Linux-libre 4.7.2-gnupck-4.7.2-gnu

41 files changed, 541 insertions, 384 deletions

diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 858f98ef7..0f92d9743 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -110,7 +110,7 @@
 #define ___DEF (_PAGE_PRESENT | _PAGE_CACHEABLE)
 
 /* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL)
 
 /* More Abbrevaited helpers */
 #define PAGE_U_NONE     __pgprot(___DEF)
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 73d7e4c75..ab74b5d91 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -92,7 +92,8 @@ static void *arc_dma_alloc(struct device *dev, size_t size,
 static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
-	struct page *page = virt_to_page(dma_handle);
+	phys_addr_t paddr = plat_dma_to_phys(dev, dma_handle);
+	struct page *page = virt_to_page(paddr);
 	int is_non_coh = 1;
 
 	is_non_coh = dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs) ||
diff --git a/arch/arm/boot/dts/arm-realview-pbx-a9.dts b/arch/arm/boot/dts/arm-realview-pbx-a9.dts
index db808f92d..90d00b407 100644
--- a/arch/arm/boot/dts/arm-realview-pbx-a9.dts
+++ b/arch/arm/boot/dts/arm-realview-pbx-a9.dts
@@ -70,13 +70,12 @@
 		 * associativity as these may be erroneously set
 		 * up by boot loader(s).
 		 */
-		cache-size = <1048576>; // 1MB
-		cache-sets = <4096>;
+		cache-size = <131072>; // 128KB
+		cache-sets = <512>;
 		cache-line-size = <32>;
 		arm,parity-disable;
-		arm,tag-latency = <1>;
-		arm,data-latency = <1 1>;
-		arm,dirty-latency = <1>;
+		arm,tag-latency = <1 1 1>;
+		arm,data-latency = <1 1 1>;
 	};
 
 	scu: scu@1f000000 {
diff --git a/arch/arm/boot/dts/sun4i-a10-a1000.dts b/arch/arm/boot/dts/sun4i-a10-a1000.dts
index c92a1ae33..fa70b8fbf 100644
--- a/arch/arm/boot/dts/sun4i-a10-a1000.dts
+++ b/arch/arm/boot/dts/sun4i-a10-a1000.dts
@@ -84,6 +84,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 15 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/sun4i-a10-hackberry.dts b/arch/arm/boot/dts/sun4i-a10-hackberry.dts
index 2b17c5199..6de83a618 100644
--- a/arch/arm/boot/dts/sun4i-a10-hackberry.dts
+++ b/arch/arm/boot/dts/sun4i-a10-hackberry.dts
@@ -66,6 +66,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
index 7afc7a64e..e28f080b1 100644
--- a/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
+++ b/arch/arm/boot/dts/sun4i-a10-jesurun-q5.dts
@@ -80,6 +80,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 7 19 GPIO_ACTIVE_HIGH>;   /* PH19 */
 	};
diff --git a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
index 9fea918f9..39731a78f 100644
--- a/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
+++ b/arch/arm/boot/dts/sun5i-a10s-wobo-i5.dts
@@ -79,6 +79,7 @@
 		regulator-name = "emac-3v3";
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <20000>;
 		enable-active-high;
 		gpio = <&pio 0 2 GPIO_ACTIVE_HIGH>;
 	};
diff --git a/arch/arm/boot/dts/tegra124-jetson-tk1.dts b/arch/arm/boot/dts/tegra124-jetson-tk1.dts
index 941f36263..f4d8125c1 100644
--- a/arch/arm/boot/dts/tegra124-jetson-tk1.dts
+++ b/arch/arm/boot/dts/tegra124-jetson-tk1.dts
@@ -1386,7 +1386,7 @@
 	 *   Pin 41: BR_UART1_TXD
 	 *   Pin 44: BR_UART1_RXD
 	 */
-	serial@70006000 {
+	serial@0,70006000 {
 		compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart";
 		status = "okay";
 	};
@@ -1398,7 +1398,7 @@
 	 *   Pin 71: UART2_CTS_L
 	 *   Pin 74: UART2_RTS_L
 	 */
-	serial@70006040 {
+	serial@0,70006040 {
 		compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart";
 		status = "okay";
 	};
diff --git a/arch/arm/configs/aspeed_g4_defconfig b/arch/arm/configs/aspeed_g4_defconfig
index b6e54ee9b..ca39c04fe 100644
--- a/arch/arm/configs/aspeed_g4_defconfig
+++ b/arch/arm/configs/aspeed_g4_defconfig
@@ -58,7 +58,7 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_FIRMWARE_MEMMAP=y
 CONFIG_FANOTIFY=y
-CONFIG_PRINTK_TIME=1
+CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_PAGE_POISONING=y
diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig
index 892605167..4f366b037 100644
--- a/arch/arm/configs/aspeed_g5_defconfig
+++ b/arch/arm/configs/aspeed_g5_defconfig
@@ -59,7 +59,7 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_FIRMWARE_MEMMAP=y
 CONFIG_FANOTIFY=y
-CONFIG_PRINTK_TIME=1
+CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_PAGE_POISONING=y
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ff7ed5697..d2485c749 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -49,6 +49,7 @@ struct arm_dma_alloc_args {
 	pgprot_t prot;
 	const void *caller;
 	bool want_vaddr;
+	int coherent_flag;
 };
 
 struct arm_dma_free_args {
@@ -59,6 +60,9 @@ struct arm_dma_free_args {
 	bool want_vaddr;
 };
 
+#define NORMAL	    0
+#define COHERENT    1
+
 struct arm_dma_allocator {
 	void *(*alloc)(struct arm_dma_alloc_args *args,
 		       struct page **ret_page);
@@ -272,7 +276,7 @@ static u64 get_coherent_dma_mask(struct device *dev)
 	return mask;
 }
 
-static void __dma_clear_buffer(struct page *page, size_t size)
+static void __dma_clear_buffer(struct page *page, size_t size, int coherent_flag)
 {
 	/*
 	 * Ensure that the allocated pages are zeroed, and that any data
@@ -284,17 +288,21 @@ static void __dma_clear_buffer(struct page *page, size_t size)
 		while (size > 0) {
 			void *ptr = kmap_atomic(page);
 			memset(ptr, 0, PAGE_SIZE);
-			dmac_flush_range(ptr, ptr + PAGE_SIZE);
+			if (coherent_flag != COHERENT)
+				dmac_flush_range(ptr, ptr + PAGE_SIZE);
 			kunmap_atomic(ptr);
 			page++;
 			size -= PAGE_SIZE;
 		}
-		outer_flush_range(base, end);
+		if (coherent_flag != COHERENT)
+			outer_flush_range(base, end);
 	} else {
 		void *ptr = page_address(page);
 		memset(ptr, 0, size);
-		dmac_flush_range(ptr, ptr + size);
-		outer_flush_range(__pa(ptr), __pa(ptr) + size);
+		if (coherent_flag != COHERENT) {
+			dmac_flush_range(ptr, ptr + size);
+			outer_flush_range(__pa(ptr), __pa(ptr) + size);
+		}
 	}
 }
 
@@ -302,7 +310,8 @@ static void __dma_clear_buffer(struct page *page, size_t size)
  * Allocate a DMA buffer for 'dev' of size 'size' using the
  * specified gfp mask.  Note that 'size' must be page aligned.
  */
-static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gfp)
+static struct page *__dma_alloc_buffer(struct device *dev, size_t size,
+				       gfp_t gfp, int coherent_flag)
 {
 	unsigned long order = get_order(size);
 	struct page *page, *p, *e;
@@ -318,7 +327,7 @@ static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gf
 	for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++)
 		__free_page(p);
 
-	__dma_clear_buffer(page, size);
+	__dma_clear_buffer(page, size, coherent_flag);
 
 	return page;
 }
@@ -340,7 +349,8 @@ static void __dma_free_buffer(struct page *page, size_t size)
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
-				     const void *caller, bool want_vaddr);
+				     const void *caller, bool want_vaddr,
+				     int coherent_flag);
 
 static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 				 pgprot_t prot, struct page **ret_page,
@@ -405,10 +415,13 @@ static int __init atomic_pool_init(void)
 	atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
 	if (!atomic_pool)
 		goto out;
-
+	/*
+	 * The atomic pool is only used for non-coherent allocations
+	 * so we must pass NORMAL for coherent_flag.
+	 */
 	if (dev_get_cma_area(NULL))
 		ptr = __alloc_from_contiguous(NULL, atomic_pool_size, prot,
-					      &page, atomic_pool_init, true);
+				      &page, atomic_pool_init, true, NORMAL);
 	else
 		ptr = __alloc_remap_buffer(NULL, atomic_pool_size, gfp, prot,
 					   &page, atomic_pool_init, true);
@@ -522,7 +535,11 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 {
 	struct page *page;
 	void *ptr = NULL;
-	page = __dma_alloc_buffer(dev, size, gfp);
+	/*
+	 * __alloc_remap_buffer is only called when the device is
+	 * non-coherent
+	 */
+	page = __dma_alloc_buffer(dev, size, gfp, NORMAL);
 	if (!page)
 		return NULL;
 	if (!want_vaddr)
@@ -577,7 +594,8 @@ static int __free_from_pool(void *start, size_t size)
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
-				     const void *caller, bool want_vaddr)
+				     const void *caller, bool want_vaddr,
+				     int coherent_flag)
 {
 	unsigned long order = get_order(size);
 	size_t count = size >> PAGE_SHIFT;
@@ -588,7 +606,7 @@ static void *__alloc_from_contiguous(struct device *dev, size_t size,
 	if (!page)
 		return NULL;
 
-	__dma_clear_buffer(page, size);
+	__dma_clear_buffer(page, size, coherent_flag);
 
 	if (!want_vaddr)
 		goto out;
@@ -638,7 +656,7 @@ static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot)
 #define __get_dma_pgprot(attrs, prot)				__pgprot(0)
 #define __alloc_remap_buffer(dev, size, gfp, prot, ret, c, wv)	NULL
 #define __alloc_from_pool(size, ret_page)			NULL
-#define __alloc_from_contiguous(dev, size, prot, ret, c, wv)	NULL
+#define __alloc_from_contiguous(dev, size, prot, ret, c, wv, coherent_flag)	NULL
 #define __free_from_pool(cpu_addr, size)			do { } while (0)
 #define __free_from_contiguous(dev, page, cpu_addr, size, wv)	do { } while (0)
 #define __dma_free_remap(cpu_addr, size)			do { } while (0)
@@ -649,7 +667,8 @@ static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
 				   struct page **ret_page)
 {
 	struct page *page;
-	page = __dma_alloc_buffer(dev, size, gfp);
+	/* __alloc_simple_buffer is only called when the device is coherent */
+	page = __dma_alloc_buffer(dev, size, gfp, COHERENT);
 	if (!page)
 		return NULL;
 
@@ -679,7 +698,7 @@ static void *cma_allocator_alloc(struct arm_dma_alloc_args *args,
 {
 	return __alloc_from_contiguous(args->dev, args->size, args->prot,
 				       ret_page, args->caller,
-				       args->want_vaddr);
+				       args->want_vaddr, args->coherent_flag);
 }
 
 static void cma_allocator_free(struct arm_dma_free_args *args)
@@ -746,6 +765,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		.prot = prot,
 		.caller = caller,
 		.want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs),
+		.coherent_flag = is_coherent ? COHERENT : NORMAL,
 	};
 
 #ifdef CONFIG_DMA_API_DEBUG
@@ -1253,7 +1273,8 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping,
 static const int iommu_order_array[] = { 9, 8, 4, 0 };
 
 static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
-					  gfp_t gfp, struct dma_attrs *attrs)
+					  gfp_t gfp, struct dma_attrs *attrs,
+					  int coherent_flag)
 {
 	struct page **pages;
 	int count = size >> PAGE_SHIFT;
@@ -1277,7 +1298,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 		if (!page)
 			goto error;
 
-		__dma_clear_buffer(page, size);
+		__dma_clear_buffer(page, size, coherent_flag);
 
 		for (i = 0; i < count; i++)
 			pages[i] = page + i;
@@ -1327,7 +1348,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 				pages[i + j] = pages[i] + j;
 		}
 
-		__dma_clear_buffer(pages[i], PAGE_SIZE << order);
+		__dma_clear_buffer(pages[i], PAGE_SIZE << order, coherent_flag);
 		i += 1 << order;
 		count -= 1 << order;
 	}
@@ -1505,7 +1526,8 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	 */
 	gfp &= ~(__GFP_COMP);
 
-	pages = __iommu_alloc_buffer(dev, size, gfp, attrs);
+	/* For now always consider we are in a non-coherent case */
+	pages = __iommu_alloc_buffer(dev, size, gfp, attrs, NORMAL);
 	if (!pages)
 		return NULL;
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5a0a691d4..20384925b 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -872,7 +872,7 @@ config RELOCATABLE
 
 config RANDOMIZE_BASE
 	bool "Randomize the address of the kernel image"
-	select ARM64_MODULE_PLTS
+	select ARM64_MODULE_PLTS if MODULES
 	select RELOCATABLE
 	help
 	  Randomizes the virtual address at which the kernel image is
diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
index 8b4a7c915..080203e3a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi
@@ -670,7 +670,7 @@
 		#address-cells = <0>;
 
 		reg = <0x0 0xffb71000 0x0 0x1000>,
-		      <0x0 0xffb72000 0x0 0x1000>,
+		      <0x0 0xffb72000 0x0 0x2000>,
 		      <0x0 0xffb74000 0x0 0x2000>,
 		      <0x0 0xffb76000 0x0 0x2000>;
 		interrupts = <GIC_PPI 9
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 4fbf3c542..0800d23e2 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -151,7 +151,6 @@ static int debug_monitors_init(void)
 	/* Clear the OS lock. */
 	on_each_cpu(clear_os_lock, NULL, 1);
 	isb();
-	local_dbg_enable();
 
 	/* Register hotplug handler. */
 	__register_cpu_notifier(&os_lock_nb);
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 21ab5df9f..65d81f965 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -35,6 +35,7 @@
 #include <asm/sections.h>
 #include <asm/smp.h>
 #include <asm/suspend.h>
+#include <asm/sysreg.h>
 #include <asm/virt.h>
 
 /*
@@ -217,12 +218,22 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	set_pte(pte, __pte(virt_to_phys((void *)dst) |
 			 pgprot_val(PAGE_KERNEL_EXEC)));
 
-	/* Load our new page tables */
-	asm volatile("msr	ttbr0_el1, %0;"
-		     "isb;"
-		     "tlbi	vmalle1is;"
-		     "dsb	ish;"
-		     "isb" : : "r"(virt_to_phys(pgd)));
+	/*
+	 * Load our new page tables. A strict BBM approach requires that we
+	 * ensure that TLBs are free of any entries that may overlap with the
+	 * global mappings we are about to install.
+	 *
+	 * For a real hibernate/resume cycle TTBR0 currently points to a zero
+	 * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI
+	 * runtime services), while for a userspace-driven test_resume cycle it
+	 * points to userspace page tables (and we must point it at a zero page
+	 * ourselves). Elsewhere we only (un)install the idmap with preemption
+	 * disabled, so T0SZ should be as required regardless.
+	 */
+	cpu_set_reserved_ttbr0();
+	local_flush_tlb_all();
+	write_sysreg(virt_to_phys(pgd), ttbr0_el1);
+	isb();
 
 	*phys_dst_addr = virt_to_phys((void *)dst);
 
@@ -394,6 +405,38 @@ int swsusp_arch_resume(void)
 					  void *, phys_addr_t, phys_addr_t);
 
 	/*
+	 * Restoring the memory image will overwrite the ttbr1 page tables.
+	 * Create a second copy of just the linear map, and use this when
+	 * restoring.
+	 */
+	tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
+	if (!tmp_pg_dir) {
+		pr_err("Failed to allocate memory for temporary page tables.");
+		rc = -ENOMEM;
+		goto out;
+	}
+	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
+	if (rc)
+		goto out;
+
+	/*
+	 * Since we only copied the linear map, we need to find restore_pblist's
+	 * linear map address.
+	 */
+	lm_restore_pblist = LMADDR(restore_pblist);
+
+	/*
+	 * We need a zero page that is zero before & after resume in order to
+	 * to break before make on the ttbr1 page tables.
+	 */
+	zero_page = (void *)get_safe_page(GFP_ATOMIC);
+	if (!zero_page) {
+		pr_err("Failed to allocate zero page.");
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/*
 	 * Locate the exit code in the bottom-but-one page, so that *NULL
 	 * still has disastrous affects.
 	 */
@@ -419,27 +462,6 @@ int swsusp_arch_resume(void)
 	__flush_dcache_area(hibernate_exit, exit_size);
 
 	/*
-	 * Restoring the memory image will overwrite the ttbr1 page tables.
-	 * Create a second copy of just the linear map, and use this when
-	 * restoring.
-	 */
-	tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
-	if (!tmp_pg_dir) {
-		pr_err("Failed to allocate memory for temporary page tables.");
-		rc = -ENOMEM;
-		goto out;
-	}
-	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
-	if (rc)
-		goto out;
-
-	/*
-	 * Since we only copied the linear map, we need to find restore_pblist's
-	 * linear map address.
-	 */
-	lm_restore_pblist = LMADDR(restore_pblist);
-
-	/*
 	 * KASLR will cause the el2 vectors to be in a different location in
 	 * the resumed kernel. Load hibernate's temporary copy into el2.
 	 *
@@ -453,12 +475,6 @@ int swsusp_arch_resume(void)
 		__hyp_set_vectors(el2_vectors);
 	}
 
-	/*
-	 * We need a zero page that is zero before & after resume in order to
-	 * to break before make on the ttbr1 page tables.
-	 */
-	zero_page = (void *)get_safe_page(GFP_ATOMIC);
-
 	hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1,
 		       resume_hdr.reenter_kernel, lm_restore_pblist,
 		       resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page));
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 62ff3c062..490db85de 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -267,7 +267,6 @@ asmlinkage void secondary_start_kernel(void)
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
-	local_dbg_enable();
 	local_irq_enable();
 	local_async_enable();
 
@@ -437,9 +436,9 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 void __init smp_prepare_boot_cpu(void)
 {
+	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 	cpuinfo_store_boot_cpu();
 	save_boot_cpu_run_el();
-	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 }
 
 static u64 __init of_get_cpu_mpidr(struct device_node *dn)
@@ -694,6 +693,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	smp_store_cpu_info(smp_processor_id());
 
 	/*
+	 * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set
+	 * secondary CPUs present.
+	 */
+	if (max_cpus == 0)
+		return;
+
+	/*
 	 * Initialise the present map (which describes the set of CPUs
 	 * actually populated at the present time) and release the
 	 * secondaries from the bootloader.
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 435e820e8..e564d4595 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -181,9 +181,9 @@ SECTIONS
 		*(.hash)
 	}
 
-	__rela_offset	= ADDR(.rela) - KIMAGE_VADDR;
+	__rela_offset	= ABSOLUTE(ADDR(.rela) - KIMAGE_VADDR);
 	__rela_size	= SIZEOF(.rela);
-	__dynsym_offset	= ADDR(.dynsym) - KIMAGE_VADDR;
+	__dynsym_offset	= ABSOLUTE(ADDR(.dynsym) - KIMAGE_VADDR);
 
 	. = ALIGN(SEGMENT_ALIGN);
 	__init_end = .;
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 0f7c40eb3..934137647 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -27,8 +27,8 @@ static void __hyp_text __sysreg_do_nothing(struct kvm_cpu_context *ctxt) { }
 /*
  * Non-VHE: Both host and guest must save everything.
  *
- * VHE: Host must save tpidr*_el[01], actlr_el1, sp0, pc, pstate, and
- * guest must save everything.
+ * VHE: Host must save tpidr*_el[01], actlr_el1, mdscr_el1, sp0, pc,
+ * pstate, and guest must save everything.
  */
 
 static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
@@ -37,6 +37,7 @@ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 	ctxt->sys_regs[TPIDR_EL0]	= read_sysreg(tpidr_el0);
 	ctxt->sys_regs[TPIDRRO_EL0]	= read_sysreg(tpidrro_el0);
 	ctxt->sys_regs[TPIDR_EL1]	= read_sysreg(tpidr_el1);
+	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 	ctxt->gp_regs.regs.sp		= read_sysreg(sp_el0);
 	ctxt->gp_regs.regs.pc		= read_sysreg_el2(elr);
 	ctxt->gp_regs.regs.pstate	= read_sysreg_el2(spsr);
@@ -61,7 +62,6 @@ static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
 	ctxt->sys_regs[AMAIR_EL1]	= read_sysreg_el1(amair);
 	ctxt->sys_regs[CNTKCTL_EL1]	= read_sysreg_el1(cntkctl);
 	ctxt->sys_regs[PAR_EL1]		= read_sysreg(par_el1);
-	ctxt->sys_regs[MDSCR_EL1]	= read_sysreg(mdscr_el1);
 
 	ctxt->gp_regs.sp_el1		= read_sysreg(sp_el1);
 	ctxt->gp_regs.elr_el1		= read_sysreg_el1(elr);
@@ -90,6 +90,7 @@ static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctx
 	write_sysreg(ctxt->sys_regs[TPIDR_EL0],	  tpidr_el0);
 	write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
 	write_sysreg(ctxt->sys_regs[TPIDR_EL1],	  tpidr_el1);
+	write_sysreg(ctxt->sys_regs[MDSCR_EL1],	  mdscr_el1);
 	write_sysreg(ctxt->gp_regs.regs.sp,	  sp_el0);
 	write_sysreg_el2(ctxt->gp_regs.regs.pc,	  elr);
 	write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr);
@@ -114,7 +115,6 @@ static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
 	write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1],	amair);
 	write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], 	cntkctl);
 	write_sysreg(ctxt->sys_regs[PAR_EL1],		par_el1);
-	write_sysreg(ctxt->sys_regs[MDSCR_EL1],		mdscr_el1);
 
 	write_sysreg(ctxt->gp_regs.sp_el1,		sp_el1);
 	write_sysreg_el1(ctxt->gp_regs.elr_el1,		elr);
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index e9e0e6db7..898c0e6ae 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -132,16 +132,14 @@ static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
 static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	bool is_aarch32;
+	bool is_aarch32 = vcpu_mode_is_32bit(vcpu);
 	u32 esr = 0;
 
-	is_aarch32 = vcpu_mode_is_32bit(vcpu);
-
-	*vcpu_spsr(vcpu) = cpsr;
 	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
-
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
+
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_spsr(vcpu) = cpsr;
 
 	vcpu_sys_reg(vcpu, FAR_EL1) = addr;
 
@@ -172,11 +170,11 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
 	u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
 
-	*vcpu_spsr(vcpu) = cpsr;
 	*vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
-
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
+
 	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_spsr(vcpu) = cpsr;
 
 	/*
 	 * Build an unknown exception, depending on the instruction
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 0f85a46c3..3e90a2cad 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -748,9 +748,9 @@ void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
 	/*
 	 * Check whether the physical FDT address is set and meets the minimum
 	 * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
-	 * at least 8 bytes so that we can always access the size field of the
-	 * FDT header after mapping the first chunk, double check here if that
-	 * is indeed the case.
+	 * at least 8 bytes so that we can always access the magic and size
+	 * fields of the FDT header after mapping the first chunk, double check
+	 * here if that is indeed the case.
 	 */
 	BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
 	if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
@@ -778,7 +778,7 @@ void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
 	create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE),
 			dt_virt_base, SWAPPER_BLOCK_SIZE, prot);
 
-	if (fdt_check_header(dt_virt) != 0)
+	if (fdt_magic(dt_virt) != FDT_MAGIC)
 		return NULL;
 
 	*size = fdt_totalsize(dt_virt);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index c4317879b..5bb61de23 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -180,6 +180,8 @@ ENTRY(__cpu_setup)
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
 	mov	x0, #1 << 12			// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x0			// access to the DCC from EL0
+	isb					// Unmask debug exceptions now,
+	enable_dbg				// since this is per-cpu
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	/*
 	 * Memory region attributes for LPAE:
diff --git a/arch/metag/include/asm/cmpxchg_lnkget.h b/arch/metag/include/asm/cmpxchg_lnkget.h
index 0154e2807..2369ad394 100644
--- a/arch/metag/include/asm/cmpxchg_lnkget.h
+++ b/arch/metag/include/asm/cmpxchg_lnkget.h
@@ -73,7 +73,7 @@ static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
 		      "	DCACHE	[%2], %0\n"
 #endif
 		      "2:\n"
-		      : "=&d" (temp), "=&da" (retval)
+		      : "=&d" (temp), "=&d" (retval)
 		      : "da" (m), "bd" (old), "da" (new)
 		      : "cc"
 		      );
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index e4c21bbf9..804d2a2a1 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -276,12 +276,7 @@ int r4k_clockevent_init(void)
 				  CLOCK_EVT_FEAT_C3STOP |
 				  CLOCK_EVT_FEAT_PERCPU;
 
-	clockevent_set_clock(cd, mips_hpt_frequency);
-
-	/* Calculate the min / max delta */
-	cd->max_delta_ns	= clockevent_delta2ns(0x7fffffff, cd);
 	min_delta		= calculate_min_delta();
-	cd->min_delta_ns	= clockevent_delta2ns(min_delta, cd);
 
 	cd->rating		= 300;
 	cd->irq			= irq;
@@ -289,7 +284,7 @@ int r4k_clockevent_init(void)
 	cd->set_next_event	= mips_next_event;
 	cd->event_handler	= mips_event_handler;
 
-	clockevents_register_device(cd);
+	clockevents_config_and_register(cd, mips_hpt_frequency, min_delta, 0x7fffffff);
 
 	if (cp0_timer_irq_installed)
 		return 0;
diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
index 1f910563f..d76275da5 100644
--- a/arch/mips/kernel/csrc-r4k.c
+++ b/arch/mips/kernel/csrc-r4k.c
@@ -23,7 +23,7 @@ static struct clocksource clocksource_mips = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static u64 notrace r4k_read_sched_clock(void)
+static u64 __maybe_unused notrace r4k_read_sched_clock(void)
 {
 	return read_c0_count();
 }
@@ -82,7 +82,9 @@ int __init init_r4k_clocksource(void)
 
 	clocksource_register_hz(&clocksource_mips, mips_hpt_frequency);
 
+#ifndef CONFIG_CPU_FREQ
 	sched_clock_register(r4k_read_sched_clock, 32, mips_hpt_frequency);
+#endif
 
 	return 0;
 }
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 645c8a198..2b42a74ed 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1615,8 +1615,14 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 
 	preempt_disable();
 	if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) {
-		if (kvm_mips_host_tlb_lookup(vcpu, va) < 0)
-			kvm_mips_handle_kseg0_tlb_fault(va, vcpu);
+		if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 &&
+		    kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) {
+			kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n",
+				__func__, va, vcpu, read_c0_entryhi());
+			er = EMULATE_FAIL;
+			preempt_enable();
+			goto done;
+		}
 	} else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) ||
 		   KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) {
 		int index;
@@ -1654,14 +1660,19 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 								run, vcpu);
 				preempt_enable();
 				goto dont_update_pc;
-			} else {
-				/*
-				 * We fault an entry from the guest tlb to the
-				 * shadow host TLB
-				 */
-				kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
-								     NULL,
-								     NULL);
+			}
+			/*
+			 * We fault an entry from the guest tlb to the
+			 * shadow host TLB
+			 */
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
+								 NULL, NULL)) {
+				kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, va, index, vcpu,
+					read_c0_entryhi());
+				er = EMULATE_FAIL;
+				preempt_enable();
+				goto done;
 			}
 		}
 	} else {
@@ -2625,8 +2636,13 @@ enum emulation_result kvm_mips_handle_tlbmiss(unsigned long cause,
 			 * OK we have a Guest TLB entry, now inject it into the
 			 * shadow host TLB
 			 */
-			kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, NULL,
-							     NULL);
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
+								 NULL, NULL)) {
+				kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, va, index, vcpu,
+					read_c0_entryhi());
+				er = EMULATE_FAIL;
+			}
 		}
 	}
 
diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c
index ed021ae78..ad2270ff8 100644
--- a/arch/mips/kvm/tlb.c
+++ b/arch/mips/kvm/tlb.c
@@ -284,7 +284,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr,
 	}
 
 	gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT);
-	if (gfn >= kvm->arch.guest_pmap_npages) {
+	if ((gfn | 1) >= kvm->arch.guest_pmap_npages) {
 		kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__,
 			gfn, badvaddr);
 		kvm_mips_dump_host_tlbs();
@@ -373,26 +373,40 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
 	unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
 	struct kvm *kvm = vcpu->kvm;
 	kvm_pfn_t pfn0, pfn1;
+	gfn_t gfn0, gfn1;
+	long tlb_lo[2];
 	int ret;
 
-	if ((tlb->tlb_hi & VPN2_MASK) == 0) {
-		pfn0 = 0;
-		pfn1 = 0;
-	} else {
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
-					   >> PAGE_SHIFT) < 0)
-			return -1;
-
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
-					   >> PAGE_SHIFT) < 0)
-			return -1;
-
-		pfn0 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
-					    >> PAGE_SHIFT];
-		pfn1 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
-					    >> PAGE_SHIFT];
+	tlb_lo[0] = tlb->tlb_lo0;
+	tlb_lo[1] = tlb->tlb_lo1;
+
+	/*
+	 * The commpage address must not be mapped to anything else if the guest
+	 * TLB contains entries nearby, or commpage accesses will break.
+	 */
+	if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) &
+			VPN2_MASK & (PAGE_MASK << 1)))
+		tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0;
+
+	gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT;
+	gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT;
+	if (gfn0 >= kvm->arch.guest_pmap_npages ||
+	    gfn1 >= kvm->arch.guest_pmap_npages) {
+		kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n",
+			__func__, gfn0, gfn1, tlb->tlb_hi);
+		kvm_mips_dump_guest_tlbs(vcpu);
+		return -1;
 	}
 
+	if (kvm_mips_map_page(kvm, gfn0) < 0)
+		return -1;
+
+	if (kvm_mips_map_page(kvm, gfn1) < 0)
+		return -1;
+
+	pfn0 = kvm->arch.guest_pmap[gfn0];
+	pfn1 = kvm->arch.guest_pmap[gfn1];
+
 	if (hpa0)
 		*hpa0 = pfn0 << PAGE_SHIFT;
 
@@ -401,9 +415,9 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
 
 	/* Get attributes from the Guest TLB */
 	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
-		   (tlb->tlb_lo0 & MIPS3_PG_D) | (tlb->tlb_lo0 & MIPS3_PG_V);
+		   (tlb_lo[0] & MIPS3_PG_D) | (tlb_lo[0] & MIPS3_PG_V);
 	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) |
-		   (tlb->tlb_lo1 & MIPS3_PG_D) | (tlb->tlb_lo1 & MIPS3_PG_V);
+		   (tlb_lo[1] & MIPS3_PG_D) | (tlb_lo[1] & MIPS3_PG_V);
 
 	kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
 		  tlb->tlb_lo0, tlb->tlb_lo1);
@@ -776,10 +790,16 @@ uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu)
 				local_irq_restore(flags);
 				return KVM_INVALID_INST;
 			}
-			kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
-							     &vcpu->arch.
-							     guest_tlb[index],
-							     NULL, NULL);
+			if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
+						&vcpu->arch.guest_tlb[index],
+						NULL, NULL)) {
+				kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n",
+					__func__, opc, index, vcpu,
+					read_c0_entryhi());
+				kvm_mips_dump_guest_tlbs(vcpu);
+				local_irq_restore(flags);
+				return KVM_INVALID_INST;
+			}
 			inst = *(opc);
 		}
 		local_irq_restore(flags);
diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c
index 249039af6..4788bea62 100644
--- a/arch/mips/loongson64/loongson-3/hpet.c
+++ b/arch/mips/loongson64/loongson-3/hpet.c
@@ -13,8 +13,8 @@
 #define SMBUS_PCI_REG64		0x64
 #define SMBUS_PCI_REGB4		0xb4
 
-#define HPET_MIN_CYCLES		64
-#define HPET_MIN_PROG_DELTA	(HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
+#define HPET_MIN_CYCLES		16
+#define HPET_MIN_PROG_DELTA	(HPET_MIN_CYCLES * 12)
 
 static DEFINE_SPINLOCK(hpet_lock);
 DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device);
@@ -157,14 +157,14 @@ static int hpet_tick_resume(struct clock_event_device *evt)
 static int hpet_next_event(unsigned long delta,
 		struct clock_event_device *evt)
 {
-	unsigned int cnt;
-	int res;
+	u32 cnt;
+	s32 res;
 
 	cnt = hpet_read(HPET_COUNTER);
-	cnt += delta;
+	cnt += (u32) delta;
 	hpet_write(HPET_T0_CMP, cnt);
 
-	res = (int)(cnt - hpet_read(HPET_COUNTER));
+	res = (s32)(cnt - hpet_read(HPET_COUNTER));
 
 	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
@@ -230,7 +230,7 @@ void __init setup_hpet_timer(void)
 
 	cd = &per_cpu(hpet_clockevent_device, cpu);
 	cd->name = "hpet";
-	cd->rating = 320;
+	cd->rating = 100;
 	cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	cd->set_state_shutdown = hpet_set_state_shutdown;
 	cd->set_state_periodic = hpet_set_state_periodic;
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index 9c2220a45..45e3b8799 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -65,7 +65,7 @@ static struct insn insn_table[] = {
 #ifndef CONFIG_CPU_MIPSR6
 	{ insn_cache,  M(cache_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 #else
-	{ insn_cache,  M6(cache_op, 0, 0, 0, cache6_op),  RS | RT | SIMM9 },
+	{ insn_cache,  M6(spec3_op, 0, 0, 0, cache6_op),  RS | RT | SIMM9 },
 #endif
 	{ insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
 	{ insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD },
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index b7019b559..298afcf3b 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -338,8 +338,6 @@ _GLOBAL(__tm_recheckpoint)
 	 */
 	subi	r7, r7, STACK_FRAME_OVERHEAD
 
-	SET_SCRATCH0(r1)
-
 	mfmsr	r6
 	/* R4 = original MSR to indicate whether thread used FP/Vector etc. */
 
@@ -468,6 +466,7 @@ restore_gprs:
 	 * until we turn MSR RI back on.
 	 */
 
+	SET_SCRATCH0(r1)
 	ld	r5, -8(r1)
 	ld	r1, -16(r1)
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e571ad277..38e108eae 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -655,112 +655,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 BEGIN_FTR_SECTION
-	b	skip_tm
-END_FTR_SECTION_IFCLR(CPU_FTR_TM)
-
-	/* Turn on TM/FP/VSX/VMX so we can restore them. */
-	mfmsr	r5
-	li	r6, MSR_TM >> 32
-	sldi	r6, r6, 32
-	or	r5, r5, r6
-	ori	r5, r5, MSR_FP
-	oris	r5, r5, (MSR_VEC | MSR_VSX)@h
-	mtmsrd	r5
-
-	/*
-	 * The user may change these outside of a transaction, so they must
-	 * always be context switched.
-	 */
-	ld	r5, VCPU_TFHAR(r4)
-	ld	r6, VCPU_TFIAR(r4)
-	ld	r7, VCPU_TEXASR(r4)
-	mtspr	SPRN_TFHAR, r5
-	mtspr	SPRN_TFIAR, r6
-	mtspr	SPRN_TEXASR, r7
-
-	ld	r5, VCPU_MSR(r4)
-	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
-	beq	skip_tm	/* TM not active in guest */
-
-	/* Make sure the failure summary is set, otherwise we'll program check
-	 * when we trechkpt.  It's possible that this might have been not set
-	 * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
-	 * host.
-	 */
-	oris	r7, r7, (TEXASR_FS)@h
-	mtspr	SPRN_TEXASR, r7
-
-	/*
-	 * We need to load up the checkpointed state for the guest.
-	 * We need to do this early as it will blow away any GPRs, VSRs and
-	 * some SPRs.
-	 */
-
-	mr	r31, r4
-	addi	r3, r31, VCPU_FPRS_TM
-	bl	load_fp_state
-	addi	r3, r31, VCPU_VRS_TM
-	bl	load_vr_state
-	mr	r4, r31
-	lwz	r7, VCPU_VRSAVE_TM(r4)
-	mtspr	SPRN_VRSAVE, r7
-
-	ld	r5, VCPU_LR_TM(r4)
-	lwz	r6, VCPU_CR_TM(r4)
-	ld	r7, VCPU_CTR_TM(r4)
-	ld	r8, VCPU_AMR_TM(r4)
-	ld	r9, VCPU_TAR_TM(r4)
-	mtlr	r5
-	mtcr	r6
-	mtctr	r7
-	mtspr	SPRN_AMR, r8
-	mtspr	SPRN_TAR, r9
-
-	/*
-	 * Load up PPR and DSCR values but don't put them in the actual SPRs
-	 * till the last moment to avoid running with userspace PPR and DSCR for
-	 * too long.
-	 */
-	ld	r29, VCPU_DSCR_TM(r4)
-	ld	r30, VCPU_PPR_TM(r4)
-
-	std	r2, PACATMSCRATCH(r13) /* Save TOC */
-
-	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
-	li	r5, 0
-	mtmsrd	r5, 1
-
-	/* Load GPRs r0-r28 */
-	reg = 0
-	.rept	29
-	ld	reg, VCPU_GPRS_TM(reg)(r31)
-	reg = reg + 1
-	.endr
-
-	mtspr	SPRN_DSCR, r29
-	mtspr	SPRN_PPR, r30
-
-	/* Load final GPRs */
-	ld	29, VCPU_GPRS_TM(29)(r31)
-	ld	30, VCPU_GPRS_TM(30)(r31)
-	ld	31, VCPU_GPRS_TM(31)(r31)
-
-	/* TM checkpointed state is now setup.  All GPRs are now volatile. */
-	TRECHKPT
-
-	/* Now let's get back the state we need. */
-	HMT_MEDIUM
-	GET_PACA(r13)
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-	ld	r4, HSTATE_KVM_VCPU(r13)
-	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATMSCRATCH(r13)
-
-	/* Set the MSR RI since we have our registers back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-skip_tm:
+	bl	kvmppc_restore_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 
 	/* Load guest PMU registers */
@@ -841,12 +737,6 @@ BEGIN_FTR_SECTION
 	/* Skip next section on POWER7 */
 	b	8f
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
-	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
-	mfmsr	r8
-	li	r0, 1
-	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r8
-
 	/* Load up POWER8-specific registers */
 	ld	r5, VCPU_IAMR(r4)
 	lwz	r6, VCPU_PSPB(r4)
@@ -1436,106 +1326,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 BEGIN_FTR_SECTION
-	b	2f
-END_FTR_SECTION_IFCLR(CPU_FTR_TM)
-	/* Turn on TM. */
-	mfmsr	r8
-	li	r0, 1
-	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r8
-
-	ld	r5, VCPU_MSR(r9)
-	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
-	beq	1f	/* TM not active in guest. */
-
-	li	r3, TM_CAUSE_KVM_RESCHED
-
-	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
-	li	r5, 0
-	mtmsrd	r5, 1
-
-	/* All GPRs are volatile at this point. */
-	TRECLAIM(R3)
-
-	/* Temporarily store r13 and r9 so we have some regs to play with */
-	SET_SCRATCH0(r13)
-	GET_PACA(r13)
-	std	r9, PACATMSCRATCH(r13)
-	ld	r9, HSTATE_KVM_VCPU(r13)
-
-	/* Get a few more GPRs free. */
-	std	r29, VCPU_GPRS_TM(29)(r9)
-	std	r30, VCPU_GPRS_TM(30)(r9)
-	std	r31, VCPU_GPRS_TM(31)(r9)
-
-	/* Save away PPR and DSCR soon so don't run with user values. */
-	mfspr	r31, SPRN_PPR
-	HMT_MEDIUM
-	mfspr	r30, SPRN_DSCR
-	ld	r29, HSTATE_DSCR(r13)
-	mtspr	SPRN_DSCR, r29
-
-	/* Save all but r9, r13 & r29-r31 */
-	reg = 0
-	.rept	29
-	.if (reg != 9) && (reg != 13)
-	std	reg, VCPU_GPRS_TM(reg)(r9)
-	.endif
-	reg = reg + 1
-	.endr
-	/* ... now save r13 */
-	GET_SCRATCH0(r4)
-	std	r4, VCPU_GPRS_TM(13)(r9)
-	/* ... and save r9 */
-	ld	r4, PACATMSCRATCH(r13)
-	std	r4, VCPU_GPRS_TM(9)(r9)
-
-	/* Reload stack pointer and TOC. */
-	ld	r1, HSTATE_HOST_R1(r13)
-	ld	r2, PACATOC(r13)
-
-	/* Set MSR RI now we have r1 and r13 back. */
-	li	r5, MSR_RI
-	mtmsrd	r5, 1
-
-	/* Save away checkpinted SPRs. */
-	std	r31, VCPU_PPR_TM(r9)
-	std	r30, VCPU_DSCR_TM(r9)
-	mflr	r5
-	mfcr	r6
-	mfctr	r7
-	mfspr	r8, SPRN_AMR
-	mfspr	r10, SPRN_TAR
-	std	r5, VCPU_LR_TM(r9)
-	stw	r6, VCPU_CR_TM(r9)
-	std	r7, VCPU_CTR_TM(r9)
-	std	r8, VCPU_AMR_TM(r9)
-	std	r10, VCPU_TAR_TM(r9)
-
-	/* Restore r12 as trap number. */
-	lwz	r12, VCPU_TRAP(r9)
-
-	/* Save FP/VSX. */
-	addi	r3, r9, VCPU_FPRS_TM
-	bl	store_fp_state
-	addi	r3, r9, VCPU_VRS_TM
-	bl	store_vr_state
-	mfspr	r6, SPRN_VRSAVE
-	stw	r6, VCPU_VRSAVE_TM(r9)
-1:
-	/*
-	 * We need to save these SPRs after the treclaim so that the software
-	 * error code is recorded correctly in the TEXASR.  Also the user may
-	 * change these outside of a transaction, so they must always be
-	 * context switched.
-	 */
-	mfspr	r5, SPRN_TFHAR
-	mfspr	r6, SPRN_TFIAR
-	mfspr	r7, SPRN_TEXASR
-	std	r5, VCPU_TFHAR(r9)
-	std	r6, VCPU_TFIAR(r9)
-	std	r7, VCPU_TEXASR(r9)
-2:
+	bl	kvmppc_save_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 
 	/* Increment yield count if they have a VPA */
@@ -2245,6 +2037,13 @@ _GLOBAL(kvmppc_h_cede)		/* r3 = vcpu pointer, r11 = msr, r13 = paca */
 	/* save FP state */
 	bl	kvmppc_save_fp
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	bl	kvmppc_save_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+
 	/*
 	 * Set DEC to the smaller of DEC and HDEC, so that we wake
 	 * no later than the end of our timeslice (HDEC interrupts
@@ -2321,6 +2120,12 @@ kvm_end_cede:
 	bl	kvmhv_accumulate_time
 #endif
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	bl	kvmppc_restore_tm
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
+
 	/* load up FP state */
 	bl	kvmppc_load_fp
 
@@ -2631,6 +2436,239 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	mr	r4,r31
 	blr
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+/*
+ * Save transactional state and TM-related registers.
+ * Called with r9 pointing to the vcpu struct.
+ * This can modify all checkpointed registers, but
+ * restores r1, r2 and r9 (vcpu pointer) before exit.
+ */
+kvmppc_save_tm:
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+
+	/* Turn on TM. */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	ld	r5, VCPU_MSR(r9)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beq	1f	/* TM not active in guest. */
+
+	std	r1, HSTATE_HOST_R1(r13)
+	li	r3, TM_CAUSE_KVM_RESCHED
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* All GPRs are volatile at this point. */
+	TRECLAIM(R3)
+
+	/* Temporarily store r13 and r9 so we have some regs to play with */
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r9, PACATMSCRATCH(r13)
+	ld	r9, HSTATE_KVM_VCPU(r13)
+
+	/* Get a few more GPRs free. */
+	std	r29, VCPU_GPRS_TM(29)(r9)
+	std	r30, VCPU_GPRS_TM(30)(r9)
+	std	r31, VCPU_GPRS_TM(31)(r9)
+
+	/* Save away PPR and DSCR soon so don't run with user values. */
+	mfspr	r31, SPRN_PPR
+	HMT_MEDIUM
+	mfspr	r30, SPRN_DSCR
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+
+	/* Save all but r9, r13 & r29-r31 */
+	reg = 0
+	.rept	29
+	.if (reg != 9) && (reg != 13)
+	std	reg, VCPU_GPRS_TM(reg)(r9)
+	.endif
+	reg = reg + 1
+	.endr
+	/* ... now save r13 */
+	GET_SCRATCH0(r4)
+	std	r4, VCPU_GPRS_TM(13)(r9)
+	/* ... and save r9 */
+	ld	r4, PACATMSCRATCH(r13)
+	std	r4, VCPU_GPRS_TM(9)(r9)
+
+	/* Reload stack pointer and TOC. */
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATOC(r13)
+
+	/* Set MSR RI now we have r1 and r13 back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	/* Save away checkpinted SPRs. */
+	std	r31, VCPU_PPR_TM(r9)
+	std	r30, VCPU_DSCR_TM(r9)
+	mflr	r5
+	mfcr	r6
+	mfctr	r7
+	mfspr	r8, SPRN_AMR
+	mfspr	r10, SPRN_TAR
+	std	r5, VCPU_LR_TM(r9)
+	stw	r6, VCPU_CR_TM(r9)
+	std	r7, VCPU_CTR_TM(r9)
+	std	r8, VCPU_AMR_TM(r9)
+	std	r10, VCPU_TAR_TM(r9)
+
+	/* Restore r12 as trap number. */
+	lwz	r12, VCPU_TRAP(r9)
+
+	/* Save FP/VSX. */
+	addi	r3, r9, VCPU_FPRS_TM
+	bl	store_fp_state
+	addi	r3, r9, VCPU_VRS_TM
+	bl	store_vr_state
+	mfspr	r6, SPRN_VRSAVE
+	stw	r6, VCPU_VRSAVE_TM(r9)
+1:
+	/*
+	 * We need to save these SPRs after the treclaim so that the software
+	 * error code is recorded correctly in the TEXASR.  Also the user may
+	 * change these outside of a transaction, so they must always be
+	 * context switched.
+	 */
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	mfspr	r7, SPRN_TEXASR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+	std	r7, VCPU_TEXASR(r9)
+
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+
+/*
+ * Restore transactional state and TM-related registers.
+ * Called with r4 pointing to the vcpu struct.
+ * This potentially modifies all checkpointed registers.
+ * It restores r1, r2, r4 from the PACA.
+ */
+kvmppc_restore_tm:
+	mflr	r0
+	std	r0, PPC_LR_STKOFF(r1)
+
+	/* Turn on TM/FP/VSX/VMX so we can restore them. */
+	mfmsr	r5
+	li	r6, MSR_TM >> 32
+	sldi	r6, r6, 32
+	or	r5, r5, r6
+	ori	r5, r5, MSR_FP
+	oris	r5, r5, (MSR_VEC | MSR_VSX)@h
+	mtmsrd	r5
+
+	/*
+	 * The user may change these outside of a transaction, so they must
+	 * always be context switched.
+	 */
+	ld	r5, VCPU_TFHAR(r4)
+	ld	r6, VCPU_TFIAR(r4)
+	ld	r7, VCPU_TEXASR(r4)
+	mtspr	SPRN_TFHAR, r5
+	mtspr	SPRN_TFIAR, r6
+	mtspr	SPRN_TEXASR, r7
+
+	ld	r5, VCPU_MSR(r4)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beqlr		/* TM not active in guest */
+	std	r1, HSTATE_HOST_R1(r13)
+
+	/* Make sure the failure summary is set, otherwise we'll program check
+	 * when we trechkpt.  It's possible that this might have been not set
+	 * on a kvmppc_set_one_reg() call but we shouldn't let this crash the
+	 * host.
+	 */
+	oris	r7, r7, (TEXASR_FS)@h
+	mtspr	SPRN_TEXASR, r7
+
+	/*
+	 * We need to load up the checkpointed state for the guest.
+	 * We need to do this early as it will blow away any GPRs, VSRs and
+	 * some SPRs.
+	 */
+
+	mr	r31, r4
+	addi	r3, r31, VCPU_FPRS_TM
+	bl	load_fp_state
+	addi	r3, r31, VCPU_VRS_TM
+	bl	load_vr_state
+	mr	r4, r31
+	lwz	r7, VCPU_VRSAVE_TM(r4)
+	mtspr	SPRN_VRSAVE, r7
+
+	ld	r5, VCPU_LR_TM(r4)
+	lwz	r6, VCPU_CR_TM(r4)
+	ld	r7, VCPU_CTR_TM(r4)
+	ld	r8, VCPU_AMR_TM(r4)
+	ld	r9, VCPU_TAR_TM(r4)
+	mtlr	r5
+	mtcr	r6
+	mtctr	r7
+	mtspr	SPRN_AMR, r8
+	mtspr	SPRN_TAR, r9
+
+	/*
+	 * Load up PPR and DSCR values but don't put them in the actual SPRs
+	 * till the last moment to avoid running with userspace PPR and DSCR for
+	 * too long.
+	 */
+	ld	r29, VCPU_DSCR_TM(r4)
+	ld	r30, VCPU_PPR_TM(r4)
+
+	std	r2, PACATMSCRATCH(r13) /* Save TOC */
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* Load GPRs r0-r28 */
+	reg = 0
+	.rept	29
+	ld	reg, VCPU_GPRS_TM(reg)(r31)
+	reg = reg + 1
+	.endr
+
+	mtspr	SPRN_DSCR, r29
+	mtspr	SPRN_PPR, r30
+
+	/* Load final GPRs */
+	ld	29, VCPU_GPRS_TM(29)(r31)
+	ld	30, VCPU_GPRS_TM(30)(r31)
+	ld	31, VCPU_GPRS_TM(31)(r31)
+
+	/* TM checkpointed state is now setup.  All GPRs are now volatile. */
+	TRECHKPT
+
+	/* Now let's get back the state we need. */
+	HMT_MEDIUM
+	GET_PACA(r13)
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+	ld	r4, HSTATE_KVM_VCPU(r13)
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATMSCRATCH(r13)
+
+	/* Set the MSR RI since we have our registers back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+#endif
+
 /*
  * We come here if we get any exception or interrupt while we are
  * executing host real mode code while in guest MMU context.
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 18d2beb89..42b968a85 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -893,7 +893,7 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long address);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char key, bool nq);
-unsigned char get_guest_storage_key(struct mm_struct *mm, unsigned long addr);
+unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr);
 
 /*
  * Certain architectures need to do special things when PTEs
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index a2e6ef32e..0a2031618 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -81,7 +81,8 @@ static inline void __tlb_flush_full(struct mm_struct *mm)
 }
 
 /*
- * Flush TLB entries for a specific ASCE on all CPUs.
+ * Flush TLB entries for a specific ASCE on all CPUs. Should never be used
+ * when more than one asce (e.g. gmap) ran on this mm.
  */
 static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
 {
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index cace818d8..313c3b8cf 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -85,7 +85,7 @@ EXPORT_SYMBOL_GPL(gmap_alloc);
 static void gmap_flush_tlb(struct gmap *gmap)
 {
 	if (MACHINE_HAS_IDTE)
-		__tlb_flush_asce(gmap->mm, gmap->asce);
+		__tlb_flush_idte(gmap->asce);
 	else
 		__tlb_flush_global();
 }
@@ -124,7 +124,7 @@ void gmap_free(struct gmap *gmap)
 
 	/* Flush tlb. */
 	if (MACHINE_HAS_IDTE)
-		__tlb_flush_asce(gmap->mm, gmap->asce);
+		__tlb_flush_idte(gmap->asce);
 	else
 		__tlb_flush_global();
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 9f0ce0e6e..ebb4f8711 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -543,7 +543,7 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 }
 EXPORT_SYMBOL(set_guest_storage_key);
 
-unsigned char get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
+unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
 {
 	unsigned char key;
 	spinlock_t *ptl;
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 8acaf4e38..a86d7cc2c 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -15,6 +15,7 @@
 #include <kern_util.h>
 #include <os.h>
 #include <sysdep/mcontext.h>
+#include <um_malloc.h>
 
 void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = {
 	[SIGTRAP]	= relay_signal,
@@ -32,7 +33,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
 	struct uml_pt_regs *r;
 	int save_errno = errno;
 
-	r = malloc(sizeof(struct uml_pt_regs));
+	r = uml_kmalloc(sizeof(struct uml_pt_regs), UM_GFP_ATOMIC);
 	if (!r)
 		panic("out of memory");
 
@@ -91,7 +92,7 @@ static void timer_real_alarm_handler(mcontext_t *mc)
 {
 	struct uml_pt_regs *regs;
 
-	regs = malloc(sizeof(struct uml_pt_regs));
+	regs = uml_kmalloc(sizeof(struct uml_pt_regs), UM_GFP_ATOMIC);
 	if (!regs)
 		panic("out of memory");
 
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index e35632ef2..62dfc644c 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -98,7 +98,7 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm,
 }
 
 static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
-		bool write, bool foreign)
+		bool write, bool execute, bool foreign)
 {
 	/* by default, allow everything */
 	return true;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 874e8bd64..bd136ac14 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2546,7 +2546,7 @@ void hswep_uncore_cpu_init(void)
 
 static struct intel_uncore_type hswep_uncore_ha = {
 	.name		= "ha",
-	.num_counters   = 5,
+	.num_counters   = 4,
 	.num_boxes	= 2,
 	.perf_ctr_bits	= 48,
 	SNBEP_UNCORE_PCI_COMMON_INIT(),
@@ -2565,7 +2565,7 @@ static struct uncore_event_desc hswep_uncore_imc_events[] = {
 
 static struct intel_uncore_type hswep_uncore_imc = {
 	.name		= "imc",
-	.num_counters   = 5,
+	.num_counters   = 4,
 	.num_boxes	= 8,
 	.perf_ctr_bits	= 48,
 	.fixed_ctr_bits	= 48,
@@ -2611,7 +2611,7 @@ static struct intel_uncore_type hswep_uncore_irp = {
 
 static struct intel_uncore_type hswep_uncore_qpi = {
 	.name			= "qpi",
-	.num_counters		= 5,
+	.num_counters		= 4,
 	.num_boxes		= 3,
 	.perf_ctr_bits		= 48,
 	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
@@ -2693,7 +2693,7 @@ static struct event_constraint hswep_uncore_r3qpi_constraints[] = {
 
 static struct intel_uncore_type hswep_uncore_r3qpi = {
 	.name		= "r3qpi",
-	.num_counters   = 4,
+	.num_counters   = 3,
 	.num_boxes	= 3,
 	.perf_ctr_bits	= 44,
 	.constraints	= hswep_uncore_r3qpi_constraints,
@@ -2892,7 +2892,7 @@ static struct intel_uncore_type bdx_uncore_ha = {
 
 static struct intel_uncore_type bdx_uncore_imc = {
 	.name		= "imc",
-	.num_counters   = 5,
+	.num_counters   = 4,
 	.num_boxes	= 8,
 	.perf_ctr_bits	= 48,
 	.fixed_ctr_bits	= 48,
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index c146f3c26..0149ac59c 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -539,6 +539,7 @@ static void mtrr_lookup_var_start(struct mtrr_iter *iter)
 
 	iter->fixed = false;
 	iter->start_max = iter->start;
+	iter->range = NULL;
 	iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node);
 
 	__mtrr_lookup_var_next(iter);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 64a79f271..8326d6891 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8224,6 +8224,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
+			exit_reason != EXIT_REASON_PML_FULL &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -8854,6 +8855,22 @@ static void vmx_load_vmcs01(struct kvm_vcpu *vcpu)
 	put_cpu();
 }
 
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
+{
+       struct vcpu_vmx *vmx = to_vmx(vcpu);
+       int r;
+
+       r = vcpu_load(vcpu);
+       BUG_ON(r);
+       vmx_load_vmcs01(vcpu);
+       free_nested(vmx);
+       vcpu_put(vcpu);
+}
+
 static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8862,8 +8879,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 		vmx_destroy_pml_buffer(vmx);
 	free_vpid(vmx->vpid);
 	leave_guest_mode(vcpu);
-	vmx_load_vmcs01(vcpu);
-	free_nested(vmx);
+	vmx_free_vcpu_nested(vcpu);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7da5dd205..fea2c5717 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -91,6 +91,7 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu);
 static void process_nmi(struct kvm_vcpu *vcpu);
+static void process_smi(struct kvm_vcpu *vcpu);
 static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 
 struct kvm_x86_ops *kvm_x86_ops __read_mostly;
@@ -5296,13 +5297,8 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu)
 		/* This is a good place to trace that we are exiting SMM.  */
 		trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false);
 
-		if (unlikely(vcpu->arch.smi_pending)) {
-			kvm_make_request(KVM_REQ_SMI, vcpu);
-			vcpu->arch.smi_pending = 0;
-		} else {
-			/* Process a latched INIT, if any.  */
-			kvm_make_request(KVM_REQ_EVENT, vcpu);
-		}
+		/* Process a latched INIT or SMI, if any.  */
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
 	}
 
 	kvm_mmu_reset_context(vcpu);
@@ -6102,7 +6098,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 	}
 
 	/* try to inject new event if pending */
-	if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
+	if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
+		vcpu->arch.smi_pending = false;
+		process_smi(vcpu);
+	} else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
 		--vcpu->arch.nmi_pending;
 		vcpu->arch.nmi_injected = true;
 		kvm_x86_ops->set_nmi(vcpu);
@@ -6312,11 +6311,6 @@ static void process_smi(struct kvm_vcpu *vcpu)
 	char buf[512];
 	u32 cr0;
 
-	if (is_smm(vcpu)) {
-		vcpu->arch.smi_pending = true;
-		return;
-	}
-
 	trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
 	vcpu->arch.hflags |= HF_SMM_MASK;
 	memset(buf, 0, 512);
@@ -6379,6 +6373,12 @@ static void process_smi(struct kvm_vcpu *vcpu)
 	kvm_mmu_reset_context(vcpu);
 }
 
+static void process_smi_request(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.smi_pending = true;
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
+}
+
 void kvm_make_scan_ioapic_request(struct kvm *kvm)
 {
 	kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
@@ -6500,7 +6500,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
 			record_steal_time(vcpu);
 		if (kvm_check_request(KVM_REQ_SMI, vcpu))
-			process_smi(vcpu);
+			process_smi_request(vcpu);
 		if (kvm_check_request(KVM_REQ_NMI, vcpu))
 			process_nmi(vcpu);
 		if (kvm_check_request(KVM_REQ_PMU, vcpu))
@@ -6573,8 +6573,18 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 		if (inject_pending_event(vcpu, req_int_win) != 0)
 			req_immediate_exit = true;
-		/* enable NMI/IRQ window open exits if needed */
 		else {
+			/* Enable NMI/IRQ window open exits if needed.
+			 *
+			 * SMIs have two cases: 1) they can be nested, and
+			 * then there is nothing to do here because RSM will
+			 * cause a vmexit anyway; 2) or the SMI can be pending
+			 * because inject_pending_event has completed the
+			 * injection of an IRQ or NMI from the previous vmexit,
+			 * and then we request an immediate exit to inject the SMI.
+			 */
+			if (vcpu->arch.smi_pending && !is_smm(vcpu))
+				req_immediate_exit = true;
 			if (vcpu->arch.nmi_pending)
 				kvm_x86_ops->enable_nmi_window(vcpu);
 			if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
@@ -6625,8 +6635,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	kvm_load_guest_xcr0(vcpu);
 
-	if (req_immediate_exit)
+	if (req_immediate_exit) {
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
 		smp_send_reschedule(vcpu->cpu);
+	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
 	wait_lapic_expire(vcpu);
@@ -7427,6 +7439,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	vcpu->arch.hflags = 0;
 
+	vcpu->arch.smi_pending = 0;
 	atomic_set(&vcpu->arch.nmi_queued, 0);
 	vcpu->arch.nmi_pending = 0;
 	vcpu->arch.nmi_injected = false;
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 8b93e634a..ae97f24a4 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -37,6 +37,7 @@
 
 /* Quirks for the listed devices */
 #define PCI_DEVICE_ID_INTEL_MRFL_MMC	0x1190
+#define PCI_DEVICE_ID_INTEL_MRFL_HSU	0x1191
 
 /* Fixed BAR fields */
 #define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00	/* Fixed BAR (TBD) */
@@ -225,13 +226,20 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 		/* Special treatment for IRQ0 */
 		if (dev->irq == 0) {
 			/*
+			 * Skip HS UART common registers device since it has
+			 * IRQ0 assigned and not used by the kernel.
+			 */
+			if (dev->device == PCI_DEVICE_ID_INTEL_MRFL_HSU)
+				return -EBUSY;
+			/*
 			 * TNG has IRQ0 assigned to eMMC controller. But there
 			 * are also other devices with bogus PCI configuration
 			 * that have IRQ0 assigned. This check ensures that
-			 * eMMC gets it.
+			 * eMMC gets it. The rest of devices still could be
+			 * enabled without interrupt line being allocated.
 			 */
 			if (dev->device != PCI_DEVICE_ID_INTEL_MRFL_MMC)
-				return -EBUSY;
+				return 0;
 		}
 		break;
 	default: