Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/vxlan.c
	drivers/vhost/net.c
	include/linux/if_vlan.h
	net/core/dev.c

The net/core/dev.c conflict was the overlap of one commit marking an
existing function static whilst another was adding a new function.

In the include/linux/if_vlan.h case, the type used for a local
variable was changed in 'net', whereas the function got rewritten
to fix a stacked vlan bug in 'net-next'.

In drivers/vhost/net.c, Al Viro's iov_iter conversions in 'net-next'
overlapped with an endainness fix for VHOST 1.0 in 'net'.

In drivers/net/vxlan.c, vxlan_find_vni() added a 'flags' parameter
in 'net-next' whereas in 'net' there was a bug fix to pass in the
correct network namespace pointer in calls to this function.

Signed-off-by: David S. Miller <davem@davemloft.net>

36 files changed, 476 insertions, 199 deletions

diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 68be9017593d..132c70e2d2f1 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -263,16 +263,37 @@ restart:	adr	r0, LC0
 		 * OK... Let's do some funky business here.
 		 * If we do have a DTB appended to zImage, and we do have
 		 * an ATAG list around, we want the later to be translated
-		 * and folded into the former here.  To be on the safe side,
-		 * let's temporarily move  the stack away into the malloc
-		 * area.  No GOT fixup has occurred yet, but none of the
-		 * code we're about to call uses any global variable.
+		 * and folded into the former here. No GOT fixup has occurred
+		 * yet, but none of the code we're about to call uses any
+		 * global variable.
 		*/
-		add	sp, sp, #0x10000
+
+		/* Get the initial DTB size */
+		ldr	r5, [r6, #4]
+#ifndef __ARMEB__
+		/* convert to little endian */
+		eor	r1, r5, r5, ror #16
+		bic	r1, r1, #0x00ff0000
+		mov	r5, r5, ror #8
+		eor	r5, r5, r1, lsr #8
+#endif
+		/* 50% DTB growth should be good enough */
+		add	r5, r5, r5, lsr #1
+		/* preserve 64-bit alignment */
+		add	r5, r5, #7
+		bic	r5, r5, #7
+		/* clamp to 32KB min and 1MB max */
+		cmp	r5, #(1 << 15)
+		movlo	r5, #(1 << 15)
+		cmp	r5, #(1 << 20)
+		movhi	r5, #(1 << 20)
+		/* temporarily relocate the stack past the DTB work space */
+		add	sp, sp, r5
+
 		stmfd	sp!, {r0-r3, ip, lr}
 		mov	r0, r8
 		mov	r1, r6
-		sub	r2, sp, r6
+		mov	r2, r5
 		bl	atags_to_fdt
 
 		/*
@@ -285,11 +306,11 @@ restart:	adr	r0, LC0
 		bic	r0, r0, #1
 		add	r0, r0, #0x100
 		mov	r1, r6
-		sub	r2, sp, r6
+		mov	r2, r5
 		bleq	atags_to_fdt
 
 		ldmfd	sp!, {r0-r3, ip, lr}
-		sub	sp, sp, #0x10000
+		sub	sp, sp, r5
 #endif
 
 		mov	r8, r6			@ use the appended device tree
@@ -306,7 +327,7 @@ restart:	adr	r0, LC0
 		subs	r1, r5, r1
 		addhi	r9, r9, r1
 
-		/* Get the dtb's size */
+		/* Get the current DTB size */
 		ldr	r5, [r6, #4]
 #ifndef __ARMEB__
 		/* convert r5 (dtb size) to little endian */
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/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-v7m.S b/arch/arm/kernel/entry-v7m.S
index 2260f1855820..8944f4991c3c 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -22,10 +22,12 @@
 
 __invalid_entry:
 	v7m_exception_entry
+#ifdef CONFIG_PRINTK
 	adr	r0, strerr
 	mrs	r1, ipsr
 	mov	r2, lr
 	bl	printk
+#endif
 	mov	r0, sp
 	bl	show_regs
 1:	b	1b
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 caa21e9b8cd9..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
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-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/Kconfig b/arch/arm/mm/Kconfig
index 03823e784f63..c43c71455566 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1012,6 +1012,7 @@ config ARCH_SUPPORTS_BIG_ENDIAN
 
 config ARM_KERNMEM_PERMS
 	bool "Restrict kernel memory permissions"
+	depends on MMU
 	help
 	  If this is set, kernel memory other than kernel text (and rodata)
 	  will be made non-executable. The tradeoff is that each region is
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 91892569710f..845769e41332 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -144,21 +144,17 @@ static void flush_context(unsigned int cpu)
 	/* Update the list of reserved ASIDs and the ASID bitmap. */
 	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
 	for_each_possible_cpu(i) {
-		if (i == cpu) {
-			asid = 0;
-		} else {
-			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
-			/*
-			 * If this CPU has already been through a
-			 * rollover, but hasn't run another task in
-			 * the meantime, we must preserve its reserved
-			 * ASID, as this is the only trace we have of
-			 * the process it is still running.
-			 */
-			if (asid == 0)
-				asid = per_cpu(reserved_asids, i);
-			__set_bit(asid & ~ASID_MASK, asid_map);
-		}
+		asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
+		/*
+		 * If this CPU has already been through a
+		 * rollover, but hasn't run another task in
+		 * the meantime, we must preserve its reserved
+		 * ASID, as this is the only trace we have of
+		 * the process it is still running.
+		 */
+		if (asid == 0)
+			asid = per_cpu(reserved_asids, i);
+		__set_bit(asid & ~ASID_MASK, asid_map);
 		per_cpu(reserved_asids, i) = asid;
 	}
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7864797609b3..903dba064a03 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 +2048,10 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 {
 	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
 
-	arm_iommu_detach_device(dev);
+	if (!mapping)
+		return;
+
+	__arm_iommu_detach_device(dev);
 	arm_iommu_release_mapping(mapping);
 }