Merge tag 'gpio-v3.19-5' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio

Pull gpio fixes from Linus Walleij:
 "Yet more GPIO fixes for the v3.19 series.

  There is a high bug-spot activity in GPIO this merge window, much due
  to Johan Hovolds spearheading into actually exercising the removal
  path for GPIO chips, something that was never really exercised before.

  The other two fixes are augmenting erroneous behaviours in two
  specific drivers for minor systems.

  Summary from signed tag:

   - Two fixes stabilizing that which was never stable before: removal
     of GPIO chips, now let's stop leaking memory.
   - Make sure OMAP IRQs are usable when the irqchip API is used
     orthogonally to the gpiochip API.
   - Provide a default GPIO base for the mcp23s08 driver"

* tag 'gpio-v3.19-5' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio:
  gpio: sysfs: fix memory leak in gpiod_sysfs_set_active_low
  gpio: sysfs: fix memory leak in gpiod_export_link
  gpio: mcp23s08: handle default gpio base
  gpio: omap: Fix bad device access with setup_irq()
diff --git a/Documentation/devicetree/bindings/i2c/i2c-st.txt b/Documentation/devicetree/bindings/i2c/i2c-st.txt
index 437e0db..4c26fda 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-st.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-st.txt
@@ -31,7 +31,7 @@
 	compatible	= "st,comms-ssc4-i2c";
 	reg		= <0xfed40000 0x110>;
 	interrupts	=  <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>;
-	clocks		= <&CLK_S_ICN_REG_0>;
+	clocks		= <&clk_s_a0_ls CLK_ICN_REG>;
 	clock-names	= "ssc";
 	clock-frequency = <400000>;
 	pinctrl-names	= "default";
diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
index 9f4e382..9f41d05 100644
--- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt
+++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
@@ -47,6 +47,7 @@
 dallas,ds4510		CPU Supervisor with Nonvolatile Memory and Programmable I/O
 dallas,ds75		Digital Thermometer and Thermostat
 dlg,da9053		DA9053: flexible system level PMIC with multicore support
+dlg,da9063		DA9063: system PMIC for quad-core application processors
 epson,rx8025		High-Stability. I2C-Bus INTERFACE REAL TIME CLOCK MODULE
 epson,rx8581		I2C-BUS INTERFACE REAL TIME CLOCK MODULE
 fsl,mag3110		MAG3110: Xtrinsic High Accuracy, 3D Magnetometer
diff --git a/MAINTAINERS b/MAINTAINERS
index 2ebb056..aaa039d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -708,6 +708,16 @@
 F:	drivers/staging/iio/*/ad*
 F:	staging/iio/trigger/iio-trig-bfin-timer.c
 
+ANDROID DRIVERS
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+M:	Arve Hjønnevåg <arve@android.com>
+M:	Riley Andrews <riandrews@android.com>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/gregkh/staging.git
+L:	devel@driverdev.osuosl.org
+S:	Supported
+F:	drivers/android/
+F:	drivers/staging/android/
+
 AOA (Apple Onboard Audio) ALSA DRIVER
 M:	Johannes Berg <johannes@sipsolutions.net>
 L:	linuxppc-dev@lists.ozlabs.org
@@ -10166,6 +10176,7 @@
 M:	"Hans J. Koch" <hjk@hansjkoch.de>
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
 F:	Documentation/DocBook/uio-howto.tmpl
 F:	drivers/uio/
 F:	include/linux/uio*.h
diff --git a/Makefile b/Makefile
index 95a0e82..c8e17c0 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 19
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Diseased Newt
 
 # *DOCUMENTATION*
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 98838a0..9d0ac09 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -156,6 +156,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 6f7e3a6..563cb27 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -161,6 +161,8 @@
 
 	if (fault & VM_FAULT_OOM)
 		goto out_of_memory;
+	else if (fault & VM_FAULT_SIGSEGV)
+		goto bad_area;
 	else if (fault & VM_FAULT_SIGBUS)
 		goto do_sigbus;
 
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dts b/arch/arm/boot/dts/imx6sx-sdb.dts
index 8c1febd..c108bb4 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dts
+++ b/arch/arm/boot/dts/imx6sx-sdb.dts
@@ -166,12 +166,12 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		ethphy1: ethernet-phy@0 {
-			reg = <0>;
+		ethphy1: ethernet-phy@1 {
+			reg = <1>;
 		};
 
-		ethphy2: ethernet-phy@1 {
-			reg = <1>;
+		ethphy2: ethernet-phy@2 {
+			reg = <2>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 7b4099f..d5c4669 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -17,14 +17,6 @@
 
 	aliases {
 		ethernet0 = &emac;
-		serial0 = &uart0;
-		serial1 = &uart1;
-		serial2 = &uart2;
-		serial3 = &uart3;
-		serial4 = &uart4;
-		serial5 = &uart5;
-		serial6 = &uart6;
-		serial7 = &uart7;
 	};
 
 	chosen {
@@ -39,6 +31,14 @@
 				 <&ahb_gates 44>;
 			status = "disabled";
 		};
+
+		framebuffer@1 {
+			compatible = "allwinner,simple-framebuffer", "simple-framebuffer";
+			allwinner,pipeline = "de_fe0-de_be0-lcd0-hdmi";
+			clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>,
+				 <&ahb_gates 44>, <&ahb_gates 46>;
+			status = "disabled";
+		};
 	};
 
 	cpus {
@@ -438,8 +438,8 @@
 			reg-names = "phy_ctrl", "pmu1", "pmu2";
 			clocks = <&usb_clk 8>;
 			clock-names = "usb_phy";
-			resets = <&usb_clk 1>, <&usb_clk 2>;
-			reset-names = "usb1_reset", "usb2_reset";
+			resets = <&usb_clk 0>, <&usb_clk 1>, <&usb_clk 2>;
+			reset-names = "usb0_reset", "usb1_reset", "usb2_reset";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
index fe3c559..bfa7428 100644
--- a/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
+++ b/arch/arm/boot/dts/sun5i-a10s-olinuxino-micro.dts
@@ -55,6 +55,12 @@
 	model = "Olimex A10s-Olinuxino Micro";
 	compatible = "olimex,a10s-olinuxino-micro", "allwinner,sun5i-a10s";
 
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart2;
+		serial2 = &uart3;
+	};
+
 	soc@01c00000 {
 		emac: ethernet@01c0b000 {
 			pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index 1b76667..2e7d826 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -18,10 +18,6 @@
 
 	aliases {
 		ethernet0 = &emac;
-		serial0 = &uart0;
-		serial1 = &uart1;
-		serial2 = &uart2;
-		serial3 = &uart3;
 	};
 
 	chosen {
@@ -390,8 +386,8 @@
 			reg-names = "phy_ctrl", "pmu1";
 			clocks = <&usb_clk 8>;
 			clock-names = "usb_phy";
-			resets = <&usb_clk 1>;
-			reset-names = "usb1_reset";
+			resets = <&usb_clk 0>, <&usb_clk 1>;
+			reset-names = "usb0_reset", "usb1_reset";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts b/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts
index eeed1f2..c7be3ab 100644
--- a/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts
+++ b/arch/arm/boot/dts/sun5i-a13-hsg-h702.dts
@@ -53,6 +53,10 @@
 	model = "HSG H702";
 	compatible = "hsg,h702", "allwinner,sun5i-a13";
 
+	aliases {
+		serial0 = &uart1;
+	};
+
 	soc@01c00000 {
 		mmc0: mmc@01c0f000 {
 			pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sun5i-a13-olinuxino-micro.dts b/arch/arm/boot/dts/sun5i-a13-olinuxino-micro.dts
index 916ee8b..3decefb 100644
--- a/arch/arm/boot/dts/sun5i-a13-olinuxino-micro.dts
+++ b/arch/arm/boot/dts/sun5i-a13-olinuxino-micro.dts
@@ -54,6 +54,10 @@
 	model = "Olimex A13-Olinuxino Micro";
 	compatible = "olimex,a13-olinuxino-micro", "allwinner,sun5i-a13";
 
+	aliases {
+		serial0 = &uart1;
+	};
+
 	soc@01c00000 {
 		mmc0: mmc@01c0f000 {
 			pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
index e31d291..b421f7f 100644
--- a/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
+++ b/arch/arm/boot/dts/sun5i-a13-olinuxino.dts
@@ -55,6 +55,10 @@
 	model = "Olimex A13-Olinuxino";
 	compatible = "olimex,a13-olinuxino", "allwinner,sun5i-a13";
 
+	aliases {
+		serial0 = &uart1;
+	};
+
 	soc@01c00000 {
 		mmc0: mmc@01c0f000 {
 			pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index c35217e..c556688 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -16,11 +16,6 @@
 / {
 	interrupt-parent = <&intc>;
 
-	aliases {
-		serial0 = &uart1;
-		serial1 = &uart3;
-	};
-
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -349,8 +344,8 @@
 			reg-names = "phy_ctrl", "pmu1";
 			clocks = <&usb_clk 8>;
 			clock-names = "usb_phy";
-			resets = <&usb_clk 1>;
-			reset-names = "usb1_reset";
+			resets = <&usb_clk 0>, <&usb_clk 1>;
+			reset-names = "usb0_reset", "usb1_reset";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi
index f47156b..1e7e7bc 100644
--- a/arch/arm/boot/dts/sun6i-a31.dtsi
+++ b/arch/arm/boot/dts/sun6i-a31.dtsi
@@ -53,12 +53,6 @@
 	interrupt-parent = <&gic>;
 
 	aliases {
-		serial0 = &uart0;
-		serial1 = &uart1;
-		serial2 = &uart2;
-		serial3 = &uart3;
-		serial4 = &uart4;
-		serial5 = &uart5;
 		ethernet0 = &gmac;
 	};
 
diff --git a/arch/arm/boot/dts/sun7i-a20-bananapi.dts b/arch/arm/boot/dts/sun7i-a20-bananapi.dts
index 1cf1214..bd7b15a 100644
--- a/arch/arm/boot/dts/sun7i-a20-bananapi.dts
+++ b/arch/arm/boot/dts/sun7i-a20-bananapi.dts
@@ -55,6 +55,12 @@
 	model = "LeMaker Banana Pi";
 	compatible = "lemaker,bananapi", "allwinner,sun7i-a20";
 
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart3;
+		serial2 = &uart7;
+	};
+
 	soc@01c00000 {
 		spi0: spi@01c05000 {
 			pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sun7i-a20-hummingbird.dts b/arch/arm/boot/dts/sun7i-a20-hummingbird.dts
index 0e4bfa3..0bcefcb 100644
--- a/arch/arm/boot/dts/sun7i-a20-hummingbird.dts
+++ b/arch/arm/boot/dts/sun7i-a20-hummingbird.dts
@@ -19,6 +19,14 @@
 	model = "Merrii A20 Hummingbird";
 	compatible = "merrii,a20-hummingbird", "allwinner,sun7i-a20";
 
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart2;
+		serial2 = &uart3;
+		serial3 = &uart4;
+		serial4 = &uart5;
+	};
+
 	soc@01c00000 {
 		mmc0: mmc@01c0f000 {
 			pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
index 9d669cdf..66cc777 100644
--- a/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
+++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-micro.dts
@@ -20,6 +20,9 @@
 	compatible = "olimex,a20-olinuxino-micro", "allwinner,sun7i-a20";
 
 	aliases {
+		serial0 = &uart0;
+		serial1 = &uart6;
+		serial2 = &uart7;
 		spi0 = &spi1;
 		spi1 = &spi2;
 	};
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index e21ce59..89749ce 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -54,14 +54,6 @@
 
 	aliases {
 		ethernet0 = &gmac;
-		serial0 = &uart0;
-		serial1 = &uart1;
-		serial2 = &uart2;
-		serial3 = &uart3;
-		serial4 = &uart4;
-		serial5 = &uart5;
-		serial6 = &uart6;
-		serial7 = &uart7;
 	};
 
 	chosen {
diff --git a/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts b/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts
index 7f2117c..32ad808 100644
--- a/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts
+++ b/arch/arm/boot/dts/sun8i-a23-ippo-q8h-v5.dts
@@ -55,6 +55,10 @@
 	model = "Ippo Q8H Dual Core Tablet (v5)";
 	compatible = "ippo,q8h-v5", "allwinner,sun8i-a23";
 
+	aliases {
+		serial0 = &r_uart;
+	};
+
 	chosen {
 		bootargs = "earlyprintk console=ttyS0,115200";
 	};
diff --git a/arch/arm/boot/dts/sun8i-a23.dtsi b/arch/arm/boot/dts/sun8i-a23.dtsi
index 0746cd1..86584fc 100644
--- a/arch/arm/boot/dts/sun8i-a23.dtsi
+++ b/arch/arm/boot/dts/sun8i-a23.dtsi
@@ -52,15 +52,6 @@
 / {
 	interrupt-parent = <&gic>;
 
-	aliases {
-		serial0 = &uart0;
-		serial1 = &uart1;
-		serial2 = &uart2;
-		serial3 = &uart3;
-		serial4 = &uart4;
-		serial5 = &r_uart;
-	};
-
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm/boot/dts/sun9i-a80-optimus.dts b/arch/arm/boot/dts/sun9i-a80-optimus.dts
index 506948f..11ec710 100644
--- a/arch/arm/boot/dts/sun9i-a80-optimus.dts
+++ b/arch/arm/boot/dts/sun9i-a80-optimus.dts
@@ -54,6 +54,11 @@
 	model = "Merrii A80 Optimus Board";
 	compatible = "merrii,a80-optimus", "allwinner,sun9i-a80";
 
+	aliases {
+		serial0 = &uart0;
+		serial1 = &uart4;
+	};
+
 	chosen {
 		bootargs = "earlyprintk console=ttyS0,115200";
 	};
diff --git a/arch/arm/boot/dts/sun9i-a80.dtsi b/arch/arm/boot/dts/sun9i-a80.dtsi
index 494714f..9ef44382 100644
--- a/arch/arm/boot/dts/sun9i-a80.dtsi
+++ b/arch/arm/boot/dts/sun9i-a80.dtsi
@@ -52,16 +52,6 @@
 / {
 	interrupt-parent = <&gic>;
 
-	aliases {
-		serial0 = &uart0;
-		serial1 = &uart1;
-		serial2 = &uart2;
-		serial3 = &uart3;
-		serial4 = &uart4;
-		serial5 = &uart5;
-		serial6 = &r_uart;
-	};
-
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 66ce176..7b01523 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -38,6 +38,16 @@
 	vcpu->arch.hcr = HCR_GUEST_MASK;
 }
 
+static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.hcr;
+}
+
+static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr)
+{
+	vcpu->arch.hcr = hcr;
+}
+
 static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu)
 {
 	return 1;
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 254e065..04b4ea0 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -125,9 +125,6 @@
 	 * Anything that is not used directly from assembly code goes
 	 * here.
 	 */
-	/* dcache set/way operation pending */
-	int last_pcpu;
-	cpumask_t require_dcache_flush;
 
 	/* Don't run the guest on this vcpu */
 	bool pause;
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 63e0ecc..1bca8f8 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -44,6 +44,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/highmem.h>
 #include <asm/cacheflush.h>
 #include <asm/pgalloc.h>
 
@@ -161,13 +162,10 @@
 	return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
 }
 
-static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
-					     unsigned long size,
-					     bool ipa_uncached)
+static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
+					       unsigned long size,
+					       bool ipa_uncached)
 {
-	if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached)
-		kvm_flush_dcache_to_poc((void *)hva, size);
-	
 	/*
 	 * If we are going to insert an instruction page and the icache is
 	 * either VIPT or PIPT, there is a potential problem where the host
@@ -179,18 +177,77 @@
 	 *
 	 * VIVT caches are tagged using both the ASID and the VMID and doesn't
 	 * need any kind of flushing (DDI 0406C.b - Page B3-1392).
+	 *
+	 * We need to do this through a kernel mapping (using the
+	 * user-space mapping has proved to be the wrong
+	 * solution). For that, we need to kmap one page at a time,
+	 * and iterate over the range.
 	 */
-	if (icache_is_pipt()) {
-		__cpuc_coherent_user_range(hva, hva + size);
-	} else if (!icache_is_vivt_asid_tagged()) {
+
+	bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached;
+
+	VM_BUG_ON(size & PAGE_MASK);
+
+	if (!need_flush && !icache_is_pipt())
+		goto vipt_cache;
+
+	while (size) {
+		void *va = kmap_atomic_pfn(pfn);
+
+		if (need_flush)
+			kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+
+		if (icache_is_pipt())
+			__cpuc_coherent_user_range((unsigned long)va,
+						   (unsigned long)va + PAGE_SIZE);
+
+		size -= PAGE_SIZE;
+		pfn++;
+
+		kunmap_atomic(va);
+	}
+
+vipt_cache:
+	if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) {
 		/* any kind of VIPT cache */
 		__flush_icache_all();
 	}
 }
 
+static inline void __kvm_flush_dcache_pte(pte_t pte)
+{
+	void *va = kmap_atomic(pte_page(pte));
+
+	kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+
+	kunmap_atomic(va);
+}
+
+static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
+{
+	unsigned long size = PMD_SIZE;
+	pfn_t pfn = pmd_pfn(pmd);
+
+	while (size) {
+		void *va = kmap_atomic_pfn(pfn);
+
+		kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+
+		pfn++;
+		size -= PAGE_SIZE;
+
+		kunmap_atomic(va);
+	}
+}
+
+static inline void __kvm_flush_dcache_pud(pud_t pud)
+{
+}
+
 #define kvm_virt_to_phys(x)		virt_to_idmap((unsigned long)(x))
 
-void stage2_flush_vm(struct kvm *kvm);
+void kvm_set_way_flush(struct kvm_vcpu *vcpu);
+void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
 
 #endif	/* !__ASSEMBLY__ */
 
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 2d6d910..0b0d58a 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -281,15 +281,6 @@
 	vcpu->cpu = cpu;
 	vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state);
 
-	/*
-	 * Check whether this vcpu requires the cache to be flushed on
-	 * this physical CPU. This is a consequence of doing dcache
-	 * operations by set/way on this vcpu. We do it here to be in
-	 * a non-preemptible section.
-	 */
-	if (cpumask_test_and_clear_cpu(cpu, &vcpu->arch.require_dcache_flush))
-		flush_cache_all(); /* We'd really want v7_flush_dcache_all() */
-
 	kvm_arm_set_running_vcpu(vcpu);
 }
 
@@ -541,7 +532,6 @@
 		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
-		vcpu->arch.last_pcpu = smp_processor_id();
 		kvm_guest_exit();
 		trace_kvm_exit(*vcpu_pc(vcpu));
 		/*
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 7928dbd..f3d88dc 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -189,82 +189,40 @@
 	return true;
 }
 
-/* See note at ARM ARM B1.14.4 */
+/*
+ * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
+ */
 static bool access_dcsw(struct kvm_vcpu *vcpu,
 			const struct coproc_params *p,
 			const struct coproc_reg *r)
 {
-	unsigned long val;
-	int cpu;
-
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p);
 
-	cpu = get_cpu();
-
-	cpumask_setall(&vcpu->arch.require_dcache_flush);
-	cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush);
-
-	/* If we were already preempted, take the long way around */
-	if (cpu != vcpu->arch.last_pcpu) {
-		flush_cache_all();
-		goto done;
-	}
-
-	val = *vcpu_reg(vcpu, p->Rt1);
-
-	switch (p->CRm) {
-	case 6:			/* Upgrade DCISW to DCCISW, as per HCR.SWIO */
-	case 14:		/* DCCISW */
-		asm volatile("mcr p15, 0, %0, c7, c14, 2" : : "r" (val));
-		break;
-
-	case 10:		/* DCCSW */
-		asm volatile("mcr p15, 0, %0, c7, c10, 2" : : "r" (val));
-		break;
-	}
-
-done:
-	put_cpu();
-
+	kvm_set_way_flush(vcpu);
 	return true;
 }
 
 /*
  * Generic accessor for VM registers. Only called as long as HCR_TVM
- * is set.
+ * is set.  If the guest enables the MMU, we stop trapping the VM
+ * sys_regs and leave it in complete control of the caches.
+ *
+ * Used by the cpu-specific code.
  */
-static bool access_vm_reg(struct kvm_vcpu *vcpu,
-			  const struct coproc_params *p,
-			  const struct coproc_reg *r)
+bool access_vm_reg(struct kvm_vcpu *vcpu,
+		   const struct coproc_params *p,
+		   const struct coproc_reg *r)
 {
+	bool was_enabled = vcpu_has_cache_enabled(vcpu);
+
 	BUG_ON(!p->is_write);
 
 	vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1);
 	if (p->is_64bit)
 		vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2);
 
-	return true;
-}
-
-/*
- * SCTLR accessor. Only called as long as HCR_TVM is set.  If the
- * guest enables the MMU, we stop trapping the VM sys_regs and leave
- * it in complete control of the caches.
- *
- * Used by the cpu-specific code.
- */
-bool access_sctlr(struct kvm_vcpu *vcpu,
-		  const struct coproc_params *p,
-		  const struct coproc_reg *r)
-{
-	access_vm_reg(vcpu, p, r);
-
-	if (vcpu_has_cache_enabled(vcpu)) {	/* MMU+Caches enabled? */
-		vcpu->arch.hcr &= ~HCR_TVM;
-		stage2_flush_vm(vcpu->kvm);
-	}
-
+	kvm_toggle_cache(vcpu, was_enabled);
 	return true;
 }
 
diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h
index 1a44bbe..88d24a3 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -153,8 +153,8 @@
 #define is64		.is_64 = true
 #define is32		.is_64 = false
 
-bool access_sctlr(struct kvm_vcpu *vcpu,
-		  const struct coproc_params *p,
-		  const struct coproc_reg *r);
+bool access_vm_reg(struct kvm_vcpu *vcpu,
+		   const struct coproc_params *p,
+		   const struct coproc_reg *r);
 
 #endif /* __ARM_KVM_COPROC_LOCAL_H__ */
diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c
index e6f4ae4..a713675 100644
--- a/arch/arm/kvm/coproc_a15.c
+++ b/arch/arm/kvm/coproc_a15.c
@@ -34,7 +34,7 @@
 static const struct coproc_reg a15_regs[] = {
 	/* SCTLR: swapped by interrupt.S. */
 	{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
-			access_sctlr, reset_val, c1_SCTLR, 0x00C50078 },
+			access_vm_reg, reset_val, c1_SCTLR, 0x00C50078 },
 };
 
 static struct kvm_coproc_target_table a15_target_table = {
diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c
index 17fc7cd..b19e46d 100644
--- a/arch/arm/kvm/coproc_a7.c
+++ b/arch/arm/kvm/coproc_a7.c
@@ -37,7 +37,7 @@
 static const struct coproc_reg a7_regs[] = {
 	/* SCTLR: swapped by interrupt.S. */
 	{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
-			access_sctlr, reset_val, c1_SCTLR, 0x00C50878 },
+			access_vm_reg, reset_val, c1_SCTLR, 0x00C50878 },
 };
 
 static struct kvm_coproc_target_table a7_target_table = {
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 1dc9778..1366625 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -58,6 +58,26 @@
 		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
 }
 
+/*
+ * D-Cache management functions. They take the page table entries by
+ * value, as they are flushing the cache using the kernel mapping (or
+ * kmap on 32bit).
+ */
+static void kvm_flush_dcache_pte(pte_t pte)
+{
+	__kvm_flush_dcache_pte(pte);
+}
+
+static void kvm_flush_dcache_pmd(pmd_t pmd)
+{
+	__kvm_flush_dcache_pmd(pmd);
+}
+
+static void kvm_flush_dcache_pud(pud_t pud)
+{
+	__kvm_flush_dcache_pud(pud);
+}
+
 static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
 				  int min, int max)
 {
@@ -119,6 +139,26 @@
 	put_page(virt_to_page(pmd));
 }
 
+/*
+ * Unmapping vs dcache management:
+ *
+ * If a guest maps certain memory pages as uncached, all writes will
+ * bypass the data cache and go directly to RAM.  However, the CPUs
+ * can still speculate reads (not writes) and fill cache lines with
+ * data.
+ *
+ * Those cache lines will be *clean* cache lines though, so a
+ * clean+invalidate operation is equivalent to an invalidate
+ * operation, because no cache lines are marked dirty.
+ *
+ * Those clean cache lines could be filled prior to an uncached write
+ * by the guest, and the cache coherent IO subsystem would therefore
+ * end up writing old data to disk.
+ *
+ * This is why right after unmapping a page/section and invalidating
+ * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
+ * the IO subsystem will never hit in the cache.
+ */
 static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
 		       phys_addr_t addr, phys_addr_t end)
 {
@@ -128,9 +168,16 @@
 	start_pte = pte = pte_offset_kernel(pmd, addr);
 	do {
 		if (!pte_none(*pte)) {
+			pte_t old_pte = *pte;
+
 			kvm_set_pte(pte, __pte(0));
-			put_page(virt_to_page(pte));
 			kvm_tlb_flush_vmid_ipa(kvm, addr);
+
+			/* No need to invalidate the cache for device mappings */
+			if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+				kvm_flush_dcache_pte(old_pte);
+
+			put_page(virt_to_page(pte));
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
@@ -149,8 +196,13 @@
 		next = kvm_pmd_addr_end(addr, end);
 		if (!pmd_none(*pmd)) {
 			if (kvm_pmd_huge(*pmd)) {
+				pmd_t old_pmd = *pmd;
+
 				pmd_clear(pmd);
 				kvm_tlb_flush_vmid_ipa(kvm, addr);
+
+				kvm_flush_dcache_pmd(old_pmd);
+
 				put_page(virt_to_page(pmd));
 			} else {
 				unmap_ptes(kvm, pmd, addr, next);
@@ -173,8 +225,13 @@
 		next = kvm_pud_addr_end(addr, end);
 		if (!pud_none(*pud)) {
 			if (pud_huge(*pud)) {
+				pud_t old_pud = *pud;
+
 				pud_clear(pud);
 				kvm_tlb_flush_vmid_ipa(kvm, addr);
+
+				kvm_flush_dcache_pud(old_pud);
+
 				put_page(virt_to_page(pud));
 			} else {
 				unmap_pmds(kvm, pud, addr, next);
@@ -209,10 +266,9 @@
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		if (!pte_none(*pte)) {
-			hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
-			kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE);
-		}
+		if (!pte_none(*pte) &&
+		    (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+			kvm_flush_dcache_pte(*pte);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
@@ -226,12 +282,10 @@
 	do {
 		next = kvm_pmd_addr_end(addr, end);
 		if (!pmd_none(*pmd)) {
-			if (kvm_pmd_huge(*pmd)) {
-				hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
-				kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE);
-			} else {
+			if (kvm_pmd_huge(*pmd))
+				kvm_flush_dcache_pmd(*pmd);
+			else
 				stage2_flush_ptes(kvm, pmd, addr, next);
-			}
 		}
 	} while (pmd++, addr = next, addr != end);
 }
@@ -246,12 +300,10 @@
 	do {
 		next = kvm_pud_addr_end(addr, end);
 		if (!pud_none(*pud)) {
-			if (pud_huge(*pud)) {
-				hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
-				kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE);
-			} else {
+			if (pud_huge(*pud))
+				kvm_flush_dcache_pud(*pud);
+			else
 				stage2_flush_pmds(kvm, pud, addr, next);
-			}
 		}
 	} while (pud++, addr = next, addr != end);
 }
@@ -278,7 +330,7 @@
  * Go through the stage 2 page tables and invalidate any cache lines
  * backing memory already mapped to the VM.
  */
-void stage2_flush_vm(struct kvm *kvm)
+static void stage2_flush_vm(struct kvm *kvm)
 {
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
@@ -905,6 +957,12 @@
 	return !pfn_valid(pfn);
 }
 
+static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
+				      unsigned long size, bool uncached)
+{
+	__coherent_cache_guest_page(vcpu, pfn, size, uncached);
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_memory_slot *memslot, unsigned long hva,
 			  unsigned long fault_status)
@@ -994,8 +1052,7 @@
 			kvm_set_s2pmd_writable(&new_pmd);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE,
-					  fault_ipa_uncached);
+		coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached);
 		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
 	} else {
 		pte_t new_pte = pfn_pte(pfn, mem_type);
@@ -1003,8 +1060,7 @@
 			kvm_set_s2pte_writable(&new_pte);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_cache_guest_page(vcpu, hva, PAGE_SIZE,
-					  fault_ipa_uncached);
+		coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached);
 		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
 			pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
 	}
@@ -1411,3 +1467,71 @@
 	unmap_stage2_range(kvm, gpa, size);
 	spin_unlock(&kvm->mmu_lock);
 }
+
+/*
+ * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
+ *
+ * Main problems:
+ * - S/W ops are local to a CPU (not broadcast)
+ * - We have line migration behind our back (speculation)
+ * - System caches don't support S/W at all (damn!)
+ *
+ * In the face of the above, the best we can do is to try and convert
+ * S/W ops to VA ops. Because the guest is not allowed to infer the
+ * S/W to PA mapping, it can only use S/W to nuke the whole cache,
+ * which is a rather good thing for us.
+ *
+ * Also, it is only used when turning caches on/off ("The expected
+ * usage of the cache maintenance instructions that operate by set/way
+ * is associated with the cache maintenance instructions associated
+ * with the powerdown and powerup of caches, if this is required by
+ * the implementation.").
+ *
+ * We use the following policy:
+ *
+ * - If we trap a S/W operation, we enable VM trapping to detect
+ *   caches being turned on/off, and do a full clean.
+ *
+ * - We flush the caches on both caches being turned on and off.
+ *
+ * - Once the caches are enabled, we stop trapping VM ops.
+ */
+void kvm_set_way_flush(struct kvm_vcpu *vcpu)
+{
+	unsigned long hcr = vcpu_get_hcr(vcpu);
+
+	/*
+	 * If this is the first time we do a S/W operation
+	 * (i.e. HCR_TVM not set) flush the whole memory, and set the
+	 * VM trapping.
+	 *
+	 * Otherwise, rely on the VM trapping to wait for the MMU +
+	 * Caches to be turned off. At that point, we'll be able to
+	 * clean the caches again.
+	 */
+	if (!(hcr & HCR_TVM)) {
+		trace_kvm_set_way_flush(*vcpu_pc(vcpu),
+					vcpu_has_cache_enabled(vcpu));
+		stage2_flush_vm(vcpu->kvm);
+		vcpu_set_hcr(vcpu, hcr | HCR_TVM);
+	}
+}
+
+void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled)
+{
+	bool now_enabled = vcpu_has_cache_enabled(vcpu);
+
+	/*
+	 * If switching the MMU+caches on, need to invalidate the caches.
+	 * If switching it off, need to clean the caches.
+	 * Clean + invalidate does the trick always.
+	 */
+	if (now_enabled != was_enabled)
+		stage2_flush_vm(vcpu->kvm);
+
+	/* Caches are now on, stop trapping VM ops (until a S/W op) */
+	if (now_enabled)
+		vcpu_set_hcr(vcpu, vcpu_get_hcr(vcpu) & ~HCR_TVM);
+
+	trace_kvm_toggle_cache(*vcpu_pc(vcpu), was_enabled, now_enabled);
+}
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index b1d640f..b6a6e71 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -223,6 +223,45 @@
 		  __entry->vcpu_pc, __entry->r0, __entry->imm)
 );
 
+TRACE_EVENT(kvm_set_way_flush,
+	    TP_PROTO(unsigned long vcpu_pc, bool cache),
+	    TP_ARGS(vcpu_pc, cache),
+
+	    TP_STRUCT__entry(
+		    __field(	unsigned long,	vcpu_pc		)
+		    __field(	bool,		cache		)
+	    ),
+
+	    TP_fast_assign(
+		    __entry->vcpu_pc		= vcpu_pc;
+		    __entry->cache		= cache;
+	    ),
+
+	    TP_printk("S/W flush at 0x%016lx (cache %s)",
+		      __entry->vcpu_pc, __entry->cache ? "on" : "off")
+);
+
+TRACE_EVENT(kvm_toggle_cache,
+	    TP_PROTO(unsigned long vcpu_pc, bool was, bool now),
+	    TP_ARGS(vcpu_pc, was, now),
+
+	    TP_STRUCT__entry(
+		    __field(	unsigned long,	vcpu_pc		)
+		    __field(	bool,		was		)
+		    __field(	bool,		now		)
+	    ),
+
+	    TP_fast_assign(
+		    __entry->vcpu_pc		= vcpu_pc;
+		    __entry->was		= was;
+		    __entry->now		= now;
+	    ),
+
+	    TP_printk("VM op at 0x%016lx (cache was %s, now %s)",
+		      __entry->vcpu_pc, __entry->was ? "on" : "off",
+		      __entry->now ? "on" : "off")
+);
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index caa21e9..ccef880 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -190,6 +190,13 @@
 	arch_ioremap_caller = armada_pcie_wa_ioremap_caller;
 
 	/*
+	 * We should switch the PL310 to I/O coherency mode only if
+	 * I/O coherency is actually enabled.
+	 */
+	if (!coherency_available())
+		return;
+
+	/*
 	 * Add the PL310 property "arm,io-coherent". This makes sure the
 	 * outer sync operation is not used, which allows to
 	 * workaround the system erratum that causes deadlocks when
diff --git a/arch/arm/mach-shmobile/board-ape6evm.c b/arch/arm/mach-shmobile/board-ape6evm.c
index 66f6781..444f22d 100644
--- a/arch/arm/mach-shmobile/board-ape6evm.c
+++ b/arch/arm/mach-shmobile/board-ape6evm.c
@@ -18,6 +18,8 @@
 #include <linux/gpio_keys.h>
 #include <linux/input.h>
 #include <linux/interrupt.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic.h>
 #include <linux/kernel.h>
 #include <linux/mfd/tmio.h>
 #include <linux/mmc/host.h>
@@ -273,6 +275,22 @@
 				      sizeof(ape6evm_leds_pdata));
 }
 
+static void __init ape6evm_legacy_init_time(void)
+{
+	/* Do not invoke DT-based timers via clocksource_of_init() */
+}
+
+static void __init ape6evm_legacy_init_irq(void)
+{
+	void __iomem *gic_dist_base = ioremap_nocache(0xf1001000, 0x1000);
+	void __iomem *gic_cpu_base = ioremap_nocache(0xf1002000, 0x1000);
+
+	gic_init(0, 29, gic_dist_base, gic_cpu_base);
+
+	/* Do not invoke DT-based interrupt code via irqchip_init() */
+}
+
+
 static const char *ape6evm_boards_compat_dt[] __initdata = {
 	"renesas,ape6evm",
 	NULL,
@@ -280,7 +298,9 @@
 
 DT_MACHINE_START(APE6EVM_DT, "ape6evm")
 	.init_early	= shmobile_init_delay,
+	.init_irq       = ape6evm_legacy_init_irq,
 	.init_machine	= ape6evm_add_standard_devices,
 	.init_late	= shmobile_init_late,
 	.dt_compat	= ape6evm_boards_compat_dt,
+	.init_time	= ape6evm_legacy_init_time,
 MACHINE_END
diff --git a/arch/arm/mach-shmobile/board-lager.c b/arch/arm/mach-shmobile/board-lager.c
index f8197eb..65b128d 100644
--- a/arch/arm/mach-shmobile/board-lager.c
+++ b/arch/arm/mach-shmobile/board-lager.c
@@ -21,6 +21,8 @@
 #include <linux/input.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic.h>
 #include <linux/kernel.h>
 #include <linux/leds.h>
 #include <linux/mfd/tmio.h>
@@ -811,6 +813,16 @@
 					  lager_ksz8041_fixup);
 }
 
+static void __init lager_legacy_init_irq(void)
+{
+	void __iomem *gic_dist_base = ioremap_nocache(0xf1001000, 0x1000);
+	void __iomem *gic_cpu_base = ioremap_nocache(0xf1002000, 0x1000);
+
+	gic_init(0, 29, gic_dist_base, gic_cpu_base);
+
+	/* Do not invoke DT-based interrupt code via irqchip_init() */
+}
+
 static const char * const lager_boards_compat_dt[] __initconst = {
 	"renesas,lager",
 	NULL,
@@ -819,6 +831,7 @@
 DT_MACHINE_START(LAGER_DT, "lager")
 	.smp		= smp_ops(r8a7790_smp_ops),
 	.init_early	= shmobile_init_delay,
+	.init_irq	= lager_legacy_init_irq,
 	.init_time	= rcar_gen2_timer_init,
 	.init_machine	= lager_init,
 	.init_late	= shmobile_init_late,
diff --git a/arch/arm/mach-shmobile/setup-rcar-gen2.c b/arch/arm/mach-shmobile/setup-rcar-gen2.c
index 3dd6edd..cc9470d 100644
--- a/arch/arm/mach-shmobile/setup-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/setup-rcar-gen2.c
@@ -133,7 +133,9 @@
 #ifdef CONFIG_COMMON_CLK
 	rcar_gen2_clocks_init(mode);
 #endif
+#ifdef CONFIG_ARCH_SHMOBILE_MULTI
 	clocksource_of_init();
+#endif
 }
 
 struct memory_reserve_config {
diff --git a/arch/arm/mach-shmobile/timer.c b/arch/arm/mach-shmobile/timer.c
index f1d027a..0edf2a6 100644
--- a/arch/arm/mach-shmobile/timer.c
+++ b/arch/arm/mach-shmobile/timer.c
@@ -70,6 +70,18 @@
 	if (!max_freq)
 		return;
 
+#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
+	/* Non-multiplatform r8a73a4 SoC cannot use arch timer due
+	 * to GIC being initialized from C and arch timer via DT */
+	if (of_machine_is_compatible("renesas,r8a73a4"))
+		has_arch_timer = false;
+
+	/* Non-multiplatform r8a7790 SoC cannot use arch timer due
+	 * to GIC being initialized from C and arch timer via DT */
+	if (of_machine_is_compatible("renesas,r8a7790"))
+		has_arch_timer = false;
+#endif
+
 	if (!has_arch_timer || !IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) {
 		if (is_a7_a8_a9)
 			shmobile_setup_delay_hz(max_freq, 1, 3);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7864797..a673c7f 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1940,18 +1940,8 @@
 }
 EXPORT_SYMBOL_GPL(arm_iommu_release_mapping);
 
-/**
- * arm_iommu_attach_device
- * @dev: valid struct device pointer
- * @mapping: io address space mapping structure (returned from
- *	arm_iommu_create_mapping)
- *
- * Attaches specified io address space mapping to the provided device,
- * More than one client might be attached to the same io address space
- * mapping.
- */
-int arm_iommu_attach_device(struct device *dev,
-			    struct dma_iommu_mapping *mapping)
+static int __arm_iommu_attach_device(struct device *dev,
+				     struct dma_iommu_mapping *mapping)
 {
 	int err;
 
@@ -1965,15 +1955,35 @@
 	pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev));
 	return 0;
 }
-EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
 
 /**
- * arm_iommu_detach_device
+ * arm_iommu_attach_device
  * @dev: valid struct device pointer
+ * @mapping: io address space mapping structure (returned from
+ *	arm_iommu_create_mapping)
  *
- * Detaches the provided device from a previously attached map.
+ * Attaches specified io address space mapping to the provided device.
+ * This replaces the dma operations (dma_map_ops pointer) with the
+ * IOMMU aware version.
+ *
+ * More than one client might be attached to the same io address space
+ * mapping.
  */
-void arm_iommu_detach_device(struct device *dev)
+int arm_iommu_attach_device(struct device *dev,
+			    struct dma_iommu_mapping *mapping)
+{
+	int err;
+
+	err = __arm_iommu_attach_device(dev, mapping);
+	if (err)
+		return err;
+
+	set_dma_ops(dev, &iommu_ops);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
+
+static void __arm_iommu_detach_device(struct device *dev)
 {
 	struct dma_iommu_mapping *mapping;
 
@@ -1989,6 +1999,19 @@
 
 	pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
 }
+
+/**
+ * arm_iommu_detach_device
+ * @dev: valid struct device pointer
+ *
+ * Detaches the provided device from a previously attached map.
+ * This voids the dma operations (dma_map_ops pointer)
+ */
+void arm_iommu_detach_device(struct device *dev)
+{
+	__arm_iommu_detach_device(dev);
+	set_dma_ops(dev, NULL);
+}
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
 static struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent)
@@ -2011,7 +2034,7 @@
 		return false;
 	}
 
-	if (arm_iommu_attach_device(dev, mapping)) {
+	if (__arm_iommu_attach_device(dev, mapping)) {
 		pr_warn("Failed to attached device %s to IOMMU_mapping\n",
 				dev_name(dev));
 		arm_iommu_release_mapping(mapping);
@@ -2025,7 +2048,7 @@
 {
 	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
 
-	arm_iommu_detach_device(dev);
+	__arm_iommu_detach_device(dev);
 	arm_iommu_release_mapping(mapping);
 }
 
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 865a7e2..3cb4c85 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -45,6 +45,16 @@
 		vcpu->arch.hcr_el2 &= ~HCR_RW;
 }
 
+static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.hcr_el2;
+}
+
+static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr)
+{
+	vcpu->arch.hcr_el2 = hcr;
+}
+
 static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
 {
 	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 0b7dfdb..acd101a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -116,9 +116,6 @@
 	 * Anything that is not used directly from assembly code goes
 	 * here.
 	 */
-	/* dcache set/way operation pending */
-	int last_pcpu;
-	cpumask_t require_dcache_flush;
 
 	/* Don't run the guest */
 	bool pause;
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 14a74f1..adcf495 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -243,24 +243,46 @@
 	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
 }
 
-static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
-					     unsigned long size,
-					     bool ipa_uncached)
+static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
+					       unsigned long size,
+					       bool ipa_uncached)
 {
+	void *va = page_address(pfn_to_page(pfn));
+
 	if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached)
-		kvm_flush_dcache_to_poc((void *)hva, size);
+		kvm_flush_dcache_to_poc(va, size);
 
 	if (!icache_is_aliasing()) {		/* PIPT */
-		flush_icache_range(hva, hva + size);
+		flush_icache_range((unsigned long)va,
+				   (unsigned long)va + size);
 	} else if (!icache_is_aivivt()) {	/* non ASID-tagged VIVT */
 		/* any kind of VIPT cache */
 		__flush_icache_all();
 	}
 }
 
+static inline void __kvm_flush_dcache_pte(pte_t pte)
+{
+	struct page *page = pte_page(pte);
+	kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE);
+}
+
+static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
+{
+	struct page *page = pmd_page(pmd);
+	kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE);
+}
+
+static inline void __kvm_flush_dcache_pud(pud_t pud)
+{
+	struct page *page = pud_page(pud);
+	kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
+}
+
 #define kvm_virt_to_phys(x)		__virt_to_phys((unsigned long)(x))
 
-void stage2_flush_vm(struct kvm *kvm);
+void kvm_set_way_flush(struct kvm_vcpu *vcpu);
+void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
 
 #endif /* __ASSEMBLY__ */
 #endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 3d7c2df..f31e8bb 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -69,68 +69,31 @@
 	return ccsidr;
 }
 
-static void do_dc_cisw(u32 val)
-{
-	asm volatile("dc cisw, %x0" : : "r" (val));
-	dsb(ish);
-}
-
-static void do_dc_csw(u32 val)
-{
-	asm volatile("dc csw, %x0" : : "r" (val));
-	dsb(ish);
-}
-
-/* See note at ARM ARM B1.14.4 */
+/*
+ * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
+ */
 static bool access_dcsw(struct kvm_vcpu *vcpu,
 			const struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
-	unsigned long val;
-	int cpu;
-
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p);
 
-	cpu = get_cpu();
-
-	cpumask_setall(&vcpu->arch.require_dcache_flush);
-	cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush);
-
-	/* If we were already preempted, take the long way around */
-	if (cpu != vcpu->arch.last_pcpu) {
-		flush_cache_all();
-		goto done;
-	}
-
-	val = *vcpu_reg(vcpu, p->Rt);
-
-	switch (p->CRm) {
-	case 6:			/* Upgrade DCISW to DCCISW, as per HCR.SWIO */
-	case 14:		/* DCCISW */
-		do_dc_cisw(val);
-		break;
-
-	case 10:		/* DCCSW */
-		do_dc_csw(val);
-		break;
-	}
-
-done:
-	put_cpu();
-
+	kvm_set_way_flush(vcpu);
 	return true;
 }
 
 /*
  * Generic accessor for VM registers. Only called as long as HCR_TVM
- * is set.
+ * is set. If the guest enables the MMU, we stop trapping the VM
+ * sys_regs and leave it in complete control of the caches.
  */
 static bool access_vm_reg(struct kvm_vcpu *vcpu,
 			  const struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
 	unsigned long val;
+	bool was_enabled = vcpu_has_cache_enabled(vcpu);
 
 	BUG_ON(!p->is_write);
 
@@ -143,25 +106,7 @@
 		vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL;
 	}
 
-	return true;
-}
-
-/*
- * SCTLR_EL1 accessor. Only called as long as HCR_TVM is set.  If the
- * guest enables the MMU, we stop trapping the VM sys_regs and leave
- * it in complete control of the caches.
- */
-static bool access_sctlr(struct kvm_vcpu *vcpu,
-			 const struct sys_reg_params *p,
-			 const struct sys_reg_desc *r)
-{
-	access_vm_reg(vcpu, p, r);
-
-	if (vcpu_has_cache_enabled(vcpu)) {	/* MMU+Caches enabled? */
-		vcpu->arch.hcr_el2 &= ~HCR_TVM;
-		stage2_flush_vm(vcpu->kvm);
-	}
-
+	kvm_toggle_cache(vcpu, was_enabled);
 	return true;
 }
 
@@ -377,7 +322,7 @@
 	  NULL, reset_mpidr, MPIDR_EL1 },
 	/* SCTLR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
-	  access_sctlr, reset_val, SCTLR_EL1, 0x00C50078 },
+	  access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
 	/* CPACR_EL1 */
 	{ Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010),
 	  NULL, reset_val, CPACR_EL1, 0 },
@@ -657,7 +602,7 @@
  * register).
  */
 static const struct sys_reg_desc cp15_regs[] = {
-	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR },
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
 	{ Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index 0eca933..d223a8b 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -142,6 +142,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 1790f22..2686a7a 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -176,6 +176,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 9a66372..ec4917d 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -168,6 +168,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 7225dad..ba5ba7a 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -172,6 +172,8 @@
 		 */
 		if (fault & VM_FAULT_OOM) {
 			goto out_of_memory;
+		} else if (fault & VM_FAULT_SIGSEGV) {
+			goto bad_area;
 		} else if (fault & VM_FAULT_SIGBUS) {
 			signal = SIGBUS;
 			goto bad_area;
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index e9c6a80..e3d4d48901 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -200,6 +200,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 2bd7487..b2f04ae 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -145,6 +145,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto map_err;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto bus_err;
 		BUG();
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 332680e..2de5dc6 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -141,6 +141,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index fa4cf52..d46a5eb 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -224,6 +224,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index becc42b..70ab5d6 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -158,6 +158,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 3516cbd..0c2cc5d 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -262,6 +262,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 15a0bb5..34429d5 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -135,6 +135,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 0703acf..230ac20 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -171,6 +171,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 3ca9c11..e5120e6 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -256,6 +256,8 @@
 		 */
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto bad_area;
 		BUG();
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 5a236f0..1b5305d 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -76,7 +76,7 @@
 		if (*flt & VM_FAULT_OOM) {
 			ret = -ENOMEM;
 			goto out_unlock;
-		} else if (*flt & VM_FAULT_SIGBUS) {
+		} else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
 			ret = -EFAULT;
 			goto out_unlock;
 		}
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index eb79907..6154b0a 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -437,6 +437,8 @@
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
+		if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		rc = mm_fault_error(regs, address, fault);
 		if (rc >= MM_FAULT_RETURN)
 			goto bail;
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index b700a32..d2de7d5 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -304,7 +304,7 @@
 	 * all cpus at boot. Get these reg values of current cpu and use the
 	 * same accross all cpus.
 	 */
-	uint64_t lpcr_val = mfspr(SPRN_LPCR);
+	uint64_t lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
 	uint64_t hid0_val = mfspr(SPRN_HID0);
 	uint64_t hid1_val = mfspr(SPRN_HID1);
 	uint64_t hid4_val = mfspr(SPRN_HID4);
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 5b150f0..13c6e20 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -337,6 +337,7 @@
 	args.token = rtas_token("set-indicator");
 	if (args.token == RTAS_UNKNOWN_SERVICE)
 		return;
+	args.token = cpu_to_be32(args.token);
 	args.nargs = cpu_to_be32(3);
 	args.nret = cpu_to_be32(1);
 	args.rets = &args.args[3];
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 811937b..9065d5a 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -374,6 +374,12 @@
 				do_no_context(regs);
 			else
 				pagefault_out_of_memory();
+		} else if (fault & VM_FAULT_SIGSEGV) {
+			/* Kernel mode? Handle exceptions or die */
+			if (!user_mode(regs))
+				do_no_context(regs);
+			else
+				do_sigsegv(regs, SEGV_MAPERR);
 		} else if (fault & VM_FAULT_SIGBUS) {
 			/* Kernel mode? Handle exceptions or die */
 			if (!user_mode(regs))
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 52238983..6860beb 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -114,6 +114,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 541dc61..a58fec9 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -353,6 +353,8 @@
 	} else {
 		if (fault & VM_FAULT_SIGBUS)
 			do_sigbus(regs, error_code, address);
+		else if (fault & VM_FAULT_SIGSEGV)
+			bad_area(regs, error_code, address);
 		else
 			BUG();
 	}
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 908e8c1..70d8171 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -249,6 +249,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 18fcd71..4798232 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -446,6 +446,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 565e25a..0f61a73 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -442,6 +442,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 5678c35..2096173 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -80,6 +80,8 @@
 		if (unlikely(fault & VM_FAULT_ERROR)) {
 			if (fault & VM_FAULT_OOM) {
 				goto out_of_memory;
+			} else if (fault & VM_FAULT_SIGSEGV) {
+				goto out;
 			} else if (fault & VM_FAULT_SIGBUS) {
 				err = -EACCES;
 				goto out;
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index d999398..ad754b4 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -90,7 +90,7 @@
 suffix-$(CONFIG_KERNEL_LZ4) 	:= lz4
 
 RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \
-	     perl $(srctree)/arch/x86/tools/calc_run_size.pl)
+	     $(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh)
 quiet_cmd_mkpiggy = MKPIGGY $@
       cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 944bf01..498b6d9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2431,6 +2431,7 @@
 		break;
 
 	case 55: /* 22nm Atom "Silvermont"                */
+	case 76: /* 14nm Atom "Airmont"                   */
 	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 6e434f8..c4bb8b8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -142,7 +142,7 @@
 	 * or use ldexp(count, -32).
 	 * Watts = Joules/Time delta
 	 */
-	return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
+	return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit);
 }
 
 static u64 rapl_event_update(struct perf_event *event)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 10b8d3e..c635b8b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -840,7 +840,6 @@
 	box->phys_id = phys_id;
 	box->pci_dev = pdev;
 	box->pmu = pmu;
-	uncore_box_init(box);
 	pci_set_drvdata(pdev, box);
 
 	raw_spin_lock(&uncore_box_lock);
@@ -1004,10 +1003,8 @@
 			pmu = &type->pmus[j];
 			box = *per_cpu_ptr(pmu->box, cpu);
 			/* called by uncore_cpu_init? */
-			if (box && box->phys_id >= 0) {
-				uncore_box_init(box);
+			if (box && box->phys_id >= 0)
 				continue;
-			}
 
 			for_each_online_cpu(k) {
 				exist = *per_cpu_ptr(pmu->box, k);
@@ -1023,10 +1020,8 @@
 				}
 			}
 
-			if (box) {
+			if (box)
 				box->phys_id = phys_id;
-				uncore_box_init(box);
-			}
 		}
 	}
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 863d9b0..6c8c1e7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -257,6 +257,14 @@
 	return box->pmu->type->num_counters;
 }
 
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+		if (box->pmu->type->ops->init_box)
+			box->pmu->type->ops->init_box(box);
+	}
+}
+
 static inline void uncore_disable_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->type->ops->disable_box)
@@ -265,6 +273,8 @@
 
 static inline void uncore_enable_box(struct intel_uncore_box *box)
 {
+	uncore_box_init(box);
+
 	if (box->pmu->type->ops->enable_box)
 		box->pmu->type->ops->enable_box(box);
 }
@@ -287,14 +297,6 @@
 	return box->pmu->type->ops->read_counter(box, event);
 }
 
-static inline void uncore_box_init(struct intel_uncore_box *box)
-{
-	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
-		if (box->pmu->type->ops->init_box)
-			box->pmu->type->ops->init_box(box);
-	}
-}
-
 static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
 {
 	return (box->phys_id < 0);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4f0c0b9..d52dcf0 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -192,6 +192,9 @@
 		u16 cid, lid;
 		u32 ldr, aid;
 
+		if (!kvm_apic_present(vcpu))
+			continue;
+
 		aid = kvm_apic_id(apic);
 		ldr = kvm_apic_get_reg(apic, APIC_LDR);
 		cid = apic_cluster_id(new, ldr);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 38dcec4..e3ff27a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -898,6 +898,8 @@
 		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
 			     VM_FAULT_HWPOISON_LARGE))
 			do_sigbus(regs, error_code, address, fault);
+		else if (fault & VM_FAULT_SIGSEGV)
+			bad_area_nosemaphore(regs, error_code, address);
 		else
 			BUG();
 	}
diff --git a/arch/x86/tools/calc_run_size.pl b/arch/x86/tools/calc_run_size.pl
deleted file mode 100644
index 23210ba..0000000
--- a/arch/x86/tools/calc_run_size.pl
+++ /dev/null
@@ -1,39 +0,0 @@
-#!/usr/bin/perl
-#
-# Calculate the amount of space needed to run the kernel, including room for
-# the .bss and .brk sections.
-#
-# Usage:
-# objdump -h a.out | perl calc_run_size.pl
-use strict;
-
-my $mem_size = 0;
-my $file_offset = 0;
-
-my $sections=" *[0-9]+ \.(?:bss|brk) +";
-while (<>) {
-	if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) {
-		my $size = hex($1);
-		my $offset = hex($2);
-		$mem_size += $size;
-		if ($file_offset == 0) {
-			$file_offset = $offset;
-		} elsif ($file_offset != $offset) {
-			# BFD linker shows the same file offset in ELF.
-			# Gold linker shows them as consecutive.
-			next if ($file_offset + $mem_size == $offset + $size);
-
-			printf STDERR "file_offset: 0x%lx\n", $file_offset;
-			printf STDERR "mem_size: 0x%lx\n", $mem_size;
-			printf STDERR "offset: 0x%lx\n", $offset;
-			printf STDERR "size: 0x%lx\n", $size;
-
-			die ".bss and .brk are non-contiguous\n";
-		}
-	}
-}
-
-if ($file_offset == 0) {
-	die "Never found .bss or .brk file offset\n";
-}
-printf("%d\n", $mem_size + $file_offset);
diff --git a/arch/x86/tools/calc_run_size.sh b/arch/x86/tools/calc_run_size.sh
new file mode 100644
index 0000000..1a4c17b
--- /dev/null
+++ b/arch/x86/tools/calc_run_size.sh
@@ -0,0 +1,42 @@
+#!/bin/sh
+#
+# Calculate the amount of space needed to run the kernel, including room for
+# the .bss and .brk sections.
+#
+# Usage:
+# objdump -h a.out | sh calc_run_size.sh
+
+NUM='\([0-9a-fA-F]*[ \t]*\)'
+OUT=$(sed -n 's/^[ \t0-9]*.b[sr][sk][ \t]*'"$NUM$NUM$NUM$NUM"'.*/\1\4/p')
+if [ -z "$OUT" ] ; then
+	echo "Never found .bss or .brk file offset" >&2
+	exit 1
+fi
+
+OUT=$(echo ${OUT# })
+sizeA=$(printf "%d" 0x${OUT%% *})
+OUT=${OUT#* }
+offsetA=$(printf "%d" 0x${OUT%% *})
+OUT=${OUT#* }
+sizeB=$(printf "%d" 0x${OUT%% *})
+OUT=${OUT#* }
+offsetB=$(printf "%d" 0x${OUT%% *})
+
+run_size=$(( $offsetA + $sizeA + $sizeB ))
+
+# BFD linker shows the same file offset in ELF.
+if [ "$offsetA" -ne "$offsetB" ] ; then
+	# Gold linker shows them as consecutive.
+	endB=$(( $offsetB + $sizeB ))
+	if [ "$endB" != "$run_size" ] ; then
+		printf "sizeA: 0x%x\n" $sizeA >&2
+		printf "offsetA: 0x%x\n" $offsetA >&2
+		printf "sizeB: 0x%x\n" $sizeB >&2
+		printf "offsetB: 0x%x\n" $offsetB >&2
+		echo ".bss and .brk are non-contiguous" >&2
+		exit 1
+	fi
+fi
+
+printf "%d\n" $run_size
+exit 0
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index b57c4f9..9e3571a 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -117,6 +117,8 @@
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 694d5a7..c70d6e4 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -134,8 +134,6 @@
 
 source "drivers/platform/Kconfig"
 
-source "drivers/soc/Kconfig"
-
 source "drivers/clk/Kconfig"
 
 source "drivers/hwspinlock/Kconfig"
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 3ec85df..8a86b62 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -2098,32 +2098,26 @@
  * If an image has a non-zero parent overlap, get a reference to its
  * parent.
  *
- * We must get the reference before checking for the overlap to
- * coordinate properly with zeroing the parent overlap in
- * rbd_dev_v2_parent_info() when an image gets flattened.  We
- * drop it again if there is no overlap.
- *
  * Returns true if the rbd device has a parent with a non-zero
  * overlap and a reference for it was successfully taken, or
  * false otherwise.
  */
 static bool rbd_dev_parent_get(struct rbd_device *rbd_dev)
 {
-	int counter;
+	int counter = 0;
 
 	if (!rbd_dev->parent_spec)
 		return false;
 
-	counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
-	if (counter > 0 && rbd_dev->parent_overlap)
-		return true;
-
-	/* Image was flattened, but parent is not yet torn down */
+	down_read(&rbd_dev->header_rwsem);
+	if (rbd_dev->parent_overlap)
+		counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
+	up_read(&rbd_dev->header_rwsem);
 
 	if (counter < 0)
 		rbd_warn(rbd_dev, "parent reference overflow");
 
-	return false;
+	return counter > 0;
 }
 
 /*
@@ -4239,7 +4233,6 @@
 		 */
 		if (rbd_dev->parent_overlap) {
 			rbd_dev->parent_overlap = 0;
-			smp_mb();
 			rbd_dev_parent_put(rbd_dev);
 			pr_info("%s: clone image has been flattened\n",
 				rbd_dev->disk->disk_name);
@@ -4285,7 +4278,6 @@
 	 * treat it specially.
 	 */
 	rbd_dev->parent_overlap = overlap;
-	smp_mb();
 	if (!overlap) {
 
 		/* A null parent_spec indicates it's the initial probe */
@@ -5114,10 +5106,7 @@
 {
 	struct rbd_image_header	*header;
 
-	/* Drop parent reference unless it's already been done (or none) */
-
-	if (rbd_dev->parent_overlap)
-		rbd_dev_parent_put(rbd_dev);
+	rbd_dev_parent_put(rbd_dev);
 
 	/* Free dynamic fields from the header, then zero it out */
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 633532a..25bc47f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -26,6 +26,7 @@
 #include <linux/slab.h>
 #include "kfd_priv.h"
 #include "kfd_device_queue_manager.h"
+#include "kfd_pm4_headers.h"
 
 #define MQD_SIZE_ALIGNED 768
 
@@ -169,9 +170,8 @@
 	kfd->shared_resources = *gpu_resources;
 
 	/* calculate max size of mqds needed for queues */
-	size = max_num_of_processes *
-		max_num_of_queues_per_process *
-		kfd->device_info->mqd_size_aligned;
+	size = max_num_of_queues_per_device *
+			kfd->device_info->mqd_size_aligned;
 
 	/* add another 512KB for all other allocations on gart */
 	size += 512 * 1024;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 30c8fda..0d8694f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -183,6 +183,13 @@
 
 	mutex_lock(&dqm->lock);
 
+	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
+		pr_warn("amdkfd: Can't create new usermode queue because %d queues were already created\n",
+				dqm->total_queue_count);
+		mutex_unlock(&dqm->lock);
+		return -EPERM;
+	}
+
 	if (list_empty(&qpd->queues_list)) {
 		retval = allocate_vmid(dqm, qpd, q);
 		if (retval != 0) {
@@ -207,6 +214,14 @@
 	list_add(&q->list, &qpd->queues_list);
 	dqm->queue_count++;
 
+	/*
+	 * Unconditionally increment this counter, regardless of the queue's
+	 * type or whether the queue is active.
+	 */
+	dqm->total_queue_count++;
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
+
 	mutex_unlock(&dqm->lock);
 	return 0;
 }
@@ -326,6 +341,15 @@
 	if (list_empty(&qpd->queues_list))
 		deallocate_vmid(dqm, qpd, q);
 	dqm->queue_count--;
+
+	/*
+	 * Unconditionally decrement this counter, regardless of the queue's
+	 * type
+	 */
+	dqm->total_queue_count--;
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
+
 out:
 	mutex_unlock(&dqm->lock);
 	return retval;
@@ -541,10 +565,14 @@
 
 	for (i = 0; i < pipes_num; i++) {
 		inx = i + first_pipe;
+		/*
+		 * HPD buffer on GTT is allocated by amdkfd, no need to waste
+		 * space in GTT for pipelines we don't initialize
+		 */
 		pipe_hpd_addr = dqm->pipelines_addr + i * CIK_HPD_EOP_BYTES;
 		pr_debug("kfd: pipeline address %llX\n", pipe_hpd_addr);
 		/* = log2(bytes/4)-1 */
-		kfd2kgd->init_pipeline(dqm->dev->kgd, i,
+		kfd2kgd->init_pipeline(dqm->dev->kgd, inx,
 				CIK_HPD_EOP_BYTES_LOG2 - 3, pipe_hpd_addr);
 	}
 
@@ -560,7 +588,7 @@
 
 	pr_debug("kfd: In %s\n", __func__);
 
-	retval = init_pipelines(dqm, get_pipes_num(dqm), KFD_DQM_FIRST_PIPE);
+	retval = init_pipelines(dqm, get_pipes_num(dqm), get_first_pipe(dqm));
 	if (retval != 0)
 		return retval;
 
@@ -752,6 +780,21 @@
 	pr_debug("kfd: In func %s\n", __func__);
 
 	mutex_lock(&dqm->lock);
+	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
+		pr_warn("amdkfd: Can't create new kernel queue because %d queues were already created\n",
+				dqm->total_queue_count);
+		mutex_unlock(&dqm->lock);
+		return -EPERM;
+	}
+
+	/*
+	 * Unconditionally increment this counter, regardless of the queue's
+	 * type or whether the queue is active.
+	 */
+	dqm->total_queue_count++;
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
+
 	list_add(&kq->list, &qpd->priv_queue_list);
 	dqm->queue_count++;
 	qpd->is_debug = true;
@@ -775,6 +818,13 @@
 	dqm->queue_count--;
 	qpd->is_debug = false;
 	execute_queues_cpsch(dqm, false);
+	/*
+	 * Unconditionally decrement this counter, regardless of the queue's
+	 * type.
+	 */
+	dqm->total_queue_count++;
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
 	mutex_unlock(&dqm->lock);
 }
 
@@ -793,6 +843,13 @@
 
 	mutex_lock(&dqm->lock);
 
+	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
+		pr_warn("amdkfd: Can't create new usermode queue because %d queues were already created\n",
+				dqm->total_queue_count);
+		retval = -EPERM;
+		goto out;
+	}
+
 	mqd = dqm->get_mqd_manager(dqm, KFD_MQD_TYPE_CIK_CP);
 	if (mqd == NULL) {
 		mutex_unlock(&dqm->lock);
@@ -810,6 +867,15 @@
 		retval = execute_queues_cpsch(dqm, false);
 	}
 
+	/*
+	 * Unconditionally increment this counter, regardless of the queue's
+	 * type or whether the queue is active.
+	 */
+	dqm->total_queue_count++;
+
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
+
 out:
 	mutex_unlock(&dqm->lock);
 	return retval;
@@ -930,6 +996,14 @@
 
 	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
 
+	/*
+	 * Unconditionally decrement this counter, regardless of the queue's
+	 * type
+	 */
+	dqm->total_queue_count--;
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
+
 	mutex_unlock(&dqm->lock);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index c3f189e8..52035bf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -130,6 +130,7 @@
 	struct list_head	queues;
 	unsigned int		processes_count;
 	unsigned int		queue_count;
+	unsigned int		total_queue_count;
 	unsigned int		next_pipe_to_allocate;
 	unsigned int		*allocated_queues;
 	unsigned int		vmid_bitmap;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index 95d5af1..a8be6df 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -50,15 +50,10 @@
 MODULE_PARM_DESC(sched_policy,
 	"Kernel cmdline parameter that defines the amdkfd scheduling policy");
 
-int max_num_of_processes = KFD_MAX_NUM_OF_PROCESSES_DEFAULT;
-module_param(max_num_of_processes, int, 0444);
-MODULE_PARM_DESC(max_num_of_processes,
-	"Kernel cmdline parameter that defines the amdkfd maximum number of supported processes");
-
-int max_num_of_queues_per_process = KFD_MAX_NUM_OF_QUEUES_PER_PROCESS_DEFAULT;
-module_param(max_num_of_queues_per_process, int, 0444);
-MODULE_PARM_DESC(max_num_of_queues_per_process,
-	"Kernel cmdline parameter that defines the amdkfd maximum number of supported queues per process");
+int max_num_of_queues_per_device = KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT;
+module_param(max_num_of_queues_per_device, int, 0444);
+MODULE_PARM_DESC(max_num_of_queues_per_device,
+	"Maximum number of supported queues per device (1 = Minimum, 4096 = default)");
 
 bool kgd2kfd_init(unsigned interface_version,
 		  const struct kfd2kgd_calls *f2g,
@@ -100,16 +95,10 @@
 	}
 
 	/* Verify module parameters */
-	if ((max_num_of_processes < 0) ||
-		(max_num_of_processes > KFD_MAX_NUM_OF_PROCESSES)) {
-		pr_err("kfd: max_num_of_processes must be between 0 to KFD_MAX_NUM_OF_PROCESSES\n");
-		return -1;
-	}
-
-	if ((max_num_of_queues_per_process < 0) ||
-		(max_num_of_queues_per_process >
-			KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)) {
-		pr_err("kfd: max_num_of_queues_per_process must be between 0 to KFD_MAX_NUM_OF_QUEUES_PER_PROCESS\n");
+	if ((max_num_of_queues_per_device < 0) ||
+		(max_num_of_queues_per_device >
+			KFD_MAX_NUM_OF_QUEUES_PER_DEVICE)) {
+		pr_err("kfd: max_num_of_queues_per_device must be between 0 to KFD_MAX_NUM_OF_QUEUES_PER_DEVICE\n");
 		return -1;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
index 4c25ef5..6cfe7f1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
@@ -30,7 +30,7 @@
 
 int kfd_pasid_init(void)
 {
-	pasid_limit = max_num_of_processes;
+	pasid_limit = KFD_MAX_NUM_OF_PROCESSES;
 
 	pasid_bitmap = kcalloc(BITS_TO_LONGS(pasid_limit), sizeof(long), GFP_KERNEL);
 	if (!pasid_bitmap)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index b3dc13c..96dc10e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -52,20 +52,19 @@
 #define kfd_alloc_struct(ptr_to_struct)	\
 	((typeof(ptr_to_struct)) kzalloc(sizeof(*ptr_to_struct), GFP_KERNEL))
 
-/* Kernel module parameter to specify maximum number of supported processes */
-extern int max_num_of_processes;
-
-#define KFD_MAX_NUM_OF_PROCESSES_DEFAULT 32
 #define KFD_MAX_NUM_OF_PROCESSES 512
+#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS 1024
 
 /*
- * Kernel module parameter to specify maximum number of supported queues
- * per process
+ * Kernel module parameter to specify maximum number of supported queues per
+ * device
  */
-extern int max_num_of_queues_per_process;
+extern int max_num_of_queues_per_device;
 
-#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS_DEFAULT 128
-#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS 1024
+#define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT 4096
+#define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE		\
+	(KFD_MAX_NUM_OF_PROCESSES *			\
+			KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)
 
 #define KFD_KERNEL_QUEUE_SIZE 2048
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 4752678..f37cf5e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -54,11 +54,11 @@
 	pr_debug("kfd: in %s\n", __func__);
 
 	found = find_first_zero_bit(pqm->queue_slot_bitmap,
-			max_num_of_queues_per_process);
+			KFD_MAX_NUM_OF_QUEUES_PER_PROCESS);
 
 	pr_debug("kfd: the new slot id %lu\n", found);
 
-	if (found >= max_num_of_queues_per_process) {
+	if (found >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) {
 		pr_info("amdkfd: Can not open more queues for process with pasid %d\n",
 				pqm->process->pasid);
 		return -ENOMEM;
@@ -76,7 +76,7 @@
 
 	INIT_LIST_HEAD(&pqm->queues);
 	pqm->queue_slot_bitmap =
-			kzalloc(DIV_ROUND_UP(max_num_of_queues_per_process,
+			kzalloc(DIV_ROUND_UP(KFD_MAX_NUM_OF_QUEUES_PER_PROCESS,
 					BITS_PER_BYTE), GFP_KERNEL);
 	if (pqm->queue_slot_bitmap == NULL)
 		return -ENOMEM;
@@ -203,6 +203,7 @@
 		pqn->kq = NULL;
 		retval = dev->dqm->create_queue(dev->dqm, q, &pdd->qpd,
 						&q->properties.vmid);
+		pr_debug("DQM returned %d for create_queue\n", retval);
 		print_queue(q);
 		break;
 	case KFD_QUEUE_TYPE_DIQ:
@@ -222,7 +223,7 @@
 	}
 
 	if (retval != 0) {
-		pr_err("kfd: error dqm create queue\n");
+		pr_debug("Error dqm create queue\n");
 		goto err_create_queue;
 	}
 
@@ -241,7 +242,10 @@
 err_create_queue:
 	kfree(pqn);
 err_allocate_pqn:
+	/* check if queues list is empty unregister process from device */
 	clear_bit(*qid, pqm->queue_slot_bitmap);
+	if (list_empty(&pqm->queues))
+		dev->dqm->unregister_process(dev->dqm, &pdd->qpd);
 	return retval;
 }
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index cf775a4..dc386eb 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -145,6 +145,31 @@
 }
 EXPORT_SYMBOL(drm_fb_helper_add_one_connector);
 
+static void remove_from_modeset(struct drm_mode_set *set,
+		struct drm_connector *connector)
+{
+	int i, j;
+
+	for (i = 0; i < set->num_connectors; i++) {
+		if (set->connectors[i] == connector)
+			break;
+	}
+
+	if (i == set->num_connectors)
+		return;
+
+	for (j = i + 1; j < set->num_connectors; j++) {
+		set->connectors[j - 1] = set->connectors[j];
+	}
+	set->num_connectors--;
+
+	/* because i915 is pissy about this..
+	 * TODO maybe need to makes sure we set it back to !=NULL somewhere?
+	 */
+	if (set->num_connectors == 0)
+		set->fb = NULL;
+}
+
 int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper,
 				       struct drm_connector *connector)
 {
@@ -167,6 +192,11 @@
 	}
 	fb_helper->connector_count--;
 	kfree(fb_helper_connector);
+
+	/* also cleanup dangling references to the connector: */
+	for (i = 0; i < fb_helper->crtc_count; i++)
+		remove_from_modeset(&fb_helper->crtc_info[i].mode_set, connector);
+
 	return 0;
 }
 EXPORT_SYMBOL(drm_fb_helper_remove_one_connector);
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index d476279..a9041d1 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -32,6 +32,8 @@
 struct tda998x_priv {
 	struct i2c_client *cec;
 	struct i2c_client *hdmi;
+	struct mutex mutex;
+	struct delayed_work dwork;
 	uint16_t rev;
 	uint8_t current_page;
 	int dpms;
@@ -402,9 +404,10 @@
 	uint8_t addr = REG2ADDR(reg);
 	int ret;
 
+	mutex_lock(&priv->mutex);
 	ret = set_page(priv, reg);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	ret = i2c_master_send(client, &addr, sizeof(addr));
 	if (ret < 0)
@@ -414,10 +417,12 @@
 	if (ret < 0)
 		goto fail;
 
-	return ret;
+	goto out;
 
 fail:
 	dev_err(&client->dev, "Error %d reading from 0x%x\n", ret, reg);
+out:
+	mutex_unlock(&priv->mutex);
 	return ret;
 }
 
@@ -431,13 +436,16 @@
 	buf[0] = REG2ADDR(reg);
 	memcpy(&buf[1], p, cnt);
 
+	mutex_lock(&priv->mutex);
 	ret = set_page(priv, reg);
 	if (ret < 0)
-		return;
+		goto out;
 
 	ret = i2c_master_send(client, buf, cnt + 1);
 	if (ret < 0)
 		dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg);
+out:
+	mutex_unlock(&priv->mutex);
 }
 
 static int
@@ -459,13 +467,16 @@
 	uint8_t buf[] = {REG2ADDR(reg), val};
 	int ret;
 
+	mutex_lock(&priv->mutex);
 	ret = set_page(priv, reg);
 	if (ret < 0)
-		return;
+		goto out;
 
 	ret = i2c_master_send(client, buf, sizeof(buf));
 	if (ret < 0)
 		dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg);
+out:
+	mutex_unlock(&priv->mutex);
 }
 
 static void
@@ -475,13 +486,16 @@
 	uint8_t buf[] = {REG2ADDR(reg), val >> 8, val};
 	int ret;
 
+	mutex_lock(&priv->mutex);
 	ret = set_page(priv, reg);
 	if (ret < 0)
-		return;
+		goto out;
 
 	ret = i2c_master_send(client, buf, sizeof(buf));
 	if (ret < 0)
 		dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg);
+out:
+	mutex_unlock(&priv->mutex);
 }
 
 static void
@@ -536,6 +550,17 @@
 	reg_write(priv, REG_MUX_VP_VIP_OUT, 0x24);
 }
 
+/* handle HDMI connect/disconnect */
+static void tda998x_hpd(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct tda998x_priv *priv =
+			container_of(dwork, struct tda998x_priv, dwork);
+
+	if (priv->encoder && priv->encoder->dev)
+		drm_kms_helper_hotplug_event(priv->encoder->dev);
+}
+
 /*
  * only 2 interrupts may occur: screen plug/unplug and EDID read
  */
@@ -559,8 +584,7 @@
 		priv->wq_edid_wait = 0;
 		wake_up(&priv->wq_edid);
 	} else if (cec != 0) {			/* HPD change */
-		if (priv->encoder && priv->encoder->dev)
-			drm_helper_hpd_irq_event(priv->encoder->dev);
+		schedule_delayed_work(&priv->dwork, HZ/10);
 	}
 	return IRQ_HANDLED;
 }
@@ -1170,8 +1194,10 @@
 	/* disable all IRQs and free the IRQ handler */
 	cec_write(priv, REG_CEC_RXSHPDINTENA, 0);
 	reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
-	if (priv->hdmi->irq)
+	if (priv->hdmi->irq) {
 		free_irq(priv->hdmi->irq, priv);
+		cancel_delayed_work_sync(&priv->dwork);
+	}
 
 	i2c_unregister_device(priv->cec);
 }
@@ -1255,6 +1281,7 @@
 	struct device_node *np = client->dev.of_node;
 	u32 video;
 	int rev_lo, rev_hi, ret;
+	unsigned short cec_addr;
 
 	priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(2) | VIP_CNTRL_0_SWAP_B(3);
 	priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(0) | VIP_CNTRL_1_SWAP_D(1);
@@ -1262,12 +1289,16 @@
 
 	priv->current_page = 0xff;
 	priv->hdmi = client;
-	priv->cec = i2c_new_dummy(client->adapter, 0x34);
+	/* CEC I2C address bound to TDA998x I2C addr by configuration pins */
+	cec_addr = 0x34 + (client->addr & 0x03);
+	priv->cec = i2c_new_dummy(client->adapter, cec_addr);
 	if (!priv->cec)
 		return -ENODEV;
 
 	priv->dpms = DRM_MODE_DPMS_OFF;
 
+	mutex_init(&priv->mutex);	/* protect the page access */
+
 	/* wake up the device: */
 	cec_write(priv, REG_CEC_ENAMODS,
 			CEC_ENAMODS_EN_RXSENS | CEC_ENAMODS_EN_HDMI);
@@ -1323,8 +1354,9 @@
 	if (client->irq) {
 		int irqf_trigger;
 
-		/* init read EDID waitqueue */
+		/* init read EDID waitqueue and HDP work */
 		init_waitqueue_head(&priv->wq_edid);
+		INIT_DELAYED_WORK(&priv->dwork, tda998x_hpd);
 
 		/* clear pending interrupts */
 		reg_read(priv, REG_INT_FLAGS_0);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 574057c..7643300 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -462,19 +462,13 @@
 			} else if (id == INTEL_PCH_LPT_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = PCH_LPT;
 				DRM_DEBUG_KMS("Found LynxPoint PCH\n");
-				WARN_ON(!IS_HASWELL(dev));
-				WARN_ON(IS_HSW_ULT(dev));
-			} else if (IS_BROADWELL(dev)) {
-				dev_priv->pch_type = PCH_LPT;
-				dev_priv->pch_id =
-					INTEL_PCH_LPT_LP_DEVICE_ID_TYPE;
-				DRM_DEBUG_KMS("This is Broadwell, assuming "
-					      "LynxPoint LP PCH\n");
+				WARN_ON(!IS_HASWELL(dev) && !IS_BROADWELL(dev));
+				WARN_ON(IS_HSW_ULT(dev) || IS_BDW_ULT(dev));
 			} else if (id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = PCH_LPT;
 				DRM_DEBUG_KMS("Found LynxPoint LP PCH\n");
-				WARN_ON(!IS_HASWELL(dev));
-				WARN_ON(!IS_HSW_ULT(dev));
+				WARN_ON(!IS_HASWELL(dev) && !IS_BROADWELL(dev));
+				WARN_ON(!IS_HSW_ULT(dev) && !IS_BDW_ULT(dev));
 			} else if (id == INTEL_PCH_SPT_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = PCH_SPT;
 				DRM_DEBUG_KMS("Found SunrisePoint PCH\n");
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e9f891c..9d7a715 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2159,8 +2159,7 @@
 #define IS_HSW_EARLY_SDV(dev)	(IS_HASWELL(dev) && \
 				 (INTEL_DEVID(dev) & 0xFF00) == 0x0C00)
 #define IS_BDW_ULT(dev)		(IS_BROADWELL(dev) && \
-				 ((INTEL_DEVID(dev) & 0xf) == 0x2  || \
-				 (INTEL_DEVID(dev) & 0xf) == 0x6 || \
+				 ((INTEL_DEVID(dev) & 0xf) == 0x6 ||	\
 				 (INTEL_DEVID(dev) & 0xf) == 0xe))
 #define IS_BDW_GT3(dev)		(IS_BROADWELL(dev) && \
 				 (INTEL_DEVID(dev) & 0x00F0) == 0x0020)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 76354d3..5f61482 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3148,6 +3148,13 @@
 		u32 size = i915_gem_obj_ggtt_size(obj);
 		uint64_t val;
 
+		/* Adjust fence size to match tiled area */
+		if (obj->tiling_mode != I915_TILING_NONE) {
+			uint32_t row_size = obj->stride *
+				(obj->tiling_mode == I915_TILING_Y ? 32 : 8);
+			size = (size / row_size) * row_size;
+		}
+
 		val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) &
 				 0xfffff000) << 32;
 		val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000;
@@ -4884,13 +4891,12 @@
 	for (i = 0; i < NUM_L3_SLICES(dev); i++)
 		i915_gem_l3_remap(&dev_priv->ring[RCS], i);
 
-	/*
-	 * XXX: Contexts should only be initialized once. Doing a switch to the
-	 * default context switch however is something we'd like to do after
-	 * reset or thaw (the latter may not actually be necessary for HW, but
-	 * goes with our code better). Context switching requires rings (for
-	 * the do_switch), but before enabling PPGTT. So don't move this.
-	 */
+	ret = i915_ppgtt_init_hw(dev);
+	if (ret && ret != -EIO) {
+		DRM_ERROR("PPGTT enable failed %d\n", ret);
+		i915_gem_cleanup_ringbuffer(dev);
+	}
+
 	ret = i915_gem_context_enable(dev_priv);
 	if (ret && ret != -EIO) {
 		DRM_ERROR("Context enable failed %d\n", ret);
@@ -4899,12 +4905,6 @@
 		return ret;
 	}
 
-	ret = i915_ppgtt_init_hw(dev);
-	if (ret && ret != -EIO) {
-		DRM_ERROR("PPGTT enable failed %d\n", ret);
-		i915_gem_cleanup_ringbuffer(dev);
-	}
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 4d63839..dfb783a 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -962,7 +962,7 @@
 
 	WARN_ON(panel->backlight.max == 0);
 
-	if (panel->backlight.level == 0) {
+	if (panel->backlight.level <= panel->backlight.min) {
 		panel->backlight.level = panel->backlight.max;
 		if (panel->backlight.device)
 			panel->backlight.device->props.brightness =
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index a0133c7..42cd0cf 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -816,7 +816,6 @@
 		for (; ndw > 0; ndw -= 2, --count, pe += 8) {
 			if (flags & R600_PTE_SYSTEM) {
 				value = radeon_vm_map_gart(rdev, addr);
-				value &= 0xFFFFFFFFFFFFF000ULL;
 			} else if (flags & R600_PTE_VALID) {
 				value = addr;
 			} else {
diff --git a/drivers/gpu/drm/radeon/ni_dma.c b/drivers/gpu/drm/radeon/ni_dma.c
index 4be2bb7..ce787a9 100644
--- a/drivers/gpu/drm/radeon/ni_dma.c
+++ b/drivers/gpu/drm/radeon/ni_dma.c
@@ -372,7 +372,6 @@
 		for (; ndw > 0; ndw -= 2, --count, pe += 8) {
 			if (flags & R600_PTE_SYSTEM) {
 				value = radeon_vm_map_gart(rdev, addr);
-				value &= 0xFFFFFFFFFFFFF000ULL;
 			} else if (flags & R600_PTE_VALID) {
 				value = addr;
 			} else {
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 74f06d5..279801c 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -644,6 +644,7 @@
 		return r;
 	rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
 	rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush;
+	rdev->asic->gart.get_page_entry = &r100_pci_gart_get_page_entry;
 	rdev->asic->gart.set_page = &r100_pci_gart_set_page;
 	return radeon_gart_table_ram_alloc(rdev);
 }
@@ -681,11 +682,16 @@
 	WREG32(RADEON_AIC_HI_ADDR, 0);
 }
 
+uint64_t r100_pci_gart_get_page_entry(uint64_t addr, uint32_t flags)
+{
+	return addr;
+}
+
 void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
-			    uint64_t addr, uint32_t flags)
+			    uint64_t entry)
 {
 	u32 *gtt = rdev->gart.ptr;
-	gtt[i] = cpu_to_le32(lower_32_bits(addr));
+	gtt[i] = cpu_to_le32(lower_32_bits(entry));
 }
 
 void r100_pci_gart_fini(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 064ad55..08d68f3 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -73,11 +73,8 @@
 #define R300_PTE_WRITEABLE (1 << 2)
 #define R300_PTE_READABLE  (1 << 3)
 
-void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
-			      uint64_t addr, uint32_t flags)
+uint64_t rv370_pcie_gart_get_page_entry(uint64_t addr, uint32_t flags)
 {
-	void __iomem *ptr = rdev->gart.ptr;
-
 	addr = (lower_32_bits(addr) >> 8) |
 		((upper_32_bits(addr) & 0xff) << 24);
 	if (flags & RADEON_GART_PAGE_READ)
@@ -86,10 +83,18 @@
 		addr |= R300_PTE_WRITEABLE;
 	if (!(flags & RADEON_GART_PAGE_SNOOP))
 		addr |= R300_PTE_UNSNOOPED;
+	return addr;
+}
+
+void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
+			      uint64_t entry)
+{
+	void __iomem *ptr = rdev->gart.ptr;
+
 	/* on x86 we want this to be CPU endian, on powerpc
 	 * on powerpc without HW swappers, it'll get swapped on way
 	 * into VRAM - so no need for cpu_to_le32 on VRAM tables */
-	writel(addr, ((void __iomem *)ptr) + (i * 4));
+	writel(entry, ((void __iomem *)ptr) + (i * 4));
 }
 
 int rv370_pcie_gart_init(struct radeon_device *rdev)
@@ -109,6 +114,7 @@
 		DRM_ERROR("Failed to register debugfs file for PCIE gart !\n");
 	rdev->gart.table_size = rdev->gart.num_gpu_pages * 4;
 	rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush;
+	rdev->asic->gart.get_page_entry = &rv370_pcie_gart_get_page_entry;
 	rdev->asic->gart.set_page = &rv370_pcie_gart_set_page;
 	return radeon_gart_table_vram_alloc(rdev);
 }
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 54529b8..3f2a8d3 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -242,6 +242,7 @@
  * Dummy page
  */
 struct radeon_dummy_page {
+	uint64_t	entry;
 	struct page	*page;
 	dma_addr_t	addr;
 };
@@ -645,7 +646,7 @@
 	unsigned			num_cpu_pages;
 	unsigned			table_size;
 	struct page			**pages;
-	dma_addr_t			*pages_addr;
+	uint64_t			*pages_entry;
 	bool				ready;
 };
 
@@ -1847,8 +1848,9 @@
 	/* gart */
 	struct {
 		void (*tlb_flush)(struct radeon_device *rdev);
+		uint64_t (*get_page_entry)(uint64_t addr, uint32_t flags);
 		void (*set_page)(struct radeon_device *rdev, unsigned i,
-				 uint64_t addr, uint32_t flags);
+				 uint64_t entry);
 	} gart;
 	struct {
 		int (*init)(struct radeon_device *rdev);
@@ -2852,7 +2854,8 @@
 #define radeon_vga_set_state(rdev, state) (rdev)->asic->vga_set_state((rdev), (state))
 #define radeon_asic_reset(rdev) (rdev)->asic->asic_reset((rdev))
 #define radeon_gart_tlb_flush(rdev) (rdev)->asic->gart.tlb_flush((rdev))
-#define radeon_gart_set_page(rdev, i, p, f) (rdev)->asic->gart.set_page((rdev), (i), (p), (f))
+#define radeon_gart_get_page_entry(a, f) (rdev)->asic->gart.get_page_entry((a), (f))
+#define radeon_gart_set_page(rdev, i, e) (rdev)->asic->gart.set_page((rdev), (i), (e))
 #define radeon_asic_vm_init(rdev) (rdev)->asic->vm.init((rdev))
 #define radeon_asic_vm_fini(rdev) (rdev)->asic->vm.fini((rdev))
 #define radeon_asic_vm_copy_pages(rdev, ib, pe, src, count) ((rdev)->asic->vm.copy_pages((rdev), (ib), (pe), (src), (count)))
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 121aff6..ed0e10e 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -159,11 +159,13 @@
 		DRM_INFO("Forcing AGP to PCIE mode\n");
 		rdev->flags |= RADEON_IS_PCIE;
 		rdev->asic->gart.tlb_flush = &rv370_pcie_gart_tlb_flush;
+		rdev->asic->gart.get_page_entry = &rv370_pcie_gart_get_page_entry;
 		rdev->asic->gart.set_page = &rv370_pcie_gart_set_page;
 	} else {
 		DRM_INFO("Forcing AGP to PCI mode\n");
 		rdev->flags |= RADEON_IS_PCI;
 		rdev->asic->gart.tlb_flush = &r100_pci_gart_tlb_flush;
+		rdev->asic->gart.get_page_entry = &r100_pci_gart_get_page_entry;
 		rdev->asic->gart.set_page = &r100_pci_gart_set_page;
 	}
 	rdev->mc.gtt_size = radeon_gart_size * 1024 * 1024;
@@ -199,6 +201,7 @@
 	.mc_wait_for_idle = &r100_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &r100_pci_gart_tlb_flush,
+		.get_page_entry = &r100_pci_gart_get_page_entry,
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
@@ -265,6 +268,7 @@
 	.mc_wait_for_idle = &r100_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &r100_pci_gart_tlb_flush,
+		.get_page_entry = &r100_pci_gart_get_page_entry,
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
@@ -359,6 +363,7 @@
 	.mc_wait_for_idle = &r300_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &r100_pci_gart_tlb_flush,
+		.get_page_entry = &r100_pci_gart_get_page_entry,
 		.set_page = &r100_pci_gart_set_page,
 	},
 	.ring = {
@@ -425,6 +430,7 @@
 	.mc_wait_for_idle = &r300_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
@@ -491,6 +497,7 @@
 	.mc_wait_for_idle = &r300_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
@@ -557,6 +564,7 @@
 	.mc_wait_for_idle = &rs400_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rs400_gart_tlb_flush,
+		.get_page_entry = &rs400_gart_get_page_entry,
 		.set_page = &rs400_gart_set_page,
 	},
 	.ring = {
@@ -623,6 +631,7 @@
 	.mc_wait_for_idle = &rs600_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rs600_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -691,6 +700,7 @@
 	.mc_wait_for_idle = &rs690_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rs400_gart_tlb_flush,
+		.get_page_entry = &rs400_gart_get_page_entry,
 		.set_page = &rs400_gart_set_page,
 	},
 	.ring = {
@@ -759,6 +769,7 @@
 	.mc_wait_for_idle = &rv515_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
@@ -825,6 +836,7 @@
 	.mc_wait_for_idle = &r520_mc_wait_for_idle,
 	.gart = {
 		.tlb_flush = &rv370_pcie_gart_tlb_flush,
+		.get_page_entry = &rv370_pcie_gart_get_page_entry,
 		.set_page = &rv370_pcie_gart_set_page,
 	},
 	.ring = {
@@ -919,6 +931,7 @@
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1004,6 +1017,7 @@
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1095,6 +1109,7 @@
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1199,6 +1214,7 @@
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &r600_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1317,6 +1333,7 @@
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &evergreen_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1409,6 +1426,7 @@
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &evergreen_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1500,6 +1518,7 @@
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &evergreen_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.ring = {
@@ -1635,6 +1654,7 @@
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cayman_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -1738,6 +1758,7 @@
 	.get_gpu_clock_counter = &r600_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cayman_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -1871,6 +1892,7 @@
 	.get_gpu_clock_counter = &si_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &si_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -2032,6 +2054,7 @@
 	.get_gpu_clock_counter = &cik_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cik_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
@@ -2139,6 +2162,7 @@
 	.get_gpu_clock_counter = &cik_get_gpu_clock_counter,
 	.gart = {
 		.tlb_flush = &cik_pcie_gart_tlb_flush,
+		.get_page_entry = &rs600_gart_get_page_entry,
 		.set_page = &rs600_gart_set_page,
 	},
 	.vm = {
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 2a45d54..8d787d1 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -67,8 +67,9 @@
 int r100_asic_reset(struct radeon_device *rdev);
 u32 r100_get_vblank_counter(struct radeon_device *rdev, int crtc);
 void r100_pci_gart_tlb_flush(struct radeon_device *rdev);
+uint64_t r100_pci_gart_get_page_entry(uint64_t addr, uint32_t flags);
 void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
-			    uint64_t addr, uint32_t flags);
+			    uint64_t entry);
 void r100_ring_start(struct radeon_device *rdev, struct radeon_ring *ring);
 int r100_irq_set(struct radeon_device *rdev);
 int r100_irq_process(struct radeon_device *rdev);
@@ -172,8 +173,9 @@
 				struct radeon_fence *fence);
 extern int r300_cs_parse(struct radeon_cs_parser *p);
 extern void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev);
+extern uint64_t rv370_pcie_gart_get_page_entry(uint64_t addr, uint32_t flags);
 extern void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
-				     uint64_t addr, uint32_t flags);
+				     uint64_t entry);
 extern void rv370_set_pcie_lanes(struct radeon_device *rdev, int lanes);
 extern int rv370_get_pcie_lanes(struct radeon_device *rdev);
 extern void r300_set_reg_safe(struct radeon_device *rdev);
@@ -208,8 +210,9 @@
 extern int rs400_suspend(struct radeon_device *rdev);
 extern int rs400_resume(struct radeon_device *rdev);
 void rs400_gart_tlb_flush(struct radeon_device *rdev);
+uint64_t rs400_gart_get_page_entry(uint64_t addr, uint32_t flags);
 void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags);
+			 uint64_t entry);
 uint32_t rs400_mc_rreg(struct radeon_device *rdev, uint32_t reg);
 void rs400_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 int rs400_gart_init(struct radeon_device *rdev);
@@ -232,8 +235,9 @@
 void rs600_irq_disable(struct radeon_device *rdev);
 u32 rs600_get_vblank_counter(struct radeon_device *rdev, int crtc);
 void rs600_gart_tlb_flush(struct radeon_device *rdev);
+uint64_t rs600_gart_get_page_entry(uint64_t addr, uint32_t flags);
 void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags);
+			 uint64_t entry);
 uint32_t rs600_mc_rreg(struct radeon_device *rdev, uint32_t reg);
 void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 void rs600_bandwidth_update(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 0ec6516..bd7519f 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -774,6 +774,8 @@
 		rdev->dummy_page.page = NULL;
 		return -ENOMEM;
 	}
+	rdev->dummy_page.entry = radeon_gart_get_page_entry(rdev->dummy_page.addr,
+							    RADEON_GART_PAGE_DUMMY);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 84146d5..5450fa9 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -165,6 +165,19 @@
 		radeon_bo_unpin(rdev->gart.robj);
 	radeon_bo_unreserve(rdev->gart.robj);
 	rdev->gart.table_addr = gpu_addr;
+
+	if (!r) {
+		int i;
+
+		/* We might have dropped some GART table updates while it wasn't
+		 * mapped, restore all entries
+		 */
+		for (i = 0; i < rdev->gart.num_gpu_pages; i++)
+			radeon_gart_set_page(rdev, i, rdev->gart.pages_entry[i]);
+		mb();
+		radeon_gart_tlb_flush(rdev);
+	}
+
 	return r;
 }
 
@@ -228,7 +241,6 @@
 	unsigned t;
 	unsigned p;
 	int i, j;
-	u64 page_base;
 
 	if (!rdev->gart.ready) {
 		WARN(1, "trying to unbind memory from uninitialized GART !\n");
@@ -239,14 +251,12 @@
 	for (i = 0; i < pages; i++, p++) {
 		if (rdev->gart.pages[p]) {
 			rdev->gart.pages[p] = NULL;
-			rdev->gart.pages_addr[p] = rdev->dummy_page.addr;
-			page_base = rdev->gart.pages_addr[p];
 			for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) {
+				rdev->gart.pages_entry[t] = rdev->dummy_page.entry;
 				if (rdev->gart.ptr) {
-					radeon_gart_set_page(rdev, t, page_base,
-							     RADEON_GART_PAGE_DUMMY);
+					radeon_gart_set_page(rdev, t,
+							     rdev->dummy_page.entry);
 				}
-				page_base += RADEON_GPU_PAGE_SIZE;
 			}
 		}
 	}
@@ -274,7 +284,7 @@
 {
 	unsigned t;
 	unsigned p;
-	uint64_t page_base;
+	uint64_t page_base, page_entry;
 	int i, j;
 
 	if (!rdev->gart.ready) {
@@ -285,14 +295,15 @@
 	p = t / (PAGE_SIZE / RADEON_GPU_PAGE_SIZE);
 
 	for (i = 0; i < pages; i++, p++) {
-		rdev->gart.pages_addr[p] = dma_addr[i];
 		rdev->gart.pages[p] = pagelist[i];
-		if (rdev->gart.ptr) {
-			page_base = rdev->gart.pages_addr[p];
-			for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) {
-				radeon_gart_set_page(rdev, t, page_base, flags);
-				page_base += RADEON_GPU_PAGE_SIZE;
+		page_base = dma_addr[i];
+		for (j = 0; j < (PAGE_SIZE / RADEON_GPU_PAGE_SIZE); j++, t++) {
+			page_entry = radeon_gart_get_page_entry(page_base, flags);
+			rdev->gart.pages_entry[t] = page_entry;
+			if (rdev->gart.ptr) {
+				radeon_gart_set_page(rdev, t, page_entry);
 			}
+			page_base += RADEON_GPU_PAGE_SIZE;
 		}
 	}
 	mb();
@@ -334,16 +345,15 @@
 		radeon_gart_fini(rdev);
 		return -ENOMEM;
 	}
-	rdev->gart.pages_addr = vzalloc(sizeof(dma_addr_t) *
-					rdev->gart.num_cpu_pages);
-	if (rdev->gart.pages_addr == NULL) {
+	rdev->gart.pages_entry = vmalloc(sizeof(uint64_t) *
+					 rdev->gart.num_gpu_pages);
+	if (rdev->gart.pages_entry == NULL) {
 		radeon_gart_fini(rdev);
 		return -ENOMEM;
 	}
 	/* set GART entry to point to the dummy page by default */
-	for (i = 0; i < rdev->gart.num_cpu_pages; i++) {
-		rdev->gart.pages_addr[i] = rdev->dummy_page.addr;
-	}
+	for (i = 0; i < rdev->gart.num_gpu_pages; i++)
+		rdev->gart.pages_entry[i] = rdev->dummy_page.entry;
 	return 0;
 }
 
@@ -356,15 +366,15 @@
  */
 void radeon_gart_fini(struct radeon_device *rdev)
 {
-	if (rdev->gart.pages && rdev->gart.pages_addr && rdev->gart.ready) {
+	if (rdev->gart.ready) {
 		/* unbind pages */
 		radeon_gart_unbind(rdev, 0, rdev->gart.num_cpu_pages);
 	}
 	rdev->gart.ready = false;
 	vfree(rdev->gart.pages);
-	vfree(rdev->gart.pages_addr);
+	vfree(rdev->gart.pages_entry);
 	rdev->gart.pages = NULL;
-	rdev->gart.pages_addr = NULL;
+	rdev->gart.pages_entry = NULL;
 
 	radeon_dummy_page_fini(rdev);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_kfd.c b/drivers/gpu/drm/radeon/radeon_kfd.c
index 8bf87f1..bef9a09 100644
--- a/drivers/gpu/drm/radeon/radeon_kfd.c
+++ b/drivers/gpu/drm/radeon/radeon_kfd.c
@@ -436,7 +436,7 @@
 static int kgd_init_pipeline(struct kgd_dev *kgd, uint32_t pipe_id,
 				uint32_t hpd_size, uint64_t hpd_gpu_addr)
 {
-	uint32_t mec = (++pipe_id / CIK_PIPE_PER_MEC) + 1;
+	uint32_t mec = (pipe_id / CIK_PIPE_PER_MEC) + 1;
 	uint32_t pipe = (pipe_id % CIK_PIPE_PER_MEC);
 
 	lock_srbm(kgd, mec, pipe, 0, 0);
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index cde48c4..06d2246 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -587,10 +587,8 @@
 	uint64_t result;
 
 	/* page table offset */
-	result = rdev->gart.pages_addr[addr >> PAGE_SHIFT];
-
-	/* in case cpu page size != gpu page size*/
-	result |= addr & (~PAGE_MASK);
+	result = rdev->gart.pages_entry[addr >> RADEON_GPU_PAGE_SHIFT];
+	result &= ~RADEON_GPU_PAGE_MASK;
 
 	return result;
 }
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index c5799f16..34e3235 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -212,11 +212,9 @@
 #define RS400_PTE_WRITEABLE (1 << 2)
 #define RS400_PTE_READABLE  (1 << 3)
 
-void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags)
+uint64_t rs400_gart_get_page_entry(uint64_t addr, uint32_t flags)
 {
 	uint32_t entry;
-	u32 *gtt = rdev->gart.ptr;
 
 	entry = (lower_32_bits(addr) & PAGE_MASK) |
 		((upper_32_bits(addr) & 0xff) << 4);
@@ -226,8 +224,14 @@
 		entry |= RS400_PTE_WRITEABLE;
 	if (!(flags & RADEON_GART_PAGE_SNOOP))
 		entry |= RS400_PTE_UNSNOOPED;
-	entry = cpu_to_le32(entry);
-	gtt[i] = entry;
+	return entry;
+}
+
+void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
+			 uint64_t entry)
+{
+	u32 *gtt = rdev->gart.ptr;
+	gtt[i] = cpu_to_le32(lower_32_bits(entry));
 }
 
 int rs400_mc_wait_for_idle(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 9acb1c3..74bce91 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -625,11 +625,8 @@
 	radeon_gart_table_vram_free(rdev);
 }
 
-void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
-			 uint64_t addr, uint32_t flags)
+uint64_t rs600_gart_get_page_entry(uint64_t addr, uint32_t flags)
 {
-	void __iomem *ptr = (void *)rdev->gart.ptr;
-
 	addr = addr & 0xFFFFFFFFFFFFF000ULL;
 	addr |= R600_PTE_SYSTEM;
 	if (flags & RADEON_GART_PAGE_VALID)
@@ -640,7 +637,14 @@
 		addr |= R600_PTE_WRITEABLE;
 	if (flags & RADEON_GART_PAGE_SNOOP)
 		addr |= R600_PTE_SNOOPED;
-	writeq(addr, ptr + (i * 8));
+	return addr;
+}
+
+void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
+			 uint64_t entry)
+{
+	void __iomem *ptr = (void *)rdev->gart.ptr;
+	writeq(entry, ptr + (i * 8));
 }
 
 int rs600_irq_set(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/si_dma.c b/drivers/gpu/drm/radeon/si_dma.c
index aa7b872..8320792 100644
--- a/drivers/gpu/drm/radeon/si_dma.c
+++ b/drivers/gpu/drm/radeon/si_dma.c
@@ -123,7 +123,6 @@
 		for (; ndw > 0; ndw -= 2, --count, pe += 8) {
 			if (flags & R600_PTE_SYSTEM) {
 				value = radeon_vm_map_gart(rdev, addr);
-				value &= 0xFFFFFFFFFFFFF000ULL;
 			} else if (flags & R600_PTE_VALID) {
 				value = addr;
 			} else {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 7b5d221..6c6b655 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -406,11 +406,9 @@
 		if (unlikely(ret != 0))
 			--dev_priv->num_3d_resources;
 	} else if (unhide_svga) {
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_ENABLE,
 			  vmw_read(dev_priv, SVGA_REG_ENABLE) &
 			  ~SVGA_REG_ENABLE_HIDE);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 
 	mutex_unlock(&dev_priv->release_mutex);
@@ -433,13 +431,10 @@
 	mutex_lock(&dev_priv->release_mutex);
 	if (unlikely(--dev_priv->num_3d_resources == 0))
 		vmw_release_device(dev_priv);
-	else if (hide_svga) {
-		mutex_lock(&dev_priv->hw_mutex);
+	else if (hide_svga)
 		vmw_write(dev_priv, SVGA_REG_ENABLE,
 			  vmw_read(dev_priv, SVGA_REG_ENABLE) |
 			  SVGA_REG_ENABLE_HIDE);
-		mutex_unlock(&dev_priv->hw_mutex);
-	}
 
 	n3d = (int32_t) dev_priv->num_3d_resources;
 	mutex_unlock(&dev_priv->release_mutex);
@@ -600,12 +595,14 @@
 	dev_priv->dev = dev;
 	dev_priv->vmw_chipset = chipset;
 	dev_priv->last_read_seqno = (uint32_t) -100;
-	mutex_init(&dev_priv->hw_mutex);
 	mutex_init(&dev_priv->cmdbuf_mutex);
 	mutex_init(&dev_priv->release_mutex);
 	mutex_init(&dev_priv->binding_mutex);
 	rwlock_init(&dev_priv->resource_lock);
 	ttm_lock_init(&dev_priv->reservation_sem);
+	spin_lock_init(&dev_priv->hw_lock);
+	spin_lock_init(&dev_priv->waiter_lock);
+	spin_lock_init(&dev_priv->cap_lock);
 
 	for (i = vmw_res_context; i < vmw_res_max; ++i) {
 		idr_init(&dev_priv->res_idr[i]);
@@ -626,14 +623,11 @@
 
 	dev_priv->enable_fb = enable_fbdev;
 
-	mutex_lock(&dev_priv->hw_mutex);
-
 	vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2);
 	svga_id = vmw_read(dev_priv, SVGA_REG_ID);
 	if (svga_id != SVGA_ID_2) {
 		ret = -ENOSYS;
 		DRM_ERROR("Unsupported SVGA ID 0x%x\n", svga_id);
-		mutex_unlock(&dev_priv->hw_mutex);
 		goto out_err0;
 	}
 
@@ -683,10 +677,8 @@
 		dev_priv->prim_bb_mem = dev_priv->vram_size;
 
 	ret = vmw_dma_masks(dev_priv);
-	if (unlikely(ret != 0)) {
-		mutex_unlock(&dev_priv->hw_mutex);
+	if (unlikely(ret != 0))
 		goto out_err0;
-	}
 
 	/*
 	 * Limit back buffer size to VRAM size.  Remove this once
@@ -695,8 +687,6 @@
 	if (dev_priv->prim_bb_mem > dev_priv->vram_size)
 		dev_priv->prim_bb_mem = dev_priv->vram_size;
 
-	mutex_unlock(&dev_priv->hw_mutex);
-
 	vmw_print_capabilities(dev_priv->capabilities);
 
 	if (dev_priv->capabilities & SVGA_CAP_GMR2) {
@@ -1160,9 +1150,7 @@
 		if (unlikely(ret != 0))
 			return ret;
 		vmw_kms_save_vga(dev_priv);
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_TRACES, 0);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 
 	if (active) {
@@ -1196,9 +1184,7 @@
 	if (!dev_priv->enable_fb) {
 		vmw_kms_restore_vga(dev_priv);
 		vmw_3d_resource_dec(dev_priv, true);
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_TRACES, 1);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 	return ret;
 }
@@ -1233,9 +1219,7 @@
 			DRM_ERROR("Unable to clean VRAM on master drop.\n");
 		vmw_kms_restore_vga(dev_priv);
 		vmw_3d_resource_dec(dev_priv, true);
-		mutex_lock(&dev_priv->hw_mutex);
 		vmw_write(dev_priv, SVGA_REG_TRACES, 1);
-		mutex_unlock(&dev_priv->hw_mutex);
 	}
 
 	dev_priv->active_master = &dev_priv->fbdev_master;
@@ -1367,10 +1351,8 @@
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct vmw_private *dev_priv = vmw_priv(dev);
 
-	mutex_lock(&dev_priv->hw_mutex);
 	vmw_write(dev_priv, SVGA_REG_ID, SVGA_ID_2);
 	(void) vmw_read(dev_priv, SVGA_REG_ID);
-	mutex_unlock(&dev_priv->hw_mutex);
 
 	/**
 	 * Reclaim 3d reference held by fbdev and potentially
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 4ee799b..d26a6da 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -399,7 +399,8 @@
 	uint32_t memory_size;
 	bool has_gmr;
 	bool has_mob;
-	struct mutex hw_mutex;
+	spinlock_t hw_lock;
+	spinlock_t cap_lock;
 
 	/*
 	 * VGA registers.
@@ -449,8 +450,9 @@
 	atomic_t marker_seq;
 	wait_queue_head_t fence_queue;
 	wait_queue_head_t fifo_queue;
-	int fence_queue_waiters; /* Protected by hw_mutex */
-	int goal_queue_waiters; /* Protected by hw_mutex */
+	spinlock_t waiter_lock;
+	int fence_queue_waiters; /* Protected by waiter_lock */
+	int goal_queue_waiters; /* Protected by waiter_lock */
 	atomic_t fifo_queue_waiters;
 	uint32_t last_read_seqno;
 	spinlock_t irq_lock;
@@ -553,20 +555,35 @@
 	return (struct vmw_master *) master->driver_priv;
 }
 
+/*
+ * The locking here is fine-grained, so that it is performed once
+ * for every read- and write operation. This is of course costly, but we
+ * don't perform much register access in the timing critical paths anyway.
+ * Instead we have the extra benefit of being sure that we don't forget
+ * the hw lock around register accesses.
+ */
 static inline void vmw_write(struct vmw_private *dev_priv,
 			     unsigned int offset, uint32_t value)
 {
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&dev_priv->hw_lock, irq_flags);
 	outl(offset, dev_priv->io_start + VMWGFX_INDEX_PORT);
 	outl(value, dev_priv->io_start + VMWGFX_VALUE_PORT);
+	spin_unlock_irqrestore(&dev_priv->hw_lock, irq_flags);
 }
 
 static inline uint32_t vmw_read(struct vmw_private *dev_priv,
 				unsigned int offset)
 {
-	uint32_t val;
+	unsigned long irq_flags;
+	u32 val;
 
+	spin_lock_irqsave(&dev_priv->hw_lock, irq_flags);
 	outl(offset, dev_priv->io_start + VMWGFX_INDEX_PORT);
 	val = inl(dev_priv->io_start + VMWGFX_VALUE_PORT);
+	spin_unlock_irqrestore(&dev_priv->hw_lock, irq_flags);
+
 	return val;
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index b7594cb..945f1e0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -35,7 +35,7 @@
 	struct vmw_private *dev_priv;
 	spinlock_t lock;
 	struct list_head fence_list;
-	struct work_struct work, ping_work;
+	struct work_struct work;
 	u32 user_fence_size;
 	u32 fence_size;
 	u32 event_fence_action_size;
@@ -134,14 +134,6 @@
 	return "svga";
 }
 
-static void vmw_fence_ping_func(struct work_struct *work)
-{
-	struct vmw_fence_manager *fman =
-		container_of(work, struct vmw_fence_manager, ping_work);
-
-	vmw_fifo_ping_host(fman->dev_priv, SVGA_SYNC_GENERIC);
-}
-
 static bool vmw_fence_enable_signaling(struct fence *f)
 {
 	struct vmw_fence_obj *fence =
@@ -155,11 +147,7 @@
 	if (seqno - fence->base.seqno < VMW_FENCE_WRAP)
 		return false;
 
-	if (mutex_trylock(&dev_priv->hw_mutex)) {
-		vmw_fifo_ping_host_locked(dev_priv, SVGA_SYNC_GENERIC);
-		mutex_unlock(&dev_priv->hw_mutex);
-	} else
-		schedule_work(&fman->ping_work);
+	vmw_fifo_ping_host(dev_priv, SVGA_SYNC_GENERIC);
 
 	return true;
 }
@@ -305,7 +293,6 @@
 	INIT_LIST_HEAD(&fman->fence_list);
 	INIT_LIST_HEAD(&fman->cleanup_list);
 	INIT_WORK(&fman->work, &vmw_fence_work_func);
-	INIT_WORK(&fman->ping_work, &vmw_fence_ping_func);
 	fman->fifo_down = true;
 	fman->user_fence_size = ttm_round_pot(sizeof(struct vmw_user_fence));
 	fman->fence_size = ttm_round_pot(sizeof(struct vmw_fence_obj));
@@ -323,7 +310,6 @@
 	bool lists_empty;
 
 	(void) cancel_work_sync(&fman->work);
-	(void) cancel_work_sync(&fman->ping_work);
 
 	spin_lock_irqsave(&fman->lock, irq_flags);
 	lists_empty = list_empty(&fman->fence_list) &&
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index 09e10ae..39f2b03 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -44,10 +44,10 @@
 		if (!dev_priv->has_mob)
 			return false;
 
-		mutex_lock(&dev_priv->hw_mutex);
+		spin_lock(&dev_priv->cap_lock);
 		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_3D);
 		result = vmw_read(dev_priv, SVGA_REG_DEV_CAP);
-		mutex_unlock(&dev_priv->hw_mutex);
+		spin_unlock(&dev_priv->cap_lock);
 
 		return (result != 0);
 	}
@@ -120,7 +120,6 @@
 	DRM_INFO("height %d\n", vmw_read(dev_priv, SVGA_REG_HEIGHT));
 	DRM_INFO("bpp %d\n", vmw_read(dev_priv, SVGA_REG_BITS_PER_PIXEL));
 
-	mutex_lock(&dev_priv->hw_mutex);
 	dev_priv->enable_state = vmw_read(dev_priv, SVGA_REG_ENABLE);
 	dev_priv->config_done_state = vmw_read(dev_priv, SVGA_REG_CONFIG_DONE);
 	dev_priv->traces_state = vmw_read(dev_priv, SVGA_REG_TRACES);
@@ -143,7 +142,6 @@
 	mb();
 
 	vmw_write(dev_priv, SVGA_REG_CONFIG_DONE, 1);
-	mutex_unlock(&dev_priv->hw_mutex);
 
 	max = ioread32(fifo_mem + SVGA_FIFO_MAX);
 	min = ioread32(fifo_mem  + SVGA_FIFO_MIN);
@@ -160,31 +158,28 @@
 	return vmw_fifo_send_fence(dev_priv, &dummy);
 }
 
-void vmw_fifo_ping_host_locked(struct vmw_private *dev_priv, uint32_t reason)
+void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason)
 {
 	__le32 __iomem *fifo_mem = dev_priv->mmio_virt;
+	static DEFINE_SPINLOCK(ping_lock);
+	unsigned long irq_flags;
 
+	/*
+	 * The ping_lock is needed because we don't have an atomic
+	 * test-and-set of the SVGA_FIFO_BUSY register.
+	 */
+	spin_lock_irqsave(&ping_lock, irq_flags);
 	if (unlikely(ioread32(fifo_mem + SVGA_FIFO_BUSY) == 0)) {
 		iowrite32(1, fifo_mem + SVGA_FIFO_BUSY);
 		vmw_write(dev_priv, SVGA_REG_SYNC, reason);
 	}
-}
-
-void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason)
-{
-	mutex_lock(&dev_priv->hw_mutex);
-
-	vmw_fifo_ping_host_locked(dev_priv, reason);
-
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock_irqrestore(&ping_lock, irq_flags);
 }
 
 void vmw_fifo_release(struct vmw_private *dev_priv, struct vmw_fifo_state *fifo)
 {
 	__le32 __iomem *fifo_mem = dev_priv->mmio_virt;
 
-	mutex_lock(&dev_priv->hw_mutex);
-
 	vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC);
 	while (vmw_read(dev_priv, SVGA_REG_BUSY) != 0)
 		;
@@ -198,7 +193,6 @@
 	vmw_write(dev_priv, SVGA_REG_TRACES,
 		  dev_priv->traces_state);
 
-	mutex_unlock(&dev_priv->hw_mutex);
 	vmw_marker_queue_takedown(&fifo->marker_queue);
 
 	if (likely(fifo->static_buffer != NULL)) {
@@ -271,7 +265,7 @@
 		return vmw_fifo_wait_noirq(dev_priv, bytes,
 					   interruptible, timeout);
 
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (atomic_add_return(1, &dev_priv->fifo_queue_waiters) > 0) {
 		spin_lock_irqsave(&dev_priv->irq_lock, irq_flags);
 		outl(SVGA_IRQFLAG_FIFO_PROGRESS,
@@ -280,7 +274,7 @@
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 
 	if (interruptible)
 		ret = wait_event_interruptible_timeout
@@ -296,14 +290,14 @@
 	else if (likely(ret > 0))
 		ret = 0;
 
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (atomic_dec_and_test(&dev_priv->fifo_queue_waiters)) {
 		spin_lock_irqsave(&dev_priv->irq_lock, irq_flags);
 		dev_priv->irq_mask &= ~SVGA_IRQFLAG_FIFO_PROGRESS;
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index 37881ec..69c8ce23 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -135,13 +135,13 @@
 		(pair_offset + max_size * sizeof(SVGA3dCapPair)) / sizeof(u32);
 	compat_cap->header.type = SVGA3DCAPS_RECORD_DEVCAPS;
 
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->cap_lock);
 	for (i = 0; i < max_size; ++i) {
 		vmw_write(dev_priv, SVGA_REG_DEV_CAP, i);
 		compat_cap->pairs[i][0] = i;
 		compat_cap->pairs[i][1] = vmw_read(dev_priv, SVGA_REG_DEV_CAP);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->cap_lock);
 
 	return 0;
 }
@@ -191,12 +191,12 @@
 		if (num > SVGA3D_DEVCAP_MAX)
 			num = SVGA3D_DEVCAP_MAX;
 
-		mutex_lock(&dev_priv->hw_mutex);
+		spin_lock(&dev_priv->cap_lock);
 		for (i = 0; i < num; ++i) {
 			vmw_write(dev_priv, SVGA_REG_DEV_CAP, i);
 			*bounce32++ = vmw_read(dev_priv, SVGA_REG_DEV_CAP);
 		}
-		mutex_unlock(&dev_priv->hw_mutex);
+		spin_unlock(&dev_priv->cap_lock);
 	} else if (gb_objects) {
 		ret = vmw_fill_compat_cap(dev_priv, bounce, size);
 		if (unlikely(ret != 0))
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
index 0c42376..9fe9827 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
@@ -62,13 +62,8 @@
 
 static bool vmw_fifo_idle(struct vmw_private *dev_priv, uint32_t seqno)
 {
-	uint32_t busy;
 
-	mutex_lock(&dev_priv->hw_mutex);
-	busy = vmw_read(dev_priv, SVGA_REG_BUSY);
-	mutex_unlock(&dev_priv->hw_mutex);
-
-	return (busy == 0);
+	return (vmw_read(dev_priv, SVGA_REG_BUSY) == 0);
 }
 
 void vmw_update_seqno(struct vmw_private *dev_priv,
@@ -184,7 +179,7 @@
 
 void vmw_seqno_waiter_add(struct vmw_private *dev_priv)
 {
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (dev_priv->fence_queue_waiters++ == 0) {
 		unsigned long irq_flags;
 
@@ -195,12 +190,12 @@
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 }
 
 void vmw_seqno_waiter_remove(struct vmw_private *dev_priv)
 {
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (--dev_priv->fence_queue_waiters == 0) {
 		unsigned long irq_flags;
 
@@ -209,13 +204,13 @@
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 }
 
 
 void vmw_goal_waiter_add(struct vmw_private *dev_priv)
 {
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (dev_priv->goal_queue_waiters++ == 0) {
 		unsigned long irq_flags;
 
@@ -226,12 +221,12 @@
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 }
 
 void vmw_goal_waiter_remove(struct vmw_private *dev_priv)
 {
-	mutex_lock(&dev_priv->hw_mutex);
+	spin_lock(&dev_priv->waiter_lock);
 	if (--dev_priv->goal_queue_waiters == 0) {
 		unsigned long irq_flags;
 
@@ -240,7 +235,7 @@
 		vmw_write(dev_priv, SVGA_REG_IRQMASK, dev_priv->irq_mask);
 		spin_unlock_irqrestore(&dev_priv->irq_lock, irq_flags);
 	}
-	mutex_unlock(&dev_priv->hw_mutex);
+	spin_unlock(&dev_priv->waiter_lock);
 }
 
 int vmw_wait_seqno(struct vmw_private *dev_priv,
@@ -315,9 +310,7 @@
 	if (!(dev_priv->capabilities & SVGA_CAP_IRQMASK))
 		return;
 
-	mutex_lock(&dev_priv->hw_mutex);
 	vmw_write(dev_priv, SVGA_REG_IRQMASK, 0);
-	mutex_unlock(&dev_priv->hw_mutex);
 
 	status = inl(dev_priv->io_start + VMWGFX_IRQSTATUS_PORT);
 	outl(status, dev_priv->io_start + VMWGFX_IRQSTATUS_PORT);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 3725b52..8725b79 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1828,9 +1828,7 @@
 	struct vmw_private *dev_priv = vmw_priv(dev);
 	struct vmw_display_unit *du = vmw_connector_to_du(connector);
 
-	mutex_lock(&dev_priv->hw_mutex);
 	num_displays = vmw_read(dev_priv, SVGA_REG_NUM_DISPLAYS);
-	mutex_unlock(&dev_priv->hw_mutex);
 
 	return ((vmw_connector_to_du(connector)->unit < num_displays &&
 		 du->pref_active) ?
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 31e8308..ab838d9 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -881,6 +881,7 @@
 config I2C_RCAR
 	tristate "Renesas R-Car I2C Controller"
 	depends on ARCH_SHMOBILE || COMPILE_TEST
+	select I2C_SLAVE
 	help
 	  If you say yes to this option, support will be included for the
 	  R-Car I2C controller.
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index bff20a5..958c8db 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -785,14 +785,16 @@
 	int ret;
 
 	pm_runtime_get_sync(&adap->dev);
-	clk_prepare_enable(i2c->clk);
+	ret = clk_enable(i2c->clk);
+	if (ret)
+		return ret;
 
 	for (retry = 0; retry < adap->retries; retry++) {
 
 		ret = s3c24xx_i2c_doxfer(i2c, msgs, num);
 
 		if (ret != -EAGAIN) {
-			clk_disable_unprepare(i2c->clk);
+			clk_disable(i2c->clk);
 			pm_runtime_put(&adap->dev);
 			return ret;
 		}
@@ -802,7 +804,7 @@
 		udelay(100);
 	}
 
-	clk_disable_unprepare(i2c->clk);
+	clk_disable(i2c->clk);
 	pm_runtime_put(&adap->dev);
 	return -EREMOTEIO;
 }
@@ -1197,7 +1199,7 @@
 
 	clk_prepare_enable(i2c->clk);
 	ret = s3c24xx_i2c_init(i2c);
-	clk_disable_unprepare(i2c->clk);
+	clk_disable(i2c->clk);
 	if (ret != 0) {
 		dev_err(&pdev->dev, "I2C controller init failed\n");
 		return ret;
@@ -1210,6 +1212,7 @@
 		i2c->irq = ret = platform_get_irq(pdev, 0);
 		if (ret <= 0) {
 			dev_err(&pdev->dev, "cannot find IRQ\n");
+			clk_unprepare(i2c->clk);
 			return ret;
 		}
 
@@ -1218,6 +1221,7 @@
 
 		if (ret != 0) {
 			dev_err(&pdev->dev, "cannot claim IRQ %d\n", i2c->irq);
+			clk_unprepare(i2c->clk);
 			return ret;
 		}
 	}
@@ -1225,6 +1229,7 @@
 	ret = s3c24xx_i2c_register_cpufreq(i2c);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to register cpufreq notifier\n");
+		clk_unprepare(i2c->clk);
 		return ret;
 	}
 
@@ -1241,6 +1246,7 @@
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to add bus to i2c core\n");
 		s3c24xx_i2c_deregister_cpufreq(i2c);
+		clk_unprepare(i2c->clk);
 		return ret;
 	}
 
@@ -1262,6 +1268,8 @@
 {
 	struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev);
 
+	clk_unprepare(i2c->clk);
+
 	pm_runtime_disable(&i2c->adap.dev);
 	pm_runtime_disable(&pdev->dev);
 
@@ -1293,13 +1301,16 @@
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev);
+	int ret;
 
 	if (!IS_ERR(i2c->sysreg))
 		regmap_write(i2c->sysreg, EXYNOS5_SYS_I2C_CFG, i2c->sys_i2c_cfg);
 
-	clk_prepare_enable(i2c->clk);
+	ret = clk_enable(i2c->clk);
+	if (ret)
+		return ret;
 	s3c24xx_i2c_init(i2c);
-	clk_disable_unprepare(i2c->clk);
+	clk_disable(i2c->clk);
 	i2c->suspended = 0;
 
 	return 0;
diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c
index 440d5db..007818b 100644
--- a/drivers/i2c/busses/i2c-sh_mobile.c
+++ b/drivers/i2c/busses/i2c-sh_mobile.c
@@ -139,6 +139,7 @@
 	int pos;
 	int sr;
 	bool send_stop;
+	bool stop_after_dma;
 
 	struct resource *res;
 	struct dma_chan *dma_tx;
@@ -407,7 +408,7 @@
 
 	if (pd->pos == pd->msg->len) {
 		/* Send stop if we haven't yet (DMA case) */
-		if (pd->send_stop && (iic_rd(pd, ICCR) & ICCR_BBSY))
+		if (pd->send_stop && pd->stop_after_dma)
 			i2c_op(pd, OP_TX_STOP, 0);
 		return 1;
 	}
@@ -449,6 +450,13 @@
 		real_pos = pd->pos - 2;
 
 		if (pd->pos == pd->msg->len) {
+			if (pd->stop_after_dma) {
+				/* Simulate PIO end condition after DMA transfer */
+				i2c_op(pd, OP_RX_STOP, 0);
+				pd->pos++;
+				break;
+			}
+
 			if (real_pos < 0) {
 				i2c_op(pd, OP_RX_STOP, 0);
 				break;
@@ -536,6 +544,7 @@
 
 	sh_mobile_i2c_dma_unmap(pd);
 	pd->pos = pd->msg->len;
+	pd->stop_after_dma = true;
 
 	iic_set_clr(pd, ICIC, 0, ICIC_TDMAE | ICIC_RDMAE);
 }
@@ -726,6 +735,7 @@
 		bool do_start = pd->send_stop || !i;
 		msg = &msgs[i];
 		pd->send_stop = i == num - 1 || msg->flags & I2C_M_STOP;
+		pd->stop_after_dma = false;
 
 		err = start_ch(pd, msg, do_start);
 		if (err)
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 39d25a8..e9eae57 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -2972,6 +2972,7 @@
 }
 EXPORT_SYMBOL(i2c_smbus_xfer);
 
+#if IS_ENABLED(CONFIG_I2C_SLAVE)
 int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb)
 {
 	int ret;
@@ -3019,6 +3020,7 @@
 	return ret;
 }
 EXPORT_SYMBOL_GPL(i2c_slave_unregister);
+#endif
 
 MODULE_AUTHOR("Simon G. Vogl <simon@tk.uni-linz.ac.at>");
 MODULE_DESCRIPTION("I2C-Bus main module");
diff --git a/drivers/i2c/i2c-slave-eeprom.c b/drivers/i2c/i2c-slave-eeprom.c
index 6631400..cf9b09d 100644
--- a/drivers/i2c/i2c-slave-eeprom.c
+++ b/drivers/i2c/i2c-slave-eeprom.c
@@ -74,7 +74,7 @@
 	struct eeprom_data *eeprom;
 	unsigned long flags;
 
-	if (off + count >= attr->size)
+	if (off + count > attr->size)
 		return -EFBIG;
 
 	eeprom = dev_get_drvdata(container_of(kobj, struct device, kobj));
@@ -92,7 +92,7 @@
 	struct eeprom_data *eeprom;
 	unsigned long flags;
 
-	if (off + count >= attr->size)
+	if (off + count > attr->size)
 		return -EFBIG;
 
 	eeprom = dev_get_drvdata(container_of(kobj, struct device, kobj));
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 77ecf6d..6e22682 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1097,6 +1097,8 @@
  * Asus UX31               0x361f00        20, 15, 0e      clickpad
  * Asus UX32VD             0x361f02        00, 15, 0e      clickpad
  * Avatar AVIU-145A2       0x361f00        ?               clickpad
+ * Fujitsu LIFEBOOK E544   0x470f00        d0, 12, 09      2 hw buttons
+ * Fujitsu LIFEBOOK E554   0x570f01        40, 14, 0c      2 hw buttons
  * Fujitsu H730            0x570f00        c0, 14, 0c      3 hw buttons (**)
  * Gigabyte U2442          0x450f01        58, 17, 0c      2 hw buttons
  * Lenovo L430             0x350f02        b9, 15, 0c      2 hw buttons (*)
@@ -1475,6 +1477,20 @@
 			DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H730"),
 		},
 	},
+	{
+		/* Fujitsu LIFEBOOK E554  does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E554"),
+		},
+	},
+	{
+		/* Fujitsu LIFEBOOK E544  does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E544"),
+		},
+	},
 #endif
 	{ }
 };
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index f947292..23e26e0 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -135,8 +135,9 @@
 		1232, 5710, 1156, 4696
 	},
 	{
-		(const char * const []){"LEN0034", "LEN0036", "LEN0039",
-					"LEN2002", "LEN2004", NULL},
+		(const char * const []){"LEN0034", "LEN0036", "LEN0037",
+					"LEN0039", "LEN2002", "LEN2004",
+					NULL},
 		1024, 5112, 2024, 4832
 	},
 	{
@@ -165,7 +166,7 @@
 	"LEN0034", /* T431s, L440, L540, T540, W540, X1 Carbon 2nd */
 	"LEN0035", /* X240 */
 	"LEN0036", /* T440 */
-	"LEN0037",
+	"LEN0037", /* X1 Carbon 2nd */
 	"LEN0038",
 	"LEN0039", /* T440s */
 	"LEN0041",
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 764857b..c115565 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -152,6 +152,14 @@
 		},
 	},
 	{
+		/* Medion Akoya E7225 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Medion"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"),
+		},
+	},
+	{
 		/* Blue FB5601 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "blue"),
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index f722a0c..c48da05 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -315,6 +315,7 @@
 	.attach_dev	= gart_iommu_attach_dev,
 	.detach_dev	= gart_iommu_detach_dev,
 	.map		= gart_iommu_map,
+	.map_sg		= default_iommu_map_sg,
 	.unmap		= gart_iommu_unmap,
 	.iova_to_phys	= gart_iommu_iova_to_phys,
 	.pgsize_bitmap	= GART_IOMMU_PGSIZES,
@@ -395,7 +396,7 @@
 	do_gart_setup(gart, NULL);
 
 	gart_handle = gart;
-	bus_set_iommu(&platform_bus_type, &gart_iommu_ops);
+
 	return 0;
 }
 
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 21b1562..c1c0104 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -683,7 +683,7 @@
 	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
 	if (!cmd) {
 		DMERR("could not allocate metadata struct");
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	atomic_set(&cmd->ref_count, 1);
@@ -745,7 +745,7 @@
 		return cmd;
 
 	cmd = metadata_open(bdev, data_block_size, may_format_device, policy_hint_size);
-	if (cmd) {
+	if (!IS_ERR(cmd)) {
 		mutex_lock(&table_lock);
 		cmd2 = lookup(bdev);
 		if (cmd2) {
@@ -780,9 +780,10 @@
 {
 	struct dm_cache_metadata *cmd = lookup_or_open(bdev, data_block_size,
 						       may_format_device, policy_hint_size);
-	if (cmd && !same_params(cmd, data_block_size)) {
+
+	if (!IS_ERR(cmd) && !same_params(cmd, data_block_size)) {
 		dm_cache_metadata_close(cmd);
-		return NULL;
+		return ERR_PTR(-EINVAL);
 	}
 
 	return cmd;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 4934789..07705ee 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -3385,6 +3385,12 @@
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
 
+	if (get_pool_mode(pool) >= PM_READ_ONLY) {
+		DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode",
+		      dm_device_name(pool->pool_md));
+		return -EINVAL;
+	}
+
 	if (!strcasecmp(argv[0], "create_thin"))
 		r = process_create_thin_mesg(argc, argv, pool);
 
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index f94a9fa..c672c4d 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -615,6 +615,9 @@
 
 	c_can_irq_control(priv, false);
 
+	/* put ctrl to init on stop to end ongoing transmission */
+	priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_INIT);
+
 	/* deactivate pins */
 	pinctrl_pm_select_sleep_state(dev->dev.parent);
 	priv->can.state = CAN_STATE_STOPPED;
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index c32cd61..7af379c 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -587,7 +587,7 @@
 			  usb_sndbulkpipe(dev->udev,
 					  dev->bulk_out->bEndpointAddress),
 			  buf, msg->len,
-			  kvaser_usb_simple_msg_callback, priv);
+			  kvaser_usb_simple_msg_callback, netdev);
 	usb_anchor_urb(urb, &priv->tx_submitted);
 
 	err = usb_submit_urb(urb, GFP_ATOMIC);
@@ -662,11 +662,6 @@
 	priv = dev->nets[channel];
 	stats = &priv->netdev->stats;
 
-	if (status & M16C_STATE_BUS_RESET) {
-		kvaser_usb_unlink_tx_urbs(priv);
-		return;
-	}
-
 	skb = alloc_can_err_skb(priv->netdev, &cf);
 	if (!skb) {
 		stats->rx_dropped++;
@@ -677,7 +672,7 @@
 
 	netdev_dbg(priv->netdev, "Error status: 0x%02x\n", status);
 
-	if (status & M16C_STATE_BUS_OFF) {
+	if (status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) {
 		cf->can_id |= CAN_ERR_BUSOFF;
 
 		priv->can.can_stats.bus_off++;
@@ -703,9 +698,7 @@
 		}
 
 		new_state = CAN_STATE_ERROR_PASSIVE;
-	}
-
-	if (status == M16C_STATE_BUS_ERROR) {
+	} else if (status & M16C_STATE_BUS_ERROR) {
 		if ((priv->can.state < CAN_STATE_ERROR_WARNING) &&
 		    ((txerr >= 96) || (rxerr >= 96))) {
 			cf->can_id |= CAN_ERR_CRTL;
@@ -715,7 +708,8 @@
 
 			priv->can.can_stats.error_warning++;
 			new_state = CAN_STATE_ERROR_WARNING;
-		} else if (priv->can.state > CAN_STATE_ERROR_ACTIVE) {
+		} else if ((priv->can.state > CAN_STATE_ERROR_ACTIVE) &&
+			   ((txerr < 96) && (rxerr < 96))) {
 			cf->can_id |= CAN_ERR_PROT;
 			cf->data[2] = CAN_ERR_PROT_ACTIVE;
 
@@ -1590,7 +1584,7 @@
 {
 	struct kvaser_usb *dev;
 	int err = -ENOMEM;
-	int i;
+	int i, retry = 3;
 
 	dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL);
 	if (!dev)
@@ -1608,7 +1602,15 @@
 
 	usb_set_intfdata(intf, dev);
 
-	err = kvaser_usb_get_software_info(dev);
+	/* On some x86 laptops, plugging a Kvaser device again after
+	 * an unplug makes the firmware always ignore the very first
+	 * command. For such a case, provide some room for retries
+	 * instead of completely exiting the driver.
+	 */
+	do {
+		err = kvaser_usb_get_software_info(dev);
+	} while (--retry && err == -ETIMEDOUT);
+
 	if (err) {
 		dev_err(&intf->dev,
 			"Cannot get software infos, error %d\n", err);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 75b08c6..29a0927 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -767,16 +767,17 @@
 #define MTL_Q_RQOMR			0x40
 #define MTL_Q_RQMPOCR			0x44
 #define MTL_Q_RQDR			0x4c
+#define MTL_Q_RQFCR			0x50
 #define MTL_Q_IER			0x70
 #define MTL_Q_ISR			0x74
 
 /* MTL queue register entry bit positions and sizes */
+#define MTL_Q_RQFCR_RFA_INDEX		1
+#define MTL_Q_RQFCR_RFA_WIDTH		6
+#define MTL_Q_RQFCR_RFD_INDEX		17
+#define MTL_Q_RQFCR_RFD_WIDTH		6
 #define MTL_Q_RQOMR_EHFC_INDEX		7
 #define MTL_Q_RQOMR_EHFC_WIDTH		1
-#define MTL_Q_RQOMR_RFA_INDEX		8
-#define MTL_Q_RQOMR_RFA_WIDTH		3
-#define MTL_Q_RQOMR_RFD_INDEX		13
-#define MTL_Q_RQOMR_RFD_WIDTH		3
 #define MTL_Q_RQOMR_RQS_INDEX		16
 #define MTL_Q_RQOMR_RQS_WIDTH		9
 #define MTL_Q_RQOMR_RSF_INDEX		5
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 53f5f66..4c66cd1 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -2079,10 +2079,10 @@
 
 	for (i = 0; i < pdata->rx_q_count; i++) {
 		/* Activate flow control when less than 4k left in fifo */
-		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, RFA, 2);
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQFCR, RFA, 2);
 
 		/* De-activate flow control when more than 6k left in fifo */
-		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, RFD, 4);
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQFCR, RFD, 4);
 	}
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 1d1147c..e468ed3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3175,7 +3175,7 @@
 		}
 #endif
 		if (!bnx2x_fp_lock_napi(fp))
-			return work_done;
+			return budget;
 
 		for_each_cos_in_tx_queue(fp, cos)
 			if (bnx2x_tx_queue_has_work(fp->txdata_ptr[cos]))
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index b29e027..e356afa 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1335,7 +1335,7 @@
 	int err;
 
 	if (!enic_poll_lock_napi(&enic->rq[rq]))
-		return work_done;
+		return budget;
 	/* Service RQ
 	 */
 
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index a62fc38..1c75829 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -192,6 +192,10 @@
 #define IS_TSO_HEADER(txq, addr) \
 	((addr >= txq->tso_hdrs_dma) && \
 	 (addr < txq->tso_hdrs_dma + txq->tx_ring_size * TSO_HEADER_SIZE))
+
+#define DESC_DMA_MAP_SINGLE 0
+#define DESC_DMA_MAP_PAGE 1
+
 /*
  * RX/TX descriptors.
  */
@@ -362,6 +366,7 @@
 	dma_addr_t tso_hdrs_dma;
 
 	struct tx_desc *tx_desc_area;
+	char *tx_desc_mapping; /* array to track the type of the dma mapping */
 	dma_addr_t tx_desc_dma;
 	int tx_desc_area_size;
 
@@ -750,6 +755,7 @@
 	if (txq->tx_curr_desc == txq->tx_ring_size)
 		txq->tx_curr_desc = 0;
 	desc = &txq->tx_desc_area[tx_index];
+	txq->tx_desc_mapping[tx_index] = DESC_DMA_MAP_SINGLE;
 
 	desc->l4i_chk = 0;
 	desc->byte_cnt = length;
@@ -879,14 +885,13 @@
 		skb_frag_t *this_frag;
 		int tx_index;
 		struct tx_desc *desc;
-		void *addr;
 
 		this_frag = &skb_shinfo(skb)->frags[frag];
-		addr = page_address(this_frag->page.p) + this_frag->page_offset;
 		tx_index = txq->tx_curr_desc++;
 		if (txq->tx_curr_desc == txq->tx_ring_size)
 			txq->tx_curr_desc = 0;
 		desc = &txq->tx_desc_area[tx_index];
+		txq->tx_desc_mapping[tx_index] = DESC_DMA_MAP_PAGE;
 
 		/*
 		 * The last fragment will generate an interrupt
@@ -902,8 +907,9 @@
 
 		desc->l4i_chk = 0;
 		desc->byte_cnt = skb_frag_size(this_frag);
-		desc->buf_ptr = dma_map_single(mp->dev->dev.parent, addr,
-					       desc->byte_cnt, DMA_TO_DEVICE);
+		desc->buf_ptr = skb_frag_dma_map(mp->dev->dev.parent,
+						 this_frag, 0, desc->byte_cnt,
+						 DMA_TO_DEVICE);
 	}
 }
 
@@ -936,6 +942,7 @@
 	if (txq->tx_curr_desc == txq->tx_ring_size)
 		txq->tx_curr_desc = 0;
 	desc = &txq->tx_desc_area[tx_index];
+	txq->tx_desc_mapping[tx_index] = DESC_DMA_MAP_SINGLE;
 
 	if (nr_frags) {
 		txq_submit_frag_skb(txq, skb);
@@ -1047,9 +1054,12 @@
 		int tx_index;
 		struct tx_desc *desc;
 		u32 cmd_sts;
+		char desc_dma_map;
 
 		tx_index = txq->tx_used_desc;
 		desc = &txq->tx_desc_area[tx_index];
+		desc_dma_map = txq->tx_desc_mapping[tx_index];
+
 		cmd_sts = desc->cmd_sts;
 
 		if (cmd_sts & BUFFER_OWNED_BY_DMA) {
@@ -1065,9 +1075,19 @@
 		reclaimed++;
 		txq->tx_desc_count--;
 
-		if (!IS_TSO_HEADER(txq, desc->buf_ptr))
-			dma_unmap_single(mp->dev->dev.parent, desc->buf_ptr,
-					 desc->byte_cnt, DMA_TO_DEVICE);
+		if (!IS_TSO_HEADER(txq, desc->buf_ptr)) {
+
+			if (desc_dma_map == DESC_DMA_MAP_PAGE)
+				dma_unmap_page(mp->dev->dev.parent,
+					       desc->buf_ptr,
+					       desc->byte_cnt,
+					       DMA_TO_DEVICE);
+			else
+				dma_unmap_single(mp->dev->dev.parent,
+						 desc->buf_ptr,
+						 desc->byte_cnt,
+						 DMA_TO_DEVICE);
+		}
 
 		if (cmd_sts & TX_ENABLE_INTERRUPT) {
 			struct sk_buff *skb = __skb_dequeue(&txq->tx_skb);
@@ -1996,6 +2016,7 @@
 	struct tx_queue *txq = mp->txq + index;
 	struct tx_desc *tx_desc;
 	int size;
+	int ret;
 	int i;
 
 	txq->index = index;
@@ -2048,18 +2069,34 @@
 					nexti * sizeof(struct tx_desc);
 	}
 
+	txq->tx_desc_mapping = kcalloc(txq->tx_ring_size, sizeof(char),
+				       GFP_KERNEL);
+	if (!txq->tx_desc_mapping) {
+		ret = -ENOMEM;
+		goto err_free_desc_area;
+	}
+
 	/* Allocate DMA buffers for TSO MAC/IP/TCP headers */
 	txq->tso_hdrs = dma_alloc_coherent(mp->dev->dev.parent,
 					   txq->tx_ring_size * TSO_HEADER_SIZE,
 					   &txq->tso_hdrs_dma, GFP_KERNEL);
 	if (txq->tso_hdrs == NULL) {
-		dma_free_coherent(mp->dev->dev.parent, txq->tx_desc_area_size,
-				  txq->tx_desc_area, txq->tx_desc_dma);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_free_desc_mapping;
 	}
 	skb_queue_head_init(&txq->tx_skb);
 
 	return 0;
+
+err_free_desc_mapping:
+	kfree(txq->tx_desc_mapping);
+err_free_desc_area:
+	if (index == 0 && size <= mp->tx_desc_sram_size)
+		iounmap(txq->tx_desc_area);
+	else
+		dma_free_coherent(mp->dev->dev.parent, txq->tx_desc_area_size,
+				  txq->tx_desc_area, txq->tx_desc_dma);
+	return ret;
 }
 
 static void txq_deinit(struct tx_queue *txq)
@@ -2077,6 +2114,8 @@
 	else
 		dma_free_coherent(mp->dev->dev.parent, txq->tx_desc_area_size,
 				  txq->tx_desc_area, txq->tx_desc_dma);
+	kfree(txq->tx_desc_mapping);
+
 	if (txq->tso_hdrs)
 		dma_free_coherent(mp->dev->dev.parent,
 				  txq->tx_ring_size * TSO_HEADER_SIZE,
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 6130375..c531c8a 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -2388,7 +2388,10 @@
 
 	work_done = netxen_process_rcv_ring(sds_ring, budget);
 
-	if ((work_done < budget) && tx_complete) {
+	if (!tx_complete)
+		work_done = budget;
+
+	if (work_done < budget) {
 		napi_complete(&sds_ring->napi);
 		if (test_bit(__NX_DEV_UP, &adapter->state))
 			netxen_nic_enable_int(sds_ring);
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 6576243..04283fe 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -396,6 +396,9 @@
 	[TSU_ADRL31]	= 0x01fc,
 };
 
+static void sh_eth_rcv_snd_disable(struct net_device *ndev);
+static struct net_device_stats *sh_eth_get_stats(struct net_device *ndev);
+
 static bool sh_eth_is_gether(struct sh_eth_private *mdp)
 {
 	return mdp->reg_offset == sh_eth_offset_gigabit;
@@ -1120,6 +1123,7 @@
 	int rx_ringsize = sizeof(*rxdesc) * mdp->num_rx_ring;
 	int tx_ringsize = sizeof(*txdesc) * mdp->num_tx_ring;
 	int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1;
+	dma_addr_t dma_addr;
 
 	mdp->cur_rx = 0;
 	mdp->cur_tx = 0;
@@ -1133,7 +1137,6 @@
 		/* skb */
 		mdp->rx_skbuff[i] = NULL;
 		skb = netdev_alloc_skb(ndev, skbuff_size);
-		mdp->rx_skbuff[i] = skb;
 		if (skb == NULL)
 			break;
 		sh_eth_set_receive_align(skb);
@@ -1142,9 +1145,15 @@
 		rxdesc = &mdp->rx_ring[i];
 		/* The size of the buffer is a multiple of 16 bytes. */
 		rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16);
-		dma_map_single(&ndev->dev, skb->data, rxdesc->buffer_length,
-			       DMA_FROM_DEVICE);
-		rxdesc->addr = virt_to_phys(skb->data);
+		dma_addr = dma_map_single(&ndev->dev, skb->data,
+					  rxdesc->buffer_length,
+					  DMA_FROM_DEVICE);
+		if (dma_mapping_error(&ndev->dev, dma_addr)) {
+			kfree_skb(skb);
+			break;
+		}
+		mdp->rx_skbuff[i] = skb;
+		rxdesc->addr = dma_addr;
 		rxdesc->status = cpu_to_edmac(mdp, RD_RACT | RD_RFP);
 
 		/* Rx descriptor address set */
@@ -1316,8 +1325,10 @@
 		     RFLR);
 
 	sh_eth_write(ndev, sh_eth_read(ndev, EESR), EESR);
-	if (start)
+	if (start) {
+		mdp->irq_enabled = true;
 		sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR);
+	}
 
 	/* PAUSE Prohibition */
 	val = (sh_eth_read(ndev, ECMR) & ECMR_DM) |
@@ -1356,6 +1367,33 @@
 	return ret;
 }
 
+static void sh_eth_dev_exit(struct net_device *ndev)
+{
+	struct sh_eth_private *mdp = netdev_priv(ndev);
+	int i;
+
+	/* Deactivate all TX descriptors, so DMA should stop at next
+	 * packet boundary if it's currently running
+	 */
+	for (i = 0; i < mdp->num_tx_ring; i++)
+		mdp->tx_ring[i].status &= ~cpu_to_edmac(mdp, TD_TACT);
+
+	/* Disable TX FIFO egress to MAC */
+	sh_eth_rcv_snd_disable(ndev);
+
+	/* Stop RX DMA at next packet boundary */
+	sh_eth_write(ndev, 0, EDRRR);
+
+	/* Aside from TX DMA, we can't tell when the hardware is
+	 * really stopped, so we need to reset to make sure.
+	 * Before doing that, wait for long enough to *probably*
+	 * finish transmitting the last packet and poll stats.
+	 */
+	msleep(2); /* max frame time at 10 Mbps < 1250 us */
+	sh_eth_get_stats(ndev);
+	sh_eth_reset(ndev);
+}
+
 /* free Tx skb function */
 static int sh_eth_txfree(struct net_device *ndev)
 {
@@ -1400,6 +1438,7 @@
 	u16 pkt_len = 0;
 	u32 desc_status;
 	int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1;
+	dma_addr_t dma_addr;
 
 	boguscnt = min(boguscnt, *quota);
 	limit = boguscnt;
@@ -1447,9 +1486,9 @@
 			mdp->rx_skbuff[entry] = NULL;
 			if (mdp->cd->rpadir)
 				skb_reserve(skb, NET_IP_ALIGN);
-			dma_sync_single_for_cpu(&ndev->dev, rxdesc->addr,
-						ALIGN(mdp->rx_buf_sz, 16),
-						DMA_FROM_DEVICE);
+			dma_unmap_single(&ndev->dev, rxdesc->addr,
+					 ALIGN(mdp->rx_buf_sz, 16),
+					 DMA_FROM_DEVICE);
 			skb_put(skb, pkt_len);
 			skb->protocol = eth_type_trans(skb, ndev);
 			netif_receive_skb(skb);
@@ -1469,15 +1508,20 @@
 
 		if (mdp->rx_skbuff[entry] == NULL) {
 			skb = netdev_alloc_skb(ndev, skbuff_size);
-			mdp->rx_skbuff[entry] = skb;
 			if (skb == NULL)
 				break;	/* Better luck next round. */
 			sh_eth_set_receive_align(skb);
-			dma_map_single(&ndev->dev, skb->data,
-				       rxdesc->buffer_length, DMA_FROM_DEVICE);
+			dma_addr = dma_map_single(&ndev->dev, skb->data,
+						  rxdesc->buffer_length,
+						  DMA_FROM_DEVICE);
+			if (dma_mapping_error(&ndev->dev, dma_addr)) {
+				kfree_skb(skb);
+				break;
+			}
+			mdp->rx_skbuff[entry] = skb;
 
 			skb_checksum_none_assert(skb);
-			rxdesc->addr = virt_to_phys(skb->data);
+			rxdesc->addr = dma_addr;
 		}
 		if (entry >= mdp->num_rx_ring - 1)
 			rxdesc->status |=
@@ -1573,7 +1617,6 @@
 		if (intr_status & EESR_RFRMER) {
 			/* Receive Frame Overflow int */
 			ndev->stats.rx_frame_errors++;
-			netif_err(mdp, rx_err, ndev, "Receive Abort\n");
 		}
 	}
 
@@ -1592,13 +1635,11 @@
 	if (intr_status & EESR_RDE) {
 		/* Receive Descriptor Empty int */
 		ndev->stats.rx_over_errors++;
-		netif_err(mdp, rx_err, ndev, "Receive Descriptor Empty\n");
 	}
 
 	if (intr_status & EESR_RFE) {
 		/* Receive FIFO Overflow int */
 		ndev->stats.rx_fifo_errors++;
-		netif_err(mdp, rx_err, ndev, "Receive FIFO Overflow\n");
 	}
 
 	if (!mdp->cd->no_ade && (intr_status & EESR_ADE)) {
@@ -1653,7 +1694,12 @@
 	if (intr_status & (EESR_RX_CHECK | cd->tx_check | cd->eesr_err_check))
 		ret = IRQ_HANDLED;
 	else
-		goto other_irq;
+		goto out;
+
+	if (!likely(mdp->irq_enabled)) {
+		sh_eth_write(ndev, 0, EESIPR);
+		goto out;
+	}
 
 	if (intr_status & EESR_RX_CHECK) {
 		if (napi_schedule_prep(&mdp->napi)) {
@@ -1684,7 +1730,7 @@
 		sh_eth_error(ndev, intr_status);
 	}
 
-other_irq:
+out:
 	spin_unlock(&mdp->lock);
 
 	return ret;
@@ -1712,7 +1758,8 @@
 	napi_complete(napi);
 
 	/* Reenable Rx interrupts */
-	sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR);
+	if (mdp->irq_enabled)
+		sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR);
 out:
 	return budget - quota;
 }
@@ -1968,40 +2015,50 @@
 		return -EINVAL;
 
 	if (netif_running(ndev)) {
+		netif_device_detach(ndev);
 		netif_tx_disable(ndev);
-		/* Disable interrupts by clearing the interrupt mask. */
-		sh_eth_write(ndev, 0x0000, EESIPR);
-		/* Stop the chip's Tx and Rx processes. */
-		sh_eth_write(ndev, 0, EDTRR);
-		sh_eth_write(ndev, 0, EDRRR);
-		synchronize_irq(ndev->irq);
-	}
 
-	/* Free all the skbuffs in the Rx queue. */
-	sh_eth_ring_free(ndev);
-	/* Free DMA buffer */
-	sh_eth_free_dma_buffer(mdp);
+		/* Serialise with the interrupt handler and NAPI, then
+		 * disable interrupts.  We have to clear the
+		 * irq_enabled flag first to ensure that interrupts
+		 * won't be re-enabled.
+		 */
+		mdp->irq_enabled = false;
+		synchronize_irq(ndev->irq);
+		napi_synchronize(&mdp->napi);
+		sh_eth_write(ndev, 0x0000, EESIPR);
+
+		sh_eth_dev_exit(ndev);
+
+		/* Free all the skbuffs in the Rx queue. */
+		sh_eth_ring_free(ndev);
+		/* Free DMA buffer */
+		sh_eth_free_dma_buffer(mdp);
+	}
 
 	/* Set new parameters */
 	mdp->num_rx_ring = ring->rx_pending;
 	mdp->num_tx_ring = ring->tx_pending;
 
-	ret = sh_eth_ring_init(ndev);
-	if (ret < 0) {
-		netdev_err(ndev, "%s: sh_eth_ring_init failed.\n", __func__);
-		return ret;
-	}
-	ret = sh_eth_dev_init(ndev, false);
-	if (ret < 0) {
-		netdev_err(ndev, "%s: sh_eth_dev_init failed.\n", __func__);
-		return ret;
-	}
-
 	if (netif_running(ndev)) {
+		ret = sh_eth_ring_init(ndev);
+		if (ret < 0) {
+			netdev_err(ndev, "%s: sh_eth_ring_init failed.\n",
+				   __func__);
+			return ret;
+		}
+		ret = sh_eth_dev_init(ndev, false);
+		if (ret < 0) {
+			netdev_err(ndev, "%s: sh_eth_dev_init failed.\n",
+				   __func__);
+			return ret;
+		}
+
+		mdp->irq_enabled = true;
 		sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR);
 		/* Setting the Rx mode will start the Rx process. */
 		sh_eth_write(ndev, EDRRR_R, EDRRR);
-		netif_wake_queue(ndev);
+		netif_device_attach(ndev);
 	}
 
 	return 0;
@@ -2117,6 +2174,9 @@
 	}
 	spin_unlock_irqrestore(&mdp->lock, flags);
 
+	if (skb_padto(skb, ETH_ZLEN))
+		return NETDEV_TX_OK;
+
 	entry = mdp->cur_tx % mdp->num_tx_ring;
 	mdp->tx_skbuff[entry] = skb;
 	txdesc = &mdp->tx_ring[entry];
@@ -2126,10 +2186,11 @@
 				 skb->len + 2);
 	txdesc->addr = dma_map_single(&ndev->dev, skb->data, skb->len,
 				      DMA_TO_DEVICE);
-	if (skb->len < ETH_ZLEN)
-		txdesc->buffer_length = ETH_ZLEN;
-	else
-		txdesc->buffer_length = skb->len;
+	if (dma_mapping_error(&ndev->dev, txdesc->addr)) {
+		kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+	txdesc->buffer_length = skb->len;
 
 	if (entry >= mdp->num_tx_ring - 1)
 		txdesc->status |= cpu_to_edmac(mdp, TD_TACT | TD_TDLE);
@@ -2181,14 +2242,17 @@
 
 	netif_stop_queue(ndev);
 
-	/* Disable interrupts by clearing the interrupt mask. */
+	/* Serialise with the interrupt handler and NAPI, then disable
+	 * interrupts.  We have to clear the irq_enabled flag first to
+	 * ensure that interrupts won't be re-enabled.
+	 */
+	mdp->irq_enabled = false;
+	synchronize_irq(ndev->irq);
+	napi_disable(&mdp->napi);
 	sh_eth_write(ndev, 0x0000, EESIPR);
 
-	/* Stop the chip's Tx and Rx processes. */
-	sh_eth_write(ndev, 0, EDTRR);
-	sh_eth_write(ndev, 0, EDRRR);
+	sh_eth_dev_exit(ndev);
 
-	sh_eth_get_stats(ndev);
 	/* PHY Disconnect */
 	if (mdp->phydev) {
 		phy_stop(mdp->phydev);
@@ -2198,8 +2262,6 @@
 
 	free_irq(ndev->irq, ndev);
 
-	napi_disable(&mdp->napi);
-
 	/* Free all the skbuffs in the Rx queue. */
 	sh_eth_ring_free(ndev);
 
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 71f5de1..332d3c1 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -513,6 +513,7 @@
 	u32 rx_buf_sz;			/* Based on MTU+slack. */
 	int edmac_endian;
 	struct napi_struct napi;
+	bool irq_enabled;
 	/* MII transceiver section. */
 	u32 phy_id;			/* PHY ID */
 	struct mii_bus *mii_bus;	/* MDIO bus control */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 8c6b7c1..cf62ff4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2778,6 +2778,9 @@
  * @addr: iobase memory address
  * Description: this is the main probe function used to
  * call the alloc_etherdev, allocate the priv structure.
+ * Return:
+ * on success the new private structure is returned, otherwise the error
+ * pointer.
  */
 struct stmmac_priv *stmmac_dvr_probe(struct device *device,
 				     struct plat_stmmacenet_data *plat_dat,
@@ -2789,7 +2792,7 @@
 
 	ndev = alloc_etherdev(sizeof(struct stmmac_priv));
 	if (!ndev)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	SET_NETDEV_DEV(ndev, device);
 
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index e068d48..a39131f 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1683,6 +1683,19 @@
 	if (vid == priv->data.default_vlan)
 		return 0;
 
+	if (priv->data.dual_emac) {
+		/* In dual EMAC, reserved VLAN id should not be used for
+		 * creating VLAN interfaces as this can break the dual
+		 * EMAC port separation
+		 */
+		int i;
+
+		for (i = 0; i < priv->data.slaves; i++) {
+			if (vid == priv->slaves[i].port_vlan)
+				return -EINVAL;
+		}
+	}
+
 	dev_info(priv->dev, "Adding vlanid %d to vlan filter\n", vid);
 	return cpsw_add_vlan_ale_entry(priv, vid);
 }
@@ -1696,6 +1709,15 @@
 	if (vid == priv->data.default_vlan)
 		return 0;
 
+	if (priv->data.dual_emac) {
+		int i;
+
+		for (i = 0; i < priv->data.slaves; i++) {
+			if (vid == priv->slaves[i].port_vlan)
+				return -EINVAL;
+		}
+	}
+
 	dev_info(priv->dev, "removing vlanid %d from vlan filter\n", vid);
 	ret = cpsw_ale_del_vlan(priv->ale, vid, 0);
 	if (ret != 0)
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index a14d877..2e19528 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -377,9 +377,11 @@
 	};
 
 	dst = ip6_route_output(dev_net(dev), NULL, &fl6);
-	if (IS_ERR(dst))
+	if (dst->error) {
+		ret = dst->error;
+		dst_release(dst);
 		goto err;
-
+	}
 	skb_dst_drop(skb);
 	skb_dst_set(skb, dst);
 	err = ip6_local_out(skb);
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 9a72640..62b0bf4 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -285,6 +285,7 @@
 
 	__ath_cancel_work(sc);
 
+	disable_irq(sc->irq);
 	tasklet_disable(&sc->intr_tq);
 	tasklet_disable(&sc->bcon_tasklet);
 	spin_lock_bh(&sc->sc_pcu_lock);
@@ -331,6 +332,7 @@
 		r = -EIO;
 
 out:
+	enable_irq(sc->irq);
 	spin_unlock_bh(&sc->sc_pcu_lock);
 	tasklet_enable(&sc->bcon_tasklet);
 	tasklet_enable(&sc->intr_tq);
@@ -512,9 +514,6 @@
 	if (!ah || test_bit(ATH_OP_INVALID, &common->op_flags))
 		return IRQ_NONE;
 
-	if (!AR_SREV_9100(ah) && test_bit(ATH_OP_HW_RESET, &common->op_flags))
-		return IRQ_NONE;
-
 	/* shared irq, not for us */
 	if (!ath9k_hw_intrpend(ah))
 		return IRQ_NONE;
@@ -529,7 +528,7 @@
 	ath9k_debug_sync_cause(sc, sync_cause);
 	status &= ah->imask;	/* discard unasked-for bits */
 
-	if (AR_SREV_9100(ah) && test_bit(ATH_OP_HW_RESET, &common->op_flags))
+	if (test_bit(ATH_OP_HW_RESET, &common->op_flags))
 		return IRQ_HANDLED;
 
 	/*
diff --git a/drivers/net/wireless/iwlwifi/iwl-fw-file.h b/drivers/net/wireless/iwlwifi/iwl-fw-file.h
index 1bbe4fc..660ddb1 100644
--- a/drivers/net/wireless/iwlwifi/iwl-fw-file.h
+++ b/drivers/net/wireless/iwlwifi/iwl-fw-file.h
@@ -246,6 +246,7 @@
  * @IWL_UCODE_TLV_API_BASIC_DWELL: use only basic dwell time in scan command,
  *	regardless of the band or the number of the probes. FW will calculate
  *	the actual dwell time.
+ * @IWL_UCODE_TLV_API_SINGLE_SCAN_EBS: EBS is supported for single scans too.
  */
 enum iwl_ucode_tlv_api {
 	IWL_UCODE_TLV_API_WOWLAN_CONFIG_TID	= BIT(0),
@@ -257,6 +258,7 @@
 	IWL_UCODE_TLV_API_SF_NO_DUMMY_NOTIF	= BIT(7),
 	IWL_UCODE_TLV_API_FRAGMENTED_SCAN	= BIT(8),
 	IWL_UCODE_TLV_API_BASIC_DWELL		= BIT(13),
+	IWL_UCODE_TLV_API_SINGLE_SCAN_EBS	= BIT(16),
 };
 
 /**
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
index 201846d..cfc0e65 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
@@ -653,8 +653,11 @@
 };
 
 /* iwl_scan_channel_opt - CHANNEL_OPTIMIZATION_API_S
- * @flags: enum iwl_scan_channel_flgs
- * @non_ebs_ratio: how many regular scan iteration before EBS
+ * @flags: enum iwl_scan_channel_flags
+ * @non_ebs_ratio: defines the ratio of number of scan iterations where EBS is
+ *	involved.
+ *	1 - EBS is disabled.
+ *	2 - every second scan will be full scan(and so on).
  */
 struct iwl_scan_channel_opt {
 	__le16 flags;
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index e880f9d..2091558 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -3343,18 +3343,16 @@
 		msk |= mvmsta->tfd_queue_msk;
 	}
 
-	if (drop) {
-		if (iwl_mvm_flush_tx_path(mvm, msk, true))
-			IWL_ERR(mvm, "flush request fail\n");
-		mutex_unlock(&mvm->mutex);
-	} else {
-		mutex_unlock(&mvm->mutex);
+	msk &= ~BIT(vif->hw_queue[IEEE80211_AC_VO]);
 
-		/* this can take a while, and we may need/want other operations
-		 * to succeed while doing this, so do it without the mutex held
-		 */
-		iwl_trans_wait_tx_queue_empty(mvm->trans, msk);
-	}
+	if (iwl_mvm_flush_tx_path(mvm, msk, true))
+		IWL_ERR(mvm, "flush request fail\n");
+	mutex_unlock(&mvm->mutex);
+
+	/* this can take a while, and we may need/want other operations
+	 * to succeed while doing this, so do it without the mutex held
+	 */
+	iwl_trans_wait_tx_queue_empty(mvm->trans, msk);
 }
 
 const struct ieee80211_ops iwl_mvm_hw_ops = {
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index ec9a8e7..844bf7c 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -72,6 +72,8 @@
 
 #define IWL_PLCP_QUIET_THRESH 1
 #define IWL_ACTIVE_QUIET_TIME 10
+#define IWL_DENSE_EBS_SCAN_RATIO 5
+#define IWL_SPARSE_EBS_SCAN_RATIO 1
 
 struct iwl_mvm_scan_params {
 	u32 max_out_time;
@@ -1105,6 +1107,12 @@
 		return iwl_umac_scan_stop(mvm, IWL_UMAC_SCAN_UID_SCHED_SCAN,
 					  notify);
 
+	if (mvm->scan_status == IWL_MVM_SCAN_NONE)
+		return 0;
+
+	if (iwl_mvm_is_radio_killed(mvm))
+		goto out;
+
 	if (mvm->scan_status != IWL_MVM_SCAN_SCHED &&
 	    (!(mvm->fw->ucode_capa.api[0] & IWL_UCODE_TLV_API_LMAC_SCAN) ||
 	     mvm->scan_status != IWL_MVM_SCAN_OS)) {
@@ -1141,6 +1149,7 @@
 	if (mvm->scan_status == IWL_MVM_SCAN_OS)
 		iwl_mvm_unref(mvm, IWL_MVM_REF_SCAN);
 
+out:
 	mvm->scan_status = IWL_MVM_SCAN_NONE;
 
 	if (notify) {
@@ -1297,18 +1306,6 @@
 	cmd->scan_prio = cpu_to_le32(IWL_SCAN_PRIORITY_HIGH);
 	cmd->iter_num = cpu_to_le32(1);
 
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_EBS_SUPPORT &&
-	    mvm->last_ebs_successful) {
-		cmd->channel_opt[0].flags =
-			cpu_to_le16(IWL_SCAN_CHANNEL_FLAG_EBS |
-				    IWL_SCAN_CHANNEL_FLAG_EBS_ACCURATE |
-				    IWL_SCAN_CHANNEL_FLAG_CACHE_ADD);
-		cmd->channel_opt[1].flags =
-			cpu_to_le16(IWL_SCAN_CHANNEL_FLAG_EBS |
-				    IWL_SCAN_CHANNEL_FLAG_EBS_ACCURATE |
-				    IWL_SCAN_CHANNEL_FLAG_CACHE_ADD);
-	}
-
 	if (iwl_mvm_rrm_scan_needed(mvm))
 		cmd->scan_flags |=
 			cpu_to_le32(IWL_MVM_LMAC_SCAN_FLAGS_RRM_ENABLED);
@@ -1383,6 +1380,22 @@
 	cmd->schedule[1].iterations = 0;
 	cmd->schedule[1].full_scan_mul = 0;
 
+	if (mvm->fw->ucode_capa.api[0] & IWL_UCODE_TLV_API_SINGLE_SCAN_EBS &&
+	    mvm->last_ebs_successful) {
+		cmd->channel_opt[0].flags =
+			cpu_to_le16(IWL_SCAN_CHANNEL_FLAG_EBS |
+				    IWL_SCAN_CHANNEL_FLAG_EBS_ACCURATE |
+				    IWL_SCAN_CHANNEL_FLAG_CACHE_ADD);
+		cmd->channel_opt[0].non_ebs_ratio =
+			cpu_to_le16(IWL_DENSE_EBS_SCAN_RATIO);
+		cmd->channel_opt[1].flags =
+			cpu_to_le16(IWL_SCAN_CHANNEL_FLAG_EBS |
+				    IWL_SCAN_CHANNEL_FLAG_EBS_ACCURATE |
+				    IWL_SCAN_CHANNEL_FLAG_CACHE_ADD);
+		cmd->channel_opt[1].non_ebs_ratio =
+			cpu_to_le16(IWL_SPARSE_EBS_SCAN_RATIO);
+	}
+
 	for (i = 1; i <= req->req.n_ssids; i++)
 		ssid_bitmap |= BIT(i);
 
@@ -1483,6 +1496,22 @@
 	cmd->schedule[1].iterations = 0xff;
 	cmd->schedule[1].full_scan_mul = IWL_FULL_SCAN_MULTIPLIER;
 
+	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_EBS_SUPPORT &&
+	    mvm->last_ebs_successful) {
+		cmd->channel_opt[0].flags =
+			cpu_to_le16(IWL_SCAN_CHANNEL_FLAG_EBS |
+				    IWL_SCAN_CHANNEL_FLAG_EBS_ACCURATE |
+				    IWL_SCAN_CHANNEL_FLAG_CACHE_ADD);
+		cmd->channel_opt[0].non_ebs_ratio =
+			cpu_to_le16(IWL_DENSE_EBS_SCAN_RATIO);
+		cmd->channel_opt[1].flags =
+			cpu_to_le16(IWL_SCAN_CHANNEL_FLAG_EBS |
+				    IWL_SCAN_CHANNEL_FLAG_EBS_ACCURATE |
+				    IWL_SCAN_CHANNEL_FLAG_CACHE_ADD);
+		cmd->channel_opt[1].non_ebs_ratio =
+			cpu_to_le16(IWL_SPARSE_EBS_SCAN_RATIO);
+	}
+
 	iwl_mvm_lmac_scan_cfg_channels(mvm, req->channels, req->n_channels,
 				       ssid_bitmap, cmd);
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index 4333306..c59d075 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -90,8 +90,6 @@
 
 	if (ieee80211_is_probe_resp(fc))
 		tx_flags |= TX_CMD_FLG_TSF;
-	else if (ieee80211_is_back_req(fc))
-		tx_flags |= TX_CMD_FLG_ACK | TX_CMD_FLG_BAR;
 
 	if (ieee80211_has_morefrags(fc))
 		tx_flags |= TX_CMD_FLG_MORE_FRAG;
@@ -100,6 +98,15 @@
 		u8 *qc = ieee80211_get_qos_ctl(hdr);
 		tx_cmd->tid_tspec = qc[0] & 0xf;
 		tx_flags &= ~TX_CMD_FLG_SEQ_CTL;
+	} else if (ieee80211_is_back_req(fc)) {
+		struct ieee80211_bar *bar = (void *)skb->data;
+		u16 control = le16_to_cpu(bar->control);
+
+		tx_flags |= TX_CMD_FLG_ACK | TX_CMD_FLG_BAR;
+		tx_cmd->tid_tspec = (control &
+				     IEEE80211_BAR_CTRL_TID_INFO_MASK) >>
+			IEEE80211_BAR_CTRL_TID_INFO_SHIFT;
+		WARN_ON_ONCE(tx_cmd->tid_tspec >= IWL_MAX_TID_COUNT);
 	} else {
 		tx_cmd->tid_tspec = IWL_TID_NON_QOS;
 		if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index dfd021e..f4cd0b9 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -177,7 +177,7 @@
 	struct device		*dev;
 	struct pinctrl_dev	*pctl;
 
-	int			nbanks;
+	int			nactive_banks;
 
 	uint32_t		*mux_mask;
 	int			nmux;
@@ -653,12 +653,18 @@
 	int mux;
 
 	/* check if it's a valid config */
-	if (pin->bank >= info->nbanks) {
+	if (pin->bank >= gpio_banks) {
 		dev_err(info->dev, "%s: pin conf %d bank_id %d >= nbanks %d\n",
-			name, index, pin->bank, info->nbanks);
+			name, index, pin->bank, gpio_banks);
 		return -EINVAL;
 	}
 
+	if (!gpio_chips[pin->bank]) {
+		dev_err(info->dev, "%s: pin conf %d bank_id %d not enabled\n",
+			name, index, pin->bank);
+		return -ENXIO;
+	}
+
 	if (pin->pin >= MAX_NB_GPIO_PER_BANK) {
 		dev_err(info->dev, "%s: pin conf %d pin_bank_id %d >= %d\n",
 			name, index, pin->pin, MAX_NB_GPIO_PER_BANK);
@@ -981,7 +987,8 @@
 
 	for_each_child_of_node(np, child) {
 		if (of_device_is_compatible(child, gpio_compat)) {
-			info->nbanks++;
+			if (of_device_is_available(child))
+				info->nactive_banks++;
 		} else {
 			info->nfunctions++;
 			info->ngroups += of_get_child_count(child);
@@ -1003,11 +1010,11 @@
 	}
 
 	size /= sizeof(*list);
-	if (!size || size % info->nbanks) {
-		dev_err(info->dev, "wrong mux mask array should be by %d\n", info->nbanks);
+	if (!size || size % gpio_banks) {
+		dev_err(info->dev, "wrong mux mask array should be by %d\n", gpio_banks);
 		return -EINVAL;
 	}
-	info->nmux = size / info->nbanks;
+	info->nmux = size / gpio_banks;
 
 	info->mux_mask = devm_kzalloc(info->dev, sizeof(u32) * size, GFP_KERNEL);
 	if (!info->mux_mask) {
@@ -1131,7 +1138,7 @@
 		of_match_device(at91_pinctrl_of_match, &pdev->dev)->data;
 	at91_pinctrl_child_count(info, np);
 
-	if (info->nbanks < 1) {
+	if (gpio_banks < 1) {
 		dev_err(&pdev->dev, "you need to specify at least one gpio-controller\n");
 		return -EINVAL;
 	}
@@ -1144,7 +1151,7 @@
 
 	dev_dbg(&pdev->dev, "mux-mask\n");
 	tmp = info->mux_mask;
-	for (i = 0; i < info->nbanks; i++) {
+	for (i = 0; i < gpio_banks; i++) {
 		for (j = 0; j < info->nmux; j++, tmp++) {
 			dev_dbg(&pdev->dev, "%d:%d\t0x%x\n", i, j, tmp[0]);
 		}
@@ -1162,7 +1169,7 @@
 	if (!info->groups)
 		return -ENOMEM;
 
-	dev_dbg(&pdev->dev, "nbanks = %d\n", info->nbanks);
+	dev_dbg(&pdev->dev, "nbanks = %d\n", gpio_banks);
 	dev_dbg(&pdev->dev, "nfunctions = %d\n", info->nfunctions);
 	dev_dbg(&pdev->dev, "ngroups = %d\n", info->ngroups);
 
@@ -1185,7 +1192,7 @@
 {
 	struct at91_pinctrl *info;
 	struct pinctrl_pin_desc *pdesc;
-	int ret, i, j, k;
+	int ret, i, j, k, ngpio_chips_enabled = 0;
 
 	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
 	if (!info)
@@ -1200,23 +1207,27 @@
 	 * to obtain references to the struct gpio_chip * for them, and we
 	 * need this to proceed.
 	 */
-	for (i = 0; i < info->nbanks; i++) {
-		if (!gpio_chips[i]) {
-			dev_warn(&pdev->dev, "GPIO chip %d not registered yet\n", i);
-			devm_kfree(&pdev->dev, info);
-			return -EPROBE_DEFER;
-		}
+	for (i = 0; i < gpio_banks; i++)
+		if (gpio_chips[i])
+			ngpio_chips_enabled++;
+
+	if (ngpio_chips_enabled < info->nactive_banks) {
+		dev_warn(&pdev->dev,
+			 "All GPIO chips are not registered yet (%d/%d)\n",
+			 ngpio_chips_enabled, info->nactive_banks);
+		devm_kfree(&pdev->dev, info);
+		return -EPROBE_DEFER;
 	}
 
 	at91_pinctrl_desc.name = dev_name(&pdev->dev);
-	at91_pinctrl_desc.npins = info->nbanks * MAX_NB_GPIO_PER_BANK;
+	at91_pinctrl_desc.npins = gpio_banks * MAX_NB_GPIO_PER_BANK;
 	at91_pinctrl_desc.pins = pdesc =
 		devm_kzalloc(&pdev->dev, sizeof(*pdesc) * at91_pinctrl_desc.npins, GFP_KERNEL);
 
 	if (!at91_pinctrl_desc.pins)
 		return -ENOMEM;
 
-	for (i = 0 , k = 0; i < info->nbanks; i++) {
+	for (i = 0, k = 0; i < gpio_banks; i++) {
 		for (j = 0; j < MAX_NB_GPIO_PER_BANK; j++, k++) {
 			pdesc->number = k;
 			pdesc->name = kasprintf(GFP_KERNEL, "pio%c%d", i + 'A', j);
@@ -1234,8 +1245,9 @@
 	}
 
 	/* We will handle a range of GPIO pins */
-	for (i = 0; i < info->nbanks; i++)
-		pinctrl_add_gpio_range(info->pctl, &gpio_chips[i]->range);
+	for (i = 0; i < gpio_banks; i++)
+		if (gpio_chips[i])
+			pinctrl_add_gpio_range(info->pctl, &gpio_chips[i]->range);
 
 	dev_info(&pdev->dev, "initialized AT91 pinctrl driver\n");
 
@@ -1613,9 +1625,10 @@
 static int at91_gpio_of_irq_setup(struct platform_device *pdev,
 				  struct at91_gpio_chip *at91_gpio)
 {
+	struct gpio_chip	*gpiochip_prev = NULL;
 	struct at91_gpio_chip   *prev = NULL;
 	struct irq_data		*d = irq_get_irq_data(at91_gpio->pioc_virq);
-	int ret;
+	int ret, i;
 
 	at91_gpio->pioc_hwirq = irqd_to_hwirq(d);
 
@@ -1641,24 +1654,33 @@
 		return ret;
 	}
 
-	/* Setup chained handler */
-	if (at91_gpio->pioc_idx)
-		prev = gpio_chips[at91_gpio->pioc_idx - 1];
-
 	/* The top level handler handles one bank of GPIOs, except
 	 * on some SoC it can handle up to three...
 	 * We only set up the handler for the first of the list.
 	 */
-	if (prev && prev->next == at91_gpio)
+	gpiochip_prev = irq_get_handler_data(at91_gpio->pioc_virq);
+	if (!gpiochip_prev) {
+		/* Then register the chain on the parent IRQ */
+		gpiochip_set_chained_irqchip(&at91_gpio->chip,
+					     &gpio_irqchip,
+					     at91_gpio->pioc_virq,
+					     gpio_irq_handler);
 		return 0;
+	}
 
-	/* Then register the chain on the parent IRQ */
-	gpiochip_set_chained_irqchip(&at91_gpio->chip,
-				     &gpio_irqchip,
-				     at91_gpio->pioc_virq,
-				     gpio_irq_handler);
+	prev = container_of(gpiochip_prev, struct at91_gpio_chip, chip);
 
-	return 0;
+	/* we can only have 2 banks before */
+	for (i = 0; i < 2; i++) {
+		if (prev->next) {
+			prev = prev->next;
+		} else {
+			prev->next = at91_gpio;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
 }
 
 /* This structure is replicated for each GPIO block allocated at probe time */
@@ -1675,24 +1697,6 @@
 	.ngpio			= MAX_NB_GPIO_PER_BANK,
 };
 
-static void at91_gpio_probe_fixup(void)
-{
-	unsigned i;
-	struct at91_gpio_chip *at91_gpio, *last = NULL;
-
-	for (i = 0; i < gpio_banks; i++) {
-		at91_gpio = gpio_chips[i];
-
-		/*
-		 * GPIO controller are grouped on some SoC:
-		 * PIOC, PIOD and PIOE can share the same IRQ line
-		 */
-		if (last && last->pioc_virq == at91_gpio->pioc_virq)
-			last->next = at91_gpio;
-		last = at91_gpio;
-	}
-}
-
 static struct of_device_id at91_gpio_of_match[] = {
 	{ .compatible = "atmel,at91sam9x5-gpio", .data = &at91sam9x5_ops, },
 	{ .compatible = "atmel,at91rm9200-gpio", .data = &at91rm9200_ops },
@@ -1805,8 +1809,6 @@
 	gpio_chips[alias_idx] = at91_chip;
 	gpio_banks = max(gpio_banks, alias_idx + 1);
 
-	at91_gpio_probe_fixup();
-
 	ret = at91_gpio_of_irq_setup(pdev, at91_chip);
 	if (ret)
 		goto irq_setup_err;
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index e225711..9c48fb3 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1488,7 +1488,7 @@
 }
 EXPORT_SYMBOL_GPL(regulator_get_optional);
 
-/* Locks held by regulator_put() */
+/* regulator_list_mutex lock held by regulator_put() */
 static void _regulator_put(struct regulator *regulator)
 {
 	struct regulator_dev *rdev;
@@ -1503,12 +1503,14 @@
 	/* remove any sysfs entries */
 	if (regulator->dev)
 		sysfs_remove_link(&rdev->dev.kobj, regulator->supply_name);
+	mutex_lock(&rdev->mutex);
 	kfree(regulator->supply_name);
 	list_del(&regulator->list);
 	kfree(regulator);
 
 	rdev->open_count--;
 	rdev->exclusive = 0;
+	mutex_unlock(&rdev->mutex);
 
 	module_put(rdev->owner);
 }
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index 2809ae0..ff82811 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -405,6 +405,40 @@
 	.enable_mask	= S2MPS14_ENABLE_MASK			\
 }
 
+#define regulator_desc_s2mps13_buck7(num, min, step, min_sel) {	\
+	.name		= "BUCK"#num,				\
+	.id		= S2MPS13_BUCK##num,			\
+	.ops		= &s2mps14_reg_ops,			\
+	.type		= REGULATOR_VOLTAGE,			\
+	.owner		= THIS_MODULE,				\
+	.min_uV		= min,					\
+	.uV_step	= step,					\
+	.linear_min_sel	= min_sel,				\
+	.n_voltages	= S2MPS14_BUCK_N_VOLTAGES,		\
+	.ramp_delay	= S2MPS13_BUCK_RAMP_DELAY,		\
+	.vsel_reg	= S2MPS13_REG_B1OUT + (num) * 2 - 1,	\
+	.vsel_mask	= S2MPS14_BUCK_VSEL_MASK,		\
+	.enable_reg	= S2MPS13_REG_B1CTRL + (num - 1) * 2,	\
+	.enable_mask	= S2MPS14_ENABLE_MASK			\
+}
+
+#define regulator_desc_s2mps13_buck8_10(num, min, step, min_sel) {	\
+	.name		= "BUCK"#num,				\
+	.id		= S2MPS13_BUCK##num,			\
+	.ops		= &s2mps14_reg_ops,			\
+	.type		= REGULATOR_VOLTAGE,			\
+	.owner		= THIS_MODULE,				\
+	.min_uV		= min,					\
+	.uV_step	= step,					\
+	.linear_min_sel	= min_sel,				\
+	.n_voltages	= S2MPS14_BUCK_N_VOLTAGES,		\
+	.ramp_delay	= S2MPS13_BUCK_RAMP_DELAY,		\
+	.vsel_reg	= S2MPS13_REG_B1OUT + (num) * 2 - 1,	\
+	.vsel_mask	= S2MPS14_BUCK_VSEL_MASK,		\
+	.enable_reg	= S2MPS13_REG_B1CTRL + (num) * 2 - 1,	\
+	.enable_mask	= S2MPS14_ENABLE_MASK			\
+}
+
 static const struct regulator_desc s2mps13_regulators[] = {
 	regulator_desc_s2mps13_ldo(1,  MIN_800_MV,  STEP_12_5_MV, 0x00),
 	regulator_desc_s2mps13_ldo(2,  MIN_1400_MV, STEP_50_MV,   0x0C),
@@ -452,10 +486,10 @@
 	regulator_desc_s2mps13_buck(4,  MIN_500_MV,  STEP_6_25_MV, 0x10),
 	regulator_desc_s2mps13_buck(5,  MIN_500_MV,  STEP_6_25_MV, 0x10),
 	regulator_desc_s2mps13_buck(6,  MIN_500_MV,  STEP_6_25_MV, 0x10),
-	regulator_desc_s2mps13_buck(7,  MIN_500_MV,  STEP_6_25_MV, 0x10),
-	regulator_desc_s2mps13_buck(8,  MIN_1000_MV, STEP_12_5_MV, 0x20),
-	regulator_desc_s2mps13_buck(9,  MIN_1000_MV, STEP_12_5_MV, 0x20),
-	regulator_desc_s2mps13_buck(10, MIN_500_MV,  STEP_6_25_MV, 0x10),
+	regulator_desc_s2mps13_buck7(7,  MIN_500_MV,  STEP_6_25_MV, 0x10),
+	regulator_desc_s2mps13_buck8_10(8,  MIN_1000_MV, STEP_12_5_MV, 0x20),
+	regulator_desc_s2mps13_buck8_10(9,  MIN_1000_MV, STEP_12_5_MV, 0x20),
+	regulator_desc_s2mps13_buck8_10(10, MIN_500_MV,  STEP_6_25_MV, 0x10),
 };
 
 static int s2mps14_regulator_enable(struct regulator_dev *rdev)
diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index b5e7c46..89ac1d5 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -832,6 +832,7 @@
 static const struct platform_device_id s5m_rtc_id[] = {
 	{ "s5m-rtc",		S5M8767X },
 	{ "s2mps14-rtc",	S2MPS14X },
+	{ },
 };
 
 static struct platform_driver s5m_rtc_driver = {
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index f407e37..642c77c 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1784,6 +1784,8 @@
 	QETH_DBF_TEXT(SETUP, 2, "idxanswr");
 	card = CARD_FROM_CDEV(channel->ccwdev);
 	iob = qeth_get_buffer(channel);
+	if (!iob)
+		return -ENOMEM;
 	iob->callback = idx_reply_cb;
 	memcpy(&channel->ccw, READ_CCW, sizeof(struct ccw1));
 	channel->ccw.count = QETH_BUFSIZE;
@@ -1834,6 +1836,8 @@
 	QETH_DBF_TEXT(SETUP, 2, "idxactch");
 
 	iob = qeth_get_buffer(channel);
+	if (!iob)
+		return -ENOMEM;
 	iob->callback = idx_reply_cb;
 	memcpy(&channel->ccw, WRITE_CCW, sizeof(struct ccw1));
 	channel->ccw.count = IDX_ACTIVATE_SIZE;
@@ -2021,10 +2025,36 @@
 }
 EXPORT_SYMBOL_GPL(qeth_prepare_control_data);
 
+/**
+ * qeth_send_control_data() -	send control command to the card
+ * @card:			qeth_card structure pointer
+ * @len:			size of the command buffer
+ * @iob:			qeth_cmd_buffer pointer
+ * @reply_cb:			callback function pointer
+ * @cb_card:			pointer to the qeth_card structure
+ * @cb_reply:			pointer to the qeth_reply structure
+ * @cb_cmd:			pointer to the original iob for non-IPA
+ *				commands, or to the qeth_ipa_cmd structure
+ *				for the IPA commands.
+ * @reply_param:		private pointer passed to the callback
+ *
+ * Returns the value of the `return_code' field of the response
+ * block returned from the hardware, or other error indication.
+ * Value of zero indicates successful execution of the command.
+ *
+ * Callback function gets called one or more times, with cb_cmd
+ * pointing to the response returned by the hardware. Callback
+ * function must return non-zero if more reply blocks are expected,
+ * and zero if the last or only reply block is received. Callback
+ * function can get the value of the reply_param pointer from the
+ * field 'param' of the structure qeth_reply.
+ */
+
 int qeth_send_control_data(struct qeth_card *card, int len,
 		struct qeth_cmd_buffer *iob,
-		int (*reply_cb)(struct qeth_card *, struct qeth_reply *,
-			unsigned long),
+		int (*reply_cb)(struct qeth_card *cb_card,
+				struct qeth_reply *cb_reply,
+				unsigned long cb_cmd),
 		void *reply_param)
 {
 	int rc;
@@ -2914,9 +2944,16 @@
 	struct qeth_cmd_buffer *iob;
 	struct qeth_ipa_cmd *cmd;
 
-	iob = qeth_wait_for_buffer(&card->write);
-	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
-	qeth_fill_ipacmd_header(card, cmd, ipacmd, prot);
+	iob = qeth_get_buffer(&card->write);
+	if (iob) {
+		cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
+		qeth_fill_ipacmd_header(card, cmd, ipacmd, prot);
+	} else {
+		dev_warn(&card->gdev->dev,
+			 "The qeth driver ran out of channel command buffers\n");
+		QETH_DBF_MESSAGE(1, "%s The qeth driver ran out of channel command buffers",
+				 dev_name(&card->gdev->dev));
+	}
 
 	return iob;
 }
@@ -2932,6 +2969,12 @@
 }
 EXPORT_SYMBOL_GPL(qeth_prepare_ipa_cmd);
 
+/**
+ * qeth_send_ipa_cmd() - send an IPA command
+ *
+ * See qeth_send_control_data() for explanation of the arguments.
+ */
+
 int qeth_send_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob,
 		int (*reply_cb)(struct qeth_card *, struct qeth_reply*,
 			unsigned long),
@@ -2968,6 +3011,8 @@
 	QETH_DBF_TEXT(SETUP, 2, "strtlan");
 
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_STARTLAN, 0);
+	if (!iob)
+		return -ENOMEM;
 	rc = qeth_send_ipa_cmd(card, iob, NULL, NULL);
 	return rc;
 }
@@ -3013,11 +3058,13 @@
 
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETADAPTERPARMS,
 				     QETH_PROT_IPV4);
-	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
-	cmd->data.setadapterparms.hdr.cmdlength = cmdlen;
-	cmd->data.setadapterparms.hdr.command_code = command;
-	cmd->data.setadapterparms.hdr.used_total = 1;
-	cmd->data.setadapterparms.hdr.seq_no = 1;
+	if (iob) {
+		cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
+		cmd->data.setadapterparms.hdr.cmdlength = cmdlen;
+		cmd->data.setadapterparms.hdr.command_code = command;
+		cmd->data.setadapterparms.hdr.used_total = 1;
+		cmd->data.setadapterparms.hdr.seq_no = 1;
+	}
 
 	return iob;
 }
@@ -3030,6 +3077,8 @@
 	QETH_CARD_TEXT(card, 3, "queryadp");
 	iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_COMMANDS_SUPPORTED,
 				   sizeof(struct qeth_ipacmd_setadpparms));
+	if (!iob)
+		return -ENOMEM;
 	rc = qeth_send_ipa_cmd(card, iob, qeth_query_setadapterparms_cb, NULL);
 	return rc;
 }
@@ -3080,6 +3129,8 @@
 
 	QETH_DBF_TEXT_(SETUP, 2, "qipassi%i", prot);
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_QIPASSIST, prot);
+	if (!iob)
+		return -ENOMEM;
 	rc = qeth_send_ipa_cmd(card, iob, qeth_query_ipassists_cb, NULL);
 	return rc;
 }
@@ -3119,6 +3170,8 @@
 		return -ENOMEDIUM;
 	iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_SWITCH_ATTRIBUTES,
 				sizeof(struct qeth_ipacmd_setadpparms_hdr));
+	if (!iob)
+		return -ENOMEM;
 	return qeth_send_ipa_cmd(card, iob,
 				qeth_query_switch_attributes_cb, sw_info);
 }
@@ -3146,6 +3199,8 @@
 
 	QETH_DBF_TEXT(SETUP, 2, "qdiagass");
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SET_DIAG_ASS, 0);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.diagass.subcmd_len = 16;
 	cmd->data.diagass.subcmd = QETH_DIAGS_CMD_QUERY;
@@ -3197,6 +3252,8 @@
 
 	QETH_DBF_TEXT(SETUP, 2, "diagtrap");
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SET_DIAG_ASS, 0);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.diagass.subcmd_len = 80;
 	cmd->data.diagass.subcmd = QETH_DIAGS_CMD_TRAP;
@@ -4162,6 +4219,8 @@
 
 	iob = qeth_get_adapter_cmd(card, IPA_SETADP_SET_PROMISC_MODE,
 			sizeof(struct qeth_ipacmd_setadpparms));
+	if (!iob)
+		return;
 	cmd = (struct qeth_ipa_cmd *)(iob->data + IPA_PDU_HEADER_SIZE);
 	cmd->data.setadapterparms.data.mode = mode;
 	qeth_send_ipa_cmd(card, iob, qeth_setadp_promisc_mode_cb, NULL);
@@ -4232,6 +4291,8 @@
 
 	iob = qeth_get_adapter_cmd(card, IPA_SETADP_ALTER_MAC_ADDRESS,
 				   sizeof(struct qeth_ipacmd_setadpparms));
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.setadapterparms.data.change_addr.cmd = CHANGE_ADDR_READ_MAC;
 	cmd->data.setadapterparms.data.change_addr.addr_size = OSA_ADDR_LEN;
@@ -4345,6 +4406,8 @@
 	iob = qeth_get_adapter_cmd(card, IPA_SETADP_SET_ACCESS_CONTROL,
 				   sizeof(struct qeth_ipacmd_setadpparms_hdr) +
 				   sizeof(struct qeth_set_access_ctrl));
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl;
 	access_ctrl_req->subcmd_code = isolation;
@@ -4588,6 +4651,10 @@
 
 	iob = qeth_get_adapter_cmd(card, IPA_SETADP_SET_SNMP_CONTROL,
 				   QETH_SNMP_SETADP_CMDLENGTH + req_len);
+	if (!iob) {
+		rc = -ENOMEM;
+		goto out;
+	}
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	memcpy(&cmd->data.setadapterparms.data.snmp, &ureq->cmd, req_len);
 	rc = qeth_send_ipa_snmp_cmd(card, iob, QETH_SETADP_BASE_LEN + req_len,
@@ -4599,7 +4666,7 @@
 		if (copy_to_user(udata, qinfo.udata, qinfo.udata_len))
 			rc = -EFAULT;
 	}
-
+out:
 	kfree(ureq);
 	kfree(qinfo.udata);
 	return rc;
@@ -4670,6 +4737,10 @@
 	iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_OAT,
 				   sizeof(struct qeth_ipacmd_setadpparms_hdr) +
 				   sizeof(struct qeth_query_oat));
+	if (!iob) {
+		rc = -ENOMEM;
+		goto out_free;
+	}
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	oat_req = &cmd->data.setadapterparms.data.query_oat;
 	oat_req->subcmd_code = oat_data.command;
@@ -4735,6 +4806,8 @@
 		return -EOPNOTSUPP;
 	iob = qeth_get_adapter_cmd(card, IPA_SETADP_QUERY_CARD_INFO,
 		sizeof(struct qeth_ipacmd_setadpparms_hdr));
+	if (!iob)
+		return -ENOMEM;
 	return qeth_send_ipa_cmd(card, iob, qeth_query_card_info_cb,
 					(void *)carrier_info);
 }
@@ -5060,11 +5133,23 @@
 	card->options.adp.supported_funcs = 0;
 	card->options.sbp.supported_funcs = 0;
 	card->info.diagass_support = 0;
-	qeth_query_ipassists(card, QETH_PROT_IPV4);
-	if (qeth_is_supported(card, IPA_SETADAPTERPARMS))
-		qeth_query_setadapterparms(card);
-	if (qeth_adp_supported(card, IPA_SETADP_SET_DIAG_ASSIST))
-		qeth_query_setdiagass(card);
+	rc = qeth_query_ipassists(card, QETH_PROT_IPV4);
+	if (rc == -ENOMEM)
+		goto out;
+	if (qeth_is_supported(card, IPA_SETADAPTERPARMS)) {
+		rc = qeth_query_setadapterparms(card);
+		if (rc < 0) {
+			QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc);
+			goto out;
+		}
+	}
+	if (qeth_adp_supported(card, IPA_SETADP_SET_DIAG_ASSIST)) {
+		rc = qeth_query_setdiagass(card);
+		if (rc < 0) {
+			QETH_DBF_TEXT_(SETUP, 2, "7err%d", rc);
+			goto out;
+		}
+	}
 	return 0;
 out:
 	dev_warn(&card->gdev->dev, "The qeth device driver failed to recover "
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index d02cd1a..ce87ae7 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -27,10 +27,7 @@
 static int qeth_l2_stop(struct net_device *);
 static int qeth_l2_send_delmac(struct qeth_card *, __u8 *);
 static int qeth_l2_send_setdelmac(struct qeth_card *, __u8 *,
-			   enum qeth_ipa_cmds,
-			   int (*reply_cb) (struct qeth_card *,
-					    struct qeth_reply*,
-					    unsigned long));
+			   enum qeth_ipa_cmds);
 static void qeth_l2_set_multicast_list(struct net_device *);
 static int qeth_l2_recover(void *);
 static void qeth_bridgeport_query_support(struct qeth_card *card);
@@ -130,56 +127,71 @@
 	return ndev;
 }
 
-static int qeth_l2_send_setgroupmac_cb(struct qeth_card *card,
-				struct qeth_reply *reply,
-				unsigned long data)
+static int qeth_setdel_makerc(struct qeth_card *card, int retcode)
 {
-	struct qeth_ipa_cmd *cmd;
-	__u8 *mac;
+	int rc;
 
-	QETH_CARD_TEXT(card, 2, "L2Sgmacb");
-	cmd = (struct qeth_ipa_cmd *) data;
-	mac = &cmd->data.setdelmac.mac[0];
-	/* MAC already registered, needed in couple/uncouple case */
-	if (cmd->hdr.return_code ==  IPA_RC_L2_DUP_MAC) {
-		QETH_DBF_MESSAGE(2, "Group MAC %pM already existing on %s \n",
-			  mac, QETH_CARD_IFNAME(card));
-		cmd->hdr.return_code = 0;
+	if (retcode)
+		QETH_CARD_TEXT_(card, 2, "err%04x", retcode);
+	switch (retcode) {
+	case IPA_RC_SUCCESS:
+		rc = 0;
+		break;
+	case IPA_RC_L2_UNSUPPORTED_CMD:
+		rc = -ENOSYS;
+		break;
+	case IPA_RC_L2_ADDR_TABLE_FULL:
+		rc = -ENOSPC;
+		break;
+	case IPA_RC_L2_DUP_MAC:
+	case IPA_RC_L2_DUP_LAYER3_MAC:
+		rc = -EEXIST;
+		break;
+	case IPA_RC_L2_MAC_NOT_AUTH_BY_HYP:
+	case IPA_RC_L2_MAC_NOT_AUTH_BY_ADP:
+		rc = -EPERM;
+		break;
+	case IPA_RC_L2_MAC_NOT_FOUND:
+		rc = -ENOENT;
+		break;
+	case -ENOMEM:
+		rc = -ENOMEM;
+		break;
+	default:
+		rc = -EIO;
+		break;
 	}
-	if (cmd->hdr.return_code)
-		QETH_DBF_MESSAGE(2, "Could not set group MAC %pM on %s: %x\n",
-			  mac, QETH_CARD_IFNAME(card), cmd->hdr.return_code);
-	return 0;
+	return rc;
 }
 
 static int qeth_l2_send_setgroupmac(struct qeth_card *card, __u8 *mac)
 {
+	int rc;
+
 	QETH_CARD_TEXT(card, 2, "L2Sgmac");
-	return qeth_l2_send_setdelmac(card, mac, IPA_CMD_SETGMAC,
-					  qeth_l2_send_setgroupmac_cb);
-}
-
-static int qeth_l2_send_delgroupmac_cb(struct qeth_card *card,
-				struct qeth_reply *reply,
-				unsigned long data)
-{
-	struct qeth_ipa_cmd *cmd;
-	__u8 *mac;
-
-	QETH_CARD_TEXT(card, 2, "L2Dgmacb");
-	cmd = (struct qeth_ipa_cmd *) data;
-	mac = &cmd->data.setdelmac.mac[0];
-	if (cmd->hdr.return_code)
-		QETH_DBF_MESSAGE(2, "Could not delete group MAC %pM on %s: %x\n",
-			  mac, QETH_CARD_IFNAME(card), cmd->hdr.return_code);
-	return 0;
+	rc = qeth_setdel_makerc(card, qeth_l2_send_setdelmac(card, mac,
+					IPA_CMD_SETGMAC));
+	if (rc == -EEXIST)
+		QETH_DBF_MESSAGE(2, "Group MAC %pM already existing on %s\n",
+			mac, QETH_CARD_IFNAME(card));
+	else if (rc)
+		QETH_DBF_MESSAGE(2, "Could not set group MAC %pM on %s: %d\n",
+			mac, QETH_CARD_IFNAME(card), rc);
+	return rc;
 }
 
 static int qeth_l2_send_delgroupmac(struct qeth_card *card, __u8 *mac)
 {
+	int rc;
+
 	QETH_CARD_TEXT(card, 2, "L2Dgmac");
-	return qeth_l2_send_setdelmac(card, mac, IPA_CMD_DELGMAC,
-					  qeth_l2_send_delgroupmac_cb);
+	rc = qeth_setdel_makerc(card, qeth_l2_send_setdelmac(card, mac,
+					IPA_CMD_DELGMAC));
+	if (rc)
+		QETH_DBF_MESSAGE(2,
+			"Could not delete group MAC %pM on %s: %d\n",
+			mac, QETH_CARD_IFNAME(card), rc);
+	return rc;
 }
 
 static void qeth_l2_add_mc(struct qeth_card *card, __u8 *mac, int vmac)
@@ -197,10 +209,11 @@
 	mc->is_vmac = vmac;
 
 	if (vmac) {
-		rc = qeth_l2_send_setdelmac(card, mac, IPA_CMD_SETVMAC,
-					NULL);
+		rc = qeth_setdel_makerc(card,
+			qeth_l2_send_setdelmac(card, mac, IPA_CMD_SETVMAC));
 	} else {
-		rc = qeth_l2_send_setgroupmac(card, mac);
+		rc = qeth_setdel_makerc(card,
+			qeth_l2_send_setgroupmac(card, mac));
 	}
 
 	if (!rc)
@@ -218,7 +231,7 @@
 		if (del) {
 			if (mc->is_vmac)
 				qeth_l2_send_setdelmac(card, mc->mc_addr,
-					IPA_CMD_DELVMAC, NULL);
+					IPA_CMD_DELVMAC);
 			else
 				qeth_l2_send_delgroupmac(card, mc->mc_addr);
 		}
@@ -291,6 +304,8 @@
 
 	QETH_CARD_TEXT_(card, 4, "L2sdv%x", ipacmd);
 	iob = qeth_get_ipacmd_buffer(card, ipacmd, QETH_PROT_IPV4);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.setdelvlan.vlan_id = i;
 	return qeth_send_ipa_cmd(card, iob,
@@ -313,6 +328,7 @@
 {
 	struct qeth_card *card = dev->ml_priv;
 	struct qeth_vlan_vid *id;
+	int rc;
 
 	QETH_CARD_TEXT_(card, 4, "aid:%d", vid);
 	if (!vid)
@@ -328,7 +344,11 @@
 	id = kmalloc(sizeof(struct qeth_vlan_vid), GFP_ATOMIC);
 	if (id) {
 		id->vid = vid;
-		qeth_l2_send_setdelvlan(card, vid, IPA_CMD_SETVLAN);
+		rc = qeth_l2_send_setdelvlan(card, vid, IPA_CMD_SETVLAN);
+		if (rc) {
+			kfree(id);
+			return rc;
+		}
 		spin_lock_bh(&card->vlanlock);
 		list_add_tail(&id->list, &card->vid_list);
 		spin_unlock_bh(&card->vlanlock);
@@ -343,6 +363,7 @@
 {
 	struct qeth_vlan_vid *id, *tmpid = NULL;
 	struct qeth_card *card = dev->ml_priv;
+	int rc = 0;
 
 	QETH_CARD_TEXT_(card, 4, "kid:%d", vid);
 	if (card->info.type == QETH_CARD_TYPE_OSM) {
@@ -363,11 +384,11 @@
 	}
 	spin_unlock_bh(&card->vlanlock);
 	if (tmpid) {
-		qeth_l2_send_setdelvlan(card, vid, IPA_CMD_DELVLAN);
+		rc = qeth_l2_send_setdelvlan(card, vid, IPA_CMD_DELVLAN);
 		kfree(tmpid);
 	}
 	qeth_l2_set_multicast_list(card->dev);
-	return 0;
+	return rc;
 }
 
 static int qeth_l2_stop_card(struct qeth_card *card, int recovery_mode)
@@ -539,91 +560,62 @@
 }
 
 static int qeth_l2_send_setdelmac(struct qeth_card *card, __u8 *mac,
-			   enum qeth_ipa_cmds ipacmd,
-			   int (*reply_cb) (struct qeth_card *,
-					    struct qeth_reply*,
-					    unsigned long))
+			   enum qeth_ipa_cmds ipacmd)
 {
 	struct qeth_ipa_cmd *cmd;
 	struct qeth_cmd_buffer *iob;
 
 	QETH_CARD_TEXT(card, 2, "L2sdmac");
 	iob = qeth_get_ipacmd_buffer(card, ipacmd, QETH_PROT_IPV4);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.setdelmac.mac_length = OSA_ADDR_LEN;
 	memcpy(&cmd->data.setdelmac.mac, mac, OSA_ADDR_LEN);
-	return qeth_send_ipa_cmd(card, iob, reply_cb, NULL);
-}
-
-static int qeth_l2_send_setmac_cb(struct qeth_card *card,
-			   struct qeth_reply *reply,
-			   unsigned long data)
-{
-	struct qeth_ipa_cmd *cmd;
-
-	QETH_CARD_TEXT(card, 2, "L2Smaccb");
-	cmd = (struct qeth_ipa_cmd *) data;
-	if (cmd->hdr.return_code) {
-		QETH_CARD_TEXT_(card, 2, "L2er%x", cmd->hdr.return_code);
-		card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
-		switch (cmd->hdr.return_code) {
-		case IPA_RC_L2_DUP_MAC:
-		case IPA_RC_L2_DUP_LAYER3_MAC:
-			dev_warn(&card->gdev->dev,
-				"MAC address %pM already exists\n",
-				cmd->data.setdelmac.mac);
-			break;
-		case IPA_RC_L2_MAC_NOT_AUTH_BY_HYP:
-		case IPA_RC_L2_MAC_NOT_AUTH_BY_ADP:
-			dev_warn(&card->gdev->dev,
-				"MAC address %pM is not authorized\n",
-				cmd->data.setdelmac.mac);
-			break;
-		default:
-			break;
-		}
-	} else {
-		card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
-		memcpy(card->dev->dev_addr, cmd->data.setdelmac.mac,
-		       OSA_ADDR_LEN);
-		dev_info(&card->gdev->dev,
-			"MAC address %pM successfully registered on device %s\n",
-			card->dev->dev_addr, card->dev->name);
-	}
-	return 0;
+	return qeth_send_ipa_cmd(card, iob, NULL, NULL);
 }
 
 static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac)
 {
+	int rc;
+
 	QETH_CARD_TEXT(card, 2, "L2Setmac");
-	return qeth_l2_send_setdelmac(card, mac, IPA_CMD_SETVMAC,
-					  qeth_l2_send_setmac_cb);
-}
-
-static int qeth_l2_send_delmac_cb(struct qeth_card *card,
-			   struct qeth_reply *reply,
-			   unsigned long data)
-{
-	struct qeth_ipa_cmd *cmd;
-
-	QETH_CARD_TEXT(card, 2, "L2Dmaccb");
-	cmd = (struct qeth_ipa_cmd *) data;
-	if (cmd->hdr.return_code) {
-		QETH_CARD_TEXT_(card, 2, "err%d", cmd->hdr.return_code);
-		return 0;
+	rc = qeth_setdel_makerc(card, qeth_l2_send_setdelmac(card, mac,
+					IPA_CMD_SETVMAC));
+	if (rc == 0) {
+		card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
+		memcpy(card->dev->dev_addr, mac, OSA_ADDR_LEN);
+		dev_info(&card->gdev->dev,
+			"MAC address %pM successfully registered on device %s\n",
+			card->dev->dev_addr, card->dev->name);
+	} else {
+		card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
+		switch (rc) {
+		case -EEXIST:
+			dev_warn(&card->gdev->dev,
+				"MAC address %pM already exists\n", mac);
+			break;
+		case -EPERM:
+			dev_warn(&card->gdev->dev,
+				"MAC address %pM is not authorized\n", mac);
+			break;
+		}
 	}
-	card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
-
-	return 0;
+	return rc;
 }
 
 static int qeth_l2_send_delmac(struct qeth_card *card, __u8 *mac)
 {
+	int rc;
+
 	QETH_CARD_TEXT(card, 2, "L2Delmac");
 	if (!(card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
 		return 0;
-	return qeth_l2_send_setdelmac(card, mac, IPA_CMD_DELVMAC,
-					  qeth_l2_send_delmac_cb);
+	rc = qeth_setdel_makerc(card, qeth_l2_send_setdelmac(card, mac,
+					IPA_CMD_DELVMAC));
+	if (rc == 0)
+		card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED;
+	return rc;
 }
 
 static int qeth_l2_request_initial_mac(struct qeth_card *card)
@@ -651,7 +643,7 @@
 		if (rc) {
 			QETH_DBF_MESSAGE(2, "couldn't get MAC address on "
 				"device %s: x%x\n", CARD_BUS_ID(card), rc);
-			QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc);
+			QETH_DBF_TEXT_(SETUP, 2, "1err%04x", rc);
 			return rc;
 		}
 		QETH_DBF_HEX(SETUP, 2, card->dev->dev_addr, OSA_ADDR_LEN);
@@ -687,7 +679,7 @@
 		return -ERESTARTSYS;
 	}
 	rc = qeth_l2_send_delmac(card, &card->dev->dev_addr[0]);
-	if (!rc || (rc == IPA_RC_L2_MAC_NOT_FOUND))
+	if (!rc || (rc == -ENOENT))
 		rc = qeth_l2_send_setmac(card, addr->sa_data);
 	return rc ? -EINVAL : 0;
 }
@@ -996,7 +988,7 @@
 	recover_flag = card->state;
 	rc = qeth_core_hardsetup_card(card);
 	if (rc) {
-		QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc);
+		QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc);
 		rc = -ENODEV;
 		goto out_remove;
 	}
@@ -1730,6 +1722,8 @@
 
 	QETH_CARD_TEXT(card, 2, "brqsuppo");
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETBRIDGEPORT, 0);
+	if (!iob)
+		return;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.sbp.hdr.cmdlength =
 		sizeof(struct qeth_ipacmd_sbp_hdr) +
@@ -1805,6 +1799,8 @@
 	if (!(card->options.sbp.supported_funcs & IPA_SBP_QUERY_BRIDGE_PORTS))
 		return -EOPNOTSUPP;
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETBRIDGEPORT, 0);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.sbp.hdr.cmdlength =
 		sizeof(struct qeth_ipacmd_sbp_hdr);
@@ -1817,9 +1813,7 @@
 	if (rc)
 		return rc;
 	rc = qeth_bridgeport_makerc(card, &cbctl, IPA_SBP_QUERY_BRIDGE_PORTS);
-	if (rc)
-		return rc;
-	return 0;
+	return rc;
 }
 EXPORT_SYMBOL_GPL(qeth_bridgeport_query_ports);
 
@@ -1873,6 +1867,8 @@
 	if (!(card->options.sbp.supported_funcs & setcmd))
 		return -EOPNOTSUPP;
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETBRIDGEPORT, 0);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.sbp.hdr.cmdlength = cmdlength;
 	cmd->data.sbp.hdr.command_code = setcmd;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 625227ad..e2a0ee8 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -549,6 +549,8 @@
 	QETH_CARD_TEXT(card, 4, "setdelmc");
 
 	iob = qeth_get_ipacmd_buffer(card, ipacmd, addr->proto);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	memcpy(&cmd->data.setdelipm.mac, addr->mac, OSA_ADDR_LEN);
 	if (addr->proto == QETH_PROT_IPV6)
@@ -588,6 +590,8 @@
 	QETH_CARD_TEXT_(card, 4, "flags%02X", flags);
 
 	iob = qeth_get_ipacmd_buffer(card, ipacmd, addr->proto);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	if (addr->proto == QETH_PROT_IPV6) {
 		memcpy(cmd->data.setdelip6.ip_addr, &addr->u.a6.addr,
@@ -616,6 +620,8 @@
 
 	QETH_CARD_TEXT(card, 4, "setroutg");
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETRTG, prot);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.setrtg.type = (type);
 	rc = qeth_send_ipa_cmd(card, iob, NULL, NULL);
@@ -1049,12 +1055,14 @@
 	QETH_CARD_TEXT(card, 4, "getasscm");
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETASSPARMS, prot);
 
-	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
-	cmd->data.setassparms.hdr.assist_no = ipa_func;
-	cmd->data.setassparms.hdr.length = 8 + len;
-	cmd->data.setassparms.hdr.command_code = cmd_code;
-	cmd->data.setassparms.hdr.return_code = 0;
-	cmd->data.setassparms.hdr.seq_no = 0;
+	if (iob) {
+		cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
+		cmd->data.setassparms.hdr.assist_no = ipa_func;
+		cmd->data.setassparms.hdr.length = 8 + len;
+		cmd->data.setassparms.hdr.command_code = cmd_code;
+		cmd->data.setassparms.hdr.return_code = 0;
+		cmd->data.setassparms.hdr.seq_no = 0;
+	}
 
 	return iob;
 }
@@ -1090,6 +1098,8 @@
 	QETH_CARD_TEXT(card, 4, "simassp6");
 	iob = qeth_l3_get_setassparms_cmd(card, ipa_func, cmd_code,
 				       0, QETH_PROT_IPV6);
+	if (!iob)
+		return -ENOMEM;
 	rc = qeth_l3_send_setassparms(card, iob, 0, 0,
 				   qeth_l3_default_setassparms_cb, NULL);
 	return rc;
@@ -1108,6 +1118,8 @@
 		length = sizeof(__u32);
 	iob = qeth_l3_get_setassparms_cmd(card, ipa_func, cmd_code,
 				       length, QETH_PROT_IPV4);
+	if (!iob)
+		return -ENOMEM;
 	rc = qeth_l3_send_setassparms(card, iob, length, data,
 				   qeth_l3_default_setassparms_cb, NULL);
 	return rc;
@@ -1494,6 +1506,8 @@
 
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_CREATE_ADDR,
 				     QETH_PROT_IPV6);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	*((__u16 *) &cmd->data.create_destroy_addr.unique_id[6]) =
 			card->info.unique_id;
@@ -1537,6 +1551,8 @@
 
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_CREATE_ADDR,
 				     QETH_PROT_IPV6);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	*((__u16 *) &cmd->data.create_destroy_addr.unique_id[6]) =
 			card->info.unique_id;
@@ -1611,6 +1627,8 @@
 	QETH_DBF_TEXT(SETUP, 2, "diagtrac");
 
 	iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SET_DIAG_ASS, 0);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.diagass.subcmd_len = 16;
 	cmd->data.diagass.subcmd = QETH_DIAGS_CMD_TRACE;
@@ -2442,6 +2460,8 @@
 			IPA_CMD_ASS_ARP_QUERY_INFO,
 			sizeof(struct qeth_arp_query_data) - sizeof(char),
 			prot);
+	if (!iob)
+		return -ENOMEM;
 	cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
 	cmd->data.setassparms.data.query_arp.request_bits = 0x000F;
 	cmd->data.setassparms.data.query_arp.reply_bits = 0;
@@ -2535,6 +2555,8 @@
 				       IPA_CMD_ASS_ARP_ADD_ENTRY,
 				       sizeof(struct qeth_arp_cache_entry),
 				       QETH_PROT_IPV4);
+	if (!iob)
+		return -ENOMEM;
 	rc = qeth_l3_send_setassparms(card, iob,
 				   sizeof(struct qeth_arp_cache_entry),
 				   (unsigned long) entry,
@@ -2574,6 +2596,8 @@
 				       IPA_CMD_ASS_ARP_REMOVE_ENTRY,
 				       12,
 				       QETH_PROT_IPV4);
+	if (!iob)
+		return -ENOMEM;
 	rc = qeth_l3_send_setassparms(card, iob,
 				   12, (unsigned long)buf,
 				   qeth_l3_default_setassparms_cb, NULL);
@@ -3262,6 +3286,8 @@
 
 static int qeth_l3_setup_netdev(struct qeth_card *card)
 {
+	int rc;
+
 	if (card->info.type == QETH_CARD_TYPE_OSD ||
 	    card->info.type == QETH_CARD_TYPE_OSX) {
 		if ((card->info.link_type == QETH_LINK_TYPE_LANE_TR) ||
@@ -3293,7 +3319,9 @@
 			return -ENODEV;
 		card->dev->flags |= IFF_NOARP;
 		card->dev->netdev_ops = &qeth_l3_netdev_ops;
-		qeth_l3_iqd_read_initial_mac(card);
+		rc = qeth_l3_iqd_read_initial_mac(card);
+		if (rc)
+			return rc;
 		if (card->options.hsuid[0])
 			memcpy(card->dev->perm_addr, card->options.hsuid, 9);
 	} else
@@ -3360,7 +3388,7 @@
 	recover_flag = card->state;
 	rc = qeth_core_hardsetup_card(card);
 	if (rc) {
-		QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc);
+		QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc);
 		rc = -ENODEV;
 		goto out_remove;
 	}
@@ -3401,7 +3429,7 @@
 contin:
 	rc = qeth_l3_setadapter_parms(card);
 	if (rc)
-		QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc);
+		QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc);
 	if (!card->options.sniffer) {
 		rc = qeth_l3_start_ipassists(card);
 		if (rc) {
@@ -3410,10 +3438,10 @@
 		}
 		rc = qeth_l3_setrouting_v4(card);
 		if (rc)
-			QETH_DBF_TEXT_(SETUP, 2, "4err%d", rc);
+			QETH_DBF_TEXT_(SETUP, 2, "4err%04x", rc);
 		rc = qeth_l3_setrouting_v6(card);
 		if (rc)
-			QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc);
+			QETH_DBF_TEXT_(SETUP, 2, "5err%04x", rc);
 	}
 	netif_tx_disable(card->dev);
 
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index e028854..9b38299 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -986,9 +986,9 @@
 		return -ENXIO;
 	if (!get_device(&sdev->sdev_gendev))
 		return -ENXIO;
-	/* We can fail this if we're doing SCSI operations
+	/* We can fail try_module_get if we're doing SCSI operations
 	 * from module exit (like cache flush) */
-	try_module_get(sdev->host->hostt->module);
+	__module_get(sdev->host->hostt->module);
 
 	return 0;
 }
@@ -1004,14 +1004,7 @@
  */
 void scsi_device_put(struct scsi_device *sdev)
 {
-#ifdef CONFIG_MODULE_UNLOAD
-	struct module *module = sdev->host->hostt->module;
-
-	/* The module refcount will be zero if scsi_device_get()
-	 * was called from a module removal routine */
-	if (module && module_refcount(module) != 0)
-		module_put(module);
-#endif
+	module_put(sdev->host->hostt->module);
 	put_device(&sdev->sdev_gendev);
 }
 EXPORT_SYMBOL(scsi_device_put);
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 7281316..a67d37c 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -271,7 +271,6 @@
 	iounmap(clk_reg);
 
 	dws->num_cs = 16;
-	dws->fifo_len = 40;	/* FIFO has 40 words buffer */
 
 #ifdef CONFIG_SPI_DW_MID_DMA
 	dws->dma_priv = kzalloc(sizeof(struct mid_dma), GFP_KERNEL);
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index d0d5542..8edcd1b 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -621,13 +621,13 @@
 	if (!dws->fifo_len) {
 		u32 fifo;
 
-		for (fifo = 2; fifo <= 257; fifo++) {
+		for (fifo = 2; fifo <= 256; fifo++) {
 			dw_writew(dws, DW_SPI_TXFLTR, fifo);
 			if (fifo != dw_readw(dws, DW_SPI_TXFLTR))
 				break;
 		}
 
-		dws->fifo_len = (fifo == 257) ? 0 : fifo;
+		dws->fifo_len = (fifo == 2) ? 0 : fifo - 1;
 		dw_writew(dws, DW_SPI_TXFLTR, 0);
 	}
 }
@@ -673,7 +673,7 @@
 	if (dws->dma_ops && dws->dma_ops->dma_init) {
 		ret = dws->dma_ops->dma_init(dws);
 		if (ret) {
-			dev_warn(&master->dev, "DMA init failed\n");
+			dev_warn(dev, "DMA init failed\n");
 			dws->dma_inited = 0;
 		}
 	}
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 05c623c..23822e7 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -546,8 +546,8 @@
 			cs_deassert(drv_data);
 	}
 
-	spi_finalize_current_message(drv_data->master);
 	drv_data->cur_chip = NULL;
+	spi_finalize_current_message(drv_data->master);
 }
 
 static void reset_sccr1(struct driver_data *drv_data)
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 96a5fc0..3ab7a21 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -82,7 +82,7 @@
 #define MDR1_SYNCMD_LR	 0x30000000 /*   L/R mode */
 #define MDR1_SYNCAC_SHIFT	 25 /* Sync Polarity (1 = Active-low) */
 #define MDR1_BITLSB_SHIFT	 24 /* MSB/LSB First (1 = LSB first) */
-#define MDR1_FLD_MASK	 0x000000c0 /* Frame Sync Signal Interval (0-3) */
+#define MDR1_FLD_MASK	 0x0000000c /* Frame Sync Signal Interval (0-3) */
 #define MDR1_FLD_SHIFT		  2
 #define MDR1_XXSTP	 0x00000001 /* Transmission/Reception Stop on FIFO */
 /* TMDR1 */
diff --git a/drivers/staging/lustre/lustre/llite/vvp_io.c b/drivers/staging/lustre/lustre/llite/vvp_io.c
index 930f601..65d610a 100644
--- a/drivers/staging/lustre/lustre/llite/vvp_io.c
+++ b/drivers/staging/lustre/lustre/llite/vvp_io.c
@@ -632,7 +632,7 @@
 		return 0;
 	}
 
-	if (cfio->fault.ft_flags & VM_FAULT_SIGBUS) {
+	if (cfio->fault.ft_flags & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
 		CDEBUG(D_PAGE, "got addr %p - SIGBUS\n", vmf->virtual_address);
 		return -EFAULT;
 	}
diff --git a/drivers/staging/nvec/nvec.c b/drivers/staging/nvec/nvec.c
index 093535c..120b70d 100644
--- a/drivers/staging/nvec/nvec.c
+++ b/drivers/staging/nvec/nvec.c
@@ -85,23 +85,20 @@
 static const struct mfd_cell nvec_devices[] = {
 	{
 		.name = "nvec-kbd",
-		.id = 1,
 	},
 	{
 		.name = "nvec-mouse",
-		.id = 1,
+	},
+	{
+		.name = "nvec-power",
+		.id = 0,
 	},
 	{
 		.name = "nvec-power",
 		.id = 1,
 	},
 	{
-		.name = "nvec-power",
-		.id = 2,
-	},
-	{
 		.name = "nvec-paz00",
-		.id = 1,
 	},
 };
 
@@ -891,7 +888,7 @@
 		nvec_msg_free(nvec, msg);
 	}
 
-	ret = mfd_add_devices(nvec->dev, -1, nvec_devices,
+	ret = mfd_add_devices(nvec->dev, 0, nvec_devices,
 			      ARRAY_SIZE(nvec_devices), NULL, 0, NULL);
 	if (ret)
 		dev_err(nvec->dev, "error adding subdevices\n");
diff --git a/drivers/usb/core/otg_whitelist.h b/drivers/usb/core/otg_whitelist.h
index de0c9c9..a6315ab 100644
--- a/drivers/usb/core/otg_whitelist.h
+++ b/drivers/usb/core/otg_whitelist.h
@@ -55,6 +55,11 @@
 	     le16_to_cpu(dev->descriptor.idProduct) == 0xbadd))
 		return 0;
 
+	/* OTG PET device is always targeted (see OTG 2.0 ECN 6.4.2) */
+	if ((le16_to_cpu(dev->descriptor.idVendor) == 0x1a0a &&
+	     le16_to_cpu(dev->descriptor.idProduct) == 0x0200))
+		return 1;
+
 	/* NOTE: can't use usb_match_id() since interface caches
 	 * aren't set up yet. this is cut/paste from that code.
 	 */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 0ffb4ed..41e510a 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -179,6 +179,10 @@
 	{ USB_DEVICE(0x0b05, 0x17e0), .driver_info =
 			USB_QUIRK_IGNORE_REMOTE_WAKEUP },
 
+	/* Protocol and OTG Electrical Test Device */
+	{ USB_DEVICE(0x1a0a, 0x0200), .driver_info =
+			USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
+
 	{ }  /* terminating entry must be last */
 };
 
diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c
index ad43c5b..02e3e2d 100644
--- a/drivers/usb/dwc2/core_intr.c
+++ b/drivers/usb/dwc2/core_intr.c
@@ -476,13 +476,13 @@
 	u32 gintsts;
 	irqreturn_t retval = IRQ_NONE;
 
+	spin_lock(&hsotg->lock);
+
 	if (!dwc2_is_controller_alive(hsotg)) {
 		dev_warn(hsotg->dev, "Controller is dead\n");
 		goto out;
 	}
 
-	spin_lock(&hsotg->lock);
-
 	gintsts = dwc2_read_common_intr(hsotg);
 	if (gintsts & ~GINTSTS_PRTINT)
 		retval = IRQ_HANDLED;
@@ -515,8 +515,8 @@
 		}
 	}
 
-	spin_unlock(&hsotg->lock);
 out:
+	spin_unlock(&hsotg->lock);
 	return retval;
 }
 EXPORT_SYMBOL_GPL(dwc2_handle_common_intr);
diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c
index ccfdfb2..2f9735b 100644
--- a/drivers/usb/phy/phy.c
+++ b/drivers/usb/phy/phy.c
@@ -34,7 +34,7 @@
 		return phy;
 	}
 
-	return ERR_PTR(-EPROBE_DEFER);
+	return ERR_PTR(-ENODEV);
 }
 
 static struct usb_phy *__usb_find_phy_dev(struct device *dev,
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 11c7a96..d684b4b 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -507,7 +507,7 @@
 UNUSUAL_DEV(  0x04e6, 0x000f, 0x0000, 0x9999,
 		"SCM Microsystems",
 		"eUSB SCSI Adapter (Bus Powered)",
-		USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+		USB_SC_SCSI, USB_PR_BULK, usb_stor_euscsi_init,
 		US_FL_SCM_MULT_TARG ),
 
 UNUSUAL_DEV(  0x04e6, 0x0101, 0x0200, 0x0200,
@@ -1995,6 +1995,13 @@
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ),
 
+/* Reported by Dmitry Nezhevenko <dion@dion.org.ua> */
+UNUSUAL_DEV(  0x152d, 0x2566, 0x0114, 0x0114,
+		"JMicron",
+		"USB to ATA/ATAPI Bridge",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_BROKEN_FUA ),
+
 /* Entrega Technologies U1-SC25 (later Xircom PortGear PGSCSI)
  * and Mac USB Dock USB-SCSI */
 UNUSUAL_DEV(  0x1645, 0x0007, 0x0100, 0x0133,
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 6df4357..dbc00e5 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -140,3 +140,10 @@
 		"External HDD",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_UAS),
+
+/* Reported-by: Richard Henderson <rth@redhat.com> */
+UNUSUAL_DEV(0x4971, 0x8017, 0x0000, 0x9999,
+		"SimpleTech",
+		"External HDD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_REPORT_OPCODES),
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 2f0fbc3..e427cb7e 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3065,6 +3065,8 @@
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
+	ppath->search_commit_root = 1;
+	ppath->skip_locking = 1;
 	/*
 	 * trigger the readahead for extent tree csum tree and wait for
 	 * completion. During readahead, the scrub is officially paused
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index c8b148b..3e193cb 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -667,7 +667,7 @@
 
 static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 			     s64 change, struct gfs2_quota_data *qd,
-			     struct fs_disk_quota *fdq)
+			     struct qc_dqblk *fdq)
 {
 	struct inode *inode = &ip->i_inode;
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
@@ -697,16 +697,16 @@
 	be64_add_cpu(&q.qu_value, change);
 	qd->qd_qb.qb_value = q.qu_value;
 	if (fdq) {
-		if (fdq->d_fieldmask & FS_DQ_BSOFT) {
-			q.qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift);
+		if (fdq->d_fieldmask & QC_SPC_SOFT) {
+			q.qu_warn = cpu_to_be64(fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift);
 			qd->qd_qb.qb_warn = q.qu_warn;
 		}
-		if (fdq->d_fieldmask & FS_DQ_BHARD) {
-			q.qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift);
+		if (fdq->d_fieldmask & QC_SPC_HARD) {
+			q.qu_limit = cpu_to_be64(fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift);
 			qd->qd_qb.qb_limit = q.qu_limit;
 		}
-		if (fdq->d_fieldmask & FS_DQ_BCOUNT) {
-			q.qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift);
+		if (fdq->d_fieldmask & QC_SPACE) {
+			q.qu_value = cpu_to_be64(fdq->d_space >> sdp->sd_sb.sb_bsize_shift);
 			qd->qd_qb.qb_value = q.qu_value;
 		}
 	}
@@ -1497,7 +1497,7 @@
 }
 
 static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid,
-			  struct fs_disk_quota *fdq)
+			  struct qc_dqblk *fdq)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_quota_lvb *qlvb;
@@ -1505,7 +1505,7 @@
 	struct gfs2_holder q_gh;
 	int error;
 
-	memset(fdq, 0, sizeof(struct fs_disk_quota));
+	memset(fdq, 0, sizeof(*fdq));
 
 	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
 		return -ESRCH; /* Crazy XFS error code */
@@ -1522,12 +1522,9 @@
 		goto out;
 
 	qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr;
-	fdq->d_version = FS_DQUOT_VERSION;
-	fdq->d_flags = (qid.type == USRQUOTA) ? FS_USER_QUOTA : FS_GROUP_QUOTA;
-	fdq->d_id = from_kqid_munged(current_user_ns(), qid);
-	fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_fsb2bb_shift;
-	fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_fsb2bb_shift;
-	fdq->d_bcount = be64_to_cpu(qlvb->qb_value) << sdp->sd_fsb2bb_shift;
+	fdq->d_spc_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_sb.sb_bsize_shift;
+	fdq->d_spc_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_sb.sb_bsize_shift;
+	fdq->d_space = be64_to_cpu(qlvb->qb_value) << sdp->sd_sb.sb_bsize_shift;
 
 	gfs2_glock_dq_uninit(&q_gh);
 out:
@@ -1536,10 +1533,10 @@
 }
 
 /* GFS2 only supports a subset of the XFS fields */
-#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD|FS_DQ_BCOUNT)
+#define GFS2_FIELDMASK (QC_SPC_SOFT|QC_SPC_HARD|QC_SPACE)
 
 static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid,
-			  struct fs_disk_quota *fdq)
+			  struct qc_dqblk *fdq)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
@@ -1583,17 +1580,17 @@
 		goto out_i;
 
 	/* If nothing has changed, this is a no-op */
-	if ((fdq->d_fieldmask & FS_DQ_BSOFT) &&
-	    ((fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_warn)))
-		fdq->d_fieldmask ^= FS_DQ_BSOFT;
+	if ((fdq->d_fieldmask & QC_SPC_SOFT) &&
+	    ((fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_warn)))
+		fdq->d_fieldmask ^= QC_SPC_SOFT;
 
-	if ((fdq->d_fieldmask & FS_DQ_BHARD) &&
-	    ((fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_limit)))
-		fdq->d_fieldmask ^= FS_DQ_BHARD;
+	if ((fdq->d_fieldmask & QC_SPC_HARD) &&
+	    ((fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_limit)))
+		fdq->d_fieldmask ^= QC_SPC_HARD;
 
-	if ((fdq->d_fieldmask & FS_DQ_BCOUNT) &&
-	    ((fdq->d_bcount >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_value)))
-		fdq->d_fieldmask ^= FS_DQ_BCOUNT;
+	if ((fdq->d_fieldmask & QC_SPACE) &&
+	    ((fdq->d_space >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_value)))
+		fdq->d_fieldmask ^= QC_SPACE;
 
 	if (fdq->d_fieldmask == 0)
 		goto out_i;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 10bf072..294692f 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -212,6 +212,12 @@
  */
 ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 {
+	struct inode *inode = iocb->ki_filp->f_mapping->host;
+
+	/* we only support swap file calling nfs_direct_IO */
+	if (!IS_SWAPFILE(inode))
+		return 0;
+
 #ifndef CONFIG_NFS_SWAP
 	dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n",
 			iocb->ki_filp, (long long) pos, iter->nr_segs);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 4bffe63..2211f6b 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -352,8 +352,9 @@
 
 	nfs_attr_check_mountpoint(sb, fattr);
 
-	if (((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) &&
-	    !nfs_attr_use_mounted_on_fileid(fattr))
+	if (nfs_attr_use_mounted_on_fileid(fattr))
+		fattr->fileid = fattr->mounted_on_fileid;
+	else if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0)
 		goto out_no_inode;
 	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0)
 		goto out_no_inode;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index efaa31c..b6f34bf 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -31,8 +31,6 @@
 	    (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) &&
 	     ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0)))
 		return 0;
-
-	fattr->fileid = fattr->mounted_on_fileid;
 	return 1;
 }
 
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 953daa4..706ad10 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -639,7 +639,7 @@
 			prev = pos;
 
 			status = nfs_wait_client_init_complete(pos);
-			if (status == 0) {
+			if (pos->cl_cons_state == NFS_CS_SESSION_INITING) {
 				nfs4_schedule_lease_recovery(pos);
 				status = nfs4_wait_clnt_recover(pos);
 			}
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 8f0acef..69df5b2 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2396,30 +2396,25 @@
 }
 
 /* Generic routine for getting common part of quota structure */
-static void do_get_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
+static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 {
 	struct mem_dqblk *dm = &dquot->dq_dqb;
 
 	memset(di, 0, sizeof(*di));
-	di->d_version = FS_DQUOT_VERSION;
-	di->d_flags = dquot->dq_id.type == USRQUOTA ?
-			FS_USER_QUOTA : FS_GROUP_QUOTA;
-	di->d_id = from_kqid_munged(current_user_ns(), dquot->dq_id);
-
 	spin_lock(&dq_data_lock);
-	di->d_blk_hardlimit = stoqb(dm->dqb_bhardlimit);
-	di->d_blk_softlimit = stoqb(dm->dqb_bsoftlimit);
+	di->d_spc_hardlimit = dm->dqb_bhardlimit;
+	di->d_spc_softlimit = dm->dqb_bsoftlimit;
 	di->d_ino_hardlimit = dm->dqb_ihardlimit;
 	di->d_ino_softlimit = dm->dqb_isoftlimit;
-	di->d_bcount = dm->dqb_curspace + dm->dqb_rsvspace;
-	di->d_icount = dm->dqb_curinodes;
-	di->d_btimer = dm->dqb_btime;
-	di->d_itimer = dm->dqb_itime;
+	di->d_space = dm->dqb_curspace + dm->dqb_rsvspace;
+	di->d_ino_count = dm->dqb_curinodes;
+	di->d_spc_timer = dm->dqb_btime;
+	di->d_ino_timer = dm->dqb_itime;
 	spin_unlock(&dq_data_lock);
 }
 
 int dquot_get_dqblk(struct super_block *sb, struct kqid qid,
-		    struct fs_disk_quota *di)
+		    struct qc_dqblk *di)
 {
 	struct dquot *dquot;
 
@@ -2433,70 +2428,70 @@
 }
 EXPORT_SYMBOL(dquot_get_dqblk);
 
-#define VFS_FS_DQ_MASK \
-	(FS_DQ_BCOUNT | FS_DQ_BSOFT | FS_DQ_BHARD | \
-	 FS_DQ_ICOUNT | FS_DQ_ISOFT | FS_DQ_IHARD | \
-	 FS_DQ_BTIMER | FS_DQ_ITIMER)
+#define VFS_QC_MASK \
+	(QC_SPACE | QC_SPC_SOFT | QC_SPC_HARD | \
+	 QC_INO_COUNT | QC_INO_SOFT | QC_INO_HARD | \
+	 QC_SPC_TIMER | QC_INO_TIMER)
 
 /* Generic routine for setting common part of quota structure */
-static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
+static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 {
 	struct mem_dqblk *dm = &dquot->dq_dqb;
 	int check_blim = 0, check_ilim = 0;
 	struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type];
 
-	if (di->d_fieldmask & ~VFS_FS_DQ_MASK)
+	if (di->d_fieldmask & ~VFS_QC_MASK)
 		return -EINVAL;
 
-	if (((di->d_fieldmask & FS_DQ_BSOFT) &&
-	     (di->d_blk_softlimit > dqi->dqi_maxblimit)) ||
-	    ((di->d_fieldmask & FS_DQ_BHARD) &&
-	     (di->d_blk_hardlimit > dqi->dqi_maxblimit)) ||
-	    ((di->d_fieldmask & FS_DQ_ISOFT) &&
+	if (((di->d_fieldmask & QC_SPC_SOFT) &&
+	     stoqb(di->d_spc_softlimit) > dqi->dqi_maxblimit) ||
+	    ((di->d_fieldmask & QC_SPC_HARD) &&
+	     stoqb(di->d_spc_hardlimit) > dqi->dqi_maxblimit) ||
+	    ((di->d_fieldmask & QC_INO_SOFT) &&
 	     (di->d_ino_softlimit > dqi->dqi_maxilimit)) ||
-	    ((di->d_fieldmask & FS_DQ_IHARD) &&
+	    ((di->d_fieldmask & QC_INO_HARD) &&
 	     (di->d_ino_hardlimit > dqi->dqi_maxilimit)))
 		return -ERANGE;
 
 	spin_lock(&dq_data_lock);
-	if (di->d_fieldmask & FS_DQ_BCOUNT) {
-		dm->dqb_curspace = di->d_bcount - dm->dqb_rsvspace;
+	if (di->d_fieldmask & QC_SPACE) {
+		dm->dqb_curspace = di->d_space - dm->dqb_rsvspace;
 		check_blim = 1;
 		set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_BSOFT)
-		dm->dqb_bsoftlimit = qbtos(di->d_blk_softlimit);
-	if (di->d_fieldmask & FS_DQ_BHARD)
-		dm->dqb_bhardlimit = qbtos(di->d_blk_hardlimit);
-	if (di->d_fieldmask & (FS_DQ_BSOFT | FS_DQ_BHARD)) {
+	if (di->d_fieldmask & QC_SPC_SOFT)
+		dm->dqb_bsoftlimit = di->d_spc_softlimit;
+	if (di->d_fieldmask & QC_SPC_HARD)
+		dm->dqb_bhardlimit = di->d_spc_hardlimit;
+	if (di->d_fieldmask & (QC_SPC_SOFT | QC_SPC_HARD)) {
 		check_blim = 1;
 		set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_ICOUNT) {
-		dm->dqb_curinodes = di->d_icount;
+	if (di->d_fieldmask & QC_INO_COUNT) {
+		dm->dqb_curinodes = di->d_ino_count;
 		check_ilim = 1;
 		set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_ISOFT)
+	if (di->d_fieldmask & QC_INO_SOFT)
 		dm->dqb_isoftlimit = di->d_ino_softlimit;
-	if (di->d_fieldmask & FS_DQ_IHARD)
+	if (di->d_fieldmask & QC_INO_HARD)
 		dm->dqb_ihardlimit = di->d_ino_hardlimit;
-	if (di->d_fieldmask & (FS_DQ_ISOFT | FS_DQ_IHARD)) {
+	if (di->d_fieldmask & (QC_INO_SOFT | QC_INO_HARD)) {
 		check_ilim = 1;
 		set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_BTIMER) {
-		dm->dqb_btime = di->d_btimer;
+	if (di->d_fieldmask & QC_SPC_TIMER) {
+		dm->dqb_btime = di->d_spc_timer;
 		check_blim = 1;
 		set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_ITIMER) {
-		dm->dqb_itime = di->d_itimer;
+	if (di->d_fieldmask & QC_INO_TIMER) {
+		dm->dqb_itime = di->d_ino_timer;
 		check_ilim = 1;
 		set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
 	}
@@ -2506,7 +2501,7 @@
 		    dm->dqb_curspace < dm->dqb_bsoftlimit) {
 			dm->dqb_btime = 0;
 			clear_bit(DQ_BLKS_B, &dquot->dq_flags);
-		} else if (!(di->d_fieldmask & FS_DQ_BTIMER))
+		} else if (!(di->d_fieldmask & QC_SPC_TIMER))
 			/* Set grace only if user hasn't provided his own... */
 			dm->dqb_btime = get_seconds() + dqi->dqi_bgrace;
 	}
@@ -2515,7 +2510,7 @@
 		    dm->dqb_curinodes < dm->dqb_isoftlimit) {
 			dm->dqb_itime = 0;
 			clear_bit(DQ_INODES_B, &dquot->dq_flags);
-		} else if (!(di->d_fieldmask & FS_DQ_ITIMER))
+		} else if (!(di->d_fieldmask & QC_INO_TIMER))
 			/* Set grace only if user hasn't provided his own... */
 			dm->dqb_itime = get_seconds() + dqi->dqi_igrace;
 	}
@@ -2531,7 +2526,7 @@
 }
 
 int dquot_set_dqblk(struct super_block *sb, struct kqid qid,
-		  struct fs_disk_quota *di)
+		  struct qc_dqblk *di)
 {
 	struct dquot *dquot;
 	int rc;
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 2aa4151..6f38563 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -118,17 +118,27 @@
 	return sb->s_qcop->set_info(sb, type, &info);
 }
 
-static void copy_to_if_dqblk(struct if_dqblk *dst, struct fs_disk_quota *src)
+static inline qsize_t qbtos(qsize_t blocks)
+{
+	return blocks << QIF_DQBLKSIZE_BITS;
+}
+
+static inline qsize_t stoqb(qsize_t space)
+{
+	return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS;
+}
+
+static void copy_to_if_dqblk(struct if_dqblk *dst, struct qc_dqblk *src)
 {
 	memset(dst, 0, sizeof(*dst));
-	dst->dqb_bhardlimit = src->d_blk_hardlimit;
-	dst->dqb_bsoftlimit = src->d_blk_softlimit;
-	dst->dqb_curspace = src->d_bcount;
+	dst->dqb_bhardlimit = stoqb(src->d_spc_hardlimit);
+	dst->dqb_bsoftlimit = stoqb(src->d_spc_softlimit);
+	dst->dqb_curspace = src->d_space;
 	dst->dqb_ihardlimit = src->d_ino_hardlimit;
 	dst->dqb_isoftlimit = src->d_ino_softlimit;
-	dst->dqb_curinodes = src->d_icount;
-	dst->dqb_btime = src->d_btimer;
-	dst->dqb_itime = src->d_itimer;
+	dst->dqb_curinodes = src->d_ino_count;
+	dst->dqb_btime = src->d_spc_timer;
+	dst->dqb_itime = src->d_ino_timer;
 	dst->dqb_valid = QIF_ALL;
 }
 
@@ -136,7 +146,7 @@
 			  void __user *addr)
 {
 	struct kqid qid;
-	struct fs_disk_quota fdq;
+	struct qc_dqblk fdq;
 	struct if_dqblk idq;
 	int ret;
 
@@ -154,36 +164,36 @@
 	return 0;
 }
 
-static void copy_from_if_dqblk(struct fs_disk_quota *dst, struct if_dqblk *src)
+static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src)
 {
-	dst->d_blk_hardlimit = src->dqb_bhardlimit;
-	dst->d_blk_softlimit  = src->dqb_bsoftlimit;
-	dst->d_bcount = src->dqb_curspace;
+	dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit);
+	dst->d_spc_softlimit = qbtos(src->dqb_bsoftlimit);
+	dst->d_space = src->dqb_curspace;
 	dst->d_ino_hardlimit = src->dqb_ihardlimit;
 	dst->d_ino_softlimit = src->dqb_isoftlimit;
-	dst->d_icount = src->dqb_curinodes;
-	dst->d_btimer = src->dqb_btime;
-	dst->d_itimer = src->dqb_itime;
+	dst->d_ino_count = src->dqb_curinodes;
+	dst->d_spc_timer = src->dqb_btime;
+	dst->d_ino_timer = src->dqb_itime;
 
 	dst->d_fieldmask = 0;
 	if (src->dqb_valid & QIF_BLIMITS)
-		dst->d_fieldmask |= FS_DQ_BSOFT | FS_DQ_BHARD;
+		dst->d_fieldmask |= QC_SPC_SOFT | QC_SPC_HARD;
 	if (src->dqb_valid & QIF_SPACE)
-		dst->d_fieldmask |= FS_DQ_BCOUNT;
+		dst->d_fieldmask |= QC_SPACE;
 	if (src->dqb_valid & QIF_ILIMITS)
-		dst->d_fieldmask |= FS_DQ_ISOFT | FS_DQ_IHARD;
+		dst->d_fieldmask |= QC_INO_SOFT | QC_INO_HARD;
 	if (src->dqb_valid & QIF_INODES)
-		dst->d_fieldmask |= FS_DQ_ICOUNT;
+		dst->d_fieldmask |= QC_INO_COUNT;
 	if (src->dqb_valid & QIF_BTIME)
-		dst->d_fieldmask |= FS_DQ_BTIMER;
+		dst->d_fieldmask |= QC_SPC_TIMER;
 	if (src->dqb_valid & QIF_ITIME)
-		dst->d_fieldmask |= FS_DQ_ITIMER;
+		dst->d_fieldmask |= QC_INO_TIMER;
 }
 
 static int quota_setquota(struct super_block *sb, int type, qid_t id,
 			  void __user *addr)
 {
-	struct fs_disk_quota fdq;
+	struct qc_dqblk fdq;
 	struct if_dqblk idq;
 	struct kqid qid;
 
@@ -247,10 +257,78 @@
 	return ret;
 }
 
+/*
+ * XFS defines BBTOB and BTOBB macros inside fs/xfs/ and we cannot move them
+ * out of there as xfsprogs rely on definitions being in that header file. So
+ * just define same functions here for quota purposes.
+ */
+#define XFS_BB_SHIFT 9
+
+static inline u64 quota_bbtob(u64 blocks)
+{
+	return blocks << XFS_BB_SHIFT;
+}
+
+static inline u64 quota_btobb(u64 bytes)
+{
+	return (bytes + (1 << XFS_BB_SHIFT) - 1) >> XFS_BB_SHIFT;
+}
+
+static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src)
+{
+	dst->d_spc_hardlimit = quota_bbtob(src->d_blk_hardlimit);
+	dst->d_spc_softlimit = quota_bbtob(src->d_blk_softlimit);
+	dst->d_ino_hardlimit = src->d_ino_hardlimit;
+	dst->d_ino_softlimit = src->d_ino_softlimit;
+	dst->d_space = quota_bbtob(src->d_bcount);
+	dst->d_ino_count = src->d_icount;
+	dst->d_ino_timer = src->d_itimer;
+	dst->d_spc_timer = src->d_btimer;
+	dst->d_ino_warns = src->d_iwarns;
+	dst->d_spc_warns = src->d_bwarns;
+	dst->d_rt_spc_hardlimit = quota_bbtob(src->d_rtb_hardlimit);
+	dst->d_rt_spc_softlimit = quota_bbtob(src->d_rtb_softlimit);
+	dst->d_rt_space = quota_bbtob(src->d_rtbcount);
+	dst->d_rt_spc_timer = src->d_rtbtimer;
+	dst->d_rt_spc_warns = src->d_rtbwarns;
+	dst->d_fieldmask = 0;
+	if (src->d_fieldmask & FS_DQ_ISOFT)
+		dst->d_fieldmask |= QC_INO_SOFT;
+	if (src->d_fieldmask & FS_DQ_IHARD)
+		dst->d_fieldmask |= QC_INO_HARD;
+	if (src->d_fieldmask & FS_DQ_BSOFT)
+		dst->d_fieldmask |= QC_SPC_SOFT;
+	if (src->d_fieldmask & FS_DQ_BHARD)
+		dst->d_fieldmask |= QC_SPC_HARD;
+	if (src->d_fieldmask & FS_DQ_RTBSOFT)
+		dst->d_fieldmask |= QC_RT_SPC_SOFT;
+	if (src->d_fieldmask & FS_DQ_RTBHARD)
+		dst->d_fieldmask |= QC_RT_SPC_HARD;
+	if (src->d_fieldmask & FS_DQ_BTIMER)
+		dst->d_fieldmask |= QC_SPC_TIMER;
+	if (src->d_fieldmask & FS_DQ_ITIMER)
+		dst->d_fieldmask |= QC_INO_TIMER;
+	if (src->d_fieldmask & FS_DQ_RTBTIMER)
+		dst->d_fieldmask |= QC_RT_SPC_TIMER;
+	if (src->d_fieldmask & FS_DQ_BWARNS)
+		dst->d_fieldmask |= QC_SPC_WARNS;
+	if (src->d_fieldmask & FS_DQ_IWARNS)
+		dst->d_fieldmask |= QC_INO_WARNS;
+	if (src->d_fieldmask & FS_DQ_RTBWARNS)
+		dst->d_fieldmask |= QC_RT_SPC_WARNS;
+	if (src->d_fieldmask & FS_DQ_BCOUNT)
+		dst->d_fieldmask |= QC_SPACE;
+	if (src->d_fieldmask & FS_DQ_ICOUNT)
+		dst->d_fieldmask |= QC_INO_COUNT;
+	if (src->d_fieldmask & FS_DQ_RTBCOUNT)
+		dst->d_fieldmask |= QC_RT_SPACE;
+}
+
 static int quota_setxquota(struct super_block *sb, int type, qid_t id,
 			   void __user *addr)
 {
 	struct fs_disk_quota fdq;
+	struct qc_dqblk qdq;
 	struct kqid qid;
 
 	if (copy_from_user(&fdq, addr, sizeof(fdq)))
@@ -260,13 +338,44 @@
 	qid = make_kqid(current_user_ns(), type, id);
 	if (!qid_valid(qid))
 		return -EINVAL;
-	return sb->s_qcop->set_dqblk(sb, qid, &fdq);
+	copy_from_xfs_dqblk(&qdq, &fdq);
+	return sb->s_qcop->set_dqblk(sb, qid, &qdq);
+}
+
+static void copy_to_xfs_dqblk(struct fs_disk_quota *dst, struct qc_dqblk *src,
+			      int type, qid_t id)
+{
+	memset(dst, 0, sizeof(*dst));
+	dst->d_version = FS_DQUOT_VERSION;
+	dst->d_id = id;
+	if (type == USRQUOTA)
+		dst->d_flags = FS_USER_QUOTA;
+	else if (type == PRJQUOTA)
+		dst->d_flags = FS_PROJ_QUOTA;
+	else
+		dst->d_flags = FS_GROUP_QUOTA;
+	dst->d_blk_hardlimit = quota_btobb(src->d_spc_hardlimit);
+	dst->d_blk_softlimit = quota_btobb(src->d_spc_softlimit);
+	dst->d_ino_hardlimit = src->d_ino_hardlimit;
+	dst->d_ino_softlimit = src->d_ino_softlimit;
+	dst->d_bcount = quota_btobb(src->d_space);
+	dst->d_icount = src->d_ino_count;
+	dst->d_itimer = src->d_ino_timer;
+	dst->d_btimer = src->d_spc_timer;
+	dst->d_iwarns = src->d_ino_warns;
+	dst->d_bwarns = src->d_spc_warns;
+	dst->d_rtb_hardlimit = quota_btobb(src->d_rt_spc_hardlimit);
+	dst->d_rtb_softlimit = quota_btobb(src->d_rt_spc_softlimit);
+	dst->d_rtbcount = quota_btobb(src->d_rt_space);
+	dst->d_rtbtimer = src->d_rt_spc_timer;
+	dst->d_rtbwarns = src->d_rt_spc_warns;
 }
 
 static int quota_getxquota(struct super_block *sb, int type, qid_t id,
 			   void __user *addr)
 {
 	struct fs_disk_quota fdq;
+	struct qc_dqblk qdq;
 	struct kqid qid;
 	int ret;
 
@@ -275,8 +384,11 @@
 	qid = make_kqid(current_user_ns(), type, id);
 	if (!qid_valid(qid))
 		return -EINVAL;
-	ret = sb->s_qcop->get_dqblk(sb, qid, &fdq);
-	if (!ret && copy_to_user(addr, &fdq, sizeof(fdq)))
+	ret = sb->s_qcop->get_dqblk(sb, qid, &qdq);
+	if (ret)
+		return ret;
+	copy_to_xfs_dqblk(&fdq, &qdq, type, id);
+	if (copy_to_user(addr, &fdq, sizeof(fdq)))
 		return -EFAULT;
 	return ret;
 }
diff --git a/fs/udf/file.c b/fs/udf/file.c
index bb15771..08f3555 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -224,7 +224,7 @@
 static int udf_release_file(struct inode *inode, struct file *filp)
 {
 	if (filp->f_mode & FMODE_WRITE &&
-	    atomic_read(&inode->i_writecount) > 1) {
+	    atomic_read(&inode->i_writecount) == 1) {
 		/*
 		 * Grab i_mutex to avoid races with writes changing i_size
 		 * while we are running.
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 3a07a93..41f6c0b 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -166,9 +166,9 @@
 /* quota ops */
 extern int		xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint);
 extern int		xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t,
-					uint, struct fs_disk_quota *);
+					uint, struct qc_dqblk *);
 extern int		xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint,
-					struct fs_disk_quota *);
+					struct qc_dqblk *);
 extern int		xfs_qm_scall_getqstat(struct xfs_mount *,
 					struct fs_quota_stat *);
 extern int		xfs_qm_scall_getqstatv(struct xfs_mount *,
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 74fca68..cb6168e 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -39,7 +39,6 @@
 STATIC int	xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *,
 					uint);
 STATIC uint	xfs_qm_export_flags(uint);
-STATIC uint	xfs_qm_export_qtype_flags(uint);
 
 /*
  * Turn off quota accounting and/or enforcement for all udquots and/or
@@ -573,8 +572,8 @@
 	return 0;
 }
 
-#define XFS_DQ_MASK \
-	(FS_DQ_LIMIT_MASK | FS_DQ_TIMER_MASK | FS_DQ_WARNS_MASK)
+#define XFS_QC_MASK \
+	(QC_LIMIT_MASK | QC_TIMER_MASK | QC_WARNS_MASK)
 
 /*
  * Adjust quota limits, and start/stop timers accordingly.
@@ -584,7 +583,7 @@
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
 	uint			type,
-	fs_disk_quota_t		*newlim)
+	struct qc_dqblk		*newlim)
 {
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
 	struct xfs_disk_dquot	*ddq;
@@ -593,9 +592,9 @@
 	int			error;
 	xfs_qcnt_t		hard, soft;
 
-	if (newlim->d_fieldmask & ~XFS_DQ_MASK)
+	if (newlim->d_fieldmask & ~XFS_QC_MASK)
 		return -EINVAL;
-	if ((newlim->d_fieldmask & XFS_DQ_MASK) == 0)
+	if ((newlim->d_fieldmask & XFS_QC_MASK) == 0)
 		return 0;
 
 	/*
@@ -633,11 +632,11 @@
 	/*
 	 * Make sure that hardlimits are >= soft limits before changing.
 	 */
-	hard = (newlim->d_fieldmask & FS_DQ_BHARD) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_hardlimit) :
+	hard = (newlim->d_fieldmask & QC_SPC_HARD) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_hardlimit) :
 			be64_to_cpu(ddq->d_blk_hardlimit);
-	soft = (newlim->d_fieldmask & FS_DQ_BSOFT) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_softlimit) :
+	soft = (newlim->d_fieldmask & QC_SPC_SOFT) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_softlimit) :
 			be64_to_cpu(ddq->d_blk_softlimit);
 	if (hard == 0 || hard >= soft) {
 		ddq->d_blk_hardlimit = cpu_to_be64(hard);
@@ -650,11 +649,11 @@
 	} else {
 		xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft);
 	}
-	hard = (newlim->d_fieldmask & FS_DQ_RTBHARD) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_hardlimit) :
+	hard = (newlim->d_fieldmask & QC_RT_SPC_HARD) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_hardlimit) :
 			be64_to_cpu(ddq->d_rtb_hardlimit);
-	soft = (newlim->d_fieldmask & FS_DQ_RTBSOFT) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_softlimit) :
+	soft = (newlim->d_fieldmask & QC_RT_SPC_SOFT) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_softlimit) :
 			be64_to_cpu(ddq->d_rtb_softlimit);
 	if (hard == 0 || hard >= soft) {
 		ddq->d_rtb_hardlimit = cpu_to_be64(hard);
@@ -667,10 +666,10 @@
 		xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft);
 	}
 
-	hard = (newlim->d_fieldmask & FS_DQ_IHARD) ?
+	hard = (newlim->d_fieldmask & QC_INO_HARD) ?
 		(xfs_qcnt_t) newlim->d_ino_hardlimit :
 			be64_to_cpu(ddq->d_ino_hardlimit);
-	soft = (newlim->d_fieldmask & FS_DQ_ISOFT) ?
+	soft = (newlim->d_fieldmask & QC_INO_SOFT) ?
 		(xfs_qcnt_t) newlim->d_ino_softlimit :
 			be64_to_cpu(ddq->d_ino_softlimit);
 	if (hard == 0 || hard >= soft) {
@@ -687,12 +686,12 @@
 	/*
 	 * Update warnings counter(s) if requested
 	 */
-	if (newlim->d_fieldmask & FS_DQ_BWARNS)
-		ddq->d_bwarns = cpu_to_be16(newlim->d_bwarns);
-	if (newlim->d_fieldmask & FS_DQ_IWARNS)
-		ddq->d_iwarns = cpu_to_be16(newlim->d_iwarns);
-	if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
-		ddq->d_rtbwarns = cpu_to_be16(newlim->d_rtbwarns);
+	if (newlim->d_fieldmask & QC_SPC_WARNS)
+		ddq->d_bwarns = cpu_to_be16(newlim->d_spc_warns);
+	if (newlim->d_fieldmask & QC_INO_WARNS)
+		ddq->d_iwarns = cpu_to_be16(newlim->d_ino_warns);
+	if (newlim->d_fieldmask & QC_RT_SPC_WARNS)
+		ddq->d_rtbwarns = cpu_to_be16(newlim->d_rt_spc_warns);
 
 	if (id == 0) {
 		/*
@@ -702,24 +701,24 @@
 		 * soft and hard limit values (already done, above), and
 		 * for warnings.
 		 */
-		if (newlim->d_fieldmask & FS_DQ_BTIMER) {
-			q->qi_btimelimit = newlim->d_btimer;
-			ddq->d_btimer = cpu_to_be32(newlim->d_btimer);
+		if (newlim->d_fieldmask & QC_SPC_TIMER) {
+			q->qi_btimelimit = newlim->d_spc_timer;
+			ddq->d_btimer = cpu_to_be32(newlim->d_spc_timer);
 		}
-		if (newlim->d_fieldmask & FS_DQ_ITIMER) {
-			q->qi_itimelimit = newlim->d_itimer;
-			ddq->d_itimer = cpu_to_be32(newlim->d_itimer);
+		if (newlim->d_fieldmask & QC_INO_TIMER) {
+			q->qi_itimelimit = newlim->d_ino_timer;
+			ddq->d_itimer = cpu_to_be32(newlim->d_ino_timer);
 		}
-		if (newlim->d_fieldmask & FS_DQ_RTBTIMER) {
-			q->qi_rtbtimelimit = newlim->d_rtbtimer;
-			ddq->d_rtbtimer = cpu_to_be32(newlim->d_rtbtimer);
+		if (newlim->d_fieldmask & QC_RT_SPC_TIMER) {
+			q->qi_rtbtimelimit = newlim->d_rt_spc_timer;
+			ddq->d_rtbtimer = cpu_to_be32(newlim->d_rt_spc_timer);
 		}
-		if (newlim->d_fieldmask & FS_DQ_BWARNS)
-			q->qi_bwarnlimit = newlim->d_bwarns;
-		if (newlim->d_fieldmask & FS_DQ_IWARNS)
-			q->qi_iwarnlimit = newlim->d_iwarns;
-		if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
-			q->qi_rtbwarnlimit = newlim->d_rtbwarns;
+		if (newlim->d_fieldmask & QC_SPC_WARNS)
+			q->qi_bwarnlimit = newlim->d_spc_warns;
+		if (newlim->d_fieldmask & QC_INO_WARNS)
+			q->qi_iwarnlimit = newlim->d_ino_warns;
+		if (newlim->d_fieldmask & QC_RT_SPC_WARNS)
+			q->qi_rtbwarnlimit = newlim->d_rt_spc_warns;
 	} else {
 		/*
 		 * If the user is now over quota, start the timelimit.
@@ -824,7 +823,7 @@
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
 	uint			type,
-	struct fs_disk_quota	*dst)
+	struct qc_dqblk		*dst)
 {
 	struct xfs_dquot	*dqp;
 	int			error;
@@ -848,28 +847,25 @@
 	}
 
 	memset(dst, 0, sizeof(*dst));
-	dst->d_version = FS_DQUOT_VERSION;
-	dst->d_flags = xfs_qm_export_qtype_flags(dqp->q_core.d_flags);
-	dst->d_id = be32_to_cpu(dqp->q_core.d_id);
-	dst->d_blk_hardlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit));
-	dst->d_blk_softlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit));
+	dst->d_spc_hardlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit));
+	dst->d_spc_softlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit));
 	dst->d_ino_hardlimit = be64_to_cpu(dqp->q_core.d_ino_hardlimit);
 	dst->d_ino_softlimit = be64_to_cpu(dqp->q_core.d_ino_softlimit);
-	dst->d_bcount = XFS_FSB_TO_BB(mp, dqp->q_res_bcount);
-	dst->d_icount = dqp->q_res_icount;
-	dst->d_btimer = be32_to_cpu(dqp->q_core.d_btimer);
-	dst->d_itimer = be32_to_cpu(dqp->q_core.d_itimer);
-	dst->d_iwarns = be16_to_cpu(dqp->q_core.d_iwarns);
-	dst->d_bwarns = be16_to_cpu(dqp->q_core.d_bwarns);
-	dst->d_rtb_hardlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit));
-	dst->d_rtb_softlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit));
-	dst->d_rtbcount = XFS_FSB_TO_BB(mp, dqp->q_res_rtbcount);
-	dst->d_rtbtimer = be32_to_cpu(dqp->q_core.d_rtbtimer);
-	dst->d_rtbwarns = be16_to_cpu(dqp->q_core.d_rtbwarns);
+	dst->d_space = XFS_FSB_TO_B(mp, dqp->q_res_bcount);
+	dst->d_ino_count = dqp->q_res_icount;
+	dst->d_spc_timer = be32_to_cpu(dqp->q_core.d_btimer);
+	dst->d_ino_timer = be32_to_cpu(dqp->q_core.d_itimer);
+	dst->d_ino_warns = be16_to_cpu(dqp->q_core.d_iwarns);
+	dst->d_spc_warns = be16_to_cpu(dqp->q_core.d_bwarns);
+	dst->d_rt_spc_hardlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit));
+	dst->d_rt_spc_softlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit));
+	dst->d_rt_space = XFS_FSB_TO_B(mp, dqp->q_res_rtbcount);
+	dst->d_rt_spc_timer = be32_to_cpu(dqp->q_core.d_rtbtimer);
+	dst->d_rt_spc_warns = be16_to_cpu(dqp->q_core.d_rtbwarns);
 
 	/*
 	 * Internally, we don't reset all the timers when quota enforcement
@@ -882,23 +878,23 @@
 	     dqp->q_core.d_flags == XFS_DQ_GROUP) ||
 	    (!XFS_IS_PQUOTA_ENFORCED(mp) &&
 	     dqp->q_core.d_flags == XFS_DQ_PROJ)) {
-		dst->d_btimer = 0;
-		dst->d_itimer = 0;
-		dst->d_rtbtimer = 0;
+		dst->d_spc_timer = 0;
+		dst->d_ino_timer = 0;
+		dst->d_rt_spc_timer = 0;
 	}
 
 #ifdef DEBUG
-	if (((XFS_IS_UQUOTA_ENFORCED(mp) && dst->d_flags == FS_USER_QUOTA) ||
-	     (XFS_IS_GQUOTA_ENFORCED(mp) && dst->d_flags == FS_GROUP_QUOTA) ||
-	     (XFS_IS_PQUOTA_ENFORCED(mp) && dst->d_flags == FS_PROJ_QUOTA)) &&
-	    dst->d_id != 0) {
-		if ((dst->d_bcount > dst->d_blk_softlimit) &&
-		    (dst->d_blk_softlimit > 0)) {
-			ASSERT(dst->d_btimer != 0);
+	if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) ||
+	     (XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) ||
+	     (XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) &&
+	    id != 0) {
+		if ((dst->d_space > dst->d_spc_softlimit) &&
+		    (dst->d_spc_softlimit > 0)) {
+			ASSERT(dst->d_spc_timer != 0);
 		}
-		if ((dst->d_icount > dst->d_ino_softlimit) &&
+		if ((dst->d_ino_count > dst->d_ino_softlimit) &&
 		    (dst->d_ino_softlimit > 0)) {
-			ASSERT(dst->d_itimer != 0);
+			ASSERT(dst->d_ino_timer != 0);
 		}
 	}
 #endif
@@ -908,26 +904,6 @@
 }
 
 STATIC uint
-xfs_qm_export_qtype_flags(
-	uint flags)
-{
-	/*
-	 * Can't be more than one, or none.
-	 */
-	ASSERT((flags & (FS_PROJ_QUOTA | FS_USER_QUOTA)) !=
-		(FS_PROJ_QUOTA | FS_USER_QUOTA));
-	ASSERT((flags & (FS_PROJ_QUOTA | FS_GROUP_QUOTA)) !=
-		(FS_PROJ_QUOTA | FS_GROUP_QUOTA));
-	ASSERT((flags & (FS_USER_QUOTA | FS_GROUP_QUOTA)) !=
-		(FS_USER_QUOTA | FS_GROUP_QUOTA));
-	ASSERT((flags & (FS_PROJ_QUOTA|FS_USER_QUOTA|FS_GROUP_QUOTA)) != 0);
-
-	return (flags & XFS_DQ_USER) ?
-		FS_USER_QUOTA : (flags & XFS_DQ_PROJ) ?
-			FS_PROJ_QUOTA : FS_GROUP_QUOTA;
-}
-
-STATIC uint
 xfs_qm_export_flags(
 	uint flags)
 {
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index 7542bbe..801a84c 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -131,7 +131,7 @@
 xfs_fs_get_dqblk(
 	struct super_block	*sb,
 	struct kqid		qid,
-	struct fs_disk_quota	*fdq)
+	struct qc_dqblk		*qdq)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
@@ -141,14 +141,14 @@
 		return -ESRCH;
 
 	return xfs_qm_scall_getquota(mp, from_kqid(&init_user_ns, qid),
-				      xfs_quota_type(qid.type), fdq);
+				      xfs_quota_type(qid.type), qdq);
 }
 
 STATIC int
 xfs_fs_set_dqblk(
 	struct super_block	*sb,
 	struct kqid		qid,
-	struct fs_disk_quota	*fdq)
+	struct qc_dqblk		*qdq)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
@@ -160,7 +160,7 @@
 		return -ESRCH;
 
 	return xfs_qm_scall_setqlim(mp, from_kqid(&init_user_ns, qid),
-				     xfs_quota_type(qid.type), fdq);
+				     xfs_quota_type(qid.type), qdq);
 }
 
 const struct quotactl_ops xfs_quotactl_operations = {
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index e3a1721..7c76959 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -228,7 +228,9 @@
 	struct device dev;		/* the device structure		*/
 	int irq;			/* irq issued by device		*/
 	struct list_head detected;
+#if IS_ENABLED(CONFIG_I2C_SLAVE)
 	i2c_slave_cb_t slave_cb;	/* callback for slave mode	*/
+#endif
 };
 #define to_i2c_client(d) container_of(d, struct i2c_client, dev)
 
@@ -253,6 +255,7 @@
 
 /* I2C slave support */
 
+#if IS_ENABLED(CONFIG_I2C_SLAVE)
 enum i2c_slave_event {
 	I2C_SLAVE_REQ_READ_START,
 	I2C_SLAVE_REQ_READ_END,
@@ -269,6 +272,7 @@
 {
 	return client->slave_cb(client, event, val);
 }
+#endif
 
 /**
  * struct i2c_board_info - template for device creation
@@ -404,8 +408,10 @@
 	/* To determine what the adapter supports */
 	u32 (*functionality) (struct i2c_adapter *);
 
+#if IS_ENABLED(CONFIG_I2C_SLAVE)
 	int (*reg_slave)(struct i2c_client *client);
 	int (*unreg_slave)(struct i2c_client *client);
+#endif
 };
 
 /**
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5449d2f..64ce58b 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -176,7 +176,7 @@
  */
 # define might_sleep() \
 	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
-# define sched_annotate_sleep()	__set_current_state(TASK_RUNNING)
+# define sched_annotate_sleep()	(current->task_state_change = 0)
 #else
   static inline void ___might_sleep(const char *file, int line,
 				   int preempt_offset) { }
diff --git a/include/linux/mfd/samsung/s2mps13.h b/include/linux/mfd/samsung/s2mps13.h
index ce5dda8..b1fd675 100644
--- a/include/linux/mfd/samsung/s2mps13.h
+++ b/include/linux/mfd/samsung/s2mps13.h
@@ -59,6 +59,7 @@
 	S2MPS13_REG_B6CTRL,
 	S2MPS13_REG_B6OUT,
 	S2MPS13_REG_B7CTRL,
+	S2MPS13_REG_B7SW,
 	S2MPS13_REG_B7OUT,
 	S2MPS13_REG_B8CTRL,
 	S2MPS13_REG_B8OUT,
@@ -102,6 +103,7 @@
 	S2MPS13_REG_L26CTRL,
 	S2MPS13_REG_L27CTRL,
 	S2MPS13_REG_L28CTRL,
+	S2MPS13_REG_L29CTRL,
 	S2MPS13_REG_L30CTRL,
 	S2MPS13_REG_L31CTRL,
 	S2MPS13_REG_L32CTRL,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80fc92a..dd5ea30 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1070,6 +1070,7 @@
 #define VM_FAULT_WRITE	0x0008	/* Special case for get_user_pages */
 #define VM_FAULT_HWPOISON 0x0010	/* Hit poisoned small page */
 #define VM_FAULT_HWPOISON_LARGE 0x0020  /* Hit poisoned large page. Index encoded in upper bits */
+#define VM_FAULT_SIGSEGV 0x0040
 
 #define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
 #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
@@ -1078,8 +1079,9 @@
 
 #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
 
-#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
-			 VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE)
+#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \
+			 VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \
+			 VM_FAULT_FALLBACK)
 
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((x) << 12)
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 853698c..7620098 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -85,11 +85,6 @@
 	oom_killer_disabled = false;
 }
 
-static inline bool oom_gfp_allowed(gfp_t gfp_mask)
-{
-	return (gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY);
-}
-
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
 static inline bool task_will_free_mem(struct task_struct *task)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4f7a61c..664de5a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -450,11 +450,6 @@
 #endif /* CONFIG_PERF_EVENTS */
 };
 
-enum perf_event_context_type {
-	task_context,
-	cpu_context,
-};
-
 /**
  * struct perf_event_context - event context structure
  *
@@ -462,7 +457,6 @@
  */
 struct perf_event_context {
 	struct pmu			*pmu;
-	enum perf_event_context_type	type;
 	/*
 	 * Protect the states of the events in the list,
 	 * nr_active, and the list:
diff --git a/include/linux/printk.h b/include/linux/printk.h
index c8f1703..4d5bf57 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -10,9 +10,6 @@
 extern const char linux_banner[];
 extern const char linux_proc_banner[];
 
-extern char *log_buf_addr_get(void);
-extern u32 log_buf_len_get(void);
-
 static inline int printk_get_level(const char *buffer)
 {
 	if (buffer[0] == KERN_SOH_ASCII && buffer[1]) {
@@ -163,6 +160,8 @@
 
 extern void wake_up_klogd(void);
 
+char *log_buf_addr_get(void);
+u32 log_buf_len_get(void);
 void log_buf_kexec_setup(void);
 void __init setup_log_buf(int early);
 void dump_stack_set_arch_desc(const char *fmt, ...);
@@ -198,6 +197,16 @@
 {
 }
 
+static inline char *log_buf_addr_get(void)
+{
+	return NULL;
+}
+
+static inline u32 log_buf_len_get(void)
+{
+	return 0;
+}
+
 static inline void log_buf_kexec_setup(void)
 {
 }
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 50978b7..097d7eb2 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -321,6 +321,49 @@
 
 struct path;
 
+/* Structure for communicating via ->get_dqblk() & ->set_dqblk() */
+struct qc_dqblk {
+	int d_fieldmask;	/* mask of fields to change in ->set_dqblk() */
+	u64 d_spc_hardlimit;	/* absolute limit on used space */
+	u64 d_spc_softlimit;	/* preferred limit on used space */
+	u64 d_ino_hardlimit;	/* maximum # allocated inodes */
+	u64 d_ino_softlimit;	/* preferred inode limit */
+	u64 d_space;		/* Space owned by the user */
+	u64 d_ino_count;	/* # inodes owned by the user */
+	s64 d_ino_timer;	/* zero if within inode limits */
+				/* if not, we refuse service */
+	s64 d_spc_timer;	/* similar to above; for space */
+	int d_ino_warns;	/* # warnings issued wrt num inodes */
+	int d_spc_warns;	/* # warnings issued wrt used space */
+	u64 d_rt_spc_hardlimit;	/* absolute limit on realtime space */
+	u64 d_rt_spc_softlimit;	/* preferred limit on RT space */
+	u64 d_rt_space;		/* realtime space owned */
+	s64 d_rt_spc_timer;	/* similar to above; for RT space */
+	int d_rt_spc_warns;	/* # warnings issued wrt RT space */
+};
+
+/* Field specifiers for ->set_dqblk() in struct qc_dqblk */
+#define	QC_INO_SOFT	(1<<0)
+#define	QC_INO_HARD	(1<<1)
+#define	QC_SPC_SOFT	(1<<2)
+#define	QC_SPC_HARD	(1<<3)
+#define	QC_RT_SPC_SOFT	(1<<4)
+#define	QC_RT_SPC_HARD	(1<<5)
+#define QC_LIMIT_MASK (QC_INO_SOFT | QC_INO_HARD | QC_SPC_SOFT | QC_SPC_HARD | \
+		       QC_RT_SPC_SOFT | QC_RT_SPC_HARD)
+#define	QC_SPC_TIMER	(1<<6)
+#define	QC_INO_TIMER	(1<<7)
+#define	QC_RT_SPC_TIMER	(1<<8)
+#define QC_TIMER_MASK (QC_SPC_TIMER | QC_INO_TIMER | QC_RT_SPC_TIMER)
+#define	QC_SPC_WARNS	(1<<9)
+#define	QC_INO_WARNS	(1<<10)
+#define	QC_RT_SPC_WARNS	(1<<11)
+#define QC_WARNS_MASK (QC_SPC_WARNS | QC_INO_WARNS | QC_RT_SPC_WARNS)
+#define	QC_SPACE	(1<<12)
+#define	QC_INO_COUNT	(1<<13)
+#define	QC_RT_SPACE	(1<<14)
+#define QC_ACCT_MASK (QC_SPACE | QC_INO_COUNT | QC_RT_SPACE)
+
 /* Operations handling requests from userspace */
 struct quotactl_ops {
 	int (*quota_on)(struct super_block *, int, int, struct path *);
@@ -329,8 +372,8 @@
 	int (*quota_sync)(struct super_block *, int);
 	int (*get_info)(struct super_block *, int, struct if_dqinfo *);
 	int (*set_info)(struct super_block *, int, struct if_dqinfo *);
-	int (*get_dqblk)(struct super_block *, struct kqid, struct fs_disk_quota *);
-	int (*set_dqblk)(struct super_block *, struct kqid, struct fs_disk_quota *);
+	int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *);
+	int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *);
 	int (*get_xstate)(struct super_block *, struct fs_quota_stat *);
 	int (*set_xstate)(struct super_block *, unsigned int, int);
 	int (*get_xstatev)(struct super_block *, struct fs_quota_statv *);
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index f23538a..29e3455 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -98,9 +98,9 @@
 int dquot_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
 int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
 int dquot_get_dqblk(struct super_block *sb, struct kqid id,
-		struct fs_disk_quota *di);
+		struct qc_dqblk *di);
 int dquot_set_dqblk(struct super_block *sb, struct kqid id,
-		struct fs_disk_quota *di);
+		struct qc_dqblk *di);
 
 int __dquot_transfer(struct inode *inode, struct dquot **transfer_to);
 int dquot_transfer(struct inode *inode, struct iattr *iattr);
diff --git a/include/net/ip.h b/include/net/ip.h
index 0bb6207..f7cbd70 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -39,11 +39,12 @@
 	struct ip_options	opt;		/* Compiled IP options		*/
 	unsigned char		flags;
 
-#define IPSKB_FORWARDED		1
-#define IPSKB_XFRM_TUNNEL_SIZE	2
-#define IPSKB_XFRM_TRANSFORMED	4
-#define IPSKB_FRAG_COMPLETE	8
-#define IPSKB_REROUTED		16
+#define IPSKB_FORWARDED		BIT(0)
+#define IPSKB_XFRM_TUNNEL_SIZE	BIT(1)
+#define IPSKB_XFRM_TRANSFORMED	BIT(2)
+#define IPSKB_FRAG_COMPLETE	BIT(3)
+#define IPSKB_REROUTED		BIT(4)
+#define IPSKB_DOREDIRECT	BIT(5)
 
 	u16			frag_max_size;
 };
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 088ac0b..536edc2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -150,7 +150,7 @@
 	int ufd = attr->map_fd;
 	struct fd f = fdget(ufd);
 	struct bpf_map *map;
-	void *key, *value;
+	void *key, *value, *ptr;
 	int err;
 
 	if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
@@ -169,20 +169,29 @@
 	if (copy_from_user(key, ukey, map->key_size) != 0)
 		goto free_key;
 
-	err = -ENOENT;
-	rcu_read_lock();
-	value = map->ops->map_lookup_elem(map, key);
+	err = -ENOMEM;
+	value = kmalloc(map->value_size, GFP_USER);
 	if (!value)
-		goto err_unlock;
+		goto free_key;
+
+	rcu_read_lock();
+	ptr = map->ops->map_lookup_elem(map, key);
+	if (ptr)
+		memcpy(value, ptr, map->value_size);
+	rcu_read_unlock();
+
+	err = -ENOENT;
+	if (!ptr)
+		goto free_value;
 
 	err = -EFAULT;
 	if (copy_to_user(uvalue, value, map->value_size) != 0)
-		goto err_unlock;
+		goto free_value;
 
 	err = 0;
 
-err_unlock:
-	rcu_read_unlock();
+free_value:
+	kfree(value);
 free_key:
 	kfree(key);
 err_put:
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index bb263d0..04cfe8a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1909,7 +1909,7 @@
 	 *
 	 * And don't kill the default root.
 	 */
-	if (css_has_online_children(&root->cgrp.self) ||
+	if (!list_empty(&root->cgrp.self.children) ||
 	    root == &cgrp_dfl_root)
 		cgroup_put(&root->cgrp);
 	else
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 882f835..19efcf1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6776,7 +6776,6 @@
 		__perf_event_init_context(&cpuctx->ctx);
 		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
 		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
-		cpuctx->ctx.type = cpu_context;
 		cpuctx->ctx.pmu = pmu;
 
 		__perf_cpu_hrtimer_init(cpuctx, cpu);
@@ -7420,7 +7419,19 @@
 		 * task or CPU context:
 		 */
 		if (move_group) {
-			if (group_leader->ctx->type != ctx->type)
+			/*
+			 * Make sure we're both on the same task, or both
+			 * per-cpu events.
+			 */
+			if (group_leader->ctx->task != ctx->task)
+				goto err_context;
+
+			/*
+			 * Make sure we're both events for the same CPU;
+			 * grouping events for different CPUs is broken; since
+			 * you can never concurrently schedule them anyhow.
+			 */
+			if (group_leader->cpu != event->cpu)
 				goto err_context;
 		} else {
 			if (group_leader->ctx != ctx)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c0accc0..e628cb1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7292,13 +7292,12 @@
 	 * since we will exit with TASK_RUNNING make sure we enter with it,
 	 * otherwise we will destroy state.
 	 */
-	if (WARN_ONCE(current->state != TASK_RUNNING,
+	WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change,
 			"do not call blocking ops when !TASK_RUNNING; "
 			"state=%lx set at [<%p>] %pS\n",
 			current->state,
 			(void *)current->task_state_change,
-			(void *)current->task_state_change))
-		__set_current_state(TASK_RUNNING);
+			(void *)current->task_state_change);
 
 	___might_sleep(file, line, preempt_offset);
 }
diff --git a/mm/gup.c b/mm/gup.c
index a900759..8dd50ce 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -296,7 +296,7 @@
 			return -ENOMEM;
 		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
 			return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
-		if (ret & VM_FAULT_SIGBUS)
+		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
 			return -EFAULT;
 		BUG();
 	}
@@ -571,7 +571,7 @@
 			return -ENOMEM;
 		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
 			return -EHWPOISON;
-		if (ret & VM_FAULT_SIGBUS)
+		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
 			return -EFAULT;
 		BUG();
 	}
diff --git a/mm/ksm.c b/mm/ksm.c
index d247efa..15647fb 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -376,7 +376,7 @@
 		else
 			ret = VM_FAULT_WRITE;
 		put_page(page);
-	} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM)));
+	} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM)));
 	/*
 	 * We must loop because handle_mm_fault() may back out if there's
 	 * any difficulty e.g. if pte accessed bit gets updated concurrently.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 851924f..683b478 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1477,9 +1477,9 @@
 
 	pr_info("Task in ");
 	pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
-	pr_info(" killed as a result of limit of ");
+	pr_cont(" killed as a result of limit of ");
 	pr_cont_cgroup_path(memcg->css.cgroup);
-	pr_info("\n");
+	pr_cont("\n");
 
 	rcu_read_unlock();
 
diff --git a/mm/memory.c b/mm/memory.c
index 54f3a9b..2c3536c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2632,7 +2632,7 @@
 
 	/* Check if we need to add a guard page to the stack */
 	if (check_stack_guard_page(vma, address) < 0)
-		return VM_FAULT_SIGBUS;
+		return VM_FAULT_SIGSEGV;
 
 	/* Use the zero-page for reads */
 	if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7633c50..8e20f9c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2332,12 +2332,21 @@
 __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, struct zone *preferred_zone,
-	int classzone_idx, int migratetype)
+	int classzone_idx, int migratetype, unsigned long *did_some_progress)
 {
 	struct page *page;
 
-	/* Acquire the per-zone oom lock for each zone */
+	*did_some_progress = 0;
+
+	if (oom_killer_disabled)
+		return NULL;
+
+	/*
+	 * Acquire the per-zone oom lock for each zone.  If that
+	 * fails, somebody else is making progress for us.
+	 */
 	if (!oom_zonelist_trylock(zonelist, gfp_mask)) {
+		*did_some_progress = 1;
 		schedule_timeout_uninterruptible(1);
 		return NULL;
 	}
@@ -2363,12 +2372,18 @@
 		goto out;
 
 	if (!(gfp_mask & __GFP_NOFAIL)) {
+		/* Coredumps can quickly deplete all memory reserves */
+		if (current->flags & PF_DUMPCORE)
+			goto out;
 		/* The OOM killer will not help higher order allocs */
 		if (order > PAGE_ALLOC_COSTLY_ORDER)
 			goto out;
 		/* The OOM killer does not needlessly kill tasks for lowmem */
 		if (high_zoneidx < ZONE_NORMAL)
 			goto out;
+		/* The OOM killer does not compensate for light reclaim */
+		if (!(gfp_mask & __GFP_FS))
+			goto out;
 		/*
 		 * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
 		 * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
@@ -2381,7 +2396,7 @@
 	}
 	/* Exhausted what can be done so it's blamo time */
 	out_of_memory(zonelist, gfp_mask, order, nodemask, false);
-
+	*did_some_progress = 1;
 out:
 	oom_zonelist_unlock(zonelist, gfp_mask);
 	return page;
@@ -2658,7 +2673,7 @@
 	    (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
-restart:
+retry:
 	if (!(gfp_mask & __GFP_NO_KSWAPD))
 		wake_all_kswapds(order, zonelist, high_zoneidx,
 				preferred_zone, nodemask);
@@ -2681,7 +2696,6 @@
 		classzone_idx = zonelist_zone_idx(preferred_zoneref);
 	}
 
-rebalance:
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
 			high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
@@ -2788,54 +2802,28 @@
 	if (page)
 		goto got_pg;
 
-	/*
-	 * If we failed to make any progress reclaiming, then we are
-	 * running out of options and have to consider going OOM
-	 */
-	if (!did_some_progress) {
-		if (oom_gfp_allowed(gfp_mask)) {
-			if (oom_killer_disabled)
-				goto nopage;
-			/* Coredumps can quickly deplete all memory reserves */
-			if ((current->flags & PF_DUMPCORE) &&
-			    !(gfp_mask & __GFP_NOFAIL))
-				goto nopage;
-			page = __alloc_pages_may_oom(gfp_mask, order,
-					zonelist, high_zoneidx,
-					nodemask, preferred_zone,
-					classzone_idx, migratetype);
-			if (page)
-				goto got_pg;
-
-			if (!(gfp_mask & __GFP_NOFAIL)) {
-				/*
-				 * The oom killer is not called for high-order
-				 * allocations that may fail, so if no progress
-				 * is being made, there are no other options and
-				 * retrying is unlikely to help.
-				 */
-				if (order > PAGE_ALLOC_COSTLY_ORDER)
-					goto nopage;
-				/*
-				 * The oom killer is not called for lowmem
-				 * allocations to prevent needlessly killing
-				 * innocent tasks.
-				 */
-				if (high_zoneidx < ZONE_NORMAL)
-					goto nopage;
-			}
-
-			goto restart;
-		}
-	}
-
 	/* Check if we should retry the allocation */
 	pages_reclaimed += did_some_progress;
 	if (should_alloc_retry(gfp_mask, order, did_some_progress,
 						pages_reclaimed)) {
+		/*
+		 * If we fail to make progress by freeing individual
+		 * pages, but the allocation wants us to keep going,
+		 * start OOM killing tasks.
+		 */
+		if (!did_some_progress) {
+			page = __alloc_pages_may_oom(gfp_mask, order, zonelist,
+						high_zoneidx, nodemask,
+						preferred_zone, classzone_idx,
+						migratetype,&did_some_progress);
+			if (page)
+				goto got_pg;
+			if (!did_some_progress)
+				goto nopage;
+		}
 		/* Wait for some write requests to complete then retry */
 		wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
-		goto rebalance;
+		goto retry;
 	} else {
 		/*
 		 * High-order allocations do not necessarily loop after
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ab2505c..dcd90c8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2656,7 +2656,7 @@
 	 * should make reasonable progress.
 	 */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
-					gfp_mask, nodemask) {
+					gfp_zone(gfp_mask), nodemask) {
 		if (zone_idx(zone) > ZONE_NORMAL)
 			continue;
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 515569f..589aafd 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -46,6 +46,7 @@
 	snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d:%.2x",
 			ds->index, ds->pd->sw_addr);
 	ds->slave_mii_bus->parent = ds->master_dev;
+	ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask;
 }
 
 
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 3a83ce5..787b3c2 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -129,7 +129,8 @@
 	 *	We now generate an ICMP HOST REDIRECT giving the route
 	 *	we calculated.
 	 */
-	if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
+	if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
+	    !skb_sec_path(skb))
 		ip_rt_send_redirect(skb);
 
 	skb->priority = rt_tos2priority(iph->tos);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index c0d82f7..2a3720f 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -966,8 +966,11 @@
 
 	sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
 	if (sk != NULL) {
+		struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
+
 		pr_debug("rcv on socket %p\n", sk);
-		ping_queue_rcv_skb(sk, skb_get(skb));
+		if (skb2)
+			ping_queue_rcv_skb(sk, skb2);
 		sock_put(sk);
 		return true;
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6a2155b..d58dd0e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1554,11 +1554,10 @@
 
 	do_cache = res->fi && !itag;
 	if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
+	    skb->protocol == htons(ETH_P_IP) &&
 	    (IN_DEV_SHARED_MEDIA(out_dev) ||
-	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
-		flags |= RTCF_DOREDIRECT;
-		do_cache = false;
-	}
+	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+		IPCB(skb)->flags |= IPSKB_DOREDIRECT;
 
 	if (skb->protocol != htons(ETH_P_IP)) {
 		/* Not IP (i.e. ARP). Do not create route, if it is
@@ -2303,6 +2302,8 @@
 	r->rtm_flags	= (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
 	if (rt->rt_flags & RTCF_NOTIFY)
 		r->rtm_flags |= RTM_F_NOTIFY;
+	if (IPCB(skb)->flags & IPSKB_DOREDIRECT)
+		r->rtm_flags |= RTCF_DOREDIRECT;
 
 	if (nla_put_be32(skb, RTA_DST, dst))
 		goto nla_put_failure;
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 7927db0..4a000f1 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -99,11 +99,13 @@
 	s_slot = cb->args[0];
 	num = s_num = cb->args[1];
 
-	for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) {
+	for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) {
 		struct sock *sk;
 		struct hlist_nulls_node *node;
 		struct udp_hslot *hslot = &table->hash[slot];
 
+		num = 0;
+
 		if (hlist_nulls_empty(&hslot->head))
 			continue;
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index b2d1838..f1c6d5e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -659,6 +659,29 @@
 	return 0;
 }
 
+static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
+			  struct net *net)
+{
+	if (atomic_read(&rt->rt6i_ref) != 1) {
+		/* This route is used as dummy address holder in some split
+		 * nodes. It is not leaked, but it still holds other resources,
+		 * which must be released in time. So, scan ascendant nodes
+		 * and replace dummy references to this route with references
+		 * to still alive ones.
+		 */
+		while (fn) {
+			if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
+				fn->leaf = fib6_find_prefix(net, fn);
+				atomic_inc(&fn->leaf->rt6i_ref);
+				rt6_release(rt);
+			}
+			fn = fn->parent;
+		}
+		/* No more references are possible at this point. */
+		BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
+	}
+}
+
 /*
  *	Insert routing information in a node.
  */
@@ -807,11 +830,12 @@
 		rt->dst.rt6_next = iter->dst.rt6_next;
 		atomic_inc(&rt->rt6i_ref);
 		inet6_rt_notify(RTM_NEWROUTE, rt, info);
-		rt6_release(iter);
 		if (!(fn->fn_flags & RTN_RTINFO)) {
 			info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
 			fn->fn_flags |= RTN_RTINFO;
 		}
+		fib6_purge_rt(iter, fn, info->nl_net);
+		rt6_release(iter);
 	}
 
 	return 0;
@@ -1322,24 +1346,7 @@
 		fn = fib6_repair_tree(net, fn);
 	}
 
-	if (atomic_read(&rt->rt6i_ref) != 1) {
-		/* This route is used as dummy address holder in some split
-		 * nodes. It is not leaked, but it still holds other resources,
-		 * which must be released in time. So, scan ascendant nodes
-		 * and replace dummy references to this route with references
-		 * to still alive ones.
-		 */
-		while (fn) {
-			if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
-				fn->leaf = fib6_find_prefix(net, fn);
-				atomic_inc(&fn->leaf->rt6i_ref);
-				rt6_release(rt);
-			}
-			fn = fn->parent;
-		}
-		/* No more references are possible at this point. */
-		BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
-	}
+	fib6_purge_rt(rt, fn, net);
 
 	inet6_rt_notify(RTM_DELROUTE, rt, info);
 	rt6_release(rt);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 166e33b..49596535 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1242,12 +1242,16 @@
 		rt = net->ipv6.ip6_null_entry;
 	else if (rt->dst.error) {
 		rt = net->ipv6.ip6_null_entry;
-	} else if (rt == net->ipv6.ip6_null_entry) {
+		goto out;
+	}
+
+	if (rt == net->ipv6.ip6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
 			goto restart;
 	}
 
+out:
 	dst_hold(&rt->dst);
 
 	read_unlock_bh(&table->tb6_lock);
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 5f98364..48bf5a0 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -130,12 +130,18 @@
 {
 	struct flowi6 *fl6 = &fl->u.ip6;
 	int onlyproto = 0;
-	u16 offset = skb_network_header_len(skb);
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
+	u16 offset = sizeof(*hdr);
 	struct ipv6_opt_hdr *exthdr;
 	const unsigned char *nh = skb_network_header(skb);
-	u8 nexthdr = nh[IP6CB(skb)->nhoff];
+	u16 nhoff = IP6CB(skb)->nhoff;
 	int oif = 0;
+	u8 nexthdr;
+
+	if (!nhoff)
+		nhoff = offsetof(struct ipv6hdr, nexthdr);
+
+	nexthdr = nh[nhoff];
 
 	if (skb_dst(skb))
 		oif = skb_dst(skb)->dev->ifindex;
diff --git a/net/llc/sysctl_net_llc.c b/net/llc/sysctl_net_llc.c
index 612a5dd..799bafc 100644
--- a/net/llc/sysctl_net_llc.c
+++ b/net/llc/sysctl_net_llc.c
@@ -18,28 +18,28 @@
 	{
 		.procname	= "ack",
 		.data		= &sysctl_llc2_ack_timeout,
-		.maxlen		= sizeof(long),
+		.maxlen		= sizeof(sysctl_llc2_ack_timeout),
 		.mode		= 0644,
 		.proc_handler   = proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "busy",
 		.data		= &sysctl_llc2_busy_timeout,
-		.maxlen		= sizeof(long),
+		.maxlen		= sizeof(sysctl_llc2_busy_timeout),
 		.mode		= 0644,
 		.proc_handler   = proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "p",
 		.data		= &sysctl_llc2_p_timeout,
-		.maxlen		= sizeof(long),
+		.maxlen		= sizeof(sysctl_llc2_p_timeout),
 		.mode		= 0644,
 		.proc_handler   = proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "rej",
 		.data		= &sysctl_llc2_rej_timeout,
-		.maxlen		= sizeof(long),
+		.maxlen		= sizeof(sysctl_llc2_rej_timeout),
 		.mode		= 0644,
 		.proc_handler   = proc_dointvec_jiffies,
 	},
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 4c5192e..4a95fe3 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -86,20 +86,6 @@
 		}
 	}
 
-	/* tear down aggregation sessions and remove STAs */
-	mutex_lock(&local->sta_mtx);
-	list_for_each_entry(sta, &local->sta_list, list) {
-		if (sta->uploaded) {
-			enum ieee80211_sta_state state;
-
-			state = sta->sta_state;
-			for (; state > IEEE80211_STA_NOTEXIST; state--)
-				WARN_ON(drv_sta_state(local, sta->sdata, sta,
-						      state, state - 1));
-		}
-	}
-	mutex_unlock(&local->sta_mtx);
-
 	/* remove all interfaces that were created in the driver */
 	list_for_each_entry(sdata, &local->interfaces, list) {
 		if (!ieee80211_sdata_running(sdata))
@@ -111,6 +97,21 @@
 		case NL80211_IFTYPE_STATION:
 			ieee80211_mgd_quiesce(sdata);
 			break;
+		case NL80211_IFTYPE_WDS:
+			/* tear down aggregation sessions and remove STAs */
+			mutex_lock(&local->sta_mtx);
+			sta = sdata->u.wds.sta;
+			if (sta && sta->uploaded) {
+				enum ieee80211_sta_state state;
+
+				state = sta->sta_state;
+				for (; state > IEEE80211_STA_NOTEXIST; state--)
+					WARN_ON(drv_sta_state(local, sta->sdata,
+							      sta, state,
+							      state - 1));
+			}
+			mutex_unlock(&local->sta_mtx);
+			break;
 		default:
 			break;
 		}
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 683b10f..d69ca51 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -272,7 +272,7 @@
 	else if (rate && rate->flags & IEEE80211_RATE_ERP_G)
 		channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ;
 	else if (rate)
-		channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ;
+		channel_flags |= IEEE80211_CHAN_CCK | IEEE80211_CHAN_2GHZ;
 	else
 		channel_flags |= IEEE80211_CHAN_2GHZ;
 	put_unaligned_le16(channel_flags, pos);
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 84c8219..f59adf8 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -180,6 +180,11 @@
 	}
 
 	bpf_size = bpf_len * sizeof(*bpf_ops);
+	if (bpf_size != nla_len(tb[TCA_BPF_OPS])) {
+		ret = -EINVAL;
+		goto errout;
+	}
+
 	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
 	if (bpf_ops == NULL) {
 		ret = -ENOMEM;
@@ -215,15 +220,21 @@
 				   struct cls_bpf_head *head)
 {
 	unsigned int i = 0x80000000;
+	u32 handle;
 
 	do {
 		if (++head->hgen == 0x7FFFFFFF)
 			head->hgen = 1;
 	} while (--i > 0 && cls_bpf_get(tp, head->hgen));
-	if (i == 0)
-		pr_err("Insufficient number of handles\n");
 
-	return i;
+	if (unlikely(i == 0)) {
+		pr_err("Insufficient number of handles\n");
+		handle = 0;
+	} else {
+		handle = head->hgen;
+	}
+
+	return handle;
 }
 
 static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index f791edd..26d06db 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1182,7 +1182,6 @@
 	asoc->peer.peer_hmacs = new->peer.peer_hmacs;
 	new->peer.peer_hmacs = NULL;
 
-	sctp_auth_key_put(asoc->asoc_shared_key);
 	sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC);
 }
 
diff --git a/net/socket.c b/net/socket.c
index a2c33a4..418795c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -869,9 +869,6 @@
 static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb,
 					 struct sock_iocb *siocb)
 {
-	if (!is_sync_kiocb(iocb))
-		BUG();
-
 	siocb->kiocb = iocb;
 	iocb->private = siocb;
 	return siocb;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 7ca4b51..8887c6e 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2854,6 +2854,9 @@
 	if (!rdev->ops->get_key)
 		return -EOPNOTSUPP;
 
+	if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
+		return -ENOENT;
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
@@ -2873,10 +2876,6 @@
 	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr))
 		goto nla_put_failure;
 
-	if (pairwise && mac_addr &&
-	    !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
-		return -ENOENT;
-
 	err = rdev_get_key(rdev, dev, key_idx, pairwise, mac_addr, &cookie,
 			   get_key_callback);
 
@@ -3047,7 +3046,7 @@
 	wdev_lock(dev->ieee80211_ptr);
 	err = nl80211_key_allowed(dev->ieee80211_ptr);
 
-	if (key.type == NL80211_KEYTYPE_PAIRWISE && mac_addr &&
+	if (key.type == NL80211_KEYTYPE_GROUP && mac_addr &&
 	    !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
 		err = -ENOENT;
 
diff --git a/net/wireless/util.c b/net/wireless/util.c
index d0ac795..5488c36 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -308,6 +308,12 @@
 		goto out;
 	}
 
+	if (ieee80211_is_mgmt(fc)) {
+		if (ieee80211_has_order(fc))
+			hdrlen += IEEE80211_HT_CTL_LEN;
+		goto out;
+	}
+
 	if (ieee80211_is_ctl(fc)) {
 		/*
 		 * ACK and CTS are 10 bytes, all others 16. To see how
diff --git a/samples/bpf/test_maps.c b/samples/bpf/test_maps.c
index e286b42..6299ee9 100644
--- a/samples/bpf/test_maps.c
+++ b/samples/bpf/test_maps.c
@@ -69,9 +69,9 @@
 
 	/* iterate over two elements */
 	assert(bpf_get_next_key(map_fd, &key, &next_key) == 0 &&
-	       next_key == 2);
+	       (next_key == 1 || next_key == 2));
 	assert(bpf_get_next_key(map_fd, &next_key, &next_key) == 0 &&
-	       next_key == 1);
+	       (next_key == 1 || next_key == 2));
 	assert(bpf_get_next_key(map_fd, &next_key, &next_key) == -1 &&
 	       errno == ENOENT);
 
diff --git a/sound/core/seq/seq_dummy.c b/sound/core/seq/seq_dummy.c
index ec667f1..5d905d9 100644
--- a/sound/core/seq/seq_dummy.c
+++ b/sound/core/seq/seq_dummy.c
@@ -82,36 +82,6 @@
 static int my_client = -1;
 
 /*
- * unuse callback - send ALL_SOUNDS_OFF and RESET_CONTROLLERS events
- * to subscribers.
- * Note: this callback is called only after all subscribers are removed.
- */
-static int
-dummy_unuse(void *private_data, struct snd_seq_port_subscribe *info)
-{
-	struct snd_seq_dummy_port *p;
-	int i;
-	struct snd_seq_event ev;
-
-	p = private_data;
-	memset(&ev, 0, sizeof(ev));
-	if (p->duplex)
-		ev.source.port = p->connect;
-	else
-		ev.source.port = p->port;
-	ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS;
-	ev.type = SNDRV_SEQ_EVENT_CONTROLLER;
-	for (i = 0; i < 16; i++) {
-		ev.data.control.channel = i;
-		ev.data.control.param = MIDI_CTL_ALL_SOUNDS_OFF;
-		snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0);
-		ev.data.control.param = MIDI_CTL_RESET_CONTROLLERS;
-		snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0);
-	}
-	return 0;
-}
-
-/*
  * event input callback - just redirect events to subscribers
  */
 static int
@@ -175,7 +145,6 @@
 		| SNDRV_SEQ_PORT_TYPE_PORT;
 	memset(&pcb, 0, sizeof(pcb));
 	pcb.owner = THIS_MODULE;
-	pcb.unuse = dummy_unuse;
 	pcb.event_input = dummy_input;
 	pcb.private_free = dummy_free;
 	pcb.private_data = rec;
diff --git a/sound/soc/adi/axi-i2s.c b/sound/soc/adi/axi-i2s.c
index 7752860..4c23381 100644
--- a/sound/soc/adi/axi-i2s.c
+++ b/sound/soc/adi/axi-i2s.c
@@ -240,6 +240,8 @@
 	if (ret)
 		goto err_clk_disable;
 
+	return 0;
+
 err_clk_disable:
 	clk_disable_unprepare(i2s->clk);
 	return ret;
diff --git a/sound/soc/codecs/pcm512x.c b/sound/soc/codecs/pcm512x.c
index e5f2fb8..30c673c 100644
--- a/sound/soc/codecs/pcm512x.c
+++ b/sound/soc/codecs/pcm512x.c
@@ -188,8 +188,8 @@
 static const char * const pcm512x_dsp_program_texts[] = {
 	"FIR interpolation with de-emphasis",
 	"Low latency IIR with de-emphasis",
-	"Fixed process flow",
 	"High attenuation with de-emphasis",
+	"Fixed process flow",
 	"Ringing-less low latency FIR",
 };
 
diff --git a/sound/soc/codecs/rt286.c b/sound/soc/codecs/rt286.c
index 2cd4fe4..1d1c7f8 100644
--- a/sound/soc/codecs/rt286.c
+++ b/sound/soc/codecs/rt286.c
@@ -861,10 +861,8 @@
 		RT286_I2S_CTRL1, 0x0018, d_len_code << 3);
 	dev_dbg(codec->dev, "format val = 0x%x\n", val);
 
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		snd_soc_update_bits(codec, RT286_DAC_FORMAT, 0x407f, val);
-	else
-		snd_soc_update_bits(codec, RT286_ADC_FORMAT, 0x407f, val);
+	snd_soc_update_bits(codec, RT286_DAC_FORMAT, 0x407f, val);
+	snd_soc_update_bits(codec, RT286_ADC_FORMAT, 0x407f, val);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index c0fbe18..918ada9 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -2083,10 +2083,14 @@
 	struct rt5677_priv *rt5677 = snd_soc_codec_get_drvdata(codec);
 
 	switch (event) {
-	case SND_SOC_DAPM_POST_PMU:
+	case SND_SOC_DAPM_PRE_PMU:
 		regmap_update_bits(rt5677->regmap, RT5677_PLL1_CTRL2, 0x2, 0x2);
+		break;
+
+	case SND_SOC_DAPM_POST_PMU:
 		regmap_update_bits(rt5677->regmap, RT5677_PLL1_CTRL2, 0x2, 0x0);
 		break;
+
 	default:
 		return 0;
 	}
@@ -2101,10 +2105,14 @@
 	struct rt5677_priv *rt5677 = snd_soc_codec_get_drvdata(codec);
 
 	switch (event) {
-	case SND_SOC_DAPM_POST_PMU:
+	case SND_SOC_DAPM_PRE_PMU:
 		regmap_update_bits(rt5677->regmap, RT5677_PLL2_CTRL2, 0x2, 0x2);
+		break;
+
+	case SND_SOC_DAPM_POST_PMU:
 		regmap_update_bits(rt5677->regmap, RT5677_PLL2_CTRL2, 0x2, 0x0);
 		break;
+
 	default:
 		return 0;
 	}
@@ -2212,9 +2220,11 @@
 
 static const struct snd_soc_dapm_widget rt5677_dapm_widgets[] = {
 	SND_SOC_DAPM_SUPPLY("PLL1", RT5677_PWR_ANLG2, RT5677_PWR_PLL1_BIT,
-		0, rt5677_set_pll1_event, SND_SOC_DAPM_POST_PMU),
+		0, rt5677_set_pll1_event, SND_SOC_DAPM_PRE_PMU |
+		SND_SOC_DAPM_POST_PMU),
 	SND_SOC_DAPM_SUPPLY("PLL2", RT5677_PWR_ANLG2, RT5677_PWR_PLL2_BIT,
-		0, rt5677_set_pll2_event, SND_SOC_DAPM_POST_PMU),
+		0, rt5677_set_pll2_event, SND_SOC_DAPM_PRE_PMU |
+		SND_SOC_DAPM_POST_PMU),
 
 	/* Input Side */
 	/* micbias */
diff --git a/sound/soc/codecs/ts3a227e.c b/sound/soc/codecs/ts3a227e.c
index 1d12057..9f2dced 100644
--- a/sound/soc/codecs/ts3a227e.c
+++ b/sound/soc/codecs/ts3a227e.c
@@ -254,6 +254,7 @@
 	struct ts3a227e *ts3a227e;
 	struct device *dev = &i2c->dev;
 	int ret;
+	unsigned int acc_reg;
 
 	ts3a227e = devm_kzalloc(&i2c->dev, sizeof(*ts3a227e), GFP_KERNEL);
 	if (ts3a227e == NULL)
@@ -283,6 +284,11 @@
 			   INTB_DISABLE | ADC_COMPLETE_INT_DISABLE,
 			   ADC_COMPLETE_INT_DISABLE);
 
+	/* Read jack status because chip might not trigger interrupt at boot. */
+	regmap_read(ts3a227e->regmap, TS3A227E_REG_ACCESSORY_STATUS, &acc_reg);
+	ts3a227e_new_jack_state(ts3a227e, acc_reg);
+	ts3a227e_jack_report(ts3a227e);
+
 	return 0;
 }
 
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index 4d2d2b1..75b87c5 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -1076,10 +1076,13 @@
 	{ "Right Capture PGA", NULL, "Right Capture Mux" },
 	{ "Right Capture PGA", NULL, "Right Capture Inverting Mux" },
 
-	{ "AIFOUTL", "Left",  "ADCL" },
-	{ "AIFOUTL", "Right", "ADCR" },
-	{ "AIFOUTR", "Left",  "ADCL" },
-	{ "AIFOUTR", "Right", "ADCR" },
+	{ "AIFOUTL Mux", "Left", "ADCL" },
+	{ "AIFOUTL Mux", "Right", "ADCR" },
+	{ "AIFOUTR Mux", "Left", "ADCL" },
+	{ "AIFOUTR Mux", "Right", "ADCR" },
+
+	{ "AIFOUTL", NULL, "AIFOUTL Mux" },
+	{ "AIFOUTR", NULL, "AIFOUTR Mux" },
 
 	{ "ADCL", NULL, "CLK_DSP" },
 	{ "ADCL", NULL, "Left Capture PGA" },
@@ -1089,12 +1092,16 @@
 };
 
 static const struct snd_soc_dapm_route dac_intercon[] = {
-	{ "DACL", "Right", "AIFINR" },
-	{ "DACL", "Left",  "AIFINL" },
+	{ "DACL Mux", "Left", "AIFINL" },
+	{ "DACL Mux", "Right", "AIFINR" },
+
+	{ "DACR Mux", "Left", "AIFINL" },
+	{ "DACR Mux", "Right", "AIFINR" },
+
+	{ "DACL", NULL, "DACL Mux" },
 	{ "DACL", NULL, "CLK_DSP" },
 
-	{ "DACR", "Right", "AIFINR" },
-	{ "DACR", "Left",  "AIFINL" },
+	{ "DACR", NULL, "DACR Mux" },
 	{ "DACR", NULL, "CLK_DSP" },
 
 	{ "Charge pump", NULL, "SYSCLK" },
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index 031a1ae..a96eb49 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -556,7 +556,7 @@
 	{ 22050, 2 },
 	{ 24000, 2 },
 	{ 16000, 3 },
-	{ 11250, 4 },
+	{ 11025, 4 },
 	{ 12000, 4 },
 	{  8000, 5 },
 };
diff --git a/sound/soc/fsl/fsl_esai.h b/sound/soc/fsl/fsl_esai.h
index 91a550f..5e793bb 100644
--- a/sound/soc/fsl/fsl_esai.h
+++ b/sound/soc/fsl/fsl_esai.h
@@ -302,7 +302,7 @@
 #define ESAI_xCCR_xFP_MASK	(((1 << ESAI_xCCR_xFP_WIDTH) - 1) << ESAI_xCCR_xFP_SHIFT)
 #define ESAI_xCCR_xFP(v)	((((v) - 1) << ESAI_xCCR_xFP_SHIFT) & ESAI_xCCR_xFP_MASK)
 #define ESAI_xCCR_xDC_SHIFT     9
-#define ESAI_xCCR_xDC_WIDTH	4
+#define ESAI_xCCR_xDC_WIDTH	5
 #define ESAI_xCCR_xDC_MASK	(((1 << ESAI_xCCR_xDC_WIDTH) - 1) << ESAI_xCCR_xDC_SHIFT)
 #define ESAI_xCCR_xDC(v)	((((v) - 1) << ESAI_xCCR_xDC_SHIFT) & ESAI_xCCR_xDC_MASK)
 #define ESAI_xCCR_xPSR_SHIFT	8
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index a65f17d..059496e 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -1362,9 +1362,9 @@
 	}
 
 	ssi_private->irq = platform_get_irq(pdev, 0);
-	if (!ssi_private->irq) {
+	if (ssi_private->irq < 0) {
 		dev_err(&pdev->dev, "no irq for node %s\n", np->full_name);
-		return -ENXIO;
+		return ssi_private->irq;
 	}
 
 	/* Are the RX and the TX clocks locked? */
diff --git a/sound/soc/fsl/imx-wm8962.c b/sound/soc/fsl/imx-wm8962.c
index 4caacb0..cd146d4 100644
--- a/sound/soc/fsl/imx-wm8962.c
+++ b/sound/soc/fsl/imx-wm8962.c
@@ -257,6 +257,7 @@
 	if (ret)
 		goto clk_fail;
 	data->card.num_links = 1;
+	data->card.owner = THIS_MODULE;
 	data->card.dai_link = &data->dai;
 	data->card.dapm_widgets = imx_wm8962_dapm_widgets;
 	data->card.num_dapm_widgets = ARRAY_SIZE(imx_wm8962_dapm_widgets);
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index fb9240f..7fe3009 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -452,9 +452,8 @@
 }
 
 /* Decrease the reference count of the device nodes */
-static int asoc_simple_card_unref(struct platform_device *pdev)
+static int asoc_simple_card_unref(struct snd_soc_card *card)
 {
-	struct snd_soc_card *card = platform_get_drvdata(pdev);
 	struct snd_soc_dai_link *dai_link;
 	int num_links;
 
@@ -556,7 +555,7 @@
 		return ret;
 
 err:
-	asoc_simple_card_unref(pdev);
+	asoc_simple_card_unref(&priv->snd_card);
 	return ret;
 }
 
@@ -572,7 +571,7 @@
 		snd_soc_jack_free_gpios(&simple_card_mic_jack, 1,
 					&simple_card_mic_jack_gpio);
 
-	return asoc_simple_card_unref(pdev);
+	return asoc_simple_card_unref(card);
 }
 
 static const struct of_device_id asoc_simple_of_match[] = {
diff --git a/sound/soc/intel/sst-firmware.c b/sound/soc/intel/sst-firmware.c
index ef2e8b5..b3f9489 100644
--- a/sound/soc/intel/sst-firmware.c
+++ b/sound/soc/intel/sst-firmware.c
@@ -706,6 +706,7 @@
 	struct list_head *block_list)
 {
 	struct sst_mem_block *block, *tmp;
+	struct sst_block_allocator ba_tmp = *ba;
 	u32 end = ba->offset + ba->size, block_end;
 	int err;
 
@@ -730,9 +731,9 @@
 		if (ba->offset >= block->offset && ba->offset < block_end) {
 
 			/* align ba to block boundary */
-			ba->size -= block_end - ba->offset;
-			ba->offset = block_end;
-			err = block_alloc_contiguous(dsp, ba, block_list);
+			ba_tmp.size -= block_end - ba->offset;
+			ba_tmp.offset = block_end;
+			err = block_alloc_contiguous(dsp, &ba_tmp, block_list);
 			if (err < 0)
 				return -ENOMEM;
 
@@ -767,10 +768,10 @@
 			list_move(&block->list, &dsp->used_block_list);
 			list_add(&block->module_list, block_list);
 			/* align ba to block boundary */
-			ba->size -= block_end - ba->offset;
-			ba->offset = block_end;
+			ba_tmp.size -= block_end - ba->offset;
+			ba_tmp.offset = block_end;
 
-			err = block_alloc_contiguous(dsp, ba, block_list);
+			err = block_alloc_contiguous(dsp, &ba_tmp, block_list);
 			if (err < 0)
 				return -ENOMEM;
 
diff --git a/sound/soc/intel/sst-haswell-ipc.c b/sound/soc/intel/sst-haswell-ipc.c
index 3f8c482..5bf1404 100644
--- a/sound/soc/intel/sst-haswell-ipc.c
+++ b/sound/soc/intel/sst-haswell-ipc.c
@@ -1228,6 +1228,11 @@
 	struct sst_dsp *sst = hsw->dsp;
 	unsigned long flags;
 
+	if (!stream) {
+		dev_warn(hsw->dev, "warning: stream is NULL, no stream to free, ignore it.\n");
+		return 0;
+	}
+
 	/* dont free DSP streams that are not commited */
 	if (!stream->commited)
 		goto out;
@@ -1415,6 +1420,16 @@
 	u32 header;
 	int ret;
 
+	if (!stream) {
+		dev_warn(hsw->dev, "warning: stream is NULL, no stream to commit, ignore it.\n");
+		return 0;
+	}
+
+	if (stream->commited) {
+		dev_warn(hsw->dev, "warning: stream is already committed, ignore it.\n");
+		return 0;
+	}
+
 	trace_ipc_request("stream alloc", stream->host_id);
 
 	header = IPC_GLB_TYPE(IPC_GLB_ALLOCATE_STREAM);
@@ -1519,6 +1534,11 @@
 {
 	int ret;
 
+	if (!stream) {
+		dev_warn(hsw->dev, "warning: stream is NULL, no stream to pause, ignore it.\n");
+		return 0;
+	}
+
 	trace_ipc_request("stream pause", stream->reply.stream_hw_id);
 
 	ret = sst_hsw_stream_operations(hsw, IPC_STR_PAUSE,
@@ -1535,6 +1555,11 @@
 {
 	int ret;
 
+	if (!stream) {
+		dev_warn(hsw->dev, "warning: stream is NULL, no stream to resume, ignore it.\n");
+		return 0;
+	}
+
 	trace_ipc_request("stream resume", stream->reply.stream_hw_id);
 
 	ret = sst_hsw_stream_operations(hsw, IPC_STR_RESUME,
@@ -1550,6 +1575,11 @@
 {
 	int ret, tries = 10;
 
+	if (!stream) {
+		dev_warn(hsw->dev, "warning: stream is NULL, no stream to reset, ignore it.\n");
+		return 0;
+	}
+
 	/* dont reset streams that are not commited */
 	if (!stream->commited)
 		return 0;
diff --git a/sound/soc/omap/omap-mcbsp.c b/sound/soc/omap/omap-mcbsp.c
index 8b79cafa..c7eb9dd 100644
--- a/sound/soc/omap/omap-mcbsp.c
+++ b/sound/soc/omap/omap-mcbsp.c
@@ -434,7 +434,7 @@
 	case SND_SOC_DAIFMT_CBM_CFS:
 		/* McBSP slave. FS clock as output */
 		regs->srgr2	|= FSGM;
-		regs->pcr0	|= FSXM;
+		regs->pcr0	|= FSXM | FSRM;
 		break;
 	case SND_SOC_DAIFMT_CBM_CFM:
 		/* McBSP slave */
diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c
index 13d8507..dcc26ed 100644
--- a/sound/soc/rockchip/rockchip_i2s.c
+++ b/sound/soc/rockchip/rockchip_i2s.c
@@ -335,6 +335,7 @@
 			    SNDRV_PCM_FMTBIT_S24_LE),
 	},
 	.ops = &rockchip_i2s_dai_ops,
+	.symmetric_rates = 1,
 };
 
 static const struct snd_soc_component_driver rockchip_i2s_component = {
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index 590a82f..025c38f 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -659,7 +659,8 @@
 			rtd->dai_link->stream_name);
 
 		ret = snd_pcm_new_internal(rtd->card->snd_card, new_name, num,
-				1, 0, &be_pcm);
+				rtd->dai_link->dpcm_playback,
+				rtd->dai_link->dpcm_capture, &be_pcm);
 		if (ret < 0) {
 			dev_err(rtd->card->dev, "ASoC: can't create compressed for %s\n",
 				rtd->dai_link->name);
@@ -668,8 +669,10 @@
 
 		rtd->pcm = be_pcm;
 		rtd->fe_compr = 1;
-		be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd;
-		be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd;
+		if (rtd->dai_link->dpcm_playback)
+			be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd;
+		else if (rtd->dai_link->dpcm_capture)
+			be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd;
 		memcpy(compr->ops, &soc_compr_dyn_ops, sizeof(soc_compr_dyn_ops));
 	} else
 		memcpy(compr->ops, &soc_compr_ops, sizeof(soc_compr_ops));
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
index 790ceba..28431d1 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
@@ -5,7 +5,10 @@
  *	ANY CHANGES MADE HERE WILL BE LOST! 
  *
  */
-
+#include <stdbool.h>
+#ifndef HAS_BOOL
+# define HAS_BOOL 1
+#endif
 #line 1 "Context.xs"
 /*
  * Context.xs.  XS interfaces for perf script.
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 79999ce..01bc4e2 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -177,14 +177,17 @@
 		goto out_free_ops;
 
 	ops->locked.ins = ins__find(name);
+	free(name);
+
 	if (ops->locked.ins == NULL)
 		goto out_free_ops;
 
 	if (!ops->locked.ins->ops)
 		return 0;
 
-	if (ops->locked.ins->ops->parse)
-		ops->locked.ins->ops->parse(ops->locked.ops);
+	if (ops->locked.ins->ops->parse &&
+	    ops->locked.ins->ops->parse(ops->locked.ops) < 0)
+		goto out_free_ops;
 
 	return 0;
 
@@ -208,6 +211,13 @@
 
 static void lock__delete(struct ins_operands *ops)
 {
+	struct ins *ins = ops->locked.ins;
+
+	if (ins && ins->ops->free)
+		ins->ops->free(ops->locked.ops);
+	else
+		ins__delete(ops->locked.ops);
+
 	zfree(&ops->locked.ops);
 	zfree(&ops->target.raw);
 	zfree(&ops->target.name);
@@ -531,8 +541,8 @@
 	if (!dl->ins->ops)
 		return;
 
-	if (dl->ins->ops->parse)
-		dl->ins->ops->parse(&dl->ops);
+	if (dl->ins->ops->parse && dl->ins->ops->parse(&dl->ops) < 0)
+		dl->ins = NULL;
 }
 
 static int disasm_line__parse(char *line, char **namep, char **rawp)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index cbab1fb..2e507b5 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1445,7 +1445,7 @@
 	case ENOENT:
 		scnprintf(buf, size, "%s",
 			  "Error:\tUnable to find debugfs\n"
-			  "Hint:\tWas your kernel was compiled with debugfs support?\n"
+			  "Hint:\tWas your kernel compiled with debugfs support?\n"
 			  "Hint:\tIs the debugfs filesystem mounted?\n"
 			  "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
 		break;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 6951a9d..0e42438 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -116,6 +116,22 @@
 #define map__for_each_symbol(map, pos, n)	\
 	dso__for_each_symbol(map->dso, pos, n, map->type)
 
+/* map__for_each_symbol_with_name - iterate over the symbols in the given map
+ *                                  that have the given name
+ *
+ * @map: the 'struct map *' in which symbols itereated
+ * @sym_name: the symbol name
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @filter: to use when loading the DSO
+ */
+#define __map__for_each_symbol_by_name(map, sym_name, pos, filter)	\
+	for (pos = map__find_symbol_by_name(map, sym_name, filter);	\
+	     pos && strcmp(pos->name, sym_name) == 0;		\
+	     pos = symbol__next_by_name(pos))
+
+#define map__for_each_symbol_by_name(map, sym_name, pos)		\
+	__map__for_each_symbol_by_name(map, sym_name, (pos), NULL)
+
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 void map__init(struct map *map, enum map_type type,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 94a717b..919937e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -446,7 +446,7 @@
 	}
 
 	for (i = 0; i < ntevs; i++) {
-		if (tevs[i].point.address) {
+		if (tevs[i].point.address && !tevs[i].point.retprobe) {
 			tmp = strdup(reloc_sym->name);
 			if (!tmp)
 				return -ENOMEM;
@@ -2193,18 +2193,17 @@
 	return ret;
 }
 
-static char *looking_function_name;
-static int num_matched_functions;
-
-static int probe_function_filter(struct map *map __maybe_unused,
-				      struct symbol *sym)
+static int find_probe_functions(struct map *map, char *name)
 {
-	if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
-	    strcmp(looking_function_name, sym->name) == 0) {
-		num_matched_functions++;
-		return 0;
+	int found = 0;
+	struct symbol *sym;
+
+	map__for_each_symbol_by_name(map, name, sym) {
+		if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL)
+			found++;
 	}
-	return 1;
+
+	return found;
 }
 
 #define strdup_or_goto(str, label)	\
@@ -2222,10 +2221,10 @@
 	struct kmap *kmap = NULL;
 	struct ref_reloc_sym *reloc_sym = NULL;
 	struct symbol *sym;
-	struct rb_node *nd;
 	struct probe_trace_event *tev;
 	struct perf_probe_point *pp = &pev->point;
 	struct probe_trace_point *tp;
+	int num_matched_functions;
 	int ret, i;
 
 	/* Init maps of given executable or kernel */
@@ -2242,10 +2241,8 @@
 	 * Load matched symbols: Since the different local symbols may have
 	 * same name but different addresses, this lists all the symbols.
 	 */
-	num_matched_functions = 0;
-	looking_function_name = pp->function;
-	ret = map__load(map, probe_function_filter);
-	if (ret || num_matched_functions == 0) {
+	num_matched_functions = find_probe_functions(map, pp->function);
+	if (num_matched_functions == 0) {
 		pr_err("Failed to find symbol %s in %s\n", pp->function,
 			target ? : "kernel");
 		ret = -ENOENT;
@@ -2257,7 +2254,7 @@
 		goto out;
 	}
 
-	if (!pev->uprobes) {
+	if (!pev->uprobes && !pp->retprobe) {
 		kmap = map__kmap(map);
 		reloc_sym = kmap->ref_reloc_sym;
 		if (!reloc_sym) {
@@ -2275,7 +2272,8 @@
 	}
 
 	ret = 0;
-	map__for_each_symbol(map, sym, nd) {
+
+	map__for_each_symbol_by_name(map, pp->function, sym) {
 		tev = (*tevs) + ret;
 		tp = &tev->point;
 		if (ret == num_matched_functions) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c24c5b8..a194702 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -396,6 +396,7 @@
 					    const char *name)
 {
 	struct rb_node *n;
+	struct symbol_name_rb_node *s;
 
 	if (symbols == NULL)
 		return NULL;
@@ -403,7 +404,6 @@
 	n = symbols->rb_node;
 
 	while (n) {
-		struct symbol_name_rb_node *s;
 		int cmp;
 
 		s = rb_entry(n, struct symbol_name_rb_node, rb_node);
@@ -414,10 +414,24 @@
 		else if (cmp > 0)
 			n = n->rb_right;
 		else
-			return &s->sym;
+			break;
 	}
 
-	return NULL;
+	if (n == NULL)
+		return NULL;
+
+	/* return first symbol that has same name (if any) */
+	for (n = rb_prev(n); n; n = rb_prev(n)) {
+		struct symbol_name_rb_node *tmp;
+
+		tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
+		if (strcmp(tmp->sym.name, s->sym.name))
+			break;
+
+		s = tmp;
+	}
+
+	return &s->sym;
 }
 
 struct symbol *dso__find_symbol(struct dso *dso,
@@ -436,6 +450,17 @@
 	return symbols__next(sym);
 }
 
+struct symbol *symbol__next_by_name(struct symbol *sym)
+{
+	struct symbol_name_rb_node *s = container_of(sym, struct symbol_name_rb_node, sym);
+	struct rb_node *n = rb_next(&s->rb_node);
+
+	return n ? &rb_entry(n, struct symbol_name_rb_node, rb_node)->sym : NULL;
+}
+
+ /*
+  * Teturns first symbol that matched with @name.
+  */
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name)
 {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 9d602e9..1650dcb 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -231,6 +231,7 @@
 				u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name);
+struct symbol *symbol__next_by_name(struct symbol *sym);
 
 struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
 struct symbol *dso__next_symbol(struct symbol *sym);