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>

Documentation/devicetree/bindings/i2c/i2c-st.txt

@@ -31,7 +31,7 @@ i2c0: i2c@fed40000 {
 	compatible	= "st,comms-ssc4-i2c";
 	reg		= <0xfed40000 0x110>;
 	interrupts	=  <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>;
-	clocks		= <&CLK_S_ICN_REG_0>;
+	clocks		= <&clk_s_a0_ls CLK_ICN_REG>;
 	clock-names	= "ssc";
 	clock-frequency = <400000>;
 	pinctrl-names	= "default";

Documentation/devicetree/bindings/i2c/trivial-devices.txt

@@ -47,6 +47,7 @@ dallas,ds3232		Extremely Accurate I²C RTC with Integrated Crystal and SRAM
 dallas,ds4510		CPU Supervisor with Nonvolatile Memory and Programmable I/O
 dallas,ds75		Digital Thermometer and Thermostat
 dlg,da9053		DA9053: flexible system level PMIC with multicore support
+dlg,da9063		DA9063: system PMIC for quad-core application processors
 epson,rx8025		High-Stability. I2C-Bus INTERFACE REAL TIME CLOCK MODULE
 epson,rx8581		I2C-BUS INTERFACE REAL TIME CLOCK MODULE
 fsl,mag3110		MAG3110: Xtrinsic High Accuracy, 3D Magnetometer

Documentation/networking/netlink_mmap.txt

@@ -199,16 +199,9 @@ frame header.
 TX limitations
 --------------
 
-Kernel processing usually involves validation of the message received by
+As of Jan 2015 the message is always copied from the ring frame to an
-user-space, then processing its contents. The kernel must assure that
+allocated buffer due to unresolved security concerns.
-userspace is not able to modify the message contents after they have been
+See commit 4682a0358639b29cf ("netlink: Always copy on mmap TX.").
-validated. In order to do so, the message is copied from the ring frame
-to an allocated buffer if either of these conditions is false:
-
-- only a single mapping of the ring exists
-- the file descriptor is not shared between processes
-
-This means that for threaded programs, the kernel will fall back to copying.
 
 Example
 -------

MAINTAINERS

@@ -708,6 +708,16 @@ X:	drivers/iio/*/adjd*
 F:	drivers/staging/iio/*/ad*
 F:	staging/iio/trigger/iio-trig-bfin-timer.c
 
+ANDROID DRIVERS
+M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+M:	Arve Hjønnevåg <arve@android.com>
+M:	Riley Andrews <riandrews@android.com>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/gregkh/staging.git
+L:	devel@driverdev.osuosl.org
+S:	Supported
+F:	drivers/android/
+F:	drivers/staging/android/
+
 AOA (Apple Onboard Audio) ALSA DRIVER
 M:	Johannes Berg <johannes@sipsolutions.net>
 L:	linuxppc-dev@lists.ozlabs.org
@@ -10181,6 +10191,7 @@ USERSPACE I/O (UIO)
 M:	"Hans J. Koch" <hjk@hansjkoch.de>
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
 F:	Documentation/DocBook/uio-howto.tmpl
 F:	drivers/uio/
 F:	include/linux/uio*.h

Makefile

@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 19
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Diseased Newt
 
 # *DOCUMENTATION*

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();

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;
 

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,
+		 * and folded into the former here. No GOT fixup has occurred
-		 * let's temporarily move  the stack away into the malloc
+		 * yet, but none of the code we're about to call uses any
-		 * area.  No GOT fixup has occurred yet, but none of the
+		 * global variable.
-		 * 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 */

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>;
+			resets = <&usb_clk 0>, <&usb_clk 1>, <&usb_clk 2>;
-			reset-names = "usb1_reset", "usb2_reset";
+			reset-names = "usb0_reset", "usb1_reset", "usb2_reset";
 			status = "disabled";
 		};
 

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";

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>;
+			resets = <&usb_clk 0>, <&usb_clk 1>;
-			reset-names = "usb1_reset";
+			reset-names = "usb0_reset", "usb1_reset";
 			status = "disabled";
 		};
 

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";

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";

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";

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>;
+			resets = <&usb_clk 0>, <&usb_clk 1>;
-			reset-names = "usb1_reset";
+			reset-names = "usb0_reset", "usb1_reset";
 			status = "disabled";
 		};
 

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;
 	};
 

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";

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";

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;
 	};

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 {

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";
 	};

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>;

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";
 	};

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>;

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;

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;

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,
+static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
-					     unsigned long size,
+					       unsigned long size,
-					     bool ipa_uncached)
+					       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);
+	bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached;
-	} else if (!icache_is_vivt_asid_tagged()) {
+
+	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__ */
 

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

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));
 		/*

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();
+	kvm_set_way_flush(vcpu);
-
-	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();
-
 	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,
+bool access_vm_reg(struct kvm_vcpu *vcpu,
-			  const struct coproc_params *p,
+		   const struct coproc_params *p,
-			  const struct coproc_reg *r)
+		   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;
+	kvm_toggle_cache(vcpu, was_enabled);
-}
-
-/*
- * 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);
-	}
-
 	return true;
 }
 

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,
+bool access_vm_reg(struct kvm_vcpu *vcpu,
-		  const struct coproc_params *p,
+		   const struct coproc_params *p,
-		  const struct coproc_reg *r);
+		   const struct coproc_reg *r);
 
 #endif /* __ARM_KVM_COPROC_LOCAL_H__ */

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 = {

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 = {

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)) {
+		if (!pte_none(*pte) &&
-			hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+		    (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
-			kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE);
+			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)) {
+			if (kvm_pmd_huge(*pmd))
-				hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+				kvm_flush_dcache_pmd(*pmd);
-				kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE);
+			else
-			} 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)) {
+			if (pud_huge(*pud))
-				hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+				kvm_flush_dcache_pud(*pud);
-				kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE);
+			else
-			} 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,
+		coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached);
-					  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,
+		coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached);
-					  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);
+}

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

arch/arm/mach-mvebu/coherency.c

@@ -189,6 +189,13 @@ static void __init armada_375_380_coherency_init(struct device_node *np)
 	coherency_cpu_base = of_iomap(np, 0);
 	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

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

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,

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 {

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);

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

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 = atomic64_xchg(&per_cpu(active_asids, i), 0);
-			asid = 0;
+		/*
-		} else {
+		 * If this CPU has already been through a
-			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
+		 * rollover, but hasn't run another task in
-			/*
+		 * the meantime, we must preserve its reserved
-			 * If this CPU has already been through a
+		 * ASID, as this is the only trace we have of
-			 * rollover, but hasn't run another task in
+		 * the process it is still running.
-			 * the meantime, we must preserve its reserved
+		 */
-			 * ASID, as this is the only trace we have of
+		if (asid == 0)
-			 * the process it is still running.
+			asid = per_cpu(reserved_asids, i);
-			 */
+		__set_bit(asid & ~ASID_MASK, asid_map);
-			if (asid == 0)
-				asid = per_cpu(reserved_asids, i);
-			__set_bit(asid & ~ASID_MASK, asid_map);
-		}
 		per_cpu(reserved_asids, i) = asid;
 	}
 

arch/arm/mm/dma-mapping.c

@@ -1940,18 +1940,8 @@ 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,
- * arm_iommu_attach_device
+				     struct dma_iommu_mapping *mapping)
- * @dev: valid struct device pointer
- * @mapping: io address space mapping structure (returned from
- *	arm_iommu_create_mapping)
- *
- * Attaches specified io address space mapping to the provided device,
- * More than one client might be attached to the same io address space
- * mapping.
- */
-int arm_iommu_attach_device(struct device *dev,
-			    struct dma_iommu_mapping *mapping)
 {
 	int err;
 
@@ -1965,15 +1955,35 @@ int arm_iommu_attach_device(struct device *dev,
 	pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev));
 	return 0;
 }
-EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
 
 /**
- * arm_iommu_detach_device
+ * arm_iommu_attach_device
  * @dev: valid struct device pointer
+ * @mapping: io address space mapping structure (returned from
+ *	arm_iommu_create_mapping)
  *
- * Detaches the provided device from a previously attached map.
+ * Attaches specified io address space mapping to the provided device.
+ * This replaces the dma operations (dma_map_ops pointer) with the
+ * IOMMU aware version.
+ *
+ * More than one client might be attached to the same io address space
+ * mapping.
  */
-void arm_iommu_detach_device(struct device *dev)
+int arm_iommu_attach_device(struct device *dev,
+			    struct dma_iommu_mapping *mapping)
+{
+	int err;
+
+	err = __arm_iommu_attach_device(dev, mapping);
+	if (err)
+		return err;
+
+	set_dma_ops(dev, &iommu_ops);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
+
+static void __arm_iommu_detach_device(struct device *dev)
 {
 	struct dma_iommu_mapping *mapping;
 
@@ -1989,6 +1999,19 @@ 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);
 }
 

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;

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;

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,
+static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
-					     unsigned long size,
+					       unsigned long size,
-					     bool ipa_uncached)
+					       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__ */

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)
+/*
-{
+ * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
-	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 */
 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();
+	kvm_set_way_flush(vcpu);
-
-	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();
-
 	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;
+	kvm_toggle_cache(vcpu, was_enabled);
-}
-
-/*
- * 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);
-	}
-
 	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 },

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();

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();

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();

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;

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();

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();

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();

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();

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();

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();

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();

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();

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();

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;
 		}

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;

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))

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();

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();
 	}

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();

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();

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();

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;

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));

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)

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) {
+			if (box && box->phys_id >= 0)
-				uncore_box_init(box);
 				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;

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);

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);

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();
 	}

arch/x86/pci/common.c

@@ -448,6 +448,22 @@ static const struct dmi_system_id pciprobe_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"),
 		},
 	},
+        {
+                .callback = set_scan_all,
+                .ident = "Stratus/NEC ftServer",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"),
+                },
+        },
+        {
+                .callback = set_scan_all,
+                .ident = "Stratus/NEC ftServer",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"),
+                },
+        },
 	{}
 };
 

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();

block/blk-mq-sysfs.c

@@ -15,26 +15,6 @@
 
 static void blk_mq_sysfs_release(struct kobject *kobj)
 {
-	struct request_queue *q;
-
-	q = container_of(kobj, struct request_queue, mq_kobj);
-	free_percpu(q->queue_ctx);
-}
-
-static void blk_mq_ctx_release(struct kobject *kobj)
-{
-	struct blk_mq_ctx *ctx;
-
-	ctx = container_of(kobj, struct blk_mq_ctx, kobj);
-	kobject_put(&ctx->queue->mq_kobj);
-}
-
-static void blk_mq_hctx_release(struct kobject *kobj)
-{
-	struct blk_mq_hw_ctx *hctx;
-
-	hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj);
-	kfree(hctx);
 }
 
 struct blk_mq_ctx_sysfs_entry {
@@ -338,13 +318,13 @@ static struct kobj_type blk_mq_ktype = {
 static struct kobj_type blk_mq_ctx_ktype = {
 	.sysfs_ops	= &blk_mq_sysfs_ops,
 	.default_attrs	= default_ctx_attrs,
-	.release	= blk_mq_ctx_release,
+	.release	= blk_mq_sysfs_release,
 };
 
 static struct kobj_type blk_mq_hw_ktype = {
 	.sysfs_ops	= &blk_mq_hw_sysfs_ops,
 	.default_attrs	= default_hw_ctx_attrs,
-	.release	= blk_mq_hctx_release,
+	.release	= blk_mq_sysfs_release,
 };
 
 static void blk_mq_unregister_hctx(struct blk_mq_hw_ctx *hctx)
@@ -375,7 +355,6 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx)
 		return ret;
 
 	hctx_for_each_ctx(hctx, ctx, i) {
-		kobject_get(&q->mq_kobj);
 		ret = kobject_add(&ctx->kobj, &hctx->kobj, "cpu%u", ctx->cpu);
 		if (ret)
 			break;

block/blk-mq.c

@@ -1867,6 +1867,27 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
 	mutex_unlock(&set->tag_list_lock);
 }
 
+/*
+ * It is the actual release handler for mq, but we do it from
+ * request queue's release handler for avoiding use-after-free
+ * and headache because q->mq_kobj shouldn't have been introduced,
+ * but we can't group ctx/kctx kobj without it.
+ */
+void blk_mq_release(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	/* hctx kobj stays in hctx */
+	queue_for_each_hw_ctx(q, hctx, i)
+		kfree(hctx);
+
+	kfree(q->queue_hw_ctx);
+
+	/* ctx kobj stays in queue_ctx */
+	free_percpu(q->queue_ctx);
+}
+
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 {
 	struct blk_mq_hw_ctx **hctxs;
@@ -2000,10 +2021,8 @@ void blk_mq_free_queue(struct request_queue *q)
 
 	percpu_ref_exit(&q->mq_usage_counter);
 
-	kfree(q->queue_hw_ctx);
 	kfree(q->mq_map);
 
-	q->queue_hw_ctx = NULL;
 	q->mq_map = NULL;
 
 	mutex_lock(&all_q_mutex);

block/blk-mq.h

@@ -62,6 +62,8 @@ extern void blk_mq_sysfs_unregister(struct request_queue *q);
 
 extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
 
+void blk_mq_release(struct request_queue *q);
+
 /*
  * Basic implementation of sparser bitmap, allowing the user to spread
  * the bits over more cachelines.

block/blk-sysfs.c

@@ -517,6 +517,8 @@ static void blk_release_queue(struct kobject *kobj)
 
 	if (!q->mq_ops)
 		blk_free_flush_queue(q->fq);
+	else
+		blk_mq_release(q);
 
 	blk_trace_shutdown(q);
 

drivers/Kconfig

@@ -134,8 +134,6 @@ source "drivers/staging/Kconfig"
 
 source "drivers/platform/Kconfig"
 
-source "drivers/soc/Kconfig"
-
 source "drivers/clk/Kconfig"
 
 source "drivers/hwspinlock/Kconfig"

drivers/acpi/acpi_lpss.c

@@ -1,7 +1,7 @@
 /*
  * ACPI support for Intel Lynxpoint LPSS.
  *
- * Copyright (C) 2013, 2014, Intel Corporation
+ * Copyright (C) 2013, Intel Corporation
  * Authors: Mika Westerberg <mika.westerberg@linux.intel.com>
  *          Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  *
@@ -60,8 +60,6 @@ ACPI_MODULE_NAME("acpi_lpss");
 #define LPSS_CLK_DIVIDER		BIT(2)
 #define LPSS_LTR			BIT(3)
 #define LPSS_SAVE_CTX			BIT(4)
-#define LPSS_DEV_PROXY			BIT(5)
-#define LPSS_PROXY_REQ			BIT(6)
 
 struct lpss_private_data;
 
@@ -72,10 +70,8 @@ struct lpss_device_desc {
 	void (*setup)(struct lpss_private_data *pdata);
 };
 
-static struct device *proxy_device;
-
 static struct lpss_device_desc lpss_dma_desc = {
-	.flags = LPSS_CLK | LPSS_PROXY_REQ,
+	.flags = LPSS_CLK,
 };
 
 struct lpss_private_data {
@@ -150,24 +146,22 @@ static struct lpss_device_desc byt_pwm_dev_desc = {
 };
 
 static struct lpss_device_desc byt_uart_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX |
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
-		 LPSS_DEV_PROXY,
 	.prv_offset = 0x800,
 	.setup = lpss_uart_setup,
 };
 
 static struct lpss_device_desc byt_spi_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX |
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
-		 LPSS_DEV_PROXY,
 	.prv_offset = 0x400,
 };
 
 static struct lpss_device_desc byt_sdio_dev_desc = {
-	.flags = LPSS_CLK | LPSS_DEV_PROXY,
+	.flags = LPSS_CLK,
 };
 
 static struct lpss_device_desc byt_i2c_dev_desc = {
-	.flags = LPSS_CLK | LPSS_SAVE_CTX | LPSS_DEV_PROXY,
+	.flags = LPSS_CLK | LPSS_SAVE_CTX,
 	.prv_offset = 0x800,
 	.setup = byt_i2c_setup,
 };
@@ -374,8 +368,6 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 	adev->driver_data = pdata;
 	pdev = acpi_create_platform_device(adev);
 	if (!IS_ERR_OR_NULL(pdev)) {
-		if (!proxy_device && dev_desc->flags & LPSS_DEV_PROXY)
-			proxy_device = &pdev->dev;
 		return 1;
 	}
 
@@ -600,14 +592,7 @@ static int acpi_lpss_runtime_suspend(struct device *dev)
 	if (pdata->dev_desc->flags & LPSS_SAVE_CTX)
 		acpi_lpss_save_ctx(dev, pdata);
 
-	ret = acpi_dev_runtime_suspend(dev);
+	return acpi_dev_runtime_suspend(dev);
-	if (ret)
-		return ret;
-
-	if (pdata->dev_desc->flags & LPSS_PROXY_REQ && proxy_device)
-		return pm_runtime_put_sync_suspend(proxy_device);
-
-	return 0;
 }
 
 static int acpi_lpss_runtime_resume(struct device *dev)
@@ -615,12 +600,6 @@ static int acpi_lpss_runtime_resume(struct device *dev)
 	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
 	int ret;
 
-	if (pdata->dev_desc->flags & LPSS_PROXY_REQ && proxy_device) {
-		ret = pm_runtime_get_sync(proxy_device);
-		if (ret)
-			return ret;
-	}
-
 	ret = acpi_dev_runtime_resume(dev);
 	if (ret)
 		return ret;

drivers/block/rbd.c

@@ -2098,32 +2098,26 @@ static void rbd_dev_parent_put(struct rbd_device *rbd_dev)
  * If an image has a non-zero parent overlap, get a reference to its
  * parent.
  *
- * We must get the reference before checking for the overlap to
- * coordinate properly with zeroing the parent overlap in
- * rbd_dev_v2_parent_info() when an image gets flattened.  We
- * drop it again if there is no overlap.
- *
  * Returns true if the rbd device has a parent with a non-zero
  * overlap and a reference for it was successfully taken, or
  * false otherwise.
  */
 static bool rbd_dev_parent_get(struct rbd_device *rbd_dev)
 {
-	int counter;
+	int counter = 0;
 
 	if (!rbd_dev->parent_spec)
 		return false;
 
-	counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
+	down_read(&rbd_dev->header_rwsem);
-	if (counter > 0 && rbd_dev->parent_overlap)
+	if (rbd_dev->parent_overlap)
-		return true;
+		counter = atomic_inc_return_safe(&rbd_dev->parent_ref);
-
+	up_read(&rbd_dev->header_rwsem);
-	/* Image was flattened, but parent is not yet torn down */
 
 	if (counter < 0)
 		rbd_warn(rbd_dev, "parent reference overflow");
 
-	return false;
+	return counter > 0;
 }
 
 /*
@@ -4239,7 +4233,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 		 */
 		if (rbd_dev->parent_overlap) {
 			rbd_dev->parent_overlap = 0;
-			smp_mb();
 			rbd_dev_parent_put(rbd_dev);
 			pr_info("%s: clone image has been flattened\n",
 				rbd_dev->disk->disk_name);
@@ -4285,7 +4278,6 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 	 * treat it specially.
 	 */
 	rbd_dev->parent_overlap = overlap;
-	smp_mb();
 	if (!overlap) {
 
 		/* A null parent_spec indicates it's the initial probe */
@@ -5114,10 +5106,7 @@ static void rbd_dev_unprobe(struct rbd_device *rbd_dev)
 {
 	struct rbd_image_header	*header;
 
-	/* Drop parent reference unless it's already been done (or none) */
+	rbd_dev_parent_put(rbd_dev);
-
-	if (rbd_dev->parent_overlap)
-		rbd_dev_parent_put(rbd_dev);
 
 	/* Free dynamic fields from the header, then zero it out */
 

drivers/gpio/gpio-mcp23s08.c

@@ -801,9 +801,11 @@ static int mcp230xx_probe(struct i2c_client *client,
 		client->irq = irq_of_parse_and_map(client->dev.of_node, 0);
 	} else {
 		pdata = dev_get_platdata(&client->dev);
-		if (!pdata || !gpio_is_valid(pdata->base)) {
+		if (!pdata) {
-			dev_dbg(&client->dev, "invalid platform data\n");
+			pdata = devm_kzalloc(&client->dev,
-			return -EINVAL;
+					sizeof(struct mcp23s08_platform_data),
+					GFP_KERNEL);
+			pdata->base = -1;
 		}
 	}
 
@@ -924,10 +926,11 @@ static int mcp23s08_probe(struct spi_device *spi)
 	} else {
 		type = spi_get_device_id(spi)->driver_data;
 		pdata = dev_get_platdata(&spi->dev);
-		if (!pdata || !gpio_is_valid(pdata->base)) {
+		if (!pdata) {
-			dev_dbg(&spi->dev,
+			pdata = devm_kzalloc(&spi->dev,
-					"invalid or missing platform data\n");
+					sizeof(struct mcp23s08_platform_data),
-			return -EINVAL;
+					GFP_KERNEL);
+			pdata->base = -1;
 		}
 
 		for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++) {

drivers/gpio/gpio-omap.c

@@ -88,6 +88,8 @@ struct gpio_bank {
 #define BANK_USED(bank) (bank->mod_usage || bank->irq_usage)
 #define LINE_USED(line, offset) (line & (BIT(offset)))
 
+static void omap_gpio_unmask_irq(struct irq_data *d);
+
 static int omap_irq_to_gpio(struct gpio_bank *bank, unsigned int gpio_irq)
 {
 	return bank->chip.base + gpio_irq;
@@ -477,6 +479,16 @@ static int omap_gpio_is_input(struct gpio_bank *bank, int mask)
 	return readl_relaxed(reg) & mask;
 }
 
+static void omap_gpio_init_irq(struct gpio_bank *bank, unsigned gpio,
+			       unsigned offset)
+{
+	if (!LINE_USED(bank->mod_usage, offset)) {
+		omap_enable_gpio_module(bank, offset);
+		omap_set_gpio_direction(bank, offset, 1);
+	}
+	bank->irq_usage |= BIT(GPIO_INDEX(bank, gpio));
+}
+
 static int omap_gpio_irq_type(struct irq_data *d, unsigned type)
 {
 	struct gpio_bank *bank = omap_irq_data_get_bank(d);
@@ -506,15 +518,11 @@ static int omap_gpio_irq_type(struct irq_data *d, unsigned type)
 	spin_lock_irqsave(&bank->lock, flags);
 	offset = GPIO_INDEX(bank, gpio);
 	retval = omap_set_gpio_triggering(bank, offset, type);
-	if (!LINE_USED(bank->mod_usage, offset)) {
+	omap_gpio_init_irq(bank, gpio, offset);
-		omap_enable_gpio_module(bank, offset);
+	if (!omap_gpio_is_input(bank, BIT(offset))) {
-		omap_set_gpio_direction(bank, offset, 1);
-	} else if (!omap_gpio_is_input(bank, BIT(offset))) {
 		spin_unlock_irqrestore(&bank->lock, flags);
 		return -EINVAL;
 	}
-
-	bank->irq_usage |= BIT(GPIO_INDEX(bank, gpio));
 	spin_unlock_irqrestore(&bank->lock, flags);
 
 	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
@@ -792,6 +800,24 @@ exit:
 	pm_runtime_put(bank->dev);
 }
 
+static unsigned int omap_gpio_irq_startup(struct irq_data *d)
+{
+	struct gpio_bank *bank = omap_irq_data_get_bank(d);
+	unsigned int gpio = omap_irq_to_gpio(bank, d->hwirq);
+	unsigned long flags;
+	unsigned offset = GPIO_INDEX(bank, gpio);
+
+	if (!BANK_USED(bank))
+		pm_runtime_get_sync(bank->dev);
+
+	spin_lock_irqsave(&bank->lock, flags);
+	omap_gpio_init_irq(bank, gpio, offset);
+	spin_unlock_irqrestore(&bank->lock, flags);
+	omap_gpio_unmask_irq(d);
+
+	return 0;
+}
+
 static void omap_gpio_irq_shutdown(struct irq_data *d)
 {
 	struct gpio_bank *bank = omap_irq_data_get_bank(d);
@@ -1181,6 +1207,7 @@ static int omap_gpio_probe(struct platform_device *pdev)
 	if (!irqc)
 		return -ENOMEM;
 
+	irqc->irq_startup = omap_gpio_irq_startup,
 	irqc->irq_shutdown = omap_gpio_irq_shutdown,
 	irqc->irq_ack = omap_gpio_ack_irq,
 	irqc->irq_mask = omap_gpio_mask_irq,

drivers/gpio/gpiolib-sysfs.c

@@ -648,6 +648,7 @@ int gpiod_export_link(struct device *dev, const char *name,
 		if (tdev != NULL) {
 			status = sysfs_create_link(&dev->kobj, &tdev->kobj,
 						name);
+			put_device(tdev);
 		} else {
 			status = -ENODEV;
 		}
@@ -695,7 +696,7 @@ int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value)
 	}
 
 	status = sysfs_set_active_low(desc, dev, value);
-
+	put_device(dev);
 unlock:
 	mutex_unlock(&sysfs_lock);
 

drivers/gpu/drm/amd/amdkfd/kfd_device.c

@@ -26,6 +26,7 @@
 #include <linux/slab.h>
 #include "kfd_priv.h"
 #include "kfd_device_queue_manager.h"
+#include "kfd_pm4_headers.h"
 
 #define MQD_SIZE_ALIGNED 768
 
@@ -169,9 +170,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 	kfd->shared_resources = *gpu_resources;
 
 	/* calculate max size of mqds needed for queues */
-	size = max_num_of_processes *
+	size = max_num_of_queues_per_device *
-		max_num_of_queues_per_process *
+			kfd->device_info->mqd_size_aligned;
-		kfd->device_info->mqd_size_aligned;
 
 	/* add another 512KB for all other allocations on gart */
 	size += 512 * 1024;

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

@@ -183,6 +183,13 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 
 	mutex_lock(&dqm->lock);
 
+	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
+		pr_warn("amdkfd: Can't create new usermode queue because %d queues were already created\n",
+				dqm->total_queue_count);
+		mutex_unlock(&dqm->lock);
+		return -EPERM;
+	}
+
 	if (list_empty(&qpd->queues_list)) {
 		retval = allocate_vmid(dqm, qpd, q);
 		if (retval != 0) {
@@ -207,6 +214,14 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 	list_add(&q->list, &qpd->queues_list);
 	dqm->queue_count++;
 
+	/*
+	 * Unconditionally increment this counter, regardless of the queue's
+	 * type or whether the queue is active.
+	 */
+	dqm->total_queue_count++;
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
+
 	mutex_unlock(&dqm->lock);
 	return 0;
 }
@@ -326,6 +341,15 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
 	if (list_empty(&qpd->queues_list))
 		deallocate_vmid(dqm, qpd, q);
 	dqm->queue_count--;
+
+	/*
+	 * Unconditionally decrement this counter, regardless of the queue's
+	 * type
+	 */
+	dqm->total_queue_count--;
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
+
 out:
 	mutex_unlock(&dqm->lock);
 	return retval;
@@ -541,10 +565,14 @@ static int init_pipelines(struct device_queue_manager *dqm,
 
 	for (i = 0; i < pipes_num; i++) {
 		inx = i + first_pipe;
+		/*
+		 * HPD buffer on GTT is allocated by amdkfd, no need to waste
+		 * space in GTT for pipelines we don't initialize
+		 */
 		pipe_hpd_addr = dqm->pipelines_addr + i * CIK_HPD_EOP_BYTES;
 		pr_debug("kfd: pipeline address %llX\n", pipe_hpd_addr);
 		/* = log2(bytes/4)-1 */
-		kfd2kgd->init_pipeline(dqm->dev->kgd, i,
+		kfd2kgd->init_pipeline(dqm->dev->kgd, inx,
 				CIK_HPD_EOP_BYTES_LOG2 - 3, pipe_hpd_addr);
 	}
 
@@ -560,7 +588,7 @@ static int init_scheduler(struct device_queue_manager *dqm)
 
 	pr_debug("kfd: In %s\n", __func__);
 
-	retval = init_pipelines(dqm, get_pipes_num(dqm), KFD_DQM_FIRST_PIPE);
+	retval = init_pipelines(dqm, get_pipes_num(dqm), get_first_pipe(dqm));
 	if (retval != 0)
 		return retval;
 
@@ -752,6 +780,21 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	pr_debug("kfd: In func %s\n", __func__);
 
 	mutex_lock(&dqm->lock);
+	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
+		pr_warn("amdkfd: Can't create new kernel queue because %d queues were already created\n",
+				dqm->total_queue_count);
+		mutex_unlock(&dqm->lock);
+		return -EPERM;
+	}
+
+	/*
+	 * Unconditionally increment this counter, regardless of the queue's
+	 * type or whether the queue is active.
+	 */
+	dqm->total_queue_count++;
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
+
 	list_add(&kq->list, &qpd->priv_queue_list);
 	dqm->queue_count++;
 	qpd->is_debug = true;
@@ -775,6 +818,13 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	dqm->queue_count--;
 	qpd->is_debug = false;
 	execute_queues_cpsch(dqm, false);
+	/*
+	 * Unconditionally decrement this counter, regardless of the queue's
+	 * type.
+	 */
+	dqm->total_queue_count--;
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
 	mutex_unlock(&dqm->lock);
 }
 
@@ -793,6 +843,13 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 
 	mutex_lock(&dqm->lock);
 
+	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
+		pr_warn("amdkfd: Can't create new usermode queue because %d queues were already created\n",
+				dqm->total_queue_count);
+		retval = -EPERM;
+		goto out;
+	}
+
 	mqd = dqm->get_mqd_manager(dqm, KFD_MQD_TYPE_CIK_CP);
 	if (mqd == NULL) {
 		mutex_unlock(&dqm->lock);
@@ -810,6 +867,15 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		retval = execute_queues_cpsch(dqm, false);
 	}
 
+	/*
+	 * Unconditionally increment this counter, regardless of the queue's
+	 * type or whether the queue is active.
+	 */
+	dqm->total_queue_count++;
+
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
+
 out:
 	mutex_unlock(&dqm->lock);
 	return retval;
@@ -930,6 +996,14 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
 	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
 
+	/*
+	 * Unconditionally decrement this counter, regardless of the queue's
+	 * type
+	 */
+	dqm->total_queue_count--;
+	pr_debug("Total of %d queues are accountable so far\n",
+			dqm->total_queue_count);
+
 	mutex_unlock(&dqm->lock);
 
 	return 0;

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h

@@ -130,6 +130,7 @@ struct device_queue_manager {
 	struct list_head	queues;
 	unsigned int		processes_count;
 	unsigned int		queue_count;
+	unsigned int		total_queue_count;
 	unsigned int		next_pipe_to_allocate;
 	unsigned int		*allocated_queues;
 	unsigned int		vmid_bitmap;

drivers/gpu/drm/amd/amdkfd/kfd_module.c

@@ -50,15 +50,10 @@ module_param(sched_policy, int, 0444);
 MODULE_PARM_DESC(sched_policy,
 	"Kernel cmdline parameter that defines the amdkfd scheduling policy");
 
-int max_num_of_processes = KFD_MAX_NUM_OF_PROCESSES_DEFAULT;
+int max_num_of_queues_per_device = KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT;
-module_param(max_num_of_processes, int, 0444);
+module_param(max_num_of_queues_per_device, int, 0444);
-MODULE_PARM_DESC(max_num_of_processes,
+MODULE_PARM_DESC(max_num_of_queues_per_device,
-	"Kernel cmdline parameter that defines the amdkfd maximum number of supported processes");
+	"Maximum number of supported queues per device (1 = Minimum, 4096 = default)");
-
-int max_num_of_queues_per_process = KFD_MAX_NUM_OF_QUEUES_PER_PROCESS_DEFAULT;
-module_param(max_num_of_queues_per_process, int, 0444);
-MODULE_PARM_DESC(max_num_of_queues_per_process,
-	"Kernel cmdline parameter that defines the amdkfd maximum number of supported queues per process");
 
 bool kgd2kfd_init(unsigned interface_version,
 		  const struct kfd2kgd_calls *f2g,
@@ -100,16 +95,10 @@ static int __init kfd_module_init(void)
 	}
 
 	/* Verify module parameters */
-	if ((max_num_of_processes < 0) ||
+	if ((max_num_of_queues_per_device < 1) ||
-		(max_num_of_processes > KFD_MAX_NUM_OF_PROCESSES)) {
+		(max_num_of_queues_per_device >
-		pr_err("kfd: max_num_of_processes must be between 0 to KFD_MAX_NUM_OF_PROCESSES\n");
+			KFD_MAX_NUM_OF_QUEUES_PER_DEVICE)) {
-		return -1;
+		pr_err("kfd: max_num_of_queues_per_device must be between 1 to KFD_MAX_NUM_OF_QUEUES_PER_DEVICE\n");
-	}
-
-	if ((max_num_of_queues_per_process < 0) ||
-		(max_num_of_queues_per_process >
-			KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)) {
-		pr_err("kfd: max_num_of_queues_per_process must be between 0 to KFD_MAX_NUM_OF_QUEUES_PER_PROCESS\n");
 		return -1;
 	}
 

drivers/gpu/drm/amd/amdkfd/kfd_pasid.c

@@ -30,7 +30,7 @@ static DEFINE_MUTEX(pasid_mutex);
 
 int kfd_pasid_init(void)
 {
-	pasid_limit = max_num_of_processes;
+	pasid_limit = KFD_MAX_NUM_OF_PROCESSES;
 
 	pasid_bitmap = kcalloc(BITS_TO_LONGS(pasid_limit), sizeof(long), GFP_KERNEL);
 	if (!pasid_bitmap)

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -52,20 +52,19 @@
 #define kfd_alloc_struct(ptr_to_struct)	\
 	((typeof(ptr_to_struct)) kzalloc(sizeof(*ptr_to_struct), GFP_KERNEL))
 
-/* Kernel module parameter to specify maximum number of supported processes */
-extern int max_num_of_processes;
-
-#define KFD_MAX_NUM_OF_PROCESSES_DEFAULT 32
 #define KFD_MAX_NUM_OF_PROCESSES 512
+#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS 1024
 
 /*
- * Kernel module parameter to specify maximum number of supported queues
+ * Kernel module parameter to specify maximum number of supported queues per
- * per process
+ * device
  */
-extern int max_num_of_queues_per_process;
+extern int max_num_of_queues_per_device;
 
-#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS_DEFAULT 128
+#define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT 4096
-#define KFD_MAX_NUM_OF_QUEUES_PER_PROCESS 1024
+#define KFD_MAX_NUM_OF_QUEUES_PER_DEVICE		\
+	(KFD_MAX_NUM_OF_PROCESSES *			\
+			KFD_MAX_NUM_OF_QUEUES_PER_PROCESS)
 
 #define KFD_KERNEL_QUEUE_SIZE 2048
 

drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c

@@ -54,11 +54,11 @@ static int find_available_queue_slot(struct process_queue_manager *pqm,
 	pr_debug("kfd: in %s\n", __func__);
 
 	found = find_first_zero_bit(pqm->queue_slot_bitmap,
-			max_num_of_queues_per_process);
+			KFD_MAX_NUM_OF_QUEUES_PER_PROCESS);
 
 	pr_debug("kfd: the new slot id %lu\n", found);
 
-	if (found >= max_num_of_queues_per_process) {
+	if (found >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) {
 		pr_info("amdkfd: Can not open more queues for process with pasid %d\n",
 				pqm->process->pasid);
 		return -ENOMEM;
@@ -76,7 +76,7 @@ int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p)
 
 	INIT_LIST_HEAD(&pqm->queues);
 	pqm->queue_slot_bitmap =
-			kzalloc(DIV_ROUND_UP(max_num_of_queues_per_process,
+			kzalloc(DIV_ROUND_UP(KFD_MAX_NUM_OF_QUEUES_PER_PROCESS,
 					BITS_PER_BYTE), GFP_KERNEL);
 	if (pqm->queue_slot_bitmap == NULL)
 		return -ENOMEM;
@@ -203,6 +203,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 		pqn->kq = NULL;
 		retval = dev->dqm->create_queue(dev->dqm, q, &pdd->qpd,
 						&q->properties.vmid);
+		pr_debug("DQM returned %d for create_queue\n", retval);
 		print_queue(q);
 		break;
 	case KFD_QUEUE_TYPE_DIQ:
@@ -222,7 +223,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 	}
 
 	if (retval != 0) {
-		pr_err("kfd: error dqm create queue\n");
+		pr_debug("Error dqm create queue\n");
 		goto err_create_queue;
 	}
 
@@ -241,7 +242,10 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 err_create_queue:
 	kfree(pqn);
 err_allocate_pqn:
+	/* check if queues list is empty unregister process from device */
 	clear_bit(*qid, pqm->queue_slot_bitmap);
+	if (list_empty(&pqm->queues))
+		dev->dqm->unregister_process(dev->dqm, &pdd->qpd);
 	return retval;
 }
 
@@ -311,7 +315,11 @@ int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 	BUG_ON(!pqm);
 
 	pqn = get_queue_by_qid(pqm, qid);
-	BUG_ON(!pqn);
+	if (!pqn) {
+		pr_debug("amdkfd: No queue %d exists for update operation\n",
+				qid);
+		return -EFAULT;
+	}
 
 	pqn->q->properties.queue_address = p->queue_address;
 	pqn->q->properties.queue_size = p->queue_size;

drivers/gpu/drm/cirrus/cirrus_drv.c

@@ -16,9 +16,12 @@
 #include "cirrus_drv.h"
 
 int cirrus_modeset = -1;
+int cirrus_bpp = 24;
 
 MODULE_PARM_DESC(modeset, "Disable/Enable modesetting");
 module_param_named(modeset, cirrus_modeset, int, 0400);
+MODULE_PARM_DESC(bpp, "Max bits-per-pixel (default:24)");
+module_param_named(bpp, cirrus_bpp, int, 0400);
 
 /*
  * This is the generic driver code. This binds the driver to the drm core,

drivers/gpu/drm/cirrus/cirrus_drv.h

@@ -262,4 +262,7 @@ static inline void cirrus_bo_unreserve(struct cirrus_bo *bo)
 
 int cirrus_bo_push_sysram(struct cirrus_bo *bo);
 int cirrus_bo_pin(struct cirrus_bo *bo, u32 pl_flag, u64 *gpu_addr);
+
+extern int cirrus_bpp;
+
 #endif				/* __CIRRUS_DRV_H__ */

drivers/gpu/drm/cirrus/cirrus_main.c

@@ -320,6 +320,8 @@ bool cirrus_check_framebuffer(struct cirrus_device *cdev, int width, int height,
 	const int max_pitch = 0x1FF << 3; /* (4096 - 1) & ~111b bytes */
 	const int max_size = cdev->mc.vram_size;
 
+	if (bpp > cirrus_bpp)
+		return false;
 	if (bpp > 32)
 		return false;
 

drivers/gpu/drm/cirrus/cirrus_mode.c

@@ -501,8 +501,13 @@ static int cirrus_vga_get_modes(struct drm_connector *connector)
 	int count;
 
 	/* Just add a static list of modes */
-	count = drm_add_modes_noedid(connector, 1280, 1024);
+	if (cirrus_bpp <= 24) {
-	drm_set_preferred_mode(connector, 1024, 768);
+		count = drm_add_modes_noedid(connector, 1280, 1024);
+		drm_set_preferred_mode(connector, 1024, 768);
+	} else {
+		count = drm_add_modes_noedid(connector, 800, 600);
+		drm_set_preferred_mode(connector, 800, 600);
+	}
 	return count;
 }
 

drivers/gpu/drm/drm_fb_helper.c

@@ -145,6 +145,31 @@ int drm_fb_helper_add_one_connector(struct drm_fb_helper *fb_helper, struct drm_
 }
 EXPORT_SYMBOL(drm_fb_helper_add_one_connector);
 
+static void remove_from_modeset(struct drm_mode_set *set,
+		struct drm_connector *connector)
+{
+	int i, j;
+
+	for (i = 0; i < set->num_connectors; i++) {
+		if (set->connectors[i] == connector)
+			break;
+	}
+
+	if (i == set->num_connectors)
+		return;
+
+	for (j = i + 1; j < set->num_connectors; j++) {
+		set->connectors[j - 1] = set->connectors[j];
+	}
+	set->num_connectors--;
+
+	/* because i915 is pissy about this..
+	 * TODO maybe need to makes sure we set it back to !=NULL somewhere?
+	 */
+	if (set->num_connectors == 0)
+		set->fb = NULL;
+}
+
 int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper,
 				       struct drm_connector *connector)
 {
@@ -167,6 +192,11 @@ int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper,
 	}
 	fb_helper->connector_count--;
 	kfree(fb_helper_connector);
+
+	/* also cleanup dangling references to the connector: */
+	for (i = 0; i < fb_helper->crtc_count; i++)
+		remove_from_modeset(&fb_helper->crtc_info[i].mode_set, connector);
+
 	return 0;
 }
 EXPORT_SYMBOL(drm_fb_helper_remove_one_connector);

drivers/gpu/drm/i2c/tda998x_drv.c

@@ -32,6 +32,8 @@
 struct tda998x_priv {
 	struct i2c_client *cec;
 	struct i2c_client *hdmi;
+	struct mutex mutex;
+	struct delayed_work dwork;
 	uint16_t rev;
 	uint8_t current_page;
 	int dpms;
@@ -402,9 +404,10 @@ reg_read_range(struct tda998x_priv *priv, uint16_t reg, char *buf, int cnt)
 	uint8_t addr = REG2ADDR(reg);
 	int ret;
 
+	mutex_lock(&priv->mutex);
 	ret = set_page(priv, reg);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	ret = i2c_master_send(client, &addr, sizeof(addr));
 	if (ret < 0)
@@ -414,10 +417,12 @@ reg_read_range(struct tda998x_priv *priv, uint16_t reg, char *buf, int cnt)
 	if (ret < 0)
 		goto fail;
 
-	return ret;
+	goto out;
 
 fail:
 	dev_err(&client->dev, "Error %d reading from 0x%x\n", ret, reg);
+out:
+	mutex_unlock(&priv->mutex);
 	return ret;
 }
 
@@ -431,13 +436,16 @@ reg_write_range(struct tda998x_priv *priv, uint16_t reg, uint8_t *p, int cnt)
 	buf[0] = REG2ADDR(reg);
 	memcpy(&buf[1], p, cnt);
 
+	mutex_lock(&priv->mutex);
 	ret = set_page(priv, reg);
 	if (ret < 0)
-		return;
+		goto out;
 
 	ret = i2c_master_send(client, buf, cnt + 1);
 	if (ret < 0)
 		dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg);
+out:
+	mutex_unlock(&priv->mutex);
 }
 
 static int
@@ -459,13 +467,16 @@ reg_write(struct tda998x_priv *priv, uint16_t reg, uint8_t val)
 	uint8_t buf[] = {REG2ADDR(reg), val};
 	int ret;
 
+	mutex_lock(&priv->mutex);
 	ret = set_page(priv, reg);
 	if (ret < 0)
-		return;
+		goto out;
 
 	ret = i2c_master_send(client, buf, sizeof(buf));
 	if (ret < 0)
 		dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg);
+out:
+	mutex_unlock(&priv->mutex);
 }
 
 static void
@@ -475,13 +486,16 @@ reg_write16(struct tda998x_priv *priv, uint16_t reg, uint16_t val)
 	uint8_t buf[] = {REG2ADDR(reg), val >> 8, val};
 	int ret;
 
+	mutex_lock(&priv->mutex);
 	ret = set_page(priv, reg);
 	if (ret < 0)
-		return;
+		goto out;
 
 	ret = i2c_master_send(client, buf, sizeof(buf));
 	if (ret < 0)
 		dev_err(&client->dev, "Error %d writing to 0x%x\n", ret, reg);
+out:
+	mutex_unlock(&priv->mutex);
 }
 
 static void
@@ -536,6 +550,17 @@ tda998x_reset(struct tda998x_priv *priv)
 	reg_write(priv, REG_MUX_VP_VIP_OUT, 0x24);
 }
 
+/* handle HDMI connect/disconnect */
+static void tda998x_hpd(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct tda998x_priv *priv =
+			container_of(dwork, struct tda998x_priv, dwork);
+
+	if (priv->encoder && priv->encoder->dev)
+		drm_kms_helper_hotplug_event(priv->encoder->dev);
+}
+
 /*
  * only 2 interrupts may occur: screen plug/unplug and EDID read
  */
@@ -559,8 +584,7 @@ static irqreturn_t tda998x_irq_thread(int irq, void *data)
 		priv->wq_edid_wait = 0;
 		wake_up(&priv->wq_edid);
 	} else if (cec != 0) {			/* HPD change */
-		if (priv->encoder && priv->encoder->dev)
+		schedule_delayed_work(&priv->dwork, HZ/10);
-			drm_helper_hpd_irq_event(priv->encoder->dev);
 	}
 	return IRQ_HANDLED;
 }
@@ -1170,8 +1194,10 @@ static void tda998x_destroy(struct tda998x_priv *priv)
 	/* disable all IRQs and free the IRQ handler */
 	cec_write(priv, REG_CEC_RXSHPDINTENA, 0);
 	reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
-	if (priv->hdmi->irq)
+	if (priv->hdmi->irq) {
 		free_irq(priv->hdmi->irq, priv);
+		cancel_delayed_work_sync(&priv->dwork);
+	}
 
 	i2c_unregister_device(priv->cec);
 }
@@ -1255,6 +1281,7 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 	struct device_node *np = client->dev.of_node;
 	u32 video;
 	int rev_lo, rev_hi, ret;
+	unsigned short cec_addr;
 
 	priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(2) | VIP_CNTRL_0_SWAP_B(3);
 	priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(0) | VIP_CNTRL_1_SWAP_D(1);
@@ -1262,12 +1289,16 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 
 	priv->current_page = 0xff;
 	priv->hdmi = client;
-	priv->cec = i2c_new_dummy(client->adapter, 0x34);
+	/* CEC I2C address bound to TDA998x I2C addr by configuration pins */
+	cec_addr = 0x34 + (client->addr & 0x03);
+	priv->cec = i2c_new_dummy(client->adapter, cec_addr);
 	if (!priv->cec)
 		return -ENODEV;
 
 	priv->dpms = DRM_MODE_DPMS_OFF;
 
+	mutex_init(&priv->mutex);	/* protect the page access */
+
 	/* wake up the device: */
 	cec_write(priv, REG_CEC_ENAMODS,
 			CEC_ENAMODS_EN_RXSENS | CEC_ENAMODS_EN_HDMI);
@@ -1323,8 +1354,9 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 	if (client->irq) {
 		int irqf_trigger;
 
-		/* init read EDID waitqueue */
+		/* init read EDID waitqueue and HDP work */
 		init_waitqueue_head(&priv->wq_edid);
+		INIT_DELAYED_WORK(&priv->dwork, tda998x_hpd);
 
 		/* clear pending interrupts */
 		reg_read(priv, REG_INT_FLAGS_0);