diff --git a/Documentation/arm/sunxi/README b/Documentation/arm/sunxi/README
index 1fe2d7f..5e38e158 100644
--- a/Documentation/arm/sunxi/README
+++ b/Documentation/arm/sunxi/README
@@ -36,7 +36,7 @@
         + User Manual
           http://dl.linux-sunxi.org/A20/A20%20User%20Manual%202013-03-22.pdf
 
-      - Allwinner A23
+      - Allwinner A23 (sun8i)
         + Datasheet
           http://dl.linux-sunxi.org/A23/A23%20Datasheet%20V1.0%2020130830.pdf
         + User Manual
@@ -55,7 +55,23 @@
         + User Manual
           http://dl.linux-sunxi.org/A31/A3x_release_document/A31s/IC/A31s%20User%20Manual%20%20V1.0%2020130322.pdf
 
+      - Allwinner A33 (sun8i)
+        + Datasheet
+          http://dl.linux-sunxi.org/A33/A33%20Datasheet%20release%201.1.pdf
+        + User Manual
+          http://dl.linux-sunxi.org/A33/A33%20user%20manual%20release%201.1.pdf
+
+      - Allwinner H3 (sun8i)
+        + Datasheet
+          http://dl.linux-sunxi.org/H3/Allwinner_H3_Datasheet_V1.0.pdf
+
     * Quad ARM Cortex-A15, Quad ARM Cortex-A7 based SoCs
       - Allwinner A80
         + Datasheet
 	  http://dl.linux-sunxi.org/A80/A80_Datasheet_Revision_1.0_0404.pdf
+
+    * Octa ARM Cortex-A7 based SoCs
+      - Allwinner A83T
+        + Not Supported
+        + Datasheet
+          http://dl.linux-sunxi.org/A83T/A83T_datasheet_Revision_1.1.pdf
diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt
index 2251dcc..06c88a4 100644
--- a/Documentation/devicetree/bindings/arm/l2cc.txt
+++ b/Documentation/devicetree/bindings/arm/l2cc.txt
@@ -67,6 +67,12 @@
   disable if zero.
 - arm,prefetch-offset : Override prefetch offset value. Valid values are
   0-7, 15, 23, and 31.
+- arm,shared-override : The default behavior of the pl310 cache controller with
+  respect to the shareable attribute is to transform "normal memory
+  non-cacheable transactions" into "cacheable no allocate" (for reads) or
+  "write through no write allocate" (for writes).
+  On systems where this may cause DMA buffer corruption, this property must be
+  specified to indicate that such transforms are precluded.
 - prefetch-data : Data prefetch. Value: <0> (forcibly disable), <1>
   (forcibly enable), property absent (retain settings set by firmware)
 - prefetch-instr : Instruction prefetch. Value: <0> (forcibly disable),
diff --git a/Documentation/devicetree/bindings/arm/sunxi.txt b/Documentation/devicetree/bindings/arm/sunxi.txt
index 42941fd..67da205 100644
--- a/Documentation/devicetree/bindings/arm/sunxi.txt
+++ b/Documentation/devicetree/bindings/arm/sunxi.txt
@@ -9,4 +9,6 @@
   allwinner,sun6i-a31
   allwinner,sun7i-a20
   allwinner,sun8i-a23
+  allwinner,sun8i-a33
+  allwinner,sun8i-h3
   allwinner,sun9i-a80
diff --git a/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt b/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
index 938f8e1..0db6047 100644
--- a/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
@@ -8,6 +8,7 @@
 Required properties:
 - compatible	: Should be of the form "ti,emif-<ip-rev>" where <ip-rev>
   is the IP revision of the specific EMIF instance.
+		  For am437x should be ti,emif-am4372.
 
 - phy-type	: <u32> indicating the DDR phy type. Following are the
   allowed values
diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt
index f732a83..8cc17ca 100644
--- a/Documentation/power/swsusp.txt
+++ b/Documentation/power/swsusp.txt
@@ -410,8 +410,17 @@
 
 Q: Can I suspend-to-disk using a swap partition under LVM?
 
-A: No. You can suspend successfully, but you'll not be able to
-resume. uswsusp should be able to work with LVM. See suspend.sf.net.
+A: Yes and No.  You can suspend successfully, but the kernel will not be able
+to resume on its own.  You need an initramfs that can recognize the resume
+situation, activate the logical volume containing the swap volume (but not
+touch any filesystems!), and eventually call
+
+echo -n "$major:$minor" > /sys/power/resume
+
+where $major and $minor are the respective major and minor device numbers of
+the swap volume.
+
+uswsusp works with LVM, too.  See http://suspend.sourceforge.net/
 
 Q: I upgraded the kernel from 2.6.15 to 2.6.16. Both kernels were
 compiled with the similar configuration files. Anyway I found that
diff --git a/MAINTAINERS b/MAINTAINERS
index 8133cef..fd60784 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1614,6 +1614,7 @@
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/boot/dts/vexpress*
+F:	arch/arm64/boot/dts/arm/vexpress*
 F:	arch/arm/mach-vexpress/
 F:	*/*/vexpress*
 F:	*/*/*/vexpress*
@@ -2562,19 +2563,31 @@
 F:	arch/powerpc/oprofile/*cell*
 F:	arch/powerpc/platforms/cell/
 
-CEPH DISTRIBUTED FILE SYSTEM CLIENT
+CEPH COMMON CODE (LIBCEPH)
+M:	Ilya Dryomov <idryomov@gmail.com>
 M:	"Yan, Zheng" <zyan@redhat.com>
 M:	Sage Weil <sage@redhat.com>
 L:	ceph-devel@vger.kernel.org
 W:	http://ceph.com/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T:	git git://github.com/ceph/ceph-client.git
 S:	Supported
-F:	Documentation/filesystems/ceph.txt
-F:	fs/ceph/
 F:	net/ceph/
 F:	include/linux/ceph/
 F:	include/linux/crush/
 
+CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH)
+M:	"Yan, Zheng" <zyan@redhat.com>
+M:	Sage Weil <sage@redhat.com>
+M:	Ilya Dryomov <idryomov@gmail.com>
+L:	ceph-devel@vger.kernel.org
+W:	http://ceph.com/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T:	git git://github.com/ceph/ceph-client.git
+S:	Supported
+F:	Documentation/filesystems/ceph.txt
+F:	fs/ceph/
+
 CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
 L:	linux-usb@vger.kernel.org
 S:	Orphan
@@ -6147,6 +6160,7 @@
 Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
 S:	Supported
 F:	drivers/nvdimm/pmem.c
+F:	include/linux/pmem.h
 
 LINUX FOR IBM pSERIES (RS/6000)
 M:	Paul Mackerras <paulus@au.ibm.com>
@@ -6161,7 +6175,7 @@
 W:	http://www.penguinppc.org/
 L:	linuxppc-dev@lists.ozlabs.org
 Q:	http://patchwork.ozlabs.org/project/linuxppc-dev/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git
 S:	Supported
 F:	Documentation/powerpc/
 F:	arch/powerpc/
@@ -8366,10 +8380,12 @@
 M:	Ilya Dryomov <idryomov@gmail.com>
 M:	Sage Weil <sage@redhat.com>
 M:	Alex Elder <elder@kernel.org>
-M:	ceph-devel@vger.kernel.org
+L:	ceph-devel@vger.kernel.org
 W:	http://ceph.com/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T:	git git://github.com/ceph/ceph-client.git
 S:	Supported
+F:	Documentation/ABI/testing/sysfs-bus-rbd
 F:	drivers/block/rbd.c
 F:	drivers/block/rbd_types.h
 
diff --git a/Makefile b/Makefile
index 13270c0..257ef58 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 2
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a750c14..3458828 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -188,6 +188,9 @@
 config ARCH_HAS_BANDGAP
 	bool
 
+config FIX_EARLYCON_MEM
+	def_bool y if MMU
+
 config GENERIC_HWEIGHT
 	bool
 	default y
@@ -1693,6 +1696,27 @@
 config HIGHPTE
 	bool "Allocate 2nd-level pagetables from highmem"
 	depends on HIGHMEM
+	help
+	  The VM uses one page of physical memory for each page table.
+	  For systems with a lot of processes, this can use a lot of
+	  precious low memory, eventually leading to low memory being
+	  consumed by page tables.  Setting this option will allow
+	  user-space 2nd level page tables to reside in high memory.
+
+config CPU_SW_DOMAIN_PAN
+	bool "Enable use of CPU domains to implement privileged no-access"
+	depends on MMU && !ARM_LPAE
+	default y
+	help
+	  Increase kernel security by ensuring that normal kernel accesses
+	  are unable to access userspace addresses.  This can help prevent
+	  use-after-free bugs becoming an exploitable privilege escalation
+	  by ensuring that magic values (such as LIST_POISON) will always
+	  fault when dereferenced.
+
+	  CPUs with low-vector mappings use a best-efforts implementation.
+	  Their lower 1MB needs to remain accessible for the vectors, but
+	  the remainder of userspace will become appropriately inaccessible.
 
 config HW_PERF_EVENTS
 	bool "Enable hardware performance counter support for perf events"
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index f1b1579..a2e16f9 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -1635,7 +1635,7 @@
 
 config DEBUG_SET_MODULE_RONX
 	bool "Set loadable kernel module data as NX and text as RO"
-	depends on MODULES
+	depends on MODULES && MMU
 	---help---
 	  This option helps catch unintended modifications to loadable
 	  kernel module's text and read-only data. It also prevents execution
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 07ab3d2..7451b44 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -312,6 +312,9 @@
 
 PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
 
+bootpImage uImage: zImage
+zImage: Image
+
 $(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts
index 901739f..5c42d25 100644
--- a/arch/arm/boot/dts/am335x-boneblack.dts
+++ b/arch/arm/boot/dts/am335x-boneblack.dts
@@ -80,3 +80,7 @@
 		status = "okay";
 	};
 };
+
+&rtc {
+	system-power-controller;
+};
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index c80a3e2..ade28c79 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -132,6 +132,12 @@
 			};
 		};
 
+		emif: emif@4c000000 {
+			compatible = "ti,emif-am4372";
+			reg = <0x4c000000 0x1000000>;
+			ti,hwmods = "emif";
+		};
+
 		edma: edma@49000000 {
 			compatible = "ti,edma3";
 			ti,hwmods = "tpcc", "tptc0", "tptc1", "tptc2";
@@ -941,6 +947,7 @@
 				ti,hwmods = "dss_rfbi";
 				clocks = <&disp_clk>;
 				clock-names = "fck";
+				status = "disabled";
 			};
 		};
 
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index a42cc37..a63bf78 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -605,6 +605,10 @@
 	phy-supply = <&ldousb_reg>;
 };
 
+&usb2_phy2 {
+	phy-supply = <&ldousb_reg>;
+};
+
 &usb1 {
 	dr_mode = "host";
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/atlas7.dtsi b/arch/arm/boot/dts/atlas7.dtsi
index 5dfd3a4..3e21311 100644
--- a/arch/arm/boot/dts/atlas7.dtsi
+++ b/arch/arm/boot/dts/atlas7.dtsi
@@ -135,6 +135,1025 @@
 			compatible = "sirf,atlas7-ioc";
 			reg = <0x18880000 0x1000>,
 				<0x10E40000 0x1000>;
+
+			audio_ac97_pmx: audio_ac97@0 {
+				audio_ac97 {
+					groups = "audio_ac97_grp";
+					function = "audio_ac97";
+				};
+			};
+
+			audio_func_dbg_pmx: audio_func_dbg@0 {
+				audio_func_dbg {
+					groups = "audio_func_dbg_grp";
+					function = "audio_func_dbg";
+				};
+			};
+
+			audio_i2s_pmx: audio_i2s@0 {
+				audio_i2s {
+					groups = "audio_i2s_grp";
+					function = "audio_i2s";
+				};
+			};
+
+			audio_i2s_2ch_pmx: audio_i2s_2ch@0 {
+				audio_i2s_2ch {
+					groups = "audio_i2s_2ch_grp";
+					function = "audio_i2s_2ch";
+				};
+			};
+
+			audio_i2s_extclk_pmx: audio_i2s_extclk@0 {
+				audio_i2s_extclk {
+					groups = "audio_i2s_extclk_grp";
+					function = "audio_i2s_extclk";
+				};
+			};
+
+			audio_uart0_pmx: audio_uart0@0 {
+				audio_uart0 {
+					groups = "audio_uart0_grp";
+					function = "audio_uart0";
+				};
+			};
+
+			audio_uart1_pmx: audio_uart1@0 {
+				audio_uart1 {
+					groups = "audio_uart1_grp";
+					function = "audio_uart1";
+				};
+			};
+
+			audio_uart2_pmx0: audio_uart2@0 {
+				audio_uart2_0 {
+					groups = "audio_uart2_grp0";
+					function = "audio_uart2_m0";
+				};
+			};
+
+			audio_uart2_pmx1: audio_uart2@1 {
+				audio_uart2_1 {
+					groups = "audio_uart2_grp1";
+					function = "audio_uart2_m1";
+				};
+			};
+
+			c_can_trnsvr_pmx: c_can_trnsvr@0 {
+				c_can_trnsvr {
+					groups = "c_can_trnsvr_grp";
+					function = "c_can_trnsvr";
+				};
+			};
+
+			c0_can_pmx0: c0_can@0 {
+				c0_can_0 {
+					groups = "c0_can_grp0";
+					function = "c0_can_m0";
+				};
+			};
+
+			c0_can_pmx1: c0_can@1 {
+				c0_can_1 {
+					groups = "c0_can_grp1";
+					function = "c0_can_m1";
+				};
+			};
+
+			c1_can_pmx0: c1_can@0 {
+				c1_can_0 {
+					groups = "c1_can_grp0";
+					function = "c1_can_m0";
+				};
+			};
+
+			c1_can_pmx1: c1_can@1 {
+				c1_can_1 {
+					groups = "c1_can_grp1";
+					function = "c1_can_m1";
+				};
+			};
+
+			c1_can_pmx2: c1_can@2 {
+				c1_can_2 {
+					groups = "c1_can_grp2";
+					function = "c1_can_m2";
+				};
+			};
+
+			ca_audio_lpc_pmx: ca_audio_lpc@0 {
+				ca_audio_lpc {
+					groups = "ca_audio_lpc_grp";
+					function = "ca_audio_lpc";
+				};
+			};
+
+			ca_bt_lpc_pmx: ca_bt_lpc@0 {
+				ca_bt_lpc {
+					groups = "ca_bt_lpc_grp";
+					function = "ca_bt_lpc";
+				};
+			};
+
+			ca_coex_pmx: ca_coex@0 {
+				ca_coex {
+					groups = "ca_coex_grp";
+					function = "ca_coex";
+				};
+			};
+
+			ca_curator_lpc_pmx: ca_curator_lpc@0 {
+				ca_curator_lpc {
+					groups = "ca_curator_lpc_grp";
+					function = "ca_curator_lpc";
+				};
+			};
+
+			ca_pcm_debug_pmx: ca_pcm_debug@0 {
+				ca_pcm_debug {
+					groups = "ca_pcm_debug_grp";
+					function = "ca_pcm_debug";
+				};
+			};
+
+			ca_pio_pmx: ca_pio@0 {
+				ca_pio {
+					groups = "ca_pio_grp";
+					function = "ca_pio";
+				};
+			};
+
+			ca_sdio_debug_pmx: ca_sdio_debug@0 {
+				ca_sdio_debug {
+					groups = "ca_sdio_debug_grp";
+					function = "ca_sdio_debug";
+				};
+			};
+
+			ca_spi_pmx: ca_spi@0 {
+				ca_spi {
+					groups = "ca_spi_grp";
+					function = "ca_spi";
+				};
+			};
+
+			ca_trb_pmx: ca_trb@0 {
+				ca_trb {
+					groups = "ca_trb_grp";
+					function = "ca_trb";
+				};
+			};
+
+			ca_uart_debug_pmx: ca_uart_debug@0 {
+				ca_uart_debug {
+					groups = "ca_uart_debug_grp";
+					function = "ca_uart_debug";
+				};
+			};
+
+			clkc_pmx0: clkc@0 {
+				clkc_0 {
+					groups = "clkc_grp0";
+					function = "clkc_m0";
+				};
+			};
+
+			clkc_pmx1: clkc@1 {
+				clkc_1 {
+					groups = "clkc_grp1";
+					function = "clkc_m1";
+				};
+			};
+
+			gn_gnss_i2c_pmx: gn_gnss_i2c@0 {
+				gn_gnss_i2c {
+					groups = "gn_gnss_i2c_grp";
+					function = "gn_gnss_i2c";
+				};
+			};
+
+			gn_gnss_uart_nopause_pmx: gn_gnss_uart_nopause@0 {
+				gn_gnss_uart_nopause {
+					groups = "gn_gnss_uart_nopause_grp";
+					function = "gn_gnss_uart_nopause";
+				};
+			};
+
+			gn_gnss_uart_pmx: gn_gnss_uart@0 {
+				gn_gnss_uart {
+					groups = "gn_gnss_uart_grp";
+					function = "gn_gnss_uart";
+				};
+			};
+
+			gn_trg_spi_pmx0: gn_trg_spi@0 {
+				gn_trg_spi_0 {
+					groups = "gn_trg_spi_grp0";
+					function = "gn_trg_spi_m0";
+				};
+			};
+
+			gn_trg_spi_pmx1: gn_trg_spi@1 {
+				gn_trg_spi_1 {
+					groups = "gn_trg_spi_grp1";
+					function = "gn_trg_spi_m1";
+				};
+			};
+
+			cvbs_dbg_pmx: cvbs_dbg@0 {
+				cvbs_dbg {
+					groups = "cvbs_dbg_grp";
+					function = "cvbs_dbg";
+				};
+			};
+
+			cvbs_dbg_test_pmx0: cvbs_dbg_test@0 {
+				cvbs_dbg_test_0 {
+					groups = "cvbs_dbg_test_grp0";
+					function = "cvbs_dbg_test_m0";
+				};
+			};
+
+			cvbs_dbg_test_pmx1: cvbs_dbg_test@1 {
+				cvbs_dbg_test_1 {
+					groups = "cvbs_dbg_test_grp1";
+					function = "cvbs_dbg_test_m1";
+				};
+			};
+
+			cvbs_dbg_test_pmx2: cvbs_dbg_test@2 {
+				cvbs_dbg_test_2 {
+					groups = "cvbs_dbg_test_grp2";
+					function = "cvbs_dbg_test_m2";
+				};
+			};
+
+			cvbs_dbg_test_pmx3: cvbs_dbg_test@3 {
+				cvbs_dbg_test_3 {
+					groups = "cvbs_dbg_test_grp3";
+					function = "cvbs_dbg_test_m3";
+				};
+			};
+
+			cvbs_dbg_test_pmx4: cvbs_dbg_test@4 {
+				cvbs_dbg_test_4 {
+					groups = "cvbs_dbg_test_grp4";
+					function = "cvbs_dbg_test_m4";
+				};
+			};
+
+			cvbs_dbg_test_pmx5: cvbs_dbg_test@5 {
+				cvbs_dbg_test_5 {
+					groups = "cvbs_dbg_test_grp5";
+					function = "cvbs_dbg_test_m5";
+				};
+			};
+
+			cvbs_dbg_test_pmx6: cvbs_dbg_test@6 {
+				cvbs_dbg_test_6 {
+					groups = "cvbs_dbg_test_grp6";
+					function = "cvbs_dbg_test_m6";
+				};
+			};
+
+			cvbs_dbg_test_pmx7: cvbs_dbg_test@7 {
+				cvbs_dbg_test_7 {
+					groups = "cvbs_dbg_test_grp7";
+					function = "cvbs_dbg_test_m7";
+				};
+			};
+
+			cvbs_dbg_test_pmx8: cvbs_dbg_test@8 {
+				cvbs_dbg_test_8 {
+					groups = "cvbs_dbg_test_grp8";
+					function = "cvbs_dbg_test_m8";
+				};
+			};
+
+			cvbs_dbg_test_pmx9: cvbs_dbg_test@9 {
+				cvbs_dbg_test_9 {
+					groups = "cvbs_dbg_test_grp9";
+					function = "cvbs_dbg_test_m9";
+				};
+			};
+
+			cvbs_dbg_test_pmx10: cvbs_dbg_test@10 {
+				cvbs_dbg_test_10 {
+					groups = "cvbs_dbg_test_grp10";
+					function = "cvbs_dbg_test_m10";
+				};
+			};
+
+			cvbs_dbg_test_pmx11: cvbs_dbg_test@11 {
+				cvbs_dbg_test_11 {
+					groups = "cvbs_dbg_test_grp11";
+					function = "cvbs_dbg_test_m11";
+				};
+			};
+
+			cvbs_dbg_test_pmx12: cvbs_dbg_test@12 {
+				cvbs_dbg_test_12 {
+					groups = "cvbs_dbg_test_grp12";
+					function = "cvbs_dbg_test_m12";
+				};
+			};
+
+			cvbs_dbg_test_pmx13: cvbs_dbg_test@13 {
+				cvbs_dbg_test_13 {
+					groups = "cvbs_dbg_test_grp13";
+					function = "cvbs_dbg_test_m13";
+				};
+			};
+
+			cvbs_dbg_test_pmx14: cvbs_dbg_test@14 {
+				cvbs_dbg_test_14 {
+					groups = "cvbs_dbg_test_grp14";
+					function = "cvbs_dbg_test_m14";
+				};
+			};
+
+			cvbs_dbg_test_pmx15: cvbs_dbg_test@15 {
+				cvbs_dbg_test_15 {
+					groups = "cvbs_dbg_test_grp15";
+					function = "cvbs_dbg_test_m15";
+				};
+			};
+
+			gn_gnss_power_pmx: gn_gnss_power@0 {
+				gn_gnss_power {
+					groups = "gn_gnss_power_grp";
+					function = "gn_gnss_power";
+				};
+			};
+
+			gn_gnss_sw_status_pmx: gn_gnss_sw_status@0 {
+				gn_gnss_sw_status {
+					groups = "gn_gnss_sw_status_grp";
+					function = "gn_gnss_sw_status";
+				};
+			};
+
+			gn_gnss_eclk_pmx: gn_gnss_eclk@0 {
+				gn_gnss_eclk {
+					groups = "gn_gnss_eclk_grp";
+					function = "gn_gnss_eclk";
+				};
+			};
+
+			gn_gnss_irq1_pmx0: gn_gnss_irq1@0 {
+				gn_gnss_irq1_0 {
+					groups = "gn_gnss_irq1_grp0";
+					function = "gn_gnss_irq1_m0";
+				};
+			};
+
+			gn_gnss_irq2_pmx0: gn_gnss_irq2@0 {
+				gn_gnss_irq2_0 {
+					groups = "gn_gnss_irq2_grp0";
+					function = "gn_gnss_irq2_m0";
+				};
+			};
+
+			gn_gnss_tm_pmx: gn_gnss_tm@0 {
+				gn_gnss_tm {
+					groups = "gn_gnss_tm_grp";
+					function = "gn_gnss_tm";
+				};
+			};
+
+			gn_gnss_tsync_pmx: gn_gnss_tsync@0 {
+				gn_gnss_tsync {
+					groups = "gn_gnss_tsync_grp";
+					function = "gn_gnss_tsync";
+				};
+			};
+
+			gn_io_gnsssys_sw_cfg_pmx: gn_io_gnsssys_sw_cfg@0 {
+				gn_io_gnsssys_sw_cfg {
+					groups = "gn_io_gnsssys_sw_cfg_grp";
+					function = "gn_io_gnsssys_sw_cfg";
+				};
+			};
+
+			gn_trg_pmx0: gn_trg@0 {
+				gn_trg_0 {
+					groups = "gn_trg_grp0";
+					function = "gn_trg_m0";
+				};
+			};
+
+			gn_trg_pmx1: gn_trg@1 {
+				gn_trg_1 {
+					groups = "gn_trg_grp1";
+					function = "gn_trg_m1";
+				};
+			};
+
+			gn_trg_shutdown_pmx0: gn_trg_shutdown@0 {
+				gn_trg_shutdown_0 {
+					groups = "gn_trg_shutdown_grp0";
+					function = "gn_trg_shutdown_m0";
+				};
+			};
+
+			gn_trg_shutdown_pmx1: gn_trg_shutdown@1 {
+				gn_trg_shutdown_1 {
+					groups = "gn_trg_shutdown_grp1";
+					function = "gn_trg_shutdown_m1";
+				};
+			};
+
+			gn_trg_shutdown_pmx2: gn_trg_shutdown@2 {
+				gn_trg_shutdown_2 {
+					groups = "gn_trg_shutdown_grp2";
+					function = "gn_trg_shutdown_m2";
+				};
+			};
+
+			gn_trg_shutdown_pmx3: gn_trg_shutdown@3 {
+				gn_trg_shutdown_3 {
+					groups = "gn_trg_shutdown_grp3";
+					function = "gn_trg_shutdown_m3";
+				};
+			};
+
+			i2c0_pmx: i2c0@0 {
+				i2c0 {
+					groups = "i2c0_grp";
+					function = "i2c0";
+				};
+			};
+
+			i2c1_pmx: i2c1@0 {
+				i2c1 {
+					groups = "i2c1_grp";
+					function = "i2c1";
+				};
+			};
+
+			jtag_pmx0: jtag@0 {
+				jtag_0 {
+					groups = "jtag_grp0";
+					function = "jtag_m0";
+				};
+			};
+
+			ks_kas_spi_pmx0: ks_kas_spi@0 {
+				ks_kas_spi_0 {
+					groups = "ks_kas_spi_grp0";
+					function = "ks_kas_spi_m0";
+				};
+			};
+
+			ld_ldd_pmx: ld_ldd@0 {
+				ld_ldd {
+					groups = "ld_ldd_grp";
+					function = "ld_ldd";
+				};
+			};
+
+			ld_ldd_16bit_pmx: ld_ldd_16bit@0 {
+				ld_ldd_16bit {
+					groups = "ld_ldd_16bit_grp";
+					function = "ld_ldd_16bit";
+				};
+			};
+
+			ld_ldd_fck_pmx: ld_ldd_fck@0 {
+				ld_ldd_fck {
+					groups = "ld_ldd_fck_grp";
+					function = "ld_ldd_fck";
+				};
+			};
+
+			ld_ldd_lck_pmx: ld_ldd_lck@0 {
+				ld_ldd_lck {
+					groups = "ld_ldd_lck_grp";
+					function = "ld_ldd_lck";
+				};
+			};
+
+			lr_lcdrom_pmx: lr_lcdrom@0 {
+				lr_lcdrom {
+					groups = "lr_lcdrom_grp";
+					function = "lr_lcdrom";
+				};
+			};
+
+			lvds_analog_pmx: lvds_analog@0 {
+				lvds_analog {
+					groups = "lvds_analog_grp";
+					function = "lvds_analog";
+				};
+			};
+
+			nd_df_pmx: nd_df@0 {
+				nd_df {
+					groups = "nd_df_grp";
+					function = "nd_df";
+				};
+			};
+
+			nd_df_nowp_pmx: nd_df_nowp@0 {
+				nd_df_nowp {
+					groups = "nd_df_nowp_grp";
+					function = "nd_df_nowp";
+				};
+			};
+
+			ps_pmx: ps@0 {
+				ps {
+					groups = "ps_grp";
+					function = "ps";
+				};
+			};
+
+			pwc_core_on_pmx: pwc_core_on@0 {
+				pwc_core_on {
+					groups = "pwc_core_on_grp";
+					function = "pwc_core_on";
+				};
+			};
+
+			pwc_ext_on_pmx: pwc_ext_on@0 {
+				pwc_ext_on {
+					groups = "pwc_ext_on_grp";
+					function = "pwc_ext_on";
+				};
+			};
+
+			pwc_gpio3_clk_pmx: pwc_gpio3_clk@0 {
+				pwc_gpio3_clk {
+					groups = "pwc_gpio3_clk_grp";
+					function = "pwc_gpio3_clk";
+				};
+			};
+
+			pwc_io_on_pmx: pwc_io_on@0 {
+				pwc_io_on {
+					groups = "pwc_io_on_grp";
+					function = "pwc_io_on";
+				};
+			};
+
+			pwc_lowbatt_b_pmx0: pwc_lowbatt_b@0 {
+				pwc_lowbatt_b_0 {
+					groups = "pwc_lowbatt_b_grp0";
+					function = "pwc_lowbatt_b_m0";
+				};
+			};
+
+			pwc_mem_on_pmx: pwc_mem_on@0 {
+				pwc_mem_on {
+					groups = "pwc_mem_on_grp";
+					function = "pwc_mem_on";
+				};
+			};
+
+			pwc_on_key_b_pmx0: pwc_on_key_b@0 {
+				pwc_on_key_b_0 {
+					groups = "pwc_on_key_b_grp0";
+					function = "pwc_on_key_b_m0";
+				};
+			};
+
+			pwc_wakeup_src0_pmx: pwc_wakeup_src0@0 {
+				pwc_wakeup_src0 {
+					groups = "pwc_wakeup_src0_grp";
+					function = "pwc_wakeup_src0";
+				};
+			};
+
+			pwc_wakeup_src1_pmx: pwc_wakeup_src1@0 {
+				pwc_wakeup_src1 {
+					groups = "pwc_wakeup_src1_grp";
+					function = "pwc_wakeup_src1";
+				};
+			};
+
+			pwc_wakeup_src2_pmx: pwc_wakeup_src2@0 {
+				pwc_wakeup_src2 {
+					groups = "pwc_wakeup_src2_grp";
+					function = "pwc_wakeup_src2";
+				};
+			};
+
+			pwc_wakeup_src3_pmx: pwc_wakeup_src3@0 {
+				pwc_wakeup_src3 {
+					groups = "pwc_wakeup_src3_grp";
+					function = "pwc_wakeup_src3";
+				};
+			};
+
+			pw_cko0_pmx0: pw_cko0@0 {
+				pw_cko0_0 {
+					groups = "pw_cko0_grp0";
+					function = "pw_cko0_m0";
+				};
+			};
+
+			pw_cko0_pmx1: pw_cko0@1 {
+				pw_cko0_1 {
+					groups = "pw_cko0_grp1";
+					function = "pw_cko0_m1";
+				};
+			};
+
+			pw_cko0_pmx2: pw_cko0@2 {
+				pw_cko0_2 {
+					groups = "pw_cko0_grp2";
+					function = "pw_cko0_m2";
+				};
+			};
+
+			pw_cko1_pmx0: pw_cko1@0 {
+				pw_cko1_0 {
+					groups = "pw_cko1_grp0";
+					function = "pw_cko1_m0";
+				};
+			};
+
+			pw_cko1_pmx1: pw_cko1@1 {
+				pw_cko1_1 {
+					groups = "pw_cko1_grp1";
+					function = "pw_cko1_m1";
+				};
+			};
+
+			pw_i2s01_clk_pmx0: pw_i2s01_clk@0 {
+				pw_i2s01_clk_0 {
+					groups = "pw_i2s01_clk_grp0";
+					function = "pw_i2s01_clk_m0";
+				};
+			};
+
+			pw_i2s01_clk_pmx1: pw_i2s01_clk@1 {
+				pw_i2s01_clk_1 {
+					groups = "pw_i2s01_clk_grp1";
+					function = "pw_i2s01_clk_m1";
+				};
+			};
+
+			pw_pwm0_pmx: pw_pwm0@0 {
+				pw_pwm0 {
+					groups = "pw_pwm0_grp";
+					function = "pw_pwm0";
+				};
+			};
+
+			pw_pwm1_pmx: pw_pwm1@0 {
+				pw_pwm1 {
+					groups = "pw_pwm1_grp";
+					function = "pw_pwm1";
+				};
+			};
+
+			pw_pwm2_pmx0: pw_pwm2@0 {
+				pw_pwm2_0 {
+					groups = "pw_pwm2_grp0";
+					function = "pw_pwm2_m0";
+				};
+			};
+
+			pw_pwm2_pmx1: pw_pwm2@1 {
+				pw_pwm2_1 {
+					groups = "pw_pwm2_grp1";
+					function = "pw_pwm2_m1";
+				};
+			};
+
+			pw_pwm3_pmx0: pw_pwm3@0 {
+				pw_pwm3_0 {
+					groups = "pw_pwm3_grp0";
+					function = "pw_pwm3_m0";
+				};
+			};
+
+			pw_pwm3_pmx1: pw_pwm3@1 {
+				pw_pwm3_1 {
+					groups = "pw_pwm3_grp1";
+					function = "pw_pwm3_m1";
+				};
+			};
+
+			pw_pwm_cpu_vol_pmx0: pw_pwm_cpu_vol@0 {
+				pw_pwm_cpu_vol_0 {
+					groups = "pw_pwm_cpu_vol_grp0";
+					function = "pw_pwm_cpu_vol_m0";
+				};
+			};
+
+			pw_pwm_cpu_vol_pmx1: pw_pwm_cpu_vol@1 {
+				pw_pwm_cpu_vol_1 {
+					groups = "pw_pwm_cpu_vol_grp1";
+					function = "pw_pwm_cpu_vol_m1";
+				};
+			};
+
+			pw_backlight_pmx0: pw_backlight@0 {
+				pw_backlight_0 {
+					groups = "pw_backlight_grp0";
+					function = "pw_backlight_m0";
+				};
+			};
+
+			pw_backlight_pmx1: pw_backlight@1 {
+				pw_backlight_1 {
+					groups = "pw_backlight_grp1";
+					function = "pw_backlight_m1";
+				};
+			};
+
+			rg_eth_mac_pmx: rg_eth_mac@0 {
+				rg_eth_mac {
+					groups = "rg_eth_mac_grp";
+					function = "rg_eth_mac";
+				};
+			};
+
+			rg_gmac_phy_intr_n_pmx: rg_gmac_phy_intr_n@0 {
+				rg_gmac_phy_intr_n {
+					groups = "rg_gmac_phy_intr_n_grp";
+					function = "rg_gmac_phy_intr_n";
+				};
+			};
+
+			rg_rgmii_mac_pmx: rg_rgmii_mac@0 {
+				rg_rgmii_mac {
+					groups = "rg_rgmii_mac_grp";
+					function = "rg_rgmii_mac";
+				};
+			};
+
+			rg_rgmii_phy_ref_clk_pmx0: rg_rgmii_phy_ref_clk@0 {
+				rg_rgmii_phy_ref_clk_0 {
+					groups =
+						"rg_rgmii_phy_ref_clk_grp0";
+					function =
+						"rg_rgmii_phy_ref_clk_m0";
+				};
+			};
+
+			rg_rgmii_phy_ref_clk_pmx1: rg_rgmii_phy_ref_clk@1 {
+				rg_rgmii_phy_ref_clk_1 {
+					groups =
+						"rg_rgmii_phy_ref_clk_grp1";
+					function =
+						"rg_rgmii_phy_ref_clk_m1";
+				};
+			};
+
+			sd0_pmx: sd0@0 {
+				sd0 {
+					groups = "sd0_grp";
+					function = "sd0";
+				};
+			};
+
+			sd0_4bit_pmx: sd0_4bit@0 {
+				sd0_4bit {
+					groups = "sd0_4bit_grp";
+					function = "sd0_4bit";
+				};
+			};
+
+			sd1_pmx: sd1@0 {
+				sd1 {
+					groups = "sd1_grp";
+					function = "sd1";
+				};
+			};
+
+			sd1_4bit_pmx0: sd1_4bit@0 {
+				sd1_4bit_0 {
+					groups = "sd1_4bit_grp0";
+					function = "sd1_4bit_m0";
+				};
+			};
+
+			sd1_4bit_pmx1: sd1_4bit@1 {
+				sd1_4bit_1 {
+					groups = "sd1_4bit_grp1";
+					function = "sd1_4bit_m1";
+				};
+			};
+
+			sd2_pmx0: sd2@0 {
+				sd2_0 {
+					groups = "sd2_grp0";
+					function = "sd2_m0";
+				};
+			};
+
+			sd2_no_cdb_pmx0: sd2_no_cdb@0 {
+				sd2_no_cdb_0 {
+					groups = "sd2_no_cdb_grp0";
+					function = "sd2_no_cdb_m0";
+				};
+			};
+
+			sd3_pmx: sd3@0 {
+				sd3 {
+					groups = "sd3_grp";
+					function = "sd3";
+				};
+			};
+
+			sd5_pmx: sd5@0 {
+				sd5 {
+					groups = "sd5_grp";
+					function = "sd5";
+				};
+			};
+
+			sd6_pmx0: sd6@0 {
+				sd6_0 {
+					groups = "sd6_grp0";
+					function = "sd6_m0";
+				};
+			};
+
+			sd6_pmx1: sd6@1 {
+				sd6_1 {
+					groups = "sd6_grp1";
+					function = "sd6_m1";
+				};
+			};
+
+			sp0_ext_ldo_on_pmx: sp0_ext_ldo_on@0 {
+				sp0_ext_ldo_on {
+					groups = "sp0_ext_ldo_on_grp";
+					function = "sp0_ext_ldo_on";
+				};
+			};
+
+			sp0_qspi_pmx: sp0_qspi@0 {
+				sp0_qspi {
+					groups = "sp0_qspi_grp";
+					function = "sp0_qspi";
+				};
+			};
+
+			sp1_spi_pmx: sp1_spi@0 {
+				sp1_spi {
+					groups = "sp1_spi_grp";
+					function = "sp1_spi";
+				};
+			};
+
+			tpiu_trace_pmx: tpiu_trace@0 {
+				tpiu_trace {
+					groups = "tpiu_trace_grp";
+					function = "tpiu_trace";
+				};
+			};
+
+			uart0_pmx: uart0@0 {
+				uart0 {
+					groups = "uart0_grp";
+					function = "uart0";
+				};
+			};
+
+			uart0_nopause_pmx: uart0_nopause@0 {
+				uart0_nopause {
+					groups = "uart0_nopause_grp";
+					function = "uart0_nopause";
+				};
+			};
+
+			uart1_pmx: uart1@0 {
+				uart1 {
+					groups = "uart1_grp";
+					function = "uart1";
+				};
+			};
+
+			uart2_pmx: uart2@0 {
+				uart2 {
+					groups = "uart2_grp";
+					function = "uart2";
+				};
+			};
+
+			uart3_pmx0: uart3@0 {
+				uart3_0 {
+					groups = "uart3_grp0";
+					function = "uart3_m0";
+				};
+			};
+
+			uart3_pmx1: uart3@1 {
+				uart3_1 {
+					groups = "uart3_grp1";
+					function = "uart3_m1";
+				};
+			};
+
+			uart3_pmx2: uart3@2 {
+				uart3_2 {
+					groups = "uart3_grp2";
+					function = "uart3_m2";
+				};
+			};
+
+			uart3_pmx3: uart3@3 {
+				uart3_3 {
+					groups = "uart3_grp3";
+					function = "uart3_m3";
+				};
+			};
+
+			uart3_nopause_pmx0: uart3_nopause@0 {
+				uart3_nopause_0 {
+					groups = "uart3_nopause_grp0";
+					function = "uart3_nopause_m0";
+				};
+			};
+
+			uart3_nopause_pmx1: uart3_nopause@1 {
+				uart3_nopause_1 {
+					groups = "uart3_nopause_grp1";
+					function = "uart3_nopause_m1";
+				};
+			};
+
+			uart4_pmx0: uart4@0 {
+				uart4_0 {
+					groups = "uart4_grp0";
+					function = "uart4_m0";
+				};
+			};
+
+			uart4_pmx1: uart4@1 {
+				uart4_1 {
+					groups = "uart4_grp1";
+					function = "uart4_m1";
+				};
+			};
+
+			uart4_pmx2: uart4@2 {
+				uart4_2 {
+					groups = "uart4_grp2";
+					function = "uart4_m2";
+				};
+			};
+
+			uart4_nopause_pmx: uart4_nopause@0 {
+				uart4_nopause {
+					groups = "uart4_nopause_grp";
+					function = "uart4_nopause";
+				};
+			};
+
+			usb0_drvvbus_pmx: usb0_drvvbus@0 {
+				usb0_drvvbus {
+					groups = "usb0_drvvbus_grp";
+					function = "usb0_drvvbus";
+				};
+			};
+
+			usb1_drvvbus_pmx: usb1_drvvbus@0 {
+				usb1_drvvbus {
+					groups = "usb1_drvvbus_grp";
+					function = "usb1_drvvbus";
+				};
+			};
+
+			visbus_dout_pmx: visbus_dout@0 {
+				visbus_dout {
+					groups = "visbus_dout_grp";
+					function = "visbus_dout";
+				};
+			};
+
+			vi_vip1_pmx: vi_vip1@0 {
+				vi_vip1 {
+					groups = "vi_vip1_grp";
+					function = "vi_vip1";
+				};
+			};
+
+			vi_vip1_ext_pmx: vi_vip1_ext@0 {
+				vi_vip1_ext {
+					groups = "vi_vip1_ext_grp";
+					function = "vi_vip1_ext";
+				};
+			};
+
+			vi_vip1_low8bit_pmx: vi_vip1_low8bit@0 {
+				vi_vip1_low8bit {
+					groups = "vi_vip1_low8bit_grp";
+					function = "vi_vip1_low8bit";
+				};
+			};
+
+			vi_vip1_high8bit_pmx: vi_vip1_high8bit@0 {
+				vi_vip1_high8bit {
+					groups = "vi_vip1_high8bit_grp";
+					function = "vi_vip1_high8bit";
+				};
+			};
 		};
 
 		pmipc {
@@ -356,6 +1375,12 @@
 				clock-names = "gpio0_io";
 				gpio-controller;
 				interrupt-controller;
+
+				gpio-banks = <2>;
+				gpio-ranges = <&pinctrl 0 0 0>,
+						<&pinctrl 32 0 0>;
+				gpio-ranges-group-names = "lvds_gpio_grp",
+							"uart_nand_gpio_grp";
 			};
 
 			nand@17050000 {
@@ -461,11 +1486,22 @@
 				#interrupt-cells = <2>;
 				compatible = "sirf,atlas7-gpio";
 				reg = <0x13300000 0x1000>;
-				interrupts = <0 43 0>, <0 44 0>, <0 45 0>;
+				interrupts = <0 43 0>, <0 44 0>,
+						<0 45 0>, <0 46 0>;
 				clocks = <&car 84>;
 				clock-names = "gpio1_io";
 				gpio-controller;
 				interrupt-controller;
+
+				gpio-banks = <4>;
+				gpio-ranges = <&pinctrl 0 0 0>,
+						<&pinctrl 32 0 0>,
+						<&pinctrl 64 0 0>,
+						<&pinctrl 96 0 0>;
+				gpio-ranges-group-names = "gnss_gpio_grp",
+							"lcd_vip_gpio_grp",
+							"sdio_i2s_gpio_grp",
+							"sp_rgmii_gpio_grp";
 			};
 
 			sd2: sdhci@14200000 {
@@ -744,6 +1780,10 @@
 				interrupts = <0 47 0>;
 				gpio-controller;
 				interrupt-controller;
+
+				gpio-banks = <1>;
+				gpio-ranges = <&pinctrl 0 0 0>;
+				gpio-ranges-group-names = "rtc_gpio_grp";
 			};
 
 			rtc-iobg@18840000 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index 107395c..17f63f7 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -150,6 +150,16 @@
 			interface-type = "ace";
 			reg = <0x5000 0x1000>;
 		};
+
+		pmu@9000 {
+			 compatible = "arm,cci-400-pmu,r0";
+			 reg = <0x9000 0x5000>;
+			 interrupts = <0 105 4>,
+				      <0 101 4>,
+				      <0 102 4>,
+				      <0 103 4>,
+				      <0 104 4>;
+		};
 	};
 
 	memory-controller@7ffd0000 {
@@ -187,11 +197,22 @@
 			     <1 10 0xf08>;
 	};
 
-	pmu {
+	pmu_a15 {
 		compatible = "arm,cortex-a15-pmu";
 		interrupts = <0 68 4>,
 			     <0 69 4>;
-		interrupt-affinity = <&cpu0>, <&cpu1>;
+		interrupt-affinity = <&cpu0>,
+				     <&cpu1>;
+	};
+
+	pmu_a7 {
+		compatible = "arm,cortex-a7-pmu";
+		interrupts = <0 128 4>,
+			     <0 129 4>,
+			     <0 130 4>;
+		interrupt-affinity = <&cpu2>,
+				     <&cpu3>,
+				     <&cpu4>;
 	};
 
 	oscclk6a: oscclk6a {
diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c
index 92e54d7..2b25b60 100644
--- a/arch/arm/common/mcpm_platsmp.c
+++ b/arch/arm/common/mcpm_platsmp.c
@@ -65,14 +65,10 @@
 	return !mcpm_wait_for_cpu_powerdown(pcpu, pcluster);
 }
 
-static int mcpm_cpu_disable(unsigned int cpu)
+static bool mcpm_cpu_can_disable(unsigned int cpu)
 {
-	/*
-	 * We assume all CPUs may be shut down.
-	 * This would be the hook to use for eventual Secure
-	 * OS migration requests as described in the PSCI spec.
-	 */
-	return 0;
+	/* We assume all CPUs may be shut down. */
+	return true;
 }
 
 static void mcpm_cpu_die(unsigned int cpu)
@@ -92,7 +88,7 @@
 	.smp_secondary_init	= mcpm_secondary_init,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_kill		= mcpm_cpu_kill,
-	.cpu_disable		= mcpm_cpu_disable,
+	.cpu_can_disable	= mcpm_cpu_can_disable,
 	.cpu_die		= mcpm_cpu_die,
 #endif
 };
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 6d83a1b..5fd8df6 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -353,7 +353,6 @@
 CONFIG_POWER_RESET_GPIO=y
 CONFIG_POWER_RESET_GPIO_RESTART=y
 CONFIG_POWER_RESET_KEYSTONE=y
-CONFIG_POWER_RESET_SUN6I=y
 CONFIG_POWER_RESET_RMOBILE=y
 CONFIG_SENSORS_LM90=y
 CONFIG_SENSORS_LM95245=y
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 8ecba00..7ebc346b 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -2,6 +2,7 @@
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_PERF_EVENTS=y
+CONFIG_MODULES=y
 CONFIG_ARCH_SUNXI=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
@@ -77,7 +78,6 @@
 CONFIG_GPIO_SYSFS=y
 CONFIG_POWER_SUPPLY=y
 CONFIG_POWER_RESET=y
-CONFIG_POWER_RESET_SUN6I=y
 CONFIG_THERMAL=y
 CONFIG_CPU_THERMAL=y
 CONFIG_WATCHDOG=y
@@ -87,6 +87,10 @@
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_AXP20X=y
 CONFIG_REGULATOR_GPIO=y
+CONFIG_FB=y
+CONFIG_FB_SIMPLE=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 83c5019..517ef6d 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -12,7 +12,6 @@
 generic-y += kdebug.h
 generic-y += local.h
 generic-y += local64.h
-generic-y += mcs_spinlock.h
 generic-y += msgbuf.h
 generic-y += param.h
 generic-y += parport.h
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 4abe572..7bbf325 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -108,33 +108,37 @@
 	.endm
 #endif
 
-	.macro asm_trace_hardirqs_off
+	.macro asm_trace_hardirqs_off, save=1
 #if defined(CONFIG_TRACE_IRQFLAGS)
+	.if \save
 	stmdb   sp!, {r0-r3, ip, lr}
+	.endif
 	bl	trace_hardirqs_off
+	.if \save
 	ldmia	sp!, {r0-r3, ip, lr}
+	.endif
 #endif
 	.endm
 
-	.macro asm_trace_hardirqs_on_cond, cond
+	.macro asm_trace_hardirqs_on, cond=al, save=1
 #if defined(CONFIG_TRACE_IRQFLAGS)
 	/*
 	 * actually the registers should be pushed and pop'd conditionally, but
 	 * after bl the flags are certainly clobbered
 	 */
+	.if \save
 	stmdb   sp!, {r0-r3, ip, lr}
+	.endif
 	bl\cond	trace_hardirqs_on
+	.if \save
 	ldmia	sp!, {r0-r3, ip, lr}
+	.endif
 #endif
 	.endm
 
-	.macro asm_trace_hardirqs_on
-	asm_trace_hardirqs_on_cond al
-	.endm
-
-	.macro disable_irq
+	.macro disable_irq, save=1
 	disable_irq_notrace
-	asm_trace_hardirqs_off
+	asm_trace_hardirqs_off \save
 	.endm
 
 	.macro enable_irq
@@ -173,7 +177,7 @@
 
 	.macro restore_irqs, oldcpsr
 	tst	\oldcpsr, #PSR_I_BIT
-	asm_trace_hardirqs_on_cond eq
+	asm_trace_hardirqs_on cond=eq
 	restore_irqs_notrace \oldcpsr
 	.endm
 
@@ -445,6 +449,53 @@
 #endif
 	.endm
 
+	.macro	uaccess_disable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_DISABLE
+	mcr	p15, 0, \tmp, c3, c0, 0		@ Set domain register
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+	.macro	uaccess_enable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_ENABLE
+	mcr	p15, 0, \tmp, c3, c0, 0
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+	.macro	uaccess_save, tmp
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	mrc	p15, 0, \tmp, c3, c0, 0
+	str	\tmp, [sp, #S_FRAME_SIZE]
+#endif
+	.endm
+
+	.macro	uaccess_restore
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	ldr	r0, [sp, #S_FRAME_SIZE]
+	mcr	p15, 0, r0, c3, c0, 0
+#endif
+	.endm
+
+	.macro	uaccess_save_and_disable, tmp
+	uaccess_save \tmp
+	uaccess_disable \tmp
+	.endm
+
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
 #if __LINUX_ARM_ARCH__ < 6
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index 5638099..e943e6c 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -35,9 +35,9 @@
 static inline void ____atomic_set_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	*p |= mask;
@@ -47,9 +47,9 @@
 static inline void ____atomic_clear_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	*p &= ~mask;
@@ -59,9 +59,9 @@
 static inline void ____atomic_change_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	*p ^= mask;
@@ -73,9 +73,9 @@
 {
 	unsigned long flags;
 	unsigned int res;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	res = *p;
@@ -90,9 +90,9 @@
 {
 	unsigned long flags;
 	unsigned int res;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	res = *p;
@@ -107,9 +107,9 @@
 {
 	unsigned long flags;
 	unsigned int res;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	res = *p;
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 4812cda..d5525bf 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -140,8 +140,6 @@
  * is visible to DMA, or data written by DMA to system memory is
  * visible to the CPU.
  */
-#define dmac_map_area			cpu_cache.dma_map_area
-#define dmac_unmap_area			cpu_cache.dma_unmap_area
 #define dmac_flush_range		cpu_cache.dma_flush_range
 
 #else
@@ -161,8 +159,6 @@
  * is visible to DMA, or data written by DMA to system memory is
  * visible to the CPU.
  */
-extern void dmac_map_area(const void *, size_t, int);
-extern void dmac_unmap_area(const void *, size_t, int);
 extern void dmac_flush_range(const void *, const void *);
 
 #endif
@@ -506,4 +502,21 @@
 void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
 			     void *kaddr, unsigned long len);
 
+/**
+ * secure_flush_area - ensure coherency across the secure boundary
+ * @addr: virtual address
+ * @size: size of region
+ *
+ * Ensure that the specified area of memory is coherent across the secure
+ * boundary from the non-secure side.  This is used when calling secure
+ * firmware where the secure firmware does not ensure coherency.
+ */
+static inline void secure_flush_area(const void *addr, size_t size)
+{
+	phys_addr_t phys = __pa(addr);
+
+	__cpuc_flush_dcache_area((void *)addr, size);
+	outer_flush_range(phys, phys + size);
+}
+
 #endif
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index b52101d..a68b9d8 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -14,7 +14,7 @@
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-#define DMA_ERROR_CODE	(~0)
+#define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
 extern struct dma_map_ops arm_dma_ops;
 extern struct dma_map_ops arm_coherent_dma_ops;
 
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 6ddbe44..e878129 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -34,15 +34,14 @@
  */
 #ifndef CONFIG_IO_36
 #define DOMAIN_KERNEL	0
-#define DOMAIN_TABLE	0
 #define DOMAIN_USER	1
 #define DOMAIN_IO	2
 #else
 #define DOMAIN_KERNEL	2
-#define DOMAIN_TABLE	2
 #define DOMAIN_USER	1
 #define DOMAIN_IO	0
 #endif
+#define DOMAIN_VECTORS	3
 
 /*
  * Domain types
@@ -55,11 +54,46 @@
 #define DOMAIN_MANAGER	1
 #endif
 
-#define domain_val(dom,type)	((type) << (2*(dom)))
+#define domain_mask(dom)	((3) << (2 * (dom)))
+#define domain_val(dom,type)	((type) << (2 * (dom)))
+
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+#define DACR_INIT \
+	(domain_val(DOMAIN_USER, DOMAIN_NOACCESS) | \
+	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
+#else
+#define DACR_INIT \
+	(domain_val(DOMAIN_USER, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
+#endif
+
+#define __DACR_DEFAULT \
+	domain_val(DOMAIN_KERNEL, DOMAIN_CLIENT) | \
+	domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT)
+
+#define DACR_UACCESS_DISABLE	\
+	(__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
+#define DACR_UACCESS_ENABLE	\
+	(__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_CLIENT))
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_CPU_USE_DOMAINS
+static inline unsigned int get_domain(void)
+{
+	unsigned int domain;
+
+	asm(
+	"mrc	p15, 0, %0, c3, c0	@ get domain"
+	 : "=r" (domain));
+
+	return domain;
+}
+
 static inline void set_domain(unsigned val)
 {
 	asm volatile(
@@ -68,17 +102,16 @@
 	isb();
 }
 
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define modify_domain(dom,type)					\
 	do {							\
-	struct thread_info *thread = current_thread_info();	\
-	unsigned int domain = thread->cpu_domain;		\
-	domain &= ~domain_val(dom, DOMAIN_MANAGER);		\
-	thread->cpu_domain = domain | domain_val(dom, type);	\
-	set_domain(thread->cpu_domain);				\
+		unsigned int domain = get_domain();		\
+		domain &= ~domain_mask(dom);			\
+		domain = domain | domain_val(dom, type);	\
+		set_domain(domain);				\
 	} while (0)
 
 #else
-static inline void set_domain(unsigned val) { }
 static inline void modify_domain(unsigned dom, unsigned type)	{ }
 #endif
 
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index 0415eae..58cfe9f 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -6,9 +6,13 @@
 #define FIXADDR_TOP		(FIXADDR_END - PAGE_SIZE)
 
 #include <asm/kmap_types.h>
+#include <asm/pgtable.h>
 
 enum fixed_addresses {
-	FIX_KMAP_BEGIN,
+	FIX_EARLYCON_MEM_BASE,
+	__end_of_permanent_fixed_addresses,
+
+	FIX_KMAP_BEGIN = __end_of_permanent_fixed_addresses,
 	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1,
 
 	/* Support writing RO kernel text via kprobes, jump labels, etc. */
@@ -18,7 +22,16 @@
 	__end_of_fixed_addresses
 };
 
+#define FIXMAP_PAGE_COMMON	(L_PTE_YOUNG | L_PTE_PRESENT | L_PTE_XN | L_PTE_DIRTY)
+
+#define FIXMAP_PAGE_NORMAL	(FIXMAP_PAGE_COMMON | L_PTE_MT_WRITEBACK)
+
+/* Used by set_fixmap_(io|nocache), both meant for mapping a device */
+#define FIXMAP_PAGE_IO		(FIXMAP_PAGE_COMMON | L_PTE_MT_DEV_SHARED | L_PTE_SHARED)
+#define FIXMAP_PAGE_NOCACHE	FIXMAP_PAGE_IO
+
 void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot);
+void __init early_fixmap_init(void);
 
 #include <asm-generic/fixmap.h>
 
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 5eed828..6795368 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -22,8 +22,11 @@
 #ifdef CONFIG_SMP
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+({								\
+	unsigned int __ua_flags;				\
 	smp_mb();						\
 	prefetchw(uaddr);					\
+	__ua_flags = uaccess_save_and_enable();			\
 	__asm__ __volatile__(					\
 	"1:	ldrex	%1, [%3]\n"				\
 	"	" insn "\n"					\
@@ -34,12 +37,15 @@
 	__futex_atomic_ex_table("%5")				\
 	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
-	: "cc", "memory")
+	: "cc", "memory");					\
+	uaccess_restore(__ua_flags);				\
+})
 
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	unsigned int __ua_flags;
 	int ret;
 	u32 val;
 
@@ -49,6 +55,7 @@
 	smp_mb();
 	/* Prefetching cannot fault */
 	prefetchw(uaddr);
+	__ua_flags = uaccess_save_and_enable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	ldrex	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -61,6 +68,7 @@
 	: "=&r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
+	uaccess_restore(__ua_flags);
 	smp_mb();
 
 	*uval = val;
@@ -73,6 +81,8 @@
 #include <asm/domain.h>
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+({								\
+	unsigned int __ua_flags = uaccess_save_and_enable();	\
 	__asm__ __volatile__(					\
 	"1:	" TUSER(ldr) "	%1, [%3]\n"			\
 	"	" insn "\n"					\
@@ -81,12 +91,15 @@
 	__futex_atomic_ex_table("%5")				\
 	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
-	: "cc", "memory")
+	: "cc", "memory");					\
+	uaccess_restore(__ua_flags);				\
+})
 
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	unsigned int __ua_flags;
 	int ret = 0;
 	u32 val;
 
@@ -94,6 +107,7 @@
 		return -EFAULT;
 
 	preempt_disable();
+	__ua_flags = uaccess_save_and_enable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	" TUSER(ldr) "	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -103,6 +117,7 @@
 	: "+r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
+	uaccess_restore(__ua_flags);
 
 	*uval = val;
 	preempt_enable();
diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
index a3c24cd..cab07f6 100644
--- a/arch/arm/include/asm/glue-cache.h
+++ b/arch/arm/include/asm/glue-cache.h
@@ -158,8 +158,6 @@
 #define __cpuc_coherent_user_range	__glue(_CACHE,_coherent_user_range)
 #define __cpuc_flush_dcache_area	__glue(_CACHE,_flush_kern_dcache_area)
 
-#define dmac_map_area			__glue(_CACHE,_dma_map_area)
-#define dmac_unmap_area			__glue(_CACHE,_dma_unmap_area)
 #define dmac_flush_range		__glue(_CACHE,_dma_flush_range)
 #endif
 
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 1c3938f..4859820 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -140,16 +140,11 @@
  * The _caller variety takes a __builtin_return_address(0) value for
  * /proc/vmalloc to use - and should only be used in non-inline functions.
  */
-extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
-	size_t, unsigned int, void *);
 extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
 	void *);
-
 extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int);
 extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
 extern void __iounmap(volatile void __iomem *addr);
-extern void __arm_iounmap(volatile void __iomem *addr);
 
 extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 	unsigned int, void *);
@@ -321,21 +316,24 @@
 static inline void memset_io(volatile void __iomem *dst, unsigned c,
 	size_t count)
 {
-	memset((void __force *)dst, c, count);
+	extern void mmioset(void *, unsigned int, size_t);
+	mmioset((void __force *)dst, c, count);
 }
 #define memset_io(dst,c,count) memset_io(dst,c,count)
 
 static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
 	size_t count)
 {
-	memcpy(to, (const void __force *)from, count);
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy(to, (const void __force *)from, count);
 }
 #define memcpy_fromio(to,from,count) memcpy_fromio(to,from,count)
 
 static inline void memcpy_toio(volatile void __iomem *to, const void *from,
 	size_t count)
 {
-	memcpy((void __force *)to, from, count);
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy((void __force *)to, from, count);
 }
 #define memcpy_toio(to,from,count) memcpy_toio(to,from,count)
 
@@ -348,18 +346,61 @@
 #endif	/* readl */
 
 /*
- * ioremap and friends.
+ * ioremap() and friends.
  *
- * ioremap takes a PCI memory address, as specified in
- * Documentation/io-mapping.txt.
+ * ioremap() takes a resource address, and size.  Due to the ARM memory
+ * types, it is important to use the correct ioremap() function as each
+ * mapping has specific properties.
  *
+ * Function		Memory type	Cacheability	Cache hint
+ * ioremap()		Device		n/a		n/a
+ * ioremap_nocache()	Device		n/a		n/a
+ * ioremap_cache()	Normal		Writeback	Read allocate
+ * ioremap_wc()		Normal		Non-cacheable	n/a
+ * ioremap_wt()		Normal		Non-cacheable	n/a
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
+ * - writes may be delayed before they hit the endpoint device
+ *
+ * ioremap_nocache() is the same as ioremap() as there are too many device
+ * drivers using this for device registers, and documentation which tells
+ * people to use it for such for this to be any different.  This is not a
+ * safe fallback for memory-like mappings, or memory regions where the
+ * compiler may generate unaligned accesses - eg, via inlining its own
+ * memcpy.
+ *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ * - ordering is not guaranteed without explicit dependencies or barrier
+ *   instructions
+ * - writes may be delayed before they hit the endpoint memory
+ *
+ * The cache hint is only a performance hint: CPUs may alias these hints.
+ * Eg, a CPU not implementing read allocate but implementing write allocate
+ * will provide a write allocate mapping instead.
  */
-#define ioremap(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_cache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
-#define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
-#define ioremap_wt(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
-#define iounmap				__arm_iounmap
+void __iomem *ioremap(resource_size_t res_cookie, size_t size);
+#define ioremap ioremap
+#define ioremap_nocache ioremap
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size);
+#define ioremap_cache ioremap_cache
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
+#define ioremap_wc ioremap_wc
+#define ioremap_wt ioremap_wc
+
+void iounmap(volatile void __iomem *iomem_cookie);
+#define iounmap iounmap
 
 /*
  * io{read,write}{16,32}be() macros
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 3a72d69..b7f6fb4 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -275,7 +275,7 @@
  */
 #define __pa(x)			__virt_to_phys((unsigned long)(x))
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
-#define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+#define pfn_to_kaddr(pfn)	__va((phys_addr_t)(pfn) << PAGE_SHIFT)
 
 extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
 
@@ -286,7 +286,7 @@
  */
 static inline phys_addr_t __virt_to_idmap(unsigned long x)
 {
-	if (arch_virt_to_idmap)
+	if (IS_ENABLED(CONFIG_MMU) && arch_virt_to_idmap)
 		return arch_virt_to_idmap(x);
 	else
 		return __virt_to_phys(x);
diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
index 5e68278..d0131ee 100644
--- a/arch/arm/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -23,6 +23,7 @@
 #define PMD_PXNTABLE		(_AT(pmdval_t, 1) << 2)     /* v7 */
 #define PMD_BIT4		(_AT(pmdval_t, 1) << 4)
 #define PMD_DOMAIN(x)		(_AT(pmdval_t, (x)) << 5)
+#define PMD_DOMAIN_MASK		PMD_DOMAIN(0x0f)
 #define PMD_PROTECTION		(_AT(pmdval_t, 1) << 9)		/* v5 */
 /*
  *   - section
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index bfd662e..aeddd28 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -129,7 +129,36 @@
 
 /*
  * These are the memory types, defined to be compatible with
- * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
+ * pre-ARMv6 CPUs cacheable and bufferable bits: n/a,n/a,C,B
+ * ARMv6+ without TEX remapping, they are a table index.
+ * ARMv6+ with TEX remapping, they correspond to n/a,TEX(0),C,B
+ *
+ * MT type		Pre-ARMv6	ARMv6+ type / cacheable status
+ * UNCACHED		Uncached	Strongly ordered
+ * BUFFERABLE		Bufferable	Normal memory / non-cacheable
+ * WRITETHROUGH		Writethrough	Normal memory / write through
+ * WRITEBACK		Writeback	Normal memory / write back, read alloc
+ * MINICACHE		Minicache	N/A
+ * WRITEALLOC		Writeback	Normal memory / write back, write alloc
+ * DEV_SHARED		Uncached	Device memory (shared)
+ * DEV_NONSHARED	Uncached	Device memory (non-shared)
+ * DEV_WC		Bufferable	Normal memory / non-cacheable
+ * DEV_CACHED		Writeback	Normal memory / write back, read alloc
+ * VECTORS		Variable	Normal memory / variable
+ *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
  */
 #define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
 #define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 2f3ac1b..ef35665 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -74,7 +74,6 @@
 extern int __cpu_disable(void);
 
 extern void __cpu_die(unsigned int cpu);
-extern void cpu_die(void);
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
@@ -105,6 +104,7 @@
 #ifdef CONFIG_HOTPLUG_CPU
 	int  (*cpu_kill)(unsigned int cpu);
 	void (*cpu_die)(unsigned int cpu);
+	bool  (*cpu_can_disable)(unsigned int cpu);
 	int  (*cpu_disable)(unsigned int cpu);
 #endif
 #endif
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index 993e522..f908071 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -107,4 +107,13 @@
 extern int platform_can_secondary_boot(void);
 extern int platform_can_cpu_hotplug(void);
 
+#ifdef CONFIG_HOTPLUG_CPU
+extern int platform_can_hotplug_cpu(unsigned int cpu);
+#else
+static inline int platform_can_hotplug_cpu(unsigned int cpu)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
index c99e259..12ebfcc 100644
--- a/arch/arm/include/asm/switch_to.h
+++ b/arch/arm/include/asm/switch_to.h
@@ -10,7 +10,9 @@
  * CPU.
  */
 #if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7)
-#define finish_arch_switch(prev)	dsb(ish)
+#define __complete_pending_tlbi()	dsb(ish)
+#else
+#define __complete_pending_tlbi()
 #endif
 
 /*
@@ -22,6 +24,7 @@
 
 #define switch_to(prev,next,last)					\
 do {									\
+	__complete_pending_tlbi();					\
 	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
 } while (0)
 
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index bd32ede..d0a1119 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -74,9 +74,6 @@
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
-	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_IO, DOMAIN_CLIENT),		\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
@@ -136,22 +133,18 @@
 
 /*
  * thread information flags:
- *  TIF_SYSCALL_TRACE	- syscall trace active
- *  TIF_SYSCAL_AUDIT	- syscall auditing active
- *  TIF_SIGPENDING	- signal pending
- *  TIF_NEED_RESCHED	- rescheduling necessary
- *  TIF_NOTIFY_RESUME	- callback before returning to user
  *  TIF_USEDFPU		- FPU was used by this task this quantum (SMP)
  *  TIF_POLLING_NRFLAG	- true if poll_idle() is polling TIF_NEED_RESCHED
  */
-#define TIF_SIGPENDING		0
-#define TIF_NEED_RESCHED	1
+#define TIF_SIGPENDING		0	/* signal pending */
+#define TIF_NEED_RESCHED	1	/* rescheduling necessary */
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
-#define TIF_UPROBE		7
-#define TIF_SYSCALL_TRACE	8
-#define TIF_SYSCALL_AUDIT	9
-#define TIF_SYSCALL_TRACEPOINT	10
-#define TIF_SECCOMP		11	/* seccomp syscall filtering active */
+#define TIF_UPROBE		3	/* breakpointed or singlestepping */
+#define TIF_SYSCALL_TRACE	4	/* syscall trace active */
+#define TIF_SYSCALL_AUDIT	5	/* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
+#define TIF_SECCOMP		7	/* seccomp syscall filtering active */
+
 #define TIF_NOHZ		12	/* in adaptive nohz mode */
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 74b17d0..8cc85a4 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -50,6 +50,35 @@
 extern int fixup_exception(struct pt_regs *regs);
 
 /*
+ * These two functions allow hooking accesses to userspace to increase
+ * system integrity by ensuring that the kernel can not inadvertantly
+ * perform such accesses (eg, via list poison values) which could then
+ * be exploited for priviledge escalation.
+ */
+static inline unsigned int uaccess_save_and_enable(void)
+{
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	unsigned int old_domain = get_domain();
+
+	/* Set the current domain access to permit user accesses */
+	set_domain((old_domain & ~domain_mask(DOMAIN_USER)) |
+		   domain_val(DOMAIN_USER, DOMAIN_CLIENT));
+
+	return old_domain;
+#else
+	return 0;
+#endif
+}
+
+static inline void uaccess_restore(unsigned int flags)
+{
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/* Restore the user access mask */
+	set_domain(flags);
+#endif
+}
+
+/*
  * These two are intentionally not defined anywhere - if the kernel
  * code generates any references to them, that's a bug.
  */
@@ -165,6 +194,7 @@
 		register typeof(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
+		unsigned int __ua_flags = uaccess_save_and_enable();	\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
 			if (sizeof((x)) >= 8)				\
@@ -192,6 +222,7 @@
 			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		x = (typeof(*(p))) __r2;				\
 		__e;							\
 	})
@@ -224,6 +255,7 @@
 		register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
+		unsigned int __ua_flags = uaccess_save_and_enable();	\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
 			__put_user_x(__r2, __p, __e, __l, 1);		\
@@ -239,6 +271,7 @@
 			break;						\
 		default: __e = __put_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		__e;							\
 	})
 
@@ -300,20 +333,23 @@
 do {									\
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
 	unsigned long __gu_val;						\
+	unsigned int __ua_flags;					\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
+	__ua_flags = uaccess_save_and_enable();				\
 	switch (sizeof(*(ptr))) {					\
 	case 1:	__get_user_asm_byte(__gu_val, __gu_addr, err);	break;	\
 	case 2:	__get_user_asm_half(__gu_val, __gu_addr, err);	break;	\
 	case 4:	__get_user_asm_word(__gu_val, __gu_addr, err);	break;	\
 	default: (__gu_val) = __get_user_bad();				\
 	}								\
+	uaccess_restore(__ua_flags);					\
 	(x) = (__typeof__(*(ptr)))__gu_val;				\
 } while (0)
 
-#define __get_user_asm_byte(x, addr, err)			\
+#define __get_user_asm(x, addr, err, instr)			\
 	__asm__ __volatile__(					\
-	"1:	" TUSER(ldrb) "	%1,[%2],#0\n"			\
+	"1:	" TUSER(instr) " %1, [%2], #0\n"		\
 	"2:\n"							\
 	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
@@ -329,6 +365,9 @@
 	: "r" (addr), "i" (-EFAULT)				\
 	: "cc")
 
+#define __get_user_asm_byte(x, addr, err)			\
+	__get_user_asm(x, addr, err, ldrb)
+
 #ifndef __ARMEB__
 #define __get_user_asm_half(x, __gu_addr, err)			\
 ({								\
@@ -348,22 +387,7 @@
 #endif
 
 #define __get_user_asm_word(x, addr, err)			\
-	__asm__ __volatile__(					\
-	"1:	" TUSER(ldr) "	%1,[%2],#0\n"			\
-	"2:\n"							\
-	"	.pushsection .text.fixup,\"ax\"\n"		\
-	"	.align	2\n"					\
-	"3:	mov	%0, %3\n"				\
-	"	mov	%1, #0\n"				\
-	"	b	2b\n"					\
-	"	.popsection\n"					\
-	"	.pushsection __ex_table,\"a\"\n"		\
-	"	.align	3\n"					\
-	"	.long	1b, 3b\n"				\
-	"	.popsection"					\
-	: "+r" (err), "=&r" (x)					\
-	: "r" (addr), "i" (-EFAULT)				\
-	: "cc")
+	__get_user_asm(x, addr, err, ldr)
 
 #define __put_user(x, ptr)						\
 ({									\
@@ -381,9 +405,11 @@
 #define __put_user_err(x, ptr, err)					\
 do {									\
 	unsigned long __pu_addr = (unsigned long)(ptr);			\
+	unsigned int __ua_flags;					\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
+	__ua_flags = uaccess_save_and_enable();				\
 	switch (sizeof(*(ptr))) {					\
 	case 1: __put_user_asm_byte(__pu_val, __pu_addr, err);	break;	\
 	case 2: __put_user_asm_half(__pu_val, __pu_addr, err);	break;	\
@@ -391,11 +417,12 @@
 	case 8:	__put_user_asm_dword(__pu_val, __pu_addr, err);	break;	\
 	default: __put_user_bad();					\
 	}								\
+	uaccess_restore(__ua_flags);					\
 } while (0)
 
-#define __put_user_asm_byte(x, __pu_addr, err)			\
+#define __put_user_asm(x, __pu_addr, err, instr)		\
 	__asm__ __volatile__(					\
-	"1:	" TUSER(strb) "	%1,[%2],#0\n"			\
+	"1:	" TUSER(instr) " %1, [%2], #0\n"		\
 	"2:\n"							\
 	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
@@ -410,6 +437,9 @@
 	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
 	: "cc")
 
+#define __put_user_asm_byte(x, __pu_addr, err)			\
+	__put_user_asm(x, __pu_addr, err, strb)
+
 #ifndef __ARMEB__
 #define __put_user_asm_half(x, __pu_addr, err)			\
 ({								\
@@ -427,21 +457,7 @@
 #endif
 
 #define __put_user_asm_word(x, __pu_addr, err)			\
-	__asm__ __volatile__(					\
-	"1:	" TUSER(str) "	%1,[%2],#0\n"			\
-	"2:\n"							\
-	"	.pushsection .text.fixup,\"ax\"\n"		\
-	"	.align	2\n"					\
-	"3:	mov	%0, %3\n"				\
-	"	b	2b\n"					\
-	"	.popsection\n"					\
-	"	.pushsection __ex_table,\"a\"\n"		\
-	"	.align	3\n"					\
-	"	.long	1b, 3b\n"				\
-	"	.popsection"					\
-	: "+r" (err)						\
-	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
-	: "cc")
+	__put_user_asm(x, __pu_addr, err, str)
 
 #ifndef __ARMEB__
 #define	__reg_oper0	"%R2"
@@ -474,11 +490,46 @@
 
 
 #ifdef CONFIG_MMU
-extern unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n);
-extern unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __copy_to_user_std(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
-extern unsigned long __must_check __clear_user_std(void __user *addr, unsigned long n);
+extern unsigned long __must_check
+arm_copy_from_user(void *to, const void __user *from, unsigned long n);
+
+static inline unsigned long __must_check
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_copy_from_user(to, from, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
+extern unsigned long __must_check
+arm_copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long __must_check
+__copy_to_user_std(void __user *to, const void *from, unsigned long n);
+
+static inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_copy_to_user(to, from, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
+extern unsigned long __must_check
+arm_clear_user(void __user *addr, unsigned long n);
+extern unsigned long __must_check
+__clear_user_std(void __user *addr, unsigned long n);
+
+static inline unsigned long __must_check
+__clear_user(void __user *addr, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_clear_user(addr, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
 #else
 #define __copy_from_user(to, from, n)	(memcpy(to, (void __force *)from, n), 0)
 #define __copy_to_user(to, from, n)	(memcpy((void __force *)to, from, n), 0)
@@ -511,6 +562,7 @@
 	return n;
 }
 
+/* These are from lib/ code, and use __get_user() and friends */
 extern long strncpy_from_user(char *dest, const char __user *src, long count);
 
 extern __must_check long strlen_user(const char __user *str);
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index a88671c..f89811f 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -50,6 +50,9 @@
 
 extern void fpundefinstr(void);
 
+void mmioset(void *, unsigned int, size_t);
+void mmiocpy(void *, const void *, size_t);
+
 	/* platform dependent support */
 EXPORT_SYMBOL(arm_delay_ops);
 
@@ -88,12 +91,15 @@
 EXPORT_SYMBOL(memchr);
 EXPORT_SYMBOL(__memzero);
 
+EXPORT_SYMBOL(mmioset);
+EXPORT_SYMBOL(mmiocpy);
+
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);
 
-EXPORT_SYMBOL(__copy_from_user);
-EXPORT_SYMBOL(__copy_to_user);
-EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(arm_copy_from_user);
+EXPORT_SYMBOL(arm_copy_to_user);
+EXPORT_SYMBOL(arm_clear_user);
 
 EXPORT_SYMBOL(__get_user_1);
 EXPORT_SYMBOL(__get_user_2);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 7dac308..3e1c26e 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -149,10 +149,10 @@
 #define SPFIX(code...)
 #endif
 
-	.macro	svc_entry, stack_hole=0, trace=1
+	.macro	svc_entry, stack_hole=0, trace=1, uaccess=1
  UNWIND(.fnstart		)
  UNWIND(.save {r0 - pc}		)
-	sub	sp, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	sub	sp, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
 #ifdef CONFIG_THUMB2_KERNEL
  SPFIX(	str	r0, [sp]	)	@ temporarily saved
  SPFIX(	mov	r0, sp		)
@@ -167,7 +167,7 @@
 	ldmia	r0, {r3 - r5}
 	add	r7, sp, #S_SP - 4	@ here for interlock avoidance
 	mov	r6, #-1			@  ""  ""      ""       ""
-	add	r2, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	add	r2, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
  SPFIX(	addeq	r2, r2, #4	)
 	str	r3, [sp, #-4]!		@ save the "real" r0 copied
 					@ from the exception stack
@@ -185,6 +185,11 @@
 	@
 	stmia	r7, {r2 - r6}
 
+	uaccess_save r0
+	.if \uaccess
+	uaccess_disable r0
+	.endif
+
 	.if \trace
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
@@ -194,7 +199,7 @@
 
 	.align	5
 __dabt_svc:
-	svc_entry
+	svc_entry uaccess=0
 	mov	r2, sp
 	dabt_helper
  THUMB(	ldr	r5, [sp, #S_PSR]	)	@ potentially updated CPSR
@@ -368,7 +373,7 @@
 #error "sizeof(struct pt_regs) must be a multiple of 8"
 #endif
 
-	.macro	usr_entry, trace=1
+	.macro	usr_entry, trace=1, uaccess=1
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)	@ don't unwind the user space
 	sub	sp, sp, #S_FRAME_SIZE
@@ -400,6 +405,10 @@
  ARM(	stmdb	r0, {sp, lr}^			)
  THUMB(	store_user_sp_lr r0, r1, S_SP - S_PC	)
 
+	.if \uaccess
+	uaccess_disable ip
+	.endif
+
 	@ Enable the alignment trap while in kernel mode
  ATRAP(	teq	r8, r7)
  ATRAP( mcrne	p15, 0, r8, c1, c0, 0)
@@ -410,7 +419,7 @@
 	zero_fp
 
 	.if	\trace
-#ifdef CONFIG_IRQSOFF_TRACER
+#ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
 	ct_user_exit save = 0
@@ -435,7 +444,7 @@
 
 	.align	5
 __dabt_usr:
-	usr_entry
+	usr_entry uaccess=0
 	kuser_cmpxchg_check
 	mov	r2, sp
 	dabt_helper
@@ -458,7 +467,7 @@
 
 	.align	5
 __und_usr:
-	usr_entry
+	usr_entry uaccess=0
 
 	mov	r2, r4
 	mov	r3, r5
@@ -484,6 +493,8 @@
 1:	ldrt	r0, [r4]
  ARM_BE8(rev	r0, r0)				@ little endian instruction
 
+	uaccess_disable ip
+
 	@ r0 = 32-bit ARM instruction which caused the exception
 	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
 	@ r4 = PC value for the faulting instruction
@@ -518,9 +529,10 @@
 2:	ldrht	r5, [r4]
 ARM_BE8(rev16	r5, r5)				@ little endian instruction
 	cmp	r5, #0xe800			@ 32bit instruction if xx != 0
-	blo	__und_usr_fault_16		@ 16bit undefined instruction
+	blo	__und_usr_fault_16_pan		@ 16bit undefined instruction
 3:	ldrht	r0, [r2]
 ARM_BE8(rev16	r0, r0)				@ little endian instruction
+	uaccess_disable ip
 	add	r2, r2, #2			@ r2 is PC + 2, make it PC + 4
 	str	r2, [sp, #S_PC]			@ it's a 2x16bit instr, update
 	orr	r0, r0, r5, lsl #16
@@ -715,6 +727,8 @@
 __und_usr_fault_32:
 	mov	r1, #4
 	b	1f
+__und_usr_fault_16_pan:
+	uaccess_disable ip
 __und_usr_fault_16:
 	mov	r1, #2
 1:	mov	r0, sp
@@ -770,6 +784,8 @@
 	ldr	r4, [r2, #TI_TP_VALUE]
 	ldr	r5, [r2, #TI_TP_VALUE + 4]
 #ifdef CONFIG_CPU_USE_DOMAINS
+	mrc	p15, 0, r6, c3, c0, 0		@ Get domain register
+	str	r6, [r1, #TI_CPU_DOMAIN]	@ Save old domain register
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
 	switch_tls r1, r4, r5, r3, r7
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 92828a1..30a7228 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -24,35 +24,55 @@
 
 
 	.align	5
+#if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING))
 /*
- * This is the fast syscall return path.  We do as little as
- * possible here, and this includes saving r0 back into the SVC
- * stack.
+ * This is the fast syscall return path.  We do as little as possible here,
+ * such as avoiding writing r0 to the stack.  We only use this path if we
+ * have tracing and context tracking disabled - the overheads from those
+ * features make this path too inefficient.
  */
 ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
-	disable_irq				@ disable interrupts
+	disable_irq_notrace			@ disable interrupts
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK
-	bne	__sys_trace_return
-	tst	r1, #_TIF_WORK_MASK
+	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
 	bne	fast_work_pending
-	asm_trace_hardirqs_on
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
-	ct_user_enter
 
 	restore_user_regs fast = 1, offset = S_OFF
  UNWIND(.fnend		)
+ENDPROC(ret_fast_syscall)
 
-/*
- * Ok, we need to do extra processing, enter the slow path.
- */
+	/* Ok, we need to do extra processing, enter the slow path. */
 fast_work_pending:
 	str	r0, [sp, #S_R0+S_OFF]!		@ returned r0
-work_pending:
+	/* fall through to work_pending */
+#else
+/*
+ * The "replacement" ret_fast_syscall for when tracing or context tracking
+ * is enabled.  As we will need to call out to some C functions, we save
+ * r0 first to avoid needing to save registers around each C function call.
+ */
+ret_fast_syscall:
+ UNWIND(.fnstart	)
+ UNWIND(.cantunwind	)
+	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
+	disable_irq_notrace			@ disable interrupts
+	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
+	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	beq	no_work_pending
+ UNWIND(.fnend		)
+ENDPROC(ret_fast_syscall)
+
+	/* Slower path - fall through to work_pending */
+#endif
+
+	tst	r1, #_TIF_SYSCALL_WORK
+	bne	__sys_trace_return_nosave
+slow_work_pending:
 	mov	r0, sp				@ 'regs'
 	mov	r2, why				@ 'syscall'
 	bl	do_work_pending
@@ -61,19 +81,23 @@
 	movlt	scno, #(__NR_restart_syscall - __NR_SYSCALL_BASE)
 	ldmia	sp, {r0 - r6}			@ have to reload r0 - r6
 	b	local_restart			@ ... and off we go
+ENDPROC(ret_fast_syscall)
 
 /*
  * "slow" syscall return path.  "why" tells us if this was a real syscall.
+ * IRQs may be enabled here, so always disable them.  Note that we use the
+ * "notrace" version to avoid calling into the tracing code unnecessarily.
+ * do_work_pending() will update this state if necessary.
  */
 ENTRY(ret_to_user)
 ret_slow_syscall:
-	disable_irq				@ disable interrupts
+	disable_irq_notrace			@ disable interrupts
 ENTRY(ret_to_user_from_irq)
 	ldr	r1, [tsk, #TI_FLAGS]
 	tst	r1, #_TIF_WORK_MASK
-	bne	work_pending
+	bne	slow_work_pending
 no_work_pending:
-	asm_trace_hardirqs_on
+	asm_trace_hardirqs_on save = 0
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
@@ -173,6 +197,8 @@
  USER(	ldr	scno, [lr, #-4]		)	@ get SWI instruction
 #endif
 
+	uaccess_disable tbl
+
 	adr	tbl, sys_call_table		@ load syscall table pointer
 
 #if defined(CONFIG_OABI_COMPAT)
@@ -251,6 +277,12 @@
 	bl	syscall_trace_exit
 	b	ret_slow_syscall
 
+__sys_trace_return_nosave:
+	enable_irq_notrace
+	mov	r0, sp
+	bl	syscall_trace_exit
+	b	ret_slow_syscall
+
 	.align	5
 #ifdef CONFIG_ALIGNMENT_TRAP
 	.type	__cr_alignment, #object
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 1a0045a..0d22ad2 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -196,7 +196,7 @@
 	msr	cpsr_c, \rtemp			@ switch back to the SVC mode
 	.endm
 
-#ifndef CONFIG_THUMB2_KERNEL
+
 	.macro	svc_exit, rpsr, irq = 0
 	.if	\irq != 0
 	@ IRQs already off
@@ -215,6 +215,10 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
+	uaccess_restore
+
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode SVC restore
 	msr	spsr_cxsf, \rpsr
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
 	@ We must avoid clrex due to Cortex-A15 erratum #830321
@@ -222,6 +226,20 @@
 	strex	r1, r2, [r0]			@ clear the exclusive monitor
 #endif
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+#else
+	@ Thumb mode SVC restore
+	ldr	lr, [sp, #S_SP]			@ top of the stack
+	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
+
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
+
+	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
+	ldmia	sp, {r0 - r12}
+	mov	sp, lr
+	ldr	lr, [sp], #4
+	rfeia	sp!
+#endif
 	.endm
 
 	@
@@ -241,6 +259,9 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
+	uaccess_restore
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r0, sp
 	ldmib	r0, {r1 - r14}	@ abort is deadly from here onward (it will
 				@ clobber state restored below)
@@ -250,9 +271,27 @@
 	msr	spsr_cxsf, r9
 	ldr	r0, [r0, #S_R0]
 	ldmia	r8, {pc}^
+#else
+	@ Thumb mode restore
+	add	r0, sp, #S_R2
+	ldr	lr, [sp, #S_LR]
+	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
+			        @ clobber state restored below)
+	ldmia	r0, {r2 - r12}
+	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
+	msr	cpsr_c, r1
+	sub	r0, #S_R2
+	add	r8, r0, #S_PC
+	ldmia	r0, {r0 - r1}
+	rfeia	r8
+#endif
 	.endm
 
+
 	.macro	restore_user_regs, fast = 0, offset = 0
+	uaccess_enable r1, isb=0
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r2, sp
 	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
@@ -270,72 +309,16 @@
 						@ after ldm {}^
 	add	sp, sp, #\offset + S_FRAME_SIZE
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-
-#else	/* CONFIG_THUMB2_KERNEL */
-	.macro	svc_exit, rpsr, irq = 0
-	.if	\irq != 0
-	@ IRQs already off
-#ifdef CONFIG_TRACE_IRQFLAGS
-	@ The parent context IRQs must have been enabled to get here in
-	@ the first place, so there's no point checking the PSR I bit.
-	bl	trace_hardirqs_on
-#endif
-	.else
-	@ IRQs off again before pulling preserved data off the stack
-	disable_irq_notrace
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	\rpsr, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	\rpsr, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
-	.endif
-	ldr	lr, [sp, #S_SP]			@ top of the stack
-	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
-
-	@ We must avoid clrex due to Cortex-A15 erratum #830321
-	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
-
-	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
-	ldmia	sp, {r0 - r12}
-	mov	sp, lr
-	ldr	lr, [sp], #4
-	rfeia	sp!
-	.endm
-
-	@
-	@ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit
-	@
-	@ For full details see non-Thumb implementation above.
-	@
-	.macro  svc_exit_via_fiq
-	add	r0, sp, #S_R2
-	ldr	lr, [sp, #S_LR]
-	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
-			        @ clobber state restored below)
-	ldmia	r0, {r2 - r12}
-	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
-	msr	cpsr_c, r1
-	sub	r0, #S_R2
-	add	r8, r0, #S_PC
-	ldmia	r0, {r0 - r1}
-	rfeia	r8
-	.endm
-
-#ifdef CONFIG_CPU_V7M
-	/*
-	 * Note we don't need to do clrex here as clearing the local monitor is
-	 * part of each exception entry and exit sequence.
-	 */
-	.macro	restore_user_regs, fast = 0, offset = 0
+#elif defined(CONFIG_CPU_V7M)
+	@ V7M restore.
+	@ Note that we don't need to do clrex here as clearing the local
+	@ monitor is part of the exception entry and exit sequence.
 	.if	\offset
 	add	sp, #\offset
 	.endif
 	v7m_exception_slow_exit ret_r0 = \fast
-	.endm
-#else	/* ifdef CONFIG_CPU_V7M */
-	.macro	restore_user_regs, fast = 0, offset = 0
+#else
+	@ Thumb mode restore
 	mov	r2, sp
 	load_user_sp_lr r2, r3, \offset + S_SP	@ calling sp, lr
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
@@ -353,9 +336,8 @@
 	.endif
 	add	sp, sp, #S_FRAME_SIZE - S_SP
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-#endif	/* ifdef CONFIG_CPU_V7M / else */
 #endif	/* !CONFIG_THUMB2_KERNEL */
+	.endm
 
 /*
  * Context tracking subsystem.  Used to instrument transitions
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index bd755d9..04286fd 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -399,6 +399,9 @@
 	sub	lr, r4, r5			@ mmu has been enabled
 	add	r3, r7, lr
 	ldrd	r4, [r3, #0]			@ get secondary_data.pgdir
+ARM_BE8(eor	r4, r4, r5)			@ Swap r5 and r4 in BE:
+ARM_BE8(eor	r5, r4, r5)			@ it can be done in 3 steps
+ARM_BE8(eor	r4, r4, r5)			@ without using a temp reg.
 	ldr	r8, [r3, #8]			@ get secondary_data.swapper_pg_dir
 	badr	lr, __enable_mmu		@ return address
 	mov	r13, r12			@ __secondary_switched address
@@ -461,10 +464,7 @@
 #ifdef CONFIG_ARM_LPAE
 	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
 #else
-	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
+	mov	r5, #DACR_INIT
 	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
 	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
 #endif
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 357f57e..7d5379c 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -795,8 +795,10 @@
 
 	/* Don't bother with PPIs; they're already affine */
 	irq = platform_get_irq(pdev, 0);
-	if (irq >= 0 && irq_is_percpu(irq))
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		cpumask_setall(&pmu->supported_cpus);
 		return 0;
+	}
 
 	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
 	if (!irqs)
@@ -818,12 +820,13 @@
 			if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL))
 				break;
 
-		of_node_put(dn);
 		if (cpu >= nr_cpu_ids) {
 			pr_warn("Failed to find logical CPU for %s\n",
 				dn->name);
+			of_node_put(dn);
 			break;
 		}
+		of_node_put(dn);
 
 		irqs[i] = cpu;
 		cpumask_set_cpu(cpu, &pmu->supported_cpus);
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index f192a2a..a3089ba 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -91,13 +91,6 @@
 	ledtrig_cpu(CPU_LED_IDLE_END);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-void arch_cpu_idle_dead(void)
-{
-	cpu_die();
-}
-#endif
-
 void __show_regs(struct pt_regs *regs)
 {
 	unsigned long flags;
@@ -129,12 +122,36 @@
 	buf[4] = '\0';
 
 #ifndef CONFIG_CPU_V7M
-	printk("Flags: %s  IRQs o%s  FIQs o%s  Mode %s  ISA %s  Segment %s\n",
-		buf, interrupts_enabled(regs) ? "n" : "ff",
-		fast_interrupts_enabled(regs) ? "n" : "ff",
-		processor_modes[processor_mode(regs)],
-		isa_modes[isa_mode(regs)],
-		get_fs() == get_ds() ? "kernel" : "user");
+	{
+		unsigned int domain = get_domain();
+		const char *segment;
+
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		/*
+		 * Get the domain register for the parent context. In user
+		 * mode, we don't save the DACR, so lets use what it should
+		 * be. For other modes, we place it after the pt_regs struct.
+		 */
+		if (user_mode(regs))
+			domain = DACR_UACCESS_ENABLE;
+		else
+			domain = *(unsigned int *)(regs + 1);
+#endif
+
+		if ((domain & domain_mask(DOMAIN_USER)) ==
+		    domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
+			segment = "none";
+		else if (get_fs() == get_ds())
+			segment = "kernel";
+		else
+			segment = "user";
+
+		printk("Flags: %s  IRQs o%s  FIQs o%s  Mode %s  ISA %s  Segment %s\n",
+			buf, interrupts_enabled(regs) ? "n" : "ff",
+			fast_interrupts_enabled(regs) ? "n" : "ff",
+			processor_modes[processor_mode(regs)],
+			isa_modes[isa_mode(regs)], segment);
+	}
 #else
 	printk("xPSR: %08lx\n", regs->ARM_cpsr);
 #endif
@@ -146,10 +163,9 @@
 		buf[0] = '\0';
 #ifdef CONFIG_CPU_CP15_MMU
 		{
-			unsigned int transbase, dac;
+			unsigned int transbase, dac = get_domain();
 			asm("mrc p15, 0, %0, c2, c0\n\t"
-			    "mrc p15, 0, %1, c3, c0\n"
-			    : "=r" (transbase), "=r" (dac));
+			    : "=r" (transbase));
 			snprintf(buf, sizeof(buf), "  Table: %08x  DAC: %08x",
 			  	transbase, dac);
 		}
@@ -210,6 +226,14 @@
 
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
 
+	/*
+	 * Copy the initial value of the domain access control register
+	 * from the current thread: thread->addr_limit will have been
+	 * copied from the current thread via setup_thread_stack() in
+	 * kernel/fork.c
+	 */
+	thread->cpu_domain = get_domain();
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->ARM_r0 = 0;
diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c
index 1a4d232..3826935 100644
--- a/arch/arm/kernel/reboot.c
+++ b/arch/arm/kernel/reboot.c
@@ -50,7 +50,7 @@
 	flush_cache_all();
 
 	/* Switch to the identity mapping. */
-	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
+	phys_reset = (phys_reset_t)(unsigned long)virt_to_idmap(cpu_reset);
 	phys_reset((unsigned long)addr);
 
 	/* Should never get here. */
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 36c18b7..e2ecee6 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -37,6 +37,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
+#include <asm/fixmap.h>
 #include <asm/procinfo.h>
 #include <asm/psci.h>
 #include <asm/sections.h>
@@ -954,6 +955,9 @@
 	strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = cmd_line;
 
+	if (IS_ENABLED(CONFIG_FIX_EARLYCON_MEM))
+		early_fixmap_init();
+
 	parse_early_param();
 
 #ifdef CONFIG_MMU
@@ -1015,7 +1019,7 @@
 
 	for_each_possible_cpu(cpu) {
 		struct cpuinfo_arm *cpuinfo = &per_cpu(cpu_data, cpu);
-		cpuinfo->cpu.hotpluggable = 1;
+		cpuinfo->cpu.hotpluggable = platform_can_hotplug_cpu(cpu);
 		register_cpu(&cpuinfo->cpu, cpu);
 	}
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 423663e..b6cda06 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -562,6 +562,12 @@
 asmlinkage int
 do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 {
+	/*
+	 * The assembly code enters us with IRQs off, but it hasn't
+	 * informed the tracing code of that for efficiency reasons.
+	 * Update the trace code with the current status.
+	 */
+	trace_hardirqs_off();
 	do {
 		if (likely(thread_flags & _TIF_NEED_RESCHED)) {
 			schedule();
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 90dfbed..ba0063c 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -175,13 +175,26 @@
 	if (smp_ops.cpu_disable)
 		return smp_ops.cpu_disable(cpu);
 
+	return 0;
+}
+
+int platform_can_hotplug_cpu(unsigned int cpu)
+{
+	/* cpu_die must be specified to support hotplug */
+	if (!smp_ops.cpu_die)
+		return 0;
+
+	if (smp_ops.cpu_can_disable)
+		return smp_ops.cpu_can_disable(cpu);
+
 	/*
 	 * By default, allow disabling all CPUs except the first one,
 	 * since this is special on a lot of platforms, e.g. because
 	 * of clock tick interrupts.
 	 */
-	return cpu == 0 ? -EPERM : 0;
+	return cpu != 0;
 }
+
 /*
  * __cpu_disable runs on the processor to be shutdown.
  */
@@ -253,7 +266,7 @@
  * of the other hotplug-cpu capable cores, so presumably coming
  * out of idle fixes this.
  */
-void __ref cpu_die(void)
+void arch_cpu_idle_dead(void)
 {
 	unsigned int cpu = smp_processor_id();
 
@@ -578,7 +591,7 @@
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	if ((unsigned)ipinr < NR_IPI) {
-		trace_ipi_entry(ipi_types[ipinr]);
+		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
 		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
 	}
 
@@ -637,7 +650,7 @@
 	}
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_exit(ipi_types[ipinr]);
+		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
 	set_irq_regs(old_regs);
 }
 
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 1361756..5b26e7e 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -141,11 +141,14 @@
 
 	while (1) {
 		unsigned long temp;
+		unsigned int __ua_flags;
 
+		__ua_flags = uaccess_save_and_enable();
 		if (type == TYPE_SWPB)
 			__user_swpb_asm(*data, address, res, temp);
 		else
 			__user_swp_asm(*data, address, res, temp);
+		uaccess_restore(__ua_flags);
 
 		if (likely(res != -EAGAIN) || signal_pending(current))
 			break;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index d358226..969f9d9 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -870,7 +870,6 @@
 	kuser_init(vectors_base);
 
 	flush_icache_range(vectors, vectors + PAGE_SIZE * 2);
-	modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
 #else /* ifndef CONFIG_CPU_V7M */
 	/*
 	 * on V7-M there is no need to copy the vector table to a dedicated
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index efe17dd..54a5aea 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -296,7 +296,6 @@
  */
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct timespec xtime_coarse;
 	struct timespec64 *wtm = &tk->wall_to_monotonic;
 
 	if (!cntvct_ok) {
@@ -308,10 +307,10 @@
 
 	vdso_write_begin(vdso_data);
 
-	xtime_coarse = __current_kernel_time();
 	vdso_data->tk_is_cntvct			= tk_is_cntvct(tk);
-	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
-	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
+	vdso_data->xtime_coarse_nsec		= (u32)(tk->tkr_mono.xtime_nsec >>
+							tk->tkr_mono.shift);
 	vdso_data->wtm_clock_sec		= wtm->tv_sec;
 	vdso_data->wtm_clock_nsec		= wtm->tv_nsec;
 
diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index 1710fd7..970d6c0 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -12,14 +12,14 @@
 
 		.text
 
-/* Prototype: int __clear_user(void *addr, size_t sz)
+/* Prototype: unsigned long arm_clear_user(void *addr, size_t sz)
  * Purpose  : clear some user memory
  * Params   : addr - user memory address to clear
  *          : sz   - number of bytes to clear
  * Returns  : number of bytes NOT cleared
  */
 ENTRY(__clear_user_std)
-WEAK(__clear_user)
+WEAK(arm_clear_user)
 		stmfd	sp!, {r1, lr}
 		mov	r2, #0
 		cmp	r1, #4
@@ -44,7 +44,7 @@
 USER(		strnebt	r2, [r0])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
-ENDPROC(__clear_user)
+ENDPROC(arm_clear_user)
 ENDPROC(__clear_user_std)
 
 		.pushsection .text.fixup,"ax"
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 7a235b9..1512beb 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -17,7 +17,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_from_user(void *to, const void *from, size_t n)
+ *	size_t arm_copy_from_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -89,11 +89,11 @@
 
 	.text
 
-ENTRY(__copy_from_user)
+ENTRY(arm_copy_from_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_from_user)
+ENDPROC(arm_copy_from_user)
 
 	.pushsection .fixup,"ax"
 	.align 0
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index 9648b06..caf5019 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -17,7 +17,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_to_user(void *to, const void *from, size_t n)
+ *	size_t arm_copy_to_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -93,11 +93,11 @@
 	.text
 
 ENTRY(__copy_to_user_std)
-WEAK(__copy_to_user)
+WEAK(arm_copy_to_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_to_user)
+ENDPROC(arm_copy_to_user)
 ENDPROC(__copy_to_user_std)
 
 	.pushsection .text.fixup,"ax"
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 1d0957e..1712f13 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -17,6 +17,19 @@
 
 		.text
 
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		.macro	save_regs
+		mrc	p15, 0, ip, c3, c0, 0
+		stmfd	sp!, {r1, r2, r4 - r8, ip, lr}
+		uaccess_enable ip
+		.endm
+
+		.macro	load_regs
+		ldmfd	sp!, {r1, r2, r4 - r8, ip, lr}
+		mcr	p15, 0, ip, c3, c0, 0
+		ret	lr
+		.endm
+#else
 		.macro	save_regs
 		stmfd	sp!, {r1, r2, r4 - r8, lr}
 		.endm
@@ -24,6 +37,7 @@
 		.macro	load_regs
 		ldmfd	sp!, {r1, r2, r4 - r8, pc}
 		.endm
+#endif
 
 		.macro	load1b,	reg1
 		ldrusr	\reg1, r0, 1
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index 7797e81..64111bd 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -61,8 +61,10 @@
 
 /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
 
+ENTRY(mmiocpy)
 ENTRY(memcpy)
 
 #include "copy_template.S"
 
 ENDPROC(memcpy)
+ENDPROC(mmiocpy)
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index a4ee97b..3c65e3b 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -16,6 +16,7 @@
 	.text
 	.align	5
 
+ENTRY(mmioset)
 ENTRY(memset)
 UNWIND( .fnstart         )
 	ands	r3, r0, #3		@ 1 unaligned?
@@ -133,3 +134,4 @@
 	b	1b
 UNWIND( .fnend   )
 ENDPROC(memset)
+ENDPROC(mmioset)
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 3e58d71..d72b909 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -96,7 +96,7 @@
 	}
 
 	/* the mmap semaphore is taken only if not in an atomic context */
-	atomic = in_atomic();
+	atomic = faulthandler_disabled();
 
 	if (!atomic)
 		down_read(&current->mm->mmap_sem);
@@ -136,7 +136,7 @@
 }
 
 unsigned long
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+arm_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	/*
 	 * This test is stubbed out of the main function above to keep
@@ -190,7 +190,7 @@
 	return n;
 }
 
-unsigned long __clear_user(void __user *addr, unsigned long n)
+unsigned long arm_clear_user(void __user *addr, unsigned long n)
 {
 	/* See rational for this in __copy_to_user() above. */
 	if (n < 64)
diff --git a/arch/arm/mach-omap2/dma.c b/arch/arm/mach-omap2/dma.c
index e1a56d8..1ed4be1 100644
--- a/arch/arm/mach-omap2/dma.c
+++ b/arch/arm/mach-omap2/dma.c
@@ -117,7 +117,6 @@
 	u8 revision = dma_read(REVISION, 0) & 0xff;
 	printk(KERN_INFO "OMAP DMA hardware revision %d.%d\n",
 				revision >> 4, revision & 0xf);
-	return;
 }
 
 static unsigned configure_dma_errata(void)
diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig
index e03d8b5..9ab8932 100644
--- a/arch/arm/mach-prima2/Kconfig
+++ b/arch/arm/mach-prima2/Kconfig
@@ -4,6 +4,7 @@
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_IRQ_CHIP
 	select NO_IOPORT_MAP
+	select REGMAP
 	select PINCTRL
 	select PINCTRL_SIRF
 	help
diff --git a/arch/arm/mach-prima2/rtciobrg.c b/arch/arm/mach-prima2/rtciobrg.c
index 8f66d8f..d4852d2 100644
--- a/arch/arm/mach-prima2/rtciobrg.c
+++ b/arch/arm/mach-prima2/rtciobrg.c
@@ -1,5 +1,5 @@
 /*
- * RTC I/O Bridge interfaces for CSR SiRFprimaII
+ * RTC I/O Bridge interfaces for CSR SiRFprimaII/atlas7
  * ARM access the registers of SYSRTC, GPSRTC and PWRC through this module
  *
  * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company.
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/io.h>
+#include <linux/regmap.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
@@ -66,6 +67,7 @@
 {
 	unsigned long flags, val;
 
+	/* TODO: add hwspinlock to sync with M3 */
 	spin_lock_irqsave(&rtciobrg_lock, flags);
 
 	val = __sirfsoc_rtc_iobrg_readl(addr);
@@ -90,6 +92,7 @@
 {
 	unsigned long flags;
 
+	 /* TODO: add hwspinlock to sync with M3 */
 	spin_lock_irqsave(&rtciobrg_lock, flags);
 
 	sirfsoc_rtc_iobrg_pre_writel(val, addr);
@@ -102,6 +105,45 @@
 }
 EXPORT_SYMBOL_GPL(sirfsoc_rtc_iobrg_writel);
 
+
+static int regmap_iobg_regwrite(void *context, unsigned int reg,
+				   unsigned int val)
+{
+	sirfsoc_rtc_iobrg_writel(val, reg);
+	return 0;
+}
+
+static int regmap_iobg_regread(void *context, unsigned int reg,
+				  unsigned int *val)
+{
+	*val = (u32)sirfsoc_rtc_iobrg_readl(reg);
+	return 0;
+}
+
+static struct regmap_bus regmap_iobg = {
+	.reg_write = regmap_iobg_regwrite,
+	.reg_read = regmap_iobg_regread,
+};
+
+/**
+ * devm_regmap_init_iobg(): Initialise managed register map
+ *
+ * @iobg: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The regmap will be automatically freed by the
+ * device management code.
+ */
+struct regmap *devm_regmap_init_iobg(struct device *dev,
+				    const struct regmap_config *config)
+{
+	const struct regmap_bus *bus = &regmap_iobg;
+
+	return devm_regmap_init(dev, bus, dev, config);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_init_iobg);
+
 static const struct of_device_id rtciobrg_ids[] = {
 	{ .compatible = "sirf,prima2-rtciobg" },
 	{}
@@ -132,7 +174,7 @@
 }
 postcore_initcall(sirfsoc_rtciobrg_init);
 
-MODULE_AUTHOR("Zhiwu Song <zhiwu.song@csr.com>, "
-		"Barry Song <baohua.song@csr.com>");
+MODULE_AUTHOR("Zhiwu Song <zhiwu.song@csr.com>");
+MODULE_AUTHOR("Barry Song <baohua.song@csr.com>");
 MODULE_DESCRIPTION("CSR SiRFprimaII rtc io bridge");
 MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/mach-shmobile/common.h b/arch/arm/mach-shmobile/common.h
index 476092b..8d27ec5 100644
--- a/arch/arm/mach-shmobile/common.h
+++ b/arch/arm/mach-shmobile/common.h
@@ -13,7 +13,7 @@
 extern void shmobile_smp_sleep(void);
 extern void shmobile_smp_hook(unsigned int cpu, unsigned long fn,
 			      unsigned long arg);
-extern int shmobile_smp_cpu_disable(unsigned int cpu);
+extern bool shmobile_smp_cpu_can_disable(unsigned int cpu);
 extern void shmobile_boot_scu(void);
 extern void shmobile_smp_scu_prepare_cpus(unsigned int max_cpus);
 extern void shmobile_smp_scu_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c
index 3923e09..b23378f 100644
--- a/arch/arm/mach-shmobile/platsmp.c
+++ b/arch/arm/mach-shmobile/platsmp.c
@@ -31,8 +31,8 @@
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-int shmobile_smp_cpu_disable(unsigned int cpu)
+bool shmobile_smp_cpu_can_disable(unsigned int cpu)
 {
-	return 0; /* Hotplug of any CPU is supported */
+	return true; /* Hotplug of any CPU is supported */
 }
 #endif
diff --git a/arch/arm/mach-shmobile/smp-r8a7790.c b/arch/arm/mach-shmobile/smp-r8a7790.c
index 930f45c..947e437 100644
--- a/arch/arm/mach-shmobile/smp-r8a7790.c
+++ b/arch/arm/mach-shmobile/smp-r8a7790.c
@@ -64,7 +64,7 @@
 	.smp_prepare_cpus	= r8a7790_smp_prepare_cpus,
 	.smp_boot_secondary	= shmobile_smp_apmu_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable		= shmobile_smp_cpu_disable,
+	.cpu_can_disable	= shmobile_smp_cpu_can_disable,
 	.cpu_die		= shmobile_smp_apmu_cpu_die,
 	.cpu_kill		= shmobile_smp_apmu_cpu_kill,
 #endif
diff --git a/arch/arm/mach-shmobile/smp-r8a7791.c b/arch/arm/mach-shmobile/smp-r8a7791.c
index 5e2d1db7..b2508c0 100644
--- a/arch/arm/mach-shmobile/smp-r8a7791.c
+++ b/arch/arm/mach-shmobile/smp-r8a7791.c
@@ -58,7 +58,7 @@
 	.smp_prepare_cpus	= r8a7791_smp_prepare_cpus,
 	.smp_boot_secondary	= r8a7791_smp_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable		= shmobile_smp_cpu_disable,
+	.cpu_can_disable	= shmobile_smp_cpu_can_disable,
 	.cpu_die		= shmobile_smp_apmu_cpu_die,
 	.cpu_kill		= shmobile_smp_apmu_cpu_kill,
 #endif
diff --git a/arch/arm/mach-shmobile/smp-sh73a0.c b/arch/arm/mach-shmobile/smp-sh73a0.c
index 2106d6b..ae7c764 100644
--- a/arch/arm/mach-shmobile/smp-sh73a0.c
+++ b/arch/arm/mach-shmobile/smp-sh73a0.c
@@ -68,7 +68,7 @@
 	.smp_prepare_cpus	= sh73a0_smp_prepare_cpus,
 	.smp_boot_secondary	= sh73a0_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable		= shmobile_smp_cpu_disable,
+	.cpu_can_disable	= shmobile_smp_cpu_can_disable,
 	.cpu_die		= shmobile_smp_scu_cpu_die,
 	.cpu_kill		= shmobile_smp_scu_cpu_kill,
 #endif
diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig
index 81502b9..4efe2d4 100644
--- a/arch/arm/mach-sunxi/Kconfig
+++ b/arch/arm/mach-sunxi/Kconfig
@@ -35,7 +35,7 @@
 	select SUN5I_HSTIMER
 
 config MACH_SUN8I
-	bool "Allwinner A23 (sun8i) SoCs support"
+	bool "Allwinner sun8i Family SoCs support"
 	default ARCH_SUNXI
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
diff --git a/arch/arm/mach-sunxi/sunxi.c b/arch/arm/mach-sunxi/sunxi.c
index 1bc811a..65bab28 100644
--- a/arch/arm/mach-sunxi/sunxi.c
+++ b/arch/arm/mach-sunxi/sunxi.c
@@ -67,10 +67,13 @@
 
 static const char * const sun8i_board_dt_compat[] = {
 	"allwinner,sun8i-a23",
+	"allwinner,sun8i-a33",
+	"allwinner,sun8i-h3",
 	NULL,
 };
 
-DT_MACHINE_START(SUN8I_DT, "Allwinner sun8i (A23) Family")
+DT_MACHINE_START(SUN8I_DT, "Allwinner sun8i Family")
+	.init_time	= sun6i_timer_init,
 	.dt_compat	= sun8i_board_dt_compat,
 	.init_late	= sunxi_dt_cpufreq_init,
 MACHINE_END
diff --git a/arch/arm/mm/abort-ev4.S b/arch/arm/mm/abort-ev4.S
index 54473cd4..b3b31e3 100644
--- a/arch/arm/mm/abort-ev4.S
+++ b/arch/arm/mm/abort-ev4.S
@@ -19,6 +19,7 @@
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 	ldr	r3, [r4]			@ read aborted ARM instruction
+	uaccess_disable ip			@ disable userspace access
 	bic	r1, r1, #1 << 11 | 1 << 10	@ clear bits 11 and 10 of FSR
 	tst	r3, #1 << 20			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 11		@ yes.
diff --git a/arch/arm/mm/abort-ev5t.S b/arch/arm/mm/abort-ev5t.S
index a0908d4..a6a381a 100644
--- a/arch/arm/mm/abort-ev5t.S
+++ b/arch/arm/mm/abort-ev5t.S
@@ -21,8 +21,10 @@
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
+	uaccess_disable ip			@ disable user access
 	bic	r1, r1, #1 << 11		@ clear bits 11 of FSR
-	do_ldrd_abort tmp=ip, insn=r3
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ check write
 	orreq	r1, r1, #1 << 11
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev5tj.S b/arch/arm/mm/abort-ev5tj.S
index 4006b7a..00ab011 100644
--- a/arch/arm/mm/abort-ev5tj.S
+++ b/arch/arm/mm/abort-ev5tj.S
@@ -24,7 +24,9 @@
 	bne	do_DataAbort
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
-	do_ldrd_abort tmp=ip, insn=r3
+	uaccess_disable ip			@ disable userspace access
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 8c48c5c..8801a15 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -26,16 +26,18 @@
 	ldr	ip, =0x4107b36
 	mrc	p15, 0, r3, c0, c0, 0		@ get processor id
 	teq	ip, r3, lsr #4			@ r0 ARM1136?
-	bne	do_DataAbort
+	bne	1f
 	tst	r5, #PSR_J_BIT			@ Java?
 	tsteq	r5, #PSR_T_BIT			@ Thumb?
-	bne	do_DataAbort
+	bne	1f
 	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
 	ldr	r3, [r4]			@ read aborted ARM instruction
  ARM_BE8(rev	r3, r3)
 
-	do_ldrd_abort tmp=ip, insn=r3
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	1f				@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
 #endif
+1:	uaccess_disable ip			@ disable userspace access
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index 4812ad0..e8d0e08 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -15,6 +15,7 @@
 ENTRY(v7_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
+	uaccess_disable ip			@ disable userspace access
 
 	/*
 	 * V6 code adjusts the returned DFSR.
diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S
index f398258..6d8e8e3 100644
--- a/arch/arm/mm/abort-lv4t.S
+++ b/arch/arm/mm/abort-lv4t.S
@@ -26,6 +26,7 @@
 #endif
 	bne	.data_thumb_abort
 	ldr	r8, [r4]			@ read arm instruction
+	uaccess_disable ip			@ disable userspace access
 	tst	r8, #1 << 20			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 11		@ yes.
 	and	r7, r8, #15 << 24
@@ -155,6 +156,7 @@
 
 .data_thumb_abort:
 	ldrh	r8, [r4]			@ read instruction
+	uaccess_disable ip			@ disable userspace access
 	tst	r8, #1 << 11			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 8			@ yes
 	and	r7, r8, #15 << 12
diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S
index 2cbf68e..4509bee 100644
--- a/arch/arm/mm/abort-macro.S
+++ b/arch/arm/mm/abort-macro.S
@@ -13,6 +13,7 @@
 	tst	\psr, #PSR_T_BIT
 	beq	not_thumb
 	ldrh	\tmp, [\pc]			@ Read aborted Thumb instruction
+	uaccess_disable ip			@ disable userspace access
 	and	\tmp, \tmp, # 0xfe00		@ Mask opcode field
 	cmp	\tmp, # 0x5600			@ Is it ldrsb?
 	orreq	\tmp, \tmp, #1 << 11		@ Set L-bit if yes
@@ -29,12 +30,9 @@
  *   [7:4] == 1101
  *    [20] == 0
  */
-	.macro	do_ldrd_abort, tmp, insn
-	tst	\insn, #0x0e100000		@ [27:25,20] == 0
-	bne	not_ldrd
-	and	\tmp, \insn, #0x000000f0	@ [7:4] == 1101
-	cmp	\tmp, #0x000000d0
-	beq	do_DataAbort
-not_ldrd:
+	.macro	teq_ldrd, tmp, insn
+	mov	\tmp, #0x0e100000
+	orr	\tmp, #0x000000f0
+	and	\tmp, \insn, \tmp
+	teq	\tmp, #0x000000d0
 	.endm
-
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index 097181e..5c1b7a7 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -368,7 +368,6 @@
 	struct device_node *node;
 	void __iomem *base;
 	bool l2_wt_override = false;
-	struct resource res;
 
 #if defined(CONFIG_CACHE_FEROCEON_L2_WRITETHROUGH)
 	l2_wt_override = true;
@@ -376,10 +375,7 @@
 
 	node = of_find_matching_node(NULL, feroceon_ids);
 	if (node && of_device_is_compatible(node, "marvell,kirkwood-cache")) {
-		if (of_address_to_resource(node, 0, &res))
-			return -ENODEV;
-
-		base = ioremap(res.start, resource_size(&res));
+		base = of_iomap(node, 0);
 		if (!base)
 			return -ENOMEM;
 
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 71b3d33..493692d 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -1171,6 +1171,11 @@
 		}
 	}
 
+	if (of_property_read_bool(np, "arm,shared-override")) {
+		*aux_val |= L2C_AUX_CTRL_SHARED_OVERRIDE;
+		*aux_mask &= ~L2C_AUX_CTRL_SHARED_OVERRIDE;
+	}
+
 	prefetch = l2x0_saved_regs.prefetch_ctrl;
 
 	ret = of_property_read_u32(np, "arm,double-linefill", &val);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1ced8a0..9f509b2 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -39,6 +39,7 @@
 #include <asm/system_info.h>
 #include <asm/dma-contiguous.h>
 
+#include "dma.h"
 #include "mm.h"
 
 /*
@@ -648,14 +649,18 @@
 	size = PAGE_ALIGN(size);
 	want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs);
 
-	if (is_coherent || nommu())
+	if (nommu())
+		addr = __alloc_simple_buffer(dev, size, gfp, &page);
+	else if (dev_get_cma_area(dev) && (gfp & __GFP_WAIT))
+		addr = __alloc_from_contiguous(dev, size, prot, &page,
+					       caller, want_vaddr);
+	else if (is_coherent)
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
 	else if (!(gfp & __GFP_WAIT))
 		addr = __alloc_from_pool(size, &page);
-	else if (!dev_get_cma_area(dev))
-		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller, want_vaddr);
 	else
-		addr = __alloc_from_contiguous(dev, size, prot, &page, caller, want_vaddr);
+		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page,
+					    caller, want_vaddr);
 
 	if (page)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
@@ -683,13 +688,12 @@
 static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
 	dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
-	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	void *memory;
 
 	if (dma_alloc_from_coherent(dev, size, handle, &memory))
 		return memory;
 
-	return __dma_alloc(dev, size, handle, gfp, prot, true,
+	return __dma_alloc(dev, size, handle, gfp, PAGE_KERNEL, true,
 			   attrs, __builtin_return_address(0));
 }
 
@@ -753,12 +757,12 @@
 
 	size = PAGE_ALIGN(size);
 
-	if (is_coherent || nommu()) {
+	if (nommu()) {
 		__dma_free_buffer(page, size);
-	} else if (__free_from_pool(cpu_addr, size)) {
+	} else if (!is_coherent && __free_from_pool(cpu_addr, size)) {
 		return;
 	} else if (!dev_get_cma_area(dev)) {
-		if (want_vaddr)
+		if (want_vaddr && !is_coherent)
 			__dma_free_remap(cpu_addr, size);
 		__dma_free_buffer(page, size);
 	} else {
@@ -1971,7 +1975,7 @@
 {
 	int next_bitmap;
 
-	if (mapping->nr_bitmaps > mapping->extensions)
+	if (mapping->nr_bitmaps >= mapping->extensions)
 		return -EINVAL;
 
 	next_bitmap = mapping->nr_bitmaps;
diff --git a/arch/arm/mm/dma.h b/arch/arm/mm/dma.h
new file mode 100644
index 0000000..70ea6852
--- /dev/null
+++ b/arch/arm/mm/dma.h
@@ -0,0 +1,32 @@
+#ifndef DMA_H
+#define DMA_H
+
+#include <asm/glue-cache.h>
+
+#ifndef MULTI_CACHE
+#define dmac_map_area			__glue(_CACHE,_dma_map_area)
+#define dmac_unmap_area 		__glue(_CACHE,_dma_unmap_area)
+
+/*
+ * These are private to the dma-mapping API.  Do not use directly.
+ * Their sole purpose is to ensure that data held in the cache
+ * is visible to DMA, or data written by DMA to system memory is
+ * visible to the CPU.
+ */
+extern void dmac_map_area(const void *, size_t, int);
+extern void dmac_unmap_area(const void *, size_t, int);
+
+#else
+
+/*
+ * These are private to the dma-mapping API.  Do not use directly.
+ * Their sole purpose is to ensure that data held in the cache
+ * is visible to DMA, or data written by DMA to system memory is
+ * visible to the CPU.
+ */
+#define dmac_map_area			cpu_cache.dma_map_area
+#define dmac_unmap_area 		cpu_cache.dma_unmap_area
+
+#endif
+
+#endif
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index ee8dfa7..9df5f09 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -79,7 +79,7 @@
 
 	type = kmap_atomic_idx_push();
 
-	idx = type + KM_TYPE_NR * smp_processor_id();
+	idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
 	/*
@@ -106,7 +106,7 @@
 
 	if (kvaddr >= (void *)FIXADDR_START) {
 		type = kmap_atomic_idx();
-		idx = type + KM_TYPE_NR * smp_processor_id();
+		idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
 
 		if (cache_is_vivt())
 			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
@@ -138,7 +138,7 @@
 		return page_address(page);
 
 	type = kmap_atomic_idx_push();
-	idx = type + KM_TYPE_NR * smp_processor_id();
+	idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
 	BUG_ON(!pte_none(get_fixmap_pte(vaddr)));
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index d1e5ad7..0c81056 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -255,7 +255,7 @@
 }
 #endif
 
-void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
+static void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	unsigned long offset, size_t size, unsigned int mtype, void *caller)
 {
 	const struct mem_type *type;
@@ -363,7 +363,7 @@
 		  unsigned int mtype)
 {
 	return __arm_ioremap_pfn_caller(pfn, offset, size, mtype,
-			__builtin_return_address(0));
+					__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
@@ -371,13 +371,26 @@
 				      unsigned int, void *) =
 	__arm_ioremap_caller;
 
-void __iomem *
-__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype)
+void __iomem *ioremap(resource_size_t res_cookie, size_t size)
 {
-	return arch_ioremap_caller(phys_addr, size, mtype,
-		__builtin_return_address(0));
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE,
+				   __builtin_return_address(0));
 }
-EXPORT_SYMBOL(__arm_ioremap);
+EXPORT_SYMBOL(ioremap);
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+{
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
+				   __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
+{
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE_WC,
+				   __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wc);
 
 /*
  * Remap an arbitrary physical address space into the kernel virtual
@@ -431,11 +444,11 @@
 
 void (*arch_iounmap)(volatile void __iomem *) = __iounmap;
 
-void __arm_iounmap(volatile void __iomem *io_addr)
+void iounmap(volatile void __iomem *cookie)
 {
-	arch_iounmap(io_addr);
+	arch_iounmap(cookie);
 }
-EXPORT_SYMBOL(__arm_iounmap);
+EXPORT_SYMBOL(iounmap);
 
 #ifdef CONFIG_PCI
 static int pci_ioremap_mem_type = MT_DEVICE;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6ca7d9a..7cd1514 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -291,13 +291,13 @@
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_RDONLY,
 		.prot_l1   = PMD_TYPE_TABLE,
-		.domain    = DOMAIN_USER,
+		.domain    = DOMAIN_VECTORS,
 	},
 	[MT_HIGH_VECTORS] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_USER | L_PTE_RDONLY,
 		.prot_l1   = PMD_TYPE_TABLE,
-		.domain    = DOMAIN_USER,
+		.domain    = DOMAIN_VECTORS,
 	},
 	[MT_MEMORY_RWX] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
@@ -357,6 +357,47 @@
 }
 EXPORT_SYMBOL(get_mem_type);
 
+static pte_t *(*pte_offset_fixmap)(pmd_t *dir, unsigned long addr);
+
+static pte_t bm_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS]
+	__aligned(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE) __initdata;
+
+static pte_t * __init pte_offset_early_fixmap(pmd_t *dir, unsigned long addr)
+{
+	return &bm_pte[pte_index(addr)];
+}
+
+static pte_t *pte_offset_late_fixmap(pmd_t *dir, unsigned long addr)
+{
+	return pte_offset_kernel(dir, addr);
+}
+
+static inline pmd_t * __init fixmap_pmd(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	pud_t *pud = pud_offset(pgd, addr);
+	pmd_t *pmd = pmd_offset(pud, addr);
+
+	return pmd;
+}
+
+void __init early_fixmap_init(void)
+{
+	pmd_t *pmd;
+
+	/*
+	 * The early fixmap range spans multiple pmds, for which
+	 * we are not prepared:
+	 */
+	BUILD_BUG_ON((__fix_to_virt(__end_of_permanent_fixed_addresses) >> PMD_SHIFT)
+		     != FIXADDR_TOP >> PMD_SHIFT);
+
+	pmd = fixmap_pmd(FIXADDR_TOP);
+	pmd_populate_kernel(&init_mm, pmd, bm_pte);
+
+	pte_offset_fixmap = pte_offset_early_fixmap;
+}
+
 /*
  * To avoid TLB flush broadcasts, this uses local_flush_tlb_kernel_range().
  * As a result, this can only be called with preemption disabled, as under
@@ -365,7 +406,7 @@
 void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
 {
 	unsigned long vaddr = __fix_to_virt(idx);
-	pte_t *pte = pte_offset_kernel(pmd_off_k(vaddr), vaddr);
+	pte_t *pte = pte_offset_fixmap(pmd_off_k(vaddr), vaddr);
 
 	/* Make sure fixmap region does not exceed available allocation. */
 	BUILD_BUG_ON(FIXADDR_START + (__end_of_fixed_addresses * PAGE_SIZE) >
@@ -855,7 +896,7 @@
 	}
 
 	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
-	    md->virtual >= PAGE_OFFSET &&
+	    md->virtual >= PAGE_OFFSET && md->virtual < FIXADDR_START &&
 	    (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) {
 		pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n",
 			(long long)__pfn_to_phys((u64)md->pfn), md->virtual);
@@ -1072,6 +1113,7 @@
 	int highmem = 0;
 	phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
 	struct memblock_region *reg;
+	bool should_use_highmem = false;
 
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
@@ -1090,6 +1132,7 @@
 				pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n",
 					  &block_start, &block_end);
 				memblock_remove(reg->base, reg->size);
+				should_use_highmem = true;
 				continue;
 			}
 
@@ -1100,6 +1143,7 @@
 					  &block_start, &block_end, &vmalloc_limit);
 				memblock_remove(vmalloc_limit, overlap_size);
 				block_end = vmalloc_limit;
+				should_use_highmem = true;
 			}
 		}
 
@@ -1134,6 +1178,9 @@
 		}
 	}
 
+	if (should_use_highmem)
+		pr_notice("Consider using a HIGHMEM enabled kernel.\n");
+
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
 	/*
@@ -1213,10 +1260,10 @@
 
 /*
  * Set up the device mappings.  Since we clear out the page tables for all
- * mappings above VMALLOC_START, we will remove any debug device mappings.
- * This means you have to be careful how you debug this function, or any
- * called function.  This means you can't use any function or debugging
- * method which may touch any device, otherwise the kernel _will_ crash.
+ * mappings above VMALLOC_START, except early fixmap, we might remove debug
+ * device mappings.  This means earlycon can be used to debug this function
+ * Any other function or debugging method which may touch any device _will_
+ * crash the kernel.
  */
 static void __init devicemaps_init(const struct machine_desc *mdesc)
 {
@@ -1231,7 +1278,10 @@
 
 	early_trap_init(vectors);
 
-	for (addr = VMALLOC_START; addr; addr += PMD_SIZE)
+	/*
+	 * Clear page table except top pmd used by early fixmaps
+	 */
+	for (addr = VMALLOC_START; addr < (FIXADDR_TOP & PMD_MASK); addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 	/*
@@ -1483,6 +1533,35 @@
 
 #endif
 
+static void __init early_fixmap_shutdown(void)
+{
+	int i;
+	unsigned long va = fix_to_virt(__end_of_permanent_fixed_addresses - 1);
+
+	pte_offset_fixmap = pte_offset_late_fixmap;
+	pmd_clear(fixmap_pmd(va));
+	local_flush_tlb_kernel_page(va);
+
+	for (i = 0; i < __end_of_permanent_fixed_addresses; i++) {
+		pte_t *pte;
+		struct map_desc map;
+
+		map.virtual = fix_to_virt(i);
+		pte = pte_offset_early_fixmap(pmd_off_k(map.virtual), map.virtual);
+
+		/* Only i/o device mappings are supported ATM */
+		if (pte_none(*pte) ||
+		    (pte_val(*pte) & L_PTE_MT_MASK) != L_PTE_MT_DEV_SHARED)
+			continue;
+
+		map.pfn = pte_pfn(*pte);
+		map.type = MT_DEVICE;
+		map.length = PAGE_SIZE;
+
+		create_mapping(&map);
+	}
+}
+
 /*
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
@@ -1494,7 +1573,9 @@
 	build_mem_type_table();
 	prepare_page_table();
 	map_lowmem();
+	memblock_set_current_limit(arm_lowmem_limit);
 	dma_contiguous_remap();
+	early_fixmap_shutdown();
 	devicemaps_init(mdesc);
 	kmap_init();
 	tcm_init();
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index afd7e05..1dd1093 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -351,30 +351,43 @@
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
-void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset,
-			   size_t size, unsigned int mtype, void *caller)
-{
-	return __arm_ioremap_pfn(pfn, offset, size, mtype);
-}
-
-void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size,
-			    unsigned int mtype)
-{
-	return (void __iomem *)phys_addr;
-}
-EXPORT_SYMBOL(__arm_ioremap);
-
-void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
-
 void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
-	return __arm_ioremap(phys_addr, size, mtype);
+	return (void __iomem *)phys_addr;
 }
 
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
+
+void __iomem *ioremap(resource_size_t res_cookie, size_t size)
+{
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap);
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+{
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
+{
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_WC,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wc);
+
+void __iounmap(volatile void __iomem *addr)
+{
+}
+EXPORT_SYMBOL(__iounmap);
+
 void (*arch_iounmap)(volatile void __iomem *);
 
-void __arm_iounmap(volatile void __iomem *addr)
+void iounmap(volatile void __iomem *addr)
 {
 }
-EXPORT_SYMBOL(__arm_iounmap);
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index a3681f1..e683db1 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -84,6 +84,16 @@
 		if (!new_pte)
 			goto no_pte;
 
+#ifndef CONFIG_ARM_LPAE
+		/*
+		 * Modify the PTE pointer to have the correct domain.  This
+		 * needs to be the vectors domain to avoid the low vectors
+		 * being unmapped.
+		 */
+		pmd_val(*new_pmd) &= ~PMD_DOMAIN_MASK;
+		pmd_val(*new_pmd) |= PMD_DOMAIN(DOMAIN_VECTORS);
+#endif
+
 		init_pud = pud_offset(init_pgd, 0);
 		init_pmd = pmd_offset(init_pud, 0);
 		init_pte = pte_offset_map(init_pmd, 0);
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 0716bbe..de2b246 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -274,7 +274,10 @@
 __v7_b15mp_setup:
 __v7_ca17mp_setup:
 	mov	r10, #0
-1:
+1:	adr	r12, __v7_setup_stack		@ the local stack
+	stmia	r12, {r0-r5, lr}		@ v7_invalidate_l1 touches r0-r6
+	bl      v7_invalidate_l1
+	ldmia	r12, {r0-r5, lr}
 #ifdef CONFIG_SMP
 	ALT_SMP(mrc	p15, 0, r0, c1, c0, 1)
 	ALT_UP(mov	r0, #(1 << 6))		@ fake it for UP
@@ -283,7 +286,7 @@
 	orreq	r0, r0, r10			@ Enable CPU-specific SMP bits
 	mcreq	p15, 0, r0, c1, c0, 1
 #endif
-	b	__v7_setup
+	b	__v7_setup_cont
 
 /*
  * Errata:
@@ -413,10 +416,11 @@
 
 __v7_setup:
 	adr	r12, __v7_setup_stack		@ the local stack
-	stmia	r12, {r0-r5, r7, r9, r11, lr}
+	stmia	r12, {r0-r5, lr}		@ v7_invalidate_l1 touches r0-r6
 	bl      v7_invalidate_l1
-	ldmia	r12, {r0-r5, r7, r9, r11, lr}
+	ldmia	r12, {r0-r5, lr}
 
+__v7_setup_cont:
 	and	r0, r9, #0xff000000		@ ARM?
 	teq	r0, #0x41000000
 	bne	__errata_finish
@@ -480,7 +484,7 @@
 
 	.align	2
 __v7_setup_stack:
-	.space	4 * 11				@ 11 registers
+	.space	4 * 7				@ 12 registers
 
 	__INITDATA
 
diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
index 9d259d9..1160434 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
@@ -14,7 +14,7 @@
 VDSO_LDFLAGS += -nostdlib -shared
 VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--build-id)
-VDSO_LDFLAGS += $(call cc-option, -fuse-ld=bfd)
+VDSO_LDFLAGS += $(call cc-ldoption, -fuse-ld=bfd)
 
 obj-$(CONFIG_VDSO) += vdso.o
 extra-$(CONFIG_VDSO) += vdso.lds
diff --git a/arch/arm/vdso/vdsomunge.c b/arch/arm/vdso/vdsomunge.c
index 9005b07..aedec81 100644
--- a/arch/arm/vdso/vdsomunge.c
+++ b/arch/arm/vdso/vdsomunge.c
@@ -45,13 +45,11 @@
  * it does.
  */
 
-#define _GNU_SOURCE
-
 #include <byteswap.h>
 #include <elf.h>
 #include <errno.h>
-#include <error.h>
 #include <fcntl.h>
+#include <stdarg.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -82,11 +80,25 @@
 #define EF_ARM_ABI_FLOAT_HARD 0x400
 #endif
 
+static int failed;
+static const char *argv0;
 static const char *outfile;
 
+static void fail(const char *fmt, ...)
+{
+	va_list ap;
+
+	failed = 1;
+	fprintf(stderr, "%s: ", argv0);
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	exit(EXIT_FAILURE);
+}
+
 static void cleanup(void)
 {
-	if (error_message_count > 0 && outfile != NULL)
+	if (failed && outfile != NULL)
 		unlink(outfile);
 }
 
@@ -119,68 +131,66 @@
 	int infd;
 
 	atexit(cleanup);
+	argv0 = argv[0];
 
 	if (argc != 3)
-		error(EXIT_FAILURE, 0, "Usage: %s [infile] [outfile]", argv[0]);
+		fail("Usage: %s [infile] [outfile]\n", argv[0]);
 
 	infile = argv[1];
 	outfile = argv[2];
 
 	infd = open(infile, O_RDONLY);
 	if (infd < 0)
-		error(EXIT_FAILURE, errno, "Cannot open %s", infile);
+		fail("Cannot open %s: %s\n", infile, strerror(errno));
 
 	if (fstat(infd, &stat) != 0)
-		error(EXIT_FAILURE, errno, "Failed stat for %s", infile);
+		fail("Failed stat for %s: %s\n", infile, strerror(errno));
 
 	inbuf = mmap(NULL, stat.st_size, PROT_READ, MAP_PRIVATE, infd, 0);
 	if (inbuf == MAP_FAILED)
-		error(EXIT_FAILURE, errno, "Failed to map %s", infile);
+		fail("Failed to map %s: %s\n", infile, strerror(errno));
 
 	close(infd);
 
 	inhdr = inbuf;
 
 	if (memcmp(&inhdr->e_ident, ELFMAG, SELFMAG) != 0)
-		error(EXIT_FAILURE, 0, "Not an ELF file");
+		fail("Not an ELF file\n");
 
 	if (inhdr->e_ident[EI_CLASS] != ELFCLASS32)
-		error(EXIT_FAILURE, 0, "Unsupported ELF class");
+		fail("Unsupported ELF class\n");
 
 	swap = inhdr->e_ident[EI_DATA] != HOST_ORDER;
 
 	if (read_elf_half(inhdr->e_type, swap) != ET_DYN)
-		error(EXIT_FAILURE, 0, "Not a shared object");
+		fail("Not a shared object\n");
 
-	if (read_elf_half(inhdr->e_machine, swap) != EM_ARM) {
-		error(EXIT_FAILURE, 0, "Unsupported architecture %#x",
-		      inhdr->e_machine);
-	}
+	if (read_elf_half(inhdr->e_machine, swap) != EM_ARM)
+		fail("Unsupported architecture %#x\n", inhdr->e_machine);
 
 	e_flags = read_elf_word(inhdr->e_flags, swap);
 
 	if (EF_ARM_EABI_VERSION(e_flags) != EF_ARM_EABI_VER5) {
-		error(EXIT_FAILURE, 0, "Unsupported EABI version %#x",
-		      EF_ARM_EABI_VERSION(e_flags));
+		fail("Unsupported EABI version %#x\n",
+		     EF_ARM_EABI_VERSION(e_flags));
 	}
 
 	if (e_flags & EF_ARM_ABI_FLOAT_HARD)
-		error(EXIT_FAILURE, 0,
-		      "Unexpected hard-float flag set in e_flags");
+		fail("Unexpected hard-float flag set in e_flags\n");
 
 	clear_soft_float = !!(e_flags & EF_ARM_ABI_FLOAT_SOFT);
 
 	outfd = open(outfile, O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR);
 	if (outfd < 0)
-		error(EXIT_FAILURE, errno, "Cannot open %s", outfile);
+		fail("Cannot open %s: %s\n", outfile, strerror(errno));
 
 	if (ftruncate(outfd, stat.st_size) != 0)
-		error(EXIT_FAILURE, errno, "Cannot truncate %s", outfile);
+		fail("Cannot truncate %s: %s\n", outfile, strerror(errno));
 
 	outbuf = mmap(NULL, stat.st_size, PROT_READ | PROT_WRITE, MAP_SHARED,
 		      outfd, 0);
 	if (outbuf == MAP_FAILED)
-		error(EXIT_FAILURE, errno, "Failed to map %s", outfile);
+		fail("Failed to map %s: %s\n", outfile, strerror(errno));
 
 	close(outfd);
 
@@ -195,7 +205,7 @@
 	}
 
 	if (msync(outbuf, stat.st_size, MS_SYNC) != 0)
-		error(EXIT_FAILURE, errno, "Failed to sync %s", outfile);
+		fail("Failed to sync %s: %s\n", outfile, strerror(errno));
 
 	return EXIT_SUCCESS;
 }
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 0f6edb1..318175f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -23,9 +23,9 @@
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select EDAC_SUPPORT
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS
+	select EDAC_SUPPORT
 	select GENERIC_ALLOCATOR
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
diff --git a/arch/arm64/boot/dts/apm/apm-mustang.dts b/arch/arm64/boot/dts/apm/apm-mustang.dts
index 83578e7..4c55833 100644
--- a/arch/arm64/boot/dts/apm/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm/apm-mustang.dts
@@ -23,6 +23,16 @@
 		device_type = "memory";
 		reg = < 0x1 0x00000000 0x0 0x80000000 >; /* Updated by bootloader */
 	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		button@1 {
+			label = "POWER";
+			linux,code = <116>;
+			linux,input-type = <0x1>;
+			interrupts = <0x0 0x2d 0x1>;
+		};
+	};
 };
 
 &pcie0clk {
diff --git a/arch/arm64/boot/dts/arm/Makefile b/arch/arm64/boot/dts/arm/Makefile
index c5c98b9..bb3c072 100644
--- a/arch/arm64/boot/dts/arm/Makefile
+++ b/arch/arm64/boot/dts/arm/Makefile
@@ -1,6 +1,7 @@
 dtb-$(CONFIG_ARCH_VEXPRESS) += foundation-v8.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += juno.dtb juno-r1.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2f-1xv7-ca53x2.dtb
 
 always		:= $(dtb-y)
 subdir-y	:= $(dts-dirs)
diff --git a/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts
new file mode 100644
index 0000000..5b1d018
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts
@@ -0,0 +1,191 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ * LogicTile Express 20MG
+ * V2F-1XV7
+ *
+ * Cortex-A53 (2 cores) Soft Macrocell Model
+ *
+ * HBI-0247C
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	model = "V2F-1XV7 Cortex-A53x2 SMM";
+	arm,hbi = <0x247>;
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,vexpress,v2f-1xv7,ca53x2", "arm,vexpress,v2f-1xv7", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen {
+		stdout-path = "serial0:38400n8";
+	};
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+		i2c0 = &v2m_i2c_dvi;
+		i2c1 = &v2m_i2c_pcie;
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0 0>;
+			next-level-cache = <&L2_0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0 1>;
+			next-level-cache = <&L2_0>;
+		};
+
+		L2_0: l2-cache0 {
+			compatible = "cache";
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>; /* 2GB @ 2GB */
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,gic-400";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x2000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		smbclk: osc@4 {
+			/* SMC clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 4>;
+			freq-range = <40000000 40000000>;
+			#clock-cells = <0>;
+			clock-output-names = "smclk";
+		};
+
+		volt@0 {
+			/* VIO to expansion board above */
+			compatible = "arm,vexpress-volt";
+			arm,vexpress-sysreg,func = <2 0>;
+			regulator-name = "VIO_UP";
+			regulator-min-microvolt = <800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-always-on;
+		};
+
+		volt@1 {
+			/* 12V from power connector J6 */
+			compatible = "arm,vexpress-volt";
+			arm,vexpress-sysreg,func = <2 1>;
+			regulator-name = "12";
+			regulator-always-on;
+		};
+
+		temp@0 {
+			/* FPGA temperature */
+			compatible = "arm,vexpress-temp";
+			arm,vexpress-sysreg,func = <4 0>;
+			label = "FPGA";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic GIC_SPI  0 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  1 &gic GIC_SPI  1 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  2 &gic GIC_SPI  2 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  3 &gic GIC_SPI  3 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  4 &gic GIC_SPI  4 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  5 &gic GIC_SPI  5 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  6 &gic GIC_SPI  6 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  7 &gic GIC_SPI  7 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  8 &gic GIC_SPI  8 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  9 &gic GIC_SPI  9 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 10 &gic GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 11 &gic GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 12 &gic GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 13 &gic GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 14 &gic GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 15 &gic GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 16 &gic GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 17 &gic GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 18 &gic GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 19 &gic GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 20 &gic GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 21 &gic GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 22 &gic GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 23 &gic GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 24 &gic GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 25 &gic GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 26 &gic GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 27 &gic GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 28 &gic GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 29 &gic GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 30 &gic GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 31 &gic GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 32 &gic GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 33 &gic GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 34 &gic GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 35 &gic GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 36 &gic GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 37 &gic GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 38 &gic GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 39 &gic GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 40 &gic GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 41 &gic GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 42 &gic GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
+
+		/include/ "../../../../arm/boot/dts/vexpress-v2m-rs1.dtsi"
+	};
+};
diff --git a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
index d8c0bdc..9cb7cf9 100644
--- a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
+++ b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
@@ -376,10 +376,19 @@
 		gic0: interrupt-controller@8010,00000000 {
 			compatible = "arm,gic-v3";
 			#interrupt-cells = <3>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
 			interrupt-controller;
 			reg = <0x8010 0x00000000 0x0 0x010000>, /* GICD */
 			      <0x8010 0x80000000 0x0 0x600000>; /* GICR */
 			interrupts = <1 9 0xf04>;
+
+			its: gic-its@8010,00020000 {
+				compatible = "arm,gic-v3-its";
+				msi-controller;
+				reg = <0x8010 0x20000 0x0 0x200000>;
+			};
 		};
 
 		uaa0: serial@87e0,24000000 {
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index f38c94f..4e17e7e 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -83,6 +83,7 @@
 CONFIG_ATA=y
 CONFIG_SATA_AHCI=y
 CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_AHCI_CEVA=y
 CONFIG_AHCI_XGENE=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_PATA_OF_PLATFORM=y
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 39248d3..406485e 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -19,6 +19,14 @@
 #include <asm/psci.h>
 #include <asm/smp_plat.h>
 
+/* Macros for consistency checks of the GICC subtable of MADT */
+#define ACPI_MADT_GICC_LENGTH	\
+	(acpi_gbl_FADT.header.revision < 6 ? 76 : 80)
+
+#define BAD_MADT_GICC_ENTRY(entry, end)						\
+	(!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) ||	\
+	 (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
 /* ACPI table mapping after acpi_gbl_permanent_mmap is set */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a7691a3..f860bfd 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -352,8 +352,8 @@
 	// TODO: add support for undefined instructions in kernel mode
 	enable_dbg
 	mov	x0, sp
+	mov	x2, x1
 	mov	x1, #BAD_SYNC
-	mrs	x2, esr_el1
 	b	bad_mode
 ENDPROC(el1_sync)
 
@@ -553,7 +553,7 @@
 	ct_user_exit
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
-	mrs	x2, esr_el1
+	mov	x2, x25
 	bl	bad_mode
 	b	ret_to_user
 ENDPROC(el0_sync)
diff --git a/arch/arm64/kernel/entry32.S b/arch/arm64/kernel/entry32.S
index bd9bfaa..f332d5d 100644
--- a/arch/arm64/kernel/entry32.S
+++ b/arch/arm64/kernel/entry32.S
@@ -32,13 +32,11 @@
 
 ENTRY(compat_sys_sigreturn_wrapper)
 	mov	x0, sp
-	mov	x27, #0		// prevent syscall restart handling (why)
 	b	compat_sys_sigreturn
 ENDPROC(compat_sys_sigreturn_wrapper)
 
 ENTRY(compat_sys_rt_sigreturn_wrapper)
 	mov	x0, sp
-	mov	x27, #0		// prevent syscall restart handling (why)
 	b	compat_sys_rt_sigreturn
 ENDPROC(compat_sys_rt_sigreturn_wrapper)
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 695801a..50fb469 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -438,7 +438,7 @@
 	struct acpi_madt_generic_interrupt *processor;
 
 	processor = (struct acpi_madt_generic_interrupt *)header;
-	if (BAD_MADT_ENTRY(processor, end))
+	if (BAD_MADT_GICC_ENTRY(processor, end))
 		return -EINVAL;
 
 	acpi_table_print_madt_entry(header);
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 9d84feb..773d37a 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,5 +4,3 @@
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_ARM64_PTDUMP)	+= dump.o
-
-CFLAGS_mmu.o			:= -I$(srctree)/scripts/dtc/libfdt/
diff --git a/arch/cris/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c
index 4dda9bd..e989cee 100644
--- a/arch/cris/arch-v32/drivers/sync_serial.c
+++ b/arch/cris/arch-v32/drivers/sync_serial.c
@@ -1464,7 +1464,7 @@
 		if (port->write_ts_idx == NBR_IN_DESCR)
 			port->write_ts_idx = 0;
 		idx = port->write_ts_idx++;
-		do_posix_clock_monotonic_gettime(&port->timestamp[idx]);
+		ktime_get_ts(&port->timestamp[idx]);
 		port->in_buffer_len += port->inbufchunk;
 	}
 	spin_unlock_irqrestore(&port->lock, flags);
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 2a14585..aab7e46 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2231,7 +2231,7 @@
 
 config MIPS_CPS
 	bool "MIPS Coherent Processing System support"
-	depends on SYS_SUPPORTS_MIPS_CPS && !64BIT
+	depends on SYS_SUPPORTS_MIPS_CPS
 	select MIPS_CM
 	select MIPS_CPC
 	select MIPS_CPS_PM if HOTPLUG_CPU
diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h
index 37c08a2..c9f7e23 100644
--- a/arch/mips/include/asm/mach-loongson64/mmzone.h
+++ b/arch/mips/include/asm/mach-loongson64/mmzone.h
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010 Loongson Inc. & Lemote Inc. &
- *                    Insititute of Computing Technology
+ *                    Institute of Computing Technology
  * Author:  Xiang Gao, gaoxiang@ict.ac.cn
  *          Huacai Chen, chenhc@lemote.com
  *          Xiaofu Meng, Shuangshuang Zhang
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index 2b25d1b..16f1ea9 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -23,6 +23,7 @@
 extern int smp_num_siblings;
 extern cpumask_t cpu_sibling_map[];
 extern cpumask_t cpu_core_map[];
+extern cpumask_t cpu_foreign_map;
 
 #define raw_smp_processor_id() (current_thread_info()->cpu)
 
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index c0c5e59..d8f9b35 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -600,7 +600,7 @@
 		break;
 
 	case blezl_op: /* not really i_format */
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			goto sigill_r6;
 	case blez_op:
 		/*
@@ -635,7 +635,7 @@
 		break;
 
 	case bgtzl_op:
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			goto sigill_r6;
 	case bgtz_op:
 		/*
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 55b759a..1b6ca63 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -60,7 +60,7 @@
 	 nop
 
 	/* This is an NMI */
-	la	k0, nmi_handler
+	PTR_LA	k0, nmi_handler
 	jr	k0
 	 nop
 
@@ -107,10 +107,10 @@
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
-	li	a0, KSEG0
-	add	a1, a0, t1
+	li	a0, CKSEG0
+	PTR_ADD	a1, a0, t1
 1:	cache	Index_Store_Tag_I, 0(a0)
-	add	a0, a0, t0
+	PTR_ADD	a0, a0, t0
 	bne	a0, a1, 1b
 	 nop
 icache_done:
@@ -134,12 +134,12 @@
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
-	li	a0, KSEG0
-	addu	a1, a0, t1
-	subu	a1, a1, t0
+	li	a0, CKSEG0
+	PTR_ADDU a1, a0, t1
+	PTR_SUBU a1, a1, t0
 1:	cache	Index_Store_Tag_D, 0(a0)
 	bne	a0, a1, 1b
-	 add	a0, a0, t0
+	 PTR_ADD a0, a0, t0
 dcache_done:
 
 	/* Set Kseg0 CCA to that in s0 */
@@ -152,11 +152,11 @@
 
 	/* Enter the coherent domain */
 	li	t0, 0xff
-	sw	t0, GCR_CL_COHERENCE_OFS(v1)
+	PTR_S	t0, GCR_CL_COHERENCE_OFS(v1)
 	ehb
 
 	/* Jump to kseg0 */
-	la	t0, 1f
+	PTR_LA	t0, 1f
 	jr	t0
 	 nop
 
@@ -178,9 +178,9 @@
 	 nop
 
 	/* Off we go! */
-	lw	t1, VPEBOOTCFG_PC(v0)
-	lw	gp, VPEBOOTCFG_GP(v0)
-	lw	sp, VPEBOOTCFG_SP(v0)
+	PTR_L	t1, VPEBOOTCFG_PC(v0)
+	PTR_L	gp, VPEBOOTCFG_GP(v0)
+	PTR_L	sp, VPEBOOTCFG_SP(v0)
 	jr	t1
 	 nop
 	END(mips_cps_core_entry)
@@ -217,7 +217,7 @@
 
 .org 0x480
 LEAF(excep_ejtag)
-	la	k0, ejtag_debug_handler
+	PTR_LA	k0, ejtag_debug_handler
 	jr	k0
 	 nop
 	END(excep_ejtag)
@@ -229,7 +229,7 @@
 	 nop
 
 	.set	push
-	.set	mips32r2
+	.set	mips64r2
 	.set	mt
 
 	/* Only allow 1 TC per VPE to execute... */
@@ -237,7 +237,7 @@
 
 	/* ...and for the moment only 1 VPE */
 	dvpe
-	la	t1, 1f
+	PTR_LA	t1, 1f
 	jr.hb	t1
 	 nop
 
@@ -250,25 +250,25 @@
 	mfc0	t0, CP0_MVPCONF0
 	srl	t0, t0, MVPCONF0_PVPE_SHIFT
 	andi	t0, t0, (MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT)
-	addiu	t7, t0, 1
+	addiu	ta3, t0, 1
 
 	/* If there's only 1, we're done */
 	beqz	t0, 2f
 	 nop
 
 	/* Loop through each VPE within this core */
-	li	t5, 1
+	li	ta1, 1
 
 1:	/* Operate on the appropriate TC */
-	mtc0	t5, CP0_VPECONTROL
+	mtc0	ta1, CP0_VPECONTROL
 	ehb
 
 	/* Bind TC to VPE (1:1 TC:VPE mapping) */
-	mttc0	t5, CP0_TCBIND
+	mttc0	ta1, CP0_TCBIND
 
 	/* Set exclusive TC, non-active, master */
 	li	t0, VPECONF0_MVP
-	sll	t1, t5, VPECONF0_XTC_SHIFT
+	sll	t1, ta1, VPECONF0_XTC_SHIFT
 	or	t0, t0, t1
 	mttc0	t0, CP0_VPECONF0
 
@@ -280,8 +280,8 @@
 	mttc0	t0, CP0_TCHALT
 
 	/* Next VPE */
-	addiu	t5, t5, 1
-	slt	t0, t5, t7
+	addiu	ta1, ta1, 1
+	slt	t0, ta1, ta3
 	bnez	t0, 1b
 	 nop
 
@@ -298,19 +298,19 @@
 
 LEAF(mips_cps_boot_vpes)
 	/* Retrieve CM base address */
-	la	t0, mips_cm_base
-	lw	t0, 0(t0)
+	PTR_LA	t0, mips_cm_base
+	PTR_L	t0, 0(t0)
 
 	/* Calculate a pointer to this cores struct core_boot_config */
-	lw	t0, GCR_CL_ID_OFS(t0)
+	PTR_L	t0, GCR_CL_ID_OFS(t0)
 	li	t1, COREBOOTCFG_SIZE
 	mul	t0, t0, t1
-	la	t1, mips_cps_core_bootcfg
-	lw	t1, 0(t1)
-	addu	t0, t0, t1
+	PTR_LA	t1, mips_cps_core_bootcfg
+	PTR_L	t1, 0(t1)
+	PTR_ADDU t0, t0, t1
 
 	/* Calculate this VPEs ID. If the core doesn't support MT use 0 */
-	has_mt	t6, 1f
+	has_mt	ta2, 1f
 	 li	t9, 0
 
 	/* Find the number of VPEs present in the core */
@@ -334,24 +334,24 @@
 1:	/* Calculate a pointer to this VPEs struct vpe_boot_config */
 	li	t1, VPEBOOTCFG_SIZE
 	mul	v0, t9, t1
-	lw	t7, COREBOOTCFG_VPECONFIG(t0)
-	addu	v0, v0, t7
+	PTR_L	ta3, COREBOOTCFG_VPECONFIG(t0)
+	PTR_ADDU v0, v0, ta3
 
 #ifdef CONFIG_MIPS_MT
 
 	/* If the core doesn't support MT then return */
-	bnez	t6, 1f
+	bnez	ta2, 1f
 	 nop
 	jr	ra
 	 nop
 
 	.set	push
-	.set	mips32r2
+	.set	mips64r2
 	.set	mt
 
 1:	/* Enter VPE configuration state */
 	dvpe
-	la	t1, 1f
+	PTR_LA	t1, 1f
 	jr.hb	t1
 	 nop
 1:	mfc0	t1, CP0_MVPCONTROL
@@ -360,12 +360,12 @@
 	ehb
 
 	/* Loop through each VPE */
-	lw	t6, COREBOOTCFG_VPEMASK(t0)
-	move	t8, t6
-	li	t5, 0
+	PTR_L	ta2, COREBOOTCFG_VPEMASK(t0)
+	move	t8, ta2
+	li	ta1, 0
 
 	/* Check whether the VPE should be running. If not, skip it */
-1:	andi	t0, t6, 1
+1:	andi	t0, ta2, 1
 	beqz	t0, 2f
 	 nop
 
@@ -373,7 +373,7 @@
 	mfc0	t0, CP0_VPECONTROL
 	ori	t0, t0, VPECONTROL_TARGTC
 	xori	t0, t0, VPECONTROL_TARGTC
-	or	t0, t0, t5
+	or	t0, t0, ta1
 	mtc0	t0, CP0_VPECONTROL
 	ehb
 
@@ -384,8 +384,8 @@
 
 	/* Calculate a pointer to the VPEs struct vpe_boot_config */
 	li	t0, VPEBOOTCFG_SIZE
-	mul	t0, t0, t5
-	addu	t0, t0, t7
+	mul	t0, t0, ta1
+	addu	t0, t0, ta3
 
 	/* Set the TC restart PC */
 	lw	t1, VPEBOOTCFG_PC(t0)
@@ -423,9 +423,9 @@
 	mttc0	t0, CP0_VPECONF0
 
 	/* Next VPE */
-2:	srl	t6, t6, 1
-	addiu	t5, t5, 1
-	bnez	t6, 1b
+2:	srl	ta2, ta2, 1
+	addiu	ta1, ta1, 1
+	bnez	ta2, 1b
 	 nop
 
 	/* Leave VPE configuration state */
@@ -445,7 +445,7 @@
 	/* This VPE should be offline, halt the TC */
 	li	t0, TCHALT_H
 	mtc0	t0, CP0_TCHALT
-	la	t0, 1f
+	PTR_LA	t0, 1f
 1:	jr.hb	t0
 	 nop
 
@@ -466,10 +466,10 @@
 	.set	noat
 	lw	$1, TI_CPU(gp)
 	sll	$1, $1, LONGLOG
-	la	\dest, __per_cpu_offset
+	PTR_LA	\dest, __per_cpu_offset
 	addu	$1, $1, \dest
 	lw	$1, 0($1)
-	la	\dest, cps_cpu_state
+	PTR_LA	\dest, cps_cpu_state
 	addu	\dest, \dest, $1
 	.set	pop
 	.endm
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 6e8de80..4cc1350 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -73,10 +73,11 @@
 	.set    noreorder
 	.set	nomacro
 
-1:	user_lw(t5, 16(t0))		# argument #5 from usp
-4:	user_lw(t6, 20(t0))		# argument #6 from usp
-3:	user_lw(t7, 24(t0))		# argument #7 from usp
-2:	user_lw(t8, 28(t0))		# argument #8 from usp
+load_a4: user_lw(t5, 16(t0))		# argument #5 from usp
+load_a5: user_lw(t6, 20(t0))		# argument #6 from usp
+load_a6: user_lw(t7, 24(t0))		# argument #7 from usp
+load_a7: user_lw(t8, 28(t0))		# argument #8 from usp
+loads_done:
 
 	sw	t5, 16(sp)		# argument #5 to ksp
 	sw	t6, 20(sp)		# argument #6 to ksp
@@ -85,10 +86,10 @@
 	.set	pop
 
 	.section __ex_table,"a"
-	PTR	1b,bad_stack
-	PTR	2b,bad_stack
-	PTR	3b,bad_stack
-	PTR	4b,bad_stack
+	PTR	load_a4, bad_stack_a4
+	PTR	load_a5, bad_stack_a5
+	PTR	load_a6, bad_stack_a6
+	PTR	load_a7, bad_stack_a7
 	.previous
 
 	lw	t0, TI_FLAGS($28)	# syscall tracing enabled?
@@ -153,8 +154,8 @@
 /* ------------------------------------------------------------------------ */
 
 	/*
-	 * The stackpointer for a call with more than 4 arguments is bad.
-	 * We probably should handle this case a bit more drastic.
+	 * Our open-coded access area sanity test for the stack pointer
+	 * failed. We probably should handle this case a bit more drastic.
 	 */
 bad_stack:
 	li	v0, EFAULT
@@ -163,6 +164,22 @@
 	sw	t0, PT_R7(sp)
 	j	o32_syscall_exit
 
+bad_stack_a4:
+	li	t5, 0
+	b	load_a5
+
+bad_stack_a5:
+	li	t6, 0
+	b	load_a6
+
+bad_stack_a6:
+	li	t7, 0
+	b	load_a7
+
+bad_stack_a7:
+	li	t8, 0
+	b	loads_done
+
 	/*
 	 * The system call does not exist in this kernel
 	 */
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index d07b210..f543ff4 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -69,16 +69,17 @@
 	daddu	t1, t0, 32
 	bltz	t1, bad_stack
 
-1:	lw	a4, 16(t0)		# argument #5 from usp
-2:	lw	a5, 20(t0)		# argument #6 from usp
-3:	lw	a6, 24(t0)		# argument #7 from usp
-4:	lw	a7, 28(t0)		# argument #8 from usp (for indirect syscalls)
+load_a4: lw	a4, 16(t0)		# argument #5 from usp
+load_a5: lw	a5, 20(t0)		# argument #6 from usp
+load_a6: lw	a6, 24(t0)		# argument #7 from usp
+load_a7: lw	a7, 28(t0)		# argument #8 from usp
+loads_done:
 
 	.section __ex_table,"a"
-	PTR	1b, bad_stack
-	PTR	2b, bad_stack
-	PTR	3b, bad_stack
-	PTR	4b, bad_stack
+	PTR	load_a4, bad_stack_a4
+	PTR	load_a5, bad_stack_a5
+	PTR	load_a6, bad_stack_a6
+	PTR	load_a7, bad_stack_a7
 	.previous
 
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
@@ -167,6 +168,22 @@
 	sd	t0, PT_R7(sp)
 	j	o32_syscall_exit
 
+bad_stack_a4:
+	li	a4, 0
+	b	load_a5
+
+bad_stack_a5:
+	li	a5, 0
+	b	load_a6
+
+bad_stack_a6:
+	li	a6, 0
+	b	load_a7
+
+bad_stack_a7:
+	li	a7, 0
+	b	loads_done
+
 not_o32_scall:
 	/*
 	 * This is not an o32 compatibility syscall, pass it on
@@ -383,7 +400,7 @@
 	PTR	sys_connect			/* 4170 */
 	PTR	sys_getpeername
 	PTR	sys_getsockname
-	PTR	sys_getsockopt
+	PTR	compat_sys_getsockopt
 	PTR	sys_listen
 	PTR	compat_sys_recv			/* 4175 */
 	PTR	compat_sys_recvfrom
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index be73c49..008b337 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -337,6 +337,11 @@
 			min_low_pfn = start;
 		if (end <= reserved_end)
 			continue;
+#ifdef CONFIG_BLK_DEV_INITRD
+		/* mapstart should be after initrd_end */
+		if (initrd_end && end <= (unsigned long)PFN_UP(__pa(initrd_end)))
+			continue;
+#endif
 		if (start >= mapstart)
 			continue;
 		mapstart = max(reserved_end, start);
@@ -366,14 +371,6 @@
 		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 	}
 
-#ifdef CONFIG_BLK_DEV_INITRD
-	/*
-	 * mapstart should be after initrd_end
-	 */
-	if (initrd_end)
-		mapstart = max(mapstart, (unsigned long)PFN_UP(__pa(initrd_end)));
-#endif
-
 	/*
 	 * Initialize the boot-time allocator with low memory only.
 	 */
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 4251d39..c889377 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -133,7 +133,7 @@
 	/*
 	 * Patch the start of mips_cps_core_entry to provide:
 	 *
-	 * v0 = CM base address
+	 * v1 = CM base address
 	 * s0 = kseg0 CCA
 	 */
 	entry_code = (u32 *)&mips_cps_core_entry;
@@ -369,7 +369,7 @@
 
 static void wait_for_sibling_halt(void *ptr_cpu)
 {
-	unsigned cpu = (unsigned)ptr_cpu;
+	unsigned cpu = (unsigned long)ptr_cpu;
 	unsigned vpe_id = cpu_vpe_id(&cpu_data[cpu]);
 	unsigned halted;
 	unsigned long flags;
@@ -430,7 +430,7 @@
 		 */
 		err = smp_call_function_single(cpu_death_sibling,
 					       wait_for_sibling_halt,
-					       (void *)cpu, 1);
+					       (void *)(unsigned long)cpu, 1);
 		if (err)
 			panic("Failed to call remote sibling CPU\n");
 	}
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index faa46eb..d0744cc 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -63,6 +63,13 @@
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_core_map);
 
+/*
+ * A logcal cpu mask containing only one VPE per core to
+ * reduce the number of IPIs on large MT systems.
+ */
+cpumask_t cpu_foreign_map __read_mostly;
+EXPORT_SYMBOL(cpu_foreign_map);
+
 /* representing cpus for which sibling maps can be computed */
 static cpumask_t cpu_sibling_setup_map;
 
@@ -103,6 +110,29 @@
 	}
 }
 
+/*
+ * Calculate a new cpu_foreign_map mask whenever a
+ * new cpu appears or disappears.
+ */
+static inline void calculate_cpu_foreign_map(void)
+{
+	int i, k, core_present;
+	cpumask_t temp_foreign_map;
+
+	/* Re-calculate the mask */
+	for_each_online_cpu(i) {
+		core_present = 0;
+		for_each_cpu(k, &temp_foreign_map)
+			if (cpu_data[i].package == cpu_data[k].package &&
+			    cpu_data[i].core == cpu_data[k].core)
+				core_present = 1;
+		if (!core_present)
+			cpumask_set_cpu(i, &temp_foreign_map);
+	}
+
+	cpumask_copy(&cpu_foreign_map, &temp_foreign_map);
+}
+
 struct plat_smp_ops *mp_ops;
 EXPORT_SYMBOL(mp_ops);
 
@@ -146,6 +176,8 @@
 	set_cpu_sibling_map(cpu);
 	set_cpu_core_map(cpu);
 
+	calculate_cpu_foreign_map();
+
 	cpumask_set_cpu(cpu, &cpu_callin_map);
 
 	synchronise_count_slave(cpu);
@@ -173,9 +205,18 @@
 static void stop_this_cpu(void *dummy)
 {
 	/*
-	 * Remove this CPU:
+	 * Remove this CPU. Be a bit slow here and
+	 * set the bits for every online CPU so we don't miss
+	 * any IPI whilst taking this VPE down.
 	 */
+
+	cpumask_copy(&cpu_foreign_map, cpu_online_mask);
+
+	/* Make it visible to every other CPU */
+	smp_mb();
+
 	set_cpu_online(smp_processor_id(), false);
+	calculate_cpu_foreign_map();
 	local_irq_disable();
 	while (1);
 }
@@ -197,6 +238,7 @@
 	mp_ops->prepare_cpus(max_cpus);
 	set_cpu_sibling_map(0);
 	set_cpu_core_map(0);
+	calculate_cpu_foreign_map();
 #ifndef CONFIG_HOTPLUG_CPU
 	init_cpu_present(cpu_possible_mask);
 #endif
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 2a7b38e..e207a43 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -2130,10 +2130,10 @@
 	BUG_ON(current->mm);
 	enter_lazy_tlb(&init_mm, current);
 
-		/* Boot CPU's cache setup in setup_arch(). */
-		if (!is_boot_cpu)
-			cpu_cache_init();
-		tlb_init();
+	/* Boot CPU's cache setup in setup_arch(). */
+	if (!is_boot_cpu)
+		cpu_cache_init();
+	tlb_init();
 	TLBMISS_HANDLER_SETUP();
 }
 
diff --git a/arch/mips/loongson64/common/bonito-irq.c b/arch/mips/loongson64/common/bonito-irq.c
index cc0e4fd..4e116d2 100644
--- a/arch/mips/loongson64/common/bonito-irq.c
+++ b/arch/mips/loongson64/common/bonito-irq.c
@@ -3,7 +3,7 @@
  * Author: Jun Sun, jsun@mvista.com or jsun@junsun.net
  * Copyright (C) 2000, 2001 Ralf Baechle (ralf@gnu.org)
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/common/cmdline.c b/arch/mips/loongson64/common/cmdline.c
index 72fed00..01fbed1 100644
--- a/arch/mips/loongson64/common/cmdline.c
+++ b/arch/mips/loongson64/common/cmdline.c
@@ -6,7 +6,7 @@
  * Copyright 2003 ICT CAS
  * Author: Michael Guo <guoyi@ict.ac.cn>
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  * Copyright (C) 2009 Lemote Inc.
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c b/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
index 12c75db..8750370 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
+++ b/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
@@ -1,7 +1,7 @@
 /*
  * CS5536 General timer functions
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Yanhua, yanh@lemote.com
  *
  * Copyright (C) 2009 Lemote Inc.
diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c
index 22f04ca..f6c44dd 100644
--- a/arch/mips/loongson64/common/env.c
+++ b/arch/mips/loongson64/common/env.c
@@ -6,7 +6,7 @@
  * Copyright 2003 ICT CAS
  * Author: Michael Guo <guoyi@ict.ac.cn>
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  * Copyright (C) 2009 Lemote Inc.
diff --git a/arch/mips/loongson64/common/irq.c b/arch/mips/loongson64/common/irq.c
index 687003b..d36d969 100644
--- a/arch/mips/loongson64/common/irq.c
+++ b/arch/mips/loongson64/common/irq.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/common/setup.c b/arch/mips/loongson64/common/setup.c
index d477dd6..2dc5122 100644
--- a/arch/mips/loongson64/common/setup.c
+++ b/arch/mips/loongson64/common/setup.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/fuloong-2e/irq.c b/arch/mips/loongson64/fuloong-2e/irq.c
index ef5ec8f..892963f8 100644
--- a/arch/mips/loongson64/fuloong-2e/irq.c
+++ b/arch/mips/loongson64/fuloong-2e/irq.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/lemote-2f/clock.c b/arch/mips/loongson64/lemote-2f/clock.c
index 462e34d..a78fb65 100644
--- a/arch/mips/loongson64/lemote-2f/clock.c
+++ b/arch/mips/loongson64/lemote-2f/clock.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2006 - 2008 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2006 - 2008 Lemote Inc. & Institute of Computing Technology
  * Author: Yanhua, yanh@lemote.com
  *
  * This file is subject to the terms and conditions of the GNU General Public
@@ -15,7 +15,7 @@
 #include <linux/spinlock.h>
 
 #include <asm/clock.h>
-#include <asm/mach-loongson/loongson.h>
+#include <asm/mach-loongson64/loongson.h>
 
 static LIST_HEAD(clock_list);
 static DEFINE_SPINLOCK(clock_lock);
diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c
index 12d14ed..6f9e010 100644
--- a/arch/mips/loongson64/loongson-3/numa.c
+++ b/arch/mips/loongson64/loongson-3/numa.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010 Loongson Inc. & Lemote Inc. &
- *                    Insititute of Computing Technology
+ *                    Institute of Computing Technology
  * Author:  Xiang Gao, gaoxiang@ict.ac.cn
  *          Huacai Chen, chenhc@lemote.com
  *          Xiaofu Meng, Shuangshuang Zhang
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 22b9b2c..712f17a 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -451,7 +451,7 @@
 			/* Fall through */
 		case jr_op:
 			/* For R6, JR already emulated in jalr_op */
-			if (NO_R6EMU && insn.r_format.opcode == jr_op)
+			if (NO_R6EMU && insn.r_format.func == jr_op)
 				break;
 			*contpc = regs->regs[insn.r_format.rs];
 			return 1;
@@ -551,7 +551,7 @@
 				dec_insn.next_pc_inc;
 		return 1;
 	case blezl_op:
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			break;
 	case blez_op:
 
@@ -588,7 +588,7 @@
 				dec_insn.next_pc_inc;
 		return 1;
 	case bgtzl_op:
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			break;
 	case bgtz_op:
 		/*
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 7f660dc..fbea443 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -37,6 +37,7 @@
 #include <asm/cacheflush.h> /* for run_uncached() */
 #include <asm/traps.h>
 #include <asm/dma-coherence.h>
+#include <asm/mips-cm.h>
 
 /*
  * Special Variant of smp_call_function for use by cache functions:
@@ -51,9 +52,16 @@
 {
 	preempt_disable();
 
-#ifndef CONFIG_MIPS_MT_SMP
-	smp_call_function(func, info, 1);
-#endif
+	/*
+	 * The Coherent Manager propagates address-based cache ops to other
+	 * cores but not index-based ops. However, r4k_on_each_cpu is used
+	 * in both cases so there is no easy way to tell what kind of op is
+	 * executed to the other cores. The best we can probably do is
+	 * to restrict that call when a CM is not present because both
+	 * CM-based SMP protocols (CMP & CPS) restrict index-based cache ops.
+	 */
+	if (!mips_cm_present())
+		smp_call_function_many(&cpu_foreign_map, func, info, 1);
 	func(info);
 	preempt_enable();
 }
@@ -937,7 +945,9 @@
 }
 
 static char *way_string[] = { NULL, "direct mapped", "2-way",
-	"3-way", "4-way", "5-way", "6-way", "7-way", "8-way"
+	"3-way", "4-way", "5-way", "6-way", "7-way", "8-way",
+	"9-way", "10-way", "11-way", "12-way",
+	"13-way", "14-way", "15-way", "16-way",
 };
 
 static void probe_pcache(void)
diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c
index 185e682..5625b19 100644
--- a/arch/mips/mti-malta/malta-time.c
+++ b/arch/mips/mti-malta/malta-time.c
@@ -119,18 +119,24 @@
 
 int get_c0_fdc_int(void)
 {
-	int mips_cpu_fdc_irq;
+	/*
+	 * Some cores claim the FDC is routable through the GIC, but it doesn't
+	 * actually seem to be connected for those Malta bitstreams.
+	 */
+	switch (current_cpu_type()) {
+	case CPU_INTERAPTIV:
+	case CPU_PROAPTIV:
+		return -1;
+	};
 
 	if (cpu_has_veic)
-		mips_cpu_fdc_irq = -1;
+		return -1;
 	else if (gic_present)
-		mips_cpu_fdc_irq = gic_get_c0_fdc_int();
+		return gic_get_c0_fdc_int();
 	else if (cp0_fdc_irq >= 0)
-		mips_cpu_fdc_irq = MIPS_CPU_IRQ_BASE + cp0_fdc_irq;
+		return MIPS_CPU_IRQ_BASE + cp0_fdc_irq;
 	else
-		mips_cpu_fdc_irq = -1;
-
-	return mips_cpu_fdc_irq;
+		return -1;
 }
 
 int get_c0_perfcount_int(void)
diff --git a/arch/mips/pistachio/init.c b/arch/mips/pistachio/init.c
index d2dc836..8bd8ebb 100644
--- a/arch/mips/pistachio/init.c
+++ b/arch/mips/pistachio/init.c
@@ -63,13 +63,19 @@
 	plat_setup_iocoherency();
 }
 
-#define DEFAULT_CPC_BASE_ADDR 0x1bde0000
+#define DEFAULT_CPC_BASE_ADDR	0x1bde0000
+#define DEFAULT_CDMM_BASE_ADDR	0x1bdd0000
 
 phys_addr_t mips_cpc_default_phys_base(void)
 {
 	return DEFAULT_CPC_BASE_ADDR;
 }
 
+phys_addr_t mips_cdmm_phys_base(void)
+{
+	return DEFAULT_CDMM_BASE_ADDR;
+}
+
 static void __init mips_nmi_setup(void)
 {
 	void *base;
diff --git a/arch/mips/pistachio/time.c b/arch/mips/pistachio/time.c
index 67889fc..7c73fcb 100644
--- a/arch/mips/pistachio/time.c
+++ b/arch/mips/pistachio/time.c
@@ -27,6 +27,11 @@
 	return gic_get_c0_perfcount_int();
 }
 
+int get_c0_fdc_int(void)
+{
+	return gic_get_c0_fdc_int();
+}
+
 void __init plat_time_init(void)
 {
 	struct device_node *np;
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 0a18375..f93c4a4 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -16,7 +16,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 
-extern spinlock_t pa_dbit_lock;
+extern spinlock_t pa_tlb_lock;
 
 /*
  * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
@@ -33,6 +33,19 @@
  */
 #define kern_addr_valid(addr)	(1)
 
+/* 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(struct mm_struct *mm, unsigned long addr)
+{
+	mtsp(mm->context, 1);
+	pdtlb(addr);
+	if (unlikely(split_tlb))
+		pitlb(addr);
+}
+
 /* Certain architectures need to do special things when PTEs
  * within a page table are directly modified.  Thus, the following
  * hook is made available.
@@ -42,15 +55,20 @@
                 *(pteptr) = (pteval);                           \
         } while(0)
 
-extern void purge_tlb_entries(struct mm_struct *, unsigned long);
+#define pte_inserted(x)						\
+	((pte_val(x) & (_PAGE_PRESENT|_PAGE_ACCESSED))		\
+	 == (_PAGE_PRESENT|_PAGE_ACCESSED))
 
-#define set_pte_at(mm, addr, ptep, pteval)                      \
-	do {                                                    \
+#define set_pte_at(mm, addr, ptep, pteval)			\
+	do {							\
+		pte_t old_pte;					\
 		unsigned long flags;				\
-		spin_lock_irqsave(&pa_dbit_lock, flags);	\
-		set_pte(ptep, pteval);                          \
-		purge_tlb_entries(mm, addr);                    \
-		spin_unlock_irqrestore(&pa_dbit_lock, flags);	\
+		spin_lock_irqsave(&pa_tlb_lock, flags);		\
+		old_pte = *ptep;				\
+		set_pte(ptep, pteval);				\
+		if (pte_inserted(old_pte))			\
+			purge_tlb_entries(mm, addr);		\
+		spin_unlock_irqrestore(&pa_tlb_lock, flags);	\
 	} while (0)
 
 #endif /* !__ASSEMBLY__ */
@@ -268,7 +286,7 @@
 
 #define pte_none(x)     (pte_val(x) == 0)
 #define pte_present(x)	(pte_val(x) & _PAGE_PRESENT)
-#define pte_clear(mm,addr,xp)	do { pte_val(*(xp)) = 0; } while (0)
+#define pte_clear(mm, addr, xp)  set_pte_at(mm, addr, xp, __pte(0))
 
 #define pmd_flag(x)	(pmd_val(x) & PxD_FLAG_MASK)
 #define pmd_address(x)	((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
@@ -435,15 +453,15 @@
 	if (!pte_young(*ptep))
 		return 0;
 
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	pte = *ptep;
 	if (!pte_young(pte)) {
-		spin_unlock_irqrestore(&pa_dbit_lock, flags);
+		spin_unlock_irqrestore(&pa_tlb_lock, flags);
 		return 0;
 	}
 	set_pte(ptep, pte_mkold(pte));
 	purge_tlb_entries(vma->vm_mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 	return 1;
 }
 
@@ -453,11 +471,12 @@
 	pte_t old_pte;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	old_pte = *ptep;
-	pte_clear(mm,addr,ptep);
-	purge_tlb_entries(mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	set_pte(ptep, __pte(0));
+	if (pte_inserted(old_pte))
+		purge_tlb_entries(mm, addr);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 
 	return old_pte;
 }
@@ -465,10 +484,10 @@
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	set_pte(ptep, pte_wrprotect(*ptep));
 	purge_tlb_entries(mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 }
 
 #define pte_same(A,B)	(pte_val(A) == pte_val(B))
diff --git a/arch/parisc/include/asm/tlbflush.h b/arch/parisc/include/asm/tlbflush.h
index 9d086a5..e84b964 100644
--- a/arch/parisc/include/asm/tlbflush.h
+++ b/arch/parisc/include/asm/tlbflush.h
@@ -13,6 +13,9 @@
  * active at any one time on the Merced bus.  This tlb purge
  * synchronisation is fairly lightweight and harmless so we activate
  * it on all systems not just the N class.
+
+ * It is also used to ensure PTE updates are atomic and consistent
+ * with the TLB.
  */
 extern spinlock_t pa_tlb_lock;
 
@@ -24,20 +27,24 @@
 
 #define smp_flush_tlb_all()	flush_tlb_all()
 
+int __flush_tlb_range(unsigned long sid,
+	unsigned long start, unsigned long end);
+
+#define flush_tlb_range(vma, start, end) \
+	__flush_tlb_range((vma)->vm_mm->context, start, end)
+
+#define flush_tlb_kernel_range(start, end) \
+	__flush_tlb_range(0, start, end)
+
 /*
  * flush_tlb_mm()
  *
- * XXX This code is NOT valid for HP-UX compatibility processes,
- * (although it will probably work 99% of the time). HP-UX
- * processes are free to play with the space id's and save them
- * over long periods of time, etc. so we have to preserve the
- * space and just flush the entire tlb. We need to check the
- * personality in order to do that, but the personality is not
- * currently being set correctly.
- *
- * Of course, Linux processes could do the same thing, but
- * we don't support that (and the compilers, dynamic linker,
- * etc. do not do that).
+ * The code to switch to a new context is NOT valid for processes
+ * which play with the space id's.  Thus, we have to preserve the
+ * space and just flush the entire tlb.  However, the compilers,
+ * dynamic linker, etc, do not manipulate space id's, so there
+ * could be a significant performance benefit in switching contexts
+ * and not flushing the whole tlb.
  */
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
@@ -45,10 +52,18 @@
 	BUG_ON(mm == &init_mm); /* Should never happen */
 
 #if 1 || defined(CONFIG_SMP)
+	/* Except for very small threads, flushing the whole TLB is
+	 * faster than using __flush_tlb_range.  The pdtlb and pitlb
+	 * instructions are very slow because of the TLB broadcast.
+	 * It might be faster to do local range flushes on all CPUs
+	 * on PA 2.0 systems.
+	 */
 	flush_tlb_all();
 #else
 	/* FIXME: currently broken, causing space id and protection ids
-	 *  to go out of sync, resulting in faults on userspace accesses.
+	 * to go out of sync, resulting in faults on userspace accesses.
+	 * This approach needs further investigation since running many
+	 * small applications (e.g., GCC testsuite) is faster on HP-UX.
 	 */
 	if (mm) {
 		if (mm->context != 0)
@@ -65,22 +80,12 @@
 {
 	unsigned long flags, sid;
 
-	/* For one page, it's not worth testing the split_tlb variable */
-
-	mb();
 	sid = vma->vm_mm->context;
 	purge_tlb_start(flags);
 	mtsp(sid, 1);
 	pdtlb(addr);
-	pitlb(addr);
+	if (unlikely(split_tlb))
+		pitlb(addr);
 	purge_tlb_end(flags);
 }
-
-void __flush_tlb_range(unsigned long sid,
-	unsigned long start, unsigned long end);
-
-#define flush_tlb_range(vma,start,end) __flush_tlb_range((vma)->vm_mm->context,start,end)
-
-#define flush_tlb_kernel_range(start, end) __flush_tlb_range(0,start,end)
-
 #endif
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index f6448c7..cda6dbb 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -342,12 +342,15 @@
 EXPORT_SYMBOL(flush_kernel_icache_range_asm);
 
 #define FLUSH_THRESHOLD 0x80000 /* 0.5MB */
-int parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
+static unsigned long parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
+
+#define FLUSH_TLB_THRESHOLD (2*1024*1024) /* 2MB initial TLB threshold */
+static unsigned long parisc_tlb_flush_threshold __read_mostly = FLUSH_TLB_THRESHOLD;
 
 void __init parisc_setup_cache_timing(void)
 {
 	unsigned long rangetime, alltime;
-	unsigned long size;
+	unsigned long size, start;
 
 	alltime = mfctl(16);
 	flush_data_cache();
@@ -364,14 +367,43 @@
 	/* Racy, but if we see an intermediate value, it's ok too... */
 	parisc_cache_flush_threshold = size * alltime / rangetime;
 
-	parisc_cache_flush_threshold = (parisc_cache_flush_threshold + L1_CACHE_BYTES - 1) &~ (L1_CACHE_BYTES - 1); 
+	parisc_cache_flush_threshold = L1_CACHE_ALIGN(parisc_cache_flush_threshold);
 	if (!parisc_cache_flush_threshold)
 		parisc_cache_flush_threshold = FLUSH_THRESHOLD;
 
 	if (parisc_cache_flush_threshold > cache_info.dc_size)
 		parisc_cache_flush_threshold = cache_info.dc_size;
 
-	printk(KERN_INFO "Setting cache flush threshold to %x (%d CPUs online)\n", parisc_cache_flush_threshold, num_online_cpus());
+	printk(KERN_INFO "Setting cache flush threshold to %lu kB\n",
+		parisc_cache_flush_threshold/1024);
+
+	/* calculate TLB flush threshold */
+
+	alltime = mfctl(16);
+	flush_tlb_all();
+	alltime = mfctl(16) - alltime;
+
+	size = PAGE_SIZE;
+	start = (unsigned long) _text;
+	rangetime = mfctl(16);
+	while (start < (unsigned long) _end) {
+		flush_tlb_kernel_range(start, start + PAGE_SIZE);
+		start += PAGE_SIZE;
+		size += PAGE_SIZE;
+	}
+	rangetime = mfctl(16) - rangetime;
+
+	printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n",
+		alltime, size, rangetime);
+
+	parisc_tlb_flush_threshold = size * alltime / rangetime;
+	parisc_tlb_flush_threshold *= num_online_cpus();
+	parisc_tlb_flush_threshold = PAGE_ALIGN(parisc_tlb_flush_threshold);
+	if (!parisc_tlb_flush_threshold)
+		parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD;
+
+	printk(KERN_INFO "Setting TLB flush threshold to %lu kB\n",
+		parisc_tlb_flush_threshold/1024);
 }
 
 extern void purge_kernel_dcache_page_asm(unsigned long);
@@ -403,48 +435,45 @@
 }
 EXPORT_SYMBOL(copy_user_page);
 
-void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
+/* __flush_tlb_range()
+ *
+ * returns 1 if all TLBs were flushed.
+ */
+int __flush_tlb_range(unsigned long sid, unsigned long start,
+		      unsigned long end)
 {
-	unsigned long flags;
+	unsigned long flags, size;
 
-	/* Note: purge_tlb_entries can be called at startup with
-	   no context.  */
-
-	purge_tlb_start(flags);
-	mtsp(mm->context, 1);
-	pdtlb(addr);
-	pitlb(addr);
-	purge_tlb_end(flags);
-}
-EXPORT_SYMBOL(purge_tlb_entries);
-
-void __flush_tlb_range(unsigned long sid, unsigned long start,
-		       unsigned long end)
-{
-	unsigned long npages;
-
-	npages = ((end - (start & PAGE_MASK)) + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
-	if (npages >= 512)  /* 2MB of space: arbitrary, should be tuned */
+	size = (end - start);
+	if (size >= parisc_tlb_flush_threshold) {
 		flush_tlb_all();
-	else {
-		unsigned long flags;
+		return 1;
+	}
 
+	/* Purge TLB entries for small ranges using the pdtlb and
+	   pitlb instructions.  These instructions execute locally
+	   but cause a purge request to be broadcast to other TLBs.  */
+	if (likely(!split_tlb)) {
+		while (start < end) {
+			purge_tlb_start(flags);
+			mtsp(sid, 1);
+			pdtlb(start);
+			purge_tlb_end(flags);
+			start += PAGE_SIZE;
+		}
+		return 0;
+	}
+
+	/* split TLB case */
+	while (start < end) {
 		purge_tlb_start(flags);
 		mtsp(sid, 1);
-		if (split_tlb) {
-			while (npages--) {
-				pdtlb(start);
-				pitlb(start);
-				start += PAGE_SIZE;
-			}
-		} else {
-			while (npages--) {
-				pdtlb(start);
-				start += PAGE_SIZE;
-			}
-		}
+		pdtlb(start);
+		pitlb(start);
 		purge_tlb_end(flags);
+		start += PAGE_SIZE;
 	}
+	return 0;
 }
 
 static void cacheflush_h_tmp_function(void *dummy)
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 7581961..c5ef408 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -45,7 +45,7 @@
 	.level 2.0
 #endif
 
-	.import         pa_dbit_lock,data
+	.import		pa_tlb_lock,data
 
 	/* space_to_prot macro creates a prot id from a space id */
 
@@ -420,8 +420,8 @@
 	SHLREG		%r9,PxD_VALUE_SHIFT,\pmd
 	extru		\va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index
 	dep		%r0,31,PAGE_SHIFT,\pmd  /* clear offset */
-	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd
-	LDREG		%r0(\pmd),\pte		/* pmd is now pte */
+	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */
+	LDREG		%r0(\pmd),\pte
 	bb,>=,n		\pte,_PAGE_PRESENT_BIT,\fault
 	.endm
 
@@ -453,57 +453,53 @@
 	L2_ptep		\pgd,\pte,\index,\va,\fault
 	.endm
 
-	/* Acquire pa_dbit_lock lock. */
-	.macro		dbit_lock	spc,tmp,tmp1
+	/* Acquire pa_tlb_lock lock and recheck page is still present. */
+	.macro		tlb_lock	spc,ptp,pte,tmp,tmp1,fault
 #ifdef CONFIG_SMP
 	cmpib,COND(=),n	0,\spc,2f
-	load32		PA(pa_dbit_lock),\tmp
+	load32		PA(pa_tlb_lock),\tmp
 1:	LDCW		0(\tmp),\tmp1
 	cmpib,COND(=)	0,\tmp1,1b
 	nop
+	LDREG		0(\ptp),\pte
+	bb,<,n		\pte,_PAGE_PRESENT_BIT,2f
+	b		\fault
+	stw		 \spc,0(\tmp)
 2:
 #endif
 	.endm
 
-	/* Release pa_dbit_lock lock without reloading lock address. */
-	.macro		dbit_unlock0	spc,tmp
+	/* Release pa_tlb_lock lock without reloading lock address. */
+	.macro		tlb_unlock0	spc,tmp
 #ifdef CONFIG_SMP
 	or,COND(=)	%r0,\spc,%r0
 	stw             \spc,0(\tmp)
 #endif
 	.endm
 
-	/* Release pa_dbit_lock lock. */
-	.macro		dbit_unlock1	spc,tmp
+	/* Release pa_tlb_lock lock. */
+	.macro		tlb_unlock1	spc,tmp
 #ifdef CONFIG_SMP
-	load32		PA(pa_dbit_lock),\tmp
-	dbit_unlock0	\spc,\tmp
+	load32		PA(pa_tlb_lock),\tmp
+	tlb_unlock0	\spc,\tmp
 #endif
 	.endm
 
 	/* Set the _PAGE_ACCESSED bit of the PTE.  Be clever and
 	 * don't needlessly dirty the cache line if it was already set */
-	.macro		update_ptep	spc,ptep,pte,tmp,tmp1
-#ifdef CONFIG_SMP
-	or,COND(=)	%r0,\spc,%r0
-	LDREG		0(\ptep),\pte
-#endif
+	.macro		update_accessed	ptp,pte,tmp,tmp1
 	ldi		_PAGE_ACCESSED,\tmp1
 	or		\tmp1,\pte,\tmp
 	and,COND(<>)	\tmp1,\pte,%r0
-	STREG		\tmp,0(\ptep)
+	STREG		\tmp,0(\ptp)
 	.endm
 
 	/* Set the dirty bit (and accessed bit).  No need to be
 	 * clever, this is only used from the dirty fault */
-	.macro		update_dirty	spc,ptep,pte,tmp
-#ifdef CONFIG_SMP
-	or,COND(=)	%r0,\spc,%r0
-	LDREG		0(\ptep),\pte
-#endif
+	.macro		update_dirty	ptp,pte,tmp
 	ldi		_PAGE_ACCESSED|_PAGE_DIRTY,\tmp
 	or		\tmp,\pte,\pte
-	STREG		\pte,0(\ptep)
+	STREG		\pte,0(\ptp)
 	.endm
 
 	/* bitshift difference between a PFN (based on kernel's PAGE_SIZE)
@@ -1148,14 +1144,14 @@
 
 	L3_ptep		ptp,pte,t0,va,dtlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1174,14 +1170,14 @@
 
 	L3_ptep		ptp,pte,t0,va,nadtlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1202,20 +1198,20 @@
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	idtlba		pte,(%sr1,va)
 	idtlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1235,21 +1231,20 @@
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	idtlba		pte,(%sr1,va)
 	idtlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1269,16 +1264,16 @@
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1297,16 +1292,16 @@
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 	
-        idtlbt          pte,prot
-	dbit_unlock1	spc,t0
+	idtlbt		pte,prot
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1406,14 +1401,14 @@
 
 	L3_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1430,14 +1425,14 @@
 
 	L3_ptep		ptp,pte,t0,va,naitlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1458,20 +1453,20 @@
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	iitlba		pte,(%sr1,va)
 	iitlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1482,20 +1477,20 @@
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	iitlba		pte,(%sr1,va)
 	iitlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1516,16 +1511,16 @@
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0	
+	f_extend	pte,t1
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1536,16 +1531,16 @@
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1568,14 +1563,14 @@
 
 	L3_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 		
 	idtlbt          pte,prot
-	dbit_unlock0	spc,t0
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 #else
@@ -1588,8 +1583,8 @@
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1600,8 +1595,8 @@
 	idtlbp		prot,(%sr1,va)
 
 	mtsp            t1, %sr1     /* Restore sr1 */
-	dbit_unlock0	spc,t0
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 
@@ -1612,16 +1607,16 @@
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t1
 	
-        idtlbt          pte,prot
-	dbit_unlock0	spc,t0
+	idtlbt		pte,prot
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 #endif
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 6548fd1..b99b39f 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -43,10 +43,6 @@
 
 #include "../math-emu/math-emu.h"	/* for handle_fpe() */
 
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
-DEFINE_SPINLOCK(pa_dbit_lock);
-#endif
-
 static void parisc_show_stack(struct task_struct *task, unsigned long *sp,
 	struct pt_regs *regs);
 
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index ccde8f0..112ccf4 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -52,6 +52,22 @@
 	.text
 
 /*
+ * Used by threads when the lock bit of core_idle_state is set.
+ * Threads will spin in HMT_LOW until the lock bit is cleared.
+ * r14 - pointer to core_idle_state
+ * r15 - used to load contents of core_idle_state
+ */
+
+core_idle_lock_held:
+	HMT_LOW
+3:	lwz	r15,0(r14)
+	andi.   r15,r15,PNV_CORE_IDLE_LOCK_BIT
+	bne	3b
+	HMT_MEDIUM
+	lwarx	r15,0,r14
+	blr
+
+/*
  * Pass requested state in r3:
  *	r3 - PNV_THREAD_NAP/SLEEP/WINKLE
  *
@@ -150,6 +166,10 @@
 	ld	r14,PACA_CORE_IDLE_STATE_PTR(r13)
 lwarx_loop1:
 	lwarx	r15,0,r14
+
+	andi.   r9,r15,PNV_CORE_IDLE_LOCK_BIT
+	bnel	core_idle_lock_held
+
 	andc	r15,r15,r7			/* Clear thread bit */
 
 	andi.	r15,r15,PNV_CORE_IDLE_THREAD_BITS
@@ -294,7 +314,7 @@
 	 * workaround undo code or resyncing timebase or restoring context
 	 * In either case loop until the lock bit is cleared.
 	 */
-	bne	core_idle_lock_held
+	bnel	core_idle_lock_held
 
 	cmpwi	cr2,r15,0
 	lbz	r4,PACA_SUBCORE_SIBLING_MASK(r13)
@@ -319,15 +339,6 @@
 	isync
 	b	common_exit
 
-core_idle_lock_held:
-	HMT_LOW
-core_idle_lock_loop:
-	lwz	r15,0(14)
-	andi.   r9,r15,PNV_CORE_IDLE_LOCK_BIT
-	bne	core_idle_lock_loop
-	HMT_MEDIUM
-	b	lwarx_loop2
-
 first_thread_in_subcore:
 	/* First thread in subcore to wakeup */
 	ori	r15,r15,PNV_CORE_IDLE_LOCK_BIT
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 6530f1b..37de90f 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -297,6 +297,8 @@
 
 	__this_cpu_inc(irq_stat.mce_exceptions);
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
 	if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
 		handled = cur_cpu_spec->machine_check_early(regs);
 	return handled;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 6d53597..a67c6d7 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -529,6 +529,10 @@
 		printk(KERN_ALERT "Unable to handle kernel paging request for "
 			"instruction fetch\n");
 		break;
+	case 0x600:
+		printk(KERN_ALERT "Unable to handle kernel paging request for "
+			"unaligned access at address 0x%08lx\n", regs->dar);
+		break;
 	default:
 		printk(KERN_ALERT "Unable to handle kernel paging request for "
 			"unknown fault\n");
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index ec2eb20..df95629 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -320,6 +320,8 @@
 	if (!attr)
 		return NULL;
 
+	sysfs_attr_init(&attr->attr.attr);
+
 	attr->var = str;
 	attr->attr.attr.name = name;
 	attr->attr.attr.mode = 0444;
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 4949ef0..37f959b 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -237,7 +237,7 @@
 	return elog;
 }
 
-static void elog_work_fn(struct work_struct *work)
+static irqreturn_t elog_event(int irq, void *data)
 {
 	__be64 size;
 	__be64 id;
@@ -251,7 +251,7 @@
 	rc = opal_get_elog_size(&id, &size, &type);
 	if (rc != OPAL_SUCCESS) {
 		pr_err("ELOG: OPAL log info read failed\n");
-		return;
+		return IRQ_HANDLED;
 	}
 
 	elog_size = be64_to_cpu(size);
@@ -270,16 +270,10 @@
 	 * entries.
 	 */
 	if (kset_find_obj(elog_kset, name))
-		return;
+		return IRQ_HANDLED;
 
 	create_elog_obj(log_id, elog_size, elog_type);
-}
 
-static DECLARE_WORK(elog_work, elog_work_fn);
-
-static irqreturn_t elog_event(int irq, void *data)
-{
-	schedule_work(&elog_work);
 	return IRQ_HANDLED;
 }
 
@@ -304,8 +298,8 @@
 		return irq;
 	}
 
-	rc = request_irq(irq, elog_event,
-			IRQ_TYPE_LEVEL_HIGH, "opal-elog", NULL);
+	rc = request_threaded_irq(irq, NULL, elog_event,
+			IRQF_TRIGGER_HIGH | IRQF_ONESHOT, "opal-elog", NULL);
 	if (rc) {
 		pr_err("%s: Can't request OPAL event irq (%d)\n",
 		       __func__, rc);
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
index 46cb3fe..4ece8e4 100644
--- a/arch/powerpc/platforms/powernv/opal-prd.c
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -112,6 +112,7 @@
 static int opal_prd_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	size_t addr, size;
+	pgprot_t page_prot;
 	int rc;
 
 	pr_devel("opal_prd_mmap(0x%016lx, 0x%016lx, 0x%lx, 0x%lx)\n",
@@ -125,13 +126,11 @@
 	if (!opal_prd_range_is_valid(addr, size))
 		return -EINVAL;
 
-	vma->vm_page_prot = __pgprot(pgprot_val(phys_mem_access_prot(file,
-						vma->vm_pgoff,
-						 size, vma->vm_page_prot))
-					| _PAGE_SPECIAL);
+	page_prot = phys_mem_access_prot(file, vma->vm_pgoff,
+					 size, vma->vm_page_prot);
 
 	rc = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, size,
-			vma->vm_page_prot);
+				page_prot);
 
 	return rc;
 }
diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
index 2bc3367..87f9623 100644
--- a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
@@ -18,6 +18,7 @@
 #include <linux/pci.h>
 #include <linux/semaphore.h>
 #include <asm/msi_bitmap.h>
+#include <asm/ppc-pci.h>
 
 struct ppc4xx_hsta_msi {
 	struct device *dev;
diff --git a/arch/tile/lib/memcpy_user_64.c b/arch/tile/lib/memcpy_user_64.c
index 88c7016..97bbb60 100644
--- a/arch/tile/lib/memcpy_user_64.c
+++ b/arch/tile/lib/memcpy_user_64.c
@@ -28,7 +28,7 @@
 #define _ST(p, inst, v)						\
 	({							\
 		asm("1: " #inst " %0, %1;"			\
-		    ".pushsection .coldtext.memcpy,\"ax\";"	\
+		    ".pushsection .coldtext,\"ax\";"	\
 		    "2: { move r0, %2; jrp lr };"		\
 		    ".section __ex_table,\"a\";"		\
 		    ".align 8;"					\
@@ -41,7 +41,7 @@
 	({							\
 		unsigned long __v;				\
 		asm("1: " #inst " %0, %1;"			\
-		    ".pushsection .coldtext.memcpy,\"ax\";"	\
+		    ".pushsection .coldtext,\"ax\";"	\
 		    "2: { move r0, %2; jrp lr };"		\
 		    ".section __ex_table,\"a\";"		\
 		    ".align 8;"					\
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 55bced1..3dbb7e7 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -254,6 +254,11 @@
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
+config KASAN_SHADOW_OFFSET
+	hex
+	depends on KASAN
+	default 0xdffffc0000000000
+
 config HAVE_INTEL_TXT
 	def_bool y
 	depends on INTEL_IOMMU && ACPI
@@ -2015,7 +2020,7 @@
 
 	  To compile command line arguments into the kernel,
 	  set this option to 'Y', then fill in the
-	  the boot arguments in CONFIG_CMDLINE.
+	  boot arguments in CONFIG_CMDLINE.
 
 	  Systems with fully functional boot loaders (i.e. non-embedded)
 	  should leave this option set to 'N'.
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
index 99efebb..ca3ce9a 100644
--- a/arch/x86/include/asm/espfix.h
+++ b/arch/x86/include/asm/espfix.h
@@ -9,7 +9,7 @@
 DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
 
 extern void init_espfix_bsp(void);
-extern void init_espfix_ap(void);
+extern void init_espfix_ap(int cpu);
 
 #endif /* CONFIG_X86_64 */
 
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index 8b22422..74a2a8d 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -14,15 +14,11 @@
 
 #ifndef __ASSEMBLY__
 
-extern pte_t kasan_zero_pte[];
-extern pte_t kasan_zero_pmd[];
-extern pte_t kasan_zero_pud[];
-
 #ifdef CONFIG_KASAN
-void __init kasan_map_early_shadow(pgd_t *pgd);
+void __init kasan_early_init(void);
 void __init kasan_init(void);
 #else
-static inline void kasan_map_early_shadow(pgd_t *pgd) { }
+static inline void kasan_early_init(void) { }
 static inline void kasan_init(void) { }
 #endif
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 28eba2d..f813261 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -409,12 +409,6 @@
 	int irq, vector;
 	struct apic_chip_data *data;
 
-	/*
-	 * vector_lock will make sure that we don't run into irq vector
-	 * assignments that might be happening on another cpu in parallel,
-	 * while we setup our initial vector to irq mappings.
-	 */
-	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
 	for_each_active_irq(irq) {
 		data = apic_chip_data(irq_get_irq_data(irq));
@@ -436,16 +430,16 @@
 		if (!cpumask_test_cpu(cpu, data->domain))
 			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
 	}
-	raw_spin_unlock(&vector_lock);
 }
 
 /*
- * Setup the vector to irq mappings.
+ * Setup the vector to irq mappings. Must be called with vector_lock held.
  */
 void setup_vector_irq(int cpu)
 {
 	int irq;
 
+	lockdep_assert_held(&vector_lock);
 	/*
 	 * On most of the platforms, legacy PIC delivers the interrupts on the
 	 * boot cpu. But there are certain platforms where PIC interrupts are
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 89427d8..eec40f5 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -175,7 +175,9 @@
 	}
 
 	if (*s) {
-		if (kstrtoul(s, 0, &baud) < 0 || baud == 0)
+		baud = simple_strtoull(s, &e, 0);
+
+		if (baud == 0 || s == e)
 			baud = DEFAULT_BAUD;
 	}
 
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index f5d0730..ce95676 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -131,25 +131,24 @@
 	init_espfix_random();
 
 	/* The rest is the same as for any other processor */
-	init_espfix_ap();
+	init_espfix_ap(0);
 }
 
-void init_espfix_ap(void)
+void init_espfix_ap(int cpu)
 {
-	unsigned int cpu, page;
+	unsigned int page;
 	unsigned long addr;
 	pud_t pud, *pud_p;
 	pmd_t pmd, *pmd_p;
 	pte_t pte, *pte_p;
-	int n;
+	int n, node;
 	void *stack_page;
 	pteval_t ptemask;
 
 	/* We only have to do this once... */
-	if (likely(this_cpu_read(espfix_stack)))
+	if (likely(per_cpu(espfix_stack, cpu)))
 		return;		/* Already initialized */
 
-	cpu = smp_processor_id();
 	addr = espfix_base_addr(cpu);
 	page = cpu/ESPFIX_STACKS_PER_PAGE;
 
@@ -165,12 +164,15 @@
 	if (stack_page)
 		goto unlock_done;
 
+	node = cpu_to_node(cpu);
 	ptemask = __supported_pte_mask;
 
 	pud_p = &espfix_pud_page[pud_index(addr)];
 	pud = *pud_p;
 	if (!pud_present(pud)) {
-		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+		struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0);
+
+		pmd_p = (pmd_t *)page_address(page);
 		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
 		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
@@ -180,7 +182,9 @@
 	pmd_p = pmd_offset(&pud, addr);
 	pmd = *pmd_p;
 	if (!pmd_present(pmd)) {
-		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+		struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0);
+
+		pte_p = (pte_t *)page_address(page);
 		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
 		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
@@ -188,7 +192,7 @@
 	}
 
 	pte_p = pte_offset_kernel(&pmd, addr);
-	stack_page = (void *)__get_free_page(GFP_KERNEL);
+	stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0));
 	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);
@@ -199,7 +203,7 @@
 unlock_done:
 	mutex_unlock(&espfix_init_mutex);
 done:
-	this_cpu_write(espfix_stack, addr);
-	this_cpu_write(espfix_waddr, (unsigned long)stack_page
-		       + (addr & ~PAGE_MASK));
+	per_cpu(espfix_stack, cpu) = addr;
+	per_cpu(espfix_waddr, cpu) = (unsigned long)stack_page
+				      + (addr & ~PAGE_MASK);
 }
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 5a46681..f129a9a 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -161,11 +161,12 @@
 	/* Kill off the identity-map trampoline */
 	reset_early_page_tables();
 
-	kasan_map_early_shadow(early_level4_pgt);
-
-	/* clear bss before set_intr_gate with early_idt_handler */
 	clear_bss();
 
+	clear_page(init_level4_pgt);
+
+	kasan_early_init();
+
 	for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
 		set_intr_gate(i, early_idt_handler_array[i]);
 	load_idt((const struct desc_ptr *)&idt_descr);
@@ -177,12 +178,9 @@
 	 */
 	load_ucode_bsp();
 
-	clear_page(init_level4_pgt);
 	/* set init_level4_pgt kernel high mapping*/
 	init_level4_pgt[511] = early_level4_pgt[511];
 
-	kasan_map_early_shadow(init_level4_pgt);
-
 	x86_64_start_reservations(real_mode_data);
 }
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e5c27f7..1d40ca8 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -516,38 +516,9 @@
 	/* This must match the first entry in level2_kernel_pgt */
 	.quad   0x0000000000000000
 
-#ifdef CONFIG_KASAN
-#define FILL(VAL, COUNT)				\
-	.rept (COUNT) ;					\
-	.quad	(VAL) ;					\
-	.endr
-
-NEXT_PAGE(kasan_zero_pte)
-	FILL(kasan_zero_page - __START_KERNEL_map + _KERNPG_TABLE, 512)
-NEXT_PAGE(kasan_zero_pmd)
-	FILL(kasan_zero_pte - __START_KERNEL_map + _KERNPG_TABLE, 512)
-NEXT_PAGE(kasan_zero_pud)
-	FILL(kasan_zero_pmd - __START_KERNEL_map + _KERNPG_TABLE, 512)
-
-#undef FILL
-#endif
-
-
 #include "../../x86/xen/xen-head.S"
 	
 	__PAGE_ALIGNED_BSS
 NEXT_PAGE(empty_zero_page)
 	.skip PAGE_SIZE
 
-#ifdef CONFIG_KASAN
-/*
- * This page used as early shadow. We don't use empty_zero_page
- * at early stages, stack instrumentation could write some garbage
- * to this page.
- * Latter we reuse it as zero shadow for large ranges of memory
- * that allowed to access, but not instrumented by kasan
- * (vmalloc/vmemmap ...).
- */
-NEXT_PAGE(kasan_zero_page)
-	.skip PAGE_SIZE
-#endif
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 88b36648..c7dfe1b 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -347,14 +347,22 @@
 			if (!desc)
 				continue;
 
+			/*
+			 * Protect against concurrent action removal,
+			 * affinity changes etc.
+			 */
+			raw_spin_lock(&desc->lock);
 			data = irq_desc_get_irq_data(desc);
 			cpumask_copy(&affinity_new, data->affinity);
 			cpumask_clear_cpu(this_cpu, &affinity_new);
 
 			/* Do not count inactive or per-cpu irqs. */
-			if (!irq_has_action(irq) || irqd_is_per_cpu(data))
+			if (!irq_has_action(irq) || irqd_is_per_cpu(data)) {
+				raw_spin_unlock(&desc->lock);
 				continue;
+			}
 
+			raw_spin_unlock(&desc->lock);
 			/*
 			 * A single irq may be mapped to multiple
 			 * cpu's vector_irq[] (for example IOAPIC cluster
@@ -385,6 +393,9 @@
 		 * vector. If the vector is marked in the used vectors
 		 * bitmap or an irq is assigned to it, we don't count
 		 * it as available.
+		 *
+		 * As this is an inaccurate snapshot anyway, we can do
+		 * this w/o holding vector_lock.
 		 */
 		for (vector = FIRST_EXTERNAL_VECTOR;
 		     vector < first_system_vector; vector++) {
@@ -486,6 +497,11 @@
 	 */
 	mdelay(1);
 
+	/*
+	 * We can walk the vector array of this cpu without holding
+	 * vector_lock because the cpu is already marked !online, so
+	 * nothing else will touch it.
+	 */
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
 		unsigned int irr;
 
@@ -497,9 +513,9 @@
 			irq = __this_cpu_read(vector_irq[vector]);
 
 			desc = irq_to_desc(irq);
+			raw_spin_lock(&desc->lock);
 			data = irq_desc_get_irq_data(desc);
 			chip = irq_data_get_irq_chip(data);
-			raw_spin_lock(&desc->lock);
 			if (chip->irq_retrigger) {
 				chip->irq_retrigger(data);
 				__this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8add66b..d3010aa 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -171,11 +171,6 @@
 	apic_ap_setup();
 
 	/*
-	 * Need to setup vector mappings before we enable interrupts.
-	 */
-	setup_vector_irq(smp_processor_id());
-
-	/*
 	 * Save our processor parameters. Note: this information
 	 * is needed for clock calibration.
 	 */
@@ -239,18 +234,13 @@
 	check_tsc_sync_target();
 
 	/*
-	 * Enable the espfix hack for this CPU
-	 */
-#ifdef CONFIG_X86_ESPFIX64
-	init_espfix_ap();
-#endif
-
-	/*
-	 * We need to hold vector_lock so there the set of online cpus
-	 * does not change while we are assigning vectors to cpus.  Holding
-	 * this lock ensures we don't half assign or remove an irq from a cpu.
+	 * Lock vector_lock and initialize the vectors on this cpu
+	 * before setting the cpu online. We must set it online with
+	 * vector_lock held to prevent a concurrent setup/teardown
+	 * from seeing a half valid vector space.
 	 */
 	lock_vector_lock();
+	setup_vector_irq(smp_processor_id());
 	set_cpu_online(smp_processor_id(), true);
 	unlock_vector_lock();
 	cpu_set_state_online(smp_processor_id());
@@ -854,6 +844,13 @@
 	initial_code = (unsigned long)start_secondary;
 	stack_start  = idle->thread.sp;
 
+	/*
+	 * Enable the espfix hack for this CPU
+	*/
+#ifdef CONFIG_X86_ESPFIX64
+	init_espfix_ap(cpu);
+#endif
+
 	/* So we see what's up */
 	announce_cpu(cpu, apicid);
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 5054497..7437b41 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -598,10 +598,19 @@
 			if (!pit_expect_msb(0xff-i, &delta, &d2))
 				break;
 
+			delta -= tsc;
+
+			/*
+			 * Extrapolate the error and fail fast if the error will
+			 * never be below 500 ppm.
+			 */
+			if (i == 1 &&
+			    d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11)
+				return 0;
+
 			/*
 			 * Iterate until the error is less than 500 ppm
 			 */
-			delta -= tsc;
 			if (d1+d2 >= delta >> 11)
 				continue;
 
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index ddf9ecb..e342586 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -20,7 +20,7 @@
 	unsigned long ret;
 
 	if (__range_not_ok(from, n, TASK_SIZE))
-		return 0;
+		return n;
 
 	/*
 	 * Even though this function is typically called from NMI/IRQ context
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 4860906..e1840f3 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define pr_fmt(fmt) "kasan: " fmt
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
 #include <linux/kdebug.h>
@@ -11,7 +12,19 @@
 extern pgd_t early_level4_pgt[PTRS_PER_PGD];
 extern struct range pfn_mapped[E820_X_MAX];
 
-extern unsigned char kasan_zero_page[PAGE_SIZE];
+static pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pmd_t kasan_zero_pmd[PTRS_PER_PMD] __page_aligned_bss;
+static pte_t kasan_zero_pte[PTRS_PER_PTE] __page_aligned_bss;
+
+/*
+ * This page used as early shadow. We don't use empty_zero_page
+ * at early stages, stack instrumentation could write some garbage
+ * to this page.
+ * Latter we reuse it as zero shadow for large ranges of memory
+ * that allowed to access, but not instrumented by kasan
+ * (vmalloc/vmemmap ...).
+ */
+static unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss;
 
 static int __init map_range(struct range *range)
 {
@@ -36,7 +49,7 @@
 		pgd_clear(pgd_offset_k(start));
 }
 
-void __init kasan_map_early_shadow(pgd_t *pgd)
+static void __init kasan_map_early_shadow(pgd_t *pgd)
 {
 	int i;
 	unsigned long start = KASAN_SHADOW_START;
@@ -73,7 +86,7 @@
 	while (IS_ALIGNED(addr, PMD_SIZE) && addr + PMD_SIZE <= end) {
 		WARN_ON(!pmd_none(*pmd));
 		set_pmd(pmd, __pmd(__pa_nodebug(kasan_zero_pte)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PMD_SIZE;
 		pmd = pmd_offset(pud, addr);
 	}
@@ -99,7 +112,7 @@
 	while (IS_ALIGNED(addr, PUD_SIZE) && addr + PUD_SIZE <= end) {
 		WARN_ON(!pud_none(*pud));
 		set_pud(pud, __pud(__pa_nodebug(kasan_zero_pmd)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PUD_SIZE;
 		pud = pud_offset(pgd, addr);
 	}
@@ -124,7 +137,7 @@
 	while (IS_ALIGNED(addr, PGDIR_SIZE) && addr + PGDIR_SIZE <= end) {
 		WARN_ON(!pgd_none(*pgd));
 		set_pgd(pgd, __pgd(__pa_nodebug(kasan_zero_pud)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PGDIR_SIZE;
 		pgd = pgd_offset_k(addr);
 	}
@@ -166,6 +179,26 @@
 };
 #endif
 
+void __init kasan_early_init(void)
+{
+	int i;
+	pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL;
+	pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE;
+	pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		kasan_zero_pte[i] = __pte(pte_val);
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		kasan_zero_pmd[i] = __pmd(pmd_val);
+
+	for (i = 0; i < PTRS_PER_PUD; i++)
+		kasan_zero_pud[i] = __pud(pud_val);
+
+	kasan_map_early_shadow(early_level4_pgt);
+	kasan_map_early_shadow(init_level4_pgt);
+}
+
 void __init kasan_init(void)
 {
 	int i;
@@ -176,6 +209,7 @@
 
 	memcpy(early_level4_pgt, init_level4_pgt, sizeof(early_level4_pgt));
 	load_cr3(early_level4_pgt);
+	__flush_tlb_all();
 
 	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
 
@@ -202,5 +236,8 @@
 	memset(kasan_zero_page, 0, PAGE_SIZE);
 
 	load_cr3(init_level4_pgt);
+	__flush_tlb_all();
 	init_task.kasan_depth = 0;
+
+	pr_info("Kernel address sanitizer initialized\n");
 }
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 569ee09..46b58ab 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -352,13 +352,16 @@
 				pdata->mmio_size = resource_size(rentry->res);
 			pdata->mmio_base = ioremap(rentry->res->start,
 						   pdata->mmio_size);
-			if (!pdata->mmio_base)
-				goto err_out;
 			break;
 		}
 
 	acpi_dev_free_resource_list(&resource_list);
 
+	if (!pdata->mmio_base) {
+		ret = -ENOMEM;
+		goto err_out;
+	}
+
 	pdata->dev_desc = dev_desc;
 
 	if (dev_desc->setup)
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 2161fa1..628a42c 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -18,6 +18,7 @@
 #include <linux/list.h>
 #include <linux/acpi.h>
 #include <linux/sort.h>
+#include <linux/pmem.h>
 #include <linux/io.h>
 #include "nfit.h"
 
@@ -305,6 +306,23 @@
 	return true;
 }
 
+static bool add_flush(struct acpi_nfit_desc *acpi_desc,
+		struct acpi_nfit_flush_address *flush)
+{
+	struct device *dev = acpi_desc->dev;
+	struct nfit_flush *nfit_flush = devm_kzalloc(dev, sizeof(*nfit_flush),
+			GFP_KERNEL);
+
+	if (!nfit_flush)
+		return false;
+	INIT_LIST_HEAD(&nfit_flush->list);
+	nfit_flush->flush = flush;
+	list_add_tail(&nfit_flush->list, &acpi_desc->flushes);
+	dev_dbg(dev, "%s: nfit_flush handle: %d hint_count: %d\n", __func__,
+			flush->device_handle, flush->hint_count);
+	return true;
+}
+
 static void *add_table(struct acpi_nfit_desc *acpi_desc, void *table,
 		const void *end)
 {
@@ -338,7 +356,8 @@
 			return err;
 		break;
 	case ACPI_NFIT_TYPE_FLUSH_ADDRESS:
-		dev_dbg(dev, "%s: flush\n", __func__);
+		if (!add_flush(acpi_desc, table))
+			return err;
 		break;
 	case ACPI_NFIT_TYPE_SMBIOS:
 		dev_dbg(dev, "%s: smbios\n", __func__);
@@ -389,6 +408,7 @@
 {
 	u16 dcr = __to_nfit_memdev(nfit_mem)->region_index;
 	struct nfit_memdev *nfit_memdev;
+	struct nfit_flush *nfit_flush;
 	struct nfit_dcr *nfit_dcr;
 	struct nfit_bdw *nfit_bdw;
 	struct nfit_idt *nfit_idt;
@@ -442,6 +462,14 @@
 			nfit_mem->idt_bdw = nfit_idt->idt;
 			break;
 		}
+
+		list_for_each_entry(nfit_flush, &acpi_desc->flushes, list) {
+			if (nfit_flush->flush->device_handle !=
+					nfit_memdev->memdev->device_handle)
+				continue;
+			nfit_mem->nfit_flush = nfit_flush;
+			break;
+		}
 		break;
 	}
 
@@ -978,6 +1006,24 @@
 	return mmio->base_offset + line_offset + table_offset + sub_line_offset;
 }
 
+static void wmb_blk(struct nfit_blk *nfit_blk)
+{
+
+	if (nfit_blk->nvdimm_flush) {
+		/*
+		 * The first wmb() is needed to 'sfence' all previous writes
+		 * such that they are architecturally visible for the platform
+		 * buffer flush.  Note that we've already arranged for pmem
+		 * writes to avoid the cache via arch_memcpy_to_pmem().  The
+		 * final wmb() ensures ordering for the NVDIMM flush write.
+		 */
+		wmb();
+		writeq(1, nfit_blk->nvdimm_flush);
+		wmb();
+	} else
+		wmb_pmem();
+}
+
 static u64 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw)
 {
 	struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR];
@@ -1012,7 +1058,10 @@
 		offset = to_interleave_offset(offset, mmio);
 
 	writeq(cmd, mmio->base + offset);
-	/* FIXME: conditionally perform read-back if mandated by firmware */
+	wmb_blk(nfit_blk);
+
+	if (nfit_blk->dimm_flags & ND_BLK_DCR_LATCH)
+		readq(mmio->base + offset);
 }
 
 static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
@@ -1026,7 +1075,6 @@
 
 	base_offset = nfit_blk->bdw_offset + dpa % L1_CACHE_BYTES
 		+ lane * mmio->size;
-	/* TODO: non-temporal access, flush hints, cache management etc... */
 	write_blk_ctl(nfit_blk, lane, dpa, len, rw);
 	while (len) {
 		unsigned int c;
@@ -1045,13 +1093,19 @@
 		}
 
 		if (rw)
-			memcpy(mmio->aperture + offset, iobuf + copied, c);
+			memcpy_to_pmem(mmio->aperture + offset,
+					iobuf + copied, c);
 		else
-			memcpy(iobuf + copied, mmio->aperture + offset, c);
+			memcpy_from_pmem(iobuf + copied,
+					mmio->aperture + offset, c);
 
 		copied += c;
 		len -= c;
 	}
+
+	if (rw)
+		wmb_blk(nfit_blk);
+
 	rc = read_blk_stat(nfit_blk, lane) ? -EIO : 0;
 	return rc;
 }
@@ -1124,7 +1178,7 @@
 }
 
 static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
-		struct acpi_nfit_system_address *spa)
+		struct acpi_nfit_system_address *spa, enum spa_map_type type)
 {
 	resource_size_t start = spa->address;
 	resource_size_t n = spa->length;
@@ -1152,8 +1206,15 @@
 	if (!res)
 		goto err_mem;
 
-	/* TODO: cacheability based on the spa type */
-	spa_map->iomem = ioremap_nocache(start, n);
+	if (type == SPA_MAP_APERTURE) {
+		/*
+		 * TODO: memremap_pmem() support, but that requires cache
+		 * flushing when the aperture is moved.
+		 */
+		spa_map->iomem = ioremap_wc(start, n);
+	} else
+		spa_map->iomem = ioremap_nocache(start, n);
+
 	if (!spa_map->iomem)
 		goto err_map;
 
@@ -1171,6 +1232,7 @@
  * nfit_spa_map - interleave-aware managed-mappings of acpi_nfit_system_address ranges
  * @nvdimm_bus: NFIT-bus that provided the spa table entry
  * @nfit_spa: spa table to map
+ * @type: aperture or control region
  *
  * In the case where block-data-window apertures and
  * dimm-control-regions are interleaved they will end up sharing a
@@ -1180,12 +1242,12 @@
  * unbound.
  */
 static void __iomem *nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
-		struct acpi_nfit_system_address *spa)
+		struct acpi_nfit_system_address *spa, enum spa_map_type type)
 {
 	void __iomem *iomem;
 
 	mutex_lock(&acpi_desc->spa_map_mutex);
-	iomem = __nfit_spa_map(acpi_desc, spa);
+	iomem = __nfit_spa_map(acpi_desc, spa, type);
 	mutex_unlock(&acpi_desc->spa_map_mutex);
 
 	return iomem;
@@ -1206,12 +1268,35 @@
 	return 0;
 }
 
+static int acpi_nfit_blk_get_flags(struct nvdimm_bus_descriptor *nd_desc,
+		struct nvdimm *nvdimm, struct nfit_blk *nfit_blk)
+{
+	struct nd_cmd_dimm_flags flags;
+	int rc;
+
+	memset(&flags, 0, sizeof(flags));
+	rc = nd_desc->ndctl(nd_desc, nvdimm, ND_CMD_DIMM_FLAGS, &flags,
+			sizeof(flags));
+
+	if (rc >= 0 && flags.status == 0)
+		nfit_blk->dimm_flags = flags.flags;
+	else if (rc == -ENOTTY) {
+		/* fall back to a conservative default */
+		nfit_blk->dimm_flags = ND_BLK_DCR_LATCH;
+		rc = 0;
+	} else
+		rc = -ENXIO;
+
+	return rc;
+}
+
 static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 		struct device *dev)
 {
 	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 	struct nd_blk_region *ndbr = to_nd_blk_region(dev);
+	struct nfit_flush *nfit_flush;
 	struct nfit_blk_mmio *mmio;
 	struct nfit_blk *nfit_blk;
 	struct nfit_mem *nfit_mem;
@@ -1223,8 +1308,8 @@
 	if (!nfit_mem || !nfit_mem->dcr || !nfit_mem->bdw) {
 		dev_dbg(dev, "%s: missing%s%s%s\n", __func__,
 				nfit_mem ? "" : " nfit_mem",
-				nfit_mem->dcr ? "" : " dcr",
-				nfit_mem->bdw ? "" : " bdw");
+				(nfit_mem && nfit_mem->dcr) ? "" : " dcr",
+				(nfit_mem && nfit_mem->bdw) ? "" : " bdw");
 		return -ENXIO;
 	}
 
@@ -1237,7 +1322,8 @@
 	/* map block aperture memory */
 	nfit_blk->bdw_offset = nfit_mem->bdw->offset;
 	mmio = &nfit_blk->mmio[BDW];
-	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw);
+	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw,
+			SPA_MAP_APERTURE);
 	if (!mmio->base) {
 		dev_dbg(dev, "%s: %s failed to map bdw\n", __func__,
 				nvdimm_name(nvdimm));
@@ -1259,7 +1345,8 @@
 	nfit_blk->cmd_offset = nfit_mem->dcr->command_offset;
 	nfit_blk->stat_offset = nfit_mem->dcr->status_offset;
 	mmio = &nfit_blk->mmio[DCR];
-	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr);
+	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr,
+			SPA_MAP_CONTROL);
 	if (!mmio->base) {
 		dev_dbg(dev, "%s: %s failed to map dcr\n", __func__,
 				nvdimm_name(nvdimm));
@@ -1277,6 +1364,24 @@
 		return rc;
 	}
 
+	rc = acpi_nfit_blk_get_flags(nd_desc, nvdimm, nfit_blk);
+	if (rc < 0) {
+		dev_dbg(dev, "%s: %s failed get DIMM flags\n",
+				__func__, nvdimm_name(nvdimm));
+		return rc;
+	}
+
+	nfit_flush = nfit_mem->nfit_flush;
+	if (nfit_flush && nfit_flush->flush->hint_count != 0) {
+		nfit_blk->nvdimm_flush = devm_ioremap_nocache(dev,
+				nfit_flush->flush->hint_address[0], 8);
+		if (!nfit_blk->nvdimm_flush)
+			return -ENOMEM;
+	}
+
+	if (!arch_has_pmem_api() && !nfit_blk->nvdimm_flush)
+		dev_warn(dev, "unable to guarantee persistence of writes\n");
+
 	if (mmio->line_size == 0)
 		return 0;
 
@@ -1459,6 +1564,7 @@
 	INIT_LIST_HEAD(&acpi_desc->dcrs);
 	INIT_LIST_HEAD(&acpi_desc->bdws);
 	INIT_LIST_HEAD(&acpi_desc->idts);
+	INIT_LIST_HEAD(&acpi_desc->flushes);
 	INIT_LIST_HEAD(&acpi_desc->memdevs);
 	INIT_LIST_HEAD(&acpi_desc->dimms);
 	mutex_init(&acpi_desc->spa_map_mutex);
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 81f2e8c..79b6d83 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -40,6 +40,10 @@
 	NFIT_UUID_MAX,
 };
 
+enum {
+	ND_BLK_DCR_LATCH = 2,
+};
+
 struct nfit_spa {
 	struct acpi_nfit_system_address *spa;
 	struct list_head list;
@@ -60,6 +64,11 @@
 	struct list_head list;
 };
 
+struct nfit_flush {
+	struct acpi_nfit_flush_address *flush;
+	struct list_head list;
+};
+
 struct nfit_memdev {
 	struct acpi_nfit_memory_map *memdev;
 	struct list_head list;
@@ -77,6 +86,7 @@
 	struct acpi_nfit_system_address *spa_bdw;
 	struct acpi_nfit_interleave *idt_dcr;
 	struct acpi_nfit_interleave *idt_bdw;
+	struct nfit_flush *nfit_flush;
 	struct list_head list;
 	struct acpi_device *adev;
 	unsigned long dsm_mask;
@@ -88,6 +98,7 @@
 	struct mutex spa_map_mutex;
 	struct list_head spa_maps;
 	struct list_head memdevs;
+	struct list_head flushes;
 	struct list_head dimms;
 	struct list_head spas;
 	struct list_head dcrs;
@@ -109,7 +120,7 @@
 	struct nfit_blk_mmio {
 		union {
 			void __iomem *base;
-			void *aperture;
+			void __pmem  *aperture;
 		};
 		u64 size;
 		u64 base_offset;
@@ -123,6 +134,13 @@
 	u64 bdw_offset; /* post interleave offset */
 	u64 stat_offset;
 	u64 cmd_offset;
+	void __iomem *nvdimm_flush;
+	u32 dimm_flags;
+};
+
+enum spa_map_type {
+	SPA_MAP_CONTROL,
+	SPA_MAP_APERTURE,
 };
 
 struct nfit_spa_mapping {
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index c262e4a..3b8963f 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -175,10 +175,14 @@
 	if (!addr || !length)
 		return;
 
-	acpi_reserve_region(addr, length, gas->space_id, 0, desc);
+	/* Resources are never freed */
+	if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO)
+		request_region(addr, length, desc);
+	else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
+		request_mem_region(addr, length, desc);
 }
 
-static void __init acpi_reserve_resources(void)
+static int __init acpi_reserve_resources(void)
 {
 	acpi_request_region(&acpi_gbl_FADT.xpm1a_event_block, acpi_gbl_FADT.pm1_event_length,
 		"ACPI PM1a_EVT_BLK");
@@ -207,7 +211,10 @@
 	if (!(acpi_gbl_FADT.gpe1_block_length & 0x1))
 		acpi_request_region(&acpi_gbl_FADT.xgpe1_block,
 			       acpi_gbl_FADT.gpe1_block_length, "ACPI GPE1_BLK");
+
+	return 0;
 }
+fs_initcall_sync(acpi_reserve_resources);
 
 void acpi_os_printf(const char *fmt, ...)
 {
@@ -1862,7 +1869,6 @@
 
 acpi_status __init acpi_os_initialize1(void)
 {
-	acpi_reserve_resources();
 	kacpid_wq = alloc_workqueue("kacpid", 0, 1);
 	kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1);
 	kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0);
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 10561ce..8244f01 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -26,7 +26,6 @@
 #include <linux/device.h>
 #include <linux/export.h>
 #include <linux/ioport.h>
-#include <linux/list.h>
 #include <linux/slab.h>
 
 #ifdef CONFIG_X86
@@ -622,164 +621,3 @@
 	return (type & types) ? 0 : 1;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_filter_resource_type);
-
-struct reserved_region {
-	struct list_head node;
-	u64 start;
-	u64 end;
-};
-
-static LIST_HEAD(reserved_io_regions);
-static LIST_HEAD(reserved_mem_regions);
-
-static int request_range(u64 start, u64 end, u8 space_id, unsigned long flags,
-			 char *desc)
-{
-	unsigned int length = end - start + 1;
-	struct resource *res;
-
-	res = space_id == ACPI_ADR_SPACE_SYSTEM_IO ?
-		request_region(start, length, desc) :
-		request_mem_region(start, length, desc);
-	if (!res)
-		return -EIO;
-
-	res->flags &= ~flags;
-	return 0;
-}
-
-static int add_region_before(u64 start, u64 end, u8 space_id,
-			     unsigned long flags, char *desc,
-			     struct list_head *head)
-{
-	struct reserved_region *reg;
-	int error;
-
-	reg = kmalloc(sizeof(*reg), GFP_KERNEL);
-	if (!reg)
-		return -ENOMEM;
-
-	error = request_range(start, end, space_id, flags, desc);
-	if (error) {
-		kfree(reg);
-		return error;
-	}
-
-	reg->start = start;
-	reg->end = end;
-	list_add_tail(&reg->node, head);
-	return 0;
-}
-
-/**
- * acpi_reserve_region - Reserve an I/O or memory region as a system resource.
- * @start: Starting address of the region.
- * @length: Length of the region.
- * @space_id: Identifier of address space to reserve the region from.
- * @flags: Resource flags to clear for the region after requesting it.
- * @desc: Region description (for messages).
- *
- * Reserve an I/O or memory region as a system resource to prevent others from
- * using it.  If the new region overlaps with one of the regions (in the given
- * address space) already reserved by this routine, only the non-overlapping
- * parts of it will be reserved.
- *
- * Returned is either 0 (success) or a negative error code indicating a resource
- * reservation problem.  It is the code of the first encountered error, but the
- * routine doesn't abort until it has attempted to request all of the parts of
- * the new region that don't overlap with other regions reserved previously.
- *
- * The resources requested by this routine are never released.
- */
-int acpi_reserve_region(u64 start, unsigned int length, u8 space_id,
-			unsigned long flags, char *desc)
-{
-	struct list_head *regions;
-	struct reserved_region *reg;
-	u64 end = start + length - 1;
-	int ret = 0, error = 0;
-
-	if (space_id == ACPI_ADR_SPACE_SYSTEM_IO)
-		regions = &reserved_io_regions;
-	else if (space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
-		regions = &reserved_mem_regions;
-	else
-		return -EINVAL;
-
-	if (list_empty(regions))
-		return add_region_before(start, end, space_id, flags, desc, regions);
-
-	list_for_each_entry(reg, regions, node)
-		if (reg->start == end + 1) {
-			/* The new region can be prepended to this one. */
-			ret = request_range(start, end, space_id, flags, desc);
-			if (!ret)
-				reg->start = start;
-
-			return ret;
-		} else if (reg->start > end) {
-			/* No overlap.  Add the new region here and get out. */
-			return add_region_before(start, end, space_id, flags,
-						 desc, &reg->node);
-		} else if (reg->end == start - 1) {
-			goto combine;
-		} else if (reg->end >= start) {
-			goto overlap;
-		}
-
-	/* The new region goes after the last existing one. */
-	return add_region_before(start, end, space_id, flags, desc, regions);
-
- overlap:
-	/*
-	 * The new region overlaps an existing one.
-	 *
-	 * The head part of the new region immediately preceding the existing
-	 * overlapping one can be combined with it right away.
-	 */
-	if (reg->start > start) {
-		error = request_range(start, reg->start - 1, space_id, flags, desc);
-		if (error)
-			ret = error;
-		else
-			reg->start = start;
-	}
-
- combine:
-	/*
-	 * The new region is adjacent to an existing one.  If it extends beyond
-	 * that region all the way to the next one, it is possible to combine
-	 * all three of them.
-	 */
-	while (reg->end < end) {
-		struct reserved_region *next = NULL;
-		u64 a = reg->end + 1, b = end;
-
-		if (!list_is_last(&reg->node, regions)) {
-			next = list_next_entry(reg, node);
-			if (next->start <= end)
-				b = next->start - 1;
-		}
-		error = request_range(a, b, space_id, flags, desc);
-		if (!error) {
-			if (next && next->start == b + 1) {
-				reg->end = next->end;
-				list_del(&next->node);
-				kfree(next);
-			} else {
-				reg->end = end;
-				break;
-			}
-		} else if (next) {
-			if (!ret)
-				ret = error;
-
-			reg = next;
-		} else {
-			break;
-		}
-	}
-
-	return ret ? ret : error;
-}
-EXPORT_SYMBOL_GPL(acpi_reserve_region);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 2649a06..ec25635 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1019,6 +1019,29 @@
 	return false;
 }
 
+static bool __acpi_match_device_cls(const struct acpi_device_id *id,
+				    struct acpi_hardware_id *hwid)
+{
+	int i, msk, byte_shift;
+	char buf[3];
+
+	if (!id->cls)
+		return false;
+
+	/* Apply class-code bitmask, before checking each class-code byte */
+	for (i = 1; i <= 3; i++) {
+		byte_shift = 8 * (3 - i);
+		msk = (id->cls_msk >> byte_shift) & 0xFF;
+		if (!msk)
+			continue;
+
+		sprintf(buf, "%02x", (id->cls >> byte_shift) & msk);
+		if (strncmp(buf, &hwid->id[(i - 1) * 2], 2))
+			return false;
+	}
+	return true;
+}
+
 static const struct acpi_device_id *__acpi_match_device(
 	struct acpi_device *device,
 	const struct acpi_device_id *ids,
@@ -1036,9 +1059,12 @@
 
 	list_for_each_entry(hwid, &device->pnp.ids, list) {
 		/* First, check the ACPI/PNP IDs provided by the caller. */
-		for (id = ids; id->id[0]; id++)
-			if (!strcmp((char *) id->id, hwid->id))
+		for (id = ids; id->id[0] || id->cls; id++) {
+			if (id->id[0] && !strcmp((char *) id->id, hwid->id))
 				return id;
+			else if (id->cls && __acpi_match_device_cls(id, hwid))
+				return id;
+		}
 
 		/*
 		 * Next, check ACPI_DT_NAMESPACE_HID and try to match the
@@ -2101,6 +2127,8 @@
 		if (info->valid & ACPI_VALID_UID)
 			pnp->unique_id = kstrdup(info->unique_id.string,
 							GFP_KERNEL);
+		if (info->valid & ACPI_VALID_CLS)
+			acpi_add_id(pnp, info->class_code.string);
 
 		kfree(info);
 
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 6d17a3b..15e40ee 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -48,7 +48,7 @@
 
 config ATA_ACPI
 	bool "ATA ACPI Support"
-	depends on ACPI && PCI
+	depends on ACPI
 	default y
 	help
 	  This option adds support for ATA-related ACPI objects.
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index 614c78f..1befb11 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -20,6 +20,8 @@
 #include <linux/platform_device.h>
 #include <linux/libata.h>
 #include <linux/ahci_platform.h>
+#include <linux/acpi.h>
+#include <linux/pci_ids.h>
 #include "ahci.h"
 
 #define DRV_NAME "ahci"
@@ -79,12 +81,19 @@
 };
 MODULE_DEVICE_TABLE(of, ahci_of_match);
 
+static const struct acpi_device_id ahci_acpi_match[] = {
+	{ ACPI_DEVICE_CLASS(PCI_CLASS_STORAGE_SATA_AHCI, 0xffffff) },
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, ahci_acpi_match);
+
 static struct platform_driver ahci_driver = {
 	.probe = ahci_probe,
 	.remove = ata_platform_remove_one,
 	.driver = {
 		.name = DRV_NAME,
 		.of_match_table = ahci_of_match,
+		.acpi_match_table = ahci_acpi_match,
 		.pm = &ahci_pm_ops,
 	},
 };
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 9c42883..894bda1 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -563,10 +563,8 @@
 	kfree(fw_priv);
 }
 
-static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
+static int do_firmware_uevent(struct firmware_priv *fw_priv, struct kobj_uevent_env *env)
 {
-	struct firmware_priv *fw_priv = to_firmware_priv(dev);
-
 	if (add_uevent_var(env, "FIRMWARE=%s", fw_priv->buf->fw_id))
 		return -ENOMEM;
 	if (add_uevent_var(env, "TIMEOUT=%i", loading_timeout))
@@ -577,6 +575,18 @@
 	return 0;
 }
 
+static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct firmware_priv *fw_priv = to_firmware_priv(dev);
+	int err = 0;
+
+	mutex_lock(&fw_lock);
+	if (fw_priv->buf)
+		err = do_firmware_uevent(fw_priv, env);
+	mutex_unlock(&fw_lock);
+	return err;
+}
+
 static struct class firmware_class = {
 	.name		= "firmware",
 	.class_attrs	= firmware_class_attrs,
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index cdd547b..0ee43c1 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -6,6 +6,7 @@
  * This file is released under the GPLv2.
  */
 
+#include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
@@ -19,6 +20,8 @@
 #include <linux/suspend.h>
 #include <linux/export.h>
 
+#define GENPD_RETRY_MAX_MS	250		/* Approximate */
+
 #define GENPD_DEV_CALLBACK(genpd, type, callback, dev)		\
 ({								\
 	type (*__routine)(struct device *__d); 			\
@@ -2131,6 +2134,7 @@
 static void genpd_dev_pm_detach(struct device *dev, bool power_off)
 {
 	struct generic_pm_domain *pd;
+	unsigned int i;
 	int ret = 0;
 
 	pd = pm_genpd_lookup_dev(dev);
@@ -2139,10 +2143,12 @@
 
 	dev_dbg(dev, "removing from PM domain %s\n", pd->name);
 
-	while (1) {
+	for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
 		ret = pm_genpd_remove_device(pd, dev);
 		if (ret != -EAGAIN)
 			break;
+
+		mdelay(i);
 		cond_resched();
 	}
 
@@ -2183,6 +2189,7 @@
 {
 	struct of_phandle_args pd_args;
 	struct generic_pm_domain *pd;
+	unsigned int i;
 	int ret;
 
 	if (!dev->of_node)
@@ -2218,10 +2225,12 @@
 
 	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
 
-	while (1) {
+	for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
 		ret = pm_genpd_add_device(pd, dev);
 		if (ret != -EAGAIN)
 			break;
+
+		mdelay(i);
 		cond_resched();
 	}
 
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 7470004..eb6e674 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -45,14 +45,12 @@
 		return -EEXIST;
 	}
 
-	dev->power.wakeirq = wirq;
-	spin_unlock_irqrestore(&dev->power.lock, flags);
-
 	err = device_wakeup_attach_irq(dev, wirq);
-	if (err)
-		return err;
+	if (!err)
+		dev->power.wakeirq = wirq;
 
-	return 0;
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+	return err;
 }
 
 /**
@@ -105,10 +103,10 @@
 		return;
 
 	spin_lock_irqsave(&dev->power.lock, flags);
+	device_wakeup_detach_irq(dev);
 	dev->power.wakeirq = NULL;
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 
-	device_wakeup_detach_irq(dev);
 	if (wirq->dedicated_irq)
 		free_irq(wirq->irq, wirq);
 	kfree(wirq);
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 40f7160..51f15bc 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -281,32 +281,25 @@
  * Attach a device wakeirq to the wakeup source so the device
  * wake IRQ can be configured automatically for suspend and
  * resume.
+ *
+ * Call under the device's power.lock lock.
  */
 int device_wakeup_attach_irq(struct device *dev,
 			     struct wake_irq *wakeirq)
 {
 	struct wakeup_source *ws;
-	int ret = 0;
 
-	spin_lock_irq(&dev->power.lock);
 	ws = dev->power.wakeup;
 	if (!ws) {
 		dev_err(dev, "forgot to call call device_init_wakeup?\n");
-		ret = -EINVAL;
-		goto unlock;
+		return -EINVAL;
 	}
 
-	if (ws->wakeirq) {
-		ret = -EEXIST;
-		goto unlock;
-	}
+	if (ws->wakeirq)
+		return -EEXIST;
 
 	ws->wakeirq = wakeirq;
-
-unlock:
-	spin_unlock_irq(&dev->power.lock);
-
-	return ret;
+	return 0;
 }
 
 /**
@@ -314,20 +307,16 @@
  * @dev: Device to handle
  *
  * Removes a device wakeirq from the wakeup source.
+ *
+ * Call under the device's power.lock lock.
  */
 void device_wakeup_detach_irq(struct device *dev)
 {
 	struct wakeup_source *ws;
 
-	spin_lock_irq(&dev->power.lock);
 	ws = dev->power.wakeup;
-	if (!ws)
-		goto unlock;
-
-	ws->wakeirq = NULL;
-
-unlock:
-	spin_unlock_irq(&dev->power.lock);
+	if (ws)
+		ws->wakeirq = NULL;
 }
 
 /**
diff --git a/drivers/clk/at91/clk-h32mx.c b/drivers/clk/at91/clk-h32mx.c
index 152dcb3..61566bc 100644
--- a/drivers/clk/at91/clk-h32mx.c
+++ b/drivers/clk/at91/clk-h32mx.c
@@ -116,8 +116,10 @@
 	h32mxclk->pmc = pmc;
 
 	clk = clk_register(NULL, &h32mxclk->hw);
-	if (!clk)
+	if (!clk) {
+		kfree(h32mxclk);
 		return;
+	}
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c
index c240045..27dfa96 100644
--- a/drivers/clk/at91/clk-main.c
+++ b/drivers/clk/at91/clk-main.c
@@ -171,8 +171,10 @@
 	irq_set_status_flags(osc->irq, IRQ_NOAUTOEN);
 	ret = request_irq(osc->irq, clk_main_osc_irq_handler,
 			  IRQF_TRIGGER_HIGH, name, osc);
-	if (ret)
+	if (ret) {
+		kfree(osc);
 		return ERR_PTR(ret);
+	}
 
 	if (bypass)
 		pmc_write(pmc, AT91_CKGR_MOR,
diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index f98eafe..5b3ded5 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -165,12 +165,16 @@
 	irq_set_status_flags(master->irq, IRQ_NOAUTOEN);
 	ret = request_irq(master->irq, clk_master_irq_handler,
 			  IRQF_TRIGGER_HIGH, "clk-master", master);
-	if (ret)
+	if (ret) {
+		kfree(master);
 		return ERR_PTR(ret);
+	}
 
 	clk = clk_register(NULL, &master->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(master->irq, master);
 		kfree(master);
+	}
 
 	return clk;
 }
diff --git a/drivers/clk/at91/clk-pll.c b/drivers/clk/at91/clk-pll.c
index cbbe403..18b60f4 100644
--- a/drivers/clk/at91/clk-pll.c
+++ b/drivers/clk/at91/clk-pll.c
@@ -346,12 +346,16 @@
 	irq_set_status_flags(pll->irq, IRQ_NOAUTOEN);
 	ret = request_irq(pll->irq, clk_pll_irq_handler, IRQF_TRIGGER_HIGH,
 			  id ? "clk-pllb" : "clk-plla", pll);
-	if (ret)
+	if (ret) {
+		kfree(pll);
 		return ERR_PTR(ret);
+	}
 
 	clk = clk_register(NULL, &pll->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(pll->irq, pll);
 		kfree(pll);
+	}
 
 	return clk;
 }
diff --git a/drivers/clk/at91/clk-system.c b/drivers/clk/at91/clk-system.c
index a76d03f..58008b3 100644
--- a/drivers/clk/at91/clk-system.c
+++ b/drivers/clk/at91/clk-system.c
@@ -130,13 +130,17 @@
 		irq_set_status_flags(sys->irq, IRQ_NOAUTOEN);
 		ret = request_irq(sys->irq, clk_system_irq_handler,
 				IRQF_TRIGGER_HIGH, name, sys);
-		if (ret)
+		if (ret) {
+			kfree(sys);
 			return ERR_PTR(ret);
+		}
 	}
 
 	clk = clk_register(NULL, &sys->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(sys->irq, sys);
 		kfree(sys);
+	}
 
 	return clk;
 }
diff --git a/drivers/clk/at91/clk-utmi.c b/drivers/clk/at91/clk-utmi.c
index ae3263b..30dd697 100644
--- a/drivers/clk/at91/clk-utmi.c
+++ b/drivers/clk/at91/clk-utmi.c
@@ -118,12 +118,16 @@
 	irq_set_status_flags(utmi->irq, IRQ_NOAUTOEN);
 	ret = request_irq(utmi->irq, clk_utmi_irq_handler,
 			  IRQF_TRIGGER_HIGH, "clk-utmi", utmi);
-	if (ret)
+	if (ret) {
+		kfree(utmi);
 		return ERR_PTR(ret);
+	}
 
 	clk = clk_register(NULL, &utmi->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(utmi->irq, utmi);
 		kfree(utmi);
+	}
 
 	return clk;
 }
diff --git a/drivers/clk/bcm/clk-iproc-asiu.c b/drivers/clk/bcm/clk-iproc-asiu.c
index e19c09c..f630e1b 100644
--- a/drivers/clk/bcm/clk-iproc-asiu.c
+++ b/drivers/clk/bcm/clk-iproc-asiu.c
@@ -222,10 +222,6 @@
 		struct iproc_asiu_clk *asiu_clk;
 		const char *clk_name;
 
-		clk_name = kzalloc(IPROC_CLK_NAME_LEN, GFP_KERNEL);
-		if (WARN_ON(!clk_name))
-			goto err_clk_register;
-
 		ret = of_property_read_string_index(node, "clock-output-names",
 						    i, &clk_name);
 		if (WARN_ON(ret))
@@ -259,7 +255,7 @@
 
 err_clk_register:
 	for (i = 0; i < num_clks; i++)
-		kfree(asiu->clks[i].name);
+		clk_unregister(asiu->clk_data.clks[i]);
 	iounmap(asiu->gate_base);
 
 err_iomap_gate:
diff --git a/drivers/clk/bcm/clk-iproc-pll.c b/drivers/clk/bcm/clk-iproc-pll.c
index 46fb84b..2dda4e8 100644
--- a/drivers/clk/bcm/clk-iproc-pll.c
+++ b/drivers/clk/bcm/clk-iproc-pll.c
@@ -366,7 +366,7 @@
 	val = readl(pll->pll_base + ctrl->ndiv_int.offset);
 	ndiv_int = (val >> ctrl->ndiv_int.shift) &
 		bit_mask(ctrl->ndiv_int.width);
-	ndiv = ndiv_int << ctrl->ndiv_int.shift;
+	ndiv = (u64)ndiv_int << ctrl->ndiv_int.shift;
 
 	if (ctrl->flags & IPROC_CLK_PLL_HAS_NDIV_FRAC) {
 		val = readl(pll->pll_base + ctrl->ndiv_frac.offset);
@@ -374,7 +374,8 @@
 			bit_mask(ctrl->ndiv_frac.width);
 
 		if (ndiv_frac != 0)
-			ndiv = (ndiv_int << ctrl->ndiv_int.shift) | ndiv_frac;
+			ndiv = ((u64)ndiv_int << ctrl->ndiv_int.shift) |
+				ndiv_frac;
 	}
 
 	val = readl(pll->pll_base + ctrl->pdiv.offset);
@@ -655,10 +656,6 @@
 		memset(&init, 0, sizeof(init));
 		parent_name = node->name;
 
-		clk_name = kzalloc(IPROC_CLK_NAME_LEN, GFP_KERNEL);
-		if (WARN_ON(!clk_name))
-			goto err_clk_register;
-
 		ret = of_property_read_string_index(node, "clock-output-names",
 						    i, &clk_name);
 		if (WARN_ON(ret))
@@ -690,10 +687,8 @@
 	return;
 
 err_clk_register:
-	for (i = 0; i < num_clks; i++) {
-		kfree(pll->clks[i].name);
+	for (i = 0; i < num_clks; i++)
 		clk_unregister(pll->clk_data.clks[i]);
-	}
 
 err_pll_register:
 	if (pll->asiu_base)
diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c
index b9b12a7..3f6f7ad 100644
--- a/drivers/clk/clk-stm32f4.c
+++ b/drivers/clk/clk-stm32f4.c
@@ -268,7 +268,7 @@
 	memcpy(table, stm32f42xx_gate_map, sizeof(table));
 
 	/* only bits set in table can be used as indices */
-	if (WARN_ON(secondary > 8 * sizeof(table) ||
+	if (WARN_ON(secondary >= BITS_PER_BYTE * sizeof(table) ||
 		    0 == (table[BIT_ULL_WORD(secondary)] &
 			  BIT_ULL_MASK(secondary))))
 		return -EINVAL;
diff --git a/drivers/clk/mediatek/clk-mt8173.c b/drivers/clk/mediatek/clk-mt8173.c
index 4b9e04c..8b6523d 100644
--- a/drivers/clk/mediatek/clk-mt8173.c
+++ b/drivers/clk/mediatek/clk-mt8173.c
@@ -700,6 +700,22 @@
 	MUX(CLK_PERI_UART3_SEL, "uart3_ck_sel", uart_ck_sel_parents, 0x40c, 3, 1),
 };
 
+static struct clk_onecell_data *mt8173_top_clk_data __initdata;
+static struct clk_onecell_data *mt8173_pll_clk_data __initdata;
+
+static void __init mtk_clk_enable_critical(void)
+{
+	if (!mt8173_top_clk_data || !mt8173_pll_clk_data)
+		return;
+
+	clk_prepare_enable(mt8173_pll_clk_data->clks[CLK_APMIXED_ARMCA15PLL]);
+	clk_prepare_enable(mt8173_pll_clk_data->clks[CLK_APMIXED_ARMCA7PLL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_MEM_SEL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_DDRPHYCFG_SEL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_CCI400_SEL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_RTC_SEL]);
+}
+
 static void __init mtk_topckgen_init(struct device_node *node)
 {
 	struct clk_onecell_data *clk_data;
@@ -712,19 +728,19 @@
 		return;
 	}
 
-	clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK);
+	mt8173_top_clk_data = clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK);
 
 	mtk_clk_register_factors(root_clk_alias, ARRAY_SIZE(root_clk_alias), clk_data);
 	mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data);
 	mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base,
 			&mt8173_clk_lock, clk_data);
 
-	clk_prepare_enable(clk_data->clks[CLK_TOP_CCI400_SEL]);
-
 	r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
 	if (r)
 		pr_err("%s(): could not register clock provider: %d\n",
 			__func__, r);
+
+	mtk_clk_enable_critical();
 }
 CLK_OF_DECLARE(mtk_topckgen, "mediatek,mt8173-topckgen", mtk_topckgen_init);
 
@@ -818,13 +834,13 @@
 {
 	struct clk_onecell_data *clk_data;
 
-	clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK);
+	mt8173_pll_clk_data = clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK);
 	if (!clk_data)
 		return;
 
 	mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data);
 
-	clk_prepare_enable(clk_data->clks[CLK_APMIXED_ARMCA15PLL]);
+	mtk_clk_enable_critical();
 }
 CLK_OF_DECLARE(mtk_apmixedsys, "mediatek,mt8173-apmixedsys",
 		mtk_apmixedsys_init);
diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index b95d17f..92936f0 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -530,19 +530,16 @@
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	struct freq_tbl f = *rcg->freq_tbl;
 	const struct frac_entry *frac = frac_table_pixel;
-	unsigned long request, src_rate;
+	unsigned long request;
 	int delta = 100000;
 	u32 mask = BIT(rcg->hid_width) - 1;
 	u32 hid_div;
-	int index = qcom_find_src_index(hw, rcg->parent_map, f.src);
-	struct clk *parent = clk_get_parent_by_index(hw->clk, index);
 
 	for (; frac->num; frac++) {
 		request = (rate * frac->den) / frac->num;
 
-		src_rate = __clk_round_rate(parent, request);
-		if ((src_rate < (request - delta)) ||
-			(src_rate > (request + delta)))
+		if ((parent_rate < (request - delta)) ||
+			(parent_rate > (request + delta)))
 			continue;
 
 		regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + CFG_REG,
diff --git a/drivers/clk/st/clk-flexgen.c b/drivers/clk/st/clk-flexgen.c
index 657ca14..8dd8cce 100644
--- a/drivers/clk/st/clk-flexgen.c
+++ b/drivers/clk/st/clk-flexgen.c
@@ -190,7 +190,7 @@
 
 	init.name = name;
 	init.ops = &flexgen_ops;
-	init.flags = CLK_IS_BASIC | flexgen_flags;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE | flexgen_flags;
 	init.parent_names = parent_names;
 	init.num_parents = num_parents;
 
@@ -303,6 +303,8 @@
 	if (!rlock)
 		goto err;
 
+	spin_lock_init(rlock);
+
 	for (i = 0; i < clk_data->clk_num; i++) {
 		struct clk *clk;
 		const char *clk_name;
diff --git a/drivers/clk/st/clkgen-fsyn.c b/drivers/clk/st/clkgen-fsyn.c
index e94197f..d9eb2e1 100644
--- a/drivers/clk/st/clkgen-fsyn.c
+++ b/drivers/clk/st/clkgen-fsyn.c
@@ -340,7 +340,7 @@
 		    CLKGEN_FIELD(0x30c, 0xf, 20),
 		    CLKGEN_FIELD(0x310, 0xf, 20) },
 	.lockstatus_present = true,
-	.lock_status = CLKGEN_FIELD(0x2A0, 0x1, 24),
+	.lock_status = CLKGEN_FIELD(0x2f0, 0x1, 24),
 	.powerup_polarity = 1,
 	.standby_polarity = 1,
 	.pll_ops	= &st_quadfs_pll_c32_ops,
@@ -489,7 +489,7 @@
 	struct st_clk_quadfs_pll *pll = to_quadfs_pll(hw);
 	u32 npda = CLKGEN_READ(pll, npda);
 
-	return !!npda;
+	return pll->data->powerup_polarity ? !npda : !!npda;
 }
 
 static int clk_fs660c32_vco_get_rate(unsigned long input, struct stm_fs *fs,
@@ -635,7 +635,7 @@
 
 	init.name = name;
 	init.ops = quadfs->pll_ops;
-	init.flags = CLK_IS_BASIC;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
 
@@ -774,7 +774,7 @@
 	if (fs->lock)
 		spin_lock_irqsave(fs->lock, flags);
 
-	CLKGEN_WRITE(fs, nsb[fs->chan], !fs->data->standby_polarity);
+	CLKGEN_WRITE(fs, nsb[fs->chan], fs->data->standby_polarity);
 
 	if (fs->lock)
 		spin_unlock_irqrestore(fs->lock, flags);
@@ -1082,10 +1082,6 @@
 		.compatible = "st,stih407-quadfs660-D",
 		.data = &st_fs660c32_D_407
 	},
-	{
-		.compatible = "st,stih407-quadfs660-D",
-		.data = (void *)&st_fs660c32_D_407
-	},
 	{}
 };
 
diff --git a/drivers/clk/st/clkgen-mux.c b/drivers/clk/st/clkgen-mux.c
index 4fbe6e0..717c4a9 100644
--- a/drivers/clk/st/clkgen-mux.c
+++ b/drivers/clk/st/clkgen-mux.c
@@ -237,7 +237,7 @@
 
 	init.name = name;
 	init.ops = &clkgena_divmux_ops;
-	init.flags = CLK_IS_BASIC;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE;
 	init.parent_names = parent_names;
 	init.num_parents = num_parents;
 
@@ -513,7 +513,8 @@
 					  0, &clk_name))
 		return;
 
-	clk = clk_register_divider_table(NULL, clk_name, parent_name, 0,
+	clk = clk_register_divider_table(NULL, clk_name, parent_name,
+					 CLK_GET_RATE_NOCACHE,
 					 reg + data->offset, data->shift, 1,
 					 0, data->table, NULL);
 	if (IS_ERR(clk))
@@ -582,7 +583,7 @@
 };
 static struct clkgen_mux_data stih407_a9_mux_data = {
 	.offset = 0x1a4,
-	.shift = 1,
+	.shift = 0,
 	.width = 2,
 };
 
@@ -786,7 +787,8 @@
 					     &mux->hw, &clk_mux_ops,
 					     &div->hw, &clk_divider_ops,
 					     &gate->hw, &clk_gate_ops,
-					     data->clk_flags);
+					     data->clk_flags |
+					     CLK_GET_RATE_NOCACHE);
 		if (IS_ERR(clk)) {
 			kfree(gate);
 			kfree(div);
diff --git a/drivers/clk/st/clkgen-pll.c b/drivers/clk/st/clkgen-pll.c
index 1065322..72d1c27 100644
--- a/drivers/clk/st/clkgen-pll.c
+++ b/drivers/clk/st/clkgen-pll.c
@@ -406,7 +406,7 @@
 	init.name = clk_name;
 	init.ops = pll_data->ops;
 
-	init.flags = CLK_IS_BASIC;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE;
 	init.parent_names = &parent_name;
 	init.num_parents  = 1;
 
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index 9a82f17..abf7b37 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -1391,6 +1391,7 @@
 CLK_OF_DECLARE(sun6i_a31_clk_init, "allwinner,sun6i-a31", sun6i_init_clocks);
 CLK_OF_DECLARE(sun6i_a31s_clk_init, "allwinner,sun6i-a31s", sun6i_init_clocks);
 CLK_OF_DECLARE(sun8i_a23_clk_init, "allwinner,sun8i-a23", sun6i_init_clocks);
+CLK_OF_DECLARE(sun8i_a33_clk_init, "allwinner,sun8i-a33", sun6i_init_clocks);
 
 static void __init sun9i_init_clocks(struct device_node *node)
 {
diff --git a/drivers/clocksource/timer-imx-gpt.c b/drivers/clocksource/timer-imx-gpt.c
index 879c784..2d59038 100644
--- a/drivers/clocksource/timer-imx-gpt.c
+++ b/drivers/clocksource/timer-imx-gpt.c
@@ -529,6 +529,7 @@
 
 CLOCKSOURCE_OF_DECLARE(imx1_timer, "fsl,imx1-gpt", imx1_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx21_timer, "fsl,imx21-gpt", imx21_timer_init_dt);
+CLOCKSOURCE_OF_DECLARE(imx27_timer, "fsl,imx27-gpt", imx21_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx31_timer, "fsl,imx31-gpt", imx31_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx25_timer, "fsl,imx25-gpt", imx31_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx50_timer, "fsl,imx50-gpt", imx31_timer_init_dt);
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index fc897ba..e362860 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -3,7 +3,7 @@
  *
  * The 2E revision of loongson processor not support this feature.
  *
- * Copyright (C) 2006 - 2008 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2006 - 2008 Lemote Inc. & Institute of Computing Technology
  * Author: Yanhua, yanh@lemote.com
  *
  * This file is subject to the terms and conditions of the GNU General Public
diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c
index 1bd6f9c..29e6850 100644
--- a/drivers/firmware/qcom_scm-32.c
+++ b/drivers/firmware/qcom_scm-32.c
@@ -24,7 +24,6 @@
 #include <linux/err.h>
 #include <linux/qcom_scm.h>
 
-#include <asm/outercache.h>
 #include <asm/cacheflush.h>
 
 #include "qcom_scm.h"
@@ -219,8 +218,7 @@
 	 * Flush the command buffer so that the secure world sees
 	 * the correct data.
 	 */
-	__cpuc_flush_dcache_area((void *)cmd, cmd->len);
-	outer_flush_range(cmd_addr, cmd_addr + cmd->len);
+	secure_flush_area(cmd, cmd->len);
 
 	ret = smc(cmd_addr);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 975edb1..ae43b58 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -352,7 +352,7 @@
 	if (((int64_t)timeout_ns) < 0)
 		return MAX_SCHEDULE_TIMEOUT;
 
-	timeout = ktime_sub_ns(ktime_get(), timeout_ns);
+	timeout = ktime_sub(ns_to_ktime(timeout_ns), ktime_get());
 	if (ktime_to_ns(timeout) < 0)
 		return 0;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 5cde635..6e77964 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -3403,19 +3403,25 @@
 
 	switch (entry->src_data) {
 	case 0: /* vblank */
-		if (disp_int & interrupt_status_offsets[crtc].vblank) {
+		if (disp_int & interrupt_status_offsets[crtc].vblank)
 			dce_v10_0_crtc_vblank_int_ack(adev, crtc);
-			if (amdgpu_irq_enabled(adev, source, irq_type)) {
-				drm_handle_vblank(adev->ddev, crtc);
-			}
-			DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		if (amdgpu_irq_enabled(adev, source, irq_type)) {
+			drm_handle_vblank(adev->ddev, crtc);
 		}
+		DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+
 		break;
 	case 1: /* vline */
-		if (disp_int & interrupt_status_offsets[crtc].vline) {
+		if (disp_int & interrupt_status_offsets[crtc].vline)
 			dce_v10_0_crtc_vline_int_ack(adev, crtc);
-			DRM_DEBUG("IH: D%d vline\n", crtc + 1);
-		}
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		DRM_DEBUG("IH: D%d vline\n", crtc + 1);
+
 		break;
 	default:
 		DRM_DEBUG("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 95efd98..7f7abb0 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -3402,19 +3402,25 @@
 
 	switch (entry->src_data) {
 	case 0: /* vblank */
-		if (disp_int & interrupt_status_offsets[crtc].vblank) {
+		if (disp_int & interrupt_status_offsets[crtc].vblank)
 			dce_v11_0_crtc_vblank_int_ack(adev, crtc);
-			if (amdgpu_irq_enabled(adev, source, irq_type)) {
-				drm_handle_vblank(adev->ddev, crtc);
-			}
-			DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		if (amdgpu_irq_enabled(adev, source, irq_type)) {
+			drm_handle_vblank(adev->ddev, crtc);
 		}
+		DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+
 		break;
 	case 1: /* vline */
-		if (disp_int & interrupt_status_offsets[crtc].vline) {
+		if (disp_int & interrupt_status_offsets[crtc].vline)
 			dce_v11_0_crtc_vline_int_ack(adev, crtc);
-			DRM_DEBUG("IH: D%d vline\n", crtc + 1);
-		}
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		DRM_DEBUG("IH: D%d vline\n", crtc + 1);
+
 		break;
 	default:
 		DRM_DEBUG("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index aaca8d6..08387df 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -3237,19 +3237,25 @@
 
 	switch (entry->src_data) {
 	case 0: /* vblank */
-		if (disp_int & interrupt_status_offsets[crtc].vblank) {
+		if (disp_int & interrupt_status_offsets[crtc].vblank)
 			WREG32(mmLB_VBLANK_STATUS + crtc_offsets[crtc], LB_VBLANK_STATUS__VBLANK_ACK_MASK);
-			if (amdgpu_irq_enabled(adev, source, irq_type)) {
-				drm_handle_vblank(adev->ddev, crtc);
-			}
-			DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		if (amdgpu_irq_enabled(adev, source, irq_type)) {
+			drm_handle_vblank(adev->ddev, crtc);
 		}
+		DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+
 		break;
 	case 1: /* vline */
-		if (disp_int & interrupt_status_offsets[crtc].vline) {
+		if (disp_int & interrupt_status_offsets[crtc].vline)
 			WREG32(mmLB_VLINE_STATUS + crtc_offsets[crtc], LB_VLINE_STATUS__VLINE_ACK_MASK);
-			DRM_DEBUG("IH: D%d vline\n", crtc + 1);
-		}
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		DRM_DEBUG("IH: D%d vline\n", crtc + 1);
+
 		break;
 	default:
 		DRM_DEBUG("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 8a1f999..9be0070 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -420,6 +420,12 @@
 	pqm_uninit(&p->pqm);
 
 	pdd = kfd_get_process_device_data(dev, p);
+
+	if (!pdd) {
+		mutex_unlock(&p->mutex);
+		return;
+	}
+
 	if (pdd->reset_wavefronts) {
 		dbgdev_wave_reset_wavefronts(pdd->dev, p);
 		pdd->reset_wavefronts = false;
@@ -431,8 +437,7 @@
 	 * We don't call amd_iommu_unbind_pasid() here
 	 * because the IOMMU called us.
 	 */
-	if (pdd)
-		pdd->bound = false;
+	pdd->bound = false;
 
 	mutex_unlock(&p->mutex);
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 8867818..d65cbe6 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -157,9 +157,7 @@
 	struct drm_i915_gem_object *obj;
 	int ret;
 
-	obj = i915_gem_object_create_stolen(dev, size);
-	if (obj == NULL)
-		obj = i915_gem_alloc_object(dev, size);
+	obj = i915_gem_alloc_object(dev, size);
 	if (obj == NULL)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 9daa288..dcc6a88 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2546,6 +2546,8 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
 	struct i915_address_space *vm;
+	struct i915_vma *vma;
+	bool flush;
 
 	i915_check_and_clear_faults(dev);
 
@@ -2555,17 +2557,24 @@
 				       dev_priv->gtt.base.total,
 				       true);
 
+	/* Cache flush objects bound into GGTT and rebind them. */
+	vm = &dev_priv->gtt.base;
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		struct i915_vma *vma = i915_gem_obj_to_vma(obj,
-							   &dev_priv->gtt.base);
-		if (!vma)
-			continue;
+		flush = false;
+		list_for_each_entry(vma, &obj->vma_list, vma_link) {
+			if (vma->vm != vm)
+				continue;
 
-		i915_gem_clflush_object(obj, obj->pin_display);
-		WARN_ON(i915_vma_bind(vma, obj->cache_level, PIN_UPDATE));
+			WARN_ON(i915_vma_bind(vma, obj->cache_level,
+					      PIN_UPDATE));
+
+			flush = true;
+		}
+
+		if (flush)
+			i915_gem_clflush_object(obj, obj->pin_display);
 	}
 
-
 	if (INTEL_INFO(dev)->gen >= 8) {
 		if (IS_CHERRYVIEW(dev) || IS_BROXTON(dev))
 			chv_setup_private_ppat(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 633bd1f..d61e74a 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -183,8 +183,18 @@
 		if (IS_GEN4(dev)) {
 			uint32_t ddc2 = I915_READ(DCC2);
 
-			if (!(ddc2 & DCC2_MODIFIED_ENHANCED_DISABLE))
+			if (!(ddc2 & DCC2_MODIFIED_ENHANCED_DISABLE)) {
+				/* Since the swizzling may vary within an
+				 * object, we have no idea what the swizzling
+				 * is for any page in particular. Thus we
+				 * cannot migrate tiled pages using the GPU,
+				 * nor can we tell userspace what the exact
+				 * swizzling is for any object.
+				 */
 				dev_priv->quirks |= QUIRK_PIN_SWIZZLED_PAGES;
+				swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
+				swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
+			}
 		}
 
 		if (dcc == 0xffffffff) {
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 1b61f98..647b140 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4854,6 +4854,9 @@
 	struct intel_plane *intel_plane;
 	int pipe = intel_crtc->pipe;
 
+	if (!intel_crtc->active)
+		return;
+
 	intel_crtc_wait_for_pending_flips(crtc);
 
 	intel_pre_disable_primary(crtc);
@@ -7887,7 +7890,7 @@
 	int pipe = pipe_config->cpu_transcoder;
 	enum dpio_channel port = vlv_pipe_to_channel(pipe);
 	intel_clock_t clock;
-	u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2;
+	u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2, pll_dw3;
 	int refclk = 100000;
 
 	mutex_lock(&dev_priv->sb_lock);
@@ -7895,10 +7898,13 @@
 	pll_dw0 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW0(port));
 	pll_dw1 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW1(port));
 	pll_dw2 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW2(port));
+	pll_dw3 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW3(port));
 	mutex_unlock(&dev_priv->sb_lock);
 
 	clock.m1 = (pll_dw1 & 0x7) == DPIO_CHV_M1_DIV_BY_2 ? 2 : 0;
-	clock.m2 = ((pll_dw0 & 0xff) << 22) | (pll_dw2 & 0x3fffff);
+	clock.m2 = (pll_dw0 & 0xff) << 22;
+	if (pll_dw3 & DPIO_CHV_FRAC_DIV_EN)
+		clock.m2 |= pll_dw2 & 0x3fffff;
 	clock.n = (pll_dw1 >> DPIO_CHV_N_DIV_SHIFT) & 0xf;
 	clock.p1 = (cmn_dw13 >> DPIO_CHV_P1_DIV_SHIFT) & 0x7;
 	clock.p2 = (cmn_dw13 >> DPIO_CHV_P2_DIV_SHIFT) & 0x1f;
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index f2daad8..7841970 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -285,7 +285,7 @@
 
 	if (wait) {
 		if (!wait_for_completion_timeout(&engine->compl,
-				msecs_to_jiffies(1))) {
+				msecs_to_jiffies(100))) {
 			dev_err(dmm->dev, "timed out waiting for done\n");
 			ret = -ETIMEDOUT;
 		}
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h
index ae2df41..12081e6 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.h
+++ b/drivers/gpu/drm/omapdrm/omap_drv.h
@@ -177,7 +177,7 @@
 		struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos);
 struct drm_gem_object *omap_framebuffer_bo(struct drm_framebuffer *fb, int p);
 int omap_framebuffer_pin(struct drm_framebuffer *fb);
-int omap_framebuffer_unpin(struct drm_framebuffer *fb);
+void omap_framebuffer_unpin(struct drm_framebuffer *fb);
 void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 		struct omap_drm_window *win, struct omap_overlay_info *info);
 struct drm_connector *omap_framebuffer_get_next_connector(
@@ -211,7 +211,7 @@
 		enum dma_data_direction dir);
 int omap_gem_get_paddr(struct drm_gem_object *obj,
 		dma_addr_t *paddr, bool remap);
-int omap_gem_put_paddr(struct drm_gem_object *obj);
+void omap_gem_put_paddr(struct drm_gem_object *obj);
 int omap_gem_get_pages(struct drm_gem_object *obj, struct page ***pages,
 		bool remap);
 int omap_gem_put_pages(struct drm_gem_object *obj);
@@ -236,7 +236,7 @@
 	/* PVR needs alignment to 8 pixels.. right now that is the most
 	 * restrictive stride requirement..
 	 */
-	return ALIGN(pitch, 8 * bytespp);
+	return roundup(pitch, 8 * bytespp);
 }
 
 /* map crtc to vblank mask */
diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index 0b967e7..51b1219 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -287,10 +287,10 @@
 }
 
 /* unpin, no longer being scanned out: */
-int omap_framebuffer_unpin(struct drm_framebuffer *fb)
+void omap_framebuffer_unpin(struct drm_framebuffer *fb)
 {
 	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
-	int ret, i, n = drm_format_num_planes(fb->pixel_format);
+	int i, n = drm_format_num_planes(fb->pixel_format);
 
 	mutex_lock(&omap_fb->lock);
 
@@ -298,24 +298,16 @@
 
 	if (omap_fb->pin_count > 0) {
 		mutex_unlock(&omap_fb->lock);
-		return 0;
+		return;
 	}
 
 	for (i = 0; i < n; i++) {
 		struct plane *plane = &omap_fb->planes[i];
-		ret = omap_gem_put_paddr(plane->bo);
-		if (ret)
-			goto fail;
+		omap_gem_put_paddr(plane->bo);
 		plane->paddr = 0;
 	}
 
 	mutex_unlock(&omap_fb->lock);
-
-	return 0;
-
-fail:
-	mutex_unlock(&omap_fb->lock);
-	return ret;
 }
 
 struct drm_gem_object *omap_framebuffer_bo(struct drm_framebuffer *fb, int p)
diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c
index 23b5a84..720d16b 100644
--- a/drivers/gpu/drm/omapdrm/omap_fbdev.c
+++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c
@@ -135,7 +135,7 @@
 	fbdev->ywrap_enabled = priv->has_dmm && ywrap_enabled;
 	if (fbdev->ywrap_enabled) {
 		/* need to align pitch to page size if using DMM scrolling */
-		mode_cmd.pitches[0] = ALIGN(mode_cmd.pitches[0], PAGE_SIZE);
+		mode_cmd.pitches[0] = PAGE_ALIGN(mode_cmd.pitches[0]);
 	}
 
 	/* allocate backing bo */
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 2ab7780..7ed08fdc 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -808,10 +808,10 @@
 /* Release physical address, when DMA is no longer being performed.. this
  * could potentially unpin and unmap buffers from TILER
  */
-int omap_gem_put_paddr(struct drm_gem_object *obj)
+void omap_gem_put_paddr(struct drm_gem_object *obj)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&obj->dev->struct_mutex);
 	if (omap_obj->paddr_cnt > 0) {
@@ -821,7 +821,6 @@
 			if (ret) {
 				dev_err(obj->dev->dev,
 					"could not unpin pages: %d\n", ret);
-				goto fail;
 			}
 			ret = tiler_release(omap_obj->block);
 			if (ret) {
@@ -832,9 +831,8 @@
 			omap_obj->block = NULL;
 		}
 	}
-fail:
+
 	mutex_unlock(&obj->dev->struct_mutex);
-	return ret;
 }
 
 /* Get rotated scanout address (only valid if already pinned), at the
@@ -1378,11 +1376,7 @@
 
 	omap_obj = kzalloc(sizeof(*omap_obj), GFP_KERNEL);
 	if (!omap_obj)
-		goto fail;
-
-	spin_lock(&priv->list_lock);
-	list_add(&omap_obj->mm_list, &priv->obj_list);
-	spin_unlock(&priv->list_lock);
+		return NULL;
 
 	obj = &omap_obj->base;
 
@@ -1392,11 +1386,19 @@
 		 */
 		omap_obj->vaddr =  dma_alloc_writecombine(dev->dev, size,
 				&omap_obj->paddr, GFP_KERNEL);
-		if (omap_obj->vaddr)
-			flags |= OMAP_BO_DMA;
+		if (!omap_obj->vaddr) {
+			kfree(omap_obj);
 
+			return NULL;
+		}
+
+		flags |= OMAP_BO_DMA;
 	}
 
+	spin_lock(&priv->list_lock);
+	list_add(&omap_obj->mm_list, &priv->obj_list);
+	spin_unlock(&priv->list_lock);
+
 	omap_obj->flags = flags;
 
 	if (flags & OMAP_BO_TILED) {
diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c
index cfa8276..0989046 100644
--- a/drivers/gpu/drm/omapdrm/omap_plane.c
+++ b/drivers/gpu/drm/omapdrm/omap_plane.c
@@ -17,6 +17,7 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_plane_helper.h>
 
@@ -153,9 +154,34 @@
 	dispc_ovl_enable(omap_plane->id, false);
 }
 
+static int omap_plane_atomic_check(struct drm_plane *plane,
+				   struct drm_plane_state *state)
+{
+	struct drm_crtc_state *crtc_state;
+
+	if (!state->crtc)
+		return 0;
+
+	crtc_state = drm_atomic_get_crtc_state(state->state, state->crtc);
+	if (IS_ERR(crtc_state))
+		return PTR_ERR(crtc_state);
+
+	if (state->crtc_x < 0 || state->crtc_y < 0)
+		return -EINVAL;
+
+	if (state->crtc_x + state->crtc_w > crtc_state->adjusted_mode.hdisplay)
+		return -EINVAL;
+
+	if (state->crtc_y + state->crtc_h > crtc_state->adjusted_mode.vdisplay)
+		return -EINVAL;
+
+	return 0;
+}
+
 static const struct drm_plane_helper_funcs omap_plane_helper_funcs = {
 	.prepare_fb = omap_plane_prepare_fb,
 	.cleanup_fb = omap_plane_cleanup_fb,
+	.atomic_check = omap_plane_atomic_check,
 	.atomic_update = omap_plane_atomic_update,
 	.atomic_disable = omap_plane_atomic_disable,
 };
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 4ecf5ca..248953d 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -7964,23 +7964,27 @@
 		case 1: /* D1 vblank/vline */
 			switch (src_data) {
 			case 0: /* D1 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[0]) {
-						drm_handle_vblank(rdev->ddev, 0);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_vblank(rdev, 0);
-					rdev->irq.stat_regs.cik.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D1 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int & LB_D1_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[0]) {
+					drm_handle_vblank(rdev->ddev, 0);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[0]))
+					radeon_crtc_handle_vblank(rdev, 0);
+				rdev->irq.stat_regs.cik.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D1 vblank\n");
+
 				break;
 			case 1: /* D1 vline */
-				if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int &= ~LB_D1_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D1 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int & LB_D1_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int &= ~LB_D1_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D1 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -7990,23 +7994,27 @@
 		case 2: /* D2 vblank/vline */
 			switch (src_data) {
 			case 0: /* D2 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int_cont & LB_D2_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[1]) {
-						drm_handle_vblank(rdev->ddev, 1);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_vblank(rdev, 1);
-					rdev->irq.stat_regs.cik.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D2 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont & LB_D2_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[1]) {
+					drm_handle_vblank(rdev->ddev, 1);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[1]))
+					radeon_crtc_handle_vblank(rdev, 1);
+				rdev->irq.stat_regs.cik.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D2 vblank\n");
+
 				break;
 			case 1: /* D2 vline */
-				if (rdev->irq.stat_regs.cik.disp_int_cont & LB_D2_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D2 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont & LB_D2_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D2 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -8016,23 +8024,27 @@
 		case 3: /* D3 vblank/vline */
 			switch (src_data) {
 			case 0: /* D3 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[2]) {
-						drm_handle_vblank(rdev->ddev, 2);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[2]))
-						radeon_crtc_handle_vblank(rdev, 2);
-					rdev->irq.stat_regs.cik.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D3 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[2]) {
+					drm_handle_vblank(rdev->ddev, 2);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[2]))
+					radeon_crtc_handle_vblank(rdev, 2);
+				rdev->irq.stat_regs.cik.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D3 vblank\n");
+
 				break;
 			case 1: /* D3 vline */
-				if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D3 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D3 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -8042,23 +8054,27 @@
 		case 4: /* D4 vblank/vline */
 			switch (src_data) {
 			case 0: /* D4 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[3]) {
-						drm_handle_vblank(rdev->ddev, 3);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[3]))
-						radeon_crtc_handle_vblank(rdev, 3);
-					rdev->irq.stat_regs.cik.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D4 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[3]) {
+					drm_handle_vblank(rdev->ddev, 3);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[3]))
+					radeon_crtc_handle_vblank(rdev, 3);
+				rdev->irq.stat_regs.cik.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D4 vblank\n");
+
 				break;
 			case 1: /* D4 vline */
-				if (rdev->irq.stat_regs.cik.disp_int_cont3 & LB_D4_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D4 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont3 & LB_D4_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D4 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -8068,23 +8084,27 @@
 		case 5: /* D5 vblank/vline */
 			switch (src_data) {
 			case 0: /* D5 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[4]) {
-						drm_handle_vblank(rdev->ddev, 4);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[4]))
-						radeon_crtc_handle_vblank(rdev, 4);
-					rdev->irq.stat_regs.cik.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D5 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[4]) {
+					drm_handle_vblank(rdev->ddev, 4);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[4]))
+					radeon_crtc_handle_vblank(rdev, 4);
+				rdev->irq.stat_regs.cik.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D5 vblank\n");
+
 				break;
 			case 1: /* D5 vline */
-				if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D5 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D5 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -8094,23 +8114,27 @@
 		case 6: /* D6 vblank/vline */
 			switch (src_data) {
 			case 0: /* D6 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[5]) {
-						drm_handle_vblank(rdev->ddev, 5);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[5]))
-						radeon_crtc_handle_vblank(rdev, 5);
-					rdev->irq.stat_regs.cik.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D6 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[5]) {
+					drm_handle_vblank(rdev->ddev, 5);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[5]))
+					radeon_crtc_handle_vblank(rdev, 5);
+				rdev->irq.stat_regs.cik.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D6 vblank\n");
+
 				break;
 			case 1: /* D6 vline */
-				if (rdev->irq.stat_regs.cik.disp_int_cont5 & LB_D6_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D6 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont5 & LB_D6_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D6 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -8130,88 +8154,112 @@
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
-				if (rdev->irq.stat_regs.cik.disp_int & DC_HPD1_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int &= ~DC_HPD1_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD1\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int & DC_HPD1_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int &= ~DC_HPD1_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD1\n");
+
 				break;
 			case 1:
-				if (rdev->irq.stat_regs.cik.disp_int_cont & DC_HPD2_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont &= ~DC_HPD2_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD2\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont & DC_HPD2_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont &= ~DC_HPD2_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD2\n");
+
 				break;
 			case 2:
-				if (rdev->irq.stat_regs.cik.disp_int_cont2 & DC_HPD3_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD3\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont2 & DC_HPD3_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD3\n");
+
 				break;
 			case 3:
-				if (rdev->irq.stat_regs.cik.disp_int_cont3 & DC_HPD4_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD4\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont3 & DC_HPD4_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD4\n");
+
 				break;
 			case 4:
-				if (rdev->irq.stat_regs.cik.disp_int_cont4 & DC_HPD5_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD5\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont4 & DC_HPD5_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD5\n");
+
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD6\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD6\n");
+
 				break;
 			case 6:
-				if (rdev->irq.stat_regs.cik.disp_int & DC_HPD1_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int &= ~DC_HPD1_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 1\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int & DC_HPD1_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int &= ~DC_HPD1_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 1\n");
+
 				break;
 			case 7:
-				if (rdev->irq.stat_regs.cik.disp_int_cont & DC_HPD2_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 2\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont & DC_HPD2_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 2\n");
+
 				break;
 			case 8:
-				if (rdev->irq.stat_regs.cik.disp_int_cont2 & DC_HPD3_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 3\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont2 & DC_HPD3_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 3\n");
+
 				break;
 			case 9:
-				if (rdev->irq.stat_regs.cik.disp_int_cont3 & DC_HPD4_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 4\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont3 & DC_HPD4_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 4\n");
+
 				break;
 			case 10:
-				if (rdev->irq.stat_regs.cik.disp_int_cont4 & DC_HPD5_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 5\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont4 & DC_HPD5_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 5\n");
+
 				break;
 			case 11:
-				if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 6\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 6\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 3a6d483..0acde19 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -4924,7 +4924,7 @@
 		return IRQ_NONE;
 
 	rptr = rdev->ih.rptr;
-	DRM_DEBUG("r600_irq_process start: rptr %d, wptr %d\n", rptr, wptr);
+	DRM_DEBUG("evergreen_irq_process start: rptr %d, wptr %d\n", rptr, wptr);
 
 	/* Order reading of wptr vs. reading of IH ring data */
 	rmb();
@@ -4942,23 +4942,27 @@
 		case 1: /* D1 vblank/vline */
 			switch (src_data) {
 			case 0: /* D1 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[0]) {
-						drm_handle_vblank(rdev->ddev, 0);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_vblank(rdev, 0);
-					rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D1 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D1 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[0]) {
+					drm_handle_vblank(rdev->ddev, 0);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[0]))
+					radeon_crtc_handle_vblank(rdev, 0);
+				rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D1 vblank\n");
+
 				break;
 			case 1: /* D1 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D1 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D1 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D1 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -4968,23 +4972,27 @@
 		case 2: /* D2 vblank/vline */
 			switch (src_data) {
 			case 0: /* D2 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[1]) {
-						drm_handle_vblank(rdev->ddev, 1);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_vblank(rdev, 1);
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D2 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D2 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[1]) {
+					drm_handle_vblank(rdev->ddev, 1);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[1]))
+					radeon_crtc_handle_vblank(rdev, 1);
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D2 vblank\n");
+
 				break;
 			case 1: /* D2 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D2 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D2 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D2 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -4994,23 +5002,27 @@
 		case 3: /* D3 vblank/vline */
 			switch (src_data) {
 			case 0: /* D3 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[2]) {
-						drm_handle_vblank(rdev->ddev, 2);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[2]))
-						radeon_crtc_handle_vblank(rdev, 2);
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D3 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D3 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[2]) {
+					drm_handle_vblank(rdev->ddev, 2);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[2]))
+					radeon_crtc_handle_vblank(rdev, 2);
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D3 vblank\n");
+
 				break;
 			case 1: /* D3 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D3 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D3 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D3 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -5020,23 +5032,27 @@
 		case 4: /* D4 vblank/vline */
 			switch (src_data) {
 			case 0: /* D4 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[3]) {
-						drm_handle_vblank(rdev->ddev, 3);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[3]))
-						radeon_crtc_handle_vblank(rdev, 3);
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D4 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D4 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[3]) {
+					drm_handle_vblank(rdev->ddev, 3);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[3]))
+					radeon_crtc_handle_vblank(rdev, 3);
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D4 vblank\n");
+
 				break;
 			case 1: /* D4 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D4 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D4 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D4 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -5046,23 +5062,27 @@
 		case 5: /* D5 vblank/vline */
 			switch (src_data) {
 			case 0: /* D5 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[4]) {
-						drm_handle_vblank(rdev->ddev, 4);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[4]))
-						radeon_crtc_handle_vblank(rdev, 4);
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D5 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D5 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[4]) {
+					drm_handle_vblank(rdev->ddev, 4);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[4]))
+					radeon_crtc_handle_vblank(rdev, 4);
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D5 vblank\n");
+
 				break;
 			case 1: /* D5 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D5 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D5 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D5 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -5072,23 +5092,27 @@
 		case 6: /* D6 vblank/vline */
 			switch (src_data) {
 			case 0: /* D6 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[5]) {
-						drm_handle_vblank(rdev->ddev, 5);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[5]))
-						radeon_crtc_handle_vblank(rdev, 5);
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D6 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D6 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[5]) {
+					drm_handle_vblank(rdev->ddev, 5);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[5]))
+					radeon_crtc_handle_vblank(rdev, 5);
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D6 vblank\n");
+
 				break;
 			case 1: /* D6 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D6 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D6 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D6 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -5108,88 +5132,100 @@
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
-				if (rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD1\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD1\n");
 				break;
 			case 1:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD2\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD2\n");
 				break;
 			case 2:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD3\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD3\n");
 				break;
 			case 3:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD4\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD4\n");
 				break;
 			case 4:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD5\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD5\n");
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD6\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD6\n");
 				break;
 			case 6:
-				if (rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 1\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 1\n");
 				break;
 			case 7:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 2\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 2\n");
 				break;
 			case 8:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 3\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 3\n");
 				break;
 			case 9:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 4\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 4\n");
 				break;
 			case 10:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 5\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 5\n");
 				break;
 			case 11:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 6\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 6\n");
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -5199,46 +5235,52 @@
 		case 44: /* hdmi */
 			switch (src_data) {
 			case 0:
-				if (rdev->irq.stat_regs.evergreen.afmt_status1 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status1 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI0\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status1 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status1 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI0\n");
 				break;
 			case 1:
-				if (rdev->irq.stat_regs.evergreen.afmt_status2 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status2 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI1\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status2 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status2 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI1\n");
 				break;
 			case 2:
-				if (rdev->irq.stat_regs.evergreen.afmt_status3 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status3 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI2\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status3 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status3 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI2\n");
 				break;
 			case 3:
-				if (rdev->irq.stat_regs.evergreen.afmt_status4 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status4 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI3\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status4 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status4 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI3\n");
 				break;
 			case 4:
-				if (rdev->irq.stat_regs.evergreen.afmt_status5 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status5 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI4\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status5 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status5 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI4\n");
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.evergreen.afmt_status6 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status6 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI5\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status6 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status6 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI5\n");
 				break;
 			default:
 				DRM_ERROR("Unhandled interrupt: %d %d\n", src_id, src_data);
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 8e5aeeb..158872e 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -2162,18 +2162,20 @@
 			DRM_ERROR("radeon: failed initializing UVD (%d).\n", r);
 	}
 
-	ring = &rdev->ring[TN_RING_TYPE_VCE1_INDEX];
-	if (ring->ring_size)
-		r = radeon_ring_init(rdev, ring, ring->ring_size, 0, 0x0);
+	if (rdev->family == CHIP_ARUBA) {
+		ring = &rdev->ring[TN_RING_TYPE_VCE1_INDEX];
+		if (ring->ring_size)
+			r = radeon_ring_init(rdev, ring, ring->ring_size, 0, 0x0);
 
-	ring = &rdev->ring[TN_RING_TYPE_VCE2_INDEX];
-	if (ring->ring_size)
-		r = radeon_ring_init(rdev, ring, ring->ring_size, 0, 0x0);
+		ring = &rdev->ring[TN_RING_TYPE_VCE2_INDEX];
+		if (ring->ring_size)
+			r = radeon_ring_init(rdev, ring, ring->ring_size, 0, 0x0);
 
-	if (!r)
-		r = vce_v1_0_init(rdev);
-	else if (r != -ENOENT)
-		DRM_ERROR("radeon: failed initializing VCE (%d).\n", r);
+		if (!r)
+			r = vce_v1_0_init(rdev);
+		if (r)
+			DRM_ERROR("radeon: failed initializing VCE (%d).\n", r);
+	}
 
 	r = radeon_ib_pool_init(rdev);
 	if (r) {
@@ -2396,7 +2398,8 @@
 	radeon_irq_kms_fini(rdev);
 	uvd_v1_0_fini(rdev);
 	radeon_uvd_fini(rdev);
-	radeon_vce_fini(rdev);
+	if (rdev->family == CHIP_ARUBA)
+		radeon_vce_fini(rdev);
 	cayman_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 35dafd7..4ea5b10 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -4086,23 +4086,27 @@
 		case 1: /* D1 vblank/vline */
 			switch (src_data) {
 			case 0: /* D1 vblank */
-				if (rdev->irq.stat_regs.r600.disp_int & LB_D1_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[0]) {
-						drm_handle_vblank(rdev->ddev, 0);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_vblank(rdev, 0);
-					rdev->irq.stat_regs.r600.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D1 vblank\n");
+				if (!(rdev->irq.stat_regs.r600.disp_int & LB_D1_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D1 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[0]) {
+					drm_handle_vblank(rdev->ddev, 0);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[0]))
+					radeon_crtc_handle_vblank(rdev, 0);
+				rdev->irq.stat_regs.r600.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D1 vblank\n");
+
 				break;
 			case 1: /* D1 vline */
-				if (rdev->irq.stat_regs.r600.disp_int & LB_D1_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int &= ~LB_D1_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D1 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int & LB_D1_VLINE_INTERRUPT))
+				    DRM_DEBUG("IH: D1 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int &= ~LB_D1_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D1 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -4112,23 +4116,27 @@
 		case 5: /* D2 vblank/vline */
 			switch (src_data) {
 			case 0: /* D2 vblank */
-				if (rdev->irq.stat_regs.r600.disp_int & LB_D2_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[1]) {
-						drm_handle_vblank(rdev->ddev, 1);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_vblank(rdev, 1);
-					rdev->irq.stat_regs.r600.disp_int &= ~LB_D2_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D2 vblank\n");
+				if (!(rdev->irq.stat_regs.r600.disp_int & LB_D2_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D2 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[1]) {
+					drm_handle_vblank(rdev->ddev, 1);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[1]))
+					radeon_crtc_handle_vblank(rdev, 1);
+				rdev->irq.stat_regs.r600.disp_int &= ~LB_D2_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D2 vblank\n");
+
 				break;
 			case 1: /* D1 vline */
-				if (rdev->irq.stat_regs.r600.disp_int & LB_D2_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int &= ~LB_D2_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D2 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int & LB_D2_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D2 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int &= ~LB_D2_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D2 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -4148,46 +4156,53 @@
 		case 19: /* HPD/DAC hotplug */
 			switch (src_data) {
 			case 0:
-				if (rdev->irq.stat_regs.r600.disp_int & DC_HPD1_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int &= ~DC_HPD1_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD1\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int & DC_HPD1_INTERRUPT))
+					DRM_DEBUG("IH: HPD1 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int &= ~DC_HPD1_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD1\n");
 				break;
 			case 1:
-				if (rdev->irq.stat_regs.r600.disp_int & DC_HPD2_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int &= ~DC_HPD2_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD2\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int & DC_HPD2_INTERRUPT))
+					DRM_DEBUG("IH: HPD2 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int &= ~DC_HPD2_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD2\n");
 				break;
 			case 4:
-				if (rdev->irq.stat_regs.r600.disp_int_cont & DC_HPD3_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int_cont &= ~DC_HPD3_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD3\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int_cont & DC_HPD3_INTERRUPT))
+					DRM_DEBUG("IH: HPD3 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int_cont &= ~DC_HPD3_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD3\n");
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.r600.disp_int_cont & DC_HPD4_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int_cont &= ~DC_HPD4_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD4\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int_cont & DC_HPD4_INTERRUPT))
+					DRM_DEBUG("IH: HPD4 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int_cont &= ~DC_HPD4_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD4\n");
 				break;
 			case 10:
-				if (rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD5_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int_cont2 &= ~DC_HPD5_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD5\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD5_INTERRUPT))
+					DRM_DEBUG("IH: HPD5 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int_cont2 &= ~DC_HPD5_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD5\n");
 				break;
 			case 12:
-				if (rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD6_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int_cont2 &= ~DC_HPD6_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD6\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD6_INTERRUPT))
+					DRM_DEBUG("IH: HPD6 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int_cont2 &= ~DC_HPD6_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD6\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -4197,18 +4212,22 @@
 		case 21: /* hdmi */
 			switch (src_data) {
 			case 4:
-				if (rdev->irq.stat_regs.r600.hdmi0_status & HDMI0_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.r600.hdmi0_status &= ~HDMI0_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI0\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.hdmi0_status & HDMI0_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: HDMI0 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.hdmi0_status &= ~HDMI0_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI0\n");
+
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.r600.hdmi1_status & HDMI0_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.r600.hdmi1_status &= ~HDMI0_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI1\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.hdmi1_status & HDMI0_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: HDMI1 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.hdmi1_status &= ~HDMI0_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI1\n");
+
 				break;
 			default:
 				DRM_ERROR("Unhandled interrupt: %d %d\n", src_id, src_data);
diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c
index 09e3f39..98f9ada 100644
--- a/drivers/gpu/drm/radeon/r600_cp.c
+++ b/drivers/gpu/drm/radeon/r600_cp.c
@@ -2483,7 +2483,7 @@
 	struct drm_buf *buf;
 	u32 *buffer;
 	const u8 __user *data;
-	int size, pass_size;
+	unsigned int size, pass_size;
 	u64 src_offset, dst_offset;
 
 	if (!radeon_check_offset(dev_priv, tex->offset)) {
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index 45e5406..afaf346 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -91,15 +91,34 @@
 	struct radeon_device *rdev = crtc->dev->dev_private;
 
 	if (ASIC_IS_DCE4(rdev)) {
+		WREG32(EVERGREEN_CUR_SURFACE_ADDRESS_HIGH + radeon_crtc->crtc_offset,
+		       upper_32_bits(radeon_crtc->cursor_addr));
+		WREG32(EVERGREEN_CUR_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
+		       lower_32_bits(radeon_crtc->cursor_addr));
 		WREG32(RADEON_MM_INDEX, EVERGREEN_CUR_CONTROL + radeon_crtc->crtc_offset);
 		WREG32(RADEON_MM_DATA, EVERGREEN_CURSOR_EN |
 		       EVERGREEN_CURSOR_MODE(EVERGREEN_CURSOR_24_8_PRE_MULT) |
 		       EVERGREEN_CURSOR_URGENT_CONTROL(EVERGREEN_CURSOR_URGENT_1_2));
 	} else if (ASIC_IS_AVIVO(rdev)) {
+		if (rdev->family >= CHIP_RV770) {
+			if (radeon_crtc->crtc_id)
+				WREG32(R700_D2CUR_SURFACE_ADDRESS_HIGH,
+				       upper_32_bits(radeon_crtc->cursor_addr));
+			else
+				WREG32(R700_D1CUR_SURFACE_ADDRESS_HIGH,
+				       upper_32_bits(radeon_crtc->cursor_addr));
+		}
+
+		WREG32(AVIVO_D1CUR_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
+		       lower_32_bits(radeon_crtc->cursor_addr));
 		WREG32(RADEON_MM_INDEX, AVIVO_D1CUR_CONTROL + radeon_crtc->crtc_offset);
 		WREG32(RADEON_MM_DATA, AVIVO_D1CURSOR_EN |
 		       (AVIVO_D1CURSOR_MODE_24BPP << AVIVO_D1CURSOR_MODE_SHIFT));
 	} else {
+		/* offset is from DISP(2)_BASE_ADDRESS */
+		WREG32(RADEON_CUR_OFFSET + radeon_crtc->crtc_offset,
+		       radeon_crtc->cursor_addr - radeon_crtc->legacy_display_base_addr);
+
 		switch (radeon_crtc->crtc_id) {
 		case 0:
 			WREG32(RADEON_MM_INDEX, RADEON_CRTC_GEN_CNTL);
@@ -205,8 +224,9 @@
 			| (x << 16)
 			| y));
 		/* offset is from DISP(2)_BASE_ADDRESS */
-		WREG32(RADEON_CUR_OFFSET + radeon_crtc->crtc_offset, (radeon_crtc->legacy_cursor_offset +
-								      (yorigin * 256)));
+		WREG32(RADEON_CUR_OFFSET + radeon_crtc->crtc_offset,
+		       radeon_crtc->cursor_addr - radeon_crtc->legacy_display_base_addr +
+		       yorigin * 256);
 	}
 
 	radeon_crtc->cursor_x = x;
@@ -227,53 +247,6 @@
 	return ret;
 }
 
-static int radeon_set_cursor(struct drm_crtc *crtc, struct drm_gem_object *obj)
-{
-	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
-	struct radeon_device *rdev = crtc->dev->dev_private;
-	struct radeon_bo *robj = gem_to_radeon_bo(obj);
-	uint64_t gpu_addr;
-	int ret;
-
-	ret = radeon_bo_reserve(robj, false);
-	if (unlikely(ret != 0))
-		goto fail;
-	/* Only 27 bit offset for legacy cursor */
-	ret = radeon_bo_pin_restricted(robj, RADEON_GEM_DOMAIN_VRAM,
-				       ASIC_IS_AVIVO(rdev) ? 0 : 1 << 27,
-				       &gpu_addr);
-	radeon_bo_unreserve(robj);
-	if (ret)
-		goto fail;
-
-	if (ASIC_IS_DCE4(rdev)) {
-		WREG32(EVERGREEN_CUR_SURFACE_ADDRESS_HIGH + radeon_crtc->crtc_offset,
-		       upper_32_bits(gpu_addr));
-		WREG32(EVERGREEN_CUR_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
-		       gpu_addr & 0xffffffff);
-	} else if (ASIC_IS_AVIVO(rdev)) {
-		if (rdev->family >= CHIP_RV770) {
-			if (radeon_crtc->crtc_id)
-				WREG32(R700_D2CUR_SURFACE_ADDRESS_HIGH, upper_32_bits(gpu_addr));
-			else
-				WREG32(R700_D1CUR_SURFACE_ADDRESS_HIGH, upper_32_bits(gpu_addr));
-		}
-		WREG32(AVIVO_D1CUR_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
-		       gpu_addr & 0xffffffff);
-	} else {
-		radeon_crtc->legacy_cursor_offset = gpu_addr - radeon_crtc->legacy_display_base_addr;
-		/* offset is from DISP(2)_BASE_ADDRESS */
-		WREG32(RADEON_CUR_OFFSET + radeon_crtc->crtc_offset, radeon_crtc->legacy_cursor_offset);
-	}
-
-	return 0;
-
-fail:
-	drm_gem_object_unreference_unlocked(obj);
-
-	return ret;
-}
-
 int radeon_crtc_cursor_set2(struct drm_crtc *crtc,
 			    struct drm_file *file_priv,
 			    uint32_t handle,
@@ -283,7 +256,9 @@
 			    int32_t hot_y)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
+	struct radeon_device *rdev = crtc->dev->dev_private;
 	struct drm_gem_object *obj;
+	struct radeon_bo *robj;
 	int ret;
 
 	if (!handle) {
@@ -305,6 +280,23 @@
 		return -ENOENT;
 	}
 
+	robj = gem_to_radeon_bo(obj);
+	ret = radeon_bo_reserve(robj, false);
+	if (ret != 0) {
+		drm_gem_object_unreference_unlocked(obj);
+		return ret;
+	}
+	/* Only 27 bit offset for legacy cursor */
+	ret = radeon_bo_pin_restricted(robj, RADEON_GEM_DOMAIN_VRAM,
+				       ASIC_IS_AVIVO(rdev) ? 0 : 1 << 27,
+				       &radeon_crtc->cursor_addr);
+	radeon_bo_unreserve(robj);
+	if (ret) {
+		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
+		drm_gem_object_unreference_unlocked(obj);
+		return ret;
+	}
+
 	radeon_crtc->cursor_width = width;
 	radeon_crtc->cursor_height = height;
 
@@ -323,13 +315,7 @@
 		radeon_crtc->cursor_hot_y = hot_y;
 	}
 
-	ret = radeon_set_cursor(crtc, obj);
-
-	if (ret)
-		DRM_ERROR("radeon_set_cursor returned %d, not changing cursor\n",
-			  ret);
-	else
-		radeon_show_cursor(crtc);
+	radeon_show_cursor(crtc);
 
 	radeon_lock_cursor(crtc, false);
 
@@ -341,8 +327,7 @@
 			radeon_bo_unpin(robj);
 			radeon_bo_unreserve(robj);
 		}
-		if (radeon_crtc->cursor_bo != obj)
-			drm_gem_object_unreference_unlocked(radeon_crtc->cursor_bo);
+		drm_gem_object_unreference_unlocked(radeon_crtc->cursor_bo);
 	}
 
 	radeon_crtc->cursor_bo = obj;
@@ -360,7 +345,6 @@
 void radeon_cursor_reset(struct drm_crtc *crtc)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
-	int ret;
 
 	if (radeon_crtc->cursor_bo) {
 		radeon_lock_cursor(crtc, true);
@@ -368,12 +352,7 @@
 		radeon_cursor_move_locked(crtc, radeon_crtc->cursor_x,
 					  radeon_crtc->cursor_y);
 
-		ret = radeon_set_cursor(crtc, radeon_crtc->cursor_bo);
-		if (ret)
-			DRM_ERROR("radeon_set_cursor returned %d, not showing "
-				  "cursor\n", ret);
-		else
-			radeon_show_cursor(crtc);
+		radeon_show_cursor(crtc);
 
 		radeon_lock_cursor(crtc, false);
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 2593b11..d8319da 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1080,6 +1080,22 @@
 }
 
 /**
+ * Determine a sensible default GART size according to ASIC family.
+ *
+ * @family ASIC family name
+ */
+static int radeon_gart_size_auto(enum radeon_family family)
+{
+	/* default to a larger gart size on newer asics */
+	if (family >= CHIP_TAHITI)
+		return 2048;
+	else if (family >= CHIP_RV770)
+		return 1024;
+	else
+		return 512;
+}
+
+/**
  * radeon_check_arguments - validate module params
  *
  * @rdev: radeon_device pointer
@@ -1097,27 +1113,17 @@
 	}
 
 	if (radeon_gart_size == -1) {
-		/* default to a larger gart size on newer asics */
-		if (rdev->family >= CHIP_RV770)
-			radeon_gart_size = 1024;
-		else
-			radeon_gart_size = 512;
+		radeon_gart_size = radeon_gart_size_auto(rdev->family);
 	}
 	/* gtt size must be power of two and greater or equal to 32M */
 	if (radeon_gart_size < 32) {
 		dev_warn(rdev->dev, "gart size (%d) too small\n",
 				radeon_gart_size);
-		if (rdev->family >= CHIP_RV770)
-			radeon_gart_size = 1024;
-		else
-			radeon_gart_size = 512;
+		radeon_gart_size = radeon_gart_size_auto(rdev->family);
 	} else if (!radeon_check_pot_argument(radeon_gart_size)) {
 		dev_warn(rdev->dev, "gart size (%d) must be a power of 2\n",
 				radeon_gart_size);
-		if (rdev->family >= CHIP_RV770)
-			radeon_gart_size = 1024;
-		else
-			radeon_gart_size = 512;
+		radeon_gart_size = radeon_gart_size_auto(rdev->family);
 	}
 	rdev->mc.gtt_size = (uint64_t)radeon_gart_size << 20;
 
@@ -1572,11 +1578,21 @@
 		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
 	}
 
-	/* unpin the front buffers */
+	/* unpin the front buffers and cursors */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 		struct radeon_framebuffer *rfb = to_radeon_framebuffer(crtc->primary->fb);
 		struct radeon_bo *robj;
 
+		if (radeon_crtc->cursor_bo) {
+			struct radeon_bo *robj = gem_to_radeon_bo(radeon_crtc->cursor_bo);
+			r = radeon_bo_reserve(robj, false);
+			if (r == 0) {
+				radeon_bo_unpin(robj);
+				radeon_bo_unreserve(robj);
+			}
+		}
+
 		if (rfb == NULL || rfb->obj == NULL) {
 			continue;
 		}
@@ -1639,6 +1655,7 @@
 {
 	struct drm_connector *connector;
 	struct radeon_device *rdev = dev->dev_private;
+	struct drm_crtc *crtc;
 	int r;
 
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
@@ -1678,6 +1695,27 @@
 
 	radeon_restore_bios_scratch_regs(rdev);
 
+	/* pin cursors */
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
+
+		if (radeon_crtc->cursor_bo) {
+			struct radeon_bo *robj = gem_to_radeon_bo(radeon_crtc->cursor_bo);
+			r = radeon_bo_reserve(robj, false);
+			if (r == 0) {
+				/* Only 27 bit offset for legacy cursor */
+				r = radeon_bo_pin_restricted(robj,
+							     RADEON_GEM_DOMAIN_VRAM,
+							     ASIC_IS_AVIVO(rdev) ?
+							     0 : 1 << 27,
+							     &radeon_crtc->cursor_addr);
+				if (r != 0)
+					DRM_ERROR("Failed to pin cursor BO (%d)\n", r);
+				radeon_bo_unreserve(robj);
+			}
+		}
+	}
+
 	/* init dig PHYs, disp eng pll */
 	if (rdev->is_atom_bios) {
 		radeon_atom_encoder_init(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 634793e..aeb6767 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -257,6 +257,7 @@
 	}
 
 	info->par = rfbdev;
+	info->skip_vt_switch = true;
 
 	ret = radeon_framebuffer_init(rdev->ddev, &rfbdev->rfb, &mode_cmd, gobj);
 	if (ret) {
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index ac3c131..013ec71 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -428,7 +428,6 @@
 int radeon_gem_busy_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp)
 {
-	struct radeon_device *rdev = dev->dev_private;
 	struct drm_radeon_gem_busy *args = data;
 	struct drm_gem_object *gobj;
 	struct radeon_bo *robj;
@@ -440,10 +439,16 @@
 		return -ENOENT;
 	}
 	robj = gem_to_radeon_bo(gobj);
-	r = radeon_bo_wait(robj, &cur_placement, true);
+
+	r = reservation_object_test_signaled_rcu(robj->tbo.resv, true);
+	if (r == 0)
+		r = -EBUSY;
+	else
+		r = 0;
+
+	cur_placement = ACCESS_ONCE(robj->tbo.mem.mem_type);
 	args->domain = radeon_mem_type_to_domain(cur_placement);
 	drm_gem_object_unreference_unlocked(gobj);
-	r = radeon_gem_handle_lockup(rdev, r);
 	return r;
 }
 
@@ -471,6 +476,7 @@
 		r = ret;
 
 	/* Flush HDP cache via MMIO if necessary */
+	cur_placement = ACCESS_ONCE(robj->tbo.mem.mem_type);
 	if (rdev->asic->mmio_hdp_flush &&
 	    radeon_mem_type_to_domain(cur_placement) == RADEON_GEM_DOMAIN_VRAM)
 		robj->rdev->asic->mmio_hdp_flush(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 6de5459..07909d8 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -343,7 +343,6 @@
 	int max_cursor_width;
 	int max_cursor_height;
 	uint32_t legacy_display_base_addr;
-	uint32_t legacy_cursor_offset;
 	enum radeon_rmx_type rmx_type;
 	u8 h_border;
 	u8 v_border;
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index ec10533..48d97c0 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -493,38 +493,35 @@
 	}
 
 	if (bo_va->it.start || bo_va->it.last) {
-		spin_lock(&vm->status_lock);
-		if (list_empty(&bo_va->vm_status)) {
-			/* add a clone of the bo_va to clear the old address */
-			struct radeon_bo_va *tmp;
-			spin_unlock(&vm->status_lock);
-			tmp = kzalloc(sizeof(struct radeon_bo_va), GFP_KERNEL);
-			if (!tmp) {
-				mutex_unlock(&vm->mutex);
-				r = -ENOMEM;
-				goto error_unreserve;
-			}
-			tmp->it.start = bo_va->it.start;
-			tmp->it.last = bo_va->it.last;
-			tmp->vm = vm;
-			tmp->bo = radeon_bo_ref(bo_va->bo);
-			spin_lock(&vm->status_lock);
-			list_add(&tmp->vm_status, &vm->freed);
+		/* add a clone of the bo_va to clear the old address */
+		struct radeon_bo_va *tmp;
+		tmp = kzalloc(sizeof(struct radeon_bo_va), GFP_KERNEL);
+		if (!tmp) {
+			mutex_unlock(&vm->mutex);
+			r = -ENOMEM;
+			goto error_unreserve;
 		}
-		spin_unlock(&vm->status_lock);
+		tmp->it.start = bo_va->it.start;
+		tmp->it.last = bo_va->it.last;
+		tmp->vm = vm;
+		tmp->bo = radeon_bo_ref(bo_va->bo);
 
 		interval_tree_remove(&bo_va->it, &vm->va);
+		spin_lock(&vm->status_lock);
 		bo_va->it.start = 0;
 		bo_va->it.last = 0;
+		list_del_init(&bo_va->vm_status);
+		list_add(&tmp->vm_status, &vm->freed);
+		spin_unlock(&vm->status_lock);
 	}
 
 	if (soffset || eoffset) {
+		spin_lock(&vm->status_lock);
 		bo_va->it.start = soffset;
 		bo_va->it.last = eoffset - 1;
-		interval_tree_insert(&bo_va->it, &vm->va);
-		spin_lock(&vm->status_lock);
 		list_add(&bo_va->vm_status, &vm->cleared);
 		spin_unlock(&vm->status_lock);
+		interval_tree_insert(&bo_va->it, &vm->va);
 	}
 
 	bo_va->flags = flags;
@@ -1158,7 +1155,8 @@
 
 	list_for_each_entry(bo_va, &bo->va, bo_list) {
 		spin_lock(&bo_va->vm->status_lock);
-		if (list_empty(&bo_va->vm_status))
+		if (list_empty(&bo_va->vm_status) &&
+		    (bo_va->it.start || bo_va->it.last))
 			list_add(&bo_va->vm_status, &bo_va->vm->invalidated);
 		spin_unlock(&bo_va->vm->status_lock);
 	}
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 26388b5..07037e3 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -6466,23 +6466,27 @@
 		case 1: /* D1 vblank/vline */
 			switch (src_data) {
 			case 0: /* D1 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[0]) {
-						drm_handle_vblank(rdev->ddev, 0);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_vblank(rdev, 0);
-					rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D1 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[0]) {
+					drm_handle_vblank(rdev->ddev, 0);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[0]))
+					radeon_crtc_handle_vblank(rdev, 0);
+				rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D1 vblank\n");
+
 				break;
 			case 1: /* D1 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D1 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D1 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6492,23 +6496,27 @@
 		case 2: /* D2 vblank/vline */
 			switch (src_data) {
 			case 0: /* D2 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[1]) {
-						drm_handle_vblank(rdev->ddev, 1);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_vblank(rdev, 1);
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D2 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[1]) {
+					drm_handle_vblank(rdev->ddev, 1);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[1]))
+					radeon_crtc_handle_vblank(rdev, 1);
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D2 vblank\n");
+
 				break;
 			case 1: /* D2 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D2 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D2 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6518,23 +6526,27 @@
 		case 3: /* D3 vblank/vline */
 			switch (src_data) {
 			case 0: /* D3 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[2]) {
-						drm_handle_vblank(rdev->ddev, 2);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[2]))
-						radeon_crtc_handle_vblank(rdev, 2);
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D3 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[2]) {
+					drm_handle_vblank(rdev->ddev, 2);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[2]))
+					radeon_crtc_handle_vblank(rdev, 2);
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D3 vblank\n");
+
 				break;
 			case 1: /* D3 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D3 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D3 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6544,23 +6556,27 @@
 		case 4: /* D4 vblank/vline */
 			switch (src_data) {
 			case 0: /* D4 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[3]) {
-						drm_handle_vblank(rdev->ddev, 3);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[3]))
-						radeon_crtc_handle_vblank(rdev, 3);
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D4 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[3]) {
+					drm_handle_vblank(rdev->ddev, 3);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[3]))
+					radeon_crtc_handle_vblank(rdev, 3);
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D4 vblank\n");
+
 				break;
 			case 1: /* D4 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D4 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D4 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6570,23 +6586,27 @@
 		case 5: /* D5 vblank/vline */
 			switch (src_data) {
 			case 0: /* D5 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[4]) {
-						drm_handle_vblank(rdev->ddev, 4);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[4]))
-						radeon_crtc_handle_vblank(rdev, 4);
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D5 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[4]) {
+					drm_handle_vblank(rdev->ddev, 4);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[4]))
+					radeon_crtc_handle_vblank(rdev, 4);
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D5 vblank\n");
+
 				break;
 			case 1: /* D5 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D5 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D5 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6596,23 +6616,27 @@
 		case 6: /* D6 vblank/vline */
 			switch (src_data) {
 			case 0: /* D6 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[5]) {
-						drm_handle_vblank(rdev->ddev, 5);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[5]))
-						radeon_crtc_handle_vblank(rdev, 5);
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D6 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[5]) {
+					drm_handle_vblank(rdev->ddev, 5);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[5]))
+					radeon_crtc_handle_vblank(rdev, 5);
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D6 vblank\n");
+
 				break;
 			case 1: /* D6 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D6 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D6 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6632,88 +6656,112 @@
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
-				if (rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD1\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD1\n");
+
 				break;
 			case 1:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD2\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD2\n");
+
 				break;
 			case 2:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD3\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD3\n");
+
 				break;
 			case 3:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD4\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD4\n");
+
 				break;
 			case 4:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD5\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD5\n");
+
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD6\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD6\n");
+
 				break;
 			case 6:
-				if (rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 1\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 1\n");
+
 				break;
 			case 7:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 2\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 2\n");
+
 				break;
 			case 8:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 3\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 3\n");
+
 				break;
 			case 9:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 4\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 4\n");
+
 				break;
 			case 10:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 5\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 5\n");
+
 				break;
 			case 11:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 6\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 6\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 35ac237..577d58d 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -633,6 +633,7 @@
 config I2C_MT65XX
 	tristate "MediaTek I2C adapter"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
+	depends on HAS_DMA
 	help
 	  This selects the MediaTek(R) Integrated Inter Circuit bus driver
 	  for MT65xx and MT81xx.
diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c
index 19b2d68..f325663 100644
--- a/drivers/i2c/busses/i2c-jz4780.c
+++ b/drivers/i2c/busses/i2c-jz4780.c
@@ -764,12 +764,15 @@
 	if (IS_ERR(i2c->clk))
 		return PTR_ERR(i2c->clk);
 
-	clk_prepare_enable(i2c->clk);
+	ret = clk_prepare_enable(i2c->clk);
+	if (ret)
+		return ret;
 
-	if (of_property_read_u32(pdev->dev.of_node, "clock-frequency",
-				 &clk_freq)) {
+	ret = of_property_read_u32(pdev->dev.of_node, "clock-frequency",
+				   &clk_freq);
+	if (ret) {
 		dev_err(&pdev->dev, "clock-frequency not specified in DT");
-		return clk_freq;
+		goto err;
 	}
 
 	i2c->speed = clk_freq / 1000;
@@ -790,10 +793,8 @@
 	i2c->irq = platform_get_irq(pdev, 0);
 	ret = devm_request_irq(&pdev->dev, i2c->irq, jz4780_i2c_irq, 0,
 			       dev_name(&pdev->dev), i2c);
-	if (ret) {
-		ret = -ENODEV;
+	if (ret)
 		goto err;
-	}
 
 	ret = i2c_add_adapter(&i2c->adap);
 	if (ret < 0) {
diff --git a/drivers/i2c/busses/i2c-xgene-slimpro.c b/drivers/i2c/busses/i2c-xgene-slimpro.c
index dcca707..1c9cb65 100644
--- a/drivers/i2c/busses/i2c-xgene-slimpro.c
+++ b/drivers/i2c/busses/i2c-xgene-slimpro.c
@@ -419,6 +419,7 @@
 	rc = i2c_add_adapter(adapter);
 	if (rc) {
 		dev_err(&pdev->dev, "Adapter registeration failed\n");
+		mbox_free_channel(ctx->mbox_chan);
 		return rc;
 	}
 
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 069a41f..e6d4935 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -1012,6 +1012,8 @@
  */
 void i2c_unregister_device(struct i2c_client *client)
 {
+	if (client->dev.of_node)
+		of_node_clear_flag(client->dev.of_node, OF_POPULATED);
 	device_unregister(&client->dev);
 }
 EXPORT_SYMBOL_GPL(i2c_unregister_device);
@@ -1320,8 +1322,11 @@
 
 	dev_dbg(&adap->dev, "of_i2c: walking child nodes\n");
 
-	for_each_available_child_of_node(adap->dev.of_node, node)
+	for_each_available_child_of_node(adap->dev.of_node, node) {
+		if (of_node_test_and_set_flag(node, OF_POPULATED))
+			continue;
 		of_i2c_register_device(adap, node);
+	}
 }
 
 static int of_dev_node_match(struct device *dev, void *data)
@@ -1853,6 +1858,11 @@
 		if (adap == NULL)
 			return NOTIFY_OK;	/* not for us */
 
+		if (of_node_test_and_set_flag(rd->dn, OF_POPULATED)) {
+			put_device(&adap->dev);
+			return NOTIFY_OK;
+		}
+
 		client = of_i2c_register_device(adap, rd->dn);
 		put_device(&adap->dev);
 
@@ -1863,6 +1873,10 @@
 		}
 		break;
 	case OF_RECONFIG_CHANGE_REMOVE:
+		/* already depopulated? */
+		if (!of_node_check_flag(rd->dn, OF_POPULATED))
+			return NOTIFY_OK;
+
 		/* find our device by node */
 		client = of_find_i2c_device_by_node(rd->dn);
 		if (client == NULL)
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 62641f2..5b5f403 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -771,7 +771,7 @@
  */
 static void elan_report_contact(struct elan_tp_data *data,
 				int contact_num, bool contact_valid,
-				bool hover_event, u8 *finger_data)
+				u8 *finger_data)
 {
 	struct input_dev *input = data->input;
 	unsigned int pos_x, pos_y;
@@ -815,9 +815,7 @@
 		input_mt_report_slot_state(input, MT_TOOL_FINGER, true);
 		input_report_abs(input, ABS_MT_POSITION_X, pos_x);
 		input_report_abs(input, ABS_MT_POSITION_Y, data->max_y - pos_y);
-		input_report_abs(input, ABS_MT_DISTANCE, hover_event);
-		input_report_abs(input, ABS_MT_PRESSURE,
-				 hover_event ? 0 : scaled_pressure);
+		input_report_abs(input, ABS_MT_PRESSURE, scaled_pressure);
 		input_report_abs(input, ABS_TOOL_WIDTH, mk_x);
 		input_report_abs(input, ABS_MT_TOUCH_MAJOR, major);
 		input_report_abs(input, ABS_MT_TOUCH_MINOR, minor);
@@ -839,14 +837,14 @@
 	hover_event = hover_info & 0x40;
 	for (i = 0; i < ETP_MAX_FINGERS; i++) {
 		contact_valid = tp_info & (1U << (3 + i));
-		elan_report_contact(data, i, contact_valid, hover_event,
-				    finger_data);
+		elan_report_contact(data, i, contact_valid, finger_data);
 
 		if (contact_valid)
 			finger_data += ETP_FINGER_DATA_LEN;
 	}
 
 	input_report_key(input, BTN_LEFT, tp_info & 0x01);
+	input_report_abs(input, ABS_DISTANCE, hover_event != 0);
 	input_mt_report_pointer_emulation(input, true);
 	input_sync(input);
 }
@@ -922,6 +920,7 @@
 	input_abs_set_res(input, ABS_Y, data->y_res);
 	input_set_abs_params(input, ABS_PRESSURE, 0, ETP_MAX_PRESSURE, 0, 0);
 	input_set_abs_params(input, ABS_TOOL_WIDTH, 0, ETP_FINGER_WIDTH, 0, 0);
+	input_set_abs_params(input, ABS_DISTANCE, 0, 1, 0, 0);
 
 	/* And MT parameters */
 	input_set_abs_params(input, ABS_MT_POSITION_X, 0, data->max_x, 0, 0);
@@ -934,7 +933,6 @@
 			     ETP_FINGER_WIDTH * max_width, 0, 0);
 	input_set_abs_params(input, ABS_MT_TOUCH_MINOR, 0,
 			     ETP_FINGER_WIDTH * min_width, 0, 0);
-	input_set_abs_params(input, ABS_MT_DISTANCE, 0, 1, 0, 0);
 
 	data->input = input;
 
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 35c8d0c..3a32caf 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -1199,7 +1199,7 @@
 					ABS_MT_POSITION_Y);
 		/* Image sensors can report per-contact pressure */
 		input_set_abs_params(dev, ABS_MT_PRESSURE, 0, 255, 0, 0);
-		input_mt_init_slots(dev, 3, INPUT_MT_POINTER | INPUT_MT_TRACK);
+		input_mt_init_slots(dev, 2, INPUT_MT_POINTER | INPUT_MT_TRACK);
 
 		/* Image sensors can signal 4 and 5 finger clicks */
 		__set_bit(BTN_TOOL_QUADTAP, dev->keybit);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 8d7e1c8..4dd8826 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1055,7 +1055,7 @@
 
 	processor = (struct acpi_madt_generic_interrupt *)header;
 
-	if (BAD_MADT_ENTRY(processor, end))
+	if (BAD_MADT_GICC_ENTRY(processor, end))
 		return -EINVAL;
 
 	/*
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 4400edd..b7d54d4 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -257,16 +257,6 @@
 		return MIPS_CPU_IRQ_BASE + cp0_fdc_irq;
 	}
 
-	/*
-	 * Some cores claim the FDC is routable but it doesn't actually seem to
-	 * be connected.
-	 */
-	switch (current_cpu_type()) {
-	case CPU_INTERAPTIV:
-	case CPU_PROAPTIV:
-		return -1;
-	}
-
 	return irq_create_mapping(gic_irq_domain,
 				  GIC_LOCAL_TO_HWIRQ(GIC_LOCAL_INT_FDC));
 }
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index 8911e51..3a27a84 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -2074,14 +2074,8 @@
 			ret = gpmc_probe_nand_child(pdev, child);
 		else if (of_node_cmp(child->name, "onenand") == 0)
 			ret = gpmc_probe_onenand_child(pdev, child);
-		else if (of_node_cmp(child->name, "ethernet") == 0 ||
-			 of_node_cmp(child->name, "nor") == 0 ||
-			 of_node_cmp(child->name, "uart") == 0)
+		else
 			ret = gpmc_probe_generic_child(pdev, child);
-
-		if (WARN(ret < 0, "%s: probing gpmc child %s failed\n",
-			 __func__, child->full_name))
-			of_node_put(child);
 	}
 
 	return 0;
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 0c77240..729e085 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -23,6 +23,7 @@
 
 	afu = cxl_pci_to_afu(dev);
 
+	get_device(&afu->dev);
 	ctx = cxl_context_alloc();
 	if (IS_ERR(ctx))
 		return ctx;
@@ -31,6 +32,7 @@
 	rc = cxl_context_init(ctx, afu, false, NULL);
 	if (rc) {
 		kfree(ctx);
+		put_device(&afu->dev);
 		return ERR_PTR(-ENOMEM);
 	}
 	cxl_assign_psn_space(ctx);
@@ -60,6 +62,8 @@
 	if (ctx->status != CLOSED)
 		return -EBUSY;
 
+	put_device(&ctx->afu->dev);
+
 	cxl_context_free(ctx);
 
 	return 0;
@@ -159,7 +163,6 @@
 	}
 
 	ctx->status = STARTED;
-	get_device(&ctx->afu->dev);
 out:
 	mutex_unlock(&ctx->status_mutex);
 	return rc;
@@ -175,12 +178,7 @@
 /* Stop a context.  Returns 0 on success, otherwise -Errno */
 int cxl_stop_context(struct cxl_context *ctx)
 {
-	int rc;
-
-	rc = __detach_context(ctx);
-	if (!rc)
-		put_device(&ctx->afu->dev);
-	return rc;
+	return __detach_context(ctx);
 }
 EXPORT_SYMBOL_GPL(cxl_stop_context);
 
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index 2a4c80a..1287148 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -113,11 +113,11 @@
 
 	if (ctx->afu->current_mode == CXL_MODE_DEDICATED) {
 		area = ctx->afu->psn_phys;
-		if (offset > ctx->afu->adapter->ps_size)
+		if (offset >= ctx->afu->adapter->ps_size)
 			return VM_FAULT_SIGBUS;
 	} else {
 		area = ctx->psn_phys;
-		if (offset > ctx->psn_size)
+		if (offset >= ctx->psn_size)
 			return VM_FAULT_SIGBUS;
 	}
 
@@ -145,8 +145,16 @@
  */
 int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma)
 {
+	u64 start = vma->vm_pgoff << PAGE_SHIFT;
 	u64 len = vma->vm_end - vma->vm_start;
-	len = min(len, ctx->psn_size);
+
+	if (ctx->afu->current_mode == CXL_MODE_DEDICATED) {
+		if (start + len > ctx->afu->adapter->ps_size)
+			return -EINVAL;
+	} else {
+		if (start + len > ctx->psn_size)
+			return -EINVAL;
+	}
 
 	if (ctx->afu->current_mode != CXL_MODE_DEDICATED) {
 		/* make sure there is a valid per process space for this AFU */
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
index 833348e..4a164ab 100644
--- a/drivers/misc/cxl/main.c
+++ b/drivers/misc/cxl/main.c
@@ -73,7 +73,7 @@
 		spin_lock(&adapter->afu_list_lock);
 		for (slice = 0; slice < adapter->slices; slice++) {
 			afu = adapter->afu[slice];
-			if (!afu->enabled)
+			if (!afu || !afu->enabled)
 				continue;
 			rcu_read_lock();
 			idr_for_each_entry(&afu->contexts_idr, ctx, id)
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index c68ef58..32ad097 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -539,7 +539,7 @@
 
 static void cxl_unmap_slice_regs(struct cxl_afu *afu)
 {
-	if (afu->p1n_mmio)
+	if (afu->p2n_mmio)
 		iounmap(afu->p2n_mmio);
 	if (afu->p1n_mmio)
 		iounmap(afu->p1n_mmio);
diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c
index b1d1983a..2eba002 100644
--- a/drivers/misc/cxl/vphb.c
+++ b/drivers/misc/cxl/vphb.c
@@ -112,9 +112,10 @@
 	unsigned long addr;
 
 	phb = pci_bus_to_host(bus);
-	afu = (struct cxl_afu *)phb->private_data;
 	if (phb == NULL)
 		return PCIBIOS_DEVICE_NOT_FOUND;
+	afu = (struct cxl_afu *)phb->private_data;
+
 	if (cxl_pcie_cfg_record(bus->number, devfn) > afu->crs_num)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	if (offset >= (unsigned long)phb->cfg_data)
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 357b6ae..458aa5a 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -552,22 +552,6 @@
 	schedule_work(&device->event_work);
 }
 
-void mei_cl_bus_remove_devices(struct mei_device *dev)
-{
-	struct mei_cl *cl, *next;
-
-	mutex_lock(&dev->device_lock);
-	list_for_each_entry_safe(cl, next, &dev->device_list, device_link) {
-		if (cl->device)
-			mei_cl_remove_device(cl->device);
-
-		list_del(&cl->device_link);
-		mei_cl_unlink(cl);
-		kfree(cl);
-	}
-	mutex_unlock(&dev->device_lock);
-}
-
 int __init mei_cl_bus_init(void)
 {
 	return bus_register(&mei_cl_bus_type);
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index 94514b2..00c3865 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -333,8 +333,6 @@
 
 	mei_nfc_host_exit(dev);
 
-	mei_cl_bus_remove_devices(dev);
-
 	mutex_lock(&dev->device_lock);
 
 	mei_wd_stop(dev);
diff --git a/drivers/misc/mei/nfc.c b/drivers/misc/mei/nfc.c
index b983c4e..290ef30 100644
--- a/drivers/misc/mei/nfc.c
+++ b/drivers/misc/mei/nfc.c
@@ -402,11 +402,12 @@
 
 	cldev->priv_data = NULL;
 
-	mutex_lock(&dev->device_lock);
 	/* Need to remove the device here
 	 * since mei_nfc_free will unlink the clients
 	 */
 	mei_cl_remove_device(cldev);
+
+	mutex_lock(&dev->device_lock);
 	mei_nfc_free(ndev);
 	mutex_unlock(&dev->device_lock);
 }
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 8eb22c0..7e2c43f 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -535,8 +535,6 @@
 					__func__, dimm_name, cmd_name, i);
 			return -ENXIO;
 		}
-		if (!access_ok(VERIFY_READ, p + in_len, in_size))
-			return -EFAULT;
 		if (in_len < sizeof(in_env))
 			copy = min_t(u32, sizeof(in_env) - in_len, in_size);
 		else
@@ -557,8 +555,6 @@
 					__func__, dimm_name, cmd_name, i);
 			return -EFAULT;
 		}
-		if (!access_ok(VERIFY_WRITE, p + in_len + out_len, out_size))
-			return -EFAULT;
 		if (out_len < sizeof(out_env))
 			copy = min_t(u32, sizeof(out_env) - out_len, out_size);
 		else
@@ -570,9 +566,6 @@
 	}
 
 	buf_len = out_len + in_len;
-	if (!access_ok(VERIFY_WRITE, p, sizeof(buf_len)))
-		return -EFAULT;
-
 	if (buf_len > ND_IOCTL_MAX_BUFLEN) {
 		dev_dbg(dev, "%s:%s cmd: %s buf_len: %zu > %d\n", __func__,
 				dimm_name, cmd_name, buf_len,
@@ -706,8 +699,10 @@
 	nvdimm_major = rc;
 
 	nd_class = class_create(THIS_MODULE, "nd");
-	if (IS_ERR(nd_class))
+	if (IS_ERR(nd_class)) {
+		rc = PTR_ERR(nd_class);
 		goto err_class;
+	}
 
 	return 0;
 
diff --git a/drivers/pnp/system.c b/drivers/pnp/system.c
index 515f338..49c1720 100644
--- a/drivers/pnp/system.c
+++ b/drivers/pnp/system.c
@@ -7,7 +7,6 @@
  *	Bjorn Helgaas <bjorn.helgaas@hp.com>
  */
 
-#include <linux/acpi.h>
 #include <linux/pnp.h>
 #include <linux/device.h>
 #include <linux/init.h>
@@ -23,41 +22,25 @@
 	{"", 0}
 };
 
-#ifdef CONFIG_ACPI
-static bool __reserve_range(u64 start, unsigned int length, bool io, char *desc)
-{
-	u8 space_id = io ? ACPI_ADR_SPACE_SYSTEM_IO : ACPI_ADR_SPACE_SYSTEM_MEMORY;
-	return !acpi_reserve_region(start, length, space_id, IORESOURCE_BUSY, desc);
-}
-#else
-static bool __reserve_range(u64 start, unsigned int length, bool io, char *desc)
-{
-	struct resource *res;
-
-	res = io ? request_region(start, length, desc) :
-		request_mem_region(start, length, desc);
-	if (res) {
-		res->flags &= ~IORESOURCE_BUSY;
-		return true;
-	}
-	return false;
-}
-#endif
-
 static void reserve_range(struct pnp_dev *dev, struct resource *r, int port)
 {
 	char *regionid;
 	const char *pnpid = dev_name(&dev->dev);
 	resource_size_t start = r->start, end = r->end;
-	bool reserved;
+	struct resource *res;
 
 	regionid = kmalloc(16, GFP_KERNEL);
 	if (!regionid)
 		return;
 
 	snprintf(regionid, 16, "pnp %s", pnpid);
-	reserved = __reserve_range(start, end - start + 1, !!port, regionid);
-	if (!reserved)
+	if (port)
+		res = request_region(start, end - start + 1, regionid);
+	else
+		res = request_mem_region(start, end - start + 1, regionid);
+	if (res)
+		res->flags &= ~IORESOURCE_BUSY;
+	else
 		kfree(regionid);
 
 	/*
@@ -66,7 +49,7 @@
 	 * have double reservations.
 	 */
 	dev_info(&dev->dev, "%pR %s reserved\n", r,
-		 reserved ? "has been" : "could not be");
+		 res ? "has been" : "could not be");
 }
 
 static void reserve_resources_of_dev(struct pnp_dev *dev)
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 86621fa..735355b 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -121,6 +121,7 @@
 #define REG_3		0x0004a0
 #define REG_4		0x000600
 #define REG_6		0x000800
+#define REG_7		0x000804
 #define REG_8		0x000820
 #define REG_9		0x000a04
 #define REG_10		0x018000
@@ -135,6 +136,8 @@
 #define REG_21		0x200218
 #define REG_22		0x0005a0
 #define REG_23		0x0005c0
+#define REG_24		0x000808
+#define REG_25		0x000b00
 #define REG_26		0x200118
 #define REG_27		0x200308
 #define REG_32		0x21003c
@@ -429,6 +432,9 @@
 #define SET_LENXY_START_RECFILL(fb, lenxy) \
 	WRITE_WORD(lenxy, fb, REG_9)
 
+#define SETUP_COPYAREA(fb) \
+	WRITE_BYTE(0, fb, REG_16b1)
+
 static void
 HYPER_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable)
 {
@@ -1004,6 +1010,36 @@
 	return 0;
 }
 
+static void
+stifb_copyarea(struct fb_info *info, const struct fb_copyarea *area)
+{
+	struct stifb_info *fb = container_of(info, struct stifb_info, info);
+
+	SETUP_COPYAREA(fb);
+
+	SETUP_HW(fb);
+	if (fb->info.var.bits_per_pixel == 32) {
+		WRITE_WORD(0xBBA0A000, fb, REG_10);
+
+		NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, 0xffffffff);
+	} else {
+		WRITE_WORD(fb->id == S9000_ID_HCRX ? 0x13a02000 : 0x13a01000, fb, REG_10);
+
+		NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, 0xff);
+	}
+
+	NGLE_QUICK_SET_IMAGE_BITMAP_OP(fb,
+		IBOvals(RopSrc, MaskAddrOffset(0),
+		BitmapExtent08, StaticReg(1),
+		DataDynamic, MaskOtc, BGx(0), FGx(0)));
+
+	WRITE_WORD(((area->sx << 16) | area->sy), fb, REG_24);
+	WRITE_WORD(((area->width << 16) | area->height), fb, REG_7);
+	WRITE_WORD(((area->dx << 16) | area->dy), fb, REG_25);
+
+	SETUP_FB(fb);
+}
+
 static void __init
 stifb_init_display(struct stifb_info *fb)
 {
@@ -1069,7 +1105,7 @@
 	.fb_setcolreg	= stifb_setcolreg,
 	.fb_blank	= stifb_blank,
 	.fb_fillrect	= cfb_fillrect,
-	.fb_copyarea	= cfb_copyarea,
+	.fb_copyarea	= stifb_copyarea,
 	.fb_imageblit	= cfb_imageblit,
 };
 
@@ -1258,7 +1294,7 @@
 	info->fbops = &stifb_ops;
 	info->screen_base = ioremap_nocache(REGION_BASE(fb,1), fix->smem_len);
 	info->screen_size = fix->smem_len;
-	info->flags = FBINFO_DEFAULT;
+	info->flags = FBINFO_DEFAULT | FBINFO_HWACCEL_COPYAREA;
 	info->pseudo_palette = &fb->pseudo_palette;
 
 	/* This has to be done !!! */
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 510040b..b1dc518 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -540,8 +540,7 @@
 	unlock_new_inode(inode);
 	return inode;
 error:
-	unlock_new_inode(inode);
-	iput(inode);
+	iget_failed(inode);
 	return ERR_PTR(retval);
 
 }
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 09e44337..e8aa57d 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -149,8 +149,7 @@
 	unlock_new_inode(inode);
 	return inode;
 error:
-	unlock_new_inode(inode);
-	iput(inode);
+	iget_failed(inode);
 	return ERR_PTR(retval);
 
 }
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 0ef5cc1..81220b2 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -44,6 +44,8 @@
 #define BTRFS_INODE_IN_DELALLOC_LIST		9
 #define BTRFS_INODE_READDIO_NEED_LOCK		10
 #define BTRFS_INODE_HAS_PROPS		        11
+/* DIO is ready to submit */
+#define BTRFS_INODE_DIO_READY		        12
 /*
  * The following 3 bits are meant only for the btree inode.
  * When any of them is set, it means an error happened while writing an
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 80a9aef..aac314e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1778,6 +1778,7 @@
 	spinlock_t unused_bgs_lock;
 	struct list_head unused_bgs;
 	struct mutex unused_bg_unpin_mutex;
+	struct mutex delete_unused_bgs_mutex;
 
 	/* For btrfs to record security options */
 	struct security_mnt_opts security_opts;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3f43bfea..a9aadb2 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1751,6 +1751,7 @@
 {
 	struct btrfs_root *root = arg;
 	int again;
+	struct btrfs_trans_handle *trans;
 
 	do {
 		again = 0;
@@ -1772,7 +1773,6 @@
 		}
 
 		btrfs_run_delayed_iputs(root);
-		btrfs_delete_unused_bgs(root->fs_info);
 		again = btrfs_clean_one_deleted_snapshot(root);
 		mutex_unlock(&root->fs_info->cleaner_mutex);
 
@@ -1781,6 +1781,16 @@
 		 * needn't do anything special here.
 		 */
 		btrfs_run_defrag_inodes(root->fs_info);
+
+		/*
+		 * Acquires fs_info->delete_unused_bgs_mutex to avoid racing
+		 * with relocation (btrfs_relocate_chunk) and relocation
+		 * acquires fs_info->cleaner_mutex (btrfs_relocate_block_group)
+		 * after acquiring fs_info->delete_unused_bgs_mutex. So we
+		 * can't hold, nor need to, fs_info->cleaner_mutex when deleting
+		 * unused block groups.
+		 */
+		btrfs_delete_unused_bgs(root->fs_info);
 sleep:
 		if (!try_to_freeze() && !again) {
 			set_current_state(TASK_INTERRUPTIBLE);
@@ -1789,6 +1799,34 @@
 			__set_current_state(TASK_RUNNING);
 		}
 	} while (!kthread_should_stop());
+
+	/*
+	 * Transaction kthread is stopped before us and wakes us up.
+	 * However we might have started a new transaction and COWed some
+	 * tree blocks when deleting unused block groups for example. So
+	 * make sure we commit the transaction we started to have a clean
+	 * shutdown when evicting the btree inode - if it has dirty pages
+	 * when we do the final iput() on it, eviction will trigger a
+	 * writeback for it which will fail with null pointer dereferences
+	 * since work queues and other resources were already released and
+	 * destroyed by the time the iput/eviction/writeback is made.
+	 */
+	trans = btrfs_attach_transaction(root);
+	if (IS_ERR(trans)) {
+		if (PTR_ERR(trans) != -ENOENT)
+			btrfs_err(root->fs_info,
+				  "cleaner transaction attach returned %ld",
+				  PTR_ERR(trans));
+	} else {
+		int ret;
+
+		ret = btrfs_commit_transaction(trans, root);
+		if (ret)
+			btrfs_err(root->fs_info,
+				  "cleaner open transaction commit returned %d",
+				  ret);
+	}
+
 	return 0;
 }
 
@@ -2492,6 +2530,7 @@
 	spin_lock_init(&fs_info->unused_bgs_lock);
 	rwlock_init(&fs_info->tree_mod_log_lock);
 	mutex_init(&fs_info->unused_bg_unpin_mutex);
+	mutex_init(&fs_info->delete_unused_bgs_mutex);
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
 	seqlock_init(&fs_info->profiles_lock);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 38b76cc..1c2bd17 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -9889,6 +9889,8 @@
 		}
 		spin_unlock(&fs_info->unused_bgs_lock);
 
+		mutex_lock(&root->fs_info->delete_unused_bgs_mutex);
+
 		/* Don't want to race with allocators so take the groups_sem */
 		down_write(&space_info->groups_sem);
 		spin_lock(&block_group->lock);
@@ -9983,6 +9985,7 @@
 end_trans:
 		btrfs_end_transaction(trans, root);
 next:
+		mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 		btrfs_put_block_group(block_group);
 		spin_lock(&fs_info->unused_bgs_lock);
 	}
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index f6a596d..d4a582a 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -246,6 +246,7 @@
 {
 	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
 	struct rb_root *rbroot = &root->free_ino_pinned->free_space_offset;
+	spinlock_t *rbroot_lock = &root->free_ino_pinned->tree_lock;
 	struct btrfs_free_space *info;
 	struct rb_node *n;
 	u64 count;
@@ -254,24 +255,30 @@
 		return;
 
 	while (1) {
+		bool add_to_ctl = true;
+
+		spin_lock(rbroot_lock);
 		n = rb_first(rbroot);
-		if (!n)
+		if (!n) {
+			spin_unlock(rbroot_lock);
 			break;
+		}
 
 		info = rb_entry(n, struct btrfs_free_space, offset_index);
 		BUG_ON(info->bitmap); /* Logic error */
 
 		if (info->offset > root->ino_cache_progress)
-			goto free;
+			add_to_ctl = false;
 		else if (info->offset + info->bytes > root->ino_cache_progress)
 			count = root->ino_cache_progress - info->offset + 1;
 		else
 			count = info->bytes;
 
-		__btrfs_add_free_space(ctl, info->offset, count);
-free:
 		rb_erase(&info->offset_index, rbroot);
-		kfree(info);
+		spin_unlock(rbroot_lock);
+		if (add_to_ctl)
+			__btrfs_add_free_space(ctl, info->offset, count);
+		kmem_cache_free(btrfs_free_space_cachep, info);
 	}
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 855935f..b33c0cf 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4989,8 +4989,9 @@
 	/*
 	 * Keep looping until we have no more ranges in the io tree.
 	 * We can have ongoing bios started by readpages (called from readahead)
-	 * that didn't get their end io callbacks called yet or they are still
-	 * in progress ((extent_io.c:end_bio_extent_readpage()). This means some
+	 * that have their endio callback (extent_io.c:end_bio_extent_readpage)
+	 * still in progress (unlocked the pages in the bio but did not yet
+	 * unlocked the ranges in the io tree). Therefore this means some
 	 * ranges can still be locked and eviction started because before
 	 * submitting those bios, which are executed by a separate task (work
 	 * queue kthread), inode references (inode->i_count) were not taken
@@ -7546,6 +7547,7 @@
 
 		current->journal_info = outstanding_extents;
 		btrfs_free_reserved_data_space(inode, len);
+		set_bit(BTRFS_INODE_DIO_READY, &BTRFS_I(inode)->runtime_flags);
 	}
 
 	/*
@@ -7871,8 +7873,6 @@
 	struct bio *dio_bio;
 	int ret;
 
-	if (err)
-		goto out_done;
 again:
 	ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
 						   &ordered_offset,
@@ -7895,7 +7895,6 @@
 		ordered = NULL;
 		goto again;
 	}
-out_done:
 	dio_bio = dip->dio_bio;
 
 	kfree(dip);
@@ -8163,9 +8162,8 @@
 static void btrfs_submit_direct(int rw, struct bio *dio_bio,
 				struct inode *inode, loff_t file_offset)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_dio_private *dip;
-	struct bio *io_bio;
+	struct btrfs_dio_private *dip = NULL;
+	struct bio *io_bio = NULL;
 	struct btrfs_io_bio *btrfs_bio;
 	int skip_sum;
 	int write = rw & REQ_WRITE;
@@ -8182,7 +8180,7 @@
 	dip = kzalloc(sizeof(*dip), GFP_NOFS);
 	if (!dip) {
 		ret = -ENOMEM;
-		goto free_io_bio;
+		goto free_ordered;
 	}
 
 	dip->private = dio_bio->bi_private;
@@ -8210,25 +8208,55 @@
 
 	if (btrfs_bio->end_io)
 		btrfs_bio->end_io(btrfs_bio, ret);
-free_io_bio:
-	bio_put(io_bio);
 
 free_ordered:
 	/*
-	 * If this is a write, we need to clean up the reserved space and kill
-	 * the ordered extent.
+	 * If we arrived here it means either we failed to submit the dip
+	 * or we either failed to clone the dio_bio or failed to allocate the
+	 * dip. If we cloned the dio_bio and allocated the dip, we can just
+	 * call bio_endio against our io_bio so that we get proper resource
+	 * cleanup if we fail to submit the dip, otherwise, we must do the
+	 * same as btrfs_endio_direct_[write|read] because we can't call these
+	 * callbacks - they require an allocated dip and a clone of dio_bio.
 	 */
-	if (write) {
-		struct btrfs_ordered_extent *ordered;
-		ordered = btrfs_lookup_ordered_extent(inode, file_offset);
-		if (!test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags) &&
-		    !test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags))
-			btrfs_free_reserved_extent(root, ordered->start,
-						   ordered->disk_len, 1);
-		btrfs_put_ordered_extent(ordered);
-		btrfs_put_ordered_extent(ordered);
+	if (io_bio && dip) {
+		bio_endio(io_bio, ret);
+		/*
+		 * The end io callbacks free our dip, do the final put on io_bio
+		 * and all the cleanup and final put for dio_bio (through
+		 * dio_end_io()).
+		 */
+		dip = NULL;
+		io_bio = NULL;
+	} else {
+		if (write) {
+			struct btrfs_ordered_extent *ordered;
+
+			ordered = btrfs_lookup_ordered_extent(inode,
+							      file_offset);
+			set_bit(BTRFS_ORDERED_IOERR, &ordered->flags);
+			/*
+			 * Decrements our ref on the ordered extent and removes
+			 * the ordered extent from the inode's ordered tree,
+			 * doing all the proper resource cleanup such as for the
+			 * reserved space and waking up any waiters for this
+			 * ordered extent (through btrfs_remove_ordered_extent).
+			 */
+			btrfs_finish_ordered_io(ordered);
+		} else {
+			unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
+			      file_offset + dio_bio->bi_iter.bi_size - 1);
+		}
+		clear_bit(BIO_UPTODATE, &dio_bio->bi_flags);
+		/*
+		 * Releases and cleans up our dio_bio, no need to bio_put()
+		 * nor bio_endio()/bio_io_error() against dio_bio.
+		 */
+		dio_end_io(dio_bio, ret);
 	}
-	bio_endio(dio_bio, ret);
+	if (io_bio)
+		bio_put(io_bio);
+	kfree(dip);
 }
 
 static ssize_t check_direct_IO(struct btrfs_root *root, struct kiocb *iocb,
@@ -8330,9 +8358,18 @@
 				   btrfs_submit_direct, flags);
 	if (iov_iter_rw(iter) == WRITE) {
 		current->journal_info = NULL;
-		if (ret < 0 && ret != -EIOCBQUEUED)
-			btrfs_delalloc_release_space(inode, count);
-		else if (ret >= 0 && (size_t)ret < count)
+		if (ret < 0 && ret != -EIOCBQUEUED) {
+			/*
+			 * If the error comes from submitting stage,
+			 * btrfs_get_blocsk_direct() has free'd data space,
+			 * and metadata space will be handled by
+			 * finish_ordered_fn, don't do that again to make
+			 * sure bytes_may_use is correct.
+			 */
+			if (!test_and_clear_bit(BTRFS_INODE_DIO_READY,
+				     &BTRFS_I(inode)->runtime_flags))
+				btrfs_delalloc_release_space(inode, count);
+		} else if (ret >= 0 && (size_t)ret < count)
 			btrfs_delalloc_release_space(inode,
 						     count - (size_t)ret);
 	}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c86b835..5d91776 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -87,7 +87,8 @@
 
 
 static int btrfs_clone(struct inode *src, struct inode *inode,
-		       u64 off, u64 olen, u64 olen_aligned, u64 destoff);
+		       u64 off, u64 olen, u64 olen_aligned, u64 destoff,
+		       int no_time_update);
 
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)
@@ -2765,14 +2766,11 @@
 	return ret;
 }
 
-static struct page *extent_same_get_page(struct inode *inode, u64 off)
+static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
 {
 	struct page *page;
-	pgoff_t index;
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 
-	index = off >> PAGE_CACHE_SHIFT;
-
 	page = grab_cache_page(inode->i_mapping, index);
 	if (!page)
 		return NULL;
@@ -2793,6 +2791,20 @@
 	return page;
 }
 
+static int gather_extent_pages(struct inode *inode, struct page **pages,
+			       int num_pages, u64 off)
+{
+	int i;
+	pgoff_t index = off >> PAGE_CACHE_SHIFT;
+
+	for (i = 0; i < num_pages; i++) {
+		pages[i] = extent_same_get_page(inode, index + i);
+		if (!pages[i])
+			return -ENOMEM;
+	}
+	return 0;
+}
+
 static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
 {
 	/* do any pending delalloc/csum calc on src, one way or
@@ -2818,52 +2830,120 @@
 	}
 }
 
-static void btrfs_double_unlock(struct inode *inode1, u64 loff1,
-				struct inode *inode2, u64 loff2, u64 len)
+static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
 {
-	unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
-	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
-
 	mutex_unlock(&inode1->i_mutex);
 	mutex_unlock(&inode2->i_mutex);
 }
 
-static void btrfs_double_lock(struct inode *inode1, u64 loff1,
-			      struct inode *inode2, u64 loff2, u64 len)
+static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
+{
+	if (inode1 < inode2)
+		swap(inode1, inode2);
+
+	mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
+	if (inode1 != inode2)
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+}
+
+static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
+				      struct inode *inode2, u64 loff2, u64 len)
+{
+	unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
+	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
+}
+
+static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+				     struct inode *inode2, u64 loff2, u64 len)
 {
 	if (inode1 < inode2) {
 		swap(inode1, inode2);
 		swap(loff1, loff2);
 	}
-
-	mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
 	lock_extent_range(inode1, loff1, len);
-	if (inode1 != inode2) {
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+	if (inode1 != inode2)
 		lock_extent_range(inode2, loff2, len);
+}
+
+struct cmp_pages {
+	int		num_pages;
+	struct page	**src_pages;
+	struct page	**dst_pages;
+};
+
+static void btrfs_cmp_data_free(struct cmp_pages *cmp)
+{
+	int i;
+	struct page *pg;
+
+	for (i = 0; i < cmp->num_pages; i++) {
+		pg = cmp->src_pages[i];
+		if (pg)
+			page_cache_release(pg);
+		pg = cmp->dst_pages[i];
+		if (pg)
+			page_cache_release(pg);
 	}
+	kfree(cmp->src_pages);
+	kfree(cmp->dst_pages);
+}
+
+static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
+				  struct inode *dst, u64 dst_loff,
+				  u64 len, struct cmp_pages *cmp)
+{
+	int ret;
+	int num_pages = PAGE_CACHE_ALIGN(len) >> PAGE_CACHE_SHIFT;
+	struct page **src_pgarr, **dst_pgarr;
+
+	/*
+	 * We must gather up all the pages before we initiate our
+	 * extent locking. We use an array for the page pointers. Size
+	 * of the array is bounded by len, which is in turn bounded by
+	 * BTRFS_MAX_DEDUPE_LEN.
+	 */
+	src_pgarr = kzalloc(num_pages * sizeof(struct page *), GFP_NOFS);
+	dst_pgarr = kzalloc(num_pages * sizeof(struct page *), GFP_NOFS);
+	if (!src_pgarr || !dst_pgarr) {
+		kfree(src_pgarr);
+		kfree(dst_pgarr);
+		return -ENOMEM;
+	}
+	cmp->num_pages = num_pages;
+	cmp->src_pages = src_pgarr;
+	cmp->dst_pages = dst_pgarr;
+
+	ret = gather_extent_pages(src, cmp->src_pages, cmp->num_pages, loff);
+	if (ret)
+		goto out;
+
+	ret = gather_extent_pages(dst, cmp->dst_pages, cmp->num_pages, dst_loff);
+
+out:
+	if (ret)
+		btrfs_cmp_data_free(cmp);
+	return 0;
 }
 
 static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
-			  u64 dst_loff, u64 len)
+			  u64 dst_loff, u64 len, struct cmp_pages *cmp)
 {
 	int ret = 0;
+	int i;
 	struct page *src_page, *dst_page;
 	unsigned int cmp_len = PAGE_CACHE_SIZE;
 	void *addr, *dst_addr;
 
+	i = 0;
 	while (len) {
 		if (len < PAGE_CACHE_SIZE)
 			cmp_len = len;
 
-		src_page = extent_same_get_page(src, loff);
-		if (!src_page)
-			return -EINVAL;
-		dst_page = extent_same_get_page(dst, dst_loff);
-		if (!dst_page) {
-			page_cache_release(src_page);
-			return -EINVAL;
-		}
+		BUG_ON(i >= cmp->num_pages);
+
+		src_page = cmp->src_pages[i];
+		dst_page = cmp->dst_pages[i];
+
 		addr = kmap_atomic(src_page);
 		dst_addr = kmap_atomic(dst_page);
 
@@ -2875,15 +2955,12 @@
 
 		kunmap_atomic(addr);
 		kunmap_atomic(dst_addr);
-		page_cache_release(src_page);
-		page_cache_release(dst_page);
 
 		if (ret)
 			break;
 
-		loff += cmp_len;
-		dst_loff += cmp_len;
 		len -= cmp_len;
+		i++;
 	}
 
 	return ret;
@@ -2914,27 +2991,62 @@
 {
 	int ret;
 	u64 len = olen;
+	struct cmp_pages cmp;
+	int same_inode = 0;
+	u64 same_lock_start = 0;
+	u64 same_lock_len = 0;
 
-	/*
-	 * btrfs_clone() can't handle extents in the same file
-	 * yet. Once that works, we can drop this check and replace it
-	 * with a check for the same inode, but overlapping extents.
-	 */
 	if (src == dst)
-		return -EINVAL;
+		same_inode = 1;
 
 	if (len == 0)
 		return 0;
 
-	btrfs_double_lock(src, loff, dst, dst_loff, len);
+	if (same_inode) {
+		mutex_lock(&src->i_mutex);
 
-	ret = extent_same_check_offsets(src, loff, &len, olen);
-	if (ret)
-		goto out_unlock;
+		ret = extent_same_check_offsets(src, loff, &len, olen);
+		if (ret)
+			goto out_unlock;
 
-	ret = extent_same_check_offsets(dst, dst_loff, &len, olen);
-	if (ret)
-		goto out_unlock;
+		/*
+		 * Single inode case wants the same checks, except we
+		 * don't want our length pushed out past i_size as
+		 * comparing that data range makes no sense.
+		 *
+		 * extent_same_check_offsets() will do this for an
+		 * unaligned length at i_size, so catch it here and
+		 * reject the request.
+		 *
+		 * This effectively means we require aligned extents
+		 * for the single-inode case, whereas the other cases
+		 * allow an unaligned length so long as it ends at
+		 * i_size.
+		 */
+		if (len != olen) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		/* Check for overlapping ranges */
+		if (dst_loff + len > loff && dst_loff < loff + len) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		same_lock_start = min_t(u64, loff, dst_loff);
+		same_lock_len = max_t(u64, loff, dst_loff) + len - same_lock_start;
+	} else {
+		btrfs_double_inode_lock(src, dst);
+
+		ret = extent_same_check_offsets(src, loff, &len, olen);
+		if (ret)
+			goto out_unlock;
+
+		ret = extent_same_check_offsets(dst, dst_loff, &len, olen);
+		if (ret)
+			goto out_unlock;
+	}
 
 	/* don't make the dst file partly checksummed */
 	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
@@ -2943,12 +3055,32 @@
 		goto out_unlock;
 	}
 
-	ret = btrfs_cmp_data(src, loff, dst, dst_loff, len);
-	if (ret == 0)
-		ret = btrfs_clone(src, dst, loff, olen, len, dst_loff);
+	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
+	if (ret)
+		goto out_unlock;
 
+	if (same_inode)
+		lock_extent_range(src, same_lock_start, same_lock_len);
+	else
+		btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+
+	/* pass original length for comparison so we stay within i_size */
+	ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
+	if (ret == 0)
+		ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1);
+
+	if (same_inode)
+		unlock_extent(&BTRFS_I(src)->io_tree, same_lock_start,
+			      same_lock_start + same_lock_len - 1);
+	else
+		btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
+
+	btrfs_cmp_data_free(&cmp);
 out_unlock:
-	btrfs_double_unlock(src, loff, dst, dst_loff, len);
+	if (same_inode)
+		mutex_unlock(&src->i_mutex);
+	else
+		btrfs_double_inode_unlock(src, dst);
 
 	return ret;
 }
@@ -3100,13 +3232,15 @@
 				     struct inode *inode,
 				     u64 endoff,
 				     const u64 destoff,
-				     const u64 olen)
+				     const u64 olen,
+				     int no_time_update)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
 	inode_inc_iversion(inode);
-	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	if (!no_time_update)
+		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	/*
 	 * We round up to the block size at eof when determining which
 	 * extents to clone above, but shouldn't round up the file size.
@@ -3191,13 +3325,13 @@
  * @inode: Inode to clone to
  * @off: Offset within source to start clone from
  * @olen: Original length, passed by user, of range to clone
- * @olen_aligned: Block-aligned value of olen, extent_same uses
- *               identical values here
+ * @olen_aligned: Block-aligned value of olen
  * @destoff: Offset within @inode to start clone
+ * @no_time_update: Whether to update mtime/ctime on the target inode
  */
 static int btrfs_clone(struct inode *src, struct inode *inode,
 		       const u64 off, const u64 olen, const u64 olen_aligned,
-		       const u64 destoff)
+		       const u64 destoff, int no_time_update)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_path *path = NULL;
@@ -3521,7 +3655,8 @@
 					      root->sectorsize);
 			ret = clone_finish_inode_update(trans, inode,
 							last_dest_end,
-							destoff, olen);
+							destoff, olen,
+							no_time_update);
 			if (ret)
 				goto out;
 			if (new_key.offset + datal >= destoff + len)
@@ -3559,7 +3694,7 @@
 		clone_update_extent_map(inode, trans, NULL, last_dest_end,
 					destoff + len - last_dest_end);
 		ret = clone_finish_inode_update(trans, inode, destoff + len,
-						destoff, olen);
+						destoff, olen, no_time_update);
 	}
 
 out:
@@ -3696,7 +3831,7 @@
 		lock_extent_range(inode, destoff, len);
 	}
 
-	ret = btrfs_clone(src, inode, off, olen, len, destoff);
+	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
 
 	if (same_inode) {
 		u64 lock_start = min_t(u64, off, destoff);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 89656d7..52170cf 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -552,6 +552,10 @@
 	trace_btrfs_ordered_extent_put(entry->inode, entry);
 
 	if (atomic_dec_and_test(&entry->refs)) {
+		ASSERT(list_empty(&entry->log_list));
+		ASSERT(list_empty(&entry->trans_list));
+		ASSERT(list_empty(&entry->root_extent_list));
+		ASSERT(RB_EMPTY_NODE(&entry->rb_node));
 		if (entry->inode)
 			btrfs_add_delayed_iput(entry->inode);
 		while (!list_empty(&entry->list)) {
@@ -579,6 +583,7 @@
 	spin_lock_irq(&tree->lock);
 	node = &entry->rb_node;
 	rb_erase(node, &tree->tree);
+	RB_CLEAR_NODE(node);
 	if (tree->last == node)
 		tree->last = NULL;
 	set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index d5f1f03..e9ace09 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1349,6 +1349,11 @@
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	int ret = 0;
+	/* Sometimes we would want to clear the limit on this qgroup.
+	 * To meet this requirement, we treat the -1 as a special value
+	 * which tell kernel to clear the limit on this qgroup.
+	 */
+	const u64 CLEAR_VALUE = -1;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
 	quota_root = fs_info->quota_root;
@@ -1364,14 +1369,42 @@
 	}
 
 	spin_lock(&fs_info->qgroup_lock);
-	if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_RFER)
-		qgroup->max_rfer = limit->max_rfer;
-	if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_EXCL)
-		qgroup->max_excl = limit->max_excl;
-	if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_RFER)
-		qgroup->rsv_rfer = limit->rsv_rfer;
-	if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_EXCL)
-		qgroup->rsv_excl = limit->rsv_excl;
+	if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_RFER) {
+		if (limit->max_rfer == CLEAR_VALUE) {
+			qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_MAX_RFER;
+			limit->flags &= ~BTRFS_QGROUP_LIMIT_MAX_RFER;
+			qgroup->max_rfer = 0;
+		} else {
+			qgroup->max_rfer = limit->max_rfer;
+		}
+	}
+	if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) {
+		if (limit->max_excl == CLEAR_VALUE) {
+			qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_MAX_EXCL;
+			limit->flags &= ~BTRFS_QGROUP_LIMIT_MAX_EXCL;
+			qgroup->max_excl = 0;
+		} else {
+			qgroup->max_excl = limit->max_excl;
+		}
+	}
+	if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_RFER) {
+		if (limit->rsv_rfer == CLEAR_VALUE) {
+			qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_RSV_RFER;
+			limit->flags &= ~BTRFS_QGROUP_LIMIT_RSV_RFER;
+			qgroup->rsv_rfer = 0;
+		} else {
+			qgroup->rsv_rfer = limit->rsv_rfer;
+		}
+	}
+	if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_EXCL) {
+		if (limit->rsv_excl == CLEAR_VALUE) {
+			qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_RSV_EXCL;
+			limit->flags &= ~BTRFS_QGROUP_LIMIT_RSV_EXCL;
+			qgroup->rsv_excl = 0;
+		} else {
+			qgroup->rsv_excl = limit->rsv_excl;
+		}
+	}
 	qgroup->lim_flags |= limit->flags;
 
 	spin_unlock(&fs_info->qgroup_lock);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 827951f..88cbb59 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4049,7 +4049,7 @@
 	if (trans && progress && err == -ENOSPC) {
 		ret = btrfs_force_chunk_alloc(trans, rc->extent_root,
 					      rc->block_group->flags);
-		if (ret == 0) {
+		if (ret == 1) {
 			err = 0;
 			progress = 0;
 			goto restart;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 9f2feab..94db0fa 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3571,7 +3571,6 @@
 static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 						int is_dev_replace)
 {
-	int ret = 0;
 	unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND;
 	int max_active = fs_info->thread_pool_size;
 
@@ -3584,34 +3583,36 @@
 			fs_info->scrub_workers =
 				btrfs_alloc_workqueue("btrfs-scrub", flags,
 						      max_active, 4);
-		if (!fs_info->scrub_workers) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		if (!fs_info->scrub_workers)
+			goto fail_scrub_workers;
+
 		fs_info->scrub_wr_completion_workers =
 			btrfs_alloc_workqueue("btrfs-scrubwrc", flags,
 					      max_active, 2);
-		if (!fs_info->scrub_wr_completion_workers) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		if (!fs_info->scrub_wr_completion_workers)
+			goto fail_scrub_wr_completion_workers;
+
 		fs_info->scrub_nocow_workers =
 			btrfs_alloc_workqueue("btrfs-scrubnc", flags, 1, 0);
-		if (!fs_info->scrub_nocow_workers) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		if (!fs_info->scrub_nocow_workers)
+			goto fail_scrub_nocow_workers;
 		fs_info->scrub_parity_workers =
 			btrfs_alloc_workqueue("btrfs-scrubparity", flags,
 					      max_active, 2);
-		if (!fs_info->scrub_parity_workers) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		if (!fs_info->scrub_parity_workers)
+			goto fail_scrub_parity_workers;
 	}
 	++fs_info->scrub_workers_refcnt;
-out:
-	return ret;
+	return 0;
+
+fail_scrub_parity_workers:
+	btrfs_destroy_workqueue(fs_info->scrub_nocow_workers);
+fail_scrub_nocow_workers:
+	btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
+fail_scrub_wr_completion_workers:
+	btrfs_destroy_workqueue(fs_info->scrub_workers);
+fail_scrub_workers:
+	return -ENOMEM;
 }
 
 static noinline_for_stack void scrub_workers_put(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 1ce80c1..9c45431 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4117,6 +4117,187 @@
 	return 0;
 }
 
+/*
+ * At the moment we always log all xattrs. This is to figure out at log replay
+ * time which xattrs must have their deletion replayed. If a xattr is missing
+ * in the log tree and exists in the fs/subvol tree, we delete it. This is
+ * because if a xattr is deleted, the inode is fsynced and a power failure
+ * happens, causing the log to be replayed the next time the fs is mounted,
+ * we want the xattr to not exist anymore (same behaviour as other filesystems
+ * with a journal, ext3/4, xfs, f2fs, etc).
+ */
+static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				struct inode *inode,
+				struct btrfs_path *path,
+				struct btrfs_path *dst_path)
+{
+	int ret;
+	struct btrfs_key key;
+	const u64 ino = btrfs_ino(inode);
+	int ins_nr = 0;
+	int start_slot = 0;
+
+	key.objectid = ino;
+	key.type = BTRFS_XATTR_ITEM_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		return ret;
+
+	while (true) {
+		int slot = path->slots[0];
+		struct extent_buffer *leaf = path->nodes[0];
+		int nritems = btrfs_header_nritems(leaf);
+
+		if (slot >= nritems) {
+			if (ins_nr > 0) {
+				u64 last_extent = 0;
+
+				ret = copy_items(trans, inode, dst_path, path,
+						 &last_extent, start_slot,
+						 ins_nr, 1, 0);
+				/* can't be 1, extent items aren't processed */
+				ASSERT(ret <= 0);
+				if (ret < 0)
+					return ret;
+				ins_nr = 0;
+			}
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				return ret;
+			else if (ret > 0)
+				break;
+			continue;
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.objectid != ino || key.type != BTRFS_XATTR_ITEM_KEY)
+			break;
+
+		if (ins_nr == 0)
+			start_slot = slot;
+		ins_nr++;
+		path->slots[0]++;
+		cond_resched();
+	}
+	if (ins_nr > 0) {
+		u64 last_extent = 0;
+
+		ret = copy_items(trans, inode, dst_path, path,
+				 &last_extent, start_slot,
+				 ins_nr, 1, 0);
+		/* can't be 1, extent items aren't processed */
+		ASSERT(ret <= 0);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * If the no holes feature is enabled we need to make sure any hole between the
+ * last extent and the i_size of our inode is explicitly marked in the log. This
+ * is to make sure that doing something like:
+ *
+ *      1) create file with 128Kb of data
+ *      2) truncate file to 64Kb
+ *      3) truncate file to 256Kb
+ *      4) fsync file
+ *      5) <crash/power failure>
+ *      6) mount fs and trigger log replay
+ *
+ * Will give us a file with a size of 256Kb, the first 64Kb of data match what
+ * the file had in its first 64Kb of data at step 1 and the last 192Kb of the
+ * file correspond to a hole. The presence of explicit holes in a log tree is
+ * what guarantees that log replay will remove/adjust file extent items in the
+ * fs/subvol tree.
+ *
+ * Here we do not need to care about holes between extents, that is already done
+ * by copy_items(). We also only need to do this in the full sync path, where we
+ * lookup for extents from the fs/subvol tree only. In the fast path case, we
+ * lookup the list of modified extent maps and if any represents a hole, we
+ * insert a corresponding extent representing a hole in the log tree.
+ */
+static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root,
+				   struct inode *inode,
+				   struct btrfs_path *path)
+{
+	int ret;
+	struct btrfs_key key;
+	u64 hole_start;
+	u64 hole_size;
+	struct extent_buffer *leaf;
+	struct btrfs_root *log = root->log_root;
+	const u64 ino = btrfs_ino(inode);
+	const u64 i_size = i_size_read(inode);
+
+	if (!btrfs_fs_incompat(root->fs_info, NO_HOLES))
+		return 0;
+
+	key.objectid = ino;
+	key.type = BTRFS_EXTENT_DATA_KEY;
+	key.offset = (u64)-1;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	ASSERT(ret != 0);
+	if (ret < 0)
+		return ret;
+
+	ASSERT(path->slots[0] > 0);
+	path->slots[0]--;
+	leaf = path->nodes[0];
+	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+
+	if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) {
+		/* inode does not have any extents */
+		hole_start = 0;
+		hole_size = i_size;
+	} else {
+		struct btrfs_file_extent_item *extent;
+		u64 len;
+
+		/*
+		 * If there's an extent beyond i_size, an explicit hole was
+		 * already inserted by copy_items().
+		 */
+		if (key.offset >= i_size)
+			return 0;
+
+		extent = btrfs_item_ptr(leaf, path->slots[0],
+					struct btrfs_file_extent_item);
+
+		if (btrfs_file_extent_type(leaf, extent) ==
+		    BTRFS_FILE_EXTENT_INLINE) {
+			len = btrfs_file_extent_inline_len(leaf,
+							   path->slots[0],
+							   extent);
+			ASSERT(len == i_size);
+			return 0;
+		}
+
+		len = btrfs_file_extent_num_bytes(leaf, extent);
+		/* Last extent goes beyond i_size, no need to log a hole. */
+		if (key.offset + len > i_size)
+			return 0;
+		hole_start = key.offset + len;
+		hole_size = i_size - hole_start;
+	}
+	btrfs_release_path(path);
+
+	/* Last extent ends at i_size. */
+	if (hole_size == 0)
+		return 0;
+
+	hole_size = ALIGN(hole_size, root->sectorsize);
+	ret = btrfs_insert_file_extent(trans, log, ino, hole_start, 0, 0,
+				       hole_size, 0, hole_size, 0, 0, 0);
+	return ret;
+}
+
 /* log a single inode in the tree log.
  * At least one parent directory for this inode must exist in the tree
  * or be logged already.
@@ -4155,6 +4336,7 @@
 	u64 ino = btrfs_ino(inode);
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	u64 logged_isize = 0;
+	bool need_log_inode_item = true;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -4263,11 +4445,6 @@
 		} else {
 			if (inode_only == LOG_INODE_ALL)
 				fast_search = true;
-			ret = log_inode_item(trans, log, dst_path, inode);
-			if (ret) {
-				err = ret;
-				goto out_unlock;
-			}
 			goto log_extents;
 		}
 
@@ -4290,6 +4467,28 @@
 		if (min_key.type > max_key.type)
 			break;
 
+		if (min_key.type == BTRFS_INODE_ITEM_KEY)
+			need_log_inode_item = false;
+
+		/* Skip xattrs, we log them later with btrfs_log_all_xattrs() */
+		if (min_key.type == BTRFS_XATTR_ITEM_KEY) {
+			if (ins_nr == 0)
+				goto next_slot;
+			ret = copy_items(trans, inode, dst_path, path,
+					 &last_extent, ins_start_slot,
+					 ins_nr, inode_only, logged_isize);
+			if (ret < 0) {
+				err = ret;
+				goto out_unlock;
+			}
+			ins_nr = 0;
+			if (ret) {
+				btrfs_release_path(path);
+				continue;
+			}
+			goto next_slot;
+		}
+
 		src = path->nodes[0];
 		if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) {
 			ins_nr++;
@@ -4357,9 +4556,26 @@
 		ins_nr = 0;
 	}
 
+	btrfs_release_path(path);
+	btrfs_release_path(dst_path);
+	err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path);
+	if (err)
+		goto out_unlock;
+	if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
+		btrfs_release_path(path);
+		btrfs_release_path(dst_path);
+		err = btrfs_log_trailing_hole(trans, root, inode, path);
+		if (err)
+			goto out_unlock;
+	}
 log_extents:
 	btrfs_release_path(path);
 	btrfs_release_path(dst_path);
+	if (need_log_inode_item) {
+		err = log_inode_item(trans, log, dst_path, inode);
+		if (err)
+			goto out_unlock;
+	}
 	if (fast_search) {
 		/*
 		 * Some ordered extents started by fsync might have completed
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 4b438b4..fbe7c10 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2766,6 +2766,20 @@
 	root = root->fs_info->chunk_root;
 	extent_root = root->fs_info->extent_root;
 
+	/*
+	 * Prevent races with automatic removal of unused block groups.
+	 * After we relocate and before we remove the chunk with offset
+	 * chunk_offset, automatic removal of the block group can kick in,
+	 * resulting in a failure when calling btrfs_remove_chunk() below.
+	 *
+	 * Make sure to acquire this mutex before doing a tree search (dev
+	 * or chunk trees) to find chunks. Otherwise the cleaner kthread might
+	 * call btrfs_remove_chunk() (through btrfs_delete_unused_bgs()) after
+	 * we release the path used to search the chunk/dev tree and before
+	 * the current task acquires this mutex and calls us.
+	 */
+	ASSERT(mutex_is_locked(&root->fs_info->delete_unused_bgs_mutex));
+
 	ret = btrfs_can_relocate(extent_root, chunk_offset);
 	if (ret)
 		return -ENOSPC;
@@ -2814,13 +2828,18 @@
 	key.type = BTRFS_CHUNK_ITEM_KEY;
 
 	while (1) {
+		mutex_lock(&root->fs_info->delete_unused_bgs_mutex);
 		ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 			goto error;
+		}
 		BUG_ON(ret == 0); /* Corruption */
 
 		ret = btrfs_previous_item(chunk_root, path, key.objectid,
 					  key.type);
+		if (ret)
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 		if (ret < 0)
 			goto error;
 		if (ret > 0)
@@ -2843,6 +2862,7 @@
 			else
 				BUG_ON(ret);
 		}
+		mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 
 		if (found_key.offset == 0)
 			break;
@@ -3299,9 +3319,12 @@
 			goto error;
 		}
 
+		mutex_lock(&fs_info->delete_unused_bgs_mutex);
 		ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 			goto error;
+		}
 
 		/*
 		 * this shouldn't happen, it means the last relocate
@@ -3313,6 +3336,7 @@
 		ret = btrfs_previous_item(chunk_root, path, 0,
 					  BTRFS_CHUNK_ITEM_KEY);
 		if (ret) {
+			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 			ret = 0;
 			break;
 		}
@@ -3321,8 +3345,10 @@
 		slot = path->slots[0];
 		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
-		if (found_key.objectid != key.objectid)
+		if (found_key.objectid != key.objectid) {
+			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 			break;
+		}
 
 		chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
 
@@ -3335,10 +3361,13 @@
 		ret = should_balance_chunk(chunk_root, leaf, chunk,
 					   found_key.offset);
 		btrfs_release_path(path);
-		if (!ret)
+		if (!ret) {
+			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 			goto loop;
+		}
 
 		if (counting) {
+			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 			spin_lock(&fs_info->balance_lock);
 			bctl->stat.expected++;
 			spin_unlock(&fs_info->balance_lock);
@@ -3348,6 +3377,7 @@
 		ret = btrfs_relocate_chunk(chunk_root,
 					   found_key.objectid,
 					   found_key.offset);
+		mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 		if (ret && ret != -ENOSPC)
 			goto error;
 		if (ret == -ENOSPC) {
@@ -4087,11 +4117,16 @@
 	key.type = BTRFS_DEV_EXTENT_KEY;
 
 	do {
+		mutex_lock(&root->fs_info->delete_unused_bgs_mutex);
 		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 			goto done;
+		}
 
 		ret = btrfs_previous_item(root, path, 0, key.type);
+		if (ret)
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 		if (ret < 0)
 			goto done;
 		if (ret) {
@@ -4105,6 +4140,7 @@
 		btrfs_item_key_to_cpu(l, &key, path->slots[0]);
 
 		if (key.objectid != device->devid) {
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 			btrfs_release_path(path);
 			break;
 		}
@@ -4113,6 +4149,7 @@
 		length = btrfs_dev_extent_length(l, dev_extent);
 
 		if (key.offset + length <= new_size) {
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 			btrfs_release_path(path);
 			break;
 		}
@@ -4122,6 +4159,7 @@
 		btrfs_release_path(path);
 
 		ret = btrfs_relocate_chunk(root, chunk_objectid, chunk_offset);
+		mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 		if (ret && ret != -ENOSPC)
 			goto done;
 		if (ret == -ENOSPC)
@@ -5715,7 +5753,6 @@
 static void btrfs_end_bio(struct bio *bio, int err)
 {
 	struct btrfs_bio *bbio = bio->bi_private;
-	struct btrfs_device *dev = bbio->stripes[0].dev;
 	int is_orig_bio = 0;
 
 	if (err) {
@@ -5723,6 +5760,7 @@
 		if (err == -EIO || err == -EREMOTEIO) {
 			unsigned int stripe_index =
 				btrfs_io_bio(bio)->stripe_index;
+			struct btrfs_device *dev;
 
 			BUG_ON(stripe_index >= bbio->num_stripes);
 			dev = bbio->stripes[stripe_index].dev;
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 6b8e2f0..48851f6 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -896,6 +896,7 @@
 /* 'X' - originally XFS but some now in the VFS */
 COMPATIBLE_IOCTL(FIFREEZE)
 COMPATIBLE_IOCTL(FITHAW)
+COMPATIBLE_IOCTL(FITRIM)
 COMPATIBLE_IOCTL(KDGETKEYCODE)
 COMPATIBLE_IOCTL(KDSETKEYCODE)
 COMPATIBLE_IOCTL(KDGKBTYPE)
diff --git a/fs/dcache.c b/fs/dcache.c
index 7a3f3e5..5c8ea15 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -642,7 +642,7 @@
 
 	/*
 	 * If we have a d_op->d_delete() operation, we sould not
-	 * let the dentry count go to zero, so use "put__or_lock".
+	 * let the dentry count go to zero, so use "put_or_lock".
 	 */
 	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE))
 		return lockref_put_or_lock(&dentry->d_lockref);
@@ -697,7 +697,7 @@
 	 */
 	smp_rmb();
 	d_flags = ACCESS_ONCE(dentry->d_flags);
-	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST;
+	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED;
 
 	/* Nothing to do? Dropping the reference was all we needed? */
 	if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
@@ -776,6 +776,9 @@
 	if (unlikely(d_unhashed(dentry)))
 		goto kill_it;
 
+	if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED))
+		goto kill_it;
+
 	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) {
 		if (dentry->d_op->d_delete(dentry))
 			goto kill_it;
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 72afcc6..feef8a9 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -325,7 +325,6 @@
 		return rc;
 
 	switch (cmd) {
-	case FITRIM:
 	case FS_IOC32_GETFLAGS:
 	case FS_IOC32_SETFLAGS:
 	case FS_IOC32_GETVERSION:
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index aadb728..2553aa8 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -504,7 +504,7 @@
 	struct buffer_head		*bh;
 	int				err;
 
-	bh = sb_getblk(inode->i_sb, pblk);
+	bh = sb_getblk_gfp(inode->i_sb, pblk, __GFP_MOVABLE | GFP_NOFS);
 	if (unlikely(!bh))
 		return ERR_PTR(-ENOMEM);
 
@@ -1089,7 +1089,7 @@
 		err = -EIO;
 		goto cleanup;
 	}
-	bh = sb_getblk(inode->i_sb, newblock);
+	bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
 	if (unlikely(!bh)) {
 		err = -ENOMEM;
 		goto cleanup;
@@ -1283,7 +1283,7 @@
 	if (newblock == 0)
 		return err;
 
-	bh = sb_getblk(inode->i_sb, newblock);
+	bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
 	if (unlikely(!bh))
 		return -ENOMEM;
 	lock_buffer(bh);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 41f8e55..cecf9aa 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1323,7 +1323,7 @@
 					     unsigned int offset,
 					     unsigned int length)
 {
-	int to_release = 0;
+	int to_release = 0, contiguous_blks = 0;
 	struct buffer_head *head, *bh;
 	unsigned int curr_off = 0;
 	struct inode *inode = page->mapping->host;
@@ -1344,14 +1344,23 @@
 
 		if ((offset <= curr_off) && (buffer_delay(bh))) {
 			to_release++;
+			contiguous_blks++;
 			clear_buffer_delay(bh);
+		} else if (contiguous_blks) {
+			lblk = page->index <<
+			       (PAGE_CACHE_SHIFT - inode->i_blkbits);
+			lblk += (curr_off >> inode->i_blkbits) -
+				contiguous_blks;
+			ext4_es_remove_extent(inode, lblk, contiguous_blks);
+			contiguous_blks = 0;
 		}
 		curr_off = next_off;
 	} while ((bh = bh->b_this_page) != head);
 
-	if (to_release) {
+	if (contiguous_blks) {
 		lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
-		ext4_es_remove_extent(inode, lblk, to_release);
+		lblk += (curr_off >> inode->i_blkbits) - contiguous_blks;
+		ext4_es_remove_extent(inode, lblk, contiguous_blks);
 	}
 
 	/* If we have released all the blocks belonging to a cluster, then we
@@ -4344,7 +4353,12 @@
 	int inode_size = EXT4_INODE_SIZE(sb);
 
 	oi.orig_ino = orig_ino;
-	ino = (orig_ino & ~(inodes_per_block - 1)) + 1;
+	/*
+	 * Calculate the first inode in the inode table block.  Inode
+	 * numbers are one-based.  That is, the first inode in a block
+	 * (assuming 4k blocks and 256 byte inodes) is (n*16 + 1).
+	 */
+	ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1;
 	for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
 		if (ino == orig_ino)
 			continue;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index cb84512..1346cfa 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -755,7 +755,6 @@
 		return err;
 	}
 	case EXT4_IOC_MOVE_EXT:
-	case FITRIM:
 	case EXT4_IOC_RESIZE_FS:
 	case EXT4_IOC_PRECACHE_EXTENTS:
 	case EXT4_IOC_SET_ENCRYPTION_POLICY:
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f6aedf8..34b610e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4816,18 +4816,12 @@
 		/*
 		 * blocks being freed are metadata. these blocks shouldn't
 		 * be used until this transaction is committed
+		 *
+		 * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed
+		 * to fail.
 		 */
-	retry:
-		new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
-		if (!new_entry) {
-			/*
-			 * We use a retry loop because
-			 * ext4_free_blocks() is not allowed to fail.
-			 */
-			cond_resched();
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
-			goto retry;
-		}
+		new_entry = kmem_cache_alloc(ext4_free_data_cachep,
+				GFP_NOFS|__GFP_NOFAIL);
 		new_entry->efd_start_cluster = bit;
 		new_entry->efd_group = block_group;
 		new_entry->efd_count = count_clusters;
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index b52374e..6163ad2 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -620,6 +620,7 @@
 	struct ext4_inode_info		*ei = EXT4_I(inode);
 	struct ext4_extent		*ex;
 	unsigned int			i, len;
+	ext4_lblk_t			start, end;
 	ext4_fsblk_t			blk;
 	handle_t			*handle;
 	int				ret;
@@ -633,6 +634,14 @@
 				       EXT4_FEATURE_RO_COMPAT_BIGALLOC))
 		return -EOPNOTSUPP;
 
+	/*
+	 * In order to get correct extent info, force all delayed allocation
+	 * blocks to be allocated, otherwise delayed allocation blocks may not
+	 * be reflected and bypass the checks on extent header.
+	 */
+	if (test_opt(inode->i_sb, DELALLOC))
+		ext4_alloc_da_blocks(inode);
+
 	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
@@ -650,11 +659,13 @@
 		goto errout;
 	}
 	if (eh->eh_entries == 0)
-		blk = len = 0;
+		blk = len = start = end = 0;
 	else {
 		len = le16_to_cpu(ex->ee_len);
 		blk = ext4_ext_pblock(ex);
-		if (len > EXT4_NDIR_BLOCKS) {
+		start = le32_to_cpu(ex->ee_block);
+		end = start + len - 1;
+		if (end >= EXT4_NDIR_BLOCKS) {
 			ret = -EOPNOTSUPP;
 			goto errout;
 		}
@@ -662,7 +673,7 @@
 
 	ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
 	memset(ei->i_data, 0, sizeof(ei->i_data));
-	for (i=0; i < len; i++)
+	for (i = start; i <= end; i++)
 		ei->i_data[i] = cpu_to_le32(blk++);
 	ext4_mark_inode_dirty(handle, inode);
 errout:
diff --git a/fs/hpfs/alloc.c b/fs/hpfs/alloc.c
index f005046..d6a4b55 100644
--- a/fs/hpfs/alloc.c
+++ b/fs/hpfs/alloc.c
@@ -484,3 +484,98 @@
 	a->btree.first_free = cpu_to_le16(8);
 	return a;
 }
+
+static unsigned find_run(__le32 *bmp, unsigned *idx)
+{
+	unsigned len;
+	while (tstbits(bmp, *idx, 1)) {
+		(*idx)++;
+		if (unlikely(*idx >= 0x4000))
+			return 0;
+	}
+	len = 1;
+	while (!tstbits(bmp, *idx + len, 1))
+		len++;
+	return len;
+}
+
+static int do_trim(struct super_block *s, secno start, unsigned len, secno limit_start, secno limit_end, unsigned minlen, unsigned *result)
+{
+	int err;
+	secno end;
+	if (fatal_signal_pending(current))
+		return -EINTR;
+	end = start + len;
+	if (start < limit_start)
+		start = limit_start;
+	if (end > limit_end)
+		end = limit_end;
+	if (start >= end)
+		return 0;
+	if (end - start < minlen)
+		return 0;
+	err = sb_issue_discard(s, start, end - start, GFP_NOFS, 0);
+	if (err)
+		return err;
+	*result += end - start;
+	return 0;
+}
+
+int hpfs_trim_fs(struct super_block *s, u64 start, u64 end, u64 minlen, unsigned *result)
+{
+	int err = 0;
+	struct hpfs_sb_info *sbi = hpfs_sb(s);
+	unsigned idx, len, start_bmp, end_bmp;
+	__le32 *bmp;
+	struct quad_buffer_head qbh;
+
+	*result = 0;
+	if (!end || end > sbi->sb_fs_size)
+		end = sbi->sb_fs_size;
+	if (start >= sbi->sb_fs_size)
+		return 0;
+	if (minlen > 0x4000)
+		return 0;
+	if (start < sbi->sb_dirband_start + sbi->sb_dirband_size && end > sbi->sb_dirband_start) {
+		hpfs_lock(s);
+		if (s->s_flags & MS_RDONLY) {
+			err = -EROFS;
+			goto unlock_1;
+		}
+		if (!(bmp = hpfs_map_dnode_bitmap(s, &qbh))) {
+			err = -EIO;
+			goto unlock_1;
+		}
+		idx = 0;
+		while ((len = find_run(bmp, &idx)) && !err) {
+			err = do_trim(s, sbi->sb_dirband_start + idx * 4, len * 4, start, end, minlen, result);
+			idx += len;
+		}
+		hpfs_brelse4(&qbh);
+unlock_1:
+		hpfs_unlock(s);
+	}
+	start_bmp = start >> 14;
+	end_bmp = (end + 0x3fff) >> 14;
+	while (start_bmp < end_bmp && !err) {
+		hpfs_lock(s);
+		if (s->s_flags & MS_RDONLY) {
+			err = -EROFS;
+			goto unlock_2;
+		}
+		if (!(bmp = hpfs_map_bitmap(s, start_bmp, &qbh, "trim"))) {
+			err = -EIO;
+			goto unlock_2;
+		}
+		idx = 0;
+		while ((len = find_run(bmp, &idx)) && !err) {
+			err = do_trim(s, (start_bmp << 14) + idx, len, start, end, minlen, result);
+			idx += len;
+		}
+		hpfs_brelse4(&qbh);
+unlock_2:
+		hpfs_unlock(s);
+		start_bmp++;
+	}
+	return err;
+}
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index 2a8e074..dc540bf 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -327,4 +327,5 @@
 	.iterate	= hpfs_readdir,
 	.release	= hpfs_dir_release,
 	.fsync		= hpfs_file_fsync,
+	.unlocked_ioctl	= hpfs_ioctl,
 };
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 6d8cfe9..7ca28d6 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -203,6 +203,7 @@
 	.release	= hpfs_file_release,
 	.fsync		= hpfs_file_fsync,
 	.splice_read	= generic_file_splice_read,
+	.unlocked_ioctl	= hpfs_ioctl,
 };
 
 const struct inode_operations hpfs_file_iops =
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index bb04b58..c4867b5 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -18,6 +18,8 @@
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/blkdev.h>
 #include <asm/unaligned.h>
 
 #include "hpfs.h"
@@ -200,6 +202,7 @@
 struct dnode *hpfs_alloc_dnode(struct super_block *, secno, dnode_secno *, struct quad_buffer_head *);
 struct fnode *hpfs_alloc_fnode(struct super_block *, secno, fnode_secno *, struct buffer_head **);
 struct anode *hpfs_alloc_anode(struct super_block *, secno, anode_secno *, struct buffer_head **);
+int hpfs_trim_fs(struct super_block *, u64, u64, u64, unsigned *);
 
 /* anode.c */
 
@@ -318,6 +321,7 @@
 void hpfs_error(struct super_block *, const char *, ...);
 int hpfs_stop_cycles(struct super_block *, int, int *, int *, char *);
 unsigned hpfs_get_free_dnodes(struct super_block *);
+long hpfs_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 
 /*
  * local time (HPFS) to GMT (Unix)
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 7cd00d3..68a9bed 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -52,17 +52,20 @@
 }
 
 /* Filesystem error... */
-static char err_buf[1024];
-
 void hpfs_error(struct super_block *s, const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
-	vsnprintf(err_buf, sizeof(err_buf), fmt, args);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	pr_err("filesystem error: %pV", &vaf);
+
 	va_end(args);
 
-	pr_err("filesystem error: %s", err_buf);
 	if (!hpfs_sb(s)->sb_was_error) {
 		if (hpfs_sb(s)->sb_err == 2) {
 			pr_cont("; crashing the system because you wanted it\n");
@@ -196,12 +199,39 @@
 	return 0;
 }
 
+
+long hpfs_ioctl(struct file *file, unsigned cmd, unsigned long arg)
+{
+	switch (cmd) {
+		case FITRIM: {
+			struct fstrim_range range;
+			secno n_trimmed;
+			int r;
+			if (!capable(CAP_SYS_ADMIN))
+				return -EPERM;
+			if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range)))
+				return -EFAULT;
+			r = hpfs_trim_fs(file_inode(file)->i_sb, range.start >> 9, (range.start + range.len) >> 9, (range.minlen + 511) >> 9, &n_trimmed);
+			if (r)
+				return r;
+			range.len = (u64)n_trimmed << 9;
+			if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range)))
+				return -EFAULT;
+			return 0;
+		}
+		default: {
+			return -ENOIOCTLCMD;
+		}
+	}
+}
+
+
 static struct kmem_cache * hpfs_inode_cachep;
 
 static struct inode *hpfs_alloc_inode(struct super_block *sb)
 {
 	struct hpfs_inode_info *ei;
-	ei = (struct hpfs_inode_info *)kmem_cache_alloc(hpfs_inode_cachep, GFP_NOFS);
+	ei = kmem_cache_alloc(hpfs_inode_cachep, GFP_NOFS);
 	if (!ei)
 		return NULL;
 	ei->vfs_inode.i_version = 1;
@@ -424,11 +454,14 @@
 	int o;
 	struct hpfs_sb_info *sbi = hpfs_sb(s);
 	char *new_opts = kstrdup(data, GFP_KERNEL);
-	
+
+	if (!new_opts)
+		return -ENOMEM;
+
 	sync_filesystem(s);
 
 	*flags |= MS_NOATIME;
-	
+
 	hpfs_lock(s);
 	uid = sbi->sb_uid; gid = sbi->sb_gid;
 	umask = 0777 & ~sbi->sb_mode;
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index 93a1232..8db8b7d 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -180,9 +180,6 @@
 	case JFS_IOC_SETFLAGS32:
 		cmd = JFS_IOC_SETFLAGS;
 		break;
-	case FITRIM:
-		cmd = FITRIM;
-		break;
 	}
 	return jfs_ioctl(filp, cmd, arg);
 }
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 9a20e51..aba4381 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1369,7 +1369,6 @@
 	case NILFS_IOCTL_SYNC:
 	case NILFS_IOCTL_RESIZE:
 	case NILFS_IOCTL_SET_ALLOC_RANGE:
-	case FITRIM:
 		break;
 	default:
 		return -ENOIOCTLCMD;
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 53e6c40..3cb097c 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -980,7 +980,6 @@
 	case OCFS2_IOC_GROUP_EXTEND:
 	case OCFS2_IOC_GROUP_ADD:
 	case OCFS2_IOC_GROUP_ADD64:
-	case FITRIM:
 		break;
 	case OCFS2_IOC_REFLINK:
 		if (copy_from_user(&args, argp, sizeof(args)))
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index f140e3db..d9da5a4 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -343,6 +343,9 @@
 	struct path realpath;
 	enum ovl_path_type type;
 
+	if (d_is_dir(dentry))
+		return d_backing_inode(dentry);
+
 	type = ovl_path_real(dentry, &realpath);
 	if (ovl_open_need_copy_up(file_flags, type, realpath.dentry)) {
 		err = ovl_want_write(dentry);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index c471dfc..d2445fa 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -58,6 +58,19 @@
 	acpi_fwnode_handle(adev) : NULL)
 #define ACPI_HANDLE(dev)		acpi_device_handle(ACPI_COMPANION(dev))
 
+/**
+ * ACPI_DEVICE_CLASS - macro used to describe an ACPI device with
+ * the PCI-defined class-code information
+ *
+ * @_cls : the class, subclass, prog-if triple for this device
+ * @_msk : the class mask for this device
+ *
+ * This macro is used to create a struct acpi_device_id that matches a
+ * specific PCI class. The .id and .driver_data fields will be left
+ * initialized with the default value.
+ */
+#define ACPI_DEVICE_CLASS(_cls, _msk)	.cls = (_cls), .cls_msk = (_msk),
+
 static inline bool has_acpi_companion(struct device *dev)
 {
 	return is_acpi_node(dev->fwnode);
@@ -309,9 +322,6 @@
 
 int acpi_resources_are_enforced(void);
 
-int acpi_reserve_region(u64 start, unsigned int length, u8 space_id,
-			unsigned long flags, char *desc);
-
 #ifdef CONFIG_HIBERNATION
 void __init acpi_no_s4_hw_signature(void);
 #endif
@@ -446,6 +456,7 @@
 #define ACPI_COMPANION(dev)		(NULL)
 #define ACPI_COMPANION_SET(dev, adev)	do { } while (0)
 #define ACPI_HANDLE(dev)		(NULL)
+#define ACPI_DEVICE_CLASS(_cls, _msk)	.cls = (0), .cls_msk = (0),
 
 struct fwnode_handle;
 
@@ -507,13 +518,6 @@
 	return 0;
 }
 
-static inline int acpi_reserve_region(u64 start, unsigned int length,
-				      u8 space_id, unsigned long flags,
-				      char *desc)
-{
-	return -ENXIO;
-}
-
 struct acpi_table_header;
 static inline int acpi_table_parse(char *id,
 				int (*handler)(struct acpi_table_header *))
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 73b4522..e6797de 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -317,6 +317,13 @@
 	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
 }
 
+
+static inline struct buffer_head *
+sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp)
+{
+	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp);
+}
+
 static inline struct buffer_head *
 sb_find_get_block(struct super_block *sb, sector_t block)
 {
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index e154994..3775327 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -8,6 +8,7 @@
 #include <linux/radix-tree.h>
 #include <linux/uio.h>
 #include <linux/workqueue.h>
+#include <net/net_namespace.h>
 
 #include <linux/ceph/types.h>
 #include <linux/ceph/buffer.h>
@@ -56,6 +57,7 @@
 	struct ceph_entity_addr my_enc_addr;
 
 	atomic_t stopping;
+	possible_net_t net;
 	bool nocrc;
 	bool tcp_nodelay;
 
@@ -267,6 +269,7 @@
 			u64 required_features,
 			bool nocrc,
 			bool tcp_nodelay);
+extern void ceph_messenger_fini(struct ceph_messenger *msgr);
 
 extern void ceph_con_init(struct ceph_connection *con, void *private,
 			const struct ceph_connection_operations *ops,
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 7f8ad95..e08a6ae 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -17,11 +17,11 @@
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
 # define __percpu	__attribute__((noderef, address_space(3)))
+# define __pmem		__attribute__((noderef, address_space(5)))
 #ifdef CONFIG_SPARSE_RCU_POINTER
 # define __rcu		__attribute__((noderef, address_space(4)))
 #else
 # define __rcu
-# define __pmem		__attribute__((noderef, address_space(5)))
 #endif
 extern void __chk_user_ptr(const volatile void __user *);
 extern void __chk_io_ptr(const volatile void __iomem *);
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 624a668..fcea4e4 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -87,7 +87,12 @@
 	const char		*name;
 } ____cacheline_internodealigned_in_smp;
 
-#ifndef CONFIG_SPARSE_IRQ
+#ifdef CONFIG_SPARSE_IRQ
+extern void irq_lock_sparse(void);
+extern void irq_unlock_sparse(void);
+#else
+static inline void irq_lock_sparse(void) { }
+static inline void irq_unlock_sparse(void) { }
 extern struct irq_desc irq_desc[NR_IRQS];
 #endif
 
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 8183d66..34f25b7 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -189,6 +189,8 @@
 struct acpi_device_id {
 	__u8 id[ACPI_ID_LEN];
 	kernel_ulong_t driver_data;
+	__u32 cls;
+	__u32 cls_msk;
 };
 
 #define PNP_ID_LEN	8
diff --git a/include/linux/rtc/sirfsoc_rtciobrg.h b/include/linux/rtc/sirfsoc_rtciobrg.h
index 2c92e1c..aefd997 100644
--- a/include/linux/rtc/sirfsoc_rtciobrg.h
+++ b/include/linux/rtc/sirfsoc_rtciobrg.h
@@ -9,10 +9,14 @@
 #ifndef _SIRFSOC_RTC_IOBRG_H_
 #define _SIRFSOC_RTC_IOBRG_H_
 
+struct regmap_config;
+
 extern void sirfsoc_rtc_iobrg_besyncing(void);
 
 extern u32 sirfsoc_rtc_iobrg_readl(u32 addr);
 
 extern void sirfsoc_rtc_iobrg_writel(u32 val, u32 addr);
+struct regmap *devm_regmap_init_iobg(struct device *dev,
+				    const struct regmap_config *config);
 
 #endif
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 3741ba1..edbfc9a 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -67,10 +67,13 @@
 static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { }
 #endif /* BROADCAST */
 
-#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state);
 #else
-static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { return 0; }
+static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	return 0;
+}
 #endif
 
 static inline void tick_broadcast_enable(void)
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 3aa72e6..6e191e4 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -145,7 +145,6 @@
 }
 #endif
 
-#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
 #define ktime_get_real_ts64(ts)	getnstimeofday64(ts)
 
 /*
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 09c6564..e85bdfd 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1021,8 +1021,7 @@
 	 * for strings that are too long, we should not have created
 	 * any.
 	 */
-	if (unlikely((len == 0) || len > MAX_ARG_STRLEN - 1)) {
-		WARN_ON(1);
+	if (WARN_ON_ONCE(len < 0 || len > MAX_ARG_STRLEN - 1)) {
 		send_sig(SIGKILL, current, 0);
 		return -1;
 	}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9c9c9fa..6a37454 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -21,6 +21,7 @@
 #include <linux/suspend.h>
 #include <linux/lockdep.h>
 #include <linux/tick.h>
+#include <linux/irq.h>
 #include <trace/events/power.h>
 
 #include "smpboot.h"
@@ -392,13 +393,19 @@
 	smpboot_park_threads(cpu);
 
 	/*
+	 * Prevent irq alloc/free while the dying cpu reorganizes the
+	 * interrupt affinities.
+	 */
+	irq_lock_sparse();
+
+	/*
 	 * So now all preempt/rcu users must observe !cpu_active().
 	 */
-
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
+		irq_unlock_sparse();
 		goto out_release;
 	}
 	BUG_ON(cpu_online(cpu));
@@ -415,6 +422,9 @@
 	smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */
 	per_cpu(cpu_dead_idle, cpu) = false;
 
+	/* Interrupts are moved away from the dying cpu, reenable alloc/free */
+	irq_unlock_sparse();
+
 	hotplug_cpu__broadcast_tick_pull(cpu);
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);
@@ -517,8 +527,18 @@
 		goto out_notify;
 	}
 
+	/*
+	 * Some architectures have to walk the irq descriptors to
+	 * setup the vector space for the cpu which comes online.
+	 * Prevent irq alloc/free across the bringup.
+	 */
+	irq_lock_sparse();
+
 	/* Arch-specific enabling code. */
 	ret = __cpu_up(cpu, idle);
+
+	irq_unlock_sparse();
+
 	if (ret != 0)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e965cfa..d3dae34 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4358,14 +4358,6 @@
 	rcu_read_unlock();
 }
 
-static void rb_free_rcu(struct rcu_head *rcu_head)
-{
-	struct ring_buffer *rb;
-
-	rb = container_of(rcu_head, struct ring_buffer, rcu_head);
-	rb_free(rb);
-}
-
 struct ring_buffer *ring_buffer_get(struct perf_event *event)
 {
 	struct ring_buffer *rb;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 2deb24c..2bbad9c 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -11,6 +11,7 @@
 struct ring_buffer {
 	atomic_t			refcount;
 	struct rcu_head			rcu_head;
+	struct irq_work			irq_work;
 #ifdef CONFIG_PERF_USE_VMALLOC
 	struct work_struct		work;
 	int				page_order;	/* allocation order  */
@@ -55,6 +56,15 @@
 };
 
 extern void rb_free(struct ring_buffer *rb);
+
+static inline void rb_free_rcu(struct rcu_head *rcu_head)
+{
+	struct ring_buffer *rb;
+
+	rb = container_of(rcu_head, struct ring_buffer, rcu_head);
+	rb_free(rb);
+}
+
 extern struct ring_buffer *
 rb_alloc(int nr_pages, long watermark, int cpu, int flags);
 extern void perf_event_wakeup(struct perf_event *event);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 9647282..b2be01b 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -221,6 +221,8 @@
 	rcu_read_unlock();
 }
 
+static void rb_irq_work(struct irq_work *work);
+
 static void
 ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 {
@@ -241,6 +243,16 @@
 
 	INIT_LIST_HEAD(&rb->event_list);
 	spin_lock_init(&rb->event_lock);
+	init_irq_work(&rb->irq_work, rb_irq_work);
+}
+
+static void ring_buffer_put_async(struct ring_buffer *rb)
+{
+	if (!atomic_dec_and_test(&rb->refcount))
+		return;
+
+	rb->rcu_head.next = (void *)rb;
+	irq_work_queue(&rb->irq_work);
 }
 
 /*
@@ -319,7 +331,7 @@
 	rb_free_aux(rb);
 
 err:
-	ring_buffer_put(rb);
+	ring_buffer_put_async(rb);
 	handle->event = NULL;
 
 	return NULL;
@@ -370,7 +382,7 @@
 
 	local_set(&rb->aux_nest, 0);
 	rb_free_aux(rb);
-	ring_buffer_put(rb);
+	ring_buffer_put_async(rb);
 }
 
 /*
@@ -557,7 +569,18 @@
 void rb_free_aux(struct ring_buffer *rb)
 {
 	if (atomic_dec_and_test(&rb->aux_refcount))
+		irq_work_queue(&rb->irq_work);
+}
+
+static void rb_irq_work(struct irq_work *work)
+{
+	struct ring_buffer *rb = container_of(work, struct ring_buffer, irq_work);
+
+	if (!atomic_read(&rb->aux_refcount))
 		__rb_free_aux(rb);
+
+	if (rb->rcu_head.next == (void *)rb)
+		call_rcu(&rb->rcu_head, rb_free_rcu);
 }
 
 #ifndef CONFIG_PERF_USE_VMALLOC
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 4834ee8..61008b8 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -76,12 +76,8 @@
 
 #ifdef CONFIG_SPARSE_IRQ
 static inline void irq_mark_irq(unsigned int irq) { }
-extern void irq_lock_sparse(void);
-extern void irq_unlock_sparse(void);
 #else
 extern void irq_mark_irq(unsigned int irq);
-static inline void irq_lock_sparse(void) { }
-static inline void irq_unlock_sparse(void) { }
 #endif
 
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
diff --git a/kernel/module.c b/kernel/module.c
index 3e0e197..4d2b82e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3557,6 +3557,7 @@
 	mutex_lock(&module_mutex);
 	/* Unlink carefully: kallsyms could be walking list. */
 	list_del_rcu(&mod->list);
+	mod_tree_remove(mod);
 	wake_up_all(&module_wq);
 	/* Wait for RCU-sched synchronizing before releasing mod->list. */
 	synchronize_sched();
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 08ccc3d..50eb107 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -120,19 +120,25 @@
 		/* The clockevent device is getting replaced. Shut it down. */
 
 	case CLOCK_EVT_STATE_SHUTDOWN:
-		return dev->set_state_shutdown(dev);
+		if (dev->set_state_shutdown)
+			return dev->set_state_shutdown(dev);
+		return 0;
 
 	case CLOCK_EVT_STATE_PERIODIC:
 		/* Core internal bug */
 		if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC))
 			return -ENOSYS;
-		return dev->set_state_periodic(dev);
+		if (dev->set_state_periodic)
+			return dev->set_state_periodic(dev);
+		return 0;
 
 	case CLOCK_EVT_STATE_ONESHOT:
 		/* Core internal bug */
 		if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
 			return -ENOSYS;
-		return dev->set_state_oneshot(dev);
+		if (dev->set_state_oneshot)
+			return dev->set_state_oneshot(dev);
+		return 0;
 
 	case CLOCK_EVT_STATE_ONESHOT_STOPPED:
 		/* Core internal bug */
@@ -471,18 +477,6 @@
 	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
 		return 0;
 
-	/* New state-specific callbacks */
-	if (!dev->set_state_shutdown)
-		return -EINVAL;
-
-	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
-	    !dev->set_state_periodic)
-		return -EINVAL;
-
-	if ((dev->features & CLOCK_EVT_FEAT_ONESHOT) &&
-	    !dev->set_state_oneshot)
-		return -EINVAL;
-
 	return 0;
 }
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index d39f32c..52b9e19 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -159,7 +159,7 @@
 {
 	struct clock_event_device *bc = tick_broadcast_device.evtdev;
 	unsigned long flags;
-	int ret;
+	int ret = 0;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -221,13 +221,14 @@
 			 * If we kept the cpu in the broadcast mask,
 			 * tell the caller to leave the per cpu device
 			 * in shutdown state. The periodic interrupt
-			 * is delivered by the broadcast device.
+			 * is delivered by the broadcast device, if
+			 * the broadcast device exists and is not
+			 * hrtimer based.
 			 */
-			ret = cpumask_test_cpu(cpu, tick_broadcast_mask);
+			if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+				ret = cpumask_test_cpu(cpu, tick_broadcast_mask);
 			break;
 		default:
-			/* Nothing to do */
-			ret = 0;
 			break;
 		}
 	}
@@ -265,8 +266,22 @@
 	 * Check, if the current cpu is in the mask
 	 */
 	if (cpumask_test_cpu(cpu, mask)) {
+		struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
 		cpumask_clear_cpu(cpu, mask);
-		local = true;
+		/*
+		 * We only run the local handler, if the broadcast
+		 * device is not hrtimer based. Otherwise we run into
+		 * a hrtimer recursion.
+		 *
+		 * local timer_interrupt()
+		 *   local_handler()
+		 *     expire_hrtimers()
+		 *       bc_handler()
+		 *         local_handler()
+		 *	     expire_hrtimers()
+		 */
+		local = !(bc->features & CLOCK_EVT_FEAT_HRTIMER);
 	}
 
 	if (!cpumask_empty(mask)) {
@@ -301,6 +316,13 @@
 	bool bc_local;
 
 	raw_spin_lock(&tick_broadcast_lock);
+
+	/* Handle spurious interrupts gracefully */
+	if (clockevent_state_shutdown(tick_broadcast_device.evtdev)) {
+		raw_spin_unlock(&tick_broadcast_lock);
+		return;
+	}
+
 	bc_local = tick_do_periodic_broadcast();
 
 	if (clockevent_state_oneshot(dev)) {
@@ -359,8 +381,16 @@
 	case TICK_BROADCAST_ON:
 		cpumask_set_cpu(cpu, tick_broadcast_on);
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
-			if (tick_broadcast_device.mode ==
-			    TICKDEV_MODE_PERIODIC)
+			/*
+			 * Only shutdown the cpu local device, if:
+			 *
+			 * - the broadcast device exists
+			 * - the broadcast device is not a hrtimer based one
+			 * - the broadcast device is in periodic mode to
+			 *   avoid a hickup during switch to oneshot mode
+			 */
+			if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER) &&
+			    tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
 				clockevents_shutdown(dev);
 		}
 		break;
@@ -379,14 +409,16 @@
 		break;
 	}
 
-	if (cpumask_empty(tick_broadcast_mask)) {
-		if (!bc_stopped)
-			clockevents_shutdown(bc);
-	} else if (bc_stopped) {
-		if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-			tick_broadcast_start_periodic(bc);
-		else
-			tick_broadcast_setup_oneshot(bc);
+	if (bc) {
+		if (cpumask_empty(tick_broadcast_mask)) {
+			if (!bc_stopped)
+				clockevents_shutdown(bc);
+		} else if (bc_stopped) {
+			if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
+				tick_broadcast_start_periodic(bc);
+			else
+				tick_broadcast_setup_oneshot(bc);
+		}
 	}
 	raw_spin_unlock(&tick_broadcast_lock);
 }
@@ -662,71 +694,82 @@
 	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 }
 
-/**
- * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode
- * @state:	The target state (enter/exit)
- *
- * The system enters/leaves a state, where affected devices might stop
- * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
- *
- * Called with interrupts disabled, so clockevents_lock is not
- * required here because the local clock event device cannot go away
- * under us.
- */
-int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 {
 	struct clock_event_device *bc, *dev;
-	struct tick_device *td;
 	int cpu, ret = 0;
 	ktime_t now;
 
 	/*
-	 * Periodic mode does not care about the enter/exit of power
-	 * states
+	 * If there is no broadcast device, tell the caller not to go
+	 * into deep idle.
 	 */
-	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-		return 0;
+	if (!tick_broadcast_device.evtdev)
+		return -EBUSY;
 
-	/*
-	 * We are called with preemtion disabled from the depth of the
-	 * idle code, so we can't be moved away.
-	 */
-	td = this_cpu_ptr(&tick_cpu_device);
-	dev = td->evtdev;
-
-	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
-		return 0;
+	dev = this_cpu_ptr(&tick_cpu_device)->evtdev;
 
 	raw_spin_lock(&tick_broadcast_lock);
 	bc = tick_broadcast_device.evtdev;
 	cpu = smp_processor_id();
 
 	if (state == TICK_BROADCAST_ENTER) {
+		/*
+		 * If the current CPU owns the hrtimer broadcast
+		 * mechanism, it cannot go deep idle and we do not add
+		 * the CPU to the broadcast mask. We don't have to go
+		 * through the EXIT path as the local timer is not
+		 * shutdown.
+		 */
+		ret = broadcast_needs_cpu(bc, cpu);
+		if (ret)
+			goto out;
+
+		/*
+		 * If the broadcast device is in periodic mode, we
+		 * return.
+		 */
+		if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
+			/* If it is a hrtimer based broadcast, return busy */
+			if (bc->features & CLOCK_EVT_FEAT_HRTIMER)
+				ret = -EBUSY;
+			goto out;
+		}
+
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
+
+			/* Conditionally shut down the local timer. */
 			broadcast_shutdown_local(bc, dev);
+
 			/*
 			 * We only reprogram the broadcast timer if we
 			 * did not mark ourself in the force mask and
 			 * if the cpu local event is earlier than the
 			 * broadcast event. If the current CPU is in
 			 * the force mask, then we are going to be
-			 * woken by the IPI right away.
+			 * woken by the IPI right away; we return
+			 * busy, so the CPU does not try to go deep
+			 * idle.
 			 */
-			if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) &&
-			    dev->next_event.tv64 < bc->next_event.tv64)
+			if (cpumask_test_cpu(cpu, tick_broadcast_force_mask)) {
+				ret = -EBUSY;
+			} else if (dev->next_event.tv64 < bc->next_event.tv64) {
 				tick_broadcast_set_event(bc, cpu, dev->next_event);
+				/*
+				 * In case of hrtimer broadcasts the
+				 * programming might have moved the
+				 * timer to this cpu. If yes, remove
+				 * us from the broadcast mask and
+				 * return busy.
+				 */
+				ret = broadcast_needs_cpu(bc, cpu);
+				if (ret) {
+					cpumask_clear_cpu(cpu,
+						tick_broadcast_oneshot_mask);
+				}
+			}
 		}
-		/*
-		 * If the current CPU owns the hrtimer broadcast
-		 * mechanism, it cannot go deep idle and we remove the
-		 * CPU from the broadcast mask. We don't have to go
-		 * through the EXIT path as the local timer is not
-		 * shutdown.
-		 */
-		ret = broadcast_needs_cpu(bc, cpu);
-		if (ret)
-			cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	} else {
 		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
@@ -938,6 +981,16 @@
 	return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
 }
 
+#else
+int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+	if (!bc || (bc->features & CLOCK_EVT_FEAT_HRTIMER))
+		return -EBUSY;
+
+	return 0;
+}
 #endif
 
 void __init tick_broadcast_init(void)
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 76446cb..55e13ef 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -343,6 +343,27 @@
 	tick_install_broadcast_device(newdev);
 }
 
+/**
+ * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode
+ * @state:	The target state (enter/exit)
+ *
+ * The system enters/leaves a state, where affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
+ *
+ * Called with interrupts disabled, so clockevents_lock is not
+ * required here because the local clock event device cannot go away
+ * under us.
+ */
+int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+
+	if (!(td->evtdev->features & CLOCK_EVT_FEAT_C3STOP))
+		return 0;
+
+	return __tick_broadcast_oneshot_control(state);
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * Transfer the do_timer job away from a dying cpu.
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index 42fdf49..a4a8d4e 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -71,4 +71,14 @@
 static inline void tick_cancel_sched_timer(int cpu) { }
 #endif
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern int __tick_broadcast_oneshot_control(enum tick_broadcast_state state);
+#else
+static inline int
+__tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	return -EBUSY;
+}
+#endif
+
 #endif
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 777eda7..39f24d6 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -18,10 +18,6 @@
 	  For better error detection enable CONFIG_STACKTRACE,
 	  and add slub_debug=U to boot cmdline.
 
-config KASAN_SHADOW_OFFSET
-	hex
-	default 0xdffffc0000000000 if X86_64
-
 choice
 	prompt "Instrumentation type"
 	depends on KASAN
diff --git a/mm/memory.c b/mm/memory.c
index a84fbb7..388dcf9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2670,6 +2670,10 @@
 
 	pte_unmap(page_table);
 
+	/* File mapping without ->vm_ops ? */
+	if (vma->vm_flags & VM_SHARED)
+		return VM_FAULT_SIGBUS;
+
 	/* Check if we need to add a guard page to the stack */
 	if (check_stack_guard_page(vma, address) < 0)
 		return VM_FAULT_SIGSEGV;
@@ -3099,6 +3103,9 @@
 			- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
 	pte_unmap(page_table);
+	/* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
+	if (!vma->vm_ops->fault)
+		return VM_FAULT_SIGBUS;
 	if (!(flags & FAULT_FLAG_WRITE))
 		return do_read_fault(mm, vma, address, pmd, pgoff, flags,
 				orig_pte);
@@ -3244,13 +3251,12 @@
 	barrier();
 	if (!pte_present(entry)) {
 		if (pte_none(entry)) {
-			if (vma->vm_ops) {
-				if (likely(vma->vm_ops->fault))
-					return do_fault(mm, vma, address, pte,
-							pmd, flags, entry);
-			}
-			return do_anonymous_page(mm, vma, address,
-						 pte, pmd, flags);
+			if (vma->vm_ops)
+				return do_fault(mm, vma, address, pte, pmd,
+						flags, entry);
+
+			return do_anonymous_page(mm, vma, address, pte, pmd,
+					flags);
 		}
 		return do_swap_page(mm, vma, address,
 					pte, pmd, flags, entry);
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index cb7db32..f30329f 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -9,6 +9,7 @@
 #include <keys/ceph-type.h>
 #include <linux/module.h>
 #include <linux/mount.h>
+#include <linux/nsproxy.h>
 #include <linux/parser.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
@@ -16,8 +17,6 @@
 #include <linux/statfs.h>
 #include <linux/string.h>
 #include <linux/vmalloc.h>
-#include <linux/nsproxy.h>
-#include <net/net_namespace.h>
 
 
 #include <linux/ceph/ceph_features.h>
@@ -131,6 +130,13 @@
 	int i;
 	int ret;
 
+	/*
+	 * Don't bother comparing options if network namespaces don't
+	 * match.
+	 */
+	if (!net_eq(current->nsproxy->net_ns, read_pnet(&client->msgr.net)))
+		return -1;
+
 	ret = memcmp(opt1, opt2, ofs);
 	if (ret)
 		return ret;
@@ -335,9 +341,6 @@
 	int err = -ENOMEM;
 	substring_t argstr[MAX_OPT_ARGS];
 
-	if (current->nsproxy->net_ns != &init_net)
-		return ERR_PTR(-EINVAL);
-
 	opt = kzalloc(sizeof(*opt), GFP_KERNEL);
 	if (!opt)
 		return ERR_PTR(-ENOMEM);
@@ -608,6 +611,7 @@
 fail_monc:
 	ceph_monc_stop(&client->monc);
 fail:
+	ceph_messenger_fini(&client->msgr);
 	kfree(client);
 	return ERR_PTR(err);
 }
@@ -621,8 +625,8 @@
 
 	/* unmount */
 	ceph_osdc_stop(&client->osdc);
-
 	ceph_monc_stop(&client->monc);
+	ceph_messenger_fini(&client->msgr);
 
 	ceph_debugfs_client_cleanup(client);
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 1679f47..e3be1d2 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -6,6 +6,7 @@
 #include <linux/inet.h>
 #include <linux/kthread.h>
 #include <linux/net.h>
+#include <linux/nsproxy.h>
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/string.h>
@@ -479,7 +480,7 @@
 	int ret;
 
 	BUG_ON(con->sock);
-	ret = sock_create_kern(&init_net, con->peer_addr.in_addr.ss_family,
+	ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family,
 			       SOCK_STREAM, IPPROTO_TCP, &sock);
 	if (ret)
 		return ret;
@@ -1731,17 +1732,17 @@
 
 static bool addr_is_blank(struct sockaddr_storage *ss)
 {
+	struct in_addr *addr = &((struct sockaddr_in *)ss)->sin_addr;
+	struct in6_addr *addr6 = &((struct sockaddr_in6 *)ss)->sin6_addr;
+
 	switch (ss->ss_family) {
 	case AF_INET:
-		return ((struct sockaddr_in *)ss)->sin_addr.s_addr == 0;
+		return addr->s_addr == htonl(INADDR_ANY);
 	case AF_INET6:
-		return
-		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[0] == 0 &&
-		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[1] == 0 &&
-		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[2] == 0 &&
-		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[3] == 0;
+		return ipv6_addr_any(addr6);
+	default:
+		return true;
 	}
-	return false;
 }
 
 static int addr_port(struct sockaddr_storage *ss)
@@ -2944,11 +2945,18 @@
 	msgr->tcp_nodelay = tcp_nodelay;
 
 	atomic_set(&msgr->stopping, 0);
+	write_pnet(&msgr->net, get_net(current->nsproxy->net_ns));
 
 	dout("%s %p\n", __func__, msgr);
 }
 EXPORT_SYMBOL(ceph_messenger_init);
 
+void ceph_messenger_fini(struct ceph_messenger *msgr)
+{
+	put_net(read_pnet(&msgr->net));
+}
+EXPORT_SYMBOL(ceph_messenger_fini);
+
 static void clear_standby(struct ceph_connection *con)
 {
 	/* come back from STANDBY? */
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index eff7de1..e70fcd1 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -63,6 +63,8 @@
 
 	DEVID(acpi_device_id);
 	DEVID_FIELD(acpi_device_id, id);
+	DEVID_FIELD(acpi_device_id, cls);
+	DEVID_FIELD(acpi_device_id, cls_msk);
 
 	DEVID(pnp_device_id);
 	DEVID_FIELD(pnp_device_id, id);
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 84c86f3..5f20882 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -523,12 +523,40 @@
 }
 ADD_TO_DEVTABLE("serio", serio_device_id, do_serio_entry);
 
-/* looks like: "acpi:ACPI0003 or acpi:PNP0C0B" or "acpi:LNXVIDEO" */
+/* looks like: "acpi:ACPI0003" or "acpi:PNP0C0B" or "acpi:LNXVIDEO" or
+ *             "acpi:bbsspp" (bb=base-class, ss=sub-class, pp=prog-if)
+ *
+ * NOTE: Each driver should use one of the following : _HID, _CIDs
+ *       or _CLS. Also, bb, ss, and pp can be substituted with ??
+ *       as don't care byte.
+ */
 static int do_acpi_entry(const char *filename,
 			void *symval, char *alias)
 {
 	DEF_FIELD_ADDR(symval, acpi_device_id, id);
-	sprintf(alias, "acpi*:%s:*", *id);
+	DEF_FIELD_ADDR(symval, acpi_device_id, cls);
+	DEF_FIELD_ADDR(symval, acpi_device_id, cls_msk);
+
+	if (id && strlen((const char *)*id))
+		sprintf(alias, "acpi*:%s:*", *id);
+	else if (cls) {
+		int i, byte_shift, cnt = 0;
+		unsigned int msk;
+
+		sprintf(&alias[cnt], "acpi*:");
+		cnt = 6;
+		for (i = 1; i <= 3; i++) {
+			byte_shift = 8 * (3-i);
+			msk = (*cls_msk >> byte_shift) & 0xFF;
+			if (msk)
+				sprintf(&alias[cnt], "%02x",
+					(*cls >> byte_shift) & 0xFF);
+			else
+				sprintf(&alias[cnt], "??");
+			cnt += 2;
+		}
+		sprintf(&alias[cnt], ":*");
+	}
 	return 1;
 }
 ADD_TO_DEVTABLE("acpi", acpi_device_id, do_acpi_entry);
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 91ee1b2..12d3db3 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -886,7 +886,8 @@
 #define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \
 		".kprobes.text"
 #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \
-		".fixup", ".entry.text", ".exception.text", ".text.*"
+		".fixup", ".entry.text", ".exception.text", ".text.*", \
+		".coldtext"
 
 #define INIT_SECTIONS      ".init.*"
 #define MEM_INIT_SECTIONS  ".meminit.*"
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 6231081..564079c 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3283,7 +3283,8 @@
 	int rc = 0;
 
 	if (default_noexec &&
-	    (prot & PROT_EXEC) && (!file || (!shared && (prot & PROT_WRITE)))) {
+	    (prot & PROT_EXEC) && (!file || IS_PRIVATE(file_inode(file)) ||
+				   (!shared && (prot & PROT_WRITE)))) {
 		/*
 		 * We are making executable an anonymous mapping or a
 		 * private file mapping that will also be writable.
diff --git a/security/selinux/ss/ebitmap.c b/security/selinux/ss/ebitmap.c
index afe6a26..57644b1 100644
--- a/security/selinux/ss/ebitmap.c
+++ b/security/selinux/ss/ebitmap.c
@@ -153,6 +153,12 @@
 		if (offset == (u32)-1)
 			return 0;
 
+		/* don't waste ebitmap space if the netlabel bitmap is empty */
+		if (bitmap == 0) {
+			offset += EBITMAP_UNIT_SIZE;
+			continue;
+		}
+
 		if (e_iter == NULL ||
 		    offset >= e_iter->startbit + EBITMAP_SIZE) {
 			e_prev = e_iter;
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index f0e7267..9098083 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -41,4 +41,62 @@
 
 #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
 
+#include <linux/types.h>
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(__u8 *)res = *(volatile __u8 *)p; break;
+	case 2: *(__u16 *)res = *(volatile __u16 *)p; break;
+	case 4: *(__u32 *)res = *(volatile __u32 *)p; break;
+	case 8: *(__u64 *)res = *(volatile __u64 *)p; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		barrier();
+	}
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
+	case 2: *(volatile __u16 *)p = *(__u16 *)res; break;
+	case 4: *(volatile __u32 *)p = *(__u32 *)res; break;
+	case 8: *(volatile __u64 *)p = *(__u64 *)res; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)p, (const void *)res, size);
+		barrier();
+	}
+}
+
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
+ * compiler is aware of some particular ordering.  One way to make the
+ * compiler aware of ordering is to put the two invocations of READ_ONCE,
+ * WRITE_ONCE or ACCESS_ONCE() in different C statements.
+ *
+ * In contrast to ACCESS_ONCE these two macros will also work on aggregate
+ * data types like structs or unions. If the size of the accessed data
+ * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
+ * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
+ * compile-time warning.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+
+#define READ_ONCE(x) \
+	({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
+#define WRITE_ONCE(x, val) \
+	({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
 #endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/include/linux/export.h b/tools/include/linux/export.h
deleted file mode 100644
index d07e586..0000000
--- a/tools/include/linux/export.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _TOOLS_LINUX_EXPORT_H_
-#define _TOOLS_LINUX_EXPORT_H_
-
-#define EXPORT_SYMBOL(sym)
-#define EXPORT_SYMBOL_GPL(sym)
-#define EXPORT_SYMBOL_GPL_FUTURE(sym)
-#define EXPORT_UNUSED_SYMBOL(sym)
-#define EXPORT_UNUSED_SYMBOL_GPL(sym)
-
-#endif
diff --git a/tools/include/linux/rbtree.h b/tools/include/linux/rbtree.h
new file mode 100644
index 0000000..1125822
--- /dev/null
+++ b/tools/include/linux/rbtree.h
@@ -0,0 +1,104 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/include/linux/rbtree.h
+
+  To use rbtrees you'll have to implement your own insert and search cores.
+  This will avoid us to use callbacks and to drop drammatically performances.
+  I know it's not the cleaner way,  but in C (not in C++) to get
+  performances and genericity...
+
+  See Documentation/rbtree.txt for documentation and samples.
+*/
+
+#ifndef __TOOLS_LINUX_PERF_RBTREE_H
+#define __TOOLS_LINUX_PERF_RBTREE_H
+
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+
+struct rb_node {
+	unsigned long  __rb_parent_color;
+	struct rb_node *rb_right;
+	struct rb_node *rb_left;
+} __attribute__((aligned(sizeof(long))));
+    /* The alignment might seem pointless, but allegedly CRIS needs it */
+
+struct rb_root {
+	struct rb_node *rb_node;
+};
+
+
+#define rb_parent(r)   ((struct rb_node *)((r)->__rb_parent_color & ~3))
+
+#define RB_ROOT	(struct rb_root) { NULL, }
+#define	rb_entry(ptr, type, member) container_of(ptr, type, member)
+
+#define RB_EMPTY_ROOT(root)  ((root)->rb_node == NULL)
+
+/* 'empty' nodes are nodes that are known not to be inserted in an rbtree */
+#define RB_EMPTY_NODE(node)  \
+	((node)->__rb_parent_color == (unsigned long)(node))
+#define RB_CLEAR_NODE(node)  \
+	((node)->__rb_parent_color = (unsigned long)(node))
+
+
+extern void rb_insert_color(struct rb_node *, struct rb_root *);
+extern void rb_erase(struct rb_node *, struct rb_root *);
+
+
+/* Find logical next and previous nodes in a tree */
+extern struct rb_node *rb_next(const struct rb_node *);
+extern struct rb_node *rb_prev(const struct rb_node *);
+extern struct rb_node *rb_first(const struct rb_root *);
+extern struct rb_node *rb_last(const struct rb_root *);
+
+/* Postorder iteration - always visit the parent after its children */
+extern struct rb_node *rb_first_postorder(const struct rb_root *);
+extern struct rb_node *rb_next_postorder(const struct rb_node *);
+
+/* Fast replacement of a single node without remove/rebalance/add/rebalance */
+extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+			    struct rb_root *root);
+
+static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
+				struct rb_node **rb_link)
+{
+	node->__rb_parent_color = (unsigned long)parent;
+	node->rb_left = node->rb_right = NULL;
+
+	*rb_link = node;
+}
+
+#define rb_entry_safe(ptr, type, member) \
+	({ typeof(ptr) ____ptr = (ptr); \
+	   ____ptr ? rb_entry(____ptr, type, member) : NULL; \
+	})
+
+
+/*
+ * Handy for checking that we are not deleting an entry that is
+ * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
+ * probably should be moved to lib/rbtree.c...
+ */
+static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+	rb_erase(n, root);
+	RB_CLEAR_NODE(n);
+}
+#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
diff --git a/tools/include/linux/rbtree_augmented.h b/tools/include/linux/rbtree_augmented.h
new file mode 100644
index 0000000..43be941
--- /dev/null
+++ b/tools/include/linux/rbtree_augmented.h
@@ -0,0 +1,245 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  (C) 2002  David Woodhouse <dwmw2@infradead.org>
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  tools/linux/include/linux/rbtree_augmented.h
+
+  Copied from:
+  linux/include/linux/rbtree_augmented.h
+*/
+
+#ifndef _TOOLS_LINUX_RBTREE_AUGMENTED_H
+#define _TOOLS_LINUX_RBTREE_AUGMENTED_H
+
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+
+/*
+ * Please note - only struct rb_augment_callbacks and the prototypes for
+ * rb_insert_augmented() and rb_erase_augmented() are intended to be public.
+ * The rest are implementation details you are not expected to depend on.
+ *
+ * See Documentation/rbtree.txt for documentation and samples.
+ */
+
+struct rb_augment_callbacks {
+	void (*propagate)(struct rb_node *node, struct rb_node *stop);
+	void (*copy)(struct rb_node *old, struct rb_node *new);
+	void (*rotate)(struct rb_node *old, struct rb_node *new);
+};
+
+extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+/*
+ * Fixup the rbtree and update the augmented information when rebalancing.
+ *
+ * On insertion, the user must update the augmented information on the path
+ * leading to the inserted node, then call rb_link_node() as usual and
+ * rb_augment_inserted() instead of the usual rb_insert_color() call.
+ * If rb_augment_inserted() rebalances the rbtree, it will callback into
+ * a user provided function to update the augmented information on the
+ * affected subtrees.
+ */
+static inline void
+rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+		    const struct rb_augment_callbacks *augment)
+{
+	__rb_insert_augmented(node, root, augment->rotate);
+}
+
+#define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield,	\
+			     rbtype, rbaugmented, rbcompute)		\
+static inline void							\
+rbname ## _propagate(struct rb_node *rb, struct rb_node *stop)		\
+{									\
+	while (rb != stop) {						\
+		rbstruct *node = rb_entry(rb, rbstruct, rbfield);	\
+		rbtype augmented = rbcompute(node);			\
+		if (node->rbaugmented == augmented)			\
+			break;						\
+		node->rbaugmented = augmented;				\
+		rb = rb_parent(&node->rbfield);				\
+	}								\
+}									\
+static inline void							\
+rbname ## _copy(struct rb_node *rb_old, struct rb_node *rb_new)		\
+{									\
+	rbstruct *old = rb_entry(rb_old, rbstruct, rbfield);		\
+	rbstruct *new = rb_entry(rb_new, rbstruct, rbfield);		\
+	new->rbaugmented = old->rbaugmented;				\
+}									\
+static void								\
+rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new)	\
+{									\
+	rbstruct *old = rb_entry(rb_old, rbstruct, rbfield);		\
+	rbstruct *new = rb_entry(rb_new, rbstruct, rbfield);		\
+	new->rbaugmented = old->rbaugmented;				\
+	old->rbaugmented = rbcompute(old);				\
+}									\
+rbstatic const struct rb_augment_callbacks rbname = {			\
+	rbname ## _propagate, rbname ## _copy, rbname ## _rotate	\
+};
+
+
+#define	RB_RED		0
+#define	RB_BLACK	1
+
+#define __rb_parent(pc)    ((struct rb_node *)(pc & ~3))
+
+#define __rb_color(pc)     ((pc) & 1)
+#define __rb_is_black(pc)  __rb_color(pc)
+#define __rb_is_red(pc)    (!__rb_color(pc))
+#define rb_color(rb)       __rb_color((rb)->__rb_parent_color)
+#define rb_is_red(rb)      __rb_is_red((rb)->__rb_parent_color)
+#define rb_is_black(rb)    __rb_is_black((rb)->__rb_parent_color)
+
+static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
+{
+	rb->__rb_parent_color = rb_color(rb) | (unsigned long)p;
+}
+
+static inline void rb_set_parent_color(struct rb_node *rb,
+				       struct rb_node *p, int color)
+{
+	rb->__rb_parent_color = (unsigned long)p | color;
+}
+
+static inline void
+__rb_change_child(struct rb_node *old, struct rb_node *new,
+		  struct rb_node *parent, struct rb_root *root)
+{
+	if (parent) {
+		if (parent->rb_left == old)
+			parent->rb_left = new;
+		else
+			parent->rb_right = new;
+	} else
+		root->rb_node = new;
+}
+
+extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+
+static __always_inline struct rb_node *
+__rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		     const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *child = node->rb_right, *tmp = node->rb_left;
+	struct rb_node *parent, *rebalance;
+	unsigned long pc;
+
+	if (!tmp) {
+		/*
+		 * Case 1: node to erase has no more than 1 child (easy!)
+		 *
+		 * Note that if there is one child it must be red due to 5)
+		 * and node must be black due to 4). We adjust colors locally
+		 * so as to bypass __rb_erase_color() later on.
+		 */
+		pc = node->__rb_parent_color;
+		parent = __rb_parent(pc);
+		__rb_change_child(node, child, parent, root);
+		if (child) {
+			child->__rb_parent_color = pc;
+			rebalance = NULL;
+		} else
+			rebalance = __rb_is_black(pc) ? parent : NULL;
+		tmp = parent;
+	} else if (!child) {
+		/* Still case 1, but this time the child is node->rb_left */
+		tmp->__rb_parent_color = pc = node->__rb_parent_color;
+		parent = __rb_parent(pc);
+		__rb_change_child(node, tmp, parent, root);
+		rebalance = NULL;
+		tmp = parent;
+	} else {
+		struct rb_node *successor = child, *child2;
+		tmp = child->rb_left;
+		if (!tmp) {
+			/*
+			 * Case 2: node's successor is its right child
+			 *
+			 *    (n)          (s)
+			 *    / \          / \
+			 *  (x) (s)  ->  (x) (c)
+			 *        \
+			 *        (c)
+			 */
+			parent = successor;
+			child2 = successor->rb_right;
+			augment->copy(node, successor);
+		} else {
+			/*
+			 * Case 3: node's successor is leftmost under
+			 * node's right child subtree
+			 *
+			 *    (n)          (s)
+			 *    / \          / \
+			 *  (x) (y)  ->  (x) (y)
+			 *      /            /
+			 *    (p)          (p)
+			 *    /            /
+			 *  (s)          (c)
+			 *    \
+			 *    (c)
+			 */
+			do {
+				parent = successor;
+				successor = tmp;
+				tmp = tmp->rb_left;
+			} while (tmp);
+			parent->rb_left = child2 = successor->rb_right;
+			successor->rb_right = child;
+			rb_set_parent(child, successor);
+			augment->copy(node, successor);
+			augment->propagate(parent, successor);
+		}
+
+		successor->rb_left = tmp = node->rb_left;
+		rb_set_parent(tmp, successor);
+
+		pc = node->__rb_parent_color;
+		tmp = __rb_parent(pc);
+		__rb_change_child(node, successor, tmp, root);
+		if (child2) {
+			successor->__rb_parent_color = pc;
+			rb_set_parent_color(child2, parent, RB_BLACK);
+			rebalance = NULL;
+		} else {
+			unsigned long pc2 = successor->__rb_parent_color;
+			successor->__rb_parent_color = pc;
+			rebalance = __rb_is_black(pc2) ? parent : NULL;
+		}
+		tmp = successor;
+	}
+
+	augment->propagate(tmp, NULL);
+	return rebalance;
+}
+
+static __always_inline void
+rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		   const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
+	if (rebalance)
+		__rb_erase_color(rebalance, root, augment->rotate);
+}
+
+#endif	/* _TOOLS_LINUX_RBTREE_AUGMENTED_H */
diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c
new file mode 100644
index 0000000..17c2b59
--- /dev/null
+++ b/tools/lib/rbtree.c
@@ -0,0 +1,548 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  (C) 2002  David Woodhouse <dwmw2@infradead.org>
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/lib/rbtree.c
+*/
+
+#include <linux/rbtree_augmented.h>
+
+/*
+ * red-black trees properties:  http://en.wikipedia.org/wiki/Rbtree
+ *
+ *  1) A node is either red or black
+ *  2) The root is black
+ *  3) All leaves (NULL) are black
+ *  4) Both children of every red node are black
+ *  5) Every simple path from root to leaves contains the same number
+ *     of black nodes.
+ *
+ *  4 and 5 give the O(log n) guarantee, since 4 implies you cannot have two
+ *  consecutive red nodes in a path and every red node is therefore followed by
+ *  a black. So if B is the number of black nodes on every simple path (as per
+ *  5), then the longest possible path due to 4 is 2B.
+ *
+ *  We shall indicate color with case, where black nodes are uppercase and red
+ *  nodes will be lowercase. Unknown color nodes shall be drawn as red within
+ *  parentheses and have some accompanying text comment.
+ */
+
+static inline void rb_set_black(struct rb_node *rb)
+{
+	rb->__rb_parent_color |= RB_BLACK;
+}
+
+static inline struct rb_node *rb_red_parent(struct rb_node *red)
+{
+	return (struct rb_node *)red->__rb_parent_color;
+}
+
+/*
+ * Helper function for rotations:
+ * - old's parent and color get assigned to new
+ * - old gets assigned new as a parent and 'color' as a color.
+ */
+static inline void
+__rb_rotate_set_parents(struct rb_node *old, struct rb_node *new,
+			struct rb_root *root, int color)
+{
+	struct rb_node *parent = rb_parent(old);
+	new->__rb_parent_color = old->__rb_parent_color;
+	rb_set_parent_color(old, new, color);
+	__rb_change_child(old, new, parent, root);
+}
+
+static __always_inline void
+__rb_insert(struct rb_node *node, struct rb_root *root,
+	    void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	struct rb_node *parent = rb_red_parent(node), *gparent, *tmp;
+
+	while (true) {
+		/*
+		 * Loop invariant: node is red
+		 *
+		 * If there is a black parent, we are done.
+		 * Otherwise, take some corrective action as we don't
+		 * want a red root or two consecutive red nodes.
+		 */
+		if (!parent) {
+			rb_set_parent_color(node, NULL, RB_BLACK);
+			break;
+		} else if (rb_is_black(parent))
+			break;
+
+		gparent = rb_red_parent(parent);
+
+		tmp = gparent->rb_right;
+		if (parent != tmp) {	/* parent == gparent->rb_left */
+			if (tmp && rb_is_red(tmp)) {
+				/*
+				 * Case 1 - color flips
+				 *
+				 *       G            g
+				 *      / \          / \
+				 *     p   u  -->   P   U
+				 *    /            /
+				 *   n            n
+				 *
+				 * However, since g's parent might be red, and
+				 * 4) does not allow this, we need to recurse
+				 * at g.
+				 */
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+				rb_set_parent_color(parent, gparent, RB_BLACK);
+				node = gparent;
+				parent = rb_parent(node);
+				rb_set_parent_color(node, parent, RB_RED);
+				continue;
+			}
+
+			tmp = parent->rb_right;
+			if (node == tmp) {
+				/*
+				 * Case 2 - left rotate at parent
+				 *
+				 *      G             G
+				 *     / \           / \
+				 *    p   U  -->    n   U
+				 *     \           /
+				 *      n         p
+				 *
+				 * This still leaves us in violation of 4), the
+				 * continuation into Case 3 will fix that.
+				 */
+				parent->rb_right = tmp = node->rb_left;
+				node->rb_left = parent;
+				if (tmp)
+					rb_set_parent_color(tmp, parent,
+							    RB_BLACK);
+				rb_set_parent_color(parent, node, RB_RED);
+				augment_rotate(parent, node);
+				parent = node;
+				tmp = node->rb_right;
+			}
+
+			/*
+			 * Case 3 - right rotate at gparent
+			 *
+			 *        G           P
+			 *       / \         / \
+			 *      p   U  -->  n   g
+			 *     /                 \
+			 *    n                   U
+			 */
+			gparent->rb_left = tmp;  /* == parent->rb_right */
+			parent->rb_right = gparent;
+			if (tmp)
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
+			augment_rotate(gparent, parent);
+			break;
+		} else {
+			tmp = gparent->rb_left;
+			if (tmp && rb_is_red(tmp)) {
+				/* Case 1 - color flips */
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+				rb_set_parent_color(parent, gparent, RB_BLACK);
+				node = gparent;
+				parent = rb_parent(node);
+				rb_set_parent_color(node, parent, RB_RED);
+				continue;
+			}
+
+			tmp = parent->rb_left;
+			if (node == tmp) {
+				/* Case 2 - right rotate at parent */
+				parent->rb_left = tmp = node->rb_right;
+				node->rb_right = parent;
+				if (tmp)
+					rb_set_parent_color(tmp, parent,
+							    RB_BLACK);
+				rb_set_parent_color(parent, node, RB_RED);
+				augment_rotate(parent, node);
+				parent = node;
+				tmp = node->rb_left;
+			}
+
+			/* Case 3 - left rotate at gparent */
+			gparent->rb_right = tmp;  /* == parent->rb_left */
+			parent->rb_left = gparent;
+			if (tmp)
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
+			augment_rotate(gparent, parent);
+			break;
+		}
+	}
+}
+
+/*
+ * Inline version for rb_erase() use - we want to be able to inline
+ * and eliminate the dummy_rotate callback there
+ */
+static __always_inline void
+____rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	struct rb_node *node = NULL, *sibling, *tmp1, *tmp2;
+
+	while (true) {
+		/*
+		 * Loop invariants:
+		 * - node is black (or NULL on first iteration)
+		 * - node is not the root (parent is not NULL)
+		 * - All leaf paths going through parent and node have a
+		 *   black node count that is 1 lower than other leaf paths.
+		 */
+		sibling = parent->rb_right;
+		if (node != sibling) {	/* node == parent->rb_left */
+			if (rb_is_red(sibling)) {
+				/*
+				 * Case 1 - left rotate at parent
+				 *
+				 *     P               S
+				 *    / \             / \
+				 *   N   s    -->    p   Sr
+				 *      / \         / \
+				 *     Sl  Sr      N   Sl
+				 */
+				parent->rb_right = tmp1 = sibling->rb_left;
+				sibling->rb_left = parent;
+				rb_set_parent_color(tmp1, parent, RB_BLACK);
+				__rb_rotate_set_parents(parent, sibling, root,
+							RB_RED);
+				augment_rotate(parent, sibling);
+				sibling = tmp1;
+			}
+			tmp1 = sibling->rb_right;
+			if (!tmp1 || rb_is_black(tmp1)) {
+				tmp2 = sibling->rb_left;
+				if (!tmp2 || rb_is_black(tmp2)) {
+					/*
+					 * Case 2 - sibling color flip
+					 * (p could be either color here)
+					 *
+					 *    (p)           (p)
+					 *    / \           / \
+					 *   N   S    -->  N   s
+					 *      / \           / \
+					 *     Sl  Sr        Sl  Sr
+					 *
+					 * This leaves us violating 5) which
+					 * can be fixed by flipping p to black
+					 * if it was red, or by recursing at p.
+					 * p is red when coming from Case 1.
+					 */
+					rb_set_parent_color(sibling, parent,
+							    RB_RED);
+					if (rb_is_red(parent))
+						rb_set_black(parent);
+					else {
+						node = parent;
+						parent = rb_parent(node);
+						if (parent)
+							continue;
+					}
+					break;
+				}
+				/*
+				 * Case 3 - right rotate at sibling
+				 * (p could be either color here)
+				 *
+				 *   (p)           (p)
+				 *   / \           / \
+				 *  N   S    -->  N   Sl
+				 *     / \             \
+				 *    sl  Sr            s
+				 *                       \
+				 *                        Sr
+				 */
+				sibling->rb_left = tmp1 = tmp2->rb_right;
+				tmp2->rb_right = sibling;
+				parent->rb_right = tmp2;
+				if (tmp1)
+					rb_set_parent_color(tmp1, sibling,
+							    RB_BLACK);
+				augment_rotate(sibling, tmp2);
+				tmp1 = sibling;
+				sibling = tmp2;
+			}
+			/*
+			 * Case 4 - left rotate at parent + color flips
+			 * (p and sl could be either color here.
+			 *  After rotation, p becomes black, s acquires
+			 *  p's color, and sl keeps its color)
+			 *
+			 *      (p)             (s)
+			 *      / \             / \
+			 *     N   S     -->   P   Sr
+			 *        / \         / \
+			 *      (sl) sr      N  (sl)
+			 */
+			parent->rb_right = tmp2 = sibling->rb_left;
+			sibling->rb_left = parent;
+			rb_set_parent_color(tmp1, sibling, RB_BLACK);
+			if (tmp2)
+				rb_set_parent(tmp2, parent);
+			__rb_rotate_set_parents(parent, sibling, root,
+						RB_BLACK);
+			augment_rotate(parent, sibling);
+			break;
+		} else {
+			sibling = parent->rb_left;
+			if (rb_is_red(sibling)) {
+				/* Case 1 - right rotate at parent */
+				parent->rb_left = tmp1 = sibling->rb_right;
+				sibling->rb_right = parent;
+				rb_set_parent_color(tmp1, parent, RB_BLACK);
+				__rb_rotate_set_parents(parent, sibling, root,
+							RB_RED);
+				augment_rotate(parent, sibling);
+				sibling = tmp1;
+			}
+			tmp1 = sibling->rb_left;
+			if (!tmp1 || rb_is_black(tmp1)) {
+				tmp2 = sibling->rb_right;
+				if (!tmp2 || rb_is_black(tmp2)) {
+					/* Case 2 - sibling color flip */
+					rb_set_parent_color(sibling, parent,
+							    RB_RED);
+					if (rb_is_red(parent))
+						rb_set_black(parent);
+					else {
+						node = parent;
+						parent = rb_parent(node);
+						if (parent)
+							continue;
+					}
+					break;
+				}
+				/* Case 3 - right rotate at sibling */
+				sibling->rb_right = tmp1 = tmp2->rb_left;
+				tmp2->rb_left = sibling;
+				parent->rb_left = tmp2;
+				if (tmp1)
+					rb_set_parent_color(tmp1, sibling,
+							    RB_BLACK);
+				augment_rotate(sibling, tmp2);
+				tmp1 = sibling;
+				sibling = tmp2;
+			}
+			/* Case 4 - left rotate at parent + color flips */
+			parent->rb_left = tmp2 = sibling->rb_right;
+			sibling->rb_right = parent;
+			rb_set_parent_color(tmp1, sibling, RB_BLACK);
+			if (tmp2)
+				rb_set_parent(tmp2, parent);
+			__rb_rotate_set_parents(parent, sibling, root,
+						RB_BLACK);
+			augment_rotate(parent, sibling);
+			break;
+		}
+	}
+}
+
+/* Non-inline version for rb_erase_augmented() use */
+void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	____rb_erase_color(parent, root, augment_rotate);
+}
+
+/*
+ * Non-augmented rbtree manipulation functions.
+ *
+ * We use dummy augmented callbacks here, and have the compiler optimize them
+ * out of the rb_insert_color() and rb_erase() function definitions.
+ */
+
+static inline void dummy_propagate(struct rb_node *node, struct rb_node *stop) {}
+static inline void dummy_copy(struct rb_node *old, struct rb_node *new) {}
+static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {}
+
+static const struct rb_augment_callbacks dummy_callbacks = {
+	dummy_propagate, dummy_copy, dummy_rotate
+};
+
+void rb_insert_color(struct rb_node *node, struct rb_root *root)
+{
+	__rb_insert(node, root, dummy_rotate);
+}
+
+void rb_erase(struct rb_node *node, struct rb_root *root)
+{
+	struct rb_node *rebalance;
+	rebalance = __rb_erase_augmented(node, root, &dummy_callbacks);
+	if (rebalance)
+		____rb_erase_color(rebalance, root, dummy_rotate);
+}
+
+/*
+ * Augmented rbtree manipulation functions.
+ *
+ * This instantiates the same __always_inline functions as in the non-augmented
+ * case, but this time with user-defined callbacks.
+ */
+
+void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	__rb_insert(node, root, augment_rotate);
+}
+
+/*
+ * This function returns the first node (in sort order) of the tree.
+ */
+struct rb_node *rb_first(const struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_left)
+		n = n->rb_left;
+	return n;
+}
+
+struct rb_node *rb_last(const struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_right)
+		n = n->rb_right;
+	return n;
+}
+
+struct rb_node *rb_next(const struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (RB_EMPTY_NODE(node))
+		return NULL;
+
+	/*
+	 * If we have a right-hand child, go down and then left as far
+	 * as we can.
+	 */
+	if (node->rb_right) {
+		node = node->rb_right;
+		while (node->rb_left)
+			node=node->rb_left;
+		return (struct rb_node *)node;
+	}
+
+	/*
+	 * No right-hand children. Everything down and left is smaller than us,
+	 * so any 'next' node must be in the general direction of our parent.
+	 * Go up the tree; any time the ancestor is a right-hand child of its
+	 * parent, keep going up. First time it's a left-hand child of its
+	 * parent, said parent is our 'next' node.
+	 */
+	while ((parent = rb_parent(node)) && node == parent->rb_right)
+		node = parent;
+
+	return parent;
+}
+
+struct rb_node *rb_prev(const struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (RB_EMPTY_NODE(node))
+		return NULL;
+
+	/*
+	 * If we have a left-hand child, go down and then right as far
+	 * as we can.
+	 */
+	if (node->rb_left) {
+		node = node->rb_left;
+		while (node->rb_right)
+			node=node->rb_right;
+		return (struct rb_node *)node;
+	}
+
+	/*
+	 * No left-hand children. Go up till we find an ancestor which
+	 * is a right-hand child of its parent.
+	 */
+	while ((parent = rb_parent(node)) && node == parent->rb_left)
+		node = parent;
+
+	return parent;
+}
+
+void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+		     struct rb_root *root)
+{
+	struct rb_node *parent = rb_parent(victim);
+
+	/* Set the surrounding nodes to point to the replacement */
+	__rb_change_child(victim, new, parent, root);
+	if (victim->rb_left)
+		rb_set_parent(victim->rb_left, new);
+	if (victim->rb_right)
+		rb_set_parent(victim->rb_right, new);
+
+	/* Copy the pointers/colour from the victim to the replacement */
+	*new = *victim;
+}
+
+static struct rb_node *rb_left_deepest_node(const struct rb_node *node)
+{
+	for (;;) {
+		if (node->rb_left)
+			node = node->rb_left;
+		else if (node->rb_right)
+			node = node->rb_right;
+		else
+			return (struct rb_node *)node;
+	}
+}
+
+struct rb_node *rb_next_postorder(const struct rb_node *node)
+{
+	const struct rb_node *parent;
+	if (!node)
+		return NULL;
+	parent = rb_parent(node);
+
+	/* If we're sitting on node, we've already seen our children */
+	if (parent && node == parent->rb_left && parent->rb_right) {
+		/* If we are the parent's left node, go to the parent's right
+		 * node then all the way down to the left */
+		return rb_left_deepest_node(parent->rb_right);
+	} else
+		/* Otherwise we are the parent's right node, and the parent
+		 * should be next */
+		return (struct rb_node *)parent;
+}
+
+struct rb_node *rb_first_postorder(const struct rb_root *root)
+{
+	if (!root->rb_node)
+		return NULL;
+
+	return rb_left_deepest_node(root->rb_node);
+}
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index fe50a1b..09dc0aa 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -18,6 +18,7 @@
 tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
 tools/lib/api
+tools/lib/rbtree.c
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/util/find_next_bit.c
@@ -44,6 +45,8 @@
 tools/include/linux/list.h
 tools/include/linux/log2.h
 tools/include/linux/poison.h
+tools/include/linux/rbtree.h
+tools/include/linux/rbtree_augmented.h
 tools/include/linux/types.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
@@ -51,12 +54,10 @@
 include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
 include/linux/perf_event.h
-include/linux/rbtree.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
 lib/hweight.c
-lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h
@@ -65,7 +66,6 @@
 arch/*/lib/memset*.S
 include/linux/poison.h
 include/linux/hw_breakpoint.h
-include/linux/rbtree_augmented.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/const.h
 include/uapi/linux/swab.h
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 586a59d..601d114 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -139,7 +139,7 @@
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c FORCE
+$(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
diff --git a/tools/perf/util/include/linux/rbtree.h b/tools/perf/util/include/linux/rbtree.h
deleted file mode 100644
index f06d89f..0000000
--- a/tools/perf/util/include/linux/rbtree.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __TOOLS_LINUX_PERF_RBTREE_H
-#define __TOOLS_LINUX_PERF_RBTREE_H
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree.h"
-
-/*
- * Handy for checking that we are not deleting an entry that is
- * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
- * probably should be moved to lib/rbtree.c...
- */
-static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
-{
-	rb_erase(n, root);
-	RB_CLEAR_NODE(n);
-}
-#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
diff --git a/tools/perf/util/include/linux/rbtree_augmented.h b/tools/perf/util/include/linux/rbtree_augmented.h
deleted file mode 100644
index 9d6fcdf..0000000
--- a/tools/perf/util/include/linux/rbtree_augmented.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree_augmented.h"
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index 8e9b645..f56914c 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -1,3 +1,6 @@
+ldflags-y += --wrap=ioremap_wt
+ldflags-y += --wrap=ioremap_wc
+ldflags-y += --wrap=devm_ioremap_nocache
 ldflags-y += --wrap=ioremap_cache
 ldflags-y += --wrap=ioremap_nocache
 ldflags-y += --wrap=iounmap
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index c85a6f6..64bfaa5 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -65,6 +65,21 @@
 	return fallback_fn(offset, size);
 }
 
+void __iomem *__wrap_devm_ioremap_nocache(struct device *dev,
+		resource_size_t offset, unsigned long size)
+{
+	struct nfit_test_resource *nfit_res;
+
+	rcu_read_lock();
+	nfit_res = get_nfit_res(offset);
+	rcu_read_unlock();
+	if (nfit_res)
+		return (void __iomem *) nfit_res->buf + offset
+			- nfit_res->res->start;
+	return devm_ioremap_nocache(dev, offset, size);
+}
+EXPORT_SYMBOL(__wrap_devm_ioremap_nocache);
+
 void __iomem *__wrap_ioremap_cache(resource_size_t offset, unsigned long size)
 {
 	return __nfit_test_ioremap(offset, size, ioremap_cache);
@@ -77,6 +92,18 @@
 }
 EXPORT_SYMBOL(__wrap_ioremap_nocache);
 
+void __iomem *__wrap_ioremap_wt(resource_size_t offset, unsigned long size)
+{
+	return __nfit_test_ioremap(offset, size, ioremap_wt);
+}
+EXPORT_SYMBOL(__wrap_ioremap_wt);
+
+void __iomem *__wrap_ioremap_wc(resource_size_t offset, unsigned long size)
+{
+	return __nfit_test_ioremap(offset, size, ioremap_wc);
+}
+EXPORT_SYMBOL(__wrap_ioremap_wc);
+
 void __wrap_iounmap(volatile void __iomem *addr)
 {
 	struct nfit_test_resource *nfit_res;
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 4b69b83..d0bdae4 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -128,6 +128,8 @@
 	int num_pm;
 	void **dimm;
 	dma_addr_t *dimm_dma;
+	void **flush;
+	dma_addr_t *flush_dma;
 	void **label;
 	dma_addr_t *label_dma;
 	void **spa_set;
@@ -155,7 +157,7 @@
 	int i, rc;
 
 	if (!nfit_mem || !test_bit(cmd, &nfit_mem->dsm_mask))
-		return -ENXIO;
+		return -ENOTTY;
 
 	/* lookup label space for the given dimm */
 	for (i = 0; i < ARRAY_SIZE(handle); i++)
@@ -331,7 +333,8 @@
 			+ sizeof(struct acpi_nfit_system_address) * NUM_SPA
 			+ sizeof(struct acpi_nfit_memory_map) * NUM_MEM
 			+ sizeof(struct acpi_nfit_control_region) * NUM_DCR
-			+ sizeof(struct acpi_nfit_data_region) * NUM_BDW;
+			+ sizeof(struct acpi_nfit_data_region) * NUM_BDW
+			+ sizeof(struct acpi_nfit_flush_address) * NUM_DCR;
 	int i;
 
 	t->nfit_buf = test_alloc(t, nfit_size, &t->nfit_dma);
@@ -356,6 +359,10 @@
 		if (!t->label[i])
 			return -ENOMEM;
 		sprintf(t->label[i], "label%d", i);
+
+		t->flush[i] = test_alloc(t, 8, &t->flush_dma[i]);
+		if (!t->flush[i])
+			return -ENOMEM;
 	}
 
 	for (i = 0; i < NUM_DCR; i++) {
@@ -408,6 +415,7 @@
 	struct acpi_nfit_system_address *spa;
 	struct acpi_nfit_control_region *dcr;
 	struct acpi_nfit_data_region *bdw;
+	struct acpi_nfit_flush_address *flush;
 	unsigned int offset;
 
 	nfit_test_init_header(nfit_buf, size);
@@ -831,6 +839,39 @@
 	bdw->capacity = DIMM_SIZE;
 	bdw->start_address = 0;
 
+	offset = offset + sizeof(struct acpi_nfit_data_region) * 4;
+	/* flush0 (dimm0) */
+	flush = nfit_buf + offset;
+	flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
+	flush->header.length = sizeof(struct acpi_nfit_flush_address);
+	flush->device_handle = handle[0];
+	flush->hint_count = 1;
+	flush->hint_address[0] = t->flush_dma[0];
+
+	/* flush1 (dimm1) */
+	flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 1;
+	flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
+	flush->header.length = sizeof(struct acpi_nfit_flush_address);
+	flush->device_handle = handle[1];
+	flush->hint_count = 1;
+	flush->hint_address[0] = t->flush_dma[1];
+
+	/* flush2 (dimm2) */
+	flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 2;
+	flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
+	flush->header.length = sizeof(struct acpi_nfit_flush_address);
+	flush->device_handle = handle[2];
+	flush->hint_count = 1;
+	flush->hint_address[0] = t->flush_dma[2];
+
+	/* flush3 (dimm3) */
+	flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 3;
+	flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
+	flush->header.length = sizeof(struct acpi_nfit_flush_address);
+	flush->device_handle = handle[3];
+	flush->hint_count = 1;
+	flush->hint_address[0] = t->flush_dma[3];
+
 	acpi_desc = &t->acpi_desc;
 	set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_dsm_force_en);
 	set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_dsm_force_en);
@@ -933,6 +974,10 @@
 				GFP_KERNEL);
 		nfit_test->dimm_dma = devm_kcalloc(dev, num, sizeof(dma_addr_t),
 				GFP_KERNEL);
+		nfit_test->flush = devm_kcalloc(dev, num, sizeof(void *),
+				GFP_KERNEL);
+		nfit_test->flush_dma = devm_kcalloc(dev, num, sizeof(dma_addr_t),
+				GFP_KERNEL);
 		nfit_test->label = devm_kcalloc(dev, num, sizeof(void *),
 				GFP_KERNEL);
 		nfit_test->label_dma = devm_kcalloc(dev, num,
@@ -943,7 +988,8 @@
 				sizeof(dma_addr_t), GFP_KERNEL);
 		if (nfit_test->dimm && nfit_test->dimm_dma && nfit_test->label
 				&& nfit_test->label_dma && nfit_test->dcr
-				&& nfit_test->dcr_dma)
+				&& nfit_test->dcr_dma && nfit_test->flush
+				&& nfit_test->flush_dma)
 			/* pass */;
 		else
 			return -ENOMEM;