Merge tag 'v3.19-rc7' into x86/asm, to refresh the branch before pulling in new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

125 files changed, 860 insertions, 482 deletions

diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c
index 076c35cd6cde..98a1525fa164 100644
--- a/arch/alpha/kernel/pci.c
+++ b/arch/alpha/kernel/pci.c
@@ -285,8 +285,12 @@ pcibios_claim_one_bus(struct pci_bus *b)
 			if (r->parent || !r->start || !r->flags)
 				continue;
 			if (pci_has_flag(PCI_PROBE_ONLY) ||
-			    (r->flags & IORESOURCE_PCI_FIXED))
-				pci_claim_resource(dev, i);
+			    (r->flags & IORESOURCE_PCI_FIXED)) {
+				if (pci_claim_resource(dev, i) == 0)
+					continue;
+
+				pci_claim_bridge_resource(dev, i);
+			}
 		}
 	}
 
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 98838a05ba6d..9d0ac091a52a 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -156,6 +156,8 @@ retry:
 	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 6f7e3a68803a..563cb27e37f5 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -161,6 +161,8 @@ good_area:
 
 	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/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 22771bc1643a..63f8b007bdc5 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1257,6 +1257,8 @@
 				tx-fifo-resize;
 				maximum-speed = "super-speed";
 				dr_mode = "otg";
+				snps,dis_u3_susphy_quirk;
+				snps,dis_u2_susphy_quirk;
 			};
 		};
 
@@ -1278,6 +1280,8 @@
 				tx-fifo-resize;
 				maximum-speed = "high-speed";
 				dr_mode = "otg";
+				snps,dis_u3_susphy_quirk;
+				snps,dis_u2_susphy_quirk;
 			};
 		};
 
@@ -1299,6 +1303,8 @@
 				tx-fifo-resize;
 				maximum-speed = "high-speed";
 				dr_mode = "otg";
+				snps,dis_u3_susphy_quirk;
+				snps,dis_u2_susphy_quirk;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index d238676a9107..e4d3aecc4ed2 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -369,7 +369,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fa0000 0x4000>;
-				clocks = <&clks 106>, <&clks 36>;
+				clocks = <&clks 106>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <36>;
 			};
@@ -388,7 +388,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fa8000 0x4000>;
-				clocks = <&clks 107>, <&clks 36>;
+				clocks = <&clks 107>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <41>;
 			};
@@ -429,7 +429,7 @@
 			pwm4: pwm@53fc8000 {
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				reg = <0x53fc8000 0x4000>;
-				clocks = <&clks 108>, <&clks 36>;
+				clocks = <&clks 108>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <42>;
 			};
@@ -476,7 +476,7 @@
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
 				#pwm-cells = <2>;
 				reg = <0x53fe0000 0x4000>;
-				clocks = <&clks 105>, <&clks 36>;
+				clocks = <&clks 105>, <&clks 52>;
 				clock-names = "ipg", "per";
 				interrupts = <26>;
 			};
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dts b/arch/arm/boot/dts/imx6sx-sdb.dts
index 8c1febd7e3f2..c108bb451337 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 7b4099fcf817..d5c4669224b1 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 fe3c559ca6a8..bfa742817690 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 1b76667f3182..2e7d8263799d 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 eeed1f236ee8..c7be3abd9fcc 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 916ee8bb826f..3decefb3c37a 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 e31d291d14cb..b421f7fa197b 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 c35217ea1f64..c556688f8b8b 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 f47156b6572b..1e7e7bcf8307 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 1cf1214cc068..bd7b15add697 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 0e4bfa3b2b85..0bcefcbbb756 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 9d669cdf031d..66cc77707198 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 e21ce5992d56..89749ce34a84 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 7f2117ce6985..32ad80804dbb 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 0746cd1024d7..86584fcf5e32 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 506948f582ee..11ec71072e81 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 494714f67b57..9ef4438206a9 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/boot/dts/tegra20-seaboard.dts b/arch/arm/boot/dts/tegra20-seaboard.dts
index ea282c7c0ca5..e2fed2712249 100644
--- a/arch/arm/boot/dts/tegra20-seaboard.dts
+++ b/arch/arm/boot/dts/tegra20-seaboard.dts
@@ -406,7 +406,7 @@
 		clock-frequency = <400000>;
 
 		magnetometer@c {
-			compatible = "ak,ak8975";
+			compatible = "asahi-kasei,ak8975";
 			reg = <0xc>;
 			interrupt-parent = <&gpio>;
 			interrupts = <TEGRA_GPIO(N, 5) IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 66ce17655bb9..7b0152321b20 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -38,6 +38,16 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 	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 254e0650e48b..04b4ea0b550a 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -125,9 +125,6 @@ struct kvm_vcpu_arch {
 	 * 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 63e0ecc04901..1bca8f8af442 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 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 	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 @@ static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
 	 *
 	 * 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/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 4176df721bf0..1a0045abead7 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -253,21 +253,22 @@
 	.endm
 
 	.macro	restore_user_regs, fast = 0, offset = 0
-	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
-	ldr	lr, [sp, #\offset + S_PC]!	@ get pc
+	mov	r2, sp
+	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
+	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
 	msr	spsr_cxsf, r1			@ save in spsr_svc
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
 	@ We must avoid clrex due to Cortex-A15 erratum #830321
-	strex	r1, r2, [sp]			@ clear the exclusive monitor
+	strex	r1, r2, [r2]			@ clear the exclusive monitor
 #endif
 	.if	\fast
-	ldmdb	sp, {r1 - lr}^			@ get calling r1 - lr
+	ldmdb	r2, {r1 - lr}^			@ get calling r1 - lr
 	.else
-	ldmdb	sp, {r0 - lr}^			@ get calling r0 - lr
+	ldmdb	r2, {r0 - lr}^			@ get calling r0 - lr
 	.endif
 	mov	r0, r0				@ ARMv5T and earlier require a nop
 						@ after ldm {}^
-	add	sp, sp, #S_FRAME_SIZE - S_PC
+	add	sp, sp, #\offset + S_FRAME_SIZE
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 	.endm
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index f7c65adaa428..557e128e4df0 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -116,8 +116,14 @@ int armpmu_event_set_period(struct perf_event *event)
 		ret = 1;
 	}
 
-	if (left > (s64)armpmu->max_period)
-		left = armpmu->max_period;
+	/*
+	 * Limit the maximum period to prevent the counter value
+	 * from overtaking the one we are about to program. In
+	 * effect we are reducing max_period to account for
+	 * interrupt latency (and we are being very conservative).
+	 */
+	if (left > (armpmu->max_period >> 1))
+		left = armpmu->max_period >> 1;
 
 	local64_set(&hwc->prev_count, (u64)-left);
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 715ae19bc7c8..e55408e96559 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -657,10 +657,13 @@ int __init arm_add_memory(u64 start, u64 size)
 
 	/*
 	 * Ensure that start/size are aligned to a page boundary.
-	 * Size is appropriately rounded down, start is rounded up.
+	 * Size is rounded down, start is rounded up.
 	 */
-	size -= start & ~PAGE_MASK;
 	aligned_start = PAGE_ALIGN(start);
+	if (aligned_start > start + size)
+		size = 0;
+	else
+		size -= aligned_start - start;
 
 #ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT
 	if (aligned_start > ULONG_MAX) {
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 2d6d91001062..0b0d58a905c4 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -281,15 +281,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	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 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		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 7928dbdf2102..f3d88dc388bc 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -189,82 +189,40 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu,
 	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 1a44bbe39643..88d24a3a9778 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -153,8 +153,8 @@ static inline int cmp_reg(const struct coproc_reg *i1,
 #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 e6f4ae48bda9..a7136757d373 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 17fc7cd479d3..b19e46d1b2c0 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 1dc9778a00af..136662547ca6 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -58,6 +58,26 @@ static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 		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 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 	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 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
 	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 @@ static void unmap_pmds(struct kvm *kvm, pud_t *pud,
 		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 @@ static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
 		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 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
 
 	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 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
 	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 @@ static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
 	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 @@ static void stage2_flush_memslot(struct kvm *kvm,
  * 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 @@ static bool kvm_is_device_pfn(unsigned long pfn)
 	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 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			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 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			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 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	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 b1d640f78623..b6a6e7102201 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -223,6 +223,45 @@ TRACE_EVENT(kvm_hvc,
 		  __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 3585cb394e9b..ccef8806bb58 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -190,6 +190,13 @@ static void __init armada_375_380_coherency_init(struct device_node *np)
 	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
@@ -246,9 +253,14 @@ static int coherency_type(void)
 	return type;
 }
 
+/*
+ * As a precaution, we currently completely disable hardware I/O
+ * coherency, until enough testing is done with automatic I/O
+ * synchronization barriers to validate that it is a proper solution.
+ */
 int coherency_available(void)
 {
-	return coherency_type() != COHERENCY_FABRIC_TYPE_NONE;
+	return false;
 }
 
 int __init coherency_init(void)
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index db57741c9c8a..64e44d6d07c0 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -211,6 +211,7 @@ extern struct device *omap2_get_iva_device(void);
 extern struct device *omap2_get_l3_device(void);
 extern struct device *omap4_get_dsp_device(void);
 
+unsigned int omap4_xlate_irq(unsigned int hwirq);
 void omap_gic_of_init(void);
 
 #ifdef CONFIG_CACHE_L2X0
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index b7cb44abe49b..cc30e49a4cc2 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -256,6 +256,38 @@ static int __init omap4_sar_ram_init(void)
 }
 omap_early_initcall(omap4_sar_ram_init);
 
+static struct of_device_id gic_match[] = {
+	{ .compatible = "arm,cortex-a9-gic", },
+	{ .compatible = "arm,cortex-a15-gic", },
+	{ },
+};
+
+static struct device_node *gic_node;
+
+unsigned int omap4_xlate_irq(unsigned int hwirq)
+{
+	struct of_phandle_args irq_data;
+	unsigned int irq;
+
+	if (!gic_node)
+		gic_node = of_find_matching_node(NULL, gic_match);
+
+	if (WARN_ON(!gic_node))
+		return hwirq;
+
+	irq_data.np = gic_node;
+	irq_data.args_count = 3;
+	irq_data.args[0] = 0;
+	irq_data.args[1] = hwirq - OMAP44XX_IRQ_GIC_START;
+	irq_data.args[2] = IRQ_TYPE_LEVEL_HIGH;
+
+	irq = irq_create_of_mapping(&irq_data);
+	if (WARN_ON(!irq))
+		irq = hwirq;
+
+	return irq;
+}
+
 void __init omap_gic_of_init(void)
 {
 	struct device_node *np;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index cbb908dc5cf0..9025ffffd2dc 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -3534,9 +3534,15 @@ int omap_hwmod_fill_resources(struct omap_hwmod *oh, struct resource *res)
 
 	mpu_irqs_cnt = _count_mpu_irqs(oh);
 	for (i = 0; i < mpu_irqs_cnt; i++) {
+		unsigned int irq;
+
+		if (oh->xlate_irq)
+			irq = oh->xlate_irq((oh->mpu_irqs + i)->irq);
+		else
+			irq = (oh->mpu_irqs + i)->irq;
 		(res + r)->name = (oh->mpu_irqs + i)->name;
-		(res + r)->start = (oh->mpu_irqs + i)->irq;
-		(res + r)->end = (oh->mpu_irqs + i)->irq;
+		(res + r)->start = irq;
+		(res + r)->end = irq;
 		(res + r)->flags = IORESOURCE_IRQ;
 		r++;
 	}
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index 35ca6efbec31..5b42fafcaf55 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -676,6 +676,7 @@ struct omap_hwmod {
 	spinlock_t			_lock;
 	struct list_head		node;
 	struct omap_hwmod_ocp_if	*_mpu_port;
+	unsigned int			(*xlate_irq)(unsigned int);
 	u16				flags;
 	u8				mpu_rt_idx;
 	u8				response_lat;
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index c314b3c31117..f5e68a782025 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -479,6 +479,7 @@ static struct omap_hwmod omap44xx_dma_system_hwmod = {
 	.class		= &omap44xx_dma_hwmod_class,
 	.clkdm_name	= "l3_dma_clkdm",
 	.mpu_irqs	= omap44xx_dma_system_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.main_clk	= "l3_div_ck",
 	.prcm = {
 		.omap4 = {
@@ -640,6 +641,7 @@ static struct omap_hwmod omap44xx_dss_dispc_hwmod = {
 	.class		= &omap44xx_dispc_hwmod_class,
 	.clkdm_name	= "l3_dss_clkdm",
 	.mpu_irqs	= omap44xx_dss_dispc_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.sdma_reqs	= omap44xx_dss_dispc_sdma_reqs,
 	.main_clk	= "dss_dss_clk",
 	.prcm = {
@@ -693,6 +695,7 @@ static struct omap_hwmod omap44xx_dss_dsi1_hwmod = {
 	.class		= &omap44xx_dsi_hwmod_class,
 	.clkdm_name	= "l3_dss_clkdm",
 	.mpu_irqs	= omap44xx_dss_dsi1_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.sdma_reqs	= omap44xx_dss_dsi1_sdma_reqs,
 	.main_clk	= "dss_dss_clk",
 	.prcm = {
@@ -726,6 +729,7 @@ static struct omap_hwmod omap44xx_dss_dsi2_hwmod = {
 	.class		= &omap44xx_dsi_hwmod_class,
 	.clkdm_name	= "l3_dss_clkdm",
 	.mpu_irqs	= omap44xx_dss_dsi2_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.sdma_reqs	= omap44xx_dss_dsi2_sdma_reqs,
 	.main_clk	= "dss_dss_clk",
 	.prcm = {
@@ -784,6 +788,7 @@ static struct omap_hwmod omap44xx_dss_hdmi_hwmod = {
 	 */
 	.flags		= HWMOD_SWSUP_SIDLE,
 	.mpu_irqs	= omap44xx_dss_hdmi_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.sdma_reqs	= omap44xx_dss_hdmi_sdma_reqs,
 	.main_clk	= "dss_48mhz_clk",
 	.prcm = {
diff --git a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
index 3e9523084b2a..7c3fac035e93 100644
--- a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
@@ -288,6 +288,7 @@ static struct omap_hwmod omap54xx_dma_system_hwmod = {
 	.class		= &omap54xx_dma_hwmod_class,
 	.clkdm_name	= "dma_clkdm",
 	.mpu_irqs	= omap54xx_dma_system_irqs,
+	.xlate_irq	= omap4_xlate_irq,
 	.main_clk	= "l3_iclk_div",
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm/mach-omap2/prcm-common.h b/arch/arm/mach-omap2/prcm-common.h
index a8e4b582c527..6163d66102a3 100644
--- a/arch/arm/mach-omap2/prcm-common.h
+++ b/arch/arm/mach-omap2/prcm-common.h
@@ -498,6 +498,7 @@ struct omap_prcm_irq_setup {
 	u8 nr_irqs;
 	const struct omap_prcm_irq *irqs;
 	int irq;
+	unsigned int (*xlate_irq)(unsigned int);
 	void (*read_pending_irqs)(unsigned long *events);
 	void (*ocp_barrier)(void);
 	void (*save_and_clear_irqen)(u32 *saved_mask);
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index cc170fb81ff7..408c64efb807 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -49,6 +49,7 @@ static struct omap_prcm_irq_setup omap4_prcm_irq_setup = {
 	.irqs			= omap4_prcm_irqs,
 	.nr_irqs		= ARRAY_SIZE(omap4_prcm_irqs),
 	.irq			= 11 + OMAP44XX_IRQ_GIC_START,
+	.xlate_irq		= omap4_xlate_irq,
 	.read_pending_irqs	= &omap44xx_prm_read_pending_irqs,
 	.ocp_barrier		= &omap44xx_prm_ocp_barrier,
 	.save_and_clear_irqen	= &omap44xx_prm_save_and_clear_irqen,
@@ -751,8 +752,10 @@ static int omap44xx_prm_late_init(void)
 		}
 
 		/* Once OMAP4 DT is filled as well */
-		if (irq_num >= 0)
+		if (irq_num >= 0) {
 			omap4_prcm_irq_setup.irq = irq_num;
+			omap4_prcm_irq_setup.xlate_irq = NULL;
+		}
 	}
 
 	omap44xx_prm_enable_io_wakeup();
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index 779940cb6e56..dea2833ca627 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -187,6 +187,7 @@ int omap_prcm_event_to_irq(const char *name)
  */
 void omap_prcm_irq_cleanup(void)
 {
+	unsigned int irq;
 	int i;
 
 	if (!prcm_irq_setup) {
@@ -211,7 +212,11 @@ void omap_prcm_irq_cleanup(void)
 	kfree(prcm_irq_setup->priority_mask);
 	prcm_irq_setup->priority_mask = NULL;
 
-	irq_set_chained_handler(prcm_irq_setup->irq, NULL);
+	if (prcm_irq_setup->xlate_irq)
+		irq = prcm_irq_setup->xlate_irq(prcm_irq_setup->irq);
+	else
+		irq = prcm_irq_setup->irq;
+	irq_set_chained_handler(irq, NULL);
 
 	if (prcm_irq_setup->base_irq > 0)
 		irq_free_descs(prcm_irq_setup->base_irq,
@@ -259,6 +264,7 @@ int omap_prcm_register_chain_handler(struct omap_prcm_irq_setup *irq_setup)
 	int offset, i;
 	struct irq_chip_generic *gc;
 	struct irq_chip_type *ct;
+	unsigned int irq;
 
 	if (!irq_setup)
 		return -EINVAL;
@@ -298,7 +304,11 @@ int omap_prcm_register_chain_handler(struct omap_prcm_irq_setup *irq_setup)
 				1 << (offset & 0x1f);
 	}
 
-	irq_set_chained_handler(irq_setup->irq, omap_prcm_irq_handler);
+	if (irq_setup->xlate_irq)
+		irq = irq_setup->xlate_irq(irq_setup->irq);
+	else
+		irq = irq_setup->irq;
+	irq_set_chained_handler(irq, omap_prcm_irq_handler);
 
 	irq_setup->base_irq = irq_alloc_descs(-1, 0, irq_setup->nr_regs * 32,
 		0);
diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c
index 4457e731f7a4..292eca0e78ed 100644
--- a/arch/arm/mach-omap2/twl-common.c
+++ b/arch/arm/mach-omap2/twl-common.c
@@ -66,19 +66,24 @@ void __init omap_pmic_init(int bus, u32 clkrate,
 	omap_register_i2c_bus(bus, clkrate, &pmic_i2c_board_info, 1);
 }
 
+#ifdef CONFIG_ARCH_OMAP4
 void __init omap4_pmic_init(const char *pmic_type,
 		    struct twl4030_platform_data *pmic_data,
 		    struct i2c_board_info *devices, int nr_devices)
 {
 	/* PMIC part*/
+	unsigned int irq;
+
 	omap_mux_init_signal("sys_nirq1", OMAP_PIN_INPUT_PULLUP | OMAP_PIN_OFF_WAKEUPENABLE);
 	omap_mux_init_signal("fref_clk0_out.sys_drm_msecure", OMAP_PIN_OUTPUT);
-	omap_pmic_init(1, 400, pmic_type, 7 + OMAP44XX_IRQ_GIC_START, pmic_data);
+	irq = omap4_xlate_irq(7 + OMAP44XX_IRQ_GIC_START);
+	omap_pmic_init(1, 400, pmic_type, irq, pmic_data);
 
 	/* Register additional devices on i2c1 bus if needed */
 	if (devices)
 		i2c_register_board_info(1, devices, nr_devices);
 }
+#endif
 
 void __init omap_pmic_late_init(void)
 {
diff --git a/arch/arm/mach-shmobile/board-ape6evm.c b/arch/arm/mach-shmobile/board-ape6evm.c
index 66f67816a844..444f22d370f0 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 @@ static void __init ape6evm_add_standard_devices(void)
 				      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 @@ static const char *ape6evm_boards_compat_dt[] __initdata = {
 
 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 f8197eb6e566..65b128dd4072 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 @@ static void __init lager_init(void)
 					  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 @@ static const char * const lager_boards_compat_dt[] __initconst = {
 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-r8a7778.c b/arch/arm/mach-shmobile/setup-r8a7778.c
index 170bd146ba17..cef8895a9b82 100644
--- a/arch/arm/mach-shmobile/setup-r8a7778.c
+++ b/arch/arm/mach-shmobile/setup-r8a7778.c
@@ -576,11 +576,18 @@ void __init r8a7778_init_irq_extpin(int irlm)
 void __init r8a7778_init_irq_dt(void)
 {
 	void __iomem *base = ioremap_nocache(0xfe700000, 0x00100000);
+#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
+	void __iomem *gic_dist_base = ioremap_nocache(0xfe438000, 0x1000);
+	void __iomem *gic_cpu_base = ioremap_nocache(0xfe430000, 0x1000);
+#endif
 
 	BUG_ON(!base);
 
+#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
+	gic_init(0, 29, gic_dist_base, gic_cpu_base);
+#else
 	irqchip_init();
-
+#endif
 	/* route all interrupts to ARM */
 	__raw_writel(0x73ffffff, base + INT2NTSR0);
 	__raw_writel(0xffffffff, base + INT2NTSR1);
diff --git a/arch/arm/mach-shmobile/setup-r8a7779.c b/arch/arm/mach-shmobile/setup-r8a7779.c
index 6156d172cf31..27dceaf9e688 100644
--- a/arch/arm/mach-shmobile/setup-r8a7779.c
+++ b/arch/arm/mach-shmobile/setup-r8a7779.c
@@ -720,10 +720,17 @@ static int r8a7779_set_wake(struct irq_data *data, unsigned int on)
 
 void __init r8a7779_init_irq_dt(void)
 {
+#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
+	void __iomem *gic_dist_base = ioremap_nocache(0xf0001000, 0x1000);
+	void __iomem *gic_cpu_base = ioremap_nocache(0xf0000100, 0x1000);
+#endif
 	gic_arch_extn.irq_set_wake = r8a7779_set_wake;
 
+#ifdef CONFIG_ARCH_SHMOBILE_LEGACY
+	gic_init(0, 29, gic_dist_base, gic_cpu_base);
+#else
 	irqchip_init();
-
+#endif
 	/* route all interrupts to ARM */
 	__raw_writel(0xffffffff, INT2NTSR0);
 	__raw_writel(0x3fffffff, INT2NTSR1);
diff --git a/arch/arm/mach-shmobile/setup-rcar-gen2.c b/arch/arm/mach-shmobile/setup-rcar-gen2.c
index 3dd6edd9bd1d..cc9470dfb1ce 100644
--- a/arch/arm/mach-shmobile/setup-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/setup-rcar-gen2.c
@@ -133,7 +133,9 @@ void __init rcar_gen2_timer_init(void)
 #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 f1d027aa7a81..0edf2a6d2bbe 100644
--- a/arch/arm/mach-shmobile/timer.c
+++ b/arch/arm/mach-shmobile/timer.c
@@ -70,6 +70,18 @@ void __init shmobile_init_delay(void)
 	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 7864797609b3..a673c7f7e208 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1940,13 +1940,32 @@ void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping)
 }
 EXPORT_SYMBOL_GPL(arm_iommu_release_mapping);
 
+static int __arm_iommu_attach_device(struct device *dev,
+				     struct dma_iommu_mapping *mapping)
+{
+	int err;
+
+	err = iommu_attach_device(mapping->domain, dev);
+	if (err)
+		return err;
+
+	kref_get(&mapping->kref);
+	dev->archdata.mapping = mapping;
+
+	pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev));
+	return 0;
+}
+
 /**
  * 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,
+ * 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.
  */
@@ -1955,25 +1974,16 @@ int arm_iommu_attach_device(struct device *dev,
 {
 	int err;
 
-	err = iommu_attach_device(mapping->domain, dev);
+	err = __arm_iommu_attach_device(dev, mapping);
 	if (err)
 		return err;
 
-	kref_get(&mapping->kref);
-	dev->archdata.mapping = mapping;
-
-	pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev));
+	set_dma_ops(dev, &iommu_ops);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
 
-/**
- * arm_iommu_detach_device
- * @dev: valid struct device pointer
- *
- * Detaches the provided device from a previously attached map.
- */
-void arm_iommu_detach_device(struct device *dev)
+static void __arm_iommu_detach_device(struct device *dev)
 {
 	struct dma_iommu_mapping *mapping;
 
@@ -1989,6 +1999,19 @@ void arm_iommu_detach_device(struct device *dev)
 
 	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 @@ static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		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 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 {
 	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/Makefile b/arch/arm64/Makefile
index 1c43cec971b5..066688863920 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -85,6 +85,7 @@ vdso_install:
 # We use MRPROPER_FILES and CLEAN_FILES now
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
+	$(Q)$(MAKE) $(clean)=$(boot)/dts
 
 define archhelp
   echo  '* Image.gz      - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)'
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index 3b8d427c3985..c62b0f4d9ef6 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -3,6 +3,4 @@ dts-dirs += apm
 dts-dirs += arm
 dts-dirs += cavium
 
-always		:= $(dtb-y)
 subdir-y	:= $(dts-dirs)
-clean-files	:= *.dtb
diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts
index cb3073e4e7a8..d429129ecb3d 100644
--- a/arch/arm64/boot/dts/arm/juno.dts
+++ b/arch/arm64/boot/dts/arm/juno.dts
@@ -22,7 +22,7 @@
 	};
 
 	chosen {
-		stdout-path = &soc_uart0;
+		stdout-path = "serial0:115200n8";
 	};
 
 	psci {
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 865a7e28ea2d..3cb4c856b10d 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -45,6 +45,16 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 		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 0b7dfdb931df..acd101a9014d 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -116,9 +116,6 @@ struct kvm_vcpu_arch {
 	 * 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 14a74f136272..adcf49547301 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -243,24 +243,46 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 	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 3d7c2df89946..f31e8bb2bc5b 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -69,68 +69,31 @@ static u32 get_ccsidr(u32 csselr)
 	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 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 		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 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  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 @@ static const struct sys_reg_desc cp14_64_regs[] = {
  * 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/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index cf33f33333cc..d54dc9ac4b70 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -15,6 +15,7 @@
  */
 #include <linux/debugfs.h>
 #include <linux/fs.h>
+#include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c
index 2c9412908024..164efa009e5b 100644
--- a/arch/avr32/kernel/module.c
+++ b/arch/avr32/kernel/module.c
@@ -19,12 +19,10 @@
 #include <linux/moduleloader.h>
 #include <linux/vmalloc.h>
 
-void module_free(struct module *mod, void *module_region)
+void module_arch_freeing_init(struct module *mod)
 {
 	vfree(mod->arch.syminfo);
 	mod->arch.syminfo = NULL;
-
-	vfree(module_region);
 }
 
 static inline int check_rela(Elf32_Rela *rela, struct module *module,
@@ -291,12 +289,3 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
 
 	return ret;
 }
-
-int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
-		    struct module *module)
-{
-	vfree(module->arch.syminfo);
-	module->arch.syminfo = NULL;
-
-	return 0;
-}
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index 0eca93327195..d223a8b57c1e 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -142,6 +142,8 @@ good_area:
 	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/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c
index 08a313fc2241..f772068d9e79 100644
--- a/arch/cris/arch-v32/drivers/sync_serial.c
+++ b/arch/cris/arch-v32/drivers/sync_serial.c
@@ -604,7 +604,7 @@ static ssize_t __sync_serial_read(struct file *file,
 				  struct timespec *ts)
 {
 	unsigned long flags;
-	int dev = MINOR(file->f_dentry->d_inode->i_rdev);
+	int dev = MINOR(file_inode(file)->i_rdev);
 	int avail;
 	struct sync_port *port;
 	unsigned char *start;
diff --git a/arch/cris/kernel/module.c b/arch/cris/kernel/module.c
index 51123f985eb5..af04cb6b6dc9 100644
--- a/arch/cris/kernel/module.c
+++ b/arch/cris/kernel/module.c
@@ -36,7 +36,7 @@ void *module_alloc(unsigned long size)
 }
 
 /* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_memfree(void *module_region)
 {
 	kfree(module_region);
 }
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 1790f22e71a2..2686a7aa8ec8 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -176,6 +176,8 @@ retry:
 	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/mb93090-mb00/pci-frv.c b/arch/frv/mb93090-mb00/pci-frv.c
index 67b1d1685759..0635bd6c2af3 100644
--- a/arch/frv/mb93090-mb00/pci-frv.c
+++ b/arch/frv/mb93090-mb00/pci-frv.c
@@ -94,7 +94,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 				r = &dev->resource[idx];
 				if (!r->start)
 					continue;
-				pci_claim_resource(dev, idx);
+				pci_claim_bridge_resource(dev, idx);
 			}
 		}
 		pcibios_allocate_bus_resources(&bus->children);
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 9a66372fc7c7..ec4917ddf678 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -168,6 +168,8 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	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/kernel/module.c b/arch/ia64/kernel/module.c
index 24603be24c14..29754aae5177 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -305,14 +305,12 @@ plt_target (struct plt_entry *plt)
 #endif /* !USE_BRL */
 
 void
-module_free (struct module *mod, void *module_region)
+module_arch_freeing_init (struct module *mod)
 {
-	if (mod && mod->arch.init_unw_table &&
-	    module_region == mod->module_init) {
+	if (mod->arch.init_unw_table) {
 		unw_remove_unwind_table(mod->arch.init_unw_table);
 		mod->arch.init_unw_table = NULL;
 	}
-	vfree(module_region);
 }
 
 /* Have we already seen one of these relocations? */
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 7225dad87094..ba5ba7accd0d 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -172,6 +172,8 @@ retry:
 		 */
 		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/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 291a582777cf..900cc93e5409 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -487,45 +487,39 @@ int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
 	return 0;
 }
 
-static int is_valid_resource(struct pci_dev *dev, int idx)
+void pcibios_fixup_device_resources(struct pci_dev *dev)
 {
-	unsigned int i, type_mask = IORESOURCE_IO | IORESOURCE_MEM;
-	struct resource *devr = &dev->resource[idx], *busr;
+	int idx;
 
 	if (!dev->bus)
-		return 0;
-
-	pci_bus_for_each_resource(dev->bus, busr, i) {
-		if (!busr || ((busr->flags ^ devr->flags) & type_mask))
-			continue;
-		if ((devr->start) && (devr->start >= busr->start) &&
-				(devr->end <= busr->end))
-			return 1;
-	}
-	return 0;
-}
+		return;
 
-static void pcibios_fixup_resources(struct pci_dev *dev, int start, int limit)
-{
-	int i;
+	for (idx = 0; idx < PCI_BRIDGE_RESOURCES; idx++) {
+		struct resource *r = &dev->resource[idx];
 
-	for (i = start; i < limit; i++) {
-		if (!dev->resource[i].flags)
+		if (!r->flags || r->parent || !r->start)
 			continue;
-		if ((is_valid_resource(dev, i)))
-			pci_claim_resource(dev, i);
-	}
-}
 
-void pcibios_fixup_device_resources(struct pci_dev *dev)
-{
-	pcibios_fixup_resources(dev, 0, PCI_BRIDGE_RESOURCES);
+		pci_claim_resource(dev, idx);
+	}
 }
 EXPORT_SYMBOL_GPL(pcibios_fixup_device_resources);
 
 static void pcibios_fixup_bridge_resources(struct pci_dev *dev)
 {
-	pcibios_fixup_resources(dev, PCI_BRIDGE_RESOURCES, PCI_NUM_RESOURCES);
+	int idx;
+
+	if (!dev->bus)
+		return;
+
+	for (idx = PCI_BRIDGE_RESOURCES; idx < PCI_NUM_RESOURCES; idx++) {
+		struct resource *r = &dev->resource[idx];
+
+		if (!r->flags || r->parent || !r->start)
+			continue;
+
+		pci_claim_bridge_resource(dev, idx);
+	}
 }
 
 /*
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index e9c6a8014bd6..e3d4d4890104 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -200,6 +200,8 @@ good_area:
 	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 2bd7487440c4..b2f04aee46ec 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -145,6 +145,8 @@ good_area:
 	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 332680e5ebf2..2de5dc695a87 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -141,6 +141,8 @@ good_area:
 	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 fa4cf52aa7a6..d46a5ebb7570 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -224,6 +224,8 @@ good_area:
 	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/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index b30e41c0c033..48528fb81eff 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -1026,6 +1026,8 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			 pr, (pr && pr->name) ? pr->name : "nil");
 
 		if (pr && !(pr->flags & IORESOURCE_UNSET)) {
+			struct pci_dev *dev = bus->self;
+
 			if (request_resource(pr, res) == 0)
 				continue;
 			/*
@@ -1035,6 +1037,12 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			 */
 			if (reparent_resources(pr, res) == 0)
 				continue;
+
+			if (dev && i < PCI_BRIDGE_RESOURCE_NUM &&
+			    pci_claim_bridge_resource(dev,
+						 i + PCI_BRIDGE_RESOURCES) == 0)
+				continue;
+
 		}
 		pr_warn("PCI: Cannot allocate resource region ");
 		pr_cont("%d of PCI bridge %d, will remap\n", i, bus->number);
@@ -1227,7 +1235,10 @@ void pcibios_claim_one_bus(struct pci_bus *bus)
 				 (unsigned long long)r->end,
 				 (unsigned int)r->flags);
 
-			pci_claim_resource(dev, i);
+			if (pci_claim_resource(dev, i) == 0)
+				continue;
+
+			pci_claim_bridge_resource(dev, i);
 		}
 	}
 
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index becc42bb1849..70ab5d664332 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -158,6 +158,8 @@ good_area:
 	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/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 9fd6834a2172..5d6139390bf8 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -1388,7 +1388,7 @@ out:
 void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
-		module_free(NULL, fp->bpf_func);
+		module_memfree(fp->bpf_func);
 
 	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 3516cbdf1ee9..0c2cc5d39c8e 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -262,6 +262,8 @@ good_area:
 	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/unit-asb2305/pci-asb2305.c b/arch/mn10300/unit-asb2305/pci-asb2305.c
index febb9cd83177..b5b036f64275 100644
--- a/arch/mn10300/unit-asb2305/pci-asb2305.c
+++ b/arch/mn10300/unit-asb2305/pci-asb2305.c
@@ -106,7 +106,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 				if (!r->flags)
 					continue;
 				if (!r->start ||
-				    pci_claim_resource(dev, idx) < 0) {
+				    pci_claim_bridge_resource(dev, idx) < 0) {
 					printk(KERN_ERR "PCI:"
 					       " Cannot allocate resource"
 					       " region %d of bridge %s\n",
diff --git a/arch/mn10300/unit-asb2305/pci.c b/arch/mn10300/unit-asb2305/pci.c
index 6b4339f8c9c2..471ff398090c 100644
--- a/arch/mn10300/unit-asb2305/pci.c
+++ b/arch/mn10300/unit-asb2305/pci.c
@@ -281,42 +281,37 @@ static int __init pci_check_direct(void)
 	return -ENODEV;
 }
 
-static int is_valid_resource(struct pci_dev *dev, int idx)
+static void pcibios_fixup_device_resources(struct pci_dev *dev)
 {
-	unsigned int i, type_mask = IORESOURCE_IO | IORESOURCE_MEM;
-	struct resource *devr = &dev->resource[idx], *busr;
-
-	if (dev->bus) {
-		pci_bus_for_each_resource(dev->bus, busr, i) {
-			if (!busr || (busr->flags ^ devr->flags) & type_mask)
-				continue;
-
-			if (devr->start &&
-			    devr->start >= busr->start &&
-			    devr->end <= busr->end)
-				return 1;
-		}
-	}
+	int idx;
 
-	return 0;
+	if (!dev->bus)
+		return;
+
+	for (idx = 0; idx < PCI_BRIDGE_RESOURCES; idx++) {
+		struct resource *r = &dev->resource[idx];
+
+		if (!r->flags || r->parent || !r->start)
+			continue;
+
+		pci_claim_resource(dev, idx);
+	}
 }
 
-static void pcibios_fixup_device_resources(struct pci_dev *dev)
+static void pcibios_fixup_bridge_resources(struct pci_dev *dev)
 {
-	int limit, i;
+	int idx;
 
-	if (dev->bus->number != 0)
+	if (!dev->bus)
 		return;
 
-	limit = (dev->hdr_type == PCI_HEADER_TYPE_NORMAL) ?
-		PCI_BRIDGE_RESOURCES : PCI_NUM_RESOURCES;
+	for (idx = PCI_BRIDGE_RESOURCES; idx < PCI_NUM_RESOURCES; idx++) {
+		struct resource *r = &dev->resource[idx];
 
-	for (i = 0; i < limit; i++) {
-		if (!dev->resource[i].flags)
+		if (!r->flags || r->parent || !r->start)
 			continue;
 
-		if (is_valid_resource(dev, i))
-			pci_claim_resource(dev, i);
+		pci_claim_bridge_resource(dev, idx);
 	}
 }
 
@@ -330,7 +325,7 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 
 	if (bus->self) {
 		pci_read_bridge_bases(bus);
-		pcibios_fixup_device_resources(bus->self);
+		pcibios_fixup_bridge_resources(bus->self);
 	}
 
 	list_for_each_entry(dev, &bus->devices, bus_list)
diff --git a/arch/nios2/kernel/module.c b/arch/nios2/kernel/module.c
index cc924a38f22a..e2e3f13f98d5 100644
--- a/arch/nios2/kernel/module.c
+++ b/arch/nios2/kernel/module.c
@@ -36,7 +36,7 @@ void *module_alloc(unsigned long size)
 }
 
 /* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_memfree(void *module_region)
 {
 	kfree(module_region);
 }
diff --git a/arch/nios2/kernel/signal.c b/arch/nios2/kernel/signal.c
index f9d27883a714..2d0ea25be171 100644
--- a/arch/nios2/kernel/signal.c
+++ b/arch/nios2/kernel/signal.c
@@ -200,7 +200,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 
 	/* Set up to return from userspace; jump to fixed address sigreturn
 	   trampoline on kuser page.  */
-	regs->ra = (unsigned long) (0x1040);
+	regs->ra = (unsigned long) (0x1044);
 
 	/* Set up registers for signal handler */
 	regs->sp = (unsigned long) frame;
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 15a0bb5fc06d..34429d5a0ccd 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -135,6 +135,8 @@ survive:
 	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 0703acf7d327..230ac20ae794 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -171,6 +171,8 @@ good_area:
 	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/kernel/module.c b/arch/parisc/kernel/module.c
index 50dfafc3f2c1..5822e8e200e6 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -298,14 +298,10 @@ static inline unsigned long count_stubs(const Elf_Rela *rela, unsigned long n)
 }
 #endif
 
-
-/* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_arch_freeing_init(struct module *mod)
 {
 	kfree(mod->arch.section);
 	mod->arch.section = NULL;
-
-	vfree(module_region);
 }
 
 /* Additional bytes needed in front of individual sections */
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 3ca9c1131cfe..e5120e653240 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -256,6 +256,8 @@ good_area:
 		 */
 		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/crypto/sha1.c b/arch/powerpc/crypto/sha1.c
index d3feba5a275f..c154cebc1041 100644
--- a/arch/powerpc/crypto/sha1.c
+++ b/arch/powerpc/crypto/sha1.c
@@ -154,4 +154,5 @@ module_exit(sha1_powerpc_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
 
+MODULE_ALIAS_CRYPTO("sha1");
 MODULE_ALIAS_CRYPTO("sha1-powerpc");
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 37d512d35943..2a525c938158 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1184,6 +1184,8 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			 pr, (pr && pr->name) ? pr->name : "nil");
 
 		if (pr && !(pr->flags & IORESOURCE_UNSET)) {
+			struct pci_dev *dev = bus->self;
+
 			if (request_resource(pr, res) == 0)
 				continue;
 			/*
@@ -1193,6 +1195,11 @@ static void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			 */
 			if (reparent_resources(pr, res) == 0)
 				continue;
+
+			if (dev && i < PCI_BRIDGE_RESOURCE_NUM &&
+			    pci_claim_bridge_resource(dev,
+						i + PCI_BRIDGE_RESOURCES) == 0)
+				continue;
 		}
 		pr_warning("PCI: Cannot allocate resource region "
 			   "%d of PCI bridge %d, will remap\n", i, bus->number);
@@ -1401,7 +1408,10 @@ void pcibios_claim_one_bus(struct pci_bus *bus)
 				 (unsigned long long)r->end,
 				 (unsigned int)r->flags);
 
-			pci_claim_resource(dev, i);
+			if (pci_claim_resource(dev, i) == 0)
+				continue;
+
+			pci_claim_bridge_resource(dev, i);
 		}
 	}
 
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 5a236f082c78..1b5305d4bdab 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -76,7 +76,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 		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 eb79907f34fa..6154b0a2b063 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -437,6 +437,8 @@ good_area:
 	 */
 	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/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 1ca125b9c226..d1916b577f2c 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -699,7 +699,7 @@ out:
 void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
-		module_free(NULL, fp->bpf_func);
+		module_memfree(fp->bpf_func);
 
 	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index b700a329c31d..d2de7d5d7574 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -304,7 +304,7 @@ int pnv_save_sprs_for_winkle(void)
 	 * 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 5b150f0c5df9..13c6e200b24e 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -337,6 +337,7 @@ static inline void disable_surveillance(void)
 	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/kernel/module.c b/arch/s390/kernel/module.c
index b89b59158b95..409d152585be 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -55,14 +55,10 @@ void *module_alloc(unsigned long size)
 }
 #endif
 
-/* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_arch_freeing_init(struct module *mod)
 {
-	if (mod) {
-		vfree(mod->arch.syminfo);
-		mod->arch.syminfo = NULL;
-	}
-	vfree(module_region);
+	vfree(mod->arch.syminfo);
+	mod->arch.syminfo = NULL;
 }
 
 static void check_rela(Elf_Rela *rela, struct module *me)
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 811937bb90be..9065d5aa3932 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -374,6 +374,12 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault)
 				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/s390/net/bpf_jit.S b/arch/s390/net/bpf_jit.S
index 7e45d13816c1..ba44c9f55346 100644
--- a/arch/s390/net/bpf_jit.S
+++ b/arch/s390/net/bpf_jit.S
@@ -22,8 +22,8 @@
  * skb_copy_bits takes 4 parameters:
  *   %r2 = skb pointer
  *   %r3 = offset into skb data
- *   %r4 = length to copy
- *   %r5 = pointer to temp buffer
+ *   %r4 = pointer to temp buffer
+ *   %r5 = length to copy
  */
 #define SKBDATA	%r8
 
@@ -44,8 +44,9 @@ ENTRY(sk_load_word)
 
 sk_load_word_slow:
 	lgr	%r9,%r2			# save %r2
-	lhi	%r4,4			# 4 bytes
-	la	%r5,160(%r15)		# pointer to temp buffer
+	lgr	%r3,%r1			# offset
+	la	%r4,160(%r15)		# pointer to temp buffer
+	lghi	%r5,4			# 4 bytes
 	brasl	%r14,skb_copy_bits	# get data from skb
 	l	%r5,160(%r15)		# load result from temp buffer
 	ltgr	%r2,%r2			# set cc to (%r2 != 0)
@@ -69,8 +70,9 @@ ENTRY(sk_load_half)
 
 sk_load_half_slow:
 	lgr	%r9,%r2			# save %r2
-	lhi	%r4,2			# 2 bytes
-	la	%r5,162(%r15)		# pointer to temp buffer
+	lgr	%r3,%r1			# offset
+	la	%r4,162(%r15)		# pointer to temp buffer
+	lghi	%r5,2			# 2 bytes
 	brasl	%r14,skb_copy_bits	# get data from skb
 	xc	160(2,%r15),160(%r15)
 	l	%r5,160(%r15)		# load result from temp buffer
@@ -95,8 +97,9 @@ ENTRY(sk_load_byte)
 
 sk_load_byte_slow:
 	lgr	%r9,%r2			# save %r2
-	lhi	%r4,1			# 1 bytes
-	la	%r5,163(%r15)		# pointer to temp buffer
+	lgr	%r3,%r1			# offset
+	la	%r4,163(%r15)		# pointer to temp buffer
+	lghi	%r5,1			# 1 byte
 	brasl	%r14,skb_copy_bits	# get data from skb
 	xc	160(3,%r15),160(%r15)
 	l	%r5,160(%r15)		# load result from temp buffer
@@ -104,11 +107,11 @@ sk_load_byte_slow:
 	lgr	%r2,%r9			# restore %r2
 	br	%r8
 
-	/* A = (*(u8 *)(skb->data+K) & 0xf) << 2 */
+	/* X = (*(u8 *)(skb->data+K) & 0xf) << 2 */
 ENTRY(sk_load_byte_msh)
 	llgfr	%r1,%r3			# extend offset
 	clr	%r11,%r3		# hlen < offset ?
-	jle	sk_load_byte_slow
+	jle	sk_load_byte_msh_slow
 	lhi	%r12,0
 	ic	%r12,0(%r1,%r10)	# get byte from skb
 	nill	%r12,0x0f
@@ -118,8 +121,9 @@ ENTRY(sk_load_byte_msh)
 
 sk_load_byte_msh_slow:
 	lgr	%r9,%r2			# save %r2
-	lhi	%r4,2			# 2 bytes
-	la	%r5,162(%r15)		# pointer to temp buffer
+	lgr	%r3,%r1			# offset
+	la	%r4,163(%r15)		# pointer to temp buffer
+	lghi	%r5,1			# 1 byte
 	brasl	%r14,skb_copy_bits	# get data from skb
 	xc	160(3,%r15),160(%r15)
 	l	%r12,160(%r15)		# load result from temp buffer
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 524496d47ef5..bbd1981cc150 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -448,15 +448,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		mask = 0x800000; /* je */
 kbranch:	/* Emit compare if the branch targets are different */
 		if (filter->jt != filter->jf) {
-			if (K <= 16383)
-				/* chi %r5,<K> */
-				EMIT4_IMM(0xa75e0000, K);
-			else if (test_facility(21))
+			if (test_facility(21))
 				/* clfi %r5,<K> */
 				EMIT6_IMM(0xc25f0000, K);
 			else
-				/* c %r5,<d(K)>(%r13) */
-				EMIT4_DISP(0x5950d000, EMIT_CONST(K));
+				/* cl %r5,<d(K)>(%r13) */
+				EMIT4_DISP(0x5550d000, EMIT_CONST(K));
 		}
 branch:		if (filter->jt == filter->jf) {
 			if (filter->jt == 0)
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 52238983527d..6860beb2a280 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -114,6 +114,8 @@ good_area:
 	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 541dc6101508..a58fec9b55e0 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -353,6 +353,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	} 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/kernel/pci.c b/arch/sparc/kernel/pci.c
index b36365f49478..9ce5afe167ff 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -639,7 +639,10 @@ static void pci_claim_bus_resources(struct pci_bus *bus)
 				       (unsigned long long)r->end,
 				       (unsigned int)r->flags);
 
-			pci_claim_resource(dev, i);
+			if (pci_claim_resource(dev, i) == 0)
+				continue;
+
+			pci_claim_bridge_resource(dev, i);
 		}
 	}
 
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 908e8c17c902..70d817154fe8 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -249,6 +249,8 @@ good_area:
 	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 18fcd7167095..479823249429 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -446,6 +446,8 @@ good_area:
 	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/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index f33e7c7a3bf7..7931eeeb649a 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -776,7 +776,7 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 				if (unlikely(proglen + ilen > oldproglen)) {
 					pr_err("bpb_jit_compile fatal error\n");
 					kfree(addrs);
-					module_free(NULL, image);
+					module_memfree(image);
 					return;
 				}
 				memcpy(image + proglen, temp, ilen);
@@ -822,7 +822,7 @@ out:
 void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
-		module_free(NULL, fp->bpf_func);
+		module_memfree(fp->bpf_func);
 
 	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/tile/kernel/module.c b/arch/tile/kernel/module.c
index 96447c9160a0..2305084c9b93 100644
--- a/arch/tile/kernel/module.c
+++ b/arch/tile/kernel/module.c
@@ -74,7 +74,7 @@ error:
 
 
 /* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_memfree(void *module_region)
 {
 	vfree(module_region);
 
@@ -83,7 +83,7 @@ void module_free(struct module *mod, void *module_region)
 		     0, 0, 0, NULL, NULL, 0);
 
 	/*
-	 * FIXME: If module_region == mod->module_init, trim exception
+	 * FIXME: Add module_arch_freeing_init to trim exception
 	 * table entries.
 	 */
 }
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 565e25a98334..0f61a73534e6 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -442,6 +442,8 @@ good_area:
 	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 5678c3571e7c..209617302df8 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -80,6 +80,8 @@ good_area:
 		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/Kconfig b/arch/x86/Kconfig
index ba397bde7948..0dc9d0144a27 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -857,7 +857,7 @@ source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors"
-	depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI
+	depends on X86_32 && !SMP && !X86_32_NON_STANDARD
 	---help---
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -868,6 +868,10 @@ config X86_UP_APIC
 	  performance counters), and the NMI watchdog which detects hard
 	  lockups.
 
+config X86_UP_APIC_MSI
+	def_bool y
+	select X86_UP_APIC if X86_32 && !SMP && !X86_32_NON_STANDARD && PCI_MSI
+
 config X86_UP_IOAPIC
 	bool "IO-APIC support on uniprocessors"
 	depends on X86_UP_APIC
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index d999398928bc..ad754b4411f7 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -90,7 +90,7 @@ suffix-$(CONFIG_KERNEL_LZO) 	:= lzo
 suffix-$(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/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c
index a225a5ca1037..fd9f6b035b16 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -931,4 +931,4 @@ module_exit(sha1_mb_mod_fini);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, multi buffer accelerated");
 
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 944bf019b74f..498b6d967138 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2431,6 +2431,7 @@ __init int intel_pmu_init(void)
 		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 6e434f8e5fc8..c4bb8b8e5017 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 @@ static inline u64 rapl_scale(u64 v)
 	 * 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 10b8d3eaaf15..c635b8b49e93 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 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	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 @@ static int uncore_cpu_starting(int cpu)
 			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 @@ static int uncore_cpu_starting(int cpu)
 				}
 			}
 
-			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 863d9b02563e..6c8c1e7e69d8 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 @@ static inline int uncore_num_counters(struct intel_uncore_box *box)
 	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_disable_box(struct intel_uncore_box *box)
 
 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 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box,
 	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/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 2142376dc8c6..8b7b0a51e742 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -674,7 +674,7 @@ static inline void *alloc_tramp(unsigned long size)
 }
 static inline void tramp_free(void *tramp)
 {
-	module_free(NULL, tramp);
+	module_memfree(tramp);
 }
 #else
 /* Trampolines can only be created if modules are supported */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index b7e50bba3bbb..505449700e0c 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -617,7 +617,7 @@ static unsigned long quick_pit_calibrate(void)
 			goto success;
 		}
 	}
-	pr_err("Fast TSC calibration failed\n");
+	pr_info("Fast TSC calibration failed\n");
 	return 0;
 
 success:
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 169b09d76ddd..de12c1d379f1 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2348,7 +2348,7 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	 * Not recognized on AMD in compat mode (but is recognized in legacy
 	 * mode).
 	 */
-	if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA)
+	if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA)
 	    && !vendor_intel(ctxt))
 		return emulate_ud(ctxt);
 
@@ -2359,25 +2359,13 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	setup_syscalls_segments(ctxt, &cs, &ss);
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
-	switch (ctxt->mode) {
-	case X86EMUL_MODE_PROT32:
-		if ((msr_data & 0xfffc) == 0x0)
-			return emulate_gp(ctxt, 0);
-		break;
-	case X86EMUL_MODE_PROT64:
-		if (msr_data == 0x0)
-			return emulate_gp(ctxt, 0);
-		break;
-	default:
-		break;
-	}
+	if ((msr_data & 0xfffc) == 0x0)
+		return emulate_gp(ctxt, 0);
 
 	ctxt->eflags &= ~(EFLG_VM | EFLG_IF);
-	cs_sel = (u16)msr_data;
-	cs_sel &= ~SELECTOR_RPL_MASK;
+	cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK;
 	ss_sel = cs_sel + 8;
-	ss_sel &= ~SELECTOR_RPL_MASK;
-	if (ctxt->mode == X86EMUL_MODE_PROT64 || (efer & EFER_LMA)) {
+	if (efer & EFER_LMA) {
 		cs.d = 0;
 		cs.l = 1;
 	}
@@ -2386,10 +2374,11 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 	ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data);
-	ctxt->_eip = msr_data;
+	ctxt->_eip = (efer & EFER_LMA) ? msr_data : (u32)msr_data;
 
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data);
-	*reg_write(ctxt, VCPU_REGS_RSP) = msr_data;
+	*reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data :
+							      (u32)msr_data;
 
 	return X86EMUL_CONTINUE;
 }
@@ -3791,8 +3780,8 @@ static const struct opcode group5[] = {
 };
 
 static const struct opcode group6[] = {
-	DI(Prot,	sldt),
-	DI(Prot,	str),
+	DI(Prot | DstMem,	sldt),
+	DI(Prot | DstMem,	str),
 	II(Prot | Priv | SrcMem16, em_lldt, lldt),
 	II(Prot | Priv | SrcMem16, em_ltr, ltr),
 	N, N, N, N,
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4f0c0b954686..d52dcf0776ea 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -192,6 +192,9 @@ static void recalculate_apic_map(struct kvm *kvm)
 		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 38dcec403b46..e3ff27a5b634 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -898,6 +898,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 		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/mm/init.c b/arch/x86/mm/init.c
index 08a7d313538a..079c3b6a3ff1 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -43,7 +43,7 @@ uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
 	[_PAGE_CACHE_MODE_WT]		= _PAGE_PCD,
 	[_PAGE_CACHE_MODE_WP]		= _PAGE_PCD,
 };
-EXPORT_SYMBOL_GPL(__cachemode2pte_tbl);
+EXPORT_SYMBOL(__cachemode2pte_tbl);
 uint8_t __pte2cachemode_tbl[8] = {
 	[__pte2cm_idx(0)] = _PAGE_CACHE_MODE_WB,
 	[__pte2cm_idx(_PAGE_PWT)] = _PAGE_CACHE_MODE_WC,
@@ -54,7 +54,7 @@ uint8_t __pte2cachemode_tbl[8] = {
 	[__pte2cm_idx(_PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
 	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
 };
-EXPORT_SYMBOL_GPL(__pte2cachemode_tbl);
+EXPORT_SYMBOL(__pte2cachemode_tbl);
 
 static unsigned long __initdata pgt_buf_start;
 static unsigned long __initdata pgt_buf_end;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 9b18ef315a55..349c0d32cc0b 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -216,7 +216,7 @@ static void pcibios_allocate_bridge_resources(struct pci_dev *dev)
 			continue;
 		if (r->parent)	/* Already allocated */
 			continue;
-		if (!r->start || pci_claim_resource(dev, idx) < 0) {
+		if (!r->start || pci_claim_bridge_resource(dev, idx) < 0) {
 			/*
 			 * Something is wrong with the region.
 			 * Invalidate the resource to prevent
diff --git a/arch/x86/tools/calc_run_size.pl b/arch/x86/tools/calc_run_size.pl
deleted file mode 100644
index 23210baade2d..000000000000
--- 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 000000000000..1a4c17bb3910
--- /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 b57c4f91f487..9e3571a6535c 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -117,6 +117,8 @@ good_area:
 	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();