  */
 static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 			      struct amdgpu_bo *bo)
@@ -343,24 +345,20 @@
 	uint64_t addr;
 	int r;
 
-	r = amdgpu_bo_reserve(bo, false);
-	if (r)
-		return r;
-
 	r = reservation_object_reserve_shared(bo->tbo.resv);
 	if (r)
 		return r;
 
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
 	if (r)
-		goto error_unreserve;
+		goto error;
 
 	addr = amdgpu_bo_gpu_offset(bo);
 	entries = amdgpu_bo_size(bo) / 8;
 
 	ib = kzalloc(sizeof(struct amdgpu_ib), GFP_KERNEL);
 	if (!ib)
-		goto error_unreserve;
+		goto error;
 
 	r = amdgpu_ib_get(ring, NULL, entries * 2 + 64, ib);
 	if (r)
@@ -378,16 +376,14 @@
 	if (!r)
 		amdgpu_bo_fence(bo, fence, true);
 	fence_put(fence);
-	if (amdgpu_enable_scheduler) {
-		amdgpu_bo_unreserve(bo);
+	if (amdgpu_enable_scheduler)
 		return 0;
-	}
+
 error_free:
 	amdgpu_ib_free(adev, ib);
 	kfree(ib);
 
-error_unreserve:
-	amdgpu_bo_unreserve(bo);
+error:
 	return r;
 }
 
@@ -926,8 +922,9 @@
 		bo_va = list_first_entry(&vm->invalidated,
 			struct amdgpu_bo_va, vm_status);
 		spin_unlock(&vm->status_lock);
-
+		mutex_lock(&bo_va->mutex);
 		r = amdgpu_vm_bo_update(adev, bo_va, NULL);
+		mutex_unlock(&bo_va->mutex);
 		if (r)
 			return r;
 
@@ -971,7 +968,7 @@
 	INIT_LIST_HEAD(&bo_va->valids);
 	INIT_LIST_HEAD(&bo_va->invalids);
 	INIT_LIST_HEAD(&bo_va->vm_status);
-
+	mutex_init(&bo_va->mutex);
 	list_add_tail(&bo_va->bo_list, &bo->va);
 
 	return bo_va;
@@ -989,7 +986,7 @@
  * Add a mapping of the BO at the specefied addr into the VM.
  * Returns 0 for success, error for failure.
  *
- * Object has to be reserved and gets unreserved by this function!
+ * Object has to be reserved and unreserved outside!
  */
 int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		     struct amdgpu_bo_va *bo_va,
@@ -1005,30 +1002,27 @@
 
 	/* validate the parameters */
 	if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK ||
-	    size == 0 || size & AMDGPU_GPU_PAGE_MASK) {
-		amdgpu_bo_unreserve(bo_va->bo);
+	    size == 0 || size & AMDGPU_GPU_PAGE_MASK)
 		return -EINVAL;
-	}
 
 	/* make sure object fit at this offset */
 	eaddr = saddr + size;
-	if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo))) {
-		amdgpu_bo_unreserve(bo_va->bo);
+	if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo)))
 		return -EINVAL;
-	}
 
 	last_pfn = eaddr / AMDGPU_GPU_PAGE_SIZE;
 	if (last_pfn > adev->vm_manager.max_pfn) {
 		dev_err(adev->dev, "va above limit (0x%08X > 0x%08X)\n",
 			last_pfn, adev->vm_manager.max_pfn);
-		amdgpu_bo_unreserve(bo_va->bo);
 		return -EINVAL;
 	}
 
 	saddr /= AMDGPU_GPU_PAGE_SIZE;
 	eaddr /= AMDGPU_GPU_PAGE_SIZE;
 
+	spin_lock(&vm->it_lock);
 	it = interval_tree_iter_first(&vm->va, saddr, eaddr - 1);
+	spin_unlock(&vm->it_lock);
 	if (it) {
 		struct amdgpu_bo_va_mapping *tmp;
 		tmp = container_of(it, struct amdgpu_bo_va_mapping, it);
@@ -1036,14 +1030,12 @@
 		dev_err(adev->dev, "bo %p va 0x%010Lx-0x%010Lx conflict with "
 			"0x%010lx-0x%010lx\n", bo_va->bo, saddr, eaddr,
 			tmp->it.start, tmp->it.last + 1);
-		amdgpu_bo_unreserve(bo_va->bo);
 		r = -EINVAL;
 		goto error;
 	}
 
 	mapping = kmalloc(sizeof(*mapping), GFP_KERNEL);
 	if (!mapping) {
-		amdgpu_bo_unreserve(bo_va->bo);
 		r = -ENOMEM;
 		goto error;
 	}
@@ -1054,8 +1046,12 @@
 	mapping->offset = offset;
 	mapping->flags = flags;
 
+	mutex_lock(&bo_va->mutex);
 	list_add(&mapping->list, &bo_va->invalids);
+	mutex_unlock(&bo_va->mutex);
+	spin_lock(&vm->it_lock);
 	interval_tree_insert(&mapping->it, &vm->va);
+	spin_unlock(&vm->it_lock);
 	trace_amdgpu_vm_bo_map(bo_va, mapping);
 
 	/* Make sure the page tables are allocated */
@@ -1067,8 +1063,6 @@
 	if (eaddr > vm->max_pde_used)
 		vm->max_pde_used = eaddr;
 
-	amdgpu_bo_unreserve(bo_va->bo);
-
 	/* walk over the address space and allocate the page tables */
 	for (pt_idx = saddr; pt_idx <= eaddr; ++pt_idx) {
 		struct reservation_object *resv = vm->page_directory->tbo.resv;
@@ -1077,13 +1071,11 @@
 		if (vm->page_tables[pt_idx].bo)
 			continue;
 
-		ww_mutex_lock(&resv->lock, NULL);
 		r = amdgpu_bo_create(adev, AMDGPU_VM_PTE_COUNT * 8,
 				     AMDGPU_GPU_PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_VRAM,
 				     AMDGPU_GEM_CREATE_NO_CPU_ACCESS,
 				     NULL, resv, &pt);
-		ww_mutex_unlock(&resv->lock);
 		if (r)
 			goto error_free;
 
@@ -1101,7 +1093,9 @@
 
 error_free:
 	list_del(&mapping->list);
+	spin_lock(&vm->it_lock);
 	interval_tree_remove(&mapping->it, &vm->va);
+	spin_unlock(&vm->it_lock);
 	trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 	kfree(mapping);
 
@@ -1119,7 +1113,7 @@
  * Remove a mapping of the BO at the specefied addr from the VM.
  * Returns 0 for success, error for failure.
  *
- * Object has to be reserved and gets unreserved by this function!
+ * Object has to be reserved and unreserved outside!
  */
 int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
 		       struct amdgpu_bo_va *bo_va,
@@ -1130,7 +1124,7 @@
 	bool valid = true;
 
 	saddr /= AMDGPU_GPU_PAGE_SIZE;
-
+	mutex_lock(&bo_va->mutex);
 	list_for_each_entry(mapping, &bo_va->valids, list) {
 		if (mapping->it.start == saddr)
 			break;
@@ -1145,20 +1139,21 @@
 		}
 
 		if (&mapping->list == &bo_va->invalids) {
-			amdgpu_bo_unreserve(bo_va->bo);
+			mutex_unlock(&bo_va->mutex);
 			return -ENOENT;
 		}
 	}
-
+	mutex_unlock(&bo_va->mutex);
 	list_del(&mapping->list);
+	spin_lock(&vm->it_lock);
 	interval_tree_remove(&mapping->it, &vm->va);
+	spin_unlock(&vm->it_lock);
 	trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 
 	if (valid)
 		list_add(&mapping->list, &vm->freed);
 	else
 		kfree(mapping);
-	amdgpu_bo_unreserve(bo_va->bo);
 
 	return 0;
 }
@@ -1187,17 +1182,21 @@
 
 	list_for_each_entry_safe(mapping, next, &bo_va->valids, list) {
 		list_del(&mapping->list);
+		spin_lock(&vm->it_lock);
 		interval_tree_remove(&mapping->it, &vm->va);
+		spin_unlock(&vm->it_lock);
 		trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 		list_add(&mapping->list, &vm->freed);
 	}
 	list_for_each_entry_safe(mapping, next, &bo_va->invalids, list) {
 		list_del(&mapping->list);
+		spin_lock(&vm->it_lock);
 		interval_tree_remove(&mapping->it, &vm->va);
+		spin_unlock(&vm->it_lock);
 		kfree(mapping);
 	}
-
 	fence_put(bo_va->last_pt_update);
+	mutex_destroy(&bo_va->mutex);
 	kfree(bo_va);
 }
 
@@ -1241,15 +1240,13 @@
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		vm->ids[i].id = 0;
 		vm->ids[i].flushed_updates = NULL;
-		vm->ids[i].last_id_use = NULL;
 	}
-	mutex_init(&vm->mutex);
 	vm->va = RB_ROOT;
 	spin_lock_init(&vm->status_lock);
 	INIT_LIST_HEAD(&vm->invalidated);
 	INIT_LIST_HEAD(&vm->cleared);
 	INIT_LIST_HEAD(&vm->freed);
-
+	spin_lock_init(&vm->it_lock);
 	pd_size = amdgpu_vm_directory_size(adev);
 	pd_entries = amdgpu_vm_num_pdes(adev);
 
@@ -1269,8 +1266,14 @@
 			     NULL, NULL, &vm->page_directory);
 	if (r)
 		return r;
-
+	r = amdgpu_bo_reserve(vm->page_directory, false);
+	if (r) {
+		amdgpu_bo_unref(&vm->page_directory);
+		vm->page_directory = NULL;
+		return r;
+	}
 	r = amdgpu_vm_clear_bo(adev, vm->page_directory);
+	amdgpu_bo_unreserve(vm->page_directory);
 	if (r) {
 		amdgpu_bo_unref(&vm->page_directory);
 		vm->page_directory = NULL;
@@ -1313,11 +1316,27 @@
 
 	amdgpu_bo_unref(&vm->page_directory);
 	fence_put(vm->page_directory_fence);
-
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		unsigned id = vm->ids[i].id;
+
+		atomic_long_cmpxchg(&adev->vm_manager.ids[id].owner,
+				    (long)vm, 0);
 		fence_put(vm->ids[i].flushed_updates);
-		fence_put(vm->ids[i].last_id_use);
 	}
 
-	mutex_destroy(&vm->mutex);
+}
+
+/**
+ * amdgpu_vm_manager_fini - cleanup VM manager
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Cleanup the VM manager and free resources.
+ */
+void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
+{
+	unsigned i;
+
+	for (i = 0; i < AMDGPU_NUM_VM; ++i)
+		fence_put(adev->vm_manager.ids[i].active);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index a1a35a5..57a2e34 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -6569,12 +6569,12 @@
 		switch (state) {
 		case AMDGPU_IRQ_STATE_DISABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
+			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		case AMDGPU_IRQ_STATE_ENABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
+			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		default:
@@ -6586,12 +6586,12 @@
 		switch (state) {
 		case AMDGPU_IRQ_STATE_DISABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
+			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		case AMDGPU_IRQ_STATE_ENABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
+			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		default:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 6776cf7..e1dcab9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -268,7 +268,6 @@
 	mmCGTT_CP_CLK_CTRL, 0xffffffff, 0x00000100,
 	mmCGTT_CPC_CLK_CTRL, 0xffffffff, 0x00000100,
 	mmCGTT_CPF_CLK_CTRL, 0xffffffff, 0x40000100,
-	mmCGTT_DRM_CLK_CTRL0, 0xffffffff, 0x00600100,
 	mmCGTT_GDS_CLK_CTRL, 0xffffffff, 0x00000100,
 	mmCGTT_IA_CLK_CTRL, 0xffffffff, 0x06000100,
 	mmCGTT_PA_CLK_CTRL, 0xffffffff, 0x00000100,
@@ -296,10 +295,6 @@
 	mmCGTS_SM_CTRL_REG, 0xffffffff, 0x96e00200,
 	mmCP_RB_WPTR_POLL_CNTL, 0xffffffff, 0x00900100,
 	mmRLC_CGCG_CGLS_CTRL, 0xffffffff, 0x0020003c,
-	mmPCIE_INDEX, 0xffffffff, 0x0140001c,
-	mmPCIE_DATA, 0x000f0000, 0x00000000,
-	mmCGTT_DRM_CLK_CTRL0, 0xff000fff, 0x00000100,
-	mmHDP_XDP_CGTT_BLK_CTRL, 0xc0000fff, 0x00000104,
 	mmCP_MEM_SLP_CNTL, 0x00000001, 0x00000001,
 };
 
@@ -1000,7 +995,7 @@
 		adev->gfx.config.max_cu_per_sh = 16;
 		adev->gfx.config.max_sh_per_se = 1;
 		adev->gfx.config.max_backends_per_se = 4;
-		adev->gfx.config.max_texture_channel_caches = 8;
+		adev->gfx.config.max_texture_channel_caches = 16;
 		adev->gfx.config.max_gprs = 256;
 		adev->gfx.config.max_gs_threads = 32;
 		adev->gfx.config.max_hw_contexts = 8;
@@ -1613,6 +1608,296 @@
 			WREG32(mmGB_MACROTILE_MODE0 + reg_offset, gb_tile_moden);
 		}
 	case CHIP_FIJI:
+		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
+			switch (reg_offset) {
+			case 0:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 1:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 2:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 3:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 4:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 5:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 6:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 7:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 8:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_LINEAR_ALIGNED) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16));
+				break;
+			case 9:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 10:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 11:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 12:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 13:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 14:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 15:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 16:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 17:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 18:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 19:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 20:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 21:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 22:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 23:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 24:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 25:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_XTHICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 26:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_XTHICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 27:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 28:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 29:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 30:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			default:
+				gb_tile_moden = 0;
+				break;
+			}
+			adev->gfx.config.tile_mode_array[reg_offset] = gb_tile_moden;
+			WREG32(mmGB_TILE_MODE0 + reg_offset, gb_tile_moden);
+		}
+		for (reg_offset = 0; reg_offset < num_secondary_tile_mode_states; reg_offset++) {
+			switch (reg_offset) {
+			case 0:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 1:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 2:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 3:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 4:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 5:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 6:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 8:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_8) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 9:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 10:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 11:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 12:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 13:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 14:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 7:
+				/* unused idx */
+				continue;
+			default:
+				gb_tile_moden = 0;
+				break;
+			}
+			adev->gfx.config.macrotile_mode_array[reg_offset] = gb_tile_moden;
+			WREG32(mmGB_MACROTILE_MODE0 + reg_offset, gb_tile_moden);
+		}
+		break;
 	case CHIP_TONGA:
 		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
 			switch (reg_offset) {
@@ -2971,10 +3256,13 @@
 	amdgpu_ring_write(ring, mmPA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START);
 	switch (adev->asic_type) {
 	case CHIP_TONGA:
-	case CHIP_FIJI:
 		amdgpu_ring_write(ring, 0x16000012);
 		amdgpu_ring_write(ring, 0x0000002A);
 		break;
+	case CHIP_FIJI:
+		amdgpu_ring_write(ring, 0x3a00161a);
+		amdgpu_ring_write(ring, 0x0000002e);
+		break;
 	case CHIP_TOPAZ:
 	case CHIP_CARRIZO:
 		amdgpu_ring_write(ring, 0x00000002);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 85bbcdc..7427d8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -40,7 +40,7 @@
 static void gmc_v7_0_set_gart_funcs(struct amdgpu_device *adev);
 static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 
-MODULE_FIRMWARE("radeon/boniare_mc.bin");
+MODULE_FIRMWARE("radeon/bonaire_mc.bin");
 MODULE_FIRMWARE("radeon/hawaii_mc.bin");
 
 /**
@@ -501,6 +501,7 @@
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE, 1);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, EFFECTIVE_L2_QUEUE_SIZE, 7);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, CONTEXT1_IDENTITY_ACCESS_MODE, 1);
+	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_DEFAULT_PAGE_OUT_TO_SYSTEM_MEMORY, 1);
 	WREG32(mmVM_L2_CNTL, tmp);
 	tmp = REG_SET_FIELD(0, VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS, 1);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1);
@@ -960,12 +961,10 @@
 
 static int gmc_v7_0_sw_fini(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v7_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
@@ -1010,12 +1009,10 @@
 
 static int gmc_v7_0_suspend(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v7_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 1bcc4e7..cb0e50e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -629,6 +629,7 @@
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE, 1);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, EFFECTIVE_L2_QUEUE_SIZE, 7);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, CONTEXT1_IDENTITY_ACCESS_MODE, 1);
+	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_DEFAULT_PAGE_OUT_TO_SYSTEM_MEMORY, 1);
 	WREG32(mmVM_L2_CNTL, tmp);
 	tmp = RREG32(mmVM_L2_CNTL2);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS, 1);
@@ -979,12 +980,10 @@
 
 static int gmc_v8_0_sw_fini(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v8_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
@@ -1031,12 +1030,10 @@
 
 static int gmc_v8_0_suspend(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v8_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 6a52db6..370c6c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -40,6 +40,9 @@
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
 #define GRBM_GFX_INDEX__VCE_INSTANCE_MASK	0x10
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0 	0x8616
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1 	0x8617
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2 	0x8618
 
 #define VCE_V3_0_FW_SIZE	(384 * 1024)
 #define VCE_V3_0_STACK_SIZE	(64 * 1024)
@@ -130,9 +133,11 @@
 
 		/* set BUSY flag */
 		WREG32_P(mmVCE_STATUS, 1, ~1);
-
-		WREG32_P(mmVCE_VCPU_CNTL, VCE_VCPU_CNTL__CLK_EN_MASK,
-			~VCE_VCPU_CNTL__CLK_EN_MASK);
+		if (adev->asic_type >= CHIP_STONEY)
+			WREG32_P(mmVCE_VCPU_CNTL, 1, ~0x200001);
+		else
+			WREG32_P(mmVCE_VCPU_CNTL, VCE_VCPU_CNTL__CLK_EN_MASK,
+				~VCE_VCPU_CNTL__CLK_EN_MASK);
 
 		WREG32_P(mmVCE_SOFT_RESET,
 			 VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK,
@@ -391,8 +396,12 @@
 	WREG32(mmVCE_LMI_SWAP_CNTL, 0);
 	WREG32(mmVCE_LMI_SWAP_CNTL1, 0);
 	WREG32(mmVCE_LMI_VM_CTRL, 0);
-
-	WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR, (adev->vce.gpu_addr >> 8));
+	if (adev->asic_type >= CHIP_STONEY) {
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR0, (adev->vce.gpu_addr >> 8));
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR1, (adev->vce.gpu_addr >> 8));
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR2, (adev->vce.gpu_addr >> 8));
+	} else
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR, (adev->vce.gpu_addr >> 8));
 	offset = AMDGPU_VCE_FIRMWARE_OFFSET;
 	size = VCE_V3_0_FW_SIZE;
 	WREG32(mmVCE_VCPU_CACHE_OFFSET0, offset & 0x7fffffff);
@@ -576,6 +585,11 @@
 				      struct amdgpu_iv_entry *entry)
 {
 	DRM_DEBUG("IH: VCE\n");
+
+	WREG32_P(mmVCE_SYS_INT_STATUS,
+		VCE_SYS_INT_STATUS__VCE_SYS_INT_TRAP_INTERRUPT_INT_MASK,
+		~VCE_SYS_INT_STATUS__VCE_SYS_INT_TRAP_INTERRUPT_INT_MASK);
+
 	switch (entry->src_data) {
 	case 0:
 		amdgpu_fence_process(&adev->vce.ring[0]);
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
index 144f50a..c89dc77 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
@@ -16,6 +16,8 @@
 	    TP_ARGS(sched_job),
 	    TP_STRUCT__entry(
 			     __field(struct amd_sched_entity *, entity)
+			     __field(struct amd_sched_job *, sched_job)
+			     __field(struct fence *, fence)
 			     __field(const char *, name)
 			     __field(u32, job_count)
 			     __field(int, hw_job_count)
@@ -23,16 +25,32 @@
 
 	    TP_fast_assign(
 			   __entry->entity = sched_job->s_entity;
+			   __entry->sched_job = sched_job;
+			   __entry->fence = &sched_job->s_fence->base;
 			   __entry->name = sched_job->sched->name;
 			   __entry->job_count = kfifo_len(
 				   &sched_job->s_entity->job_queue) / sizeof(sched_job);
 			   __entry->hw_job_count = atomic_read(
 				   &sched_job->sched->hw_rq_count);
 			   ),
-	    TP_printk("entity=%p, ring=%s, job count:%u, hw job count:%d",
-		      __entry->entity, __entry->name, __entry->job_count,
-		      __entry->hw_job_count)
+	    TP_printk("entity=%p, sched job=%p, fence=%p, ring=%s, job count:%u, hw job count:%d",
+		      __entry->entity, __entry->sched_job, __entry->fence, __entry->name,
+		      __entry->job_count, __entry->hw_job_count)
 );
+
+TRACE_EVENT(amd_sched_process_job,
+	    TP_PROTO(struct amd_sched_fence *fence),
+	    TP_ARGS(fence),
+	    TP_STRUCT__entry(
+		    __field(struct fence *, fence)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->fence = &fence->base;
+		    ),
+	    TP_printk("fence=%p signaled", __entry->fence)
+);
+
 #endif
 
 /* This part must be outside protection */
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 89619a5..651129f 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -30,10 +30,12 @@
 #define CREATE_TRACE_POINTS
 #include "gpu_sched_trace.h"
 
-static struct amd_sched_job *
-amd_sched_entity_pop_job(struct amd_sched_entity *entity);
+static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity);
 static void amd_sched_wakeup(struct amd_gpu_scheduler *sched);
 
+struct kmem_cache *sched_fence_slab;
+atomic_t sched_fence_slab_ref = ATOMIC_INIT(0);
+
 /* Initialize a given run queue struct */
 static void amd_sched_rq_init(struct amd_sched_rq *rq)
 {
@@ -61,36 +63,36 @@
 }
 
 /**
- * Select next job from a specified run queue with round robin policy.
- * Return NULL if nothing available.
+ * Select an entity which could provide a job to run
+ *
+ * @rq		The run queue to check.
+ *
+ * Try to find a ready entity, returns NULL if none found.
  */
-static struct amd_sched_job *
-amd_sched_rq_select_job(struct amd_sched_rq *rq)
+static struct amd_sched_entity *
+amd_sched_rq_select_entity(struct amd_sched_rq *rq)
 {
 	struct amd_sched_entity *entity;
-	struct amd_sched_job *sched_job;
 
 	spin_lock(&rq->lock);
 
 	entity = rq->current_entity;
 	if (entity) {
 		list_for_each_entry_continue(entity, &rq->entities, list) {
-			sched_job = amd_sched_entity_pop_job(entity);
-			if (sched_job) {
+			if (amd_sched_entity_is_ready(entity)) {
 				rq->current_entity = entity;
 				spin_unlock(&rq->lock);
-				return sched_job;
+				return entity;
 			}
 		}
 	}
 
 	list_for_each_entry(entity, &rq->entities, list) {
 
-		sched_job = amd_sched_entity_pop_job(entity);
-		if (sched_job) {
+		if (amd_sched_entity_is_ready(entity)) {
 			rq->current_entity = entity;
 			spin_unlock(&rq->lock);
-			return sched_job;
+			return entity;
 		}
 
 		if (entity == rq->current_entity)
@@ -174,6 +176,24 @@
 }
 
 /**
+ * Check if entity is ready
+ *
+ * @entity	The pointer to a valid scheduler entity
+ *
+ * Return true if entity could provide a job.
+ */
+static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity)
+{
+	if (kfifo_is_empty(&entity->job_queue))
+		return false;
+
+	if (ACCESS_ONCE(entity->dependency))
+		return false;
+
+	return true;
+}
+
+/**
  * Destroy a context entity
  *
  * @sched       Pointer to scheduler instance
@@ -208,32 +228,53 @@
 	amd_sched_wakeup(entity->sched);
 }
 
+static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity)
+{
+	struct amd_gpu_scheduler *sched = entity->sched;
+	struct fence * fence = entity->dependency;
+	struct amd_sched_fence *s_fence;
+
+	if (fence->context == entity->fence_context) {
+		/* We can ignore fences from ourself */
+		fence_put(entity->dependency);
+		return false;
+	}
+
+	s_fence = to_amd_sched_fence(fence);
+	if (s_fence && s_fence->sched == sched) {
+		/* Fence is from the same scheduler */
+		if (test_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &fence->flags)) {
+			/* Ignore it when it is already scheduled */
+			fence_put(entity->dependency);
+			return false;
+		}
+
+		/* Wait for fence to be scheduled */
+		entity->cb.func = amd_sched_entity_wakeup;
+		list_add_tail(&entity->cb.node, &s_fence->scheduled_cb);
+		return true;
+	}
+
+	if (!fence_add_callback(entity->dependency, &entity->cb,
+				amd_sched_entity_wakeup))
+		return true;
+
+	fence_put(entity->dependency);
+	return false;
+}
+
 static struct amd_sched_job *
 amd_sched_entity_pop_job(struct amd_sched_entity *entity)
 {
 	struct amd_gpu_scheduler *sched = entity->sched;
 	struct amd_sched_job *sched_job;
 
-	if (ACCESS_ONCE(entity->dependency))
-		return NULL;
-
 	if (!kfifo_out_peek(&entity->job_queue, &sched_job, sizeof(sched_job)))
 		return NULL;
 
-	while ((entity->dependency = sched->ops->dependency(sched_job))) {
-
-		if (entity->dependency->context == entity->fence_context) {
-			/* We can ignore fences from ourself */
-			fence_put(entity->dependency);
-			continue;
-		}
-
-		if (fence_add_callback(entity->dependency, &entity->cb,
-				       amd_sched_entity_wakeup))
-			fence_put(entity->dependency);
-		else
+	while ((entity->dependency = sched->ops->dependency(sched_job)))
+		if (amd_sched_entity_add_dependency_cb(entity))
 			return NULL;
-	}
 
 	return sched_job;
 }
@@ -273,22 +314,13 @@
  *
  * Returns 0 for success, negative error code otherwise.
  */
-int amd_sched_entity_push_job(struct amd_sched_job *sched_job)
+void amd_sched_entity_push_job(struct amd_sched_job *sched_job)
 {
 	struct amd_sched_entity *entity = sched_job->s_entity;
-	struct amd_sched_fence *fence = amd_sched_fence_create(
-		entity, sched_job->owner);
-
-	if (!fence)
-		return -ENOMEM;
-
-	fence_get(&fence->base);
-	sched_job->s_fence = fence;
 
 	wait_event(entity->sched->job_scheduled,
 		   amd_sched_entity_in(sched_job));
 	trace_amd_sched_job(sched_job);
-	return 0;
 }
 
 /**
@@ -310,22 +342,22 @@
 }
 
 /**
- * Select next to run
+ * Select next entity to process
 */
-static struct amd_sched_job *
-amd_sched_select_job(struct amd_gpu_scheduler *sched)
+static struct amd_sched_entity *
+amd_sched_select_entity(struct amd_gpu_scheduler *sched)
 {
-	struct amd_sched_job *sched_job;
+	struct amd_sched_entity *entity;
 
 	if (!amd_sched_ready(sched))
 		return NULL;
 
 	/* Kernel run queue has higher priority than normal run queue*/
-	sched_job = amd_sched_rq_select_job(&sched->kernel_rq);
-	if (sched_job == NULL)
-		sched_job = amd_sched_rq_select_job(&sched->sched_rq);
+	entity = amd_sched_rq_select_entity(&sched->kernel_rq);
+	if (entity == NULL)
+		entity = amd_sched_rq_select_entity(&sched->sched_rq);
 
-	return sched_job;
+	return entity;
 }
 
 static void amd_sched_process_job(struct fence *f, struct fence_cb *cb)
@@ -343,6 +375,7 @@
 		list_del_init(&s_fence->list);
 		spin_unlock_irqrestore(&sched->fence_list_lock, flags);
 	}
+	trace_amd_sched_process_job(s_fence);
 	fence_put(&s_fence->base);
 	wake_up_interruptible(&sched->wake_up_worker);
 }
@@ -386,13 +419,16 @@
 		unsigned long flags;
 
 		wait_event_interruptible(sched->wake_up_worker,
-			kthread_should_stop() ||
-			(sched_job = amd_sched_select_job(sched)));
+			(entity = amd_sched_select_entity(sched)) ||
+			kthread_should_stop());
 
+		if (!entity)
+			continue;
+
+		sched_job = amd_sched_entity_pop_job(entity);
 		if (!sched_job)
 			continue;
 
-		entity = sched_job->s_entity;
 		s_fence = sched_job->s_fence;
 
 		if (sched->timeout != MAX_SCHEDULE_TIMEOUT) {
@@ -405,6 +441,7 @@
 
 		atomic_inc(&sched->hw_rq_count);
 		fence = sched->ops->run_job(sched_job);
+		amd_sched_fence_scheduled(s_fence);
 		if (fence) {
 			r = fence_add_callback(fence, &s_fence->cb,
 					       amd_sched_process_job);
@@ -450,6 +487,13 @@
 	init_waitqueue_head(&sched->wake_up_worker);
 	init_waitqueue_head(&sched->job_scheduled);
 	atomic_set(&sched->hw_rq_count, 0);
+	if (atomic_inc_return(&sched_fence_slab_ref) == 1) {
+		sched_fence_slab = kmem_cache_create(
+			"amd_sched_fence", sizeof(struct amd_sched_fence), 0,
+			SLAB_HWCACHE_ALIGN, NULL);
+		if (!sched_fence_slab)
+			return -ENOMEM;
+	}
 
 	/* Each scheduler will run on a seperate kernel thread */
 	sched->thread = kthread_run(amd_sched_main, sched, sched->name);
@@ -470,4 +514,6 @@
 {
 	if (sched->thread)
 		kthread_stop(sched->thread);
+	if (atomic_dec_and_test(&sched_fence_slab_ref))
+		kmem_cache_destroy(sched_fence_slab);
 }
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
index 929e9ac..a0f0ae5 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
@@ -27,9 +27,14 @@
 #include <linux/kfifo.h>
 #include <linux/fence.h>
 
+#define AMD_SCHED_FENCE_SCHEDULED_BIT	FENCE_FLAG_USER_BITS
+
 struct amd_gpu_scheduler;
 struct amd_sched_rq;
 
+extern struct kmem_cache *sched_fence_slab;
+extern atomic_t sched_fence_slab_ref;
+
 /**
  * A scheduler entity is a wrapper around a job queue or a group
  * of other entities. Entities take turns emitting jobs from their 
@@ -65,6 +70,7 @@
 struct amd_sched_fence {
 	struct fence                    base;
 	struct fence_cb                 cb;
+	struct list_head		scheduled_cb;
 	struct amd_gpu_scheduler	*sched;
 	spinlock_t			lock;
 	void                            *owner;
@@ -76,7 +82,6 @@
 	struct amd_gpu_scheduler        *sched;
 	struct amd_sched_entity         *s_entity;
 	struct amd_sched_fence          *s_fence;
-	void		                *owner;
 };
 
 extern const struct fence_ops amd_sched_fence_ops;
@@ -128,11 +133,11 @@
 			  uint32_t jobs);
 void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
 			   struct amd_sched_entity *entity);
-int amd_sched_entity_push_job(struct amd_sched_job *sched_job);
+void amd_sched_entity_push_job(struct amd_sched_job *sched_job);
 
 struct amd_sched_fence *amd_sched_fence_create(
 	struct amd_sched_entity *s_entity, void *owner);
+void amd_sched_fence_scheduled(struct amd_sched_fence *fence);
 void amd_sched_fence_signal(struct amd_sched_fence *fence);
 
-
 #endif
diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c
index d802638..87c78ee 100644
--- a/drivers/gpu/drm/amd/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c
@@ -32,9 +32,11 @@
 	struct amd_sched_fence *fence = NULL;
 	unsigned seq;
 
-	fence = kzalloc(sizeof(struct amd_sched_fence), GFP_KERNEL);
+	fence = kmem_cache_zalloc(sched_fence_slab, GFP_KERNEL);
 	if (fence == NULL)
 		return NULL;
+
+	INIT_LIST_HEAD(&fence->scheduled_cb);
 	fence->owner = owner;
 	fence->sched = s_entity->sched;
 	spin_lock_init(&fence->lock);
@@ -55,6 +57,17 @@
 		FENCE_TRACE(&fence->base, "was already signaled\n");
 }
 
+void amd_sched_fence_scheduled(struct amd_sched_fence *s_fence)
+{
+	struct fence_cb *cur, *tmp;
+
+	set_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &s_fence->base.flags);
+	list_for_each_entry_safe(cur, tmp, &s_fence->scheduled_cb, node) {
+		list_del_init(&cur->node);
+		cur->func(&s_fence->base, cur);
+	}
+}
+
 static const char *amd_sched_fence_get_driver_name(struct fence *fence)
 {
 	return "amd_sched";
@@ -71,11 +84,17 @@
 	return true;
 }
 
+static void amd_sched_fence_release(struct fence *f)
+{
+	struct amd_sched_fence *fence = to_amd_sched_fence(f);
+	kmem_cache_free(sched_fence_slab, fence);
+}
+
 const struct fence_ops amd_sched_fence_ops = {
 	.get_driver_name = amd_sched_fence_get_driver_name,
 	.get_timeline_name = amd_sched_fence_get_timeline_name,
 	.enable_signaling = amd_sched_fence_enable_signaling,
 	.signaled = NULL,
 	.wait = fence_default_wait,
-	.release = NULL,
+	.release = amd_sched_fence_release,
 };
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 7bb3845..aeee083 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1432,6 +1432,45 @@
 	return ret;
 }
 
+/**
+ * drm_atomic_update_old_fb -- Unset old_fb pointers and set plane->fb pointers.
+ *
+ * @dev: drm device to check.
+ * @plane_mask: plane mask for planes that were updated.
+ * @ret: return value, can be -EDEADLK for a retry.
+ *
+ * Before doing an update plane->old_fb is set to plane->fb,
+ * but before dropping the locks old_fb needs to be set to NULL
+ * and plane->fb updated. This is a common operation for each
+ * atomic update, so this call is split off as a helper.
+ */
+void drm_atomic_clean_old_fb(struct drm_device *dev,
+			     unsigned plane_mask,
+			     int ret)
+{
+	struct drm_plane *plane;
+
+	/* if succeeded, fixup legacy plane crtc/fb ptrs before dropping
+	 * locks (ie. while it is still safe to deref plane->state).  We
+	 * need to do this here because the driver entry points cannot
+	 * distinguish between legacy and atomic ioctls.
+	 */
+	drm_for_each_plane_mask(plane, dev, plane_mask) {
+		if (ret == 0) {
+			struct drm_framebuffer *new_fb = plane->state->fb;
+			if (new_fb)
+				drm_framebuffer_reference(new_fb);
+			plane->fb = new_fb;
+			plane->crtc = plane->state->crtc;
+
+			if (plane->old_fb)
+				drm_framebuffer_unreference(plane->old_fb);
+		}
+		plane->old_fb = NULL;
+	}
+}
+EXPORT_SYMBOL(drm_atomic_clean_old_fb);
+
 int drm_mode_atomic_ioctl(struct drm_device *dev,
 			  void *data, struct drm_file *file_priv)
 {
@@ -1446,7 +1485,7 @@
 	struct drm_plane *plane;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
-	unsigned plane_mask = 0;
+	unsigned plane_mask;
 	int ret = 0;
 	unsigned int i, j;
 
@@ -1486,6 +1525,7 @@
 	state->allow_modeset = !!(arg->flags & DRM_MODE_ATOMIC_ALLOW_MODESET);
 
 retry:
+	plane_mask = 0;
 	copied_objs = 0;
 	copied_props = 0;
 
@@ -1576,24 +1616,7 @@
 	}
 
 out:
-	/* if succeeded, fixup legacy plane crtc/fb ptrs before dropping
-	 * locks (ie. while it is still safe to deref plane->state).  We
-	 * need to do this here because the driver entry points cannot
-	 * distinguish between legacy and atomic ioctls.
-	 */
-	drm_for_each_plane_mask(plane, dev, plane_mask) {
-		if (ret == 0) {
-			struct drm_framebuffer *new_fb = plane->state->fb;
-			if (new_fb)
-				drm_framebuffer_reference(new_fb);
-			plane->fb = new_fb;
-			plane->crtc = plane->state->crtc;
-
-			if (plane->old_fb)
-				drm_framebuffer_unreference(plane->old_fb);
-		}
-		plane->old_fb = NULL;
-	}
+	drm_atomic_clean_old_fb(dev, plane_mask, ret);
 
 	if (ret && arg->flags & DRM_MODE_PAGE_FLIP_EVENT) {
 		/*
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 0c6f621..e5aec45 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -210,6 +210,14 @@
 		return -EINVAL;
 	}
 
+	if (!drm_encoder_crtc_ok(new_encoder, connector_state->crtc)) {
+		DRM_DEBUG_ATOMIC("[ENCODER:%d:%s] incompatible with [CRTC:%d]\n",
+				 new_encoder->base.id,
+				 new_encoder->name,
+				 connector_state->crtc->base.id);
+		return -EINVAL;
+	}
+
 	if (new_encoder == connector_state->best_encoder) {
 		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] keeps [ENCODER:%d:%s], now on [CRTC:%d]\n",
 				 connector->base.id,
@@ -1553,6 +1561,9 @@
 		goto fail;
 	}
 
+	if (plane_state->crtc && (plane == plane->crtc->cursor))
+		plane_state->state->legacy_cursor_update = true;
+
 	ret = __drm_atomic_helper_disable_plane(plane, plane_state);
 	if (ret != 0)
 		goto fail;
@@ -1605,9 +1616,6 @@
 	plane_state->src_h = 0;
 	plane_state->src_w = 0;
 
-	if (plane->crtc && (plane == plane->crtc->cursor))
-		plane_state->state->legacy_cursor_update = true;
-
 	return 0;
 }
 
@@ -1741,6 +1749,7 @@
 	struct drm_crtc_state *crtc_state;
 	struct drm_plane_state *primary_state;
 	struct drm_crtc *crtc = set->crtc;
+	int hdisplay, vdisplay;
 	int ret;
 
 	crtc_state = drm_atomic_get_crtc_state(state, crtc);
@@ -1783,19 +1792,21 @@
 	if (ret != 0)
 		return ret;
 
+	drm_crtc_get_hv_timing(set->mode, &hdisplay, &vdisplay);
+
 	drm_atomic_set_fb_for_plane(primary_state, set->fb);
 	primary_state->crtc_x = 0;
 	primary_state->crtc_y = 0;
-	primary_state->crtc_h = set->mode->vdisplay;
-	primary_state->crtc_w = set->mode->hdisplay;
+	primary_state->crtc_h = vdisplay;
+	primary_state->crtc_w = hdisplay;
 	primary_state->src_x = set->x << 16;
 	primary_state->src_y = set->y << 16;
 	if (primary_state->rotation & (BIT(DRM_ROTATE_90) | BIT(DRM_ROTATE_270))) {
-		primary_state->src_h = set->mode->hdisplay << 16;
-		primary_state->src_w = set->mode->vdisplay << 16;
+		primary_state->src_h = hdisplay << 16;
+		primary_state->src_w = vdisplay << 16;
 	} else {
-		primary_state->src_h = set->mode->vdisplay << 16;
-		primary_state->src_w = set->mode->hdisplay << 16;
+		primary_state->src_h = vdisplay << 16;
+		primary_state->src_w = hdisplay << 16;
 	}
 
 commit:
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index e673c13..69cbab5 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -342,6 +342,7 @@
 	struct drm_plane *plane;
 	struct drm_atomic_state *state;
 	int i, ret;
+	unsigned plane_mask;
 
 	state = drm_atomic_state_alloc(dev);
 	if (!state)
@@ -349,11 +350,10 @@
 
 	state->acquire_ctx = dev->mode_config.acquire_ctx;
 retry:
+	plane_mask = 0;
 	drm_for_each_plane(plane, dev) {
 		struct drm_plane_state *plane_state;
 
-		plane->old_fb = plane->fb;
-
 		plane_state = drm_atomic_get_plane_state(state, plane);
 		if (IS_ERR(plane_state)) {
 			ret = PTR_ERR(plane_state);
@@ -362,6 +362,9 @@
 
 		plane_state->rotation = BIT(DRM_ROTATE_0);
 
+		plane->old_fb = plane->fb;
+		plane_mask |= 1 << drm_plane_index(plane);
+
 		/* disable non-primary: */
 		if (plane->type == DRM_PLANE_TYPE_PRIMARY)
 			continue;
@@ -382,19 +385,7 @@
 	ret = drm_atomic_commit(state);
 
 fail:
-	drm_for_each_plane(plane, dev) {
-		if (ret == 0) {
-			struct drm_framebuffer *new_fb = plane->state->fb;
-			if (new_fb)
-				drm_framebuffer_reference(new_fb);
-			plane->fb = new_fb;
-			plane->crtc = plane->state->crtc;
-
-			if (plane->old_fb)
-				drm_framebuffer_unreference(plane->old_fb);
-		}
-		plane->old_fb = NULL;
-	}
+	drm_atomic_clean_old_fb(dev, plane_mask, ret);
 
 	if (ret == -EDEADLK)
 		goto backoff;
@@ -1236,7 +1227,9 @@
 	struct drm_fb_helper *fb_helper = info->par;
 	struct drm_device *dev = fb_helper->dev;
 	struct drm_atomic_state *state;
+	struct drm_plane *plane;
 	int i, ret;
+	unsigned plane_mask;
 
 	state = drm_atomic_state_alloc(dev);
 	if (!state)
@@ -1244,19 +1237,22 @@
 
 	state->acquire_ctx = dev->mode_config.acquire_ctx;
 retry:
+	plane_mask = 0;
 	for(i = 0; i < fb_helper->crtc_count; i++) {
 		struct drm_mode_set *mode_set;
 
 		mode_set = &fb_helper->crtc_info[i].mode_set;
 
-		mode_set->crtc->primary->old_fb = mode_set->crtc->primary->fb;
-
 		mode_set->x = var->xoffset;
 		mode_set->y = var->yoffset;
 
 		ret = __drm_atomic_helper_set_config(mode_set, state);
 		if (ret != 0)
 			goto fail;
+
+		plane = mode_set->crtc->primary;
+		plane_mask |= drm_plane_index(plane);
+		plane->old_fb = plane->fb;
 	}
 
 	ret = drm_atomic_commit(state);
@@ -1268,26 +1264,7 @@
 
 
 fail:
-	for(i = 0; i < fb_helper->crtc_count; i++) {
-		struct drm_mode_set *mode_set;
-		struct drm_plane *plane;
-
-		mode_set = &fb_helper->crtc_info[i].mode_set;
-		plane = mode_set->crtc->primary;
-
-		if (ret == 0) {
-			struct drm_framebuffer *new_fb = plane->state->fb;
-
-			if (new_fb)
-				drm_framebuffer_reference(new_fb);
-			plane->fb = new_fb;
-			plane->crtc = plane->state->crtc;
-
-			if (plane->old_fb)
-				drm_framebuffer_unreference(plane->old_fb);
-		}
-		plane->old_fb = NULL;
-	}
+	drm_atomic_clean_old_fb(dev, plane_mask, ret);
 
 	if (ret == -EDEADLK)
 		goto backoff;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8afda45..95bb27d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -351,6 +351,8 @@
 	/* hsw/bdw */
 	DPLL_ID_WRPLL1 = 0,
 	DPLL_ID_WRPLL2 = 1,
+	DPLL_ID_SPLL = 2,
+
 	/* skl */
 	DPLL_ID_SKL_DPLL1 = 0,
 	DPLL_ID_SKL_DPLL2 = 1,
@@ -367,6 +369,7 @@
 
 	/* hsw, bdw */
 	uint32_t wrpll;
+	uint32_t spll;
 
 	/* skl */
 	/*
@@ -2648,6 +2651,7 @@
 	int enable_cmd_parser;
 	/* leave bools at the end to not create holes */
 	bool enable_hangcheck;
+	bool fastboot;
 	bool prefault_disable;
 	bool load_detect_test;
 	bool reset;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5cf4a19..91bb1fc 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3809,6 +3809,7 @@
 int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_caching *args = data;
 	struct drm_i915_gem_object *obj;
 	enum i915_cache_level level;
@@ -3837,9 +3838,11 @@
 		return -EINVAL;
 	}
 
+	intel_runtime_pm_get(dev_priv);
+
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
-		return ret;
+		goto rpm_put;
 
 	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
 	if (&obj->base == NULL) {
@@ -3852,6 +3855,9 @@
 	drm_gem_object_unreference(&obj->base);
 unlock:
 	mutex_unlock(&dev->struct_mutex);
+rpm_put:
+	intel_runtime_pm_put(dev_priv);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 96bb238..4be13a5 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -40,6 +40,7 @@
 	.preliminary_hw_support = IS_ENABLED(CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT),
 	.disable_power_well = -1,
 	.enable_ips = 1,
+	.fastboot = 0,
 	.prefault_disable = 0,
 	.load_detect_test = 0,
 	.reset = true,
@@ -133,6 +134,10 @@
 module_param_named_unsafe(enable_ips, i915.enable_ips, int, 0600);
 MODULE_PARM_DESC(enable_ips, "Enable IPS (default: true)");
 
+module_param_named(fastboot, i915.fastboot, bool, 0600);
+MODULE_PARM_DESC(fastboot,
+	"Try to skip unnecessary mode sets at boot time (default: false)");
+
 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). "
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index b84aaa0..6a2c76e 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -138,18 +138,6 @@
 	pipe_config->base.adjusted_mode.flags |= intel_crt_get_flags(encoder);
 }
 
-static void hsw_crt_pre_enable(struct intel_encoder *encoder)
-{
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	WARN(I915_READ(SPLL_CTL) & SPLL_PLL_ENABLE, "SPLL already enabled\n");
-	I915_WRITE(SPLL_CTL,
-		   SPLL_PLL_ENABLE | SPLL_PLL_FREQ_1350MHz | SPLL_PLL_SSC);
-	POSTING_READ(SPLL_CTL);
-	udelay(20);
-}
-
 /* Note: The caller is required to filter out dpms modes not supported by the
  * platform. */
 static void intel_crt_set_dpms(struct intel_encoder *encoder, int mode)
@@ -216,19 +204,6 @@
 	intel_disable_crt(encoder);
 }
 
-static void hsw_crt_post_disable(struct intel_encoder *encoder)
-{
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t val;
-
-	DRM_DEBUG_KMS("Disabling SPLL\n");
-	val = I915_READ(SPLL_CTL);
-	WARN_ON(!(val & SPLL_PLL_ENABLE));
-	I915_WRITE(SPLL_CTL, val & ~SPLL_PLL_ENABLE);
-	POSTING_READ(SPLL_CTL);
-}
-
 static void intel_enable_crt(struct intel_encoder *encoder)
 {
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
@@ -280,6 +255,10 @@
 	if (HAS_DDI(dev)) {
 		pipe_config->ddi_pll_sel = PORT_CLK_SEL_SPLL;
 		pipe_config->port_clock = 135000 * 2;
+
+		pipe_config->dpll_hw_state.wrpll = 0;
+		pipe_config->dpll_hw_state.spll =
+			SPLL_PLL_ENABLE | SPLL_PLL_FREQ_1350MHz | SPLL_PLL_SSC;
 	}
 
 	return true;
@@ -860,8 +839,6 @@
 	if (HAS_DDI(dev)) {
 		crt->base.get_config = hsw_crt_get_config;
 		crt->base.get_hw_state = intel_ddi_get_hw_state;
-		crt->base.pre_enable = hsw_crt_pre_enable;
-		crt->base.post_disable = hsw_crt_post_disable;
 	} else {
 		crt->base.get_config = intel_crt_get_config;
 		crt->base.get_hw_state = intel_crt_get_hw_state;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index b25e99a..a6752a6 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1286,6 +1286,18 @@
 		}
 
 		crtc_state->ddi_pll_sel = PORT_CLK_SEL_WRPLL(pll->id);
+	} else if (crtc_state->ddi_pll_sel == PORT_CLK_SEL_SPLL) {
+		struct drm_atomic_state *state = crtc_state->base.state;
+		struct intel_shared_dpll_config *spll =
+			&intel_atomic_get_shared_dpll_state(state)[DPLL_ID_SPLL];
+
+		if (spll->crtc_mask &&
+		    WARN_ON(spll->hw_state.spll != crtc_state->dpll_hw_state.spll))
+			return false;
+
+		crtc_state->shared_dpll = DPLL_ID_SPLL;
+		spll->hw_state.spll = crtc_state->dpll_hw_state.spll;
+		spll->crtc_mask |= 1 << intel_crtc->pipe;
 	}
 
 	return true;
@@ -2437,7 +2449,7 @@
 	}
 }
 
-static void hsw_ddi_pll_enable(struct drm_i915_private *dev_priv,
+static void hsw_ddi_wrpll_enable(struct drm_i915_private *dev_priv,
 			       struct intel_shared_dpll *pll)
 {
 	I915_WRITE(WRPLL_CTL(pll->id), pll->config.hw_state.wrpll);
@@ -2445,9 +2457,17 @@
 	udelay(20);
 }
 
-static void hsw_ddi_pll_disable(struct drm_i915_private *dev_priv,
+static void hsw_ddi_spll_enable(struct drm_i915_private *dev_priv,
 				struct intel_shared_dpll *pll)
 {
+	I915_WRITE(SPLL_CTL, pll->config.hw_state.spll);
+	POSTING_READ(SPLL_CTL);
+	udelay(20);
+}
+
+static void hsw_ddi_wrpll_disable(struct drm_i915_private *dev_priv,
+				  struct intel_shared_dpll *pll)
+{
 	uint32_t val;
 
 	val = I915_READ(WRPLL_CTL(pll->id));
@@ -2455,9 +2475,19 @@
 	POSTING_READ(WRPLL_CTL(pll->id));
 }
 
-static bool hsw_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv,
-				     struct intel_shared_dpll *pll,
-				     struct intel_dpll_hw_state *hw_state)
+static void hsw_ddi_spll_disable(struct drm_i915_private *dev_priv,
+				 struct intel_shared_dpll *pll)
+{
+	uint32_t val;
+
+	val = I915_READ(SPLL_CTL);
+	I915_WRITE(SPLL_CTL, val & ~SPLL_PLL_ENABLE);
+	POSTING_READ(SPLL_CTL);
+}
+
+static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv,
+				       struct intel_shared_dpll *pll,
+				       struct intel_dpll_hw_state *hw_state)
 {
 	uint32_t val;
 
@@ -2470,25 +2500,50 @@
 	return val & WRPLL_PLL_ENABLE;
 }
 
+static bool hsw_ddi_spll_get_hw_state(struct drm_i915_private *dev_priv,
+				      struct intel_shared_dpll *pll,
+				      struct intel_dpll_hw_state *hw_state)
+{
+	uint32_t val;
+
+	if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS))
+		return false;
+
+	val = I915_READ(SPLL_CTL);
+	hw_state->spll = val;
+
+	return val & SPLL_PLL_ENABLE;
+}
+
+
 static const char * const hsw_ddi_pll_names[] = {
 	"WRPLL 1",
 	"WRPLL 2",
+	"SPLL"
 };
 
 static void hsw_shared_dplls_init(struct drm_i915_private *dev_priv)
 {
 	int i;
 
-	dev_priv->num_shared_dpll = 2;
+	dev_priv->num_shared_dpll = 3;
 
-	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
+	for (i = 0; i < 2; i++) {
 		dev_priv->shared_dplls[i].id = i;
 		dev_priv->shared_dplls[i].name = hsw_ddi_pll_names[i];
-		dev_priv->shared_dplls[i].disable = hsw_ddi_pll_disable;
-		dev_priv->shared_dplls[i].enable = hsw_ddi_pll_enable;
+		dev_priv->shared_dplls[i].disable = hsw_ddi_wrpll_disable;
+		dev_priv->shared_dplls[i].enable = hsw_ddi_wrpll_enable;
 		dev_priv->shared_dplls[i].get_hw_state =
-			hsw_ddi_pll_get_hw_state;
+			hsw_ddi_wrpll_get_hw_state;
 	}
+
+	/* SPLL is special, but needs to be initialized anyway.. */
+	dev_priv->shared_dplls[i].id = i;
+	dev_priv->shared_dplls[i].name = hsw_ddi_pll_names[i];
+	dev_priv->shared_dplls[i].disable = hsw_ddi_spll_disable;
+	dev_priv->shared_dplls[i].enable = hsw_ddi_spll_enable;
+	dev_priv->shared_dplls[i].get_hw_state = hsw_ddi_spll_get_hw_state;
+
 }
 
 static const char * const skl_ddi_pll_names[] = {
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index f62ffc0..71860f8 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2646,11 +2646,13 @@
 	return;
 
 valid_fb:
-	plane_state->src_x = plane_state->src_y = 0;
+	plane_state->src_x = 0;
+	plane_state->src_y = 0;
 	plane_state->src_w = fb->width << 16;
 	plane_state->src_h = fb->height << 16;
 
-	plane_state->crtc_x = plane_state->src_y = 0;
+	plane_state->crtc_x = 0;
+	plane_state->crtc_y = 0;
 	plane_state->crtc_w = fb->width;
 	plane_state->crtc_h = fb->height;
 
@@ -4237,6 +4239,7 @@
 	struct intel_shared_dpll *pll;
 	struct intel_shared_dpll_config *shared_dpll;
 	enum intel_dpll_id i;
+	int max = dev_priv->num_shared_dpll;
 
 	shared_dpll = intel_atomic_get_shared_dpll_state(crtc_state->base.state);
 
@@ -4271,9 +4274,11 @@
 		WARN_ON(shared_dpll[i].crtc_mask);
 
 		goto found;
-	}
+	} else if (INTEL_INFO(dev_priv)->gen < 9 && HAS_DDI(dev_priv))
+		/* Do not consider SPLL */
+		max = 2;
 
-	for (i = 0; i < dev_priv->num_shared_dpll; i++) {
+	for (i = 0; i < max; i++) {
 		pll = &dev_priv->shared_dplls[i];
 
 		/* Only want to check enabled timings first */
@@ -9723,6 +9728,8 @@
 	case PORT_CLK_SEL_WRPLL2:
 		pipe_config->shared_dpll = DPLL_ID_WRPLL2;
 		break;
+	case PORT_CLK_SEL_SPLL:
+		pipe_config->shared_dpll = DPLL_ID_SPLL;
 	}
 }
 
@@ -12003,9 +12010,10 @@
 			      pipe_config->dpll_hw_state.cfgcr1,
 			      pipe_config->dpll_hw_state.cfgcr2);
 	} else if (HAS_DDI(dev)) {
-		DRM_DEBUG_KMS("ddi_pll_sel: %u; dpll_hw_state: wrpll: 0x%x\n",
+		DRM_DEBUG_KMS("ddi_pll_sel: %u; dpll_hw_state: wrpll: 0x%x spll: 0x%x\n",
 			      pipe_config->ddi_pll_sel,
-			      pipe_config->dpll_hw_state.wrpll);
+			      pipe_config->dpll_hw_state.wrpll,
+			      pipe_config->dpll_hw_state.spll);
 	} else {
 		DRM_DEBUG_KMS("dpll_hw_state: dpll: 0x%x, dpll_md: 0x%x, "
 			      "fp0: 0x%x, fp1: 0x%x\n",
@@ -12528,6 +12536,7 @@
 	PIPE_CONF_CHECK_X(dpll_hw_state.fp0);
 	PIPE_CONF_CHECK_X(dpll_hw_state.fp1);
 	PIPE_CONF_CHECK_X(dpll_hw_state.wrpll);
+	PIPE_CONF_CHECK_X(dpll_hw_state.spll);
 	PIPE_CONF_CHECK_X(dpll_hw_state.ctrl1);
 	PIPE_CONF_CHECK_X(dpll_hw_state.cfgcr1);
 	PIPE_CONF_CHECK_X(dpll_hw_state.cfgcr2);
@@ -13032,6 +13041,9 @@
 		struct intel_crtc_state *pipe_config =
 			to_intel_crtc_state(crtc_state);
 
+		memset(&to_intel_crtc(crtc)->atomic, 0,
+		       sizeof(struct intel_crtc_atomic_commit));
+
 		/* Catch I915_MODE_FLAG_INHERITED */
 		if (crtc_state->mode.private_flags != crtc->state->mode.private_flags)
 			crtc_state->mode_changed = true;
@@ -13056,7 +13068,8 @@
 		if (ret)
 			return ret;
 
-		if (intel_pipe_config_compare(state->dev,
+		if (i915.fastboot &&
+		    intel_pipe_config_compare(state->dev,
 					to_intel_crtc_state(crtc->state),
 					pipe_config, true)) {
 			crtc_state->mode_changed = false;
@@ -14364,16 +14377,17 @@
 static struct drm_framebuffer *
 intel_user_framebuffer_create(struct drm_device *dev,
 			      struct drm_file *filp,
-			      struct drm_mode_fb_cmd2 *mode_cmd)
+			      struct drm_mode_fb_cmd2 *user_mode_cmd)
 {
 	struct drm_i915_gem_object *obj;
+	struct drm_mode_fb_cmd2 mode_cmd = *user_mode_cmd;
 
 	obj = to_intel_bo(drm_gem_object_lookup(dev, filp,
-						mode_cmd->handles[0]));
+						mode_cmd.handles[0]));
 	if (&obj->base == NULL)
 		return ERR_PTR(-ENOENT);
 
-	return intel_framebuffer_create(dev, mode_cmd, obj);
+	return intel_framebuffer_create(dev, &mode_cmd, obj);
 }
 
 #ifndef CONFIG_DRM_FBDEV_EMULATION
@@ -14705,6 +14719,9 @@
 	/* Apple Macbook 2,1 (Core 2 T7400) */
 	{ 0x27a2, 0x8086, 0x7270, quirk_backlight_present },
 
+	/* Apple Macbook 4,1 */
+	{ 0x2a02, 0x106b, 0x00a1, quirk_backlight_present },
+
 	/* Toshiba CB35 Chromebook (Celeron 2955U) */
 	{ 0x0a06, 0x1179, 0x0a88, quirk_backlight_present },
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d52a15d..071a76b 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4449,7 +4449,7 @@
 	POSTING_READ(GEN6_RPNSWREQ);
 
 	dev_priv->rps.cur_freq = val;
-	trace_intel_gpu_freq_change(val * 50);
+	trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val));
 }
 
 static void valleyview_set_rps(struct drm_device *dev, u8 val)
@@ -7255,7 +7255,8 @@
 int intel_gpu_freq(struct drm_i915_private *dev_priv, int val)
 {
 	if (IS_GEN9(dev_priv->dev))
-		return (val * GT_FREQUENCY_MULTIPLIER) / GEN9_FREQ_SCALER;
+		return DIV_ROUND_CLOSEST(val * GT_FREQUENCY_MULTIPLIER,
+					 GEN9_FREQ_SCALER);
 	else if (IS_CHERRYVIEW(dev_priv->dev))
 		return chv_gpu_freq(dev_priv, val);
 	else if (IS_VALLEYVIEW(dev_priv->dev))
@@ -7267,13 +7268,14 @@
 int intel_freq_opcode(struct drm_i915_private *dev_priv, int val)
 {
 	if (IS_GEN9(dev_priv->dev))
-		return (val * GEN9_FREQ_SCALER) / GT_FREQUENCY_MULTIPLIER;
+		return DIV_ROUND_CLOSEST(val * GEN9_FREQ_SCALER,
+					 GT_FREQUENCY_MULTIPLIER);
 	else if (IS_CHERRYVIEW(dev_priv->dev))
 		return chv_freq_opcode(dev_priv, val);
 	else if (IS_VALLEYVIEW(dev_priv->dev))
 		return byt_freq_opcode(dev_priv, val);
 	else
-		return val / GT_FREQUENCY_MULTIPLIER;
+		return DIV_ROUND_CLOSEST(val, GT_FREQUENCY_MULTIPLIER);
 }
 
 struct request_boost {
diff --git a/drivers/gpu/drm/mgag200/mgag200_cursor.c b/drivers/gpu/drm/mgag200/mgag200_cursor.c
index 4f2068f..a7bf6a9 100644
--- a/drivers/gpu/drm/mgag200/mgag200_cursor.c
+++ b/drivers/gpu/drm/mgag200/mgag200_cursor.c
@@ -70,6 +70,11 @@
 	BUG_ON(pixels_2 != pixels_current && pixels_2 != pixels_prev);
 	BUG_ON(pixels_current == pixels_prev);
 
+	if (!handle || !file_priv) {
+		mga_hide_cursor(mdev);
+		return 0;
+	}
+
 	obj = drm_gem_object_lookup(dev, file_priv, handle);
 	if (!obj)
 		return -ENOENT;
@@ -88,12 +93,6 @@
 		goto out_unreserve1;
 	}
 
-	if (!handle) {
-		mga_hide_cursor(mdev);
-		ret = 0;
-		goto out1;
-	}
-
 	/* Move cursor buffers into VRAM if they aren't already */
 	if (!pixels_1->pin_count) {
 		ret = mgag200_bo_pin(pixels_1, TTM_PL_FLAG_VRAM,
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h
index 28bc202..40f845e 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h
@@ -7,6 +7,7 @@
 	const struct nvkm_instmem_func *func;
 	struct nvkm_subdev subdev;
 
+	spinlock_t lock;
 	struct list_head list;
 	u32 reserved;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 8b8332e..d5e6938 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -367,6 +367,7 @@
 		return -ENODEV;
 	}
 	obj = (union acpi_object *)buffer.pointer;
+	len = min(len, (int)obj->buffer.length);
 	memcpy(bios+offset, obj->buffer.pointer, len);
 	kfree(buffer.pointer);
 	return len;
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.h b/drivers/gpu/drm/nouveau/nouveau_drm.h
index 3050042e..a02813e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.h
@@ -39,6 +39,7 @@
 
 #include <nvif/client.h>
 #include <nvif/device.h>
+#include <nvif/ioctl.h>
 
 #include <drmP.h>
 
@@ -65,9 +66,10 @@
 };
 
 enum nouveau_drm_object_route {
-	NVDRM_OBJECT_NVIF = 0,
+	NVDRM_OBJECT_NVIF = NVIF_IOCTL_V0_OWNER_NVIF,
 	NVDRM_OBJECT_USIF,
 	NVDRM_OBJECT_ABI16,
+	NVDRM_OBJECT_ANY = NVIF_IOCTL_V0_OWNER_ANY,
 };
 
 enum nouveau_drm_notify_route {
diff --git a/drivers/gpu/drm/nouveau/nouveau_usif.c b/drivers/gpu/drm/nouveau/nouveau_usif.c
index 89dc4ce..6ae1b34 100644
--- a/drivers/gpu/drm/nouveau/nouveau_usif.c
+++ b/drivers/gpu/drm/nouveau/nouveau_usif.c
@@ -313,7 +313,10 @@
 	if (nvif_unpack(argv->v0, 0, 0, true)) {
 		/* block access to objects not created via this interface */
 		owner = argv->v0.owner;
-		argv->v0.owner = NVDRM_OBJECT_USIF;
+		if (argv->v0.object == 0ULL)
+			argv->v0.owner = NVDRM_OBJECT_ANY; /* except client */
+		else
+			argv->v0.owner = NVDRM_OBJECT_USIF;
 	} else
 		goto done;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
index e3c783d..caf22b5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
@@ -279,6 +279,12 @@
 };
 
 static const struct nvkm_device_pci_vendor
+nvkm_device_pci_10de_0fe4[] = {
+	{ 0x144d, 0xc740, NULL, { .War00C800_0 = true } },
+	{}
+};
+
+static const struct nvkm_device_pci_vendor
 nvkm_device_pci_10de_104b[] = {
 	{ 0x1043, 0x844c, "GeForce GT 625" },
 	{ 0x1043, 0x846b, "GeForce GT 625" },
@@ -689,6 +695,12 @@
 };
 
 static const struct nvkm_device_pci_vendor
+nvkm_device_pci_10de_11e0[] = {
+	{ 0x1558, 0x5106, NULL, { .War00C800_0 = true } },
+	{}
+};
+
+static const struct nvkm_device_pci_vendor
 nvkm_device_pci_10de_11e3[] = {
 	{ 0x17aa, 0x3683, "GeForce GTX 760A" },
 	{}
@@ -1370,7 +1382,7 @@
 	{ 0x0fe1, "GeForce GT 730M" },
 	{ 0x0fe2, "GeForce GT 745M" },
 	{ 0x0fe3, "GeForce GT 745M", nvkm_device_pci_10de_0fe3 },
-	{ 0x0fe4, "GeForce GT 750M" },
+	{ 0x0fe4, "GeForce GT 750M", nvkm_device_pci_10de_0fe4 },
 	{ 0x0fe9, "GeForce GT 750M" },
 	{ 0x0fea, "GeForce GT 755M" },
 	{ 0x0fec, "GeForce 710A" },
@@ -1485,7 +1497,7 @@
 	{ 0x11c6, "GeForce GTX 650 Ti" },
 	{ 0x11c8, "GeForce GTX 650" },
 	{ 0x11cb, "GeForce GT 740" },
-	{ 0x11e0, "GeForce GTX 770M" },
+	{ 0x11e0, "GeForce GTX 770M", nvkm_device_pci_10de_11e0 },
 	{ 0x11e1, "GeForce GTX 765M" },
 	{ 0x11e2, "GeForce GTX 765M" },
 	{ 0x11e3, "GeForce GTX 760M", nvkm_device_pci_10de_11e3 },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
index b5b8759..74de7a9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
@@ -207,6 +207,8 @@
 			const u32 b =  beta * gr->ppc_tpc_nr[gpc][ppc];
 			const u32 t = timeslice_mode;
 			const u32 o = PPC_UNIT(gpc, ppc, 0);
+			if (!(gr->ppc_mask[gpc] & (1 << ppc)))
+				continue;
 			mmio_skip(info, o + 0xc0, (t << 28) | (b << 16) | ++bo);
 			mmio_wr32(info, o + 0xc0, (t << 28) | (b << 16) | --bo);
 			bo += grctx->attrib_nr_max * gr->ppc_tpc_nr[gpc][ppc];
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc
index 194afe9..7dacb3c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc
@@ -52,10 +52,12 @@
 #endif
 
 #ifdef INCLUDE_CODE
+#define gpc_addr(reg,addr)                                                    /*
+*/	imm32(reg,addr)                                                       /*
+*/	or reg NV_PGRAPH_GPCX_GPCCS_MMIO_CTRL_BASE_ENABLE
 #define gpc_wr32(addr,reg)                                                    /*
+*/	gpc_addr($r14,addr)                                                   /*
 */	mov b32 $r15 reg                                                      /*
-*/	imm32($r14, addr)                                                     /*
-*/	or $r14 NV_PGRAPH_GPCX_GPCCS_MMIO_CTRL_BASE_ENABLE                    /*
 */	call(nv_wr32)
 
 // reports an exception to the host
@@ -161,7 +163,7 @@
 
 #if NV_PGRAPH_GPCX_UNK__SIZE > 0
 	// figure out which, and how many, UNKs are actually present
-	imm32($r14, 0x500c30)
+	gpc_addr($r14, 0x500c30)
 	clear b32 $r2
 	clear b32 $r3
 	clear b32 $r4
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h
index 64d07df..bb820ff 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h
@@ -314,7 +314,7 @@
 	0x03f01200,
 	0x0002d000,
 	0x17f104bd,
-	0x10fe0542,
+	0x10fe0545,
 	0x0007f100,
 	0x0003f007,
 	0xbd0000d0,
@@ -338,184 +338,184 @@
 	0x02d00103,
 	0xf104bd00,
 	0xf00c30e7,
-	0x24bd50e3,
-	0x44bd34bd,
-/* 0x0430: init_unk_loop */
-	0xb06821f4,
-	0x0bf400f6,
-	0x01f7f00f,
-	0xfd04f2bb,
-	0x30b6054f,
-/* 0x0445: init_unk_next */
-	0x0120b601,
-	0xb004e0b6,
-	0x1bf40126,
-/* 0x0451: init_unk_done */
-	0x070380e2,
-	0xf1080480,
-	0xf0010027,
-	0x22cf0223,
-	0x9534bd00,
-	0x07f10825,
-	0x03f0c000,
-	0x0005d001,
-	0x07f104bd,
-	0x03f0c100,
-	0x0005d001,
-	0x0e9804bd,
-	0x010f9800,
-	0x015021f5,
-	0xbb002fbb,
-	0x0e98003f,
-	0x020f9801,
-	0x015021f5,
-	0xfd050e98,
-	0x2ebb00ef,
-	0x003ebb00,
-	0x98020e98,
-	0x21f5030f,
-	0x0e980150,
-	0x00effd07,
-	0xbb002ebb,
-	0x35b6003e,
-	0x0007f102,
-	0x0103f0d3,
-	0xbd0003d0,
-	0x0825b604,
-	0xb60635b6,
-	0x30b60120,
-	0x0824b601,
-	0xb90834b6,
-	0x21f5022f,
-	0x2fbb02d3,
-	0x003fbb00,
-	0x010007f1,
-	0xd00203f0,
+	0xe5f050e3,
+	0xbd24bd01,
+/* 0x0433: init_unk_loop */
+	0xf444bd34,
+	0xf6b06821,
+	0x0f0bf400,
+	0xbb01f7f0,
+	0x4ffd04f2,
+	0x0130b605,
+/* 0x0448: init_unk_next */
+	0xb60120b6,
+	0x26b004e0,
+	0xe21bf401,
+/* 0x0454: init_unk_done */
+	0x80070380,
+	0x27f10804,
+	0x23f00100,
+	0x0022cf02,
+	0x259534bd,
+	0x0007f108,
+	0x0103f0c0,
+	0xbd0005d0,
+	0x0007f104,
+	0x0103f0c1,
+	0xbd0005d0,
+	0x000e9804,
+	0xf5010f98,
+	0xbb015021,
+	0x3fbb002f,
+	0x010e9800,
+	0xf5020f98,
+	0x98015021,
+	0xeffd050e,
+	0x002ebb00,
+	0x98003ebb,
+	0x0f98020e,
+	0x5021f503,
+	0x070e9801,
+	0xbb00effd,
+	0x3ebb002e,
+	0x0235b600,
+	0xd30007f1,
+	0xd00103f0,
 	0x04bd0003,
-	0x29f024bd,
-	0x0007f11f,
-	0x0203f008,
-	0xbd0002d0,
-/* 0x0505: main */
-	0x0031f404,
-	0xf00028f4,
-	0x21f424d7,
-	0xf401f439,
-	0xf404e4b0,
-	0x81fe1e18,
-	0x0627f001,
-	0x12fd20bd,
-	0x01e4b604,
-	0xfe051efd,
-	0x21f50018,
-	0x0ef405fa,
-/* 0x0535: main_not_ctx_xfer */
-	0x10ef94d3,
-	0xf501f5f0,
-	0xf4037e21,
-/* 0x0542: ih */
-	0x80f9c60e,
-	0xf90188fe,
-	0xf990f980,
-	0xf9b0f9a0,
-	0xf9e0f9d0,
-	0xf104bdf0,
-	0xf00200a7,
-	0xaacf00a3,
-	0x04abc400,
-	0xf02c0bf4,
-	0xe7f124d7,
-	0xe3f01a00,
-	0x00eecf00,
-	0x1900f7f1,
-	0xcf00f3f0,
-	0x21f400ff,
-	0x01e7f004,
-	0x1d0007f1,
-	0xd00003f0,
-	0x04bd000e,
-/* 0x0590: ih_no_fifo */
-	0x010007f1,
-	0xd00003f0,
-	0x04bd000a,
-	0xe0fcf0fc,
-	0xb0fcd0fc,
-	0x90fca0fc,
-	0x88fe80fc,
-	0xf480fc00,
-	0x01f80032,
-/* 0x05b4: hub_barrier_done */
-	0x9801f7f0,
-	0xfebb040e,
-	0x02ffb904,
-	0x9418e7f1,
-	0xf440e3f0,
-	0x00f89d21,
-/* 0x05cc: ctx_redswitch */
-	0xf120f7f0,
+	0xb60825b6,
+	0x20b60635,
+	0x0130b601,
+	0xb60824b6,
+	0x2fb90834,
+	0xd321f502,
+	0x002fbb02,
+	0xf1003fbb,
+	0xf0010007,
+	0x03d00203,
+	0xbd04bd00,
+	0x1f29f024,
+	0x080007f1,
+	0xd00203f0,
+	0x04bd0002,
+/* 0x0508: main */
+	0xf40031f4,
+	0xd7f00028,
+	0x3921f424,
+	0xb0f401f4,
+	0x18f404e4,
+	0x0181fe1e,
+	0xbd0627f0,
+	0x0412fd20,
+	0xfd01e4b6,
+	0x18fe051e,
+	0xfd21f500,
+	0xd30ef405,
+/* 0x0538: main_not_ctx_xfer */
+	0xf010ef94,
+	0x21f501f5,
+	0x0ef4037e,
+/* 0x0545: ih */
+	0xfe80f9c6,
+	0x80f90188,
+	0xa0f990f9,
+	0xd0f9b0f9,
+	0xf0f9e0f9,
+	0xa7f104bd,
+	0xa3f00200,
+	0x00aacf00,
+	0xf404abc4,
+	0xd7f02c0b,
+	0x00e7f124,
+	0x00e3f01a,
+	0xf100eecf,
+	0xf01900f7,
+	0xffcf00f3,
+	0x0421f400,
+	0xf101e7f0,
+	0xf01d0007,
+	0x0ed00003,
+/* 0x0593: ih_no_fifo */
+	0xf104bd00,
+	0xf0010007,
+	0x0ad00003,
+	0xfc04bd00,
+	0xfce0fcf0,
+	0xfcb0fcd0,
+	0xfc90fca0,
+	0x0088fe80,
+	0x32f480fc,
+/* 0x05b7: hub_barrier_done */
+	0xf001f800,
+	0x0e9801f7,
+	0x04febb04,
+	0xf102ffb9,
+	0xf09418e7,
+	0x21f440e3,
+/* 0x05cf: ctx_redswitch */
+	0xf000f89d,
+	0x07f120f7,
+	0x03f08500,
+	0x000fd001,
+	0xe7f004bd,
+/* 0x05e1: ctx_redswitch_delay */
+	0x01e2b608,
+	0xf1fd1bf4,
+	0xf10800f5,
+	0xf10200f5,
 	0xf0850007,
 	0x0fd00103,
-	0xf004bd00,
-/* 0x05de: ctx_redswitch_delay */
-	0xe2b608e7,
-	0xfd1bf401,
-	0x0800f5f1,
-	0x0200f5f1,
-	0x850007f1,
-	0xd00103f0,
-	0x04bd000f,
-/* 0x05fa: ctx_xfer */
-	0x07f100f8,
-	0x03f08100,
-	0x000fd002,
-	0x11f404bd,
-	0xcc21f507,
-/* 0x060d: ctx_xfer_not_load */
-	0x6a21f505,
-	0xf124bd02,
-	0xf047fc07,
-	0x02d00203,
-	0xf004bd00,
-	0x20b6012c,
-	0xfc07f103,
-	0x0203f04a,
-	0xbd0002d0,
-	0x01acf004,
-	0xf102a5f0,
-	0xf00000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98000c,
-	0x00e7f001,
-	0x016f21f5,
-	0xf101acf0,
-	0xf04000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98010c,
-	0x060f9802,
-	0x0800e7f1,
-	0x016f21f5,
+	0xf804bd00,
+/* 0x05fd: ctx_xfer */
+	0x0007f100,
+	0x0203f081,
+	0xbd000fd0,
+	0x0711f404,
+	0x05cf21f5,
+/* 0x0610: ctx_xfer_not_load */
+	0x026a21f5,
+	0x07f124bd,
+	0x03f047fc,
+	0x0002d002,
+	0x2cf004bd,
+	0x0320b601,
+	0x4afc07f1,
+	0xd00203f0,
+	0x04bd0002,
 	0xf001acf0,
-	0xb7f104a5,
-	0xb3f03000,
+	0xb7f102a5,
+	0xb3f00000,
 	0x040c9850,
 	0xbb0fc4b6,
 	0x0c9800bc,
-	0x030d9802,
-	0xf1080f98,
-	0xf50200e7,
-	0xf5016f21,
-	0xf4025e21,
-	0x12f40601,
-/* 0x06a9: ctx_xfer_post */
-	0x7f21f507,
-/* 0x06ad: ctx_xfer_done */
-	0xb421f502,
-	0x0000f805,
-	0x00000000,
+	0x010d9800,
+	0xf500e7f0,
+	0xf0016f21,
+	0xb7f101ac,
+	0xb3f04000,
+	0x040c9850,
+	0xbb0fc4b6,
+	0x0c9800bc,
+	0x020d9801,
+	0xf1060f98,
+	0xf50800e7,
+	0xf0016f21,
+	0xa5f001ac,
+	0x00b7f104,
+	0x50b3f030,
+	0xb6040c98,
+	0xbcbb0fc4,
+	0x020c9800,
+	0x98030d98,
+	0xe7f1080f,
+	0x21f50200,
+	0x21f5016f,
+	0x01f4025e,
+	0x0712f406,
+/* 0x06ac: ctx_xfer_post */
+	0x027f21f5,
+/* 0x06b0: ctx_xfer_done */
+	0x05b721f5,
+	0x000000f8,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h
index 2f59643..911976d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h
@@ -314,7 +314,7 @@
 	0x03f01200,
 	0x0002d000,
 	0x17f104bd,
-	0x10fe0542,
+	0x10fe0545,
 	0x0007f100,
 	0x0003f007,
 	0xbd0000d0,
@@ -338,184 +338,184 @@
 	0x02d00103,
 	0xf104bd00,
 	0xf00c30e7,
-	0x24bd50e3,
-	0x44bd34bd,
-/* 0x0430: init_unk_loop */
-	0xb06821f4,
-	0x0bf400f6,
-	0x01f7f00f,
-	0xfd04f2bb,
-	0x30b6054f,
-/* 0x0445: init_unk_next */
-	0x0120b601,
-	0xb004e0b6,
-	0x1bf40126,
-/* 0x0451: init_unk_done */
-	0x070380e2,
-	0xf1080480,
-	0xf0010027,
-	0x22cf0223,
-	0x9534bd00,
-	0x07f10825,
-	0x03f0c000,
-	0x0005d001,
-	0x07f104bd,
-	0x03f0c100,
-	0x0005d001,
-	0x0e9804bd,
-	0x010f9800,
-	0x015021f5,
-	0xbb002fbb,
-	0x0e98003f,
-	0x020f9801,
-	0x015021f5,
-	0xfd050e98,
-	0x2ebb00ef,
-	0x003ebb00,
-	0x98020e98,
-	0x21f5030f,
-	0x0e980150,
-	0x00effd07,
-	0xbb002ebb,
-	0x35b6003e,
-	0x0007f102,
-	0x0103f0d3,
-	0xbd0003d0,
-	0x0825b604,
-	0xb60635b6,
-	0x30b60120,
-	0x0824b601,
-	0xb90834b6,
-	0x21f5022f,
-	0x2fbb02d3,
-	0x003fbb00,
-	0x010007f1,
-	0xd00203f0,
+	0xe5f050e3,
+	0xbd24bd01,
+/* 0x0433: init_unk_loop */
+	0xf444bd34,
+	0xf6b06821,
+	0x0f0bf400,
+	0xbb01f7f0,
+	0x4ffd04f2,
+	0x0130b605,
+/* 0x0448: init_unk_next */
+	0xb60120b6,
+	0x26b004e0,
+	0xe21bf401,
+/* 0x0454: init_unk_done */
+	0x80070380,
+	0x27f10804,
+	0x23f00100,
+	0x0022cf02,
+	0x259534bd,
+	0x0007f108,
+	0x0103f0c0,
+	0xbd0005d0,
+	0x0007f104,
+	0x0103f0c1,
+	0xbd0005d0,
+	0x000e9804,
+	0xf5010f98,
+	0xbb015021,
+	0x3fbb002f,
+	0x010e9800,
+	0xf5020f98,
+	0x98015021,
+	0xeffd050e,
+	0x002ebb00,
+	0x98003ebb,
+	0x0f98020e,
+	0x5021f503,
+	0x070e9801,
+	0xbb00effd,
+	0x3ebb002e,
+	0x0235b600,
+	0xd30007f1,
+	0xd00103f0,
 	0x04bd0003,
-	0x29f024bd,
-	0x0007f11f,
-	0x0203f008,
-	0xbd0002d0,
-/* 0x0505: main */
-	0x0031f404,
-	0xf00028f4,
-	0x21f424d7,
-	0xf401f439,
-	0xf404e4b0,
-	0x81fe1e18,
-	0x0627f001,
-	0x12fd20bd,
-	0x01e4b604,
-	0xfe051efd,
-	0x21f50018,
-	0x0ef405fa,
-/* 0x0535: main_not_ctx_xfer */
-	0x10ef94d3,
-	0xf501f5f0,
-	0xf4037e21,
-/* 0x0542: ih */
-	0x80f9c60e,
-	0xf90188fe,
-	0xf990f980,
-	0xf9b0f9a0,
-	0xf9e0f9d0,
-	0xf104bdf0,
-	0xf00200a7,
-	0xaacf00a3,
-	0x04abc400,
-	0xf02c0bf4,
-	0xe7f124d7,
-	0xe3f01a00,
-	0x00eecf00,
-	0x1900f7f1,
-	0xcf00f3f0,
-	0x21f400ff,
-	0x01e7f004,
-	0x1d0007f1,
-	0xd00003f0,
-	0x04bd000e,
-/* 0x0590: ih_no_fifo */
-	0x010007f1,
-	0xd00003f0,
-	0x04bd000a,
-	0xe0fcf0fc,
-	0xb0fcd0fc,
-	0x90fca0fc,
-	0x88fe80fc,
-	0xf480fc00,
-	0x01f80032,
-/* 0x05b4: hub_barrier_done */
-	0x9801f7f0,
-	0xfebb040e,
-	0x02ffb904,
-	0x9418e7f1,
-	0xf440e3f0,
-	0x00f89d21,
-/* 0x05cc: ctx_redswitch */
-	0xf120f7f0,
+	0xb60825b6,
+	0x20b60635,
+	0x0130b601,
+	0xb60824b6,
+	0x2fb90834,
+	0xd321f502,
+	0x002fbb02,
+	0xf1003fbb,
+	0xf0010007,
+	0x03d00203,
+	0xbd04bd00,
+	0x1f29f024,
+	0x080007f1,
+	0xd00203f0,
+	0x04bd0002,
+/* 0x0508: main */
+	0xf40031f4,
+	0xd7f00028,
+	0x3921f424,
+	0xb0f401f4,
+	0x18f404e4,
+	0x0181fe1e,
+	0xbd0627f0,
+	0x0412fd20,
+	0xfd01e4b6,
+	0x18fe051e,
+	0xfd21f500,
+	0xd30ef405,
+/* 0x0538: main_not_ctx_xfer */
+	0xf010ef94,
+	0x21f501f5,
+	0x0ef4037e,
+/* 0x0545: ih */
+	0xfe80f9c6,
+	0x80f90188,
+	0xa0f990f9,
+	0xd0f9b0f9,
+	0xf0f9e0f9,
+	0xa7f104bd,
+	0xa3f00200,
+	0x00aacf00,
+	0xf404abc4,
+	0xd7f02c0b,
+	0x00e7f124,
+	0x00e3f01a,
+	0xf100eecf,
+	0xf01900f7,
+	0xffcf00f3,
+	0x0421f400,
+	0xf101e7f0,
+	0xf01d0007,
+	0x0ed00003,
+/* 0x0593: ih_no_fifo */
+	0xf104bd00,
+	0xf0010007,
+	0x0ad00003,
+	0xfc04bd00,
+	0xfce0fcf0,
+	0xfcb0fcd0,
+	0xfc90fca0,
+	0x0088fe80,
+	0x32f480fc,
+/* 0x05b7: hub_barrier_done */
+	0xf001f800,
+	0x0e9801f7,
+	0x04febb04,
+	0xf102ffb9,
+	0xf09418e7,
+	0x21f440e3,
+/* 0x05cf: ctx_redswitch */
+	0xf000f89d,
+	0x07f120f7,
+	0x03f08500,
+	0x000fd001,
+	0xe7f004bd,
+/* 0x05e1: ctx_redswitch_delay */
+	0x01e2b608,
+	0xf1fd1bf4,
+	0xf10800f5,
+	0xf10200f5,
 	0xf0850007,
 	0x0fd00103,
-	0xf004bd00,
-/* 0x05de: ctx_redswitch_delay */
-	0xe2b608e7,
-	0xfd1bf401,
-	0x0800f5f1,
-	0x0200f5f1,
-	0x850007f1,
-	0xd00103f0,
-	0x04bd000f,
-/* 0x05fa: ctx_xfer */
-	0x07f100f8,
-	0x03f08100,
-	0x000fd002,
-	0x11f404bd,
-	0xcc21f507,
-/* 0x060d: ctx_xfer_not_load */
-	0x6a21f505,
-	0xf124bd02,
-	0xf047fc07,
-	0x02d00203,
-	0xf004bd00,
-	0x20b6012c,
-	0xfc07f103,
-	0x0203f04a,
-	0xbd0002d0,
-	0x01acf004,
-	0xf102a5f0,
-	0xf00000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98000c,
-	0x00e7f001,
-	0x016f21f5,
-	0xf101acf0,
-	0xf04000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98010c,
-	0x060f9802,
-	0x0800e7f1,
-	0x016f21f5,
+	0xf804bd00,
+/* 0x05fd: ctx_xfer */
+	0x0007f100,
+	0x0203f081,
+	0xbd000fd0,
+	0x0711f404,
+	0x05cf21f5,
+/* 0x0610: ctx_xfer_not_load */
+	0x026a21f5,
+	0x07f124bd,
+	0x03f047fc,
+	0x0002d002,
+	0x2cf004bd,
+	0x0320b601,
+	0x4afc07f1,
+	0xd00203f0,
+	0x04bd0002,
 	0xf001acf0,
-	0xb7f104a5,
-	0xb3f03000,
+	0xb7f102a5,
+	0xb3f00000,
 	0x040c9850,
 	0xbb0fc4b6,
 	0x0c9800bc,
-	0x030d9802,
-	0xf1080f98,
-	0xf50200e7,
-	0xf5016f21,
-	0xf4025e21,
-	0x12f40601,
-/* 0x06a9: ctx_xfer_post */
-	0x7f21f507,
-/* 0x06ad: ctx_xfer_done */
-	0xb421f502,
-	0x0000f805,
-	0x00000000,
+	0x010d9800,
+	0xf500e7f0,
+	0xf0016f21,
+	0xb7f101ac,
+	0xb3f04000,
+	0x040c9850,
+	0xbb0fc4b6,
+	0x0c9800bc,
+	0x020d9801,
+	0xf1060f98,
+	0xf50800e7,
+	0xf0016f21,
+	0xa5f001ac,
+	0x00b7f104,
+	0x50b3f030,
+	0xb6040c98,
+	0xbcbb0fc4,
+	0x020c9800,
+	0x98030d98,
+	0xe7f1080f,
+	0x21f50200,
+	0x21f5016f,
+	0x01f4025e,
+	0x0712f406,
+/* 0x06ac: ctx_xfer_post */
+	0x027f21f5,
+/* 0x06b0: ctx_xfer_done */
+	0x05b721f5,
+	0x000000f8,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h
index ee8e54d..1c6e11b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h
@@ -314,7 +314,7 @@
 	0x03f01200,
 	0x0002d000,
 	0x17f104bd,
-	0x10fe0542,
+	0x10fe0545,
 	0x0007f100,
 	0x0003f007,
 	0xbd0000d0,
@@ -338,184 +338,184 @@
 	0x02d00103,
 	0xf104bd00,
 	0xf00c30e7,
-	0x24bd50e3,
-	0x44bd34bd,
-/* 0x0430: init_unk_loop */
-	0xb06821f4,
-	0x0bf400f6,
-	0x01f7f00f,
-	0xfd04f2bb,
-	0x30b6054f,
-/* 0x0445: init_unk_next */
-	0x0120b601,
-	0xb004e0b6,
-	0x1bf40226,
-/* 0x0451: init_unk_done */
-	0x070380e2,
-	0xf1080480,
-	0xf0010027,
-	0x22cf0223,
-	0x9534bd00,
-	0x07f10825,
-	0x03f0c000,
-	0x0005d001,
-	0x07f104bd,
-	0x03f0c100,
-	0x0005d001,
-	0x0e9804bd,
-	0x010f9800,
-	0x015021f5,
-	0xbb002fbb,
-	0x0e98003f,
-	0x020f9801,
-	0x015021f5,
-	0xfd050e98,
-	0x2ebb00ef,
-	0x003ebb00,
-	0x98020e98,
-	0x21f5030f,
-	0x0e980150,
-	0x00effd07,
-	0xbb002ebb,
-	0x35b6003e,
-	0x0007f102,
-	0x0103f0d3,
-	0xbd0003d0,
-	0x0825b604,
-	0xb60635b6,
-	0x30b60120,
-	0x0824b601,
-	0xb90834b6,
-	0x21f5022f,
-	0x2fbb02d3,
-	0x003fbb00,
-	0x010007f1,
-	0xd00203f0,
+	0xe5f050e3,
+	0xbd24bd01,
+/* 0x0433: init_unk_loop */
+	0xf444bd34,
+	0xf6b06821,
+	0x0f0bf400,
+	0xbb01f7f0,
+	0x4ffd04f2,
+	0x0130b605,
+/* 0x0448: init_unk_next */
+	0xb60120b6,
+	0x26b004e0,
+	0xe21bf402,
+/* 0x0454: init_unk_done */
+	0x80070380,
+	0x27f10804,
+	0x23f00100,
+	0x0022cf02,
+	0x259534bd,
+	0x0007f108,
+	0x0103f0c0,
+	0xbd0005d0,
+	0x0007f104,
+	0x0103f0c1,
+	0xbd0005d0,
+	0x000e9804,
+	0xf5010f98,
+	0xbb015021,
+	0x3fbb002f,
+	0x010e9800,
+	0xf5020f98,
+	0x98015021,
+	0xeffd050e,
+	0x002ebb00,
+	0x98003ebb,
+	0x0f98020e,
+	0x5021f503,
+	0x070e9801,
+	0xbb00effd,
+	0x3ebb002e,
+	0x0235b600,
+	0xd30007f1,
+	0xd00103f0,
 	0x04bd0003,
-	0x29f024bd,
-	0x0007f11f,
-	0x0203f030,
-	0xbd0002d0,
-/* 0x0505: main */
-	0x0031f404,
-	0xf00028f4,
-	0x21f424d7,
-	0xf401f439,
-	0xf404e4b0,
-	0x81fe1e18,
-	0x0627f001,
-	0x12fd20bd,
-	0x01e4b604,
-	0xfe051efd,
-	0x21f50018,
-	0x0ef405fa,
-/* 0x0535: main_not_ctx_xfer */
-	0x10ef94d3,
-	0xf501f5f0,
-	0xf4037e21,
-/* 0x0542: ih */
-	0x80f9c60e,
-	0xf90188fe,
-	0xf990f980,
-	0xf9b0f9a0,
-	0xf9e0f9d0,
-	0xf104bdf0,
-	0xf00200a7,
-	0xaacf00a3,
-	0x04abc400,
-	0xf02c0bf4,
-	0xe7f124d7,
-	0xe3f01a00,
-	0x00eecf00,
-	0x1900f7f1,
-	0xcf00f3f0,
-	0x21f400ff,
-	0x01e7f004,
-	0x1d0007f1,
-	0xd00003f0,
-	0x04bd000e,
-/* 0x0590: ih_no_fifo */
-	0x010007f1,
-	0xd00003f0,
-	0x04bd000a,
-	0xe0fcf0fc,
-	0xb0fcd0fc,
-	0x90fca0fc,
-	0x88fe80fc,
-	0xf480fc00,
-	0x01f80032,
-/* 0x05b4: hub_barrier_done */
-	0x9801f7f0,
-	0xfebb040e,
-	0x02ffb904,
-	0x9418e7f1,
-	0xf440e3f0,
-	0x00f89d21,
-/* 0x05cc: ctx_redswitch */
-	0xf120f7f0,
+	0xb60825b6,
+	0x20b60635,
+	0x0130b601,
+	0xb60824b6,
+	0x2fb90834,
+	0xd321f502,
+	0x002fbb02,
+	0xf1003fbb,
+	0xf0010007,
+	0x03d00203,
+	0xbd04bd00,
+	0x1f29f024,
+	0x300007f1,
+	0xd00203f0,
+	0x04bd0002,
+/* 0x0508: main */
+	0xf40031f4,
+	0xd7f00028,
+	0x3921f424,
+	0xb0f401f4,
+	0x18f404e4,
+	0x0181fe1e,
+	0xbd0627f0,
+	0x0412fd20,
+	0xfd01e4b6,
+	0x18fe051e,
+	0xfd21f500,
+	0xd30ef405,
+/* 0x0538: main_not_ctx_xfer */
+	0xf010ef94,
+	0x21f501f5,
+	0x0ef4037e,
+/* 0x0545: ih */
+	0xfe80f9c6,
+	0x80f90188,
+	0xa0f990f9,
+	0xd0f9b0f9,
+	0xf0f9e0f9,
+	0xa7f104bd,
+	0xa3f00200,
+	0x00aacf00,
+	0xf404abc4,
+	0xd7f02c0b,
+	0x00e7f124,
+	0x00e3f01a,
+	0xf100eecf,
+	0xf01900f7,
+	0xffcf00f3,
+	0x0421f400,
+	0xf101e7f0,
+	0xf01d0007,
+	0x0ed00003,
+/* 0x0593: ih_no_fifo */
+	0xf104bd00,
+	0xf0010007,
+	0x0ad00003,
+	0xfc04bd00,
+	0xfce0fcf0,
+	0xfcb0fcd0,
+	0xfc90fca0,
+	0x0088fe80,
+	0x32f480fc,
+/* 0x05b7: hub_barrier_done */
+	0xf001f800,
+	0x0e9801f7,
+	0x04febb04,
+	0xf102ffb9,
+	0xf09418e7,
+	0x21f440e3,
+/* 0x05cf: ctx_redswitch */
+	0xf000f89d,
+	0x07f120f7,
+	0x03f08500,
+	0x000fd001,
+	0xe7f004bd,
+/* 0x05e1: ctx_redswitch_delay */
+	0x01e2b608,
+	0xf1fd1bf4,
+	0xf10800f5,
+	0xf10200f5,
 	0xf0850007,
 	0x0fd00103,
-	0xf004bd00,
-/* 0x05de: ctx_redswitch_delay */
-	0xe2b608e7,
-	0xfd1bf401,
-	0x0800f5f1,
-	0x0200f5f1,
-	0x850007f1,
-	0xd00103f0,
-	0x04bd000f,
-/* 0x05fa: ctx_xfer */
-	0x07f100f8,
-	0x03f08100,
-	0x000fd002,
-	0x11f404bd,
-	0xcc21f507,
-/* 0x060d: ctx_xfer_not_load */
-	0x6a21f505,
-	0xf124bd02,
-	0xf047fc07,
-	0x02d00203,
-	0xf004bd00,
-	0x20b6012c,
-	0xfc07f103,
-	0x0203f04a,
-	0xbd0002d0,
-	0x01acf004,
-	0xf102a5f0,
-	0xf00000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98000c,
-	0x00e7f001,
-	0x016f21f5,
-	0xf101acf0,
-	0xf04000b7,
-	0x0c9850b3,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98010c,
-	0x060f9802,
-	0x0800e7f1,
-	0x016f21f5,
+	0xf804bd00,
+/* 0x05fd: ctx_xfer */
+	0x0007f100,
+	0x0203f081,
+	0xbd000fd0,
+	0x0711f404,
+	0x05cf21f5,
+/* 0x0610: ctx_xfer_not_load */
+	0x026a21f5,
+	0x07f124bd,
+	0x03f047fc,
+	0x0002d002,
+	0x2cf004bd,
+	0x0320b601,
+	0x4afc07f1,
+	0xd00203f0,
+	0x04bd0002,
 	0xf001acf0,
-	0xb7f104a5,
-	0xb3f03000,
+	0xb7f102a5,
+	0xb3f00000,
 	0x040c9850,
 	0xbb0fc4b6,
 	0x0c9800bc,
-	0x030d9802,
-	0xf1080f98,
-	0xf50200e7,
-	0xf5016f21,
-	0xf4025e21,
-	0x12f40601,
-/* 0x06a9: ctx_xfer_post */
-	0x7f21f507,
-/* 0x06ad: ctx_xfer_done */
-	0xb421f502,
-	0x0000f805,
-	0x00000000,
+	0x010d9800,
+	0xf500e7f0,
+	0xf0016f21,
+	0xb7f101ac,
+	0xb3f04000,
+	0x040c9850,
+	0xbb0fc4b6,
+	0x0c9800bc,
+	0x020d9801,
+	0xf1060f98,
+	0xf50800e7,
+	0xf0016f21,
+	0xa5f001ac,
+	0x00b7f104,
+	0x50b3f030,
+	0xb6040c98,
+	0xbcbb0fc4,
+	0x020c9800,
+	0x98030d98,
+	0xe7f1080f,
+	0x21f50200,
+	0x21f5016f,
+	0x01f4025e,
+	0x0712f406,
+/* 0x06ac: ctx_xfer_post */
+	0x027f21f5,
+/* 0x06b0: ctx_xfer_done */
+	0x05b721f5,
+	0x000000f8,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h
index fbcc342..84af7ec 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h
@@ -276,7 +276,7 @@
 	0x02020014,
 	0xf6120040,
 	0x04bd0002,
-	0xfe048141,
+	0xfe048441,
 	0x00400010,
 	0x0000f607,
 	0x040204bd,
@@ -295,165 +295,165 @@
 	0x01c90080,
 	0xbd0002f6,
 	0x0c308e04,
-	0xbd24bd50,
-/* 0x0383: init_unk_loop */
-	0x7e44bd34,
-	0xb0000065,
-	0x0bf400f6,
-	0xbb010f0e,
-	0x4ffd04f2,
-	0x0130b605,
-/* 0x0398: init_unk_next */
-	0xb60120b6,
-	0x26b004e0,
-	0xe21bf401,
-/* 0x03a4: init_unk_done */
-	0xb50703b5,
-	0x00820804,
-	0x22cf0201,
-	0x9534bd00,
-	0x00800825,
-	0x05f601c0,
-	0x8004bd00,
-	0xf601c100,
-	0x04bd0005,
-	0x98000e98,
-	0x207e010f,
-	0x2fbb0001,
-	0x003fbb00,
-	0x98010e98,
-	0x207e020f,
-	0x0e980001,
-	0x00effd05,
-	0xbb002ebb,
-	0x0e98003e,
-	0x030f9802,
-	0x0001207e,
-	0xfd070e98,
-	0x2ebb00ef,
-	0x003ebb00,
-	0x800235b6,
-	0xf601d300,
-	0x04bd0003,
-	0xb60825b6,
-	0x20b60635,
-	0x0130b601,
-	0xb60824b6,
-	0x2fb20834,
-	0x0002687e,
-	0xbb002fbb,
-	0x0080003f,
-	0x03f60201,
-	0xbd04bd00,
-	0x1f29f024,
-	0x02300080,
-	0xbd0002f6,
-/* 0x0445: main */
-	0x0031f404,
-	0x0d0028f4,
-	0x00377e24,
-	0xf401f400,
-	0xf404e4b0,
-	0x81fe1d18,
-	0xbd060201,
-	0x0412fd20,
-	0xfd01e4b6,
-	0x18fe051e,
-	0x05187e00,
-	0xd40ef400,
-/* 0x0474: main_not_ctx_xfer */
-	0xf010ef94,
-	0xf87e01f5,
-	0x0ef40002,
-/* 0x0481: ih */
-	0xfe80f9c7,
-	0x80f90188,
-	0xa0f990f9,
-	0xd0f9b0f9,
-	0xf0f9e0f9,
-	0x004a04bd,
-	0x00aacf02,
-	0xf404abc4,
-	0x240d1f0b,
-	0xcf1a004e,
-	0x004f00ee,
-	0x00ffcf19,
-	0x0000047e,
-	0x0040010e,
-	0x000ef61d,
-/* 0x04be: ih_no_fifo */
-	0x004004bd,
-	0x000af601,
-	0xf0fc04bd,
-	0xd0fce0fc,
-	0xa0fcb0fc,
-	0x80fc90fc,
-	0xfc0088fe,
-	0x0032f480,
-/* 0x04de: hub_barrier_done */
-	0x010f01f8,
-	0xbb040e98,
-	0xffb204fe,
-	0x4094188e,
-	0x00008f7e,
-/* 0x04f2: ctx_redswitch */
-	0x200f00f8,
+	0x01e5f050,
+	0x34bd24bd,
+/* 0x0386: init_unk_loop */
+	0x657e44bd,
+	0xf6b00000,
+	0x0e0bf400,
+	0xf2bb010f,
+	0x054ffd04,
+/* 0x039b: init_unk_next */
+	0xb60130b6,
+	0xe0b60120,
+	0x0126b004,
+/* 0x03a7: init_unk_done */
+	0xb5e21bf4,
+	0x04b50703,
+	0x01008208,
+	0x0022cf02,
+	0x259534bd,
+	0xc0008008,
+	0x0005f601,
+	0x008004bd,
+	0x05f601c1,
+	0x9804bd00,
+	0x0f98000e,
+	0x01207e01,
+	0x002fbb00,
+	0x98003fbb,
+	0x0f98010e,
+	0x01207e02,
+	0x050e9800,
+	0xbb00effd,
+	0x3ebb002e,
+	0x020e9800,
+	0x7e030f98,
+	0x98000120,
+	0xeffd070e,
+	0x002ebb00,
+	0xb6003ebb,
+	0x00800235,
+	0x03f601d3,
+	0xb604bd00,
+	0x35b60825,
+	0x0120b606,
+	0xb60130b6,
+	0x34b60824,
+	0x7e2fb208,
+	0xbb000268,
+	0x3fbb002f,
+	0x01008000,
+	0x0003f602,
+	0x24bd04bd,
+	0x801f29f0,
+	0xf6023000,
+	0x04bd0002,
+/* 0x0448: main */
+	0xf40031f4,
+	0x240d0028,
+	0x0000377e,
+	0xb0f401f4,
+	0x18f404e4,
+	0x0181fe1d,
+	0x20bd0602,
+	0xb60412fd,
+	0x1efd01e4,
+	0x0018fe05,
+	0x00051b7e,
+/* 0x0477: main_not_ctx_xfer */
+	0x94d40ef4,
+	0xf5f010ef,
+	0x02f87e01,
+	0xc70ef400,
+/* 0x0484: ih */
+	0x88fe80f9,
+	0xf980f901,
+	0xf9a0f990,
+	0xf9d0f9b0,
+	0xbdf0f9e0,
+	0x02004a04,
+	0xc400aacf,
+	0x0bf404ab,
+	0x4e240d1f,
+	0xeecf1a00,
+	0x19004f00,
+	0x7e00ffcf,
+	0x0e000004,
+	0x1d004001,
+	0xbd000ef6,
+/* 0x04c1: ih_no_fifo */
+	0x01004004,
+	0xbd000af6,
+	0xfcf0fc04,
+	0xfcd0fce0,
+	0xfca0fcb0,
+	0xfe80fc90,
+	0x80fc0088,
+	0xf80032f4,
+/* 0x04e1: hub_barrier_done */
+	0x98010f01,
+	0xfebb040e,
+	0x8effb204,
+	0x7e409418,
+	0xf800008f,
+/* 0x04f5: ctx_redswitch */
+	0x80200f00,
+	0xf6018500,
+	0x04bd000f,
+/* 0x0502: ctx_redswitch_delay */
+	0xe2b6080e,
+	0xfd1bf401,
+	0x0800f5f1,
+	0x0200f5f1,
 	0x01850080,
 	0xbd000ff6,
-/* 0x04ff: ctx_redswitch_delay */
-	0xb6080e04,
-	0x1bf401e2,
-	0x00f5f1fd,
-	0x00f5f108,
-	0x85008002,
-	0x000ff601,
-	0x00f804bd,
-/* 0x0518: ctx_xfer */
-	0x02810080,
-	0xbd000ff6,
-	0x0711f404,
-	0x0004f27e,
-/* 0x0528: ctx_xfer_not_load */
-	0x0002167e,
-	0xfc8024bd,
-	0x02f60247,
-	0xf004bd00,
-	0x20b6012c,
-	0x4afc8003,
+/* 0x051b: ctx_xfer */
+	0x8000f804,
+	0xf6028100,
+	0x04bd000f,
+	0x7e0711f4,
+/* 0x052b: ctx_xfer_not_load */
+	0x7e0004f5,
+	0xbd000216,
+	0x47fc8024,
 	0x0002f602,
-	0xacf004bd,
-	0x02a5f001,
-	0x5000008b,
-	0xb6040c98,
-	0xbcbb0fc4,
-	0x000c9800,
-	0x0e010d98,
-	0x013d7e00,
-	0x01acf000,
-	0x5040008b,
-	0xb6040c98,
-	0xbcbb0fc4,
-	0x010c9800,
-	0x98020d98,
-	0x004e060f,
-	0x013d7e08,
-	0x01acf000,
-	0x8b04a5f0,
-	0x98503000,
+	0x2cf004bd,
+	0x0320b601,
+	0x024afc80,
+	0xbd0002f6,
+	0x01acf004,
+	0x8b02a5f0,
+	0x98500000,
 	0xc4b6040c,
 	0x00bcbb0f,
-	0x98020c98,
-	0x0f98030d,
-	0x02004e08,
+	0x98000c98,
+	0x000e010d,
 	0x00013d7e,
-	0x00020a7e,
-	0xf40601f4,
-/* 0x05b2: ctx_xfer_post */
-	0x277e0712,
-/* 0x05b6: ctx_xfer_done */
-	0xde7e0002,
-	0x00f80004,
-	0x00000000,
+	0x8b01acf0,
+	0x98504000,
+	0xc4b6040c,
+	0x00bcbb0f,
+	0x98010c98,
+	0x0f98020d,
+	0x08004e06,
+	0x00013d7e,
+	0xf001acf0,
+	0x008b04a5,
+	0x0c985030,
+	0x0fc4b604,
+	0x9800bcbb,
+	0x0d98020c,
+	0x080f9803,
+	0x7e02004e,
+	0x7e00013d,
+	0xf400020a,
+	0x12f40601,
+/* 0x05b5: ctx_xfer_post */
+	0x02277e07,
+/* 0x05b9: ctx_xfer_done */
+	0x04e17e00,
+	0x0000f800,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h
index 51f5c3c..11bf363 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h
@@ -289,7 +289,7 @@
 	0x020014fe,
 	0x12004002,
 	0xbd0002f6,
-	0x05b04104,
+	0x05b34104,
 	0x400010fe,
 	0x00f60700,
 	0x0204bd00,
@@ -308,259 +308,259 @@
 	0xc900800f,
 	0x0002f601,
 	0x308e04bd,
-	0x24bd500c,
-	0x44bd34bd,
-/* 0x03b0: init_unk_loop */
-	0x0000657e,
-	0xf400f6b0,
-	0x010f0e0b,
-	0xfd04f2bb,
-	0x30b6054f,
-/* 0x03c5: init_unk_next */
-	0x0120b601,
-	0xb004e0b6,
-	0x1bf40226,
-/* 0x03d1: init_unk_done */
-	0x0703b5e2,
-	0x820804b5,
-	0xcf020100,
-	0x34bd0022,
-	0x80082595,
-	0xf601c000,
+	0xe5f0500c,
+	0xbd24bd01,
+/* 0x03b3: init_unk_loop */
+	0x7e44bd34,
+	0xb0000065,
+	0x0bf400f6,
+	0xbb010f0e,
+	0x4ffd04f2,
+	0x0130b605,
+/* 0x03c8: init_unk_next */
+	0xb60120b6,
+	0x26b004e0,
+	0xe21bf402,
+/* 0x03d4: init_unk_done */
+	0xb50703b5,
+	0x00820804,
+	0x22cf0201,
+	0x9534bd00,
+	0x00800825,
+	0x05f601c0,
+	0x8004bd00,
+	0xf601c100,
 	0x04bd0005,
-	0x01c10080,
-	0xbd0005f6,
-	0x000e9804,
-	0x7e010f98,
-	0xbb000120,
-	0x3fbb002f,
-	0x010e9800,
-	0x7e020f98,
-	0x98000120,
-	0xeffd050e,
-	0x002ebb00,
-	0x98003ebb,
-	0x0f98020e,
-	0x01207e03,
-	0x070e9800,
-	0xbb00effd,
-	0x3ebb002e,
-	0x0235b600,
-	0x01d30080,
-	0xbd0003f6,
-	0x0825b604,
-	0xb60635b6,
-	0x30b60120,
-	0x0824b601,
-	0xb20834b6,
-	0x02687e2f,
-	0x002fbb00,
-	0x0f003fbb,
-	0x8effb23f,
-	0xf0501d60,
-	0x8f7e01e5,
-	0x0c0f0000,
-	0xa88effb2,
-	0xe5f0501d,
-	0x008f7e01,
-	0x03147e00,
-	0xb23f0f00,
-	0x1d608eff,
-	0x01e5f050,
-	0x00008f7e,
-	0xffb2000f,
-	0x501d9c8e,
-	0x7e01e5f0,
-	0x0f00008f,
-	0x03147e01,
-	0x8effb200,
+	0x98000e98,
+	0x207e010f,
+	0x2fbb0001,
+	0x003fbb00,
+	0x98010e98,
+	0x207e020f,
+	0x0e980001,
+	0x00effd05,
+	0xbb002ebb,
+	0x0e98003e,
+	0x030f9802,
+	0x0001207e,
+	0xfd070e98,
+	0x2ebb00ef,
+	0x003ebb00,
+	0x800235b6,
+	0xf601d300,
+	0x04bd0003,
+	0xb60825b6,
+	0x20b60635,
+	0x0130b601,
+	0xb60824b6,
+	0x2fb20834,
+	0x0002687e,
+	0xbb002fbb,
+	0x3f0f003f,
+	0x501d608e,
+	0xb201e5f0,
+	0x008f7eff,
+	0x8e0c0f00,
 	0xf0501da8,
-	0x8f7e01e5,
-	0xff0f0000,
-	0x988effb2,
-	0xe5f0501d,
-	0x008f7e01,
-	0xb2020f00,
-	0x1da88eff,
-	0x01e5f050,
+	0xffb201e5,
 	0x00008f7e,
 	0x0003147e,
-	0x85050498,
-	0x98504000,
-	0x64b60406,
-	0x0056bb0f,
-/* 0x04e0: tpc_strand_init_tpc_loop */
-	0x05705eb8,
-	0x00657e00,
-	0xbdf6b200,
-/* 0x04ed: tpc_strand_init_idx_loop */
-	0x605eb874,
-	0x7fb20005,
-	0x00008f7e,
-	0x05885eb8,
-	0x082f9500,
-	0x00008f7e,
-	0x058c5eb8,
-	0x082f9500,
-	0x00008f7e,
-	0x05905eb8,
-	0x00657e00,
-	0x06f5b600,
-	0xb601f0b6,
-	0x2fbb08f4,
-	0x003fbb00,
-	0xb60170b6,
-	0x1bf40162,
-	0x0050b7bf,
-	0x0142b608,
-	0x0fa81bf4,
-	0x8effb23f,
-	0xf0501d60,
-	0x8f7e01e5,
-	0x0d0f0000,
-	0xa88effb2,
+	0x608e3f0f,
 	0xe5f0501d,
-	0x008f7e01,
-	0x03147e00,
-	0x01008000,
-	0x0003f602,
-	0x24bd04bd,
-	0x801f29f0,
-	0xf6023000,
-	0x04bd0002,
-/* 0x0574: main */
-	0xf40031f4,
-	0x240d0028,
-	0x0000377e,
-	0xb0f401f4,
-	0x18f404e4,
-	0x0181fe1d,
-	0x20bd0602,
-	0xb60412fd,
-	0x1efd01e4,
-	0x0018fe05,
-	0x0006477e,
-/* 0x05a3: main_not_ctx_xfer */
-	0x94d40ef4,
-	0xf5f010ef,
-	0x02f87e01,
-	0xc70ef400,
-/* 0x05b0: ih */
-	0x88fe80f9,
-	0xf980f901,
-	0xf9a0f990,
-	0xf9d0f9b0,
-	0xbdf0f9e0,
-	0x02004a04,
-	0xc400aacf,
-	0x0bf404ab,
-	0x4e240d1f,
-	0xeecf1a00,
-	0x19004f00,
-	0x7e00ffcf,
-	0x0e000004,
-	0x1d004001,
-	0xbd000ef6,
-/* 0x05ed: ih_no_fifo */
-	0x01004004,
-	0xbd000af6,
-	0xfcf0fc04,
-	0xfcd0fce0,
-	0xfca0fcb0,
-	0xfe80fc90,
-	0x80fc0088,
-	0xf80032f4,
-/* 0x060d: hub_barrier_done */
-	0x98010f01,
-	0xfebb040e,
-	0x8effb204,
-	0x7e409418,
-	0xf800008f,
-/* 0x0621: ctx_redswitch */
-	0x80200f00,
+	0x7effb201,
+	0x0f00008f,
+	0x1d9c8e00,
+	0x01e5f050,
+	0x8f7effb2,
+	0x010f0000,
+	0x0003147e,
+	0x501da88e,
+	0xb201e5f0,
+	0x008f7eff,
+	0x8eff0f00,
+	0xf0501d98,
+	0xffb201e5,
+	0x00008f7e,
+	0xa88e020f,
+	0xe5f0501d,
+	0x7effb201,
+	0x7e00008f,
+	0x98000314,
+	0x00850504,
+	0x06985040,
+	0x0f64b604,
+/* 0x04e3: tpc_strand_init_tpc_loop */
+	0xb80056bb,
+	0x0005705e,
+	0x0000657e,
+	0x74bdf6b2,
+/* 0x04f0: tpc_strand_init_idx_loop */
+	0x05605eb8,
+	0x7e7fb200,
+	0xb800008f,
+	0x0005885e,
+	0x7e082f95,
+	0xb800008f,
+	0x00058c5e,
+	0x7e082f95,
+	0xb800008f,
+	0x0005905e,
+	0x0000657e,
+	0xb606f5b6,
+	0xf4b601f0,
+	0x002fbb08,
+	0xb6003fbb,
+	0x62b60170,
+	0xbf1bf401,
+	0x080050b7,
+	0xf40142b6,
+	0x3f0fa81b,
+	0x501d608e,
+	0xb201e5f0,
+	0x008f7eff,
+	0x8e0d0f00,
+	0xf0501da8,
+	0xffb201e5,
+	0x00008f7e,
+	0x0003147e,
+	0x02010080,
+	0xbd0003f6,
+	0xf024bd04,
+	0x00801f29,
+	0x02f60230,
+/* 0x0577: main */
+	0xf404bd00,
+	0x28f40031,
+	0x7e240d00,
+	0xf4000037,
+	0xe4b0f401,
+	0x1d18f404,
+	0x020181fe,
+	0xfd20bd06,
+	0xe4b60412,
+	0x051efd01,
+	0x7e0018fe,
+	0xf400064a,
+/* 0x05a6: main_not_ctx_xfer */
+	0xef94d40e,
+	0x01f5f010,
+	0x0002f87e,
+/* 0x05b3: ih */
+	0xf9c70ef4,
+	0x0188fe80,
+	0x90f980f9,
+	0xb0f9a0f9,
+	0xe0f9d0f9,
+	0x04bdf0f9,
+	0xcf02004a,
+	0xabc400aa,
+	0x1f0bf404,
+	0x004e240d,
+	0x00eecf1a,
+	0xcf19004f,
+	0x047e00ff,
+	0x010e0000,
+	0xf61d0040,
+	0x04bd000e,
+/* 0x05f0: ih_no_fifo */
+	0xf6010040,
+	0x04bd000a,
+	0xe0fcf0fc,
+	0xb0fcd0fc,
+	0x90fca0fc,
+	0x88fe80fc,
+	0xf480fc00,
+	0x01f80032,
+/* 0x0610: hub_barrier_done */
+	0x0e98010f,
+	0x04febb04,
+	0x188effb2,
+	0x8f7e4094,
+	0x00f80000,
+/* 0x0624: ctx_redswitch */
+	0x0080200f,
+	0x0ff60185,
+	0x0e04bd00,
+/* 0x0631: ctx_redswitch_delay */
+	0x01e2b608,
+	0xf1fd1bf4,
+	0xf10800f5,
+	0x800200f5,
 	0xf6018500,
 	0x04bd000f,
-/* 0x062e: ctx_redswitch_delay */
-	0xe2b6080e,
-	0xfd1bf401,
-	0x0800f5f1,
-	0x0200f5f1,
-	0x01850080,
-	0xbd000ff6,
-/* 0x0647: ctx_xfer */
-	0x8000f804,
-	0xf6028100,
-	0x04bd000f,
-	0xc48effb2,
-	0xe5f0501d,
-	0x008f7e01,
-	0x0711f400,
-	0x0006217e,
-/* 0x0664: ctx_xfer_not_load */
-	0x0002167e,
-	0xfc8024bd,
-	0x02f60247,
-	0xf004bd00,
-	0x20b6012c,
-	0x4afc8003,
+/* 0x064a: ctx_xfer */
+	0x008000f8,
+	0x0ff60281,
+	0x8e04bd00,
+	0xf0501dc4,
+	0xffb201e5,
+	0x00008f7e,
+	0x7e0711f4,
+/* 0x0667: ctx_xfer_not_load */
+	0x7e000624,
+	0xbd000216,
+	0x47fc8024,
 	0x0002f602,
-	0x0c0f04bd,
-	0xa88effb2,
+	0x2cf004bd,
+	0x0320b601,
+	0x024afc80,
+	0xbd0002f6,
+	0x8e0c0f04,
+	0xf0501da8,
+	0xffb201e5,
+	0x00008f7e,
+	0x0003147e,
+	0x608e3f0f,
 	0xe5f0501d,
-	0x008f7e01,
-	0x03147e00,
-	0xb23f0f00,
-	0x1d608eff,
-	0x01e5f050,
-	0x00008f7e,
-	0xffb2000f,
-	0x501d9c8e,
-	0x7e01e5f0,
+	0x7effb201,
 	0x0f00008f,
-	0x03147e01,
-	0x01fcf000,
-	0xb203f0b6,
-	0x1da88eff,
+	0x1d9c8e00,
 	0x01e5f050,
-	0x00008f7e,
-	0xf001acf0,
-	0x008b02a5,
-	0x0c985000,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98000c,
-	0x7e000e01,
-	0xf000013d,
-	0x008b01ac,
-	0x0c985040,
-	0x0fc4b604,
-	0x9800bcbb,
-	0x0d98010c,
-	0x060f9802,
-	0x7e08004e,
-	0xf000013d,
+	0x8f7effb2,
+	0x010f0000,
+	0x0003147e,
+	0xb601fcf0,
+	0xa88e03f0,
+	0xe5f0501d,
+	0x7effb201,
+	0xf000008f,
 	0xa5f001ac,
-	0x30008b04,
+	0x00008b02,
 	0x040c9850,
 	0xbb0fc4b6,
 	0x0c9800bc,
-	0x030d9802,
-	0x4e080f98,
-	0x3d7e0200,
-	0x0a7e0001,
-	0x147e0002,
-	0x01f40003,
-	0x1a12f406,
-/* 0x073c: ctx_xfer_post */
-	0x0002277e,
-	0xffb20d0f,
-	0x501da88e,
-	0x7e01e5f0,
-	0x7e00008f,
-/* 0x0753: ctx_xfer_done */
-	0x7e000314,
-	0xf800060d,
-	0x00000000,
+	0x010d9800,
+	0x3d7e000e,
+	0xacf00001,
+	0x40008b01,
+	0x040c9850,
+	0xbb0fc4b6,
+	0x0c9800bc,
+	0x020d9801,
+	0x4e060f98,
+	0x3d7e0800,
+	0xacf00001,
+	0x04a5f001,
+	0x5030008b,
+	0xb6040c98,
+	0xbcbb0fc4,
+	0x020c9800,
+	0x98030d98,
+	0x004e080f,
+	0x013d7e02,
+	0x020a7e00,
+	0x03147e00,
+	0x0601f400,
+/* 0x073f: ctx_xfer_post */
+	0x7e1a12f4,
+	0x0f000227,
+	0x1da88e0d,
+	0x01e5f050,
+	0x8f7effb2,
+	0x147e0000,
+/* 0x0756: ctx_xfer_done */
+	0x107e0003,
+	0x00f80006,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index dda7a7d..9f5dfc8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -143,7 +143,7 @@
 static int
 gf100_fermi_mthd_zbc_color(struct nvkm_object *object, void *data, u32 size)
 {
-	struct gf100_gr *gr = (void *)object->engine;
+	struct gf100_gr *gr = gf100_gr(nvkm_gr(object->engine));
 	union {
 		struct fermi_a_zbc_color_v0 v0;
 	} *args = data;
@@ -189,7 +189,7 @@
 static int
 gf100_fermi_mthd_zbc_depth(struct nvkm_object *object, void *data, u32 size)
 {
-	struct gf100_gr *gr = (void *)object->engine;
+	struct gf100_gr *gr = gf100_gr(nvkm_gr(object->engine));
 	union {
 		struct fermi_a_zbc_depth_v0 v0;
 	} *args = data;
@@ -1530,6 +1530,8 @@
 		gr->ppc_nr[i]  = gr->func->ppc_nr;
 		for (j = 0; j < gr->ppc_nr[i]; j++) {
 			u8 mask = nvkm_rd32(device, GPC_UNIT(i, 0x0c30 + (j * 4)));
+			if (mask)
+				gr->ppc_mask[i] |= (1 << j);
 			gr->ppc_tpc_nr[i][j] = hweight8(mask);
 		}
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
index 4611961..02e78b8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
@@ -97,6 +97,7 @@
 	u8 tpc_nr[GPC_MAX];
 	u8 tpc_total;
 	u8 ppc_nr[GPC_MAX];
+	u8 ppc_mask[GPC_MAX];
 	u8 ppc_tpc_nr[GPC_MAX][4];
 
 	struct nvkm_memory *unk4188b4;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c
index 895ba74..1d7dd38 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c
@@ -97,7 +97,9 @@
 nvkm_instobj_dtor(struct nvkm_memory *memory)
 {
 	struct nvkm_instobj *iobj = nvkm_instobj(memory);
+	spin_lock(&iobj->imem->lock);
 	list_del(&iobj->head);
+	spin_unlock(&iobj->imem->lock);
 	nvkm_memory_del(&iobj->parent);
 	return iobj;
 }
@@ -190,7 +192,9 @@
 		nvkm_memory_ctor(&nvkm_instobj_func_slow, &iobj->memory);
 		iobj->parent = memory;
 		iobj->imem = imem;
+		spin_lock(&iobj->imem->lock);
 		list_add_tail(&iobj->head, &imem->list);
+		spin_unlock(&iobj->imem->lock);
 		memory = &iobj->memory;
 	}
 
@@ -309,5 +313,6 @@
 {
 	nvkm_subdev_ctor(&nvkm_instmem, device, index, 0, &imem->subdev);
 	imem->func = func;
+	spin_lock_init(&imem->lock);
 	INIT_LIST_HEAD(&imem->list);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c
index b61509e..b735173 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c
@@ -59,7 +59,7 @@
 	duty = (uv - bios->base) * div / bios->pwm_range;
 
 	nvkm_wr32(device, 0x20340, div);
-	nvkm_wr32(device, 0x20344, 0x8000000 | duty);
+	nvkm_wr32(device, 0x20344, 0x80000000 | duty);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index d302488..84d4563 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -221,11 +221,17 @@
 	if (!(rdev->flags & RADEON_IS_PCIE))
 		bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
 
+	/* Write-combined CPU mappings of GTT cause GPU hangs with RV6xx
+	 * See https://bugs.freedesktop.org/show_bug.cgi?id=91268
+	 */
+	if (rdev->family >= CHIP_RV610 && rdev->family <= CHIP_RV635)
+		bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
+
 #ifdef CONFIG_X86_32
 	/* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit
 	 * See https://bugs.freedesktop.org/show_bug.cgi?id=84627
 	 */
-	bo->flags &= ~RADEON_GEM_GTT_WC;
+	bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
 #elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT)
 	/* Don't try to enable write-combining when it can't work, or things
 	 * may be slow
@@ -235,9 +241,10 @@
 #warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
 	 thanks to write-combining
 
-	DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
-		      "better performance thanks to write-combining\n");
-	bo->flags &= ~RADEON_GEM_GTT_WC;
+	if (bo->flags & RADEON_GEM_GTT_WC)
+		DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
+			      "better performance thanks to write-combining\n");
+	bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC);
 #endif
 
 	radeon_ttm_placement_from_domain(bo, domain);
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 6d80dde..f4f03dc 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1542,8 +1542,7 @@
 				ret = device_create_file(rdev->dev, &dev_attr_power_method);
 				if (ret)
 					DRM_ERROR("failed to create device file for power method\n");
-				if (!ret)
-					rdev->pm.sysfs_initialized = true;
+				rdev->pm.sysfs_initialized = true;
 			}
 
 			mutex_lock(&rdev->pm.mutex);
diff --git a/drivers/gpu/drm/radeon/rv730_dpm.c b/drivers/gpu/drm/radeon/rv730_dpm.c
index 3f5e1cf..d37ba2c 100644
--- a/drivers/gpu/drm/radeon/rv730_dpm.c
+++ b/drivers/gpu/drm/radeon/rv730_dpm.c
@@ -464,7 +464,7 @@
 	result = rv770_send_msg_to_smc(rdev, PPSMC_MSG_TwoLevelsDisabled);
 
 	if (result != PPSMC_Result_OK)
-		DRM_ERROR("Could not force DPM to low\n");
+		DRM_DEBUG("Could not force DPM to low\n");
 
 	WREG32_P(GENERAL_PWRMGT, 0, ~GLOBAL_PWRMGT_EN);
 
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index b9c7707..e830c89 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -193,7 +193,7 @@
 	result = rv770_send_msg_to_smc(rdev, PPSMC_MSG_TwoLevelsDisabled);
 
 	if (result != PPSMC_Result_OK)
-		DRM_ERROR("Could not force DPM to low.\n");
+		DRM_DEBUG("Could not force DPM to low.\n");
 
 	WREG32_P(GENERAL_PWRMGT, 0, ~GLOBAL_PWRMGT_EN);
 
@@ -1418,7 +1418,7 @@
 int rv770_set_sw_state(struct radeon_device *rdev)
 {
 	if (rv770_send_msg_to_smc(rdev, PPSMC_MSG_SwitchToSwState) != PPSMC_Result_OK)
-		return -EINVAL;
+		DRM_DEBUG("rv770_set_sw_state failed\n");
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index e72bf46..a82b891 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2927,7 +2927,7 @@
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 },
-	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1762, 0x2015, 0, 120000 },
+	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1462, 0x2015, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x1043, 0x2015, 0, 120000 },
 	{ 0, 0, 0, 0 },
 };
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 7a9f476..265064c 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -168,7 +168,7 @@
 	struct drm_connector *connector;
 
 	drm_for_each_connector(connector, crtc->dev) {
-		if (connector && connector->state->crtc == crtc) {
+		if (connector->state->crtc == crtc) {
 			struct drm_encoder *encoder = connector->encoder;
 			struct vc4_encoder *vc4_encoder =
 				to_vc4_encoder(encoder);
@@ -401,7 +401,8 @@
 		dlist_next++;
 
 		HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
-			  (u32 *)vc4_crtc->dlist - (u32 *)vc4->hvs->dlist);
+			  (u32 __iomem *)vc4_crtc->dlist -
+			  (u32 __iomem *)vc4->hvs->dlist);
 
 		/* Make the next display list start after ours. */
 		vc4_crtc->dlist_size -= (dlist_next - vc4_crtc->dlist);
@@ -591,14 +592,14 @@
 	 * that will take too much.
 	 */
 	primary_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_PRIMARY);
-	if (!primary_plane) {
+	if (IS_ERR(primary_plane)) {
 		dev_err(dev, "failed to construct primary plane\n");
 		ret = PTR_ERR(primary_plane);
 		goto err;
 	}
 
 	cursor_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_CURSOR);
-	if (!cursor_plane) {
+	if (IS_ERR(cursor_plane)) {
 		dev_err(dev, "failed to construct cursor plane\n");
 		ret = PTR_ERR(cursor_plane);
 		goto err_primary;
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 6e73060..d5db9e0 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -259,7 +259,6 @@
 	.remove		= vc4_platform_drm_remove,
 	.driver		= {
 		.name	= "vc4-drm",
-		.owner	= THIS_MODULE,
 		.of_match_table = vc4_of_match,
 	},
 };
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index ab1673f..8098c5b 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -75,10 +75,10 @@
 	for (i = 0; i < 64; i += 4) {
 		DRM_INFO("0x%08x (%s): 0x%08x 0x%08x 0x%08x 0x%08x\n",
 			 i * 4, i < HVS_BOOTLOADER_DLIST_END ? "B" : "D",
-			 ((uint32_t *)vc4->hvs->dlist)[i + 0],
-			 ((uint32_t *)vc4->hvs->dlist)[i + 1],
-			 ((uint32_t *)vc4->hvs->dlist)[i + 2],
-			 ((uint32_t *)vc4->hvs->dlist)[i + 3]);
+			 readl((u32 __iomem *)vc4->hvs->dlist + i + 0),
+			 readl((u32 __iomem *)vc4->hvs->dlist + i + 1),
+			 readl((u32 __iomem *)vc4->hvs->dlist + i + 2),
+			 readl((u32 __iomem *)vc4->hvs->dlist + i + 3));
 	}
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index cdd8b10..887f3ca 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -70,7 +70,7 @@
 	return state->fb && state->crtc;
 }
 
-struct drm_plane_state *vc4_plane_duplicate_state(struct drm_plane *plane)
+static struct drm_plane_state *vc4_plane_duplicate_state(struct drm_plane *plane)
 {
 	struct vc4_plane_state *vc4_state;
 
@@ -97,8 +97,8 @@
 	return &vc4_state->base;
 }
 
-void vc4_plane_destroy_state(struct drm_plane *plane,
-			     struct drm_plane_state *state)
+static void vc4_plane_destroy_state(struct drm_plane *plane,
+				    struct drm_plane_state *state)
 {
 	struct vc4_plane_state *vc4_state = to_vc4_plane_state(state);
 
@@ -108,7 +108,7 @@
 }
 
 /* Called during init to allocate the plane's atomic state. */
-void vc4_plane_reset(struct drm_plane *plane)
+static void vc4_plane_reset(struct drm_plane *plane)
 {
 	struct vc4_plane_state *vc4_state;
 
@@ -157,6 +157,16 @@
 	int crtc_w = state->crtc_w;
 	int crtc_h = state->crtc_h;
 
+	if (state->crtc_w << 16 != state->src_w ||
+	    state->crtc_h << 16 != state->src_h) {
+		/* We don't support scaling yet, which involves
+		 * allocating the LBM memory for scaling temporary
+		 * storage, and putting filter kernels in the HVS
+		 * context.
+		 */
+		return -EINVAL;
+	}
+
 	if (crtc_x < 0) {
 		offset += drm_format_plane_cpp(fb->pixel_format, 0) * -crtc_x;
 		crtc_w += crtc_x;
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 8b29949..01a4f05 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2481,7 +2481,7 @@
 		if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) {
 			if (features->touch_max)
 				features->device_type |= WACOM_DEVICETYPE_TOUCH;
-			if (features->type >= INTUOSHT || features->type <= BAMBOO_PT)
+			if (features->type >= INTUOSHT && features->type <= BAMBOO_PT)
 				features->device_type |= WACOM_DEVICETYPE_PAD;
 
 			features->x_max = 4096;
@@ -3213,7 +3213,8 @@
 	  WACOM_DTU_OFFSET, WACOM_DTU_OFFSET };
 static const struct wacom_features wacom_features_0x336 =
 	{ "Wacom DTU1141", 23472, 13203, 1023, 0,
-	  DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4 };
+	  DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4,
+	  WACOM_DTU_OFFSET, WACOM_DTU_OFFSET };
 static const struct wacom_features wacom_features_0x57 =
 	{ "Wacom DTK2241", 95640, 54060, 2047, 63,
 	  DTK, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 6,
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index e24c2b6..7b0aa82 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -126,6 +126,7 @@
 	    Sunrise Point-LP (PCH)
 	    DNV (SOC)
 	    Broxton (SOC)
+	    Lewisburg (PCH)
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-i801.
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index c306751..f62d697 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -62,6 +62,8 @@
  * Sunrise Point-LP (PCH)	0x9d23	32	hard	yes	yes	yes
  * DNV (SOC)			0x19df	32	hard	yes	yes	yes
  * Broxton (SOC)		0x5ad4	32	hard	yes	yes	yes
+ * Lewisburg (PCH)		0xa1a3	32	hard	yes	yes	yes
+ * Lewisburg Supersku (PCH)	0xa223	32	hard	yes	yes	yes
  *
  * Features supported by this driver:
  * Software PEC				no
@@ -206,6 +208,8 @@
 #define PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS	0x9d23
 #define PCI_DEVICE_ID_INTEL_DNV_SMBUS			0x19df
 #define PCI_DEVICE_ID_INTEL_BROXTON_SMBUS		0x5ad4
+#define PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS		0xa1a3
+#define PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS	0xa223
 
 struct i801_mux_config {
 	char *gpio_chip;
@@ -869,6 +873,8 @@
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DNV_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BROXTON_SMBUS) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS) },
 	{ 0, }
 };
 
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 1e4d99d..9bb0b05 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -50,6 +50,7 @@
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
 #include <linux/of_gpio.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_data/i2c-imx.h>
 #include <linux/platform_device.h>
 #include <linux/sched.h>
diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c
index e23a7b0..0b20449 100644
--- a/drivers/i2c/busses/i2c-xiic.c
+++ b/drivers/i2c/busses/i2c-xiic.c
@@ -662,8 +662,10 @@
 
 static void xiic_start_xfer(struct xiic_i2c *i2c)
 {
-
+	spin_lock(&i2c->lock);
+	xiic_reinit(i2c);
 	__xiic_start_xfer(i2c);
+	spin_unlock(&i2c->lock);
 }
 
 static int xiic_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 040af5c..ba8eb08 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -715,7 +715,7 @@
 		if (wakeirq > 0 && wakeirq != client->irq)
 			status = dev_pm_set_dedicated_wake_irq(dev, wakeirq);
 		else if (client->irq > 0)
-			status = dev_pm_set_wake_irq(dev, wakeirq);
+			status = dev_pm_set_wake_irq(dev, client->irq);
 		else
 			status = 0;
 
diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c
index eea0c79..4d960d3 100644
--- a/drivers/iio/adc/ad7793.c
+++ b/drivers/iio/adc/ad7793.c
@@ -101,7 +101,7 @@
 #define AD7795_CH_AIN1M_AIN1M	8 /* AIN1(-) - AIN1(-) */
 
 /* ID Register Bit Designations (AD7793_REG_ID) */
-#define AD7785_ID		0xB
+#define AD7785_ID		0x3
 #define AD7792_ID		0xA
 #define AD7793_ID		0xB
 #define AD7794_ID		0xF
diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c
index 599cde3..b10f629 100644
--- a/drivers/iio/adc/vf610_adc.c
+++ b/drivers/iio/adc/vf610_adc.c
@@ -106,6 +106,13 @@
 
 #define DEFAULT_SAMPLE_TIME		1000
 
+/* V at 25°C of 696 mV */
+#define VF610_VTEMP25_3V0		950
+/* V at 25°C of 699 mV */
+#define VF610_VTEMP25_3V3		867
+/* Typical sensor slope coefficient at all temperatures */
+#define VF610_TEMP_SLOPE_COEFF		1840
+
 enum clk_sel {
 	VF610_ADCIOC_BUSCLK_SET,
 	VF610_ADCIOC_ALTCLK_SET,
@@ -197,6 +204,8 @@
 		adc_feature->clk_div = 8;
 	}
 
+	adck_rate = ipg_rate / adc_feature->clk_div;
+
 	/*
 	 * Determine the long sample time adder value to be used based
 	 * on the default minimum sample time provided.
@@ -221,7 +230,6 @@
 	 * BCT (Base Conversion Time): fixed to 25 ADCK cycles for 12 bit mode
 	 * LSTAdder(Long Sample Time): 3, 5, 7, 9, 13, 17, 21, 25 ADCK cycles
 	 */
-	adck_rate = ipg_rate / info->adc_feature.clk_div;
 	for (i = 0; i < ARRAY_SIZE(vf610_hw_avgs); i++)
 		info->sample_freq_avail[i] =
 			adck_rate / (6 + vf610_hw_avgs[i] *
@@ -663,11 +671,13 @@
 			break;
 		case IIO_TEMP:
 			/*
-			* Calculate in degree Celsius times 1000
-			* Using sensor slope of 1.84 mV/°C and
-			* V at 25°C of 696 mV
-			*/
-			*val = 25000 - ((int)info->value - 864) * 1000000 / 1840;
+			 * Calculate in degree Celsius times 1000
+			 * Using the typical sensor slope of 1.84 mV/°C
+			 * and VREFH_ADC at 3.3V, V at 25°C of 699 mV
+			 */
+			*val = 25000 - ((int)info->value - VF610_VTEMP25_3V3) *
+					1000000 / VF610_TEMP_SLOPE_COEFF;
+
 			break;
 		default:
 			mutex_unlock(&indio_dev->mlock);
diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c
index 0370624..02e636a 100644
--- a/drivers/iio/adc/xilinx-xadc-core.c
+++ b/drivers/iio/adc/xilinx-xadc-core.c
@@ -841,6 +841,7 @@
 			case XADC_REG_VCCINT:
 			case XADC_REG_VCCAUX:
 			case XADC_REG_VREFP:
+			case XADC_REG_VREFN:
 			case XADC_REG_VCCBRAM:
 			case XADC_REG_VCCPINT:
 			case XADC_REG_VCCPAUX:
diff --git a/drivers/iio/dac/ad5064.c b/drivers/iio/dac/ad5064.c
index 9e4d2c1..81ca008 100644
--- a/drivers/iio/dac/ad5064.c
+++ b/drivers/iio/dac/ad5064.c
@@ -113,12 +113,16 @@
 	ID_AD5065,
 	ID_AD5628_1,
 	ID_AD5628_2,
+	ID_AD5629_1,
+	ID_AD5629_2,
 	ID_AD5648_1,
 	ID_AD5648_2,
 	ID_AD5666_1,
 	ID_AD5666_2,
 	ID_AD5668_1,
 	ID_AD5668_2,
+	ID_AD5669_1,
+	ID_AD5669_2,
 };
 
 static int ad5064_write(struct ad5064_state *st, unsigned int cmd,
@@ -291,7 +295,7 @@
 	{ },
 };
 
-#define AD5064_CHANNEL(chan, addr, bits) {			\
+#define AD5064_CHANNEL(chan, addr, bits, _shift) {		\
 	.type = IIO_VOLTAGE,					\
 	.indexed = 1,						\
 	.output = 1,						\
@@ -303,36 +307,39 @@
 		.sign = 'u',					\
 		.realbits = (bits),				\
 		.storagebits = 16,				\
-		.shift = 20 - bits,				\
+		.shift = (_shift),				\
 	},							\
 	.ext_info = ad5064_ext_info,				\
 }
 
-#define DECLARE_AD5064_CHANNELS(name, bits) \
+#define DECLARE_AD5064_CHANNELS(name, bits, shift) \
 const struct iio_chan_spec name[] = { \
-	AD5064_CHANNEL(0, 0, bits), \
-	AD5064_CHANNEL(1, 1, bits), \
-	AD5064_CHANNEL(2, 2, bits), \
-	AD5064_CHANNEL(3, 3, bits), \
-	AD5064_CHANNEL(4, 4, bits), \
-	AD5064_CHANNEL(5, 5, bits), \
-	AD5064_CHANNEL(6, 6, bits), \
-	AD5064_CHANNEL(7, 7, bits), \
+	AD5064_CHANNEL(0, 0, bits, shift), \
+	AD5064_CHANNEL(1, 1, bits, shift), \
+	AD5064_CHANNEL(2, 2, bits, shift), \
+	AD5064_CHANNEL(3, 3, bits, shift), \
+	AD5064_CHANNEL(4, 4, bits, shift), \
+	AD5064_CHANNEL(5, 5, bits, shift), \
+	AD5064_CHANNEL(6, 6, bits, shift), \
+	AD5064_CHANNEL(7, 7, bits, shift), \
 }
 
-#define DECLARE_AD5065_CHANNELS(name, bits) \
+#define DECLARE_AD5065_CHANNELS(name, bits, shift) \
 const struct iio_chan_spec name[] = { \
-	AD5064_CHANNEL(0, 0, bits), \
-	AD5064_CHANNEL(1, 3, bits), \
+	AD5064_CHANNEL(0, 0, bits, shift), \
+	AD5064_CHANNEL(1, 3, bits, shift), \
 }
 
-static DECLARE_AD5064_CHANNELS(ad5024_channels, 12);
-static DECLARE_AD5064_CHANNELS(ad5044_channels, 14);
-static DECLARE_AD5064_CHANNELS(ad5064_channels, 16);
+static DECLARE_AD5064_CHANNELS(ad5024_channels, 12, 8);
+static DECLARE_AD5064_CHANNELS(ad5044_channels, 14, 6);
+static DECLARE_AD5064_CHANNELS(ad5064_channels, 16, 4);
 
-static DECLARE_AD5065_CHANNELS(ad5025_channels, 12);
-static DECLARE_AD5065_CHANNELS(ad5045_channels, 14);
-static DECLARE_AD5065_CHANNELS(ad5065_channels, 16);
+static DECLARE_AD5065_CHANNELS(ad5025_channels, 12, 8);
+static DECLARE_AD5065_CHANNELS(ad5045_channels, 14, 6);
+static DECLARE_AD5065_CHANNELS(ad5065_channels, 16, 4);
+
+static DECLARE_AD5064_CHANNELS(ad5629_channels, 12, 4);
+static DECLARE_AD5064_CHANNELS(ad5669_channels, 16, 0);
 
 static const struct ad5064_chip_info ad5064_chip_info_tbl[] = {
 	[ID_AD5024] = {
@@ -382,6 +389,18 @@
 		.channels = ad5024_channels,
 		.num_channels = 8,
 	},
+	[ID_AD5629_1] = {
+		.shared_vref = true,
+		.internal_vref = 2500000,
+		.channels = ad5629_channels,
+		.num_channels = 8,
+	},
+	[ID_AD5629_2] = {
+		.shared_vref = true,
+		.internal_vref = 5000000,
+		.channels = ad5629_channels,
+		.num_channels = 8,
+	},
 	[ID_AD5648_1] = {
 		.shared_vref = true,
 		.internal_vref = 2500000,
@@ -418,6 +437,18 @@
 		.channels = ad5064_channels,
 		.num_channels = 8,
 	},
+	[ID_AD5669_1] = {
+		.shared_vref = true,
+		.internal_vref = 2500000,
+		.channels = ad5669_channels,
+		.num_channels = 8,
+	},
+	[ID_AD5669_2] = {
+		.shared_vref = true,
+		.internal_vref = 5000000,
+		.channels = ad5669_channels,
+		.num_channels = 8,
+	},
 };
 
 static inline unsigned int ad5064_num_vref(struct ad5064_state *st)
@@ -597,10 +628,16 @@
 	unsigned int addr, unsigned int val)
 {
 	struct i2c_client *i2c = to_i2c_client(st->dev);
+	int ret;
 
 	st->data.i2c[0] = (cmd << 4) | addr;
 	put_unaligned_be16(val, &st->data.i2c[1]);
-	return i2c_master_send(i2c, st->data.i2c, 3);
+
+	ret = i2c_master_send(i2c, st->data.i2c, 3);
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 static int ad5064_i2c_probe(struct i2c_client *i2c,
@@ -616,12 +653,12 @@
 }
 
 static const struct i2c_device_id ad5064_i2c_ids[] = {
-	{"ad5629-1", ID_AD5628_1},
-	{"ad5629-2", ID_AD5628_2},
-	{"ad5629-3", ID_AD5628_2}, /* similar enough to ad5629-2 */
-	{"ad5669-1", ID_AD5668_1},
-	{"ad5669-2", ID_AD5668_2},
-	{"ad5669-3", ID_AD5668_2}, /* similar enough to ad5669-2 */
+	{"ad5629-1", ID_AD5629_1},
+	{"ad5629-2", ID_AD5629_2},
+	{"ad5629-3", ID_AD5629_2}, /* similar enough to ad5629-2 */
+	{"ad5669-1", ID_AD5669_1},
+	{"ad5669-2", ID_AD5669_2},
+	{"ad5669-3", ID_AD5669_2}, /* similar enough to ad5669-2 */
 	{}
 };
 MODULE_DEVICE_TABLE(i2c, ad5064_i2c_ids);
diff --git a/drivers/iio/humidity/si7020.c b/drivers/iio/humidity/si7020.c
index 12128d1..71991b5 100644
--- a/drivers/iio/humidity/si7020.c
+++ b/drivers/iio/humidity/si7020.c
@@ -50,10 +50,10 @@
 
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
-		ret = i2c_smbus_read_word_data(*client,
-					       chan->type == IIO_TEMP ?
-					       SI7020CMD_TEMP_HOLD :
-					       SI7020CMD_RH_HOLD);
+		ret = i2c_smbus_read_word_swapped(*client,
+						  chan->type == IIO_TEMP ?
+						  SI7020CMD_TEMP_HOLD :
+						  SI7020CMD_RH_HOLD);
 		if (ret < 0)
 			return ret;
 		*val = ret >> 2;
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
index 44a077f..f174ce0 100644
--- a/drivers/irqchip/irq-gic-common.c
+++ b/drivers/irqchip/irq-gic-common.c
@@ -84,12 +84,15 @@
 		writel_relaxed(GICD_INT_DEF_PRI_X4, base + GIC_DIST_PRI + i);
 
 	/*
-	 * Disable all interrupts.  Leave the PPI and SGIs alone
-	 * as they are enabled by redistributor registers.
+	 * Deactivate and disable all SPIs. Leave the PPI and SGIs
+	 * alone as they are in the redistributor registers on GICv3.
 	 */
-	for (i = 32; i < gic_irqs; i += 32)
+	for (i = 32; i < gic_irqs; i += 32) {
 		writel_relaxed(GICD_INT_EN_CLR_X32,
-					base + GIC_DIST_ENABLE_CLEAR + i / 8);
+			       base + GIC_DIST_ACTIVE_CLEAR + i / 8);
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+			       base + GIC_DIST_ENABLE_CLEAR + i / 8);
+	}
 
 	if (sync_access)
 		sync_access();
@@ -102,7 +105,9 @@
 	/*
 	 * Deal with the banked PPI and SGI interrupts - disable all
 	 * PPI interrupts, ensure all SGI interrupts are enabled.
+	 * Make sure everything is deactivated.
 	 */
+	writel_relaxed(GICD_INT_EN_CLR_X32, base + GIC_DIST_ACTIVE_CLEAR);
 	writel_relaxed(GICD_INT_EN_CLR_PPI, base + GIC_DIST_ENABLE_CLEAR);
 	writel_relaxed(GICD_INT_EN_SET_SGI, base + GIC_DIST_ENABLE_SET);
 
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 515c823..abf2ffa 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -73,9 +73,11 @@
 	union gic_base cpu_base;
 #ifdef CONFIG_CPU_PM
 	u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)];
+	u32 saved_spi_active[DIV_ROUND_UP(1020, 32)];
 	u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)];
 	u32 saved_spi_target[DIV_ROUND_UP(1020, 4)];
 	u32 __percpu *saved_ppi_enable;
+	u32 __percpu *saved_ppi_active;
 	u32 __percpu *saved_ppi_conf;
 #endif
 	struct irq_domain *domain;
@@ -566,6 +568,10 @@
 	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
 		gic_data[gic_nr].saved_spi_enable[i] =
 			readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+		gic_data[gic_nr].saved_spi_active[i] =
+			readl_relaxed(dist_base + GIC_DIST_ACTIVE_SET + i * 4);
 }
 
 /*
@@ -604,9 +610,19 @@
 		writel_relaxed(gic_data[gic_nr].saved_spi_target[i],
 			dist_base + GIC_DIST_TARGET + i * 4);
 
-	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++)
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) {
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+			dist_base + GIC_DIST_ENABLE_CLEAR + i * 4);
 		writel_relaxed(gic_data[gic_nr].saved_spi_enable[i],
 			dist_base + GIC_DIST_ENABLE_SET + i * 4);
+	}
+
+	for (i = 0; i < DIV_ROUND_UP(gic_irqs, 32); i++) {
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+			dist_base + GIC_DIST_ACTIVE_CLEAR + i * 4);
+		writel_relaxed(gic_data[gic_nr].saved_spi_active[i],
+			dist_base + GIC_DIST_ACTIVE_SET + i * 4);
+	}
 
 	writel_relaxed(GICD_ENABLE, dist_base + GIC_DIST_CTRL);
 }
@@ -631,6 +647,10 @@
 	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
 		ptr[i] = readl_relaxed(dist_base + GIC_DIST_ENABLE_SET + i * 4);
 
+	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_active);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+		ptr[i] = readl_relaxed(dist_base + GIC_DIST_ACTIVE_SET + i * 4);
+
 	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
 	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
 		ptr[i] = readl_relaxed(dist_base + GIC_DIST_CONFIG + i * 4);
@@ -654,8 +674,18 @@
 		return;
 
 	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_enable);
-	for (i = 0; i < DIV_ROUND_UP(32, 32); i++)
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++) {
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+			       dist_base + GIC_DIST_ENABLE_CLEAR + i * 4);
 		writel_relaxed(ptr[i], dist_base + GIC_DIST_ENABLE_SET + i * 4);
+	}
+
+	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_active);
+	for (i = 0; i < DIV_ROUND_UP(32, 32); i++) {
+		writel_relaxed(GICD_INT_EN_CLR_X32,
+			       dist_base + GIC_DIST_ACTIVE_CLEAR + i * 4);
+		writel_relaxed(ptr[i], dist_base + GIC_DIST_ACTIVE_SET + i * 4);
+	}
 
 	ptr = raw_cpu_ptr(gic_data[gic_nr].saved_ppi_conf);
 	for (i = 0; i < DIV_ROUND_UP(32, 16); i++)
@@ -710,6 +740,10 @@
 		sizeof(u32));
 	BUG_ON(!gic->saved_ppi_enable);
 
+	gic->saved_ppi_active = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4,
+		sizeof(u32));
+	BUG_ON(!gic->saved_ppi_active);
+
 	gic->saved_ppi_conf = __alloc_percpu(DIV_ROUND_UP(32, 16) * 4,
 		sizeof(u32));
 	BUG_ON(!gic->saved_ppi_conf);
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index f659e60..5178645 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -160,11 +160,6 @@
 }
 EXPORT_SYMBOL(nvm_erase_blk);
 
-static void nvm_core_free(struct nvm_dev *dev)
-{
-	kfree(dev);
-}
-
 static int nvm_core_init(struct nvm_dev *dev)
 {
 	struct nvm_id *id = &dev->identity;
@@ -179,12 +174,21 @@
 	dev->sec_size = grp->csecs;
 	dev->oob_size = grp->sos;
 	dev->sec_per_pg = grp->fpg_sz / grp->csecs;
-	dev->addr_mode = id->ppat;
-	dev->addr_format = id->ppaf;
+	memcpy(&dev->ppaf, &id->ppaf, sizeof(struct nvm_addr_format));
 
 	dev->plane_mode = NVM_PLANE_SINGLE;
 	dev->max_rq_size = dev->ops->max_phys_sect * dev->sec_size;
 
+	if (grp->mtype != 0) {
+		pr_err("nvm: memory type not supported\n");
+		return -EINVAL;
+	}
+
+	if (grp->fmtype != 0 && grp->fmtype != 1) {
+		pr_err("nvm: flash type not supported\n");
+		return -EINVAL;
+	}
+
 	if (grp->mpos & 0x020202)
 		dev->plane_mode = NVM_PLANE_DOUBLE;
 	if (grp->mpos & 0x040404)
@@ -213,21 +217,18 @@
 
 	if (dev->mt)
 		dev->mt->unregister_mgr(dev);
-
-	nvm_core_free(dev);
 }
 
 static int nvm_init(struct nvm_dev *dev)
 {
 	struct nvmm_type *mt;
-	int ret = 0;
+	int ret = -EINVAL;
 
 	if (!dev->q || !dev->ops)
-		return -EINVAL;
+		return ret;
 
 	if (dev->ops->identity(dev->q, &dev->identity)) {
 		pr_err("nvm: device could not be identified\n");
-		ret = -EINVAL;
 		goto err;
 	}
 
@@ -273,7 +274,6 @@
 			dev->nr_chnls);
 	return 0;
 err:
-	nvm_free(dev);
 	pr_err("nvm: failed to initialize nvm\n");
 	return ret;
 }
@@ -308,22 +308,24 @@
 	if (ret)
 		goto err_init;
 
-	down_write(&nvm_lock);
-	list_add(&dev->devices, &nvm_devices);
-	up_write(&nvm_lock);
-
 	if (dev->ops->max_phys_sect > 1) {
 		dev->ppalist_pool = dev->ops->create_dma_pool(dev->q,
 								"ppalist");
 		if (!dev->ppalist_pool) {
 			pr_err("nvm: could not create ppa pool\n");
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto err_init;
 		}
 	} else if (dev->ops->max_phys_sect > 256) {
 		pr_info("nvm: max sectors supported is 256.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_init;
 	}
 
+	down_write(&nvm_lock);
+	list_add(&dev->devices, &nvm_devices);
+	up_write(&nvm_lock);
+
 	return 0;
 err_init:
 	kfree(dev);
@@ -341,11 +343,12 @@
 		return;
 	}
 
-	nvm_exit(dev);
-
 	down_write(&nvm_lock);
 	list_del(&dev->devices);
 	up_write(&nvm_lock);
+
+	nvm_exit(dev);
+	kfree(dev);
 }
 EXPORT_SYMBOL(nvm_unregister);
 
@@ -457,11 +460,11 @@
 	lockdep_assert_held(&nvm_lock);
 
 	del_gendisk(tdisk);
+	blk_cleanup_queue(q);
+
 	if (tt->exit)
 		tt->exit(tdisk->private_data);
 
-	blk_cleanup_queue(q);
-
 	put_disk(tdisk);
 
 	list_del(&t->list);
@@ -541,7 +544,7 @@
 	if (!dev->mt)
 		return 0;
 
-	dev->mt->free_blocks_print(dev);
+	dev->mt->lun_info_print(dev);
 
 	return 0;
 }
diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index ae1fb2b..e20e74e 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -60,23 +60,28 @@
 		lun->vlun.lun_id = i % dev->luns_per_chnl;
 		lun->vlun.chnl_id = i / dev->luns_per_chnl;
 		lun->vlun.nr_free_blocks = dev->blks_per_lun;
+		lun->vlun.nr_inuse_blocks = 0;
+		lun->vlun.nr_bad_blocks = 0;
 	}
 	return 0;
 }
 
-static int gennvm_block_bb(u32 lun_id, void *bb_bitmap, unsigned int nr_blocks,
+static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks,
 								void *private)
 {
 	struct gen_nvm *gn = private;
-	struct gen_lun *lun = &gn->luns[lun_id];
+	struct nvm_dev *dev = gn->dev;
+	struct gen_lun *lun;
 	struct nvm_block *blk;
 	int i;
 
-	if (unlikely(bitmap_empty(bb_bitmap, nr_blocks)))
-		return 0;
+	ppa = dev_to_generic_addr(gn->dev, ppa);
+	lun = &gn->luns[(dev->nr_luns * ppa.g.ch) + ppa.g.lun];
 
-	i = -1;
-	while ((i = find_next_bit(bb_bitmap, nr_blocks, i + 1)) < nr_blocks) {
+	for (i = 0; i < nr_blocks; i++) {
+		if (blks[i] == 0)
+			continue;
+
 		blk = &lun->vlun.blocks[i];
 		if (!blk) {
 			pr_err("gennvm: BB data is out of bounds.\n");
@@ -84,6 +89,7 @@
 		}
 
 		list_move_tail(&blk->list, &lun->bb_list);
+		lun->vlun.nr_bad_blocks++;
 	}
 
 	return 0;
@@ -136,6 +142,7 @@
 			list_move_tail(&blk->list, &lun->used_list);
 			blk->type = 1;
 			lun->vlun.nr_free_blocks--;
+			lun->vlun.nr_inuse_blocks++;
 		}
 	}
 
@@ -164,15 +171,25 @@
 			block->id = cur_block_id++;
 
 			/* First block is reserved for device */
-			if (unlikely(lun_iter == 0 && blk_iter == 0))
+			if (unlikely(lun_iter == 0 && blk_iter == 0)) {
+				lun->vlun.nr_free_blocks--;
 				continue;
+			}
 
 			list_add_tail(&block->list, &lun->free_list);
 		}
 
 		if (dev->ops->get_bb_tbl) {
-			ret = dev->ops->get_bb_tbl(dev->q, lun->vlun.id,
-					dev->blks_per_lun, gennvm_block_bb, gn);
+			struct ppa_addr ppa;
+
+			ppa.ppa = 0;
+			ppa.g.ch = lun->vlun.chnl_id;
+			ppa.g.lun = lun->vlun.id;
+			ppa = generic_to_dev_addr(dev, ppa);
+
+			ret = dev->ops->get_bb_tbl(dev->q, ppa,
+						dev->blks_per_lun,
+						gennvm_block_bb, gn);
 			if (ret)
 				pr_err("gennvm: could not read BB table\n");
 		}
@@ -199,6 +216,7 @@
 	if (!gn)
 		return -ENOMEM;
 
+	gn->dev = dev;
 	gn->nr_luns = dev->nr_luns;
 	dev->mp = gn;
 
@@ -254,6 +272,7 @@
 	blk->type = 1;
 
 	lun->vlun.nr_free_blocks--;
+	lun->vlun.nr_inuse_blocks++;
 
 	spin_unlock(&vlun->lock);
 out:
@@ -271,16 +290,21 @@
 	case 1:
 		list_move_tail(&blk->list, &lun->free_list);
 		lun->vlun.nr_free_blocks++;
+		lun->vlun.nr_inuse_blocks--;
 		blk->type = 0;
 		break;
 	case 2:
 		list_move_tail(&blk->list, &lun->bb_list);
+		lun->vlun.nr_bad_blocks++;
+		lun->vlun.nr_inuse_blocks--;
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		pr_err("gennvm: erroneous block type (%lu -> %u)\n",
 							blk->id, blk->type);
 		list_move_tail(&blk->list, &lun->bb_list);
+		lun->vlun.nr_bad_blocks++;
+		lun->vlun.nr_inuse_blocks--;
 	}
 
 	spin_unlock(&vlun->lock);
@@ -292,10 +316,10 @@
 
 	if (rqd->nr_pages > 1) {
 		for (i = 0; i < rqd->nr_pages; i++)
-			rqd->ppa_list[i] = addr_to_generic_mode(dev,
+			rqd->ppa_list[i] = dev_to_generic_addr(dev,
 							rqd->ppa_list[i]);
 	} else {
-		rqd->ppa_addr = addr_to_generic_mode(dev, rqd->ppa_addr);
+		rqd->ppa_addr = dev_to_generic_addr(dev, rqd->ppa_addr);
 	}
 }
 
@@ -305,10 +329,10 @@
 
 	if (rqd->nr_pages > 1) {
 		for (i = 0; i < rqd->nr_pages; i++)
-			rqd->ppa_list[i] = generic_to_addr_mode(dev,
+			rqd->ppa_list[i] = generic_to_dev_addr(dev,
 							rqd->ppa_list[i]);
 	} else {
-		rqd->ppa_addr = generic_to_addr_mode(dev, rqd->ppa_addr);
+		rqd->ppa_addr = generic_to_dev_addr(dev, rqd->ppa_addr);
 	}
 }
 
@@ -354,10 +378,10 @@
 {
 	int i;
 
-	if (!dev->ops->set_bb)
+	if (!dev->ops->set_bb_tbl)
 		return;
 
-	if (dev->ops->set_bb(dev->q, rqd, 1))
+	if (dev->ops->set_bb_tbl(dev->q, rqd, 1))
 		return;
 
 	gennvm_addr_to_generic_mode(dev, rqd);
@@ -440,15 +464,24 @@
 	return &gn->luns[lunid].vlun;
 }
 
-static void gennvm_free_blocks_print(struct nvm_dev *dev)
+static void gennvm_lun_info_print(struct nvm_dev *dev)
 {
 	struct gen_nvm *gn = dev->mp;
 	struct gen_lun *lun;
 	unsigned int i;
 
-	gennvm_for_each_lun(gn, lun, i)
-		pr_info("%s: lun%8u\t%u\n",
-					dev->name, i, lun->vlun.nr_free_blocks);
+
+	gennvm_for_each_lun(gn, lun, i) {
+		spin_lock(&lun->vlun.lock);
+
+		pr_info("%s: lun%8u\t%u\t%u\t%u\n",
+				dev->name, i,
+				lun->vlun.nr_free_blocks,
+				lun->vlun.nr_inuse_blocks,
+				lun->vlun.nr_bad_blocks);
+
+		spin_unlock(&lun->vlun.lock);
+	}
 }
 
 static struct nvmm_type gennvm = {
@@ -466,7 +499,7 @@
 	.erase_blk	= gennvm_erase_blk,
 
 	.get_lun	= gennvm_get_lun,
-	.free_blocks_print = gennvm_free_blocks_print,
+	.lun_info_print = gennvm_lun_info_print,
 };
 
 static int __init gennvm_module_init(void)
diff --git a/drivers/lightnvm/gennvm.h b/drivers/lightnvm/gennvm.h
index d23bd35..9c24b5b 100644
--- a/drivers/lightnvm/gennvm.h
+++ b/drivers/lightnvm/gennvm.h
@@ -35,6 +35,8 @@
 };
 
 struct gen_nvm {
+	struct nvm_dev *dev;
+
 	int nr_luns;
 	struct gen_lun *luns;
 };
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index 7ba64c8..75e59c3 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -123,12 +123,42 @@
 	return blk->id * rrpc->dev->pgs_per_blk;
 }
 
+static struct ppa_addr linear_to_generic_addr(struct nvm_dev *dev,
+							struct ppa_addr r)
+{
+	struct ppa_addr l;
+	int secs, pgs, blks, luns;
+	sector_t ppa = r.ppa;
+
+	l.ppa = 0;
+
+	div_u64_rem(ppa, dev->sec_per_pg, &secs);
+	l.g.sec = secs;
+
+	sector_div(ppa, dev->sec_per_pg);
+	div_u64_rem(ppa, dev->sec_per_blk, &pgs);
+	l.g.pg = pgs;
+
+	sector_div(ppa, dev->pgs_per_blk);
+	div_u64_rem(ppa, dev->blks_per_lun, &blks);
+	l.g.blk = blks;
+
+	sector_div(ppa, dev->blks_per_lun);
+	div_u64_rem(ppa, dev->luns_per_chnl, &luns);
+	l.g.lun = luns;
+
+	sector_div(ppa, dev->luns_per_chnl);
+	l.g.ch = ppa;
+
+	return l;
+}
+
 static struct ppa_addr rrpc_ppa_to_gaddr(struct nvm_dev *dev, u64 addr)
 {
 	struct ppa_addr paddr;
 
 	paddr.ppa = addr;
-	return __linear_to_generic_addr(dev, paddr);
+	return linear_to_generic_addr(dev, paddr);
 }
 
 /* requires lun->lock taken */
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 917d47e..3147c8d 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -112,7 +112,8 @@
  * and encrypts / decrypts at the same time.
  */
 enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
-	     DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD };
+	     DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD,
+	     DM_CRYPT_EXIT_THREAD};
 
 /*
  * The fields in here must be read only after initialization.
@@ -1203,20 +1204,18 @@
 		if (!RB_EMPTY_ROOT(&cc->write_tree))
 			goto pop_from_list;
 
+		if (unlikely(test_bit(DM_CRYPT_EXIT_THREAD, &cc->flags))) {
+			spin_unlock_irq(&cc->write_thread_wait.lock);
+			break;
+		}
+
 		__set_current_state(TASK_INTERRUPTIBLE);
 		__add_wait_queue(&cc->write_thread_wait, &wait);
 
 		spin_unlock_irq(&cc->write_thread_wait.lock);
 
-		if (unlikely(kthread_should_stop())) {
-			set_task_state(current, TASK_RUNNING);
-			remove_wait_queue(&cc->write_thread_wait, &wait);
-			break;
-		}
-
 		schedule();
 
-		set_task_state(current, TASK_RUNNING);
 		spin_lock_irq(&cc->write_thread_wait.lock);
 		__remove_wait_queue(&cc->write_thread_wait, &wait);
 		goto continue_locked;
@@ -1531,8 +1530,13 @@
 	if (!cc)
 		return;
 
-	if (cc->write_thread)
+	if (cc->write_thread) {
+		spin_lock_irq(&cc->write_thread_wait.lock);
+		set_bit(DM_CRYPT_EXIT_THREAD, &cc->flags);
+		wake_up_locked(&cc->write_thread_wait);
+		spin_unlock_irq(&cc->write_thread_wait.lock);
 		kthread_stop(cc->write_thread);
+	}
 
 	if (cc->io_queue)
 		destroy_workqueue(cc->io_queue);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index aaa6caa..cfa29f5 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1537,32 +1537,34 @@
 		struct block_device **bdev, fmode_t *mode)
 {
 	struct multipath *m = ti->private;
-	struct pgpath *pgpath;
 	unsigned long flags;
 	int r;
 
-	r = 0;
-
 	spin_lock_irqsave(&m->lock, flags);
 
 	if (!m->current_pgpath)
 		__choose_pgpath(m, 0);
 
-	pgpath = m->current_pgpath;
-
-	if (pgpath) {
-		*bdev = pgpath->path.dev->bdev;
-		*mode = pgpath->path.dev->mode;
+	if (m->current_pgpath) {
+		if (!m->queue_io) {
+			*bdev = m->current_pgpath->path.dev->bdev;
+			*mode = m->current_pgpath->path.dev->mode;
+			r = 0;
+		} else {
+			/* pg_init has not started or completed */
+			r = -ENOTCONN;
+		}
+	} else {
+		/* No path is available */
+		if (m->queue_if_no_path)
+			r = -ENOTCONN;
+		else
+			r = -EIO;
 	}
 
-	if ((pgpath && m->queue_io) || (!pgpath && m->queue_if_no_path))
-		r = -ENOTCONN;
-	else if (!*bdev)
-		r = -EIO;
-
 	spin_unlock_irqrestore(&m->lock, flags);
 
-	if (r == -ENOTCONN && !fatal_signal_pending(current)) {
+	if (r == -ENOTCONN) {
 		spin_lock_irqsave(&m->lock, flags);
 		if (!m->current_pg) {
 			/* Path status changed, redo selection */
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 3897b90..63903a5 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2432,6 +2432,7 @@
 	case PM_WRITE:
 		if (old_mode != new_mode)
 			notify_of_pool_mode_change(pool, "write");
+		pool->pf.error_if_no_space = pt->requested_pf.error_if_no_space;
 		dm_pool_metadata_read_write(pool->pmd);
 		pool->process_bio = process_bio;
 		pool->process_discard = process_discard_bio;
@@ -4249,10 +4250,9 @@
 {
 	struct thin_c *tc = ti->private;
 	struct pool *pool = tc->pool;
-	struct queue_limits *pool_limits = dm_get_queue_limits(pool->pool_md);
 
-	if (!pool_limits->discard_granularity)
-		return; /* pool's discard support is disabled */
+	if (!pool->pf.discard_enabled)
+		return;
 
 	limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
 	limits->max_discard_sectors = 2048 * 1024 * 16; /* 16G */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6e15f35..5df4048 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -591,7 +591,7 @@
 
 out:
 	dm_put_live_table(md, *srcu_idx);
-	if (r == -ENOTCONN) {
+	if (r == -ENOTCONN && !fatal_signal_pending(current)) {
 		msleep(10);
 		goto retry;
 	}
@@ -603,9 +603,10 @@
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	struct dm_target *tgt;
+	struct block_device *tgt_bdev = NULL;
 	int srcu_idx, r;
 
-	r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+	r = dm_get_live_table_for_ioctl(md, &tgt, &tgt_bdev, &mode, &srcu_idx);
 	if (r < 0)
 		return r;
 
@@ -620,7 +621,7 @@
 			goto out;
 	}
 
-	r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+	r =  __blkdev_driver_ioctl(tgt_bdev, mode, cmd, arg);
 out:
 	dm_put_live_table(md, srcu_idx);
 	return r;
diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c
index 35759a9..e8f8472 100644
--- a/drivers/media/pci/cx23885/cx23885-core.c
+++ b/drivers/media/pci/cx23885/cx23885-core.c
@@ -1992,9 +1992,9 @@
 		(unsigned long long)pci_resource_start(pci_dev, 0));
 
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev, 0xffffffff)) {
+	err = pci_set_dma_mask(pci_dev, 0xffffffff);
+	if (err) {
 		printk("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name);
-		err = -EIO;
 		goto fail_context;
 	}
 
diff --git a/drivers/media/pci/cx25821/cx25821-core.c b/drivers/media/pci/cx25821/cx25821-core.c
index dbc695f..0042803 100644
--- a/drivers/media/pci/cx25821/cx25821-core.c
+++ b/drivers/media/pci/cx25821/cx25821-core.c
@@ -1319,7 +1319,8 @@
 		dev->pci_lat, (unsigned long long)dev->base_io_addr);
 
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev, 0xffffffff)) {
+	err = pci_set_dma_mask(pci_dev, 0xffffffff);
+	if (err) {
 		pr_err("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name);
 		err = -EIO;
 		goto fail_irq;
diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c
index 0ed1b65..1b5268f 100644
--- a/drivers/media/pci/cx88/cx88-alsa.c
+++ b/drivers/media/pci/cx88/cx88-alsa.c
@@ -890,9 +890,9 @@
 		return err;
 	}
 
-	if (!pci_set_dma_mask(pci,DMA_BIT_MASK(32))) {
+	err = pci_set_dma_mask(pci,DMA_BIT_MASK(32));
+	if (err) {
 		dprintk(0, "%s/1: Oops: no 32bit PCI DMA ???\n",core->name);
-		err = -EIO;
 		cx88_core_put(core, pci);
 		return err;
 	}
diff --git a/drivers/media/pci/cx88/cx88-mpeg.c b/drivers/media/pci/cx88/cx88-mpeg.c
index 9db7767..f34c229 100644
--- a/drivers/media/pci/cx88/cx88-mpeg.c
+++ b/drivers/media/pci/cx88/cx88-mpeg.c
@@ -393,7 +393,8 @@
 	if (pci_enable_device(dev->pci))
 		return -EIO;
 	pci_set_master(dev->pci);
-	if (!pci_set_dma_mask(dev->pci,DMA_BIT_MASK(32))) {
+	err = pci_set_dma_mask(dev->pci,DMA_BIT_MASK(32));
+	if (err) {
 		printk("%s/2: Oops: no 32bit PCI DMA ???\n",dev->core->name);
 		return -EIO;
 	}
diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c
index 0de1ad5..aef9acf 100644
--- a/drivers/media/pci/cx88/cx88-video.c
+++ b/drivers/media/pci/cx88/cx88-video.c
@@ -1314,9 +1314,9 @@
 	       dev->pci_lat,(unsigned long long)pci_resource_start(pci_dev,0));
 
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev,DMA_BIT_MASK(32))) {
+	err = pci_set_dma_mask(pci_dev,DMA_BIT_MASK(32));
+	if (err) {
 		printk("%s/0: Oops: no 32bit PCI DMA ???\n",core->name);
-		err = -EIO;
 		goto fail_core;
 	}
 	dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev);
diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
index 60b2d46..3fdbd81 100644
--- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
+++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c
@@ -810,7 +810,7 @@
 		"%s(): board vendor 0x%x, revision 0x%x\n",
 		__func__, board_vendor, board_revision);
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev, 0xffffffff)) {
+	if (pci_set_dma_mask(pci_dev, 0xffffffff) < 0) {
 		dev_err(&pci_dev->dev,
 			"%s(): 32bit PCI DMA is not supported\n", __func__);
 		goto pci_detect_err;
diff --git a/drivers/media/pci/saa7134/saa7134-core.c b/drivers/media/pci/saa7134/saa7134-core.c
index e79d63e..f720cea 100644
--- a/drivers/media/pci/saa7134/saa7134-core.c
+++ b/drivers/media/pci/saa7134/saa7134-core.c
@@ -951,9 +951,9 @@
 	       pci_name(pci_dev), dev->pci_rev, pci_dev->irq,
 	       dev->pci_lat,(unsigned long long)pci_resource_start(pci_dev,0));
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32))) {
+	err = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32));
+	if (err) {
 		pr_warn("%s: Oops: no 32bit PCI DMA ???\n", dev->name);
-		err = -EIO;
 		goto fail1;
 	}
 
diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c
index 8f36b48..8bbd092 100644
--- a/drivers/media/pci/saa7164/saa7164-core.c
+++ b/drivers/media/pci/saa7164/saa7164-core.c
@@ -1264,9 +1264,9 @@
 
 	pci_set_master(pci_dev);
 	/* TODO */
-	if (!pci_set_dma_mask(pci_dev, 0xffffffff)) {
+	err = pci_set_dma_mask(pci_dev, 0xffffffff);
+	if (err) {
 		printk("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name);
-		err = -EIO;
 		goto fail_irq;
 	}
 
diff --git a/drivers/media/pci/tw68/tw68-core.c b/drivers/media/pci/tw68/tw68-core.c
index 8c5655d..4e77618 100644
--- a/drivers/media/pci/tw68/tw68-core.c
+++ b/drivers/media/pci/tw68/tw68-core.c
@@ -257,9 +257,9 @@
 		dev->name, pci_name(pci_dev), dev->pci_rev, pci_dev->irq,
 		dev->pci_lat, (u64)pci_resource_start(pci_dev, 0));
 	pci_set_master(pci_dev);
-	if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32))) {
+	err = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32));
+	if (err) {
 		pr_info("%s: Oops: no 32bit PCI DMA ???\n", dev->name);
-		err = -EIO;
 		goto fail1;
 	}
 
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 23b6c8e..d848616 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -65,8 +65,7 @@
 #define MMC_SANITIZE_REQ_TIMEOUT 240000
 #define MMC_EXTRACT_INDEX_FROM_ARG(x) ((x & 0x00FF0000) >> 16)
 
-#define mmc_req_rel_wr(req)	(((req->cmd_flags & REQ_FUA) || \
-				  (req->cmd_flags & REQ_META)) && \
+#define mmc_req_rel_wr(req)	((req->cmd_flags & REQ_FUA) && \
 				  (rq_data_dir(req) == WRITE))
 #define PACKED_CMD_VER	0x01
 #define PACKED_CMD_WR	0x02
@@ -1467,13 +1466,9 @@
 
 	/*
 	 * Reliable writes are used to implement Forced Unit Access and
-	 * REQ_META accesses, and are supported only on MMCs.
-	 *
-	 * XXX: this really needs a good explanation of why REQ_META
-	 * is treated special.
+	 * are supported only on MMCs.
 	 */
-	bool do_rel_wr = ((req->cmd_flags & REQ_FUA) ||
-			  (req->cmd_flags & REQ_META)) &&
+	bool do_rel_wr = (req->cmd_flags & REQ_FUA) &&
 		(rq_data_dir(req) == WRITE) &&
 		(md->flags & MMC_BLK_REL_WR);
 
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index c793fda..3a9a79e 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1040,71 +1040,6 @@
 	return err;
 }
 
-static int mmc_select_hs400(struct mmc_card *card)
-{
-	struct mmc_host *host = card->host;
-	int err = 0;
-	u8 val;
-
-	/*
-	 * HS400 mode requires 8-bit bus width
-	 */
-	if (!(card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS400 &&
-	      host->ios.bus_width == MMC_BUS_WIDTH_8))
-		return 0;
-
-	/*
-	 * Before switching to dual data rate operation for HS400,
-	 * it is required to convert from HS200 mode to HS mode.
-	 */
-	mmc_set_timing(card->host, MMC_TIMING_MMC_HS);
-	mmc_set_bus_speed(card);
-
-	val = EXT_CSD_TIMING_HS |
-	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
-	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-			   EXT_CSD_HS_TIMING, val,
-			   card->ext_csd.generic_cmd6_time,
-			   true, true, true);
-	if (err) {
-		pr_err("%s: switch to high-speed from hs200 failed, err:%d\n",
-			mmc_hostname(host), err);
-		return err;
-	}
-
-	err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-			 EXT_CSD_BUS_WIDTH,
-			 EXT_CSD_DDR_BUS_WIDTH_8,
-			 card->ext_csd.generic_cmd6_time);
-	if (err) {
-		pr_err("%s: switch to bus width for hs400 failed, err:%d\n",
-			mmc_hostname(host), err);
-		return err;
-	}
-
-	val = EXT_CSD_TIMING_HS400 |
-	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
-	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-			   EXT_CSD_HS_TIMING, val,
-			   card->ext_csd.generic_cmd6_time,
-			   true, true, true);
-	if (err) {
-		pr_err("%s: switch to hs400 failed, err:%d\n",
-			 mmc_hostname(host), err);
-		return err;
-	}
-
-	mmc_set_timing(host, MMC_TIMING_MMC_HS400);
-	mmc_set_bus_speed(card);
-
-	return 0;
-}
-
-int mmc_hs200_to_hs400(struct mmc_card *card)
-{
-	return mmc_select_hs400(card);
-}
-
 /* Caller must hold re-tuning */
 static int mmc_switch_status(struct mmc_card *card)
 {
@@ -1118,6 +1053,97 @@
 	return mmc_switch_status_error(card->host, status);
 }
 
+static int mmc_select_hs400(struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	bool send_status = true;
+	unsigned int max_dtr;
+	int err = 0;
+	u8 val;
+
+	/*
+	 * HS400 mode requires 8-bit bus width
+	 */
+	if (!(card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS400 &&
+	      host->ios.bus_width == MMC_BUS_WIDTH_8))
+		return 0;
+
+	if (host->caps & MMC_CAP_WAIT_WHILE_BUSY)
+		send_status = false;
+
+	/* Reduce frequency to HS frequency */
+	max_dtr = card->ext_csd.hs_max_dtr;
+	mmc_set_clock(host, max_dtr);
+
+	/* Switch card to HS mode */
+	val = EXT_CSD_TIMING_HS |
+	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+			   EXT_CSD_HS_TIMING, val,
+			   card->ext_csd.generic_cmd6_time,
+			   true, send_status, true);
+	if (err) {
+		pr_err("%s: switch to high-speed from hs200 failed, err:%d\n",
+			mmc_hostname(host), err);
+		return err;
+	}
+
+	/* Set host controller to HS timing */
+	mmc_set_timing(card->host, MMC_TIMING_MMC_HS);
+
+	if (!send_status) {
+		err = mmc_switch_status(card);
+		if (err)
+			goto out_err;
+	}
+
+	/* Switch card to DDR */
+	err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+			 EXT_CSD_BUS_WIDTH,
+			 EXT_CSD_DDR_BUS_WIDTH_8,
+			 card->ext_csd.generic_cmd6_time);
+	if (err) {
+		pr_err("%s: switch to bus width for hs400 failed, err:%d\n",
+			mmc_hostname(host), err);
+		return err;
+	}
+
+	/* Switch card to HS400 */
+	val = EXT_CSD_TIMING_HS400 |
+	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+			   EXT_CSD_HS_TIMING, val,
+			   card->ext_csd.generic_cmd6_time,
+			   true, send_status, true);
+	if (err) {
+		pr_err("%s: switch to hs400 failed, err:%d\n",
+			 mmc_hostname(host), err);
+		return err;
+	}
+
+	/* Set host controller to HS400 timing and frequency */
+	mmc_set_timing(host, MMC_TIMING_MMC_HS400);
+	mmc_set_bus_speed(card);
+
+	if (!send_status) {
+		err = mmc_switch_status(card);
+		if (err)
+			goto out_err;
+	}
+
+	return 0;
+
+out_err:
+	pr_err("%s: %s failed, error %d\n", mmc_hostname(card->host),
+	       __func__, err);
+	return err;
+}
+
+int mmc_hs200_to_hs400(struct mmc_card *card)
+{
+	return mmc_select_hs400(card);
+}
+
 int mmc_hs400_to_hs200(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
@@ -1219,6 +1245,8 @@
 static int mmc_select_hs200(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
+	bool send_status = true;
+	unsigned int old_timing;
 	int err = -EINVAL;
 	u8 val;
 
@@ -1234,6 +1262,9 @@
 
 	mmc_select_driver_type(card);
 
+	if (host->caps & MMC_CAP_WAIT_WHILE_BUSY)
+		send_status = false;
+
 	/*
 	 * Set the bus width(4 or 8) with host's support and
 	 * switch to HS200 mode if bus width is set successfully.
@@ -1245,11 +1276,25 @@
 		err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 				   EXT_CSD_HS_TIMING, val,
 				   card->ext_csd.generic_cmd6_time,
-				   true, true, true);
-		if (!err)
-			mmc_set_timing(host, MMC_TIMING_MMC_HS200);
+				   true, send_status, true);
+		if (err)
+			goto err;
+		old_timing = host->ios.timing;
+		mmc_set_timing(host, MMC_TIMING_MMC_HS200);
+		if (!send_status) {
+			err = mmc_switch_status(card);
+			/*
+			 * mmc_select_timing() assumes timing has not changed if
+			 * it is a switch error.
+			 */
+			if (err == -EBADMSG)
+				mmc_set_timing(host, old_timing);
+		}
 	}
 err:
+	if (err)
+		pr_err("%s: %s failed, error %d\n", mmc_hostname(card->host),
+		       __func__, err);
 	return err;
 }
 
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index af71de5..1dee533 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -473,6 +473,7 @@
 
 config MMC_GOLDFISH
 	tristate "goldfish qemu Multimedia Card Interface support"
+	depends on HAS_DMA
 	depends on GOLDFISH || COMPILE_TEST
 	help
 	  This selects the Goldfish Multimedia card Interface emulation
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 39568cc..33dfd7e 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -1276,7 +1276,7 @@
 	int start = 0, len = 0;
 	int start_final = 0, len_final = 0;
 	u8 final_phase = 0xff;
-	struct msdc_delay_phase delay_phase;
+	struct msdc_delay_phase delay_phase = { 0, };
 
 	if (delay == 0) {
 		dev_err(host->dev, "phase error: [map:%x]\n", delay);
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 8cadd74..ce08896 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -805,7 +805,7 @@
 		goto out;
 	} else {
 		mmc->caps |= host->pdata->gpio_card_ro_invert ?
-			MMC_CAP2_RO_ACTIVE_HIGH : 0;
+			0 : MMC_CAP2_RO_ACTIVE_HIGH;
 	}
 
 	if (gpio_is_valid(gpio_cd))
diff --git a/drivers/mtd/nand/jz4740_nand.c b/drivers/mtd/nand/jz4740_nand.c
index dc4e844..5a99a93 100644
--- a/drivers/mtd/nand/jz4740_nand.c
+++ b/drivers/mtd/nand/jz4740_nand.c
@@ -25,6 +25,7 @@
 
 #include <linux/gpio.h>
 
+#include <asm/mach-jz4740/gpio.h>
 #include <asm/mach-jz4740/jz4740_nand.h>
 
 #define JZ_REG_NAND_CTRL	0x50
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index cc74142..ece544e 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -3110,7 +3110,7 @@
  */
 static void nand_shutdown(struct mtd_info *mtd)
 {
-	nand_get_device(mtd, FL_SHUTDOWN);
+	nand_get_device(mtd, FL_PM_SUSPENDED);
 }
 
 /* Set default functions */
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index e2afabf..7ccebae 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1500,10 +1500,11 @@
 		return -ENODEV;
 	}
 
-	if (!pci_set_dma_mask(pdev, PCNET32_DMA_MASK)) {
+	err = pci_set_dma_mask(pdev, PCNET32_DMA_MASK);
+	if (err) {
 		if (pcnet32_debug & NETIF_MSG_PROBE)
 			pr_err("architecture does not support 32bit PCI busmaster DMA\n");
-		return -ENODEV;
+		return err;
 	}
 	if (!request_region(ioaddr, PCNET32_TOTAL_SIZE, "pcnet32_probe_pci")) {
 		if (pcnet32_debug & NETIF_MSG_PROBE)
diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig
index f9f9422..8c8edaf 100644
--- a/drivers/net/wireless/Kconfig
+++ b/drivers/net/wireless/Kconfig
@@ -17,6 +17,22 @@
 
 if WLAN
 
+source "drivers/net/wireless/admtek/Kconfig"
+source "drivers/net/wireless/ath/Kconfig"
+source "drivers/net/wireless/atmel/Kconfig"
+source "drivers/net/wireless/broadcom/Kconfig"
+source "drivers/net/wireless/cisco/Kconfig"
+source "drivers/net/wireless/intel/Kconfig"
+source "drivers/net/wireless/intersil/Kconfig"
+source "drivers/net/wireless/marvell/Kconfig"
+source "drivers/net/wireless/mediatek/Kconfig"
+source "drivers/net/wireless/ralink/Kconfig"
+source "drivers/net/wireless/realtek/Kconfig"
+source "drivers/net/wireless/rsi/Kconfig"
+source "drivers/net/wireless/st/Kconfig"
+source "drivers/net/wireless/ti/Kconfig"
+source "drivers/net/wireless/zydas/Kconfig"
+
 config PCMCIA_RAYCS
 	tristate "Aviator/Raytheon 2.4GHz wireless support"
 	depends on PCMCIA
@@ -32,110 +48,6 @@
 	  To compile this driver as a module, choose M here: the module will be
 	  called ray_cs.  If unsure, say N.
 
-config LIBERTAS_THINFIRM
-	tristate "Marvell 8xxx Libertas WLAN driver support with thin firmware"
-	depends on MAC80211
-	select FW_LOADER
-	---help---
-	  A library for Marvell Libertas 8xxx devices using thinfirm.
-
-config LIBERTAS_THINFIRM_DEBUG
-	bool "Enable full debugging output in the Libertas thin firmware module."
-	depends on LIBERTAS_THINFIRM
-	---help---
-	  Debugging support.
-
-config LIBERTAS_THINFIRM_USB
-	tristate "Marvell Libertas 8388 USB 802.11b/g cards with thin firmware"
-	depends on LIBERTAS_THINFIRM && USB
-	---help---
-	  A driver for Marvell Libertas 8388 USB devices using thinfirm.
-
-config AIRO
-	tristate "Cisco/Aironet 34X/35X/4500/4800 ISA and PCI cards"
-	depends on CFG80211 && ISA_DMA_API && (PCI || BROKEN)
-	select WIRELESS_EXT
-	select CRYPTO
-	select WEXT_SPY
-	select WEXT_PRIV
-	---help---
-	  This is the standard Linux driver to support Cisco/Aironet ISA and
-	  PCI 802.11 wireless cards.
-	  It supports the new 802.11b cards from Cisco (Cisco 34X, Cisco 35X
-	  - with or without encryption) as well as card before the Cisco
-	  acquisition (Aironet 4500, Aironet 4800, Aironet 4800B).
-
-	  This driver support both the standard Linux Wireless Extensions
-	  and Cisco proprietary API, so both the Linux Wireless Tools and the
-	  Cisco Linux utilities can be used to configure the card.
-
-	  The driver can be compiled as a module and will be named "airo".
-
-config ATMEL
-      tristate "Atmel at76c50x chipset  802.11b support"
-      depends on CFG80211 && (PCI || PCMCIA)
-      select WIRELESS_EXT
-      select WEXT_PRIV
-      select FW_LOADER
-      select CRC32
-       ---help---
-        A driver 802.11b wireless cards based on the Atmel fast-vnet
-        chips. This driver supports standard Linux wireless extensions.
-
-        Many  cards based on this chipset do not have flash memory
-        and need their firmware loaded at start-up. If yours is
-        one of these, you will need to provide a firmware image
-        to be loaded into the card by the driver. The Atmel
-        firmware package can be downloaded from
-        <http://www.thekelleys.org.uk/atmel>
-
-config PCI_ATMEL
-      tristate "Atmel at76c506 PCI cards"
-      depends on ATMEL && PCI
-       ---help---
-        Enable support for PCI and mini-PCI cards containing the
-        Atmel at76c506 chip.
-
-config PCMCIA_ATMEL
-	tristate "Atmel at76c502/at76c504 PCMCIA cards"
-	depends on ATMEL && PCMCIA
-	select WIRELESS_EXT
-	select FW_LOADER
-	select CRC32
-	---help---
-	  Enable support for PCMCIA cards containing the
-	  Atmel at76c502 and at76c504 chips.
-
-config AT76C50X_USB
-        tristate "Atmel at76c503/at76c505/at76c505a USB cards"
-        depends on MAC80211 && USB
-        select FW_LOADER
-        ---help---
-          Enable support for USB Wireless devices using Atmel at76c503,
-          at76c505 or at76c505a chips.
-
-config AIRO_CS
-	tristate "Cisco/Aironet 34X/35X/4500/4800 PCMCIA cards"
-	depends on CFG80211 && PCMCIA && (BROKEN || !M32R)
-	select WIRELESS_EXT
-	select WEXT_SPY
-	select WEXT_PRIV
-	select CRYPTO
-	select CRYPTO_AES
-	---help---
-	  This is the standard Linux driver to support Cisco/Aironet PCMCIA
-	  802.11 wireless cards.  This driver is the same as the Aironet
-	  driver part of the Linux Pcmcia package.
-	  It supports the new 802.11b cards from Cisco (Cisco 34X, Cisco 35X
-	  - with or without encryption) as well as card before the Cisco
-	  acquisition (Aironet 4500, Aironet 4800, Aironet 4800B). It also
-	  supports OEM of Cisco such as the DELL TrueMobile 4800 and Xircom
-	  802.11b cards.
-
-	  This driver support both the standard Linux Wireless Extensions
-	  and Cisco proprietary API, so both the Linux Wireless Tools and the
-	  Cisco Linux utilities can be used to configure the card.
-
 config PCMCIA_WL3501
 	tristate "Planet WL3501 PCMCIA cards"
 	depends on CFG80211 && PCMCIA
@@ -146,44 +58,18 @@
 	  It has basic support for Linux wireless extensions and initial
 	  micro support for ethtool.
 
-config PRISM54
-	tristate 'Intersil Prism GT/Duette/Indigo PCI/Cardbus (DEPRECATED)'
-	depends on PCI
-	select WIRELESS_EXT
-	select WEXT_SPY
-	select WEXT_PRIV
-	select FW_LOADER
+config MAC80211_HWSIM
+	tristate "Simulated radio testing tool for mac80211"
+	depends on MAC80211
 	---help---
-	  This enables support for FullMAC PCI/Cardbus prism54 devices. This
-	  driver is now deprecated in favor for the SoftMAC driver, p54pci.
-	  p54pci supports FullMAC PCI/Cardbus devices as well.
+	  This driver is a developer testing tool that can be used to test
+	  IEEE 802.11 networking stack (mac80211) functionality. This is not
+	  needed for normal wireless LAN usage and is only for testing. See
+	  Documentation/networking/mac80211_hwsim for more information on how
+	  to use this tool.
 
-	  For more information refer to the p54 wiki:
-
-	  http://wireless.kernel.org/en/users/Drivers/p54
-
-	  Note: You need a motherboard with DMA support to use any of these cards
-
-	  When built as module you get the module prism54
-
-config USB_ZD1201
-	tristate "USB ZD1201 based Wireless device support"
-	depends on CFG80211 && USB
-	select WIRELESS_EXT
-	select WEXT_PRIV
-	select FW_LOADER
-	---help---
-	  Say Y if you want to use wireless LAN adapters based on the ZyDAS
-	  ZD1201 chip.
-
-	  This driver makes the adapter appear as a normal Ethernet interface,
-	  typically on wlan0.
-
-	  The zd1201 device requires external firmware to be loaded.
-	  This can be found at http://linux-lc100020.sourceforge.net/
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called zd1201.
+	  To compile this driver as a module, choose M here: the module will be
+	  called mac80211_hwsim.  If unsure, say N.
 
 config USB_NET_RNDIS_WLAN
 	tristate "Wireless RNDIS USB support"
@@ -214,76 +100,4 @@
 
 	  If you choose to build a module, it'll be called rndis_wlan.
 
-config ADM8211
-	tristate "ADMtek ADM8211 support"
-	depends on MAC80211 && PCI
-	select CRC32
-	select EEPROM_93CX6
-	---help---
-	  This driver is for ADM8211A, ADM8211B, and ADM8211C based cards.
-	  These are PCI/mini-PCI/Cardbus 802.11b chips found in cards such as:
-
-	  Xterasys Cardbus XN-2411b
-	  Blitz NetWave Point PC
-	  TrendNet 221pc
-	  Belkin F5D6001
-	  SMC 2635W
-	  Linksys WPC11 v1
-	  Fiberline FL-WL-200X
-	  3com Office Connect (3CRSHPW796)
-	  Corega WLPCIB-11
-	  SMC 2602W V2 EU
-	  D-Link DWL-520 Revision C
-
-	  However, some of these cards have been replaced with other chips
-	  like the RTL8180L (Xterasys Cardbus XN-2411b, Belkin F5D6001) or
-	  the Ralink RT2400 (SMC2635W) without a model number change.
-
-	  Thanks to Infineon-ADMtek for their support of this driver.
-
-source "drivers/net/wireless/realtek/rtl818x/Kconfig"
-
-config MAC80211_HWSIM
-	tristate "Simulated radio testing tool for mac80211"
-	depends on MAC80211
-	---help---
-	  This driver is a developer testing tool that can be used to test
-	  IEEE 802.11 networking stack (mac80211) functionality. This is not
-	  needed for normal wireless LAN usage and is only for testing. See
-	  Documentation/networking/mac80211_hwsim for more information on how
-	  to use this tool.
-
-	  To compile this driver as a module, choose M here: the module will be
-	  called mac80211_hwsim.  If unsure, say N.
-
-config MWL8K
-	tristate "Marvell 88W8xxx PCI/PCIe Wireless support"
-	depends on MAC80211 && PCI
-	---help---
-	  This driver supports Marvell TOPDOG 802.11 wireless cards.
-
-	  To compile this driver as a module, choose M here: the module
-	  will be called mwl8k.  If unsure, say N.
-
-source "drivers/net/wireless/ath/Kconfig"
-source "drivers/net/wireless/b43/Kconfig"
-source "drivers/net/wireless/b43legacy/Kconfig"
-source "drivers/net/wireless/brcm80211/Kconfig"
-source "drivers/net/wireless/hostap/Kconfig"
-source "drivers/net/wireless/ipw2x00/Kconfig"
-source "drivers/net/wireless/iwlwifi/Kconfig"
-source "drivers/net/wireless/iwlegacy/Kconfig"
-source "drivers/net/wireless/libertas/Kconfig"
-source "drivers/net/wireless/orinoco/Kconfig"
-source "drivers/net/wireless/p54/Kconfig"
-source "drivers/net/wireless/rt2x00/Kconfig"
-source "drivers/net/wireless/mediatek/Kconfig"
-source "drivers/net/wireless/realtek/rtlwifi/Kconfig"
-source "drivers/net/wireless/realtek/rtl8xxxu/Kconfig"
-source "drivers/net/wireless/ti/Kconfig"
-source "drivers/net/wireless/zd1211rw/Kconfig"
-source "drivers/net/wireless/mwifiex/Kconfig"
-source "drivers/net/wireless/cw1200/Kconfig"
-source "drivers/net/wireless/rsi/Kconfig"
-
 endif # WLAN
diff --git a/drivers/net/wireless/Makefile b/drivers/net/wireless/Makefile
index 740fdd3..f00d429 100644
--- a/drivers/net/wireless/Makefile
+++ b/drivers/net/wireless/Makefile
@@ -2,27 +2,21 @@
 # Makefile for the Linux Wireless network device drivers.
 #
 
-obj-$(CONFIG_IPW2100) += ipw2x00/
-obj-$(CONFIG_IPW2200) += ipw2x00/
-
-obj-$(CONFIG_HERMES)		+= orinoco/
-
-obj-$(CONFIG_AIRO)		+= airo.o
-obj-$(CONFIG_AIRO_CS)		+= airo_cs.o airo.o
-
-obj-$(CONFIG_ATMEL)             += atmel.o
-obj-$(CONFIG_PCI_ATMEL)         += atmel_pci.o 
-obj-$(CONFIG_PCMCIA_ATMEL)      += atmel_cs.o
-
-obj-$(CONFIG_AT76C50X_USB)      += at76c50x-usb.o
-
-obj-$(CONFIG_PRISM54)		+= prism54/
-
-obj-$(CONFIG_HOSTAP)		+= hostap/
-obj-$(CONFIG_B43)		+= b43/
-obj-$(CONFIG_B43LEGACY)		+= b43legacy/
-obj-$(CONFIG_ZD1211RW)		+= zd1211rw/
-obj-$(CONFIG_WLAN)		+= realtek/
+obj-$(CONFIG_WLAN_VENDOR_ADMTEK) += admtek/
+obj-$(CONFIG_WLAN_VENDOR_ATH) += ath/
+obj-$(CONFIG_WLAN_VENDOR_ATMEL) += atmel/
+obj-$(CONFIG_WLAN_VENDOR_BROADCOM) += broadcom/
+obj-$(CONFIG_WLAN_VENDOR_CISCO) += cisco/
+obj-$(CONFIG_WLAN_VENDOR_INTEL) += intel/
+obj-$(CONFIG_WLAN_VENDOR_INTERSIL) += intersil/
+obj-$(CONFIG_WLAN_VENDOR_MARVELL) += marvell/
+obj-$(CONFIG_WLAN_VENDOR_MEDIATEK) += mediatek/
+obj-$(CONFIG_WLAN_VENDOR_RALINK) += ralink/
+obj-$(CONFIG_WLAN_VENDOR_REALTEK) += realtek/
+obj-$(CONFIG_WLAN_VENDOR_RSI) += rsi/
+obj-$(CONFIG_WLAN_VENDOR_ST) += st/
+obj-$(CONFIG_WLAN_VENDOR_TI) += ti/
+obj-$(CONFIG_WLAN_VENDOR_ZYDAS) += zydas/
 
 # 16-bit wireless PCMCIA client drivers
 obj-$(CONFIG_PCMCIA_RAYCS)	+= ray_cs.o
@@ -30,33 +24,4 @@
 
 obj-$(CONFIG_USB_NET_RNDIS_WLAN)	+= rndis_wlan.o
 
-obj-$(CONFIG_USB_ZD1201)	+= zd1201.o
-obj-$(CONFIG_LIBERTAS)		+= libertas/
-
-obj-$(CONFIG_LIBERTAS_THINFIRM)	+= libertas_tf/
-
-obj-$(CONFIG_ADM8211)	+= adm8211.o
-
-obj-$(CONFIG_MWL8K)	+= mwl8k.o
-
-obj-$(CONFIG_IWLWIFI)	+= iwlwifi/
-obj-$(CONFIG_IWLEGACY)	+= iwlegacy/
-obj-$(CONFIG_RT2X00)	+= rt2x00/
-
-obj-$(CONFIG_WL_MEDIATEK)	+= mediatek/
-
-obj-$(CONFIG_P54_COMMON)	+= p54/
-
-obj-$(CONFIG_ATH_CARDS)		+= ath/
-
 obj-$(CONFIG_MAC80211_HWSIM)	+= mac80211_hwsim.o
-
-obj-$(CONFIG_WL_TI)	+= ti/
-
-obj-$(CONFIG_MWIFIEX)	+= mwifiex/
-
-obj-$(CONFIG_BRCMFMAC)	+= brcm80211/
-obj-$(CONFIG_BRCMSMAC)	+= brcm80211/
-
-obj-$(CONFIG_CW1200)	+= cw1200/
-obj-$(CONFIG_RSI_91X)	+= rsi/
diff --git a/drivers/net/wireless/admtek/Kconfig b/drivers/net/wireless/admtek/Kconfig
new file mode 100644
index 0000000..d5a2dc7
--- /dev/null
+++ b/drivers/net/wireless/admtek/Kconfig
@@ -0,0 +1,41 @@
+config WLAN_VENDOR_ADMTEK
+	bool "ADMtek devices"
+	default y
+	---help---
+	  If you have a wireless card belonging to this class, say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about  cards. If you say Y, you will be asked for
+	  your specific card in the following questions.
+
+if WLAN_VENDOR_ADMTEK
+
+config ADM8211
+	tristate "ADMtek ADM8211 support"
+	depends on MAC80211 && PCI
+	select CRC32
+	select EEPROM_93CX6
+	---help---
+	  This driver is for ADM8211A, ADM8211B, and ADM8211C based cards.
+	  These are PCI/mini-PCI/Cardbus 802.11b chips found in cards such as:
+
+	  Xterasys Cardbus XN-2411b
+	  Blitz NetWave Point PC
+	  TrendNet 221pc
+	  Belkin F5D6001
+	  SMC 2635W
+	  Linksys WPC11 v1
+	  Fiberline FL-WL-200X
+	  3com Office Connect (3CRSHPW796)
+	  Corega WLPCIB-11
+	  SMC 2602W V2 EU
+	  D-Link DWL-520 Revision C
+
+	  However, some of these cards have been replaced with other chips
+	  like the RTL8180L (Xterasys Cardbus XN-2411b, Belkin F5D6001) or
+	  the Ralink RT2400 (SMC2635W) without a model number change.
+
+	  Thanks to Infineon-ADMtek for their support of this driver.
+
+endif # WLAN_VENDOR_ADMTEK
diff --git a/drivers/net/wireless/admtek/Makefile b/drivers/net/wireless/admtek/Makefile
new file mode 100644
index 0000000..9cca7e5
--- /dev/null
+++ b/drivers/net/wireless/admtek/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_ADM8211)	+= adm8211.o
diff --git a/drivers/net/wireless/adm8211.c b/drivers/net/wireless/admtek/adm8211.c
similarity index 100%
rename from drivers/net/wireless/adm8211.c
rename to drivers/net/wireless/admtek/adm8211.c
diff --git a/drivers/net/wireless/adm8211.h b/drivers/net/wireless/admtek/adm8211.h
similarity index 100%
rename from drivers/net/wireless/adm8211.h
rename to drivers/net/wireless/admtek/adm8211.h
diff --git a/drivers/net/wireless/ath/Kconfig b/drivers/net/wireless/ath/Kconfig
index ce78260..44b2470 100644
--- a/drivers/net/wireless/ath/Kconfig
+++ b/drivers/net/wireless/ath/Kconfig
@@ -1,13 +1,16 @@
 config ATH_COMMON
 	tristate
 
-menuconfig ATH_CARDS
-	tristate "Atheros Wireless Cards"
-	depends on CFG80211 && (!UML || BROKEN)
+config WLAN_VENDOR_ATH
+	bool "Atheros/Qualcomm devices"
+	default y
 	---help---
-	  This will enable the support for the Atheros wireless drivers.
-	  ath5k, ath9k, ath9k_htc and ar9170 drivers share some common code, this option
-	  enables the common ath.ko module which shares common helpers.
+	  If you have a wireless card belonging to this class, say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about  cards. If you say Y, you will be asked for
+	  your specific card in the following questions.
 
 	  For more information and documentation on this module you can visit:
 
@@ -17,7 +20,7 @@
 
 	  http://wireless.kernel.org/en/users/Drivers/Atheros
 
-if ATH_CARDS
+if WLAN_VENDOR_ATH
 
 config ATH_DEBUG
 	bool "Atheros wireless debugging"
diff --git a/drivers/net/wireless/ath/ath10k/Kconfig b/drivers/net/wireless/ath/ath10k/Kconfig
index 72acb82..03aa35f 100644
--- a/drivers/net/wireless/ath/ath10k/Kconfig
+++ b/drivers/net/wireless/ath/ath10k/Kconfig
@@ -2,6 +2,7 @@
         tristate "Atheros 802.11ac wireless cards support"
         depends on MAC80211 && HAS_DMA
 	select ATH_COMMON
+	select CRC32
         ---help---
           This module adds support for wireless adapters based on
           Atheros IEEE 802.11ac family of chipsets.
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index aa9bd92..b41eb3f 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -51,6 +51,7 @@
 static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 	{
 		.id = QCA988X_HW_2_0_VERSION,
+		.dev_id = QCA988X_2_0_DEVICE_ID,
 		.name = "qca988x hw2.0",
 		.patch_load_addr = QCA988X_HW_2_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
@@ -58,6 +59,7 @@
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
+		.hw_4addr_pad = ATH10K_HW_4ADDR_PAD_AFTER,
 		.fw = {
 			.dir = QCA988X_HW_2_0_FW_DIR,
 			.fw = QCA988X_HW_2_0_FW_FILE,
@@ -69,7 +71,8 @@
 	},
 	{
 		.id = QCA6174_HW_2_1_VERSION,
-		.name = "qca6174 hw2.1",
+		.dev_id = QCA6164_2_1_DEVICE_ID,
+		.name = "qca6164 hw2.1",
 		.patch_load_addr = QCA6174_HW_2_1_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
 		.otp_exe_param = 0,
@@ -85,13 +88,34 @@
 		},
 	},
 	{
+		.id = QCA6174_HW_2_1_VERSION,
+		.dev_id = QCA6174_2_1_DEVICE_ID,
+		.name = "qca6174 hw2.1",
+		.patch_load_addr = QCA6174_HW_2_1_PATCH_LOAD_ADDR,
+		.uart_pin = 6,
+		.otp_exe_param = 0,
+		.channel_counters_freq_hz = 88000,
+		.max_probe_resp_desc_thres = 0,
+		.hw_4addr_pad = ATH10K_HW_4ADDR_PAD_AFTER,
+		.fw = {
+			.dir = QCA6174_HW_2_1_FW_DIR,
+			.fw = QCA6174_HW_2_1_FW_FILE,
+			.otp = QCA6174_HW_2_1_OTP_FILE,
+			.board = QCA6174_HW_2_1_BOARD_DATA_FILE,
+			.board_size = QCA6174_BOARD_DATA_SZ,
+			.board_ext_size = QCA6174_BOARD_EXT_DATA_SZ,
+		},
+	},
+	{
 		.id = QCA6174_HW_3_0_VERSION,
+		.dev_id = QCA6174_2_1_DEVICE_ID,
 		.name = "qca6174 hw3.0",
 		.patch_load_addr = QCA6174_HW_3_0_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
+		.hw_4addr_pad = ATH10K_HW_4ADDR_PAD_AFTER,
 		.fw = {
 			.dir = QCA6174_HW_3_0_FW_DIR,
 			.fw = QCA6174_HW_3_0_FW_FILE,
@@ -103,12 +127,14 @@
 	},
 	{
 		.id = QCA6174_HW_3_2_VERSION,
+		.dev_id = QCA6174_2_1_DEVICE_ID,
 		.name = "qca6174 hw3.2",
 		.patch_load_addr = QCA6174_HW_3_0_PATCH_LOAD_ADDR,
 		.uart_pin = 6,
 		.otp_exe_param = 0,
 		.channel_counters_freq_hz = 88000,
 		.max_probe_resp_desc_thres = 0,
+		.hw_4addr_pad = ATH10K_HW_4ADDR_PAD_AFTER,
 		.fw = {
 			/* uses same binaries as hw3.0 */
 			.dir = QCA6174_HW_3_0_FW_DIR,
@@ -121,6 +147,7 @@
 	},
 	{
 		.id = QCA99X0_HW_2_0_DEV_VERSION,
+		.dev_id = QCA99X0_2_0_DEVICE_ID,
 		.name = "qca99x0 hw2.0",
 		.patch_load_addr = QCA99X0_HW_2_0_PATCH_LOAD_ADDR,
 		.uart_pin = 7,
@@ -128,6 +155,7 @@
 		.continuous_frag_desc = true,
 		.channel_counters_freq_hz = 150000,
 		.max_probe_resp_desc_thres = 24,
+		.hw_4addr_pad = ATH10K_HW_4ADDR_PAD_BEFORE,
 		.fw = {
 			.dir = QCA99X0_HW_2_0_FW_DIR,
 			.fw = QCA99X0_HW_2_0_FW_FILE,
@@ -139,10 +167,31 @@
 	},
 	{
 		.id = QCA9377_HW_1_0_DEV_VERSION,
+		.dev_id = QCA9377_1_0_DEVICE_ID,
 		.name = "qca9377 hw1.0",
 		.patch_load_addr = QCA9377_HW_1_0_PATCH_LOAD_ADDR,
-		.uart_pin = 7,
+		.uart_pin = 6,
 		.otp_exe_param = 0,
+		.channel_counters_freq_hz = 88000,
+		.max_probe_resp_desc_thres = 0,
+		.fw = {
+			.dir = QCA9377_HW_1_0_FW_DIR,
+			.fw = QCA9377_HW_1_0_FW_FILE,
+			.otp = QCA9377_HW_1_0_OTP_FILE,
+			.board = QCA9377_HW_1_0_BOARD_DATA_FILE,
+			.board_size = QCA9377_BOARD_DATA_SZ,
+			.board_ext_size = QCA9377_BOARD_EXT_DATA_SZ,
+		},
+	},
+	{
+		.id = QCA9377_HW_1_1_DEV_VERSION,
+		.dev_id = QCA9377_1_0_DEVICE_ID,
+		.name = "qca9377 hw1.1",
+		.patch_load_addr = QCA9377_HW_1_0_PATCH_LOAD_ADDR,
+		.uart_pin = 6,
+		.otp_exe_param = 0,
+		.channel_counters_freq_hz = 88000,
+		.max_probe_resp_desc_thres = 0,
 		.fw = {
 			.dir = QCA9377_HW_1_0_FW_DIR,
 			.fw = QCA9377_HW_1_0_FW_FILE,
@@ -167,6 +216,7 @@
 	[ATH10K_FW_FEATURE_SUPPORTS_SKIP_CLOCK_INIT] = "skip-clock-init",
 	[ATH10K_FW_FEATURE_RAW_MODE_SUPPORT] = "raw-mode",
 	[ATH10K_FW_FEATURE_SUPPORTS_ADAPTIVE_CCA] = "adaptive-cca",
+	[ATH10K_FW_FEATURE_MFP_SUPPORT] = "mfp",
 };
 
 static unsigned int ath10k_core_get_fw_feature_str(char *buf,
@@ -843,7 +893,7 @@
 	if (!ar->board_data || !ar->board_len) {
 		ath10k_err(ar,
 			   "failed to fetch board data for %s from %s/%s\n",
-			   ar->hw_params.fw.dir, boardname, filename);
+			   boardname, ar->hw_params.fw.dir, filename);
 		ret = -ENODATA;
 		goto err;
 	}
@@ -1263,7 +1313,8 @@
 	for (i = 0; i < ARRAY_SIZE(ath10k_hw_params_list); i++) {
 		hw_params = &ath10k_hw_params_list[i];
 
-		if (hw_params->id == ar->target_version)
+		if (hw_params->id == ar->target_version &&
+		    hw_params->dev_id == ar->dev_id)
 			break;
 	}
 
@@ -1745,9 +1796,11 @@
 		goto err_power_down;
 	}
 
+	ath10k_debug_print_hwfw_info(ar);
+
 	ret = ath10k_core_get_board_id_from_otp(ar);
 	if (ret && ret != -EOPNOTSUPP) {
-		ath10k_err(ar, "failed to get board id from otp for qca99x0: %d\n",
+		ath10k_err(ar, "failed to get board id from otp: %d\n",
 			   ret);
 		return ret;
 	}
@@ -1758,6 +1811,8 @@
 		goto err_free_firmware_files;
 	}
 
+	ath10k_debug_print_board_info(ar);
+
 	ret = ath10k_core_init_firmware_features(ar);
 	if (ret) {
 		ath10k_err(ar, "fatal problem with firmware features: %d\n",
@@ -1780,7 +1835,7 @@
 		goto err_unlock;
 	}
 
-	ath10k_print_driver_info(ar);
+	ath10k_debug_print_boot_info(ar);
 	ath10k_core_stop(ar);
 
 	mutex_unlock(&ar->conf_mutex);
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 018c64f..7840cf3 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -81,26 +81,20 @@
 	return "unknown";
 }
 
+enum ath10k_skb_flags {
+	ATH10K_SKB_F_NO_HWCRYPT = BIT(0),
+	ATH10K_SKB_F_DTIM_ZERO = BIT(1),
+	ATH10K_SKB_F_DELIVER_CAB = BIT(2),
+	ATH10K_SKB_F_MGMT = BIT(3),
+	ATH10K_SKB_F_QOS = BIT(4),
+};
+
 struct ath10k_skb_cb {
 	dma_addr_t paddr;
+	u8 flags;
 	u8 eid;
-	u8 vdev_id;
-	enum ath10k_hw_txrx_mode txmode;
-	bool is_protected;
-
-	struct {
-		u8 tid;
-		u16 freq;
-		bool is_offchan;
-		bool nohwcrypt;
-		struct ath10k_htt_txbuf *txbuf;
-		u32 txbuf_paddr;
-	} __packed htt;
-
-	struct {
-		bool dtim_zero;
-		bool deliver_cab;
-	} bcn;
+	u16 msdu_id;
+	struct ieee80211_vif *vif;
 } __packed;
 
 struct ath10k_skb_rxcb {
@@ -151,6 +145,7 @@
 	struct wmi_vdev_param_map *vdev_param;
 	struct wmi_pdev_param_map *pdev_param;
 	const struct wmi_ops *ops;
+	const struct wmi_peer_flags_map *peer_flags;
 
 	u32 num_mem_chunks;
 	u32 rx_decap_mode;
@@ -512,6 +507,9 @@
 	/* Firmware Supports Adaptive CCA*/
 	ATH10K_FW_FEATURE_SUPPORTS_ADAPTIVE_CCA = 11,
 
+	/* Firmware supports management frame protection */
+	ATH10K_FW_FEATURE_MFP_SUPPORT = 12,
+
 	/* keep last */
 	ATH10K_FW_FEATURE_COUNT,
 };
@@ -534,6 +532,9 @@
 
 	/* Disable HW crypto engine */
 	ATH10K_FLAG_HW_CRYPTO_DISABLED,
+
+	/* Bluetooth coexistance enabled */
+	ATH10K_FLAG_BTCOEX,
 };
 
 enum ath10k_cal_mode {
@@ -636,6 +637,7 @@
 
 	struct ath10k_hw_params {
 		u32 id;
+		u16 dev_id;
 		const char *name;
 		u32 patch_load_addr;
 		int uart_pin;
@@ -661,6 +663,9 @@
 		 */
 		u32 max_probe_resp_desc_thres;
 
+		/* The padding bytes's location is different on various chips */
+		enum ath10k_hw_4addr_pad hw_4addr_pad;
+
 		struct ath10k_hw_params_fw {
 			const char *dir;
 			const char *fw;
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index 6cc1aa3..39fe4f3 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -19,6 +19,8 @@
 #include <linux/debugfs.h>
 #include <linux/vmalloc.h>
 #include <linux/utsname.h>
+#include <linux/crc32.h>
+#include <linux/firmware.h>
 
 #include "core.h"
 #include "debug.h"
@@ -122,28 +124,51 @@
 }
 EXPORT_SYMBOL(ath10k_info);
 
-void ath10k_print_driver_info(struct ath10k *ar)
+void ath10k_debug_print_hwfw_info(struct ath10k *ar)
 {
 	char fw_features[128] = {};
-	char boardinfo[100];
 
 	ath10k_core_get_fw_features_str(ar, fw_features, sizeof(fw_features));
 
-	if (ar->id.bmi_ids_valid)
-		scnprintf(boardinfo, sizeof(boardinfo), "bmi %d:%d",
-			  ar->id.bmi_chip_id, ar->id.bmi_board_id);
-	else
-		scnprintf(boardinfo, sizeof(boardinfo), "sub %04x:%04x",
-			  ar->id.subsystem_vendor, ar->id.subsystem_device);
-
-	ath10k_info(ar, "%s (0x%08x, 0x%08x %s) fw %s fwapi %d bdapi %d htt-ver %d.%d wmi-op %d htt-op %d cal %s max-sta %d raw %d hwcrypto %d features %s\n",
+	ath10k_info(ar, "%s target 0x%08x chip_id 0x%08x sub %04x:%04x",
 		    ar->hw_params.name,
 		    ar->target_version,
 		    ar->chip_id,
-		    boardinfo,
+		    ar->id.subsystem_vendor, ar->id.subsystem_device);
+
+	ath10k_info(ar, "kconfig debug %d debugfs %d tracing %d dfs %d testmode %d\n",
+		    config_enabled(CONFIG_ATH10K_DEBUG),
+		    config_enabled(CONFIG_ATH10K_DEBUGFS),
+		    config_enabled(CONFIG_ATH10K_TRACING),
+		    config_enabled(CONFIG_ATH10K_DFS_CERTIFIED),
+		    config_enabled(CONFIG_NL80211_TESTMODE));
+
+	ath10k_info(ar, "firmware ver %s api %d features %s crc32 %08x\n",
 		    ar->hw->wiphy->fw_version,
 		    ar->fw_api,
+		    fw_features,
+		    crc32_le(0, ar->firmware->data, ar->firmware->size));
+}
+
+void ath10k_debug_print_board_info(struct ath10k *ar)
+{
+	char boardinfo[100];
+
+	if (ar->id.bmi_ids_valid)
+		scnprintf(boardinfo, sizeof(boardinfo), "%d:%d",
+			  ar->id.bmi_chip_id, ar->id.bmi_board_id);
+	else
+		scnprintf(boardinfo, sizeof(boardinfo), "N/A");
+
+	ath10k_info(ar, "board_file api %d bmi_id %s crc32 %08x",
 		    ar->bd_api,
+		    boardinfo,
+		    crc32_le(0, ar->board->data, ar->board->size));
+}
+
+void ath10k_debug_print_boot_info(struct ath10k *ar)
+{
+	ath10k_info(ar, "htt-ver %d.%d wmi-op %d htt-op %d cal %s max-sta %d raw %d hwcrypto %d\n",
 		    ar->htt.target_version_major,
 		    ar->htt.target_version_minor,
 		    ar->wmi.op_version,
@@ -151,14 +176,14 @@
 		    ath10k_cal_mode_str(ar->cal_mode),
 		    ar->max_num_stations,
 		    test_bit(ATH10K_FLAG_RAW_MODE, &ar->dev_flags),
-		    !test_bit(ATH10K_FLAG_HW_CRYPTO_DISABLED, &ar->dev_flags),
-		    fw_features);
-	ath10k_info(ar, "debug %d debugfs %d tracing %d dfs %d testmode %d\n",
-		    config_enabled(CONFIG_ATH10K_DEBUG),
-		    config_enabled(CONFIG_ATH10K_DEBUGFS),
-		    config_enabled(CONFIG_ATH10K_TRACING),
-		    config_enabled(CONFIG_ATH10K_DFS_CERTIFIED),
-		    config_enabled(CONFIG_NL80211_TESTMODE));
+		    !test_bit(ATH10K_FLAG_HW_CRYPTO_DISABLED, &ar->dev_flags));
+}
+
+void ath10k_print_driver_info(struct ath10k *ar)
+{
+	ath10k_debug_print_hwfw_info(ar);
+	ath10k_debug_print_board_info(ar);
+	ath10k_debug_print_boot_info(ar);
 }
 EXPORT_SYMBOL(ath10k_print_driver_info);
 
@@ -2074,6 +2099,121 @@
 	.open = simple_open
 };
 
+static ssize_t ath10k_write_btcoex(struct file *file,
+				   const char __user *ubuf,
+				   size_t count, loff_t *ppos)
+{
+	struct ath10k *ar = file->private_data;
+	char buf[32];
+	size_t buf_size;
+	bool val;
+
+	buf_size = min(count, (sizeof(buf) - 1));
+	if (copy_from_user(buf, ubuf, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+
+	if (strtobool(buf, &val) != 0)
+		return -EINVAL;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (!(test_bit(ATH10K_FLAG_BTCOEX, &ar->dev_flags) ^ val))
+		goto exit;
+
+	if (val)
+		set_bit(ATH10K_FLAG_BTCOEX, &ar->dev_flags);
+	else
+		clear_bit(ATH10K_FLAG_BTCOEX, &ar->dev_flags);
+
+	if (ar->state != ATH10K_STATE_ON)
+		goto exit;
+
+	ath10k_info(ar, "restarting firmware due to btcoex change");
+
+	queue_work(ar->workqueue, &ar->restart_work);
+
+exit:
+	mutex_unlock(&ar->conf_mutex);
+
+	return count;
+}
+
+static ssize_t ath10k_read_btcoex(struct file *file, char __user *ubuf,
+				  size_t count, loff_t *ppos)
+{
+	char buf[32];
+	struct ath10k *ar = file->private_data;
+	int len = 0;
+
+	mutex_lock(&ar->conf_mutex);
+	len = scnprintf(buf, sizeof(buf) - len, "%d\n",
+			test_bit(ATH10K_FLAG_BTCOEX, &ar->dev_flags));
+	mutex_unlock(&ar->conf_mutex);
+
+	return simple_read_from_buffer(ubuf, count, ppos, buf, len);
+}
+
+static const struct file_operations fops_btcoex = {
+	.read = ath10k_read_btcoex,
+	.write = ath10k_write_btcoex,
+	.open = simple_open
+};
+
+static ssize_t ath10k_debug_fw_checksums_read(struct file *file,
+					      char __user *user_buf,
+					      size_t count, loff_t *ppos)
+{
+	struct ath10k *ar = file->private_data;
+	unsigned int len = 0, buf_len = 4096;
+	ssize_t ret_cnt;
+	char *buf;
+
+	buf = kzalloc(buf_len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (len > buf_len)
+		len = buf_len;
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "firmware-N.bin\t\t%08x\n",
+			 crc32_le(0, ar->firmware->data, ar->firmware->size));
+	len += scnprintf(buf + len, buf_len - len,
+			 "athwlan\t\t\t%08x\n",
+			 crc32_le(0, ar->firmware_data, ar->firmware_len));
+	len += scnprintf(buf + len, buf_len - len,
+			 "otp\t\t\t%08x\n",
+			 crc32_le(0, ar->otp_data, ar->otp_len));
+	len += scnprintf(buf + len, buf_len - len,
+			 "codeswap\t\t%08x\n",
+			 crc32_le(0, ar->swap.firmware_codeswap_data,
+				  ar->swap.firmware_codeswap_len));
+	len += scnprintf(buf + len, buf_len - len,
+			 "board-N.bin\t\t%08x\n",
+			 crc32_le(0, ar->board->data, ar->board->size));
+	len += scnprintf(buf + len, buf_len - len,
+			 "board\t\t\t%08x\n",
+			 crc32_le(0, ar->board_data, ar->board_len));
+
+	ret_cnt = simple_read_from_buffer(user_buf, count, ppos, buf, len);
+
+	mutex_unlock(&ar->conf_mutex);
+
+	kfree(buf);
+	return ret_cnt;
+}
+
+static const struct file_operations fops_fw_checksums = {
+	.read = ath10k_debug_fw_checksums_read,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
 int ath10k_debug_create(struct ath10k *ar)
 {
 	ar->debug.fw_crash_data = vzalloc(sizeof(*ar->debug.fw_crash_data));
@@ -2123,8 +2263,8 @@
 	debugfs_create_file("wmi_services", S_IRUSR, ar->debug.debugfs_phy, ar,
 			    &fops_wmi_services);
 
-	debugfs_create_file("simulate_fw_crash", S_IRUSR, ar->debug.debugfs_phy,
-			    ar, &fops_simulate_fw_crash);
+	debugfs_create_file("simulate_fw_crash", S_IRUSR | S_IWUSR,
+			    ar->debug.debugfs_phy, ar, &fops_simulate_fw_crash);
 
 	debugfs_create_file("fw_crash_dump", S_IRUSR, ar->debug.debugfs_phy,
 			    ar, &fops_fw_crash_dump);
@@ -2141,15 +2281,15 @@
 	debugfs_create_file("chip_id", S_IRUSR, ar->debug.debugfs_phy,
 			    ar, &fops_chip_id);
 
-	debugfs_create_file("htt_stats_mask", S_IRUSR, ar->debug.debugfs_phy,
-			    ar, &fops_htt_stats_mask);
+	debugfs_create_file("htt_stats_mask", S_IRUSR | S_IWUSR,
+			    ar->debug.debugfs_phy, ar, &fops_htt_stats_mask);
 
 	debugfs_create_file("htt_max_amsdu_ampdu", S_IRUSR | S_IWUSR,
 			    ar->debug.debugfs_phy, ar,
 			    &fops_htt_max_amsdu_ampdu);
 
-	debugfs_create_file("fw_dbglog", S_IRUSR, ar->debug.debugfs_phy,
-			    ar, &fops_fw_dbglog);
+	debugfs_create_file("fw_dbglog", S_IRUSR | S_IWUSR,
+			    ar->debug.debugfs_phy, ar, &fops_fw_dbglog);
 
 	debugfs_create_file("cal_data", S_IRUSR, ar->debug.debugfs_phy,
 			    ar, &fops_cal_data);
@@ -2183,6 +2323,13 @@
 	debugfs_create_file("tpc_stats", S_IRUSR,
 			    ar->debug.debugfs_phy, ar, &fops_tpc_stats);
 
+	if (test_bit(WMI_SERVICE_COEX_GPIO, ar->wmi.svc_map))
+		debugfs_create_file("btcoex", S_IRUGO | S_IWUSR,
+				    ar->debug.debugfs_phy, ar, &fops_btcoex);
+
+	debugfs_create_file("fw_checksums", S_IRUSR,
+			    ar->debug.debugfs_phy, ar, &fops_fw_checksums);
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/debug.h b/drivers/net/wireless/ath/ath10k/debug.h
index 7de780c..814719c 100644
--- a/drivers/net/wireless/ath/ath10k/debug.h
+++ b/drivers/net/wireless/ath/ath10k/debug.h
@@ -63,6 +63,10 @@
 __printf(2, 3) void ath10k_info(struct ath10k *ar, const char *fmt, ...);
 __printf(2, 3) void ath10k_err(struct ath10k *ar, const char *fmt, ...);
 __printf(2, 3) void ath10k_warn(struct ath10k *ar, const char *fmt, ...);
+
+void ath10k_debug_print_hwfw_info(struct ath10k *ar);
+void ath10k_debug_print_board_info(struct ath10k *ar);
+void ath10k_debug_print_boot_info(struct ath10k *ar);
 void ath10k_print_driver_info(struct ath10k *ar);
 
 #ifdef CONFIG_ATH10K_DEBUGFS
diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h
index 2bad50e..47ca048 100644
--- a/drivers/net/wireless/ath/ath10k/htt.h
+++ b/drivers/net/wireless/ath/ath10k/htt.h
@@ -166,8 +166,13 @@
 	__le16 len;
 	__le16 id;
 	__le32 frags_paddr;
-	__le16 peerid;
-	__le16 freq;
+	union {
+		__le32 peerid;
+		struct {
+			__le16 peerid;
+			__le16 freq;
+		} __packed offchan_tx;
+	} __packed;
 	u8 prefetch[0]; /* start of frame, for FW classification engine */
 } __packed;
 
@@ -1597,6 +1602,10 @@
 int ath10k_htt_tx_alloc_msdu_id(struct ath10k_htt *htt, struct sk_buff *skb);
 void ath10k_htt_tx_free_msdu_id(struct ath10k_htt *htt, u16 msdu_id);
 int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *);
-int ath10k_htt_tx(struct ath10k_htt *htt, struct sk_buff *);
+int ath10k_htt_tx(struct ath10k_htt *htt,
+		  enum ath10k_hw_txrx_mode txmode,
+		  struct sk_buff *msdu);
+void ath10k_htt_rx_pktlog_completion_handler(struct ath10k *ar,
+					     struct sk_buff *skb);
 
 #endif
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index 6060dda..91afa3a 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -536,7 +536,7 @@
 
 	size = htt->rx_ring.size * sizeof(htt->rx_ring.paddrs_ring);
 
-	vaddr = dma_alloc_coherent(htt->ar->dev, size, &paddr, GFP_DMA);
+	vaddr = dma_alloc_coherent(htt->ar->dev, size, &paddr, GFP_KERNEL);
 	if (!vaddr)
 		goto err_dma_ring;
 
@@ -545,7 +545,7 @@
 
 	vaddr = dma_alloc_coherent(htt->ar->dev,
 				   sizeof(*htt->rx_ring.alloc_idx.vaddr),
-				   &paddr, GFP_DMA);
+				   &paddr, GFP_KERNEL);
 	if (!vaddr)
 		goto err_dma_idx;
 
@@ -674,7 +674,7 @@
 		rate &= ~RX_PPDU_START_RATE_FLAG;
 
 		sband = &ar->mac.sbands[status->band];
-		status->rate_idx = ath10k_mac_hw_rate_to_idx(sband, rate);
+		status->rate_idx = ath10k_mac_hw_rate_to_idx(sband, rate, cck);
 		break;
 	case HTT_RX_HT:
 	case HTT_RX_HT_WITH_TXBF:
@@ -1114,7 +1114,20 @@
 	 */
 
 	/* pull decapped header and copy SA & DA */
-	hdr = (struct ieee80211_hdr *)msdu->data;
+	if ((ar->hw_params.hw_4addr_pad == ATH10K_HW_4ADDR_PAD_BEFORE) &&
+	    ieee80211_has_a4(((struct ieee80211_hdr *)first_hdr)->frame_control)) {
+		/* The QCA99X0 4 address mode pad 2 bytes at the
+		 * beginning of MSDU
+		 */
+		hdr = (struct ieee80211_hdr *)(msdu->data + 2);
+		/* The skb length need be extended 2 as the 2 bytes at the tail
+		 * be excluded due to the padding
+		 */
+		skb_put(msdu, 2);
+	} else {
+		hdr = (struct ieee80211_hdr *)(msdu->data);
+	}
+
 	hdr_len = ath10k_htt_rx_nwifi_hdrlen(ar, hdr);
 	ether_addr_copy(da, ieee80211_get_DA(hdr));
 	ether_addr_copy(sa, ieee80211_get_SA(hdr));
@@ -2127,6 +2140,18 @@
 }
 EXPORT_SYMBOL(ath10k_htt_t2h_msg_handler);
 
+void ath10k_htt_rx_pktlog_completion_handler(struct ath10k *ar,
+					     struct sk_buff *skb)
+{
+	struct ath10k_pktlog_10_4_hdr *hdr =
+		(struct ath10k_pktlog_10_4_hdr *)skb->data;
+
+	trace_ath10k_htt_pktlog(ar, hdr->payload,
+				sizeof(*hdr) + __le16_to_cpu(hdr->size));
+	dev_kfree_skb_any(skb);
+}
+EXPORT_SYMBOL(ath10k_htt_rx_pktlog_completion_handler);
+
 static void ath10k_htt_txrx_compl_task(unsigned long ptr)
 {
 	struct ath10k_htt *htt = (struct ath10k_htt *)ptr;
diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index 1682397..b3adadb 100644
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -111,7 +111,7 @@
 	size = htt->max_num_pending_tx * sizeof(struct ath10k_htt_txbuf);
 	htt->txbuf.vaddr = dma_alloc_coherent(ar->dev, size,
 						  &htt->txbuf.paddr,
-						  GFP_DMA);
+						  GFP_KERNEL);
 	if (!htt->txbuf.vaddr) {
 		ath10k_err(ar, "failed to alloc tx buffer\n");
 		ret = -ENOMEM;
@@ -124,7 +124,7 @@
 	size = htt->max_num_pending_tx * sizeof(struct htt_msdu_ext_desc);
 	htt->frag_desc.vaddr = dma_alloc_coherent(ar->dev, size,
 						  &htt->frag_desc.paddr,
-						  GFP_DMA);
+						  GFP_KERNEL);
 	if (!htt->frag_desc.vaddr) {
 		ath10k_warn(ar, "failed to alloc fragment desc memory\n");
 		ret = -ENOMEM;
@@ -439,6 +439,35 @@
 	return 0;
 }
 
+static u8 ath10k_htt_tx_get_vdev_id(struct ath10k *ar, struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ath10k_skb_cb *cb = ATH10K_SKB_CB(skb);
+	struct ath10k_vif *arvif = (void *)cb->vif->drv_priv;
+
+	if (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN)
+		return ar->scan.vdev_id;
+	else if (cb->vif)
+		return arvif->vdev_id;
+	else if (ar->monitor_started)
+		return ar->monitor_vdev_id;
+	else
+		return 0;
+}
+
+static u8 ath10k_htt_tx_get_tid(struct sk_buff *skb, bool is_eth)
+{
+	struct ieee80211_hdr *hdr = (void *)skb->data;
+	struct ath10k_skb_cb *cb = ATH10K_SKB_CB(skb);
+
+	if (!is_eth && ieee80211_is_mgmt(hdr->frame_control))
+		return HTT_DATA_TX_EXT_TID_MGMT;
+	else if (cb->flags & ATH10K_SKB_F_QOS)
+		return skb->priority % IEEE80211_QOS_CTL_TID_MASK;
+	else
+		return HTT_DATA_TX_EXT_TID_NON_QOS_MCAST_BCAST;
+}
+
 int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
 {
 	struct ath10k *ar = htt->ar;
@@ -446,7 +475,7 @@
 	struct sk_buff *txdesc = NULL;
 	struct htt_cmd *cmd;
 	struct ath10k_skb_cb *skb_cb = ATH10K_SKB_CB(msdu);
-	u8 vdev_id = skb_cb->vdev_id;
+	u8 vdev_id = ath10k_htt_tx_get_vdev_id(ar, msdu);
 	int len = 0;
 	int msdu_id = -1;
 	int res;
@@ -477,6 +506,13 @@
 
 	msdu_id = res;
 
+	if ((ieee80211_is_action(hdr->frame_control) ||
+	     ieee80211_is_deauth(hdr->frame_control) ||
+	     ieee80211_is_disassoc(hdr->frame_control)) &&
+	     ieee80211_has_protected(hdr->frame_control)) {
+		skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
+	}
+
 	txdesc = ath10k_htc_alloc_skb(ar, len);
 	if (!txdesc) {
 		res = -ENOMEM;
@@ -503,8 +539,6 @@
 	memcpy(cmd->mgmt_tx.hdr, msdu->data,
 	       min_t(int, msdu->len, HTT_MGMT_FRM_HDR_DOWNLOAD_LEN));
 
-	skb_cb->htt.txbuf = NULL;
-
 	res = ath10k_htc_send(&htt->ar->htc, htt->eid, txdesc);
 	if (res)
 		goto err_unmap_msdu;
@@ -525,21 +559,27 @@
 	return res;
 }
 
-int ath10k_htt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
+int ath10k_htt_tx(struct ath10k_htt *htt, enum ath10k_hw_txrx_mode txmode,
+		  struct sk_buff *msdu)
 {
 	struct ath10k *ar = htt->ar;
 	struct device *dev = ar->dev;
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)msdu->data;
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(msdu);
 	struct ath10k_skb_cb *skb_cb = ATH10K_SKB_CB(msdu);
 	struct ath10k_hif_sg_item sg_items[2];
+	struct ath10k_htt_txbuf *txbuf;
 	struct htt_data_tx_desc_frag *frags;
-	u8 vdev_id = skb_cb->vdev_id;
-	u8 tid = skb_cb->htt.tid;
+	bool is_eth = (txmode == ATH10K_HW_TXRX_ETHERNET);
+	u8 vdev_id = ath10k_htt_tx_get_vdev_id(ar, msdu);
+	u8 tid = ath10k_htt_tx_get_tid(msdu, is_eth);
 	int prefetch_len;
 	int res;
 	u8 flags0 = 0;
 	u16 msdu_id, flags1 = 0;
+	u16 freq = 0;
 	u32 frags_paddr = 0;
+	u32 txbuf_paddr;
 	struct htt_msdu_ext_desc *ext_desc = NULL;
 	bool limit_mgmt_desc = false;
 	bool is_probe_resp = false;
@@ -567,17 +607,17 @@
 	prefetch_len = min(htt->prefetch_len, msdu->len);
 	prefetch_len = roundup(prefetch_len, 4);
 
-	skb_cb->htt.txbuf = &htt->txbuf.vaddr[msdu_id];
-	skb_cb->htt.txbuf_paddr = htt->txbuf.paddr +
-		(sizeof(struct ath10k_htt_txbuf) * msdu_id);
+	txbuf = &htt->txbuf.vaddr[msdu_id];
+	txbuf_paddr = htt->txbuf.paddr +
+		      (sizeof(struct ath10k_htt_txbuf) * msdu_id);
 
 	if ((ieee80211_is_action(hdr->frame_control) ||
 	     ieee80211_is_deauth(hdr->frame_control) ||
 	     ieee80211_is_disassoc(hdr->frame_control)) &&
 	     ieee80211_has_protected(hdr->frame_control)) {
 		skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
-	} else if (!skb_cb->htt.nohwcrypt &&
-		   skb_cb->txmode == ATH10K_HW_TXRX_RAW &&
+	} else if (!(skb_cb->flags & ATH10K_SKB_F_NO_HWCRYPT) &&
+		   txmode == ATH10K_HW_TXRX_RAW &&
 		   ieee80211_has_protected(hdr->frame_control)) {
 		skb_put(msdu, IEEE80211_CCMP_MIC_LEN);
 	}
@@ -590,7 +630,10 @@
 		goto err_free_msdu_id;
 	}
 
-	switch (skb_cb->txmode) {
+	if (unlikely(info->flags & IEEE80211_TX_CTL_TX_OFFCHAN))
+		freq = ar->scan.roc_freq;
+
+	switch (txmode) {
 	case ATH10K_HW_TXRX_RAW:
 	case ATH10K_HW_TXRX_NATIVE_WIFI:
 		flags0 |= HTT_DATA_TX_DESC_FLAGS0_MAC_HDR_PRESENT;
@@ -610,16 +653,16 @@
 			frags_paddr =  htt->frag_desc.paddr +
 				(sizeof(struct htt_msdu_ext_desc) * msdu_id);
 		} else {
-			frags = skb_cb->htt.txbuf->frags;
+			frags = txbuf->frags;
 			frags[0].dword_addr.paddr =
 				__cpu_to_le32(skb_cb->paddr);
 			frags[0].dword_addr.len = __cpu_to_le32(msdu->len);
 			frags[1].dword_addr.paddr = 0;
 			frags[1].dword_addr.len = 0;
 
-			frags_paddr = skb_cb->htt.txbuf_paddr;
+			frags_paddr = txbuf_paddr;
 		}
-		flags0 |= SM(skb_cb->txmode, HTT_DATA_TX_DESC_FLAGS0_PKT_TYPE);
+		flags0 |= SM(txmode, HTT_DATA_TX_DESC_FLAGS0_PKT_TYPE);
 		break;
 	case ATH10K_HW_TXRX_MGMT:
 		flags0 |= SM(ATH10K_HW_TXRX_MGMT,
@@ -646,17 +689,13 @@
 	 * avoid extra memory allocations, compress data structures and thus
 	 * improve performance. */
 
-	skb_cb->htt.txbuf->htc_hdr.eid = htt->eid;
-	skb_cb->htt.txbuf->htc_hdr.len = __cpu_to_le16(
-			sizeof(skb_cb->htt.txbuf->cmd_hdr) +
-			sizeof(skb_cb->htt.txbuf->cmd_tx) +
-			prefetch_len);
-	skb_cb->htt.txbuf->htc_hdr.flags = 0;
+	txbuf->htc_hdr.eid = htt->eid;
+	txbuf->htc_hdr.len = __cpu_to_le16(sizeof(txbuf->cmd_hdr) +
+					   sizeof(txbuf->cmd_tx) +
+					   prefetch_len);
+	txbuf->htc_hdr.flags = 0;
 
-	if (skb_cb->htt.nohwcrypt)
-		flags0 |= HTT_DATA_TX_DESC_FLAGS0_NO_ENCRYPT;
-
-	if (!skb_cb->is_protected)
+	if (skb_cb->flags & ATH10K_SKB_F_NO_HWCRYPT)
 		flags0 |= HTT_DATA_TX_DESC_FLAGS0_NO_ENCRYPT;
 
 	flags1 |= SM((u16)vdev_id, HTT_DATA_TX_DESC_FLAGS1_VDEV_ID);
@@ -675,20 +714,27 @@
 	 */
 	flags1 |= HTT_DATA_TX_DESC_FLAGS1_POSTPONED;
 
-	skb_cb->htt.txbuf->cmd_hdr.msg_type = HTT_H2T_MSG_TYPE_TX_FRM;
-	skb_cb->htt.txbuf->cmd_tx.flags0 = flags0;
-	skb_cb->htt.txbuf->cmd_tx.flags1 = __cpu_to_le16(flags1);
-	skb_cb->htt.txbuf->cmd_tx.len = __cpu_to_le16(msdu->len);
-	skb_cb->htt.txbuf->cmd_tx.id = __cpu_to_le16(msdu_id);
-	skb_cb->htt.txbuf->cmd_tx.frags_paddr = __cpu_to_le32(frags_paddr);
-	skb_cb->htt.txbuf->cmd_tx.peerid = __cpu_to_le16(HTT_INVALID_PEERID);
-	skb_cb->htt.txbuf->cmd_tx.freq = __cpu_to_le16(skb_cb->htt.freq);
+	txbuf->cmd_hdr.msg_type = HTT_H2T_MSG_TYPE_TX_FRM;
+	txbuf->cmd_tx.flags0 = flags0;
+	txbuf->cmd_tx.flags1 = __cpu_to_le16(flags1);
+	txbuf->cmd_tx.len = __cpu_to_le16(msdu->len);
+	txbuf->cmd_tx.id = __cpu_to_le16(msdu_id);
+	txbuf->cmd_tx.frags_paddr = __cpu_to_le32(frags_paddr);
+	if (ath10k_mac_tx_frm_has_freq(ar)) {
+		txbuf->cmd_tx.offchan_tx.peerid =
+				__cpu_to_le16(HTT_INVALID_PEERID);
+		txbuf->cmd_tx.offchan_tx.freq =
+				__cpu_to_le16(freq);
+	} else {
+		txbuf->cmd_tx.peerid =
+				__cpu_to_le32(HTT_INVALID_PEERID);
+	}
 
 	trace_ath10k_htt_tx(ar, msdu_id, msdu->len, vdev_id, tid);
 	ath10k_dbg(ar, ATH10K_DBG_HTT,
 		   "htt tx flags0 %hhu flags1 %hu len %d id %hu frags_paddr %08x, msdu_paddr %08x vdev %hhu tid %hhu freq %hu\n",
 		   flags0, flags1, msdu->len, msdu_id, frags_paddr,
-		   (u32)skb_cb->paddr, vdev_id, tid, skb_cb->htt.freq);
+		   (u32)skb_cb->paddr, vdev_id, tid, freq);
 	ath10k_dbg_dump(ar, ATH10K_DBG_HTT_DUMP, NULL, "htt tx msdu: ",
 			msdu->data, msdu->len);
 	trace_ath10k_tx_hdr(ar, msdu->data, msdu->len);
@@ -696,12 +742,12 @@
 
 	sg_items[0].transfer_id = 0;
 	sg_items[0].transfer_context = NULL;
-	sg_items[0].vaddr = &skb_cb->htt.txbuf->htc_hdr;
-	sg_items[0].paddr = skb_cb->htt.txbuf_paddr +