Merge 4.5-rc2 into staging-next

This fixes a merge issue with the panel driver, and picks up fixes in
iio and other drivers that we want here.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

.mailmap

@@ -21,6 +21,7 @@ Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
 Andrew Morton <akpm@linux-foundation.org>
 Andrew Vasquez <andrew.vasquez@qlogic.com>
 Andy Adamson <andros@citi.umich.edu>
+Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com>
 Archit Taneja <archit@ti.com>
 Arnaud Patard <arnaud.patard@rtp-net.org>
 Arnd Bergmann <arnd@arndb.de>

Documentation/Intel-IOMMU.txt

@@ -3,7 +3,7 @@ Linux IOMMU Support
 
 The architecture spec can be obtained from the below location.
 
-http://www.intel.com/technology/virtualization/
+http://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/vt-directed-io-spec.pdf
 
 This guide gives a quick cheat sheet for some basic understanding.
 

Documentation/virtual/kvm/api.txt

@@ -3025,7 +3025,7 @@ len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0
 and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
 which is the maximum number of possibly pending cpu-local interrupts.
 
-4.90 KVM_SMI
+4.96 KVM_SMI
 
 Capability: KVM_CAP_X86_SMM
 Architectures: x86

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 5
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*

arch/arm/boot/compressed/Makefile

@@ -106,6 +106,15 @@ ORIG_CFLAGS := $(KBUILD_CFLAGS)
 KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
 endif
 
+# -fstack-protector-strong triggers protection checks in this code,
+# but it is being used too early to link to meaningful stack_chk logic.
+nossp_flags := $(call cc-option, -fno-stack-protector)
+CFLAGS_atags_to_fdt.o := $(nossp_flags)
+CFLAGS_fdt.o := $(nossp_flags)
+CFLAGS_fdt_ro.o := $(nossp_flags)
+CFLAGS_fdt_rw.o := $(nossp_flags)
+CFLAGS_fdt_wip.o := $(nossp_flags)
+
 ccflags-y := -fpic -mno-single-pic-base -fno-builtin -I$(obj)
 asflags-y := -DZIMAGE
 

arch/arm/include/uapi/asm/unistd.h

@@ -417,6 +417,7 @@
 #define __NR_userfaultfd		(__NR_SYSCALL_BASE+388)
 #define __NR_membarrier			(__NR_SYSCALL_BASE+389)
 #define __NR_mlock2			(__NR_SYSCALL_BASE+390)
+#define __NR_copy_file_range		(__NR_SYSCALL_BASE+391)
 
 /*
  * The following SWIs are ARM private.

arch/arm/kernel/calls.S

@@ -400,6 +400,7 @@
 		CALL(sys_userfaultfd)
 		CALL(sys_membarrier)
 		CALL(sys_mlock2)
+		CALL(sys_copy_file_range)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted

arch/arm64/Makefile

@@ -27,6 +27,8 @@ $(warning LSE atomics not supported by binutils)
 endif
 
 KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr)
+KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
+KBUILD_CFLAGS	+= $(call cc-option, -mpc-relative-literal-loads)
 KBUILD_AFLAGS	+= $(lseinstr)
 
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)

arch/arm64/configs/defconfig

@@ -16,7 +16,6 @@ CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_MEMCG=y
 CONFIG_MEMCG_SWAP=y
-CONFIG_MEMCG_KMEM=y
 CONFIG_CGROUP_HUGETLB=y
 # CONFIG_UTS_NS is not set
 # CONFIG_IPC_NS is not set
@@ -37,15 +36,13 @@ CONFIG_ARCH_EXYNOS7=y
 CONFIG_ARCH_LAYERSCAPE=y
 CONFIG_ARCH_HISI=y
 CONFIG_ARCH_MEDIATEK=y
+CONFIG_ARCH_QCOM=y
 CONFIG_ARCH_ROCKCHIP=y
 CONFIG_ARCH_SEATTLE=y
 CONFIG_ARCH_RENESAS=y
 CONFIG_ARCH_R8A7795=y
 CONFIG_ARCH_STRATIX10=y
 CONFIG_ARCH_TEGRA=y
-CONFIG_ARCH_TEGRA_132_SOC=y
-CONFIG_ARCH_TEGRA_210_SOC=y
-CONFIG_ARCH_QCOM=y
 CONFIG_ARCH_SPRD=y
 CONFIG_ARCH_THUNDER=y
 CONFIG_ARCH_UNIPHIER=y
@@ -54,14 +51,19 @@ CONFIG_ARCH_XGENE=y
 CONFIG_ARCH_ZYNQMP=y
 CONFIG_PCI=y
 CONFIG_PCI_MSI=y
+CONFIG_PCI_IOV=y
+CONFIG_PCI_RCAR_GEN2_PCIE=y
 CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCI_XGENE=y
-CONFIG_SMP=y
+CONFIG_PCI_LAYERSCAPE=y
+CONFIG_PCI_HISI=y
+CONFIG_PCIE_QCOM=y
 CONFIG_SCHED_MC=y
 CONFIG_PREEMPT=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA=y
+CONFIG_XEN=y
 CONFIG_CMDLINE="console=ttyAMA0"
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y
@@ -100,7 +102,11 @@ CONFIG_PATA_OF_PLATFORM=y
 CONFIG_NETDEVICES=y
 CONFIG_TUN=y
 CONFIG_VIRTIO_NET=y
+CONFIG_AMD_XGBE=y
 CONFIG_NET_XGENE=y
+CONFIG_E1000E=y
+CONFIG_IGB=y
+CONFIG_IGBVF=y
 CONFIG_SKY2=y
 CONFIG_RAVB=y
 CONFIG_SMC91X=y
@@ -117,25 +123,23 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_8250_MT6577=y
 CONFIG_SERIAL_8250_UNIPHIER=y
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_SERIAL_SAMSUNG=y
-CONFIG_SERIAL_SAMSUNG_UARTS_4=y
-CONFIG_SERIAL_SAMSUNG_UARTS=4
 CONFIG_SERIAL_SAMSUNG_CONSOLE=y
+CONFIG_SERIAL_TEGRA=y
 CONFIG_SERIAL_SH_SCI=y
 CONFIG_SERIAL_SH_SCI_NR_UARTS=11
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
-CONFIG_SERIAL_TEGRA=y
 CONFIG_SERIAL_MSM=y
 CONFIG_SERIAL_MSM_CONSOLE=y
-CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_XILINX_PS_UART=y
 CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y
 CONFIG_VIRTIO_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
 CONFIG_I2C_QUP=y
+CONFIG_I2C_UNIPHIER_F=y
 CONFIG_I2C_RCAR=y
 CONFIG_SPI=y
 CONFIG_SPI_PL022=y
@@ -176,8 +180,6 @@ CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_TEGRA=y
 CONFIG_MMC_SPI=y
 CONFIG_MMC_DW=y
-CONFIG_MMC_DW_IDMAC=y
-CONFIG_MMC_DW_PLTFM=y
 CONFIG_MMC_DW_EXYNOS=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
@@ -187,28 +189,33 @@ CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_CPU=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_EFI=y
+CONFIG_RTC_DRV_PL031=y
 CONFIG_RTC_DRV_XGENE=y
 CONFIG_DMADEVICES=y
-CONFIG_RCAR_DMAC=y
 CONFIG_QCOM_BAM_DMA=y
 CONFIG_TEGRA20_APB_DMA=y
+CONFIG_RCAR_DMAC=y
+CONFIG_VFIO=y
+CONFIG_VFIO_PCI=y
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_BALLOON=y
 CONFIG_VIRTIO_MMIO=y
+CONFIG_XEN_GNTDEV=y
+CONFIG_XEN_GRANT_DEV_ALLOC=y
 CONFIG_COMMON_CLK_CS2000_CP=y
 CONFIG_COMMON_CLK_QCOM=y
 CONFIG_MSM_GCC_8916=y
 CONFIG_HWSPINLOCK_QCOM=y
-# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_ARM_SMMU=y
 CONFIG_QCOM_SMEM=y
 CONFIG_QCOM_SMD=y
 CONFIG_QCOM_SMD_RPM=y
+CONFIG_ARCH_TEGRA_132_SOC=y
+CONFIG_ARCH_TEGRA_210_SOC=y
+CONFIG_HISILICON_IRQ_MBIGEN=y
 CONFIG_PHY_XGENE=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA=y
@@ -239,6 +246,7 @@ CONFIG_LOCKUP_DETECTOR=y
 # CONFIG_FTRACE is not set
 CONFIG_MEMTEST=y
 CONFIG_SECURITY=y
+CONFIG_CRYPTO_ECHAINIV=y
 CONFIG_CRYPTO_ANSI_CPRNG=y
 CONFIG_ARM64_CRYPTO=y
 CONFIG_CRYPTO_SHA1_ARM64_CE=y

arch/arm64/include/asm/pgtable.h

@@ -67,11 +67,11 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
 
-#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
-#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
-#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC))
+#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
-#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_WT))
+#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT))
-#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL))
+#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
 
 #define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
@@ -81,7 +81,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
-#define PAGE_KERNEL_ROX	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
+#define PAGE_KERNEL_ROX		__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 
@@ -153,6 +153,7 @@ extern struct page *empty_zero_page;
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
+#define pte_user(pte)		(!!(pte_val(pte) & PTE_USER))
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 #define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -163,8 +164,6 @@ extern struct page *empty_zero_page;
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
 #define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-#define pte_valid_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 #define pte_valid_not_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 #define pte_valid_young(pte) \
@@ -278,13 +277,13 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
 {
-	if (pte_valid_user(pte)) {
+	if (pte_valid(pte)) {
-		if (!pte_special(pte) && pte_exec(pte))
-			__sync_icache_dcache(pte, addr);
 		if (pte_sw_dirty(pte) && pte_write(pte))
 			pte_val(pte) &= ~PTE_RDONLY;
 		else
 			pte_val(pte) |= PTE_RDONLY;
+		if (pte_user(pte) && pte_exec(pte) && !pte_special(pte))
+			__sync_icache_dcache(pte, addr);
 	}
 
 	/*

arch/arm64/kernel/head.S

@@ -514,9 +514,14 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 #endif
 
 	/* EL2 debug */
+	mrs	x0, id_aa64dfr0_el1		// Check ID_AA64DFR0_EL1 PMUVer
+	sbfx	x0, x0, #8, #4
+	cmp	x0, #1
+	b.lt	4f				// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
 	msr	mdcr_el2, x0			// all PMU counters from EL1
+4:
 
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr

arch/arm64/kernel/image.h

@@ -64,6 +64,16 @@
 
 #ifdef CONFIG_EFI
 
+/*
+ * Prevent the symbol aliases below from being emitted into the kallsyms
+ * table, by forcing them to be absolute symbols (which are conveniently
+ * ignored by scripts/kallsyms) rather than section relative symbols.
+ * The distinction is only relevant for partial linking, and only for symbols
+ * that are defined within a section declaration (which is not the case for
+ * the definitions below) so the resulting values will be identical.
+ */
+#define KALLSYMS_HIDE(sym)	ABSOLUTE(sym)
+
 /*
  * The EFI stub has its own symbol namespace prefixed by __efistub_, to
  * isolate it from the kernel proper. The following symbols are legally
@@ -73,25 +83,25 @@
  * linked at. The routines below are all implemented in assembler in a
  * position independent manner
  */
-__efistub_memcmp		= __pi_memcmp;
+__efistub_memcmp		= KALLSYMS_HIDE(__pi_memcmp);
-__efistub_memchr		= __pi_memchr;
+__efistub_memchr		= KALLSYMS_HIDE(__pi_memchr);
-__efistub_memcpy		= __pi_memcpy;
+__efistub_memcpy		= KALLSYMS_HIDE(__pi_memcpy);
-__efistub_memmove		= __pi_memmove;
+__efistub_memmove		= KALLSYMS_HIDE(__pi_memmove);
-__efistub_memset		= __pi_memset;
+__efistub_memset		= KALLSYMS_HIDE(__pi_memset);
-__efistub_strlen		= __pi_strlen;
+__efistub_strlen		= KALLSYMS_HIDE(__pi_strlen);
-__efistub_strcmp		= __pi_strcmp;
+__efistub_strcmp		= KALLSYMS_HIDE(__pi_strcmp);
-__efistub_strncmp		= __pi_strncmp;
+__efistub_strncmp		= KALLSYMS_HIDE(__pi_strncmp);
-__efistub___flush_dcache_area	= __pi___flush_dcache_area;
+__efistub___flush_dcache_area	= KALLSYMS_HIDE(__pi___flush_dcache_area);
 
 #ifdef CONFIG_KASAN
-__efistub___memcpy		= __pi_memcpy;
+__efistub___memcpy		= KALLSYMS_HIDE(__pi_memcpy);
-__efistub___memmove		= __pi_memmove;
+__efistub___memmove		= KALLSYMS_HIDE(__pi_memmove);
-__efistub___memset		= __pi_memset;
+__efistub___memset		= KALLSYMS_HIDE(__pi_memset);
 #endif
 
-__efistub__text			= _text;
+__efistub__text			= KALLSYMS_HIDE(_text);
-__efistub__end			= _end;
+__efistub__end			= KALLSYMS_HIDE(_end);
-__efistub__edata		= _edata;
+__efistub__edata		= KALLSYMS_HIDE(_edata);
 
 #endif
 

arch/arm64/mm/dump.c

@@ -46,7 +46,7 @@ enum address_markers_idx {
 	PCI_START_NR,
 	PCI_END_NR,
 	MODULES_START_NR,
-	MODUELS_END_NR,
+	MODULES_END_NR,
 	KERNEL_SPACE_NR,
 };
 

arch/arm64/mm/kasan_init.c

@@ -120,6 +120,7 @@ static void __init cpu_set_ttbr1(unsigned long ttbr1)
 void __init kasan_init(void)
 {
 	struct memblock_region *reg;
+	int i;
 
 	/*
 	 * We are going to perform proper setup of shadow memory.
@@ -155,6 +156,14 @@ void __init kasan_init(void)
 				pfn_to_nid(virt_to_pfn(start)));
 	}
 
+	/*
+	 * KAsan may reuse the contents of kasan_zero_pte directly, so we
+	 * should make sure that it maps the zero page read-only.
+	 */
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte(&kasan_zero_pte[i],
+			pfn_pte(virt_to_pfn(kasan_zero_page), PAGE_KERNEL_RO));
+
 	memset(kasan_zero_page, 0, PAGE_SIZE);
 	cpu_set_ttbr1(__pa(swapper_pg_dir));
 	flush_tlb_all();

arch/arm64/mm/pageattr.c

@@ -57,6 +57,9 @@ static int change_memory_common(unsigned long addr, int numpages,
 	if (end < MODULES_VADDR || end >= MODULES_END)
 		return -EINVAL;
 
+	if (!numpages)
+		return 0;
+
 	data.set_mask = set_mask;
 	data.clear_mask = clear_mask;
 

arch/arm64/mm/proc-macros.S

@@ -84,3 +84,15 @@
 	b.lo	9998b
 	dsb	\domain
 	.endm
+
+/*
+ * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
+ */
+	.macro	reset_pmuserenr_el0, tmpreg
+	mrs	\tmpreg, id_aa64dfr0_el1	// Check ID_AA64DFR0_EL1 PMUVer
+	sbfx	\tmpreg, \tmpreg, #8, #4
+	cmp	\tmpreg, #1			// Skip if no PMU present
+	b.lt	9000f
+	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
+9000:
+	.endm

arch/arm64/mm/proc.S

@@ -117,7 +117,7 @@ ENTRY(cpu_do_resume)
 	 */
 	ubfx	x11, x11, #1, #1
 	msr	oslar_el1, x11
-	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
+	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	mov	x0, x12
 	dsb	nsh		// Make sure local tlb invalidation completed
 	isb
@@ -154,7 +154,7 @@ 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
-	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
+	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	/*
 	 * Memory region attributes for LPAE:
 	 *

arch/mips/bcm63xx/nvram.c

@@ -19,6 +19,8 @@
 
 #include <bcm63xx_nvram.h>
 
+#define BCM63XX_DEFAULT_PSI_SIZE	64
+
 static struct bcm963xx_nvram nvram;
 static int mac_addr_used;
 
@@ -85,3 +87,12 @@ int bcm63xx_nvram_get_mac_address(u8 *mac)
 	return 0;
 }
 EXPORT_SYMBOL(bcm63xx_nvram_get_mac_address);
+
+int bcm63xx_nvram_get_psi_size(void)
+{
+	if (nvram.psi_size > 0)
+		return nvram.psi_size;
+
+	return BCM63XX_DEFAULT_PSI_SIZE;
+}
+EXPORT_SYMBOL(bcm63xx_nvram_get_psi_size);

arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h

@@ -30,4 +30,6 @@ u8 *bcm63xx_nvram_get_name(void);
  */
 int bcm63xx_nvram_get_mac_address(u8 *mac);
 
+int bcm63xx_nvram_get_psi_size(void);
+
 #endif /* BCM63XX_NVRAM_H */

arch/powerpc/include/asm/book3s/64/hash.h

@@ -50,7 +50,9 @@
  * set of bits not changed in pmd_modify.
  */
 #define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
-			 _PAGE_ACCESSED | _PAGE_THP_HUGE)
+			 _PAGE_ACCESSED | _PAGE_THP_HUGE | _PAGE_PTE | \
+			 _PAGE_SOFT_DIRTY)
+
 
 #ifdef CONFIG_PPC_64K_PAGES
 #include <asm/book3s/64/hash-64k.h>

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -223,7 +223,6 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
 #define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
-#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))

arch/powerpc/include/asm/kvm_host.h

@@ -38,8 +38,7 @@
 
 #define KVM_MAX_VCPUS		NR_CPUS
 #define KVM_MAX_VCORES		NR_CPUS
-#define KVM_USER_MEM_SLOTS 32
+#define KVM_USER_MEM_SLOTS	512
-#define KVM_MEM_SLOTS_NUM KVM_USER_MEM_SLOTS
 
 #ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1

arch/powerpc/include/asm/systbl.h

@@ -383,3 +383,4 @@ SYSCALL(ni_syscall)
 SYSCALL(ni_syscall)
 SYSCALL(ni_syscall)
 SYSCALL(mlock2)
+SYSCALL(copy_file_range)

arch/powerpc/include/asm/unistd.h

@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		379
+#define NR_syscalls		380
 
 #define __NR__exit __NR_exit
 

arch/powerpc/include/uapi/asm/unistd.h

@@ -389,5 +389,6 @@
 #define __NR_userfaultfd	364
 #define __NR_membarrier		365
 #define __NR_mlock2		378
+#define __NR_copy_file_range	379
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */

arch/powerpc/kernel/eeh_pe.c

@@ -883,32 +883,29 @@ void eeh_pe_restore_bars(struct eeh_pe *pe)
 const char *eeh_pe_loc_get(struct eeh_pe *pe)
 {
 	struct pci_bus *bus = eeh_pe_bus_get(pe);
-	struct device_node *dn = pci_bus_to_OF_node(bus);
+	struct device_node *dn;
 	const char *loc = NULL;
 
-	if (!dn)
+	while (bus) {
-		goto out;
+		dn = pci_bus_to_OF_node(bus);
+		if (!dn) {
+			bus = bus->parent;
+			continue;
+		}
 
-	/* PHB PE or root PE ? */
+		if (pci_is_root_bus(bus))
-	if (pci_is_root_bus(bus)) {
-		loc = of_get_property(dn, "ibm,loc-code", NULL);
-		if (!loc)
 			loc = of_get_property(dn, "ibm,io-base-loc-code", NULL);
-		if (loc)
+		else
-			goto out;
+			loc = of_get_property(dn, "ibm,slot-location-code",
+					      NULL);
 
-		/* Check the root port */
+		if (loc)
-		dn = dn->child;
+			return loc;
-		if (!dn)
+
-			goto out;
+		bus = bus->parent;
 	}
 
-	loc = of_get_property(dn, "ibm,loc-code", NULL);
+	return "N/A";
-	if (!loc)
-		loc = of_get_property(dn, "ibm,slot-location-code", NULL);
-
-out:
-	return loc ? loc : "N/A";
 }
 
 /**

arch/powerpc/kernel/misc_64.S

@@ -701,31 +701,3 @@ _GLOBAL(kexec_sequence)
 	li	r5,0
 	blr	/* image->start(physid, image->start, 0); */
 #endif /* CONFIG_KEXEC */
-
-#ifdef CONFIG_MODULES
-#if defined(_CALL_ELF) && _CALL_ELF == 2
-
-#ifdef CONFIG_MODVERSIONS
-.weak __crc_TOC.
-.section "___kcrctab+TOC.","a"
-.globl __kcrctab_TOC.
-__kcrctab_TOC.:
-	.llong	__crc_TOC.
-#endif
-
-/*
- * Export a fake .TOC. since both modpost and depmod will complain otherwise.
- * Both modpost and depmod strip the leading . so we do the same here.
- */
-.section "__ksymtab_strings","a"
-__kstrtab_TOC.:
-	.asciz "TOC."
-
-.section "___ksymtab+TOC.","a"
-/* This symbol name is important: it's used by modpost to find exported syms */
-.globl __ksymtab_TOC.
-__ksymtab_TOC.:
-	.llong 0 /* .value */
-	.llong __kstrtab_TOC.
-#endif /* ELFv2 */
-#endif /* MODULES */

arch/powerpc/kernel/module_64.c

@@ -326,7 +326,10 @@ static void dedotify_versions(struct modversion_info *vers,
 		}
 }
 
-/* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */
+/*
+ * Undefined symbols which refer to .funcname, hack to funcname. Make .TOC.
+ * seem to be defined (value set later).
+ */
 static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 {
 	unsigned int i;
@@ -334,8 +337,11 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 	for (i = 1; i < numsyms; i++) {
 		if (syms[i].st_shndx == SHN_UNDEF) {
 			char *name = strtab + syms[i].st_name;
-			if (name[0] == '.')
+			if (name[0] == '.') {
+				if (strcmp(name+1, "TOC.") == 0)
+					syms[i].st_shndx = SHN_ABS;
 				memmove(name, name+1, strlen(name));
+			}
 		}
 	}
 }
@@ -351,7 +357,7 @@ static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs,
 	numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym);
 
 	for (i = 1; i < numsyms; i++) {
-		if (syms[i].st_shndx == SHN_UNDEF
+		if (syms[i].st_shndx == SHN_ABS
 		    && strcmp(strtab + syms[i].st_name, "TOC.") == 0)
 			return &syms[i];
 	}

arch/powerpc/kvm/book3s_64_mmu.c

@@ -377,15 +377,12 @@ no_seg_found:
 
 static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
 {
-	struct kvmppc_vcpu_book3s *vcpu_book3s;
 	u64 esid, esid_1t;
 	int slb_nr;
 	struct kvmppc_slb *slbe;
 
 	dprintk("KVM MMU: slbmte(0x%llx, 0x%llx)\n", rs, rb);
 
-	vcpu_book3s = to_book3s(vcpu);
-
 	esid = GET_ESID(rb);
 	esid_1t = GET_ESID_1T(rb);
 	slb_nr = rb & 0xfff;

arch/powerpc/kvm/book3s_hv.c

@@ -833,6 +833,24 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	vcpu->stat.sum_exits++;
 
+	/*
+	 * This can happen if an interrupt occurs in the last stages
+	 * of guest entry or the first stages of guest exit (i.e. after
+	 * setting paca->kvm_hstate.in_guest to KVM_GUEST_MODE_GUEST_HV
+	 * and before setting it to KVM_GUEST_MODE_HOST_HV).
+	 * That can happen due to a bug, or due to a machine check
+	 * occurring at just the wrong time.
+	 */
+	if (vcpu->arch.shregs.msr & MSR_HV) {
+		printk(KERN_EMERG "KVM trap in HV mode!\n");
+		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
+			vcpu->arch.trap, kvmppc_get_pc(vcpu),
+			vcpu->arch.shregs.msr);
+		kvmppc_dump_regs(vcpu);
+		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		run->hw.hardware_exit_reason = vcpu->arch.trap;
+		return RESUME_HOST;
+	}
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
 	switch (vcpu->arch.trap) {

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 	/* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */
 2:	rlwimi	r5, r4, 5, DAWRX_DR | DAWRX_DW
-	rlwimi	r5, r4, 1, DAWRX_WT
+	rlwimi	r5, r4, 2, DAWRX_WT
 	clrrdi	r4, r4, 3
 	std	r4, VCPU_DAWR(r3)
 	std	r5, VCPU_DAWRX(r3)
@@ -2404,6 +2404,8 @@ machine_check_realmode:
 	 * guest as machine check causing guest to crash.
 	 */
 	ld	r11, VCPU_MSR(r9)
+	rldicl.	r0, r11, 64-MSR_HV_LG, 63 /* check if it happened in HV mode */
+	bne	mc_cont			/* if so, exit to host */
 	andi.	r10, r11, MSR_RI	/* check for unrecoverable exception */
 	beq	1f			/* Deliver a machine check to guest */
 	ld	r10, VCPU_PC(r9)

arch/powerpc/kvm/powerpc.c

@@ -919,21 +919,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
+			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
+			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
 			break;
 		case KVM_REG_PPC_VRSAVE:
-			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+			val = get_reg_val(reg->id, vcpu->arch.vrsave);
-				r = -ENXIO;
-				break;
-			}
-			vcpu->arch.vrsave = set_reg_val(reg->id, val);
 			break;
 #endif /* CONFIG_ALTIVEC */
 		default:
@@ -974,17 +970,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				r = -ENXIO;
 				break;
 			}
-			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
+			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
 			break;
 		case KVM_REG_PPC_VSCR:
 			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
 				r = -ENXIO;
 				break;
 			}
-			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
+			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
 			break;
 		case KVM_REG_PPC_VRSAVE:
-			val = get_reg_val(reg->id, vcpu->arch.vrsave);
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vrsave = set_reg_val(reg->id, val);
 			break;
 #endif /* CONFIG_ALTIVEC */
 		default:

arch/powerpc/mm/mem.c

@@ -560,12 +560,12 @@ subsys_initcall(add_system_ram_resources);
  */
 int devmem_is_allowed(unsigned long pfn)
 {
+	if (page_is_rtas_user_buf(pfn))
+		return 1;
 	if (iomem_is_exclusive(PFN_PHYS(pfn)))
 		return 0;
 	if (!page_is_ram(pfn))
 		return 1;
-	if (page_is_rtas_user_buf(pfn))
-		return 1;
 	return 0;
 }
 #endif /* CONFIG_STRICT_DEVMEM */

arch/powerpc/perf/power8-pmu.c

@@ -816,7 +816,7 @@ static struct power_pmu power8_pmu = {
 	.get_constraint		= power8_get_constraint,
 	.get_alternatives	= power8_get_alternatives,
 	.disable_pmc		= power8_disable_pmc,
-	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_ARCH_207S,
+	.flags			= PPMU_HAS_SIER | PPMU_ARCH_207S,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
 	.cache_events		= &power8_cache_events,

arch/s390/include/asm/irqflags.h

@@ -8,6 +8,8 @@
 
 #include <linux/types.h>
 
+#define ARCH_IRQ_ENABLED	(3UL << (BITS_PER_LONG - 8))
+
 /* store then OR system mask. */
 #define __arch_local_irq_stosm(__or)					\
 ({									\
@@ -54,14 +56,17 @@ static inline notrace void arch_local_irq_enable(void)
 	__arch_local_irq_stosm(0x03);
 }
 
+/* This only restores external and I/O interrupt state */
 static inline notrace void arch_local_irq_restore(unsigned long flags)
 {
-	__arch_local_irq_ssm(flags);
+	/* only disabled->disabled and disabled->enabled is valid */
+	if (flags & ARCH_IRQ_ENABLED)
+		arch_local_irq_enable();
 }
 
 static inline notrace bool arch_irqs_disabled_flags(unsigned long flags)
 {
-	return !(flags & (3UL << (BITS_PER_LONG - 8)));
+	return !(flags & ARCH_IRQ_ENABLED);
 }
 
 static inline notrace bool arch_irqs_disabled(void)

arch/s390/include/asm/kvm_host.h

@@ -546,7 +546,6 @@ struct kvm_vcpu_arch {
 	struct kvm_s390_sie_block *sie_block;
 	unsigned int      host_acrs[NUM_ACRS];
 	struct fpu	  host_fpregs;
-	struct fpu	  guest_fpregs;
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
 	struct kvm_s390_pgm_info pgm;

arch/s390/include/asm/pci_io.h

@@ -8,10 +8,13 @@
 #include <asm/pci_insn.h>
 
 /* I/O Map */
-#define ZPCI_IOMAP_MAX_ENTRIES		0x7fff
+#define ZPCI_IOMAP_SHIFT		48
-#define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000ULL
+#define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000UL
-#define ZPCI_IOMAP_ADDR_IDX_MASK	0x7fff000000000000ULL
+#define ZPCI_IOMAP_ADDR_OFF_MASK	((1UL << ZPCI_IOMAP_SHIFT) - 1)
-#define ZPCI_IOMAP_ADDR_OFF_MASK	0x0000ffffffffffffULL
+#define ZPCI_IOMAP_MAX_ENTRIES							\
+	((ULONG_MAX - ZPCI_IOMAP_ADDR_BASE + 1) / (1UL << ZPCI_IOMAP_SHIFT))
+#define ZPCI_IOMAP_ADDR_IDX_MASK						\
+	(~ZPCI_IOMAP_ADDR_OFF_MASK - ZPCI_IOMAP_ADDR_BASE)
 
 struct zpci_iomap_entry {
 	u32 fh;
@@ -21,8 +24,9 @@ struct zpci_iomap_entry {
 
 extern struct zpci_iomap_entry *zpci_iomap_start;
 
+#define ZPCI_ADDR(idx) (ZPCI_IOMAP_ADDR_BASE | ((u64) idx << ZPCI_IOMAP_SHIFT))
 #define ZPCI_IDX(addr)								\
-	(((__force u64) addr & ZPCI_IOMAP_ADDR_IDX_MASK) >> 48)
+	(((__force u64) addr & ZPCI_IOMAP_ADDR_IDX_MASK) >> ZPCI_IOMAP_SHIFT)
 #define ZPCI_OFFSET(addr)							\
 	((__force u64) addr & ZPCI_IOMAP_ADDR_OFF_MASK)
 

arch/s390/include/asm/processor.h

@@ -166,14 +166,14 @@ extern __vector128 init_task_fpu_regs[__NUM_VXRS];
  */
 #define start_thread(regs, new_psw, new_stackp) do {			\
 	regs->psw.mask	= PSW_USER_BITS | PSW_MASK_EA | PSW_MASK_BA;	\
-	regs->psw.addr	= new_psw | PSW_ADDR_AMODE;			\
+	regs->psw.addr	= new_psw;					\
 	regs->gprs[15]	= new_stackp;					\
 	execve_tail();							\
 } while (0)
 
 #define start_thread31(regs, new_psw, new_stackp) do {			\
 	regs->psw.mask	= PSW_USER_BITS | PSW_MASK_BA;			\
-	regs->psw.addr	= new_psw | PSW_ADDR_AMODE;			\
+	regs->psw.addr	= new_psw;					\
 	regs->gprs[15]	= new_stackp;					\
 	crst_table_downgrade(current->mm, 1UL << 31);			\
 	execve_tail();							\

arch/s390/include/asm/ptrace.h

@@ -149,7 +149,7 @@ static inline int test_pt_regs_flag(struct pt_regs *regs, int flag)
 #define arch_has_block_step()	(1)
 
 #define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0)
-#define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN)
+#define instruction_pointer(regs) ((regs)->psw.addr)
 #define user_stack_pointer(regs)((regs)->gprs[15])
 #define profile_pc(regs) instruction_pointer(regs)
 
@@ -161,7 +161,7 @@ static inline long regs_return_value(struct pt_regs *regs)
 static inline void instruction_pointer_set(struct pt_regs *regs,
 					   unsigned long val)
 {
-	regs->psw.addr = val | PSW_ADDR_AMODE;
+	regs->psw.addr = val;
 }
 
 int regs_query_register_offset(const char *name);
@@ -171,7 +171,7 @@ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n);
 
 static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 {
-	return regs->gprs[15] & PSW_ADDR_INSN;
+	return regs->gprs[15];
 }
 
 #endif /* __ASSEMBLY__ */

arch/s390/include/uapi/asm/unistd.h

@@ -310,7 +310,8 @@
 #define __NR_recvmsg		372
 #define __NR_shutdown		373
 #define __NR_mlock2		374
-#define NR_syscalls 375
+#define __NR_copy_file_range	375
+#define NR_syscalls 376
 
 /* 
  * There are some system calls that are not present on 64 bit, some

arch/s390/kernel/compat_wrapper.c

@@ -177,3 +177,4 @@ COMPAT_SYSCALL_WRAP3(getsockname, int, fd, struct sockaddr __user *, usockaddr,
 COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len);
 COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len);
 COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags);
+COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);

arch/s390/kernel/crash_dump.c

@@ -59,8 +59,6 @@ struct save_area * __init save_area_alloc(bool is_boot_cpu)
 	struct save_area *sa;
 
 	sa = (void *) memblock_alloc(sizeof(*sa), 8);
-	if (!sa)
-		return NULL;
 	if (is_boot_cpu)
 		list_add(&sa->list, &dump_save_areas);
 	else

arch/s390/kernel/debug.c

@@ -1470,7 +1470,7 @@ debug_dflt_header_fn(debug_info_t * id, struct debug_view *view,
 		except_str = "*";
 	else
 		except_str = "-";
-	caller = ((unsigned long) entry->caller) & PSW_ADDR_INSN;
+	caller = (unsigned long) entry->caller;
 	rc += sprintf(out_buf, "%02i %011lld:%06lu %1u %1s %02i %p  ",
 		      area, (long long)time_spec.tv_sec,
 		      time_spec.tv_nsec / 1000, level, except_str,

arch/s390/kernel/dumpstack.c

@@ -34,22 +34,21 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high)
 	unsigned long addr;
 
 	while (1) {
-		sp = sp & PSW_ADDR_INSN;
 		if (sp < low || sp > high - sizeof(*sf))
 			return sp;
 		sf = (struct stack_frame *) sp;
-		addr = sf->gprs[8] & PSW_ADDR_INSN;
+		addr = sf->gprs[8];
 		printk("([<%016lx>] %pSR)\n", addr, (void *)addr);
 		/* Follow the backchain. */
 		while (1) {
 			low = sp;
-			sp = sf->back_chain & PSW_ADDR_INSN;
+			sp = sf->back_chain;
 			if (!sp)
 				break;
 			if (sp <= low || sp > high - sizeof(*sf))
 				return sp;
 			sf = (struct stack_frame *) sp;
-			addr = sf->gprs[8] & PSW_ADDR_INSN;
+			addr = sf->gprs[8];
 			printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
 		}
 		/* Zero backchain detected, check for interrupt frame. */
@@ -57,7 +56,7 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high)
 		if (sp <= low || sp > high - sizeof(*regs))
 			return sp;
 		regs = (struct pt_regs *) sp;
-		addr = regs->psw.addr & PSW_ADDR_INSN;
+		addr = regs->psw.addr;
 		printk(" [<%016lx>] %pSR\n", addr, (void *)addr);
 		low = sp;
 		sp = regs->gprs[15];

arch/s390/kernel/early.c

@@ -252,14 +252,14 @@ static void early_pgm_check_handler(void)
 	unsigned long addr;
 
 	addr = S390_lowcore.program_old_psw.addr;
-	fixup = search_exception_tables(addr & PSW_ADDR_INSN);
+	fixup = search_exception_tables(addr);
 	if (!fixup)
 		disabled_wait(0);
 	/* Disable low address protection before storing into lowcore. */
 	__ctl_store(cr0, 0, 0);
 	cr0_new = cr0 & ~(1UL << 28);
 	__ctl_load(cr0_new, 0, 0);
-	S390_lowcore.program_old_psw.addr = extable_fixup(fixup)|PSW_ADDR_AMODE;
+	S390_lowcore.program_old_psw.addr = extable_fixup(fixup);
 	__ctl_load(cr0, 0, 0);
 }
 
@@ -268,9 +268,9 @@ static noinline __init void setup_lowcore_early(void)
 	psw_t psw;
 
 	psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA;
-	psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_ext_handler;
+	psw.addr = (unsigned long) s390_base_ext_handler;
 	S390_lowcore.external_new_psw = psw;
-	psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
+	psw.addr = (unsigned long) s390_base_pgm_handler;
 	S390_lowcore.program_new_psw = psw;
 	s390_base_pgm_handler_fn = early_pgm_check_handler;
 }

arch/s390/kernel/ftrace.c

@@ -203,7 +203,7 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
 		goto out;
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
-	ip = (ip & PSW_ADDR_INSN) - MCOUNT_INSN_SIZE;
+	ip -= MCOUNT_INSN_SIZE;
 	trace.func = ip;
 	trace.depth = current->curr_ret_stack + 1;
 	/* Only trace if the calling function expects to. */

arch/s390/kernel/ipl.c

@@ -2057,12 +2057,12 @@ void s390_reset_system(void)
 	/* Set new machine check handler */
 	S390_lowcore.mcck_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT;
 	S390_lowcore.mcck_new_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) s390_base_mcck_handler;
+		(unsigned long) s390_base_mcck_handler;
 
 	/* Set new program check handler */
 	S390_lowcore.program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT;
 	S390_lowcore.program_new_psw.addr =
-		PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
+		(unsigned long) s390_base_pgm_handler;
 
 	/*
 	 * Clear subchannel ID and number to signal new kernel that no CCW or

arch/s390/kernel/kprobes.c

@@ -226,7 +226,7 @@ static void enable_singlestep(struct kprobe_ctlblk *kcb,
 	__ctl_load(per_kprobe, 9, 11);
 	regs->psw.mask |= PSW_MASK_PER;
 	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
-	regs->psw.addr = ip | PSW_ADDR_AMODE;
+	regs->psw.addr = ip;
 }
 NOKPROBE_SYMBOL(enable_singlestep);
 
@@ -238,7 +238,7 @@ static void disable_singlestep(struct kprobe_ctlblk *kcb,
 	__ctl_load(kcb->kprobe_saved_ctl, 9, 11);
 	regs->psw.mask &= ~PSW_MASK_PER;
 	regs->psw.mask |= kcb->kprobe_saved_imask;
-	regs->psw.addr = ip | PSW_ADDR_AMODE;
+	regs->psw.addr = ip;
 }
 NOKPROBE_SYMBOL(disable_singlestep);
 
@@ -310,7 +310,7 @@ static int kprobe_handler(struct pt_regs *regs)
 	 */
 	preempt_disable();
 	kcb = get_kprobe_ctlblk();
-	p = get_kprobe((void *)((regs->psw.addr & PSW_ADDR_INSN) - 2));
+	p = get_kprobe((void *)(regs->psw.addr - 2));
 
 	if (p) {
 		if (kprobe_running()) {
@@ -460,7 +460,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 			break;
 	}
 
-	regs->psw.addr = orig_ret_address | PSW_ADDR_AMODE;
+	regs->psw.addr = orig_ret_address;
 
 	pop_kprobe(get_kprobe_ctlblk());
 	kretprobe_hash_unlock(current, &flags);
@@ -490,7 +490,7 @@ NOKPROBE_SYMBOL(trampoline_probe_handler);
 static void resume_execution(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long ip = regs->psw.addr & PSW_ADDR_INSN;
+	unsigned long ip = regs->psw.addr;
 	int fixup = probe_get_fixup_type(p->ainsn.insn);
 
 	/* Check if the kprobes location is an enabled ftrace caller */
@@ -605,9 +605,9 @@ static int kprobe_trap_handler(struct pt_regs *regs, int trapnr)
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.
 		 */
-		entry = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
+		entry = search_exception_tables(regs->psw.addr);
 		if (entry) {
-			regs->psw.addr = extable_fixup(entry) | PSW_ADDR_AMODE;
+			regs->psw.addr = extable_fixup(entry);
 			return 1;
 		}
 
@@ -683,7 +683,7 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
 
 	/* setup return addr to the jprobe handler routine */
-	regs->psw.addr = (unsigned long) jp->entry | PSW_ADDR_AMODE;
+	regs->psw.addr = (unsigned long) jp->entry;
 	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
 
 	/* r15 is the stack pointer */

arch/s390/kernel/perf_event.c

@@ -74,7 +74,7 @@ static unsigned long guest_is_user_mode(struct pt_regs *regs)
 
 static unsigned long instruction_pointer_guest(struct pt_regs *regs)
 {
-	return sie_block(regs)->gpsw.addr & PSW_ADDR_INSN;
+	return sie_block(regs)->gpsw.addr;
 }
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
@@ -231,29 +231,27 @@ static unsigned long __store_trace(struct perf_callchain_entry *entry,
 	struct pt_regs *regs;
 
 	while (1) {
-		sp = sp & PSW_ADDR_INSN;
 		if (sp < low || sp > high - sizeof(*sf))
 			return sp;
 		sf = (struct stack_frame *) sp;
-		perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN);
+		perf_callchain_store(entry, sf->gprs[8]);
 		/* Follow the backchain. */
 		while (1) {
 			low = sp;
-			sp = sf->back_chain & PSW_ADDR_INSN;
+			sp = sf->back_chain;
 			if (!sp)
 				break;
 			if (sp <= low || sp > high - sizeof(*sf))
 				return sp;
 			sf = (struct stack_frame *) sp;
-			perf_callchain_store(entry,
+			perf_callchain_store(entry, sf->gprs[8]);
-					     sf->gprs[8] & PSW_ADDR_INSN);
 		}
 		/* Zero backchain detected, check for interrupt frame. */
 		sp = (unsigned long) (sf + 1);
 		if (sp <= low || sp > high - sizeof(*regs))
 			return sp;
 		regs = (struct pt_regs *) sp;
-		perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN);
+		perf_callchain_store(entry, sf->gprs[8]);
 		low = sp;
 		sp = regs->gprs[15];
 	}

arch/s390/kernel/process.c

@@ -56,10 +56,10 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
 		return 0;
 	low = task_stack_page(tsk);
 	high = (struct stack_frame *) task_pt_regs(tsk);
-	sf = (struct stack_frame *) (tsk->thread.ksp & PSW_ADDR_INSN);
+	sf = (struct stack_frame *) tsk->thread.ksp;
 	if (sf <= low || sf > high)
 		return 0;
-	sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN);
+	sf = (struct stack_frame *) sf->back_chain;
 	if (sf <= low || sf > high)
 		return 0;
 	return sf->gprs[8];
@@ -154,7 +154,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 		memset(&frame->childregs, 0, sizeof(struct pt_regs));
 		frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT |
 				PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
-		frame->childregs.psw.addr = PSW_ADDR_AMODE |
+		frame->childregs.psw.addr =
 				(unsigned long) kernel_thread_starter;
 		frame->childregs.gprs[9] = new_stackp; /* function */
 		frame->childregs.gprs[10] = arg;
@@ -220,14 +220,14 @@ unsigned long get_wchan(struct task_struct *p)
 		return 0;
 	low = task_stack_page(p);
 	high = (struct stack_frame *) task_pt_regs(p);
-	sf = (struct stack_frame *) (p->thread.ksp & PSW_ADDR_INSN);
+	sf = (struct stack_frame *) p->thread.ksp;
 	if (sf <= low || sf > high)
 		return 0;
 	for (count = 0; count < 16; count++) {
-		sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN);
+		sf = (struct stack_frame *) sf->back_chain;
 		if (sf <= low || sf > high)
 			return 0;
-		return_address = sf->gprs[8] & PSW_ADDR_INSN;
+		return_address = sf->gprs[8];
 		if (!in_sched_functions(return_address))
 			return return_address;
 	}

arch/s390/kernel/ptrace.c

@@ -84,7 +84,7 @@ void update_cr_regs(struct task_struct *task)
 		if (test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP))
 			new.control |= PER_EVENT_IFETCH;
 		new.start = 0;
-		new.end = PSW_ADDR_INSN;
+		new.end = -1UL;
 	}
 
 	/* Take care of the PER enablement bit in the PSW. */
@@ -148,7 +148,7 @@ static inline unsigned long __peek_user_per(struct task_struct *child,
 	else if (addr == (addr_t) &dummy->cr11)
 		/* End address of the active per set. */
 		return test_thread_flag(TIF_SINGLE_STEP) ?
-			PSW_ADDR_INSN : child->thread.per_user.end;
+			-1UL : child->thread.per_user.end;
 	else if (addr == (addr_t) &dummy->bits)
 		/* Single-step bit. */
 		return test_thread_flag(TIF_SINGLE_STEP) ?
@@ -495,8 +495,6 @@ long arch_ptrace(struct task_struct *child, long request,
 		}
 		return 0;
 	default:
-		/* Removing high order bit from addr (only for 31 bit). */
-		addr &= PSW_ADDR_INSN;
 		return ptrace_request(child, request, addr, data);
 	}
 }

arch/s390/kernel/setup.c

@@ -301,25 +301,21 @@ static void __init setup_lowcore(void)
 	BUILD_BUG_ON(sizeof(struct lowcore) != LC_PAGES * 4096);
 	lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0);
 	lc->restart_psw.mask = PSW_KERNEL_BITS;
-	lc->restart_psw.addr =
+	lc->restart_psw.addr = (unsigned long) restart_int_handler;
-		PSW_ADDR_AMODE | (unsigned long) restart_int_handler;
 	lc->external_new_psw.mask = PSW_KERNEL_BITS |
 		PSW_MASK_DAT | PSW_MASK_MCHECK;
-	lc->external_new_psw.addr =
+	lc->external_new_psw.addr = (unsigned long) ext_int_handler;
-		PSW_ADDR_AMODE | (unsigned long) ext_int_handler;
 	lc->svc_new_psw.mask = PSW_KERNEL_BITS |
 		PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
-	lc->svc_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) system_call;
+	lc->svc_new_psw.addr = (unsigned long) system_call;
 	lc->program_new_psw.mask = PSW_KERNEL_BITS |
 		PSW_MASK_DAT | PSW_MASK_MCHECK;
-	lc->program_new_psw.addr =
+	lc->program_new_psw.addr = (unsigned long) pgm_check_handler;
-		PSW_ADDR_AMODE | (unsigned long) pgm_check_handler;
 	lc->mcck_new_psw.mask = PSW_KERNEL_BITS;
-	lc->mcck_new_psw.addr =
+	lc->mcck_new_psw.addr = (unsigned long) mcck_int_handler;
-		PSW_ADDR_AMODE | (unsigned long) mcck_int_handler;
 	lc->io_new_psw.mask = PSW_KERNEL_BITS |
 		PSW_MASK_DAT | PSW_MASK_MCHECK;
-	lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler;
+	lc->io_new_psw.addr = (unsigned long) io_int_handler;
 	lc->clock_comparator = -1ULL;
 	lc->kernel_stack = ((unsigned long) &init_thread_union)
 		+ THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs);

arch/s390/kernel/signal.c

@@ -331,13 +331,13 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ka->sa.sa_flags & SA_RESTORER) {
-		restorer = (unsigned long) ka->sa.sa_restorer | PSW_ADDR_AMODE;
+		restorer = (unsigned long) ka->sa.sa_restorer;
 	} else {
 		/* Signal frame without vector registers are short ! */
 		__u16 __user *svc = (void __user *) frame + frame_size - 2;
 		if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc))
 			return -EFAULT;
-		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
+		restorer = (unsigned long) svc;
 	}
 
 	/* Set up registers for signal handler */
@@ -347,7 +347,7 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
 		(PSW_USER_BITS & PSW_MASK_ASC) |
 		(regs->psw.mask & ~PSW_MASK_ASC);
-	regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE;
+	regs->psw.addr = (unsigned long) ka->sa.sa_handler;
 
 	regs->gprs[2] = sig;
 	regs->gprs[3] = (unsigned long) &frame->sc;
@@ -394,13 +394,12 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	/* Set up to return from userspace.  If provided, use a stub
 	   already in userspace.  */
 	if (ksig->ka.sa.sa_flags & SA_RESTORER) {
-		restorer = (unsigned long)
+		restorer = (unsigned long) ksig->ka.sa.sa_restorer;
-			ksig->ka.sa.sa_restorer | PSW_ADDR_AMODE;
 	} else {
 		__u16 __user *svc = &frame->svc_insn;
 		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc))
 			return -EFAULT;
-		restorer = (unsigned long) svc | PSW_ADDR_AMODE;
+		restorer = (unsigned long) svc;
 	}
 
 	/* Create siginfo on the signal stack */
@@ -426,7 +425,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
 		(PSW_USER_BITS & PSW_MASK_ASC) |
 		(regs->psw.mask & ~PSW_MASK_ASC);
-	regs->psw.addr = (unsigned long) ksig->ka.sa.sa_handler | PSW_ADDR_AMODE;
+	regs->psw.addr = (unsigned long) ksig->ka.sa.sa_handler;
 
 	regs->gprs[2] = ksig->sig;
 	regs->gprs[3] = (unsigned long) &frame->info;

arch/s390/kernel/smp.c

@@ -623,8 +623,6 @@ void __init smp_save_dump_cpus(void)
 		return;
 	/* Allocate a page as dumping area for the store status sigps */
 	page = memblock_alloc_base(PAGE_SIZE, PAGE_SIZE, 1UL << 31);
-	if (!page)
-		panic("could not allocate memory for save area\n");
 	/* Set multi-threading state to the previous system. */
 	pcpu_set_smt(sclp.mtid_prev);
 	boot_cpu_addr = stap();

arch/s390/kernel/stacktrace.c

@@ -21,12 +21,11 @@ static unsigned long save_context_stack(struct stack_trace *trace,
 	unsigned long addr;
 
 	while(1) {
-		sp &= PSW_ADDR_INSN;
 		if (sp < low || sp > high)
 			return sp;
 		sf = (struct stack_frame *)sp;
 		while(1) {
-			addr = sf->gprs[8] & PSW_ADDR_INSN;
+			addr = sf->gprs[8];
 			if (!trace->skip)
 				trace->entries[trace->nr_entries++] = addr;
 			else
@@ -34,7 +33,7 @@ static unsigned long save_context_stack(struct stack_trace *trace,
 			if (trace->nr_entries >= trace->max_entries)
 				return sp;
 			low = sp;
-			sp = sf->back_chain & PSW_ADDR_INSN;
+			sp = sf->back_chain;
 			if (!sp)
 				break;
 			if (sp <= low || sp > high - sizeof(*sf))
@@ -46,7 +45,7 @@ static unsigned long save_context_stack(struct stack_trace *trace,
 		if (sp <= low || sp > high - sizeof(*regs))
 			return sp;
 		regs = (struct pt_regs *)sp;
-		addr = regs->psw.addr & PSW_ADDR_INSN;
+		addr = regs->psw.addr;
 		if (savesched || !in_sched_functions(addr)) {
 			if (!trace->skip)
 				trace->entries[trace->nr_entries++] = addr;
@@ -65,7 +64,7 @@ void save_stack_trace(struct stack_trace *trace)
 	register unsigned long sp asm ("15");
 	unsigned long orig_sp, new_sp;
 
-	orig_sp = sp & PSW_ADDR_INSN;
+	orig_sp = sp;
 	new_sp = save_context_stack(trace, orig_sp,
 				    S390_lowcore.panic_stack - PAGE_SIZE,
 				    S390_lowcore.panic_stack, 1);
@@ -86,7 +85,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	unsigned long sp, low, high;
 
-	sp = tsk->thread.ksp & PSW_ADDR_INSN;
+	sp = tsk->thread.ksp;
 	low = (unsigned long) task_stack_page(tsk);
 	high = (unsigned long) task_pt_regs(tsk);
 	save_context_stack(trace, sp, low, high, 0);

arch/s390/kernel/syscalls.S

@@ -383,3 +383,4 @@ SYSCALL(sys_recvfrom,compat_sys_recvfrom)
 SYSCALL(sys_recvmsg,compat_sys_recvmsg)
 SYSCALL(sys_shutdown,sys_shutdown)
 SYSCALL(sys_mlock2,compat_sys_mlock2)
+SYSCALL(sys_copy_file_range,compat_sys_copy_file_range) /* 375 */

arch/s390/kernel/traps.c

@@ -32,8 +32,7 @@ static inline void __user *get_trap_ip(struct pt_regs *regs)
 		address = *(unsigned long *)(current->thread.trap_tdb + 24);
 	else
 		address = regs->psw.addr;
-	return (void __user *)
+	return (void __user *) (address - (regs->int_code >> 16));
-		((address - (regs->int_code >> 16)) & PSW_ADDR_INSN);
 }
 
 static inline void report_user_fault(struct pt_regs *regs, int signr)
@@ -46,7 +45,7 @@ static inline void report_user_fault(struct pt_regs *regs, int signr)
 		return;
 	printk("User process fault: interruption code %04x ilc:%d ",
 	       regs->int_code & 0xffff, regs->int_code >> 17);
-	print_vma_addr("in ", regs->psw.addr & PSW_ADDR_INSN);
+	print_vma_addr("in ", regs->psw.addr);
 	printk("\n");
 	show_regs(regs);
 }
@@ -69,13 +68,13 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 		report_user_fault(regs, si_signo);
         } else {
                 const struct exception_table_entry *fixup;
-                fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
+		fixup = search_exception_tables(regs->psw.addr);
                 if (fixup)
-			regs->psw.addr = extable_fixup(fixup) | PSW_ADDR_AMODE;
+			regs->psw.addr = extable_fixup(fixup);
 		else {
 			enum bug_trap_type btt;
 
-			btt = report_bug(regs->psw.addr & PSW_ADDR_INSN, regs);
+			btt = report_bug(regs->psw.addr, regs);
 			if (btt == BUG_TRAP_TYPE_WARN)
 				return;
 			die(regs, str);

arch/s390/kvm/Kconfig

@@ -29,6 +29,7 @@ config KVM
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
 	select SRCU
+	select KVM_VFIO
 	---help---
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work

arch/s390/kvm/Makefile

@@ -7,7 +7,7 @@
 # as published by the Free Software Foundation.
 
 KVM := ../../../virt/kvm
-common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqchip.o
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 

arch/s390/kvm/guestdbg.c

@@ -116,7 +116,7 @@ static void enable_all_hw_wp(struct kvm_vcpu *vcpu)
 	if (*cr9 & PER_EVENT_STORE && *cr9 & PER_CONTROL_ALTERATION) {
 		*cr9 &= ~PER_CONTROL_ALTERATION;
 		*cr10 = 0;
-		*cr11 = PSW_ADDR_INSN;
+		*cr11 = -1UL;
 	} else {
 		*cr9 &= ~PER_CONTROL_ALTERATION;
 		*cr9 |= PER_EVENT_STORE;
@@ -159,7 +159,7 @@ void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->gcr[0] &= ~0x800ul;
 		vcpu->arch.sie_block->gcr[9] |= PER_EVENT_IFETCH;
 		vcpu->arch.sie_block->gcr[10] = 0;
-		vcpu->arch.sie_block->gcr[11] = PSW_ADDR_INSN;
+		vcpu->arch.sie_block->gcr[11] = -1UL;
 	}
 
 	if (guestdbg_hw_bp_enabled(vcpu)) {

arch/s390/kvm/kvm-s390.c

@@ -1423,44 +1423,18 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-/*
- * Backs up the current FP/VX register save area on a particular
- * destination.  Used to switch between different register save
- * areas.
- */
-static inline void save_fpu_to(struct fpu *dst)
-{
-	dst->fpc = current->thread.fpu.fpc;
-	dst->regs = current->thread.fpu.regs;
-}
-
-/*
- * Switches the FP/VX register save area from which to lazy
- * restore register contents.
- */
-static inline void load_fpu_from(struct fpu *from)
-{
-	current->thread.fpu.fpc = from->fpc;
-	current->thread.fpu.regs = from->regs;
-}
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	/* Save host register state */
 	save_fpu_regs();
-	save_fpu_to(&vcpu->arch.host_fpregs);
+	vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
-
+	vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
-	if (test_kvm_facility(vcpu->kvm, 129)) {
-		current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
-		/*
-		 * Use the register save area in the SIE-control block
-		 * for register restore and save in kvm_arch_vcpu_put()
-		 */
-		current->thread.fpu.vxrs =
-			(__vector128 *)&vcpu->run->s.regs.vrs;
-	} else
-		load_fpu_from(&vcpu->arch.guest_fpregs);
 
+	/* Depending on MACHINE_HAS_VX, data stored to vrs either
+	 * has vector register or floating point register format.
+	 */
+	current->thread.fpu.regs = vcpu->run->s.regs.vrs;
+	current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
 	if (test_fp_ctl(current->thread.fpu.fpc))
 		/* User space provided an invalid FPC, let's clear it */
 		current->thread.fpu.fpc = 0;
@@ -1476,19 +1450,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 
+	/* Save guest register state */
 	save_fpu_regs();
+	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
 
-	if (test_kvm_facility(vcpu->kvm, 129))
+	/* Restore host register state */
-		/*
+	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
-		 * kvm_arch_vcpu_load() set up the register save area to
+	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
-		 * the &vcpu->run->s.regs.vrs and, thus, the vector registers
-		 * are already saved.  Only the floating-point control must be
-		 * copied.
-		 */
-		vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
-	else
-		save_fpu_to(&vcpu->arch.guest_fpregs);
-	load_fpu_from(&vcpu->arch.host_fpregs);
 
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
@@ -1506,8 +1474,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
 	vcpu->arch.sie_block->gcr[0]  = 0xE0UL;
 	vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
-	vcpu->arch.guest_fpregs.fpc = 0;
+	/* make sure the new fpc will be lazily loaded */
-	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
+	save_fpu_regs();
+	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -1648,17 +1617,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.local_int.wq = &vcpu->wq;
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
 
-	/*
-	 * Allocate a save area for floating-point registers.  If the vector
-	 * extension is available, register contents are saved in the SIE
-	 * control block.  The allocated save area is still required in
-	 * particular places, for example, in kvm_s390_vcpu_store_status().
-	 */
-	vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS,
-					       GFP_KERNEL);
-	if (!vcpu->arch.guest_fpregs.fprs)
-		goto out_free_sie_block;
-
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
 		goto out_free_sie_block;
@@ -1879,19 +1837,27 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
+	/* make sure the new values will be lazily loaded */
+	save_fpu_regs();
 	if (test_fp_ctl(fpu->fpc))
 		return -EINVAL;
-	memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
+	current->thread.fpu.fpc = fpu->fpc;
-	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
+	if (MACHINE_HAS_VX)
-	save_fpu_regs();
+		convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
-	load_fpu_from(&vcpu->arch.guest_fpregs);
+	else
+		memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
+	/* make sure we have the latest values */
-	fpu->fpc = vcpu->arch.guest_fpregs.fpc;
+	save_fpu_regs();
+	if (MACHINE_HAS_VX)
+		convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+	else
+		memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+	fpu->fpc = current->thread.fpu.fpc;
 	return 0;
 }
 
@@ -2396,6 +2362,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 {
 	unsigned char archmode = 1;
+	freg_t fprs[NUM_FPRS];
 	unsigned int px;
 	u64 clkcomp;
 	int rc;
@@ -2411,8 +2378,16 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 		gpa = px;
 	} else
 		gpa -= __LC_FPREGS_SAVE_AREA;
-	rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+
-			     vcpu->arch.guest_fpregs.fprs, 128);
+	/* manually convert vector registers if necessary */
+	if (MACHINE_HAS_VX) {
+		convert_vx_to_fp(fprs, current->thread.fpu.vxrs);
+		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+				     fprs, 128);
+	} else {
+		rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
+				     vcpu->run->s.regs.vrs, 128);
+	}
 	rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA,
 			      vcpu->run->s.regs.gprs, 128);
 	rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA,
@@ -2420,7 +2395,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
 	rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA,
 			      &px, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA,
-			      &vcpu->arch.guest_fpregs.fpc, 4);
+			      &vcpu->run->s.regs.fpc, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA,
 			      &vcpu->arch.sie_block->todpr, 4);
 	rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA,
@@ -2443,19 +2418,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	 * it into the save area
 	 */
 	save_fpu_regs();
-	if (test_kvm_facility(vcpu->kvm, 129)) {
+	vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
-		/*
-		 * If the vector extension is available, the vector registers
-		 * which overlaps with floating-point registers are saved in
-		 * the SIE-control block.  Hence, extract the floating-point
-		 * registers and the FPC value and store them in the
-		 * guest_fpregs structure.
-		 */
-		vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc;
-		convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs,
-				 current->thread.fpu.vxrs);
-	} else
-		save_fpu_to(&vcpu->arch.guest_fpregs);
 	save_access_regs(vcpu->run->s.regs.acrs);
 
 	return kvm_s390_store_status_unloaded(vcpu, addr);

arch/s390/mm/fault.c

@@ -228,7 +228,7 @@ static inline void report_user_fault(struct pt_regs *regs, long signr)
 		return;
 	printk(KERN_ALERT "User process fault: interruption code %04x ilc:%d ",
 	       regs->int_code & 0xffff, regs->int_code >> 17);
-	print_vma_addr(KERN_CONT "in ", regs->psw.addr & PSW_ADDR_INSN);
+	print_vma_addr(KERN_CONT "in ", regs->psw.addr);
 	printk(KERN_CONT "\n");
 	printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n",
 	       regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
@@ -256,9 +256,9 @@ static noinline void do_no_context(struct pt_regs *regs)
 	const struct exception_table_entry *fixup;
 
 	/* Are we prepared to handle this kernel fault?  */
-	fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN);
+	fixup = search_exception_tables(regs->psw.addr);
 	if (fixup) {
-		regs->psw.addr = extable_fixup(fixup) | PSW_ADDR_AMODE;
+		regs->psw.addr = extable_fixup(fixup);
 		return;
 	}
 

arch/s390/mm/init.c

@@ -98,7 +98,7 @@ void __init paging_init(void)
 	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
 	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
 	__ctl_load(S390_lowcore.kernel_asce, 13, 13);
-	arch_local_irq_restore(4UL << (BITS_PER_LONG - 8));
+	__arch_local_irq_stosm(0x04);
 
 	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();

arch/s390/mm/mmap.c

@@ -169,12 +169,12 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags)
 {
-	if (is_compat_task() || (TASK_SIZE >= (1UL << 53)))
+	if (is_compat_task() || TASK_SIZE >= TASK_MAX_SIZE)
 		return 0;
 	if (!(flags & MAP_FIXED))
 		addr = 0;
 	if ((addr + len) >= TASK_SIZE)
-		return crst_table_upgrade(current->mm, 1UL << 53);
+		return crst_table_upgrade(current->mm, TASK_MAX_SIZE);
 	return 0;
 }
 
@@ -189,9 +189,9 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr,
 	area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
 	if (!(area & ~PAGE_MASK))
 		return area;
-	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) {
+	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) {
 		/* Upgrade the page table to 4 levels and retry. */
-		rc = crst_table_upgrade(mm, 1UL << 53);
+		rc = crst_table_upgrade(mm, TASK_MAX_SIZE);
 		if (rc)
 			return (unsigned long) rc;
 		area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
@@ -211,9 +211,9 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
 	area = arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags);
 	if (!(area & ~PAGE_MASK))
 		return area;
-	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) {
+	if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) {
 		/* Upgrade the page table to 4 levels and retry. */
-		rc = crst_table_upgrade(mm, 1UL << 53);
+		rc = crst_table_upgrade(mm, TASK_MAX_SIZE);
 		if (rc)
 			return (unsigned long) rc;
 		area = arch_get_unmapped_area_topdown(filp, addr, len,

arch/s390/mm/pgtable.c

@@ -55,7 +55,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
 	unsigned long entry;
 	int flush;
 
-	BUG_ON(limit > (1UL << 53));
+	BUG_ON(limit > TASK_MAX_SIZE);
 	flush = 0;
 repeat:
 	table = crst_table_alloc(mm);

arch/s390/numa/numa.c

@@ -57,9 +57,7 @@ static __init pg_data_t *alloc_node_data(void)
 {
 	pg_data_t *res;
 
-	res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 1);
+	res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 8);
-	if (!res)
-		panic("Could not allocate memory for node data!\n");
 	memset(res, 0, sizeof(pg_data_t));
 	return res;
 }
@@ -162,7 +160,7 @@ static int __init numa_init_late(void)
 		register_one_node(nid);
 	return 0;
 }
-device_initcall(numa_init_late);
+arch_initcall(numa_init_late);
 
 static int __init parse_debug(char *parm)
 {

arch/s390/oprofile/backtrace.c

@@ -16,24 +16,23 @@ __show_trace(unsigned int *depth, unsigned long sp,
 	struct pt_regs *regs;
 
 	while (*depth) {
-		sp = sp & PSW_ADDR_INSN;
 		if (sp < low || sp > high - sizeof(*sf))
 			return sp;
 		sf = (struct stack_frame *) sp;
 		(*depth)--;
-		oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN);
+		oprofile_add_trace(sf->gprs[8]);
 
 		/* Follow the backchain.  */
 		while (*depth) {
 			low = sp;
-			sp = sf->back_chain & PSW_ADDR_INSN;
+			sp = sf->back_chain;
 			if (!sp)
 				break;
 			if (sp <= low || sp > high - sizeof(*sf))
 				return sp;
 			sf = (struct stack_frame *) sp;
 			(*depth)--;
-			oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN);
+			oprofile_add_trace(sf->gprs[8]);
 
 		}
 
@@ -46,7 +45,7 @@ __show_trace(unsigned int *depth, unsigned long sp,
 			return sp;
 		regs = (struct pt_regs *) sp;
 		(*depth)--;
-		oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN);
+		oprofile_add_trace(sf->gprs[8]);
 		low = sp;
 		sp = regs->gprs[15];
 	}

arch/s390/pci/pci.c

@@ -68,9 +68,12 @@ static struct airq_struct zpci_airq = {
 	.isc = PCI_ISC,
 };
 
-/* I/O Map */
+#define ZPCI_IOMAP_ENTRIES						\
+	min(((unsigned long) CONFIG_PCI_NR_FUNCTIONS * PCI_BAR_COUNT),	\
+	    ZPCI_IOMAP_MAX_ENTRIES)
+
 static DEFINE_SPINLOCK(zpci_iomap_lock);
-static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
+static unsigned long *zpci_iomap_bitmap;
 struct zpci_iomap_entry *zpci_iomap_start;
 EXPORT_SYMBOL_GPL(zpci_iomap_start);
 
@@ -265,27 +268,20 @@ void __iomem *pci_iomap_range(struct pci_dev *pdev,
 			      unsigned long max)
 {
 	struct zpci_dev *zdev =	to_zpci(pdev);
-	u64 addr;
 	int idx;
 
-	if ((bar & 7) != bar)
+	if (!pci_resource_len(pdev, bar))
 		return NULL;
 
 	idx = zdev->bars[bar].map_idx;
 	spin_lock(&zpci_iomap_lock);
-	if (zpci_iomap_start[idx].count++) {
-		BUG_ON(zpci_iomap_start[idx].fh != zdev->fh ||
-		       zpci_iomap_start[idx].bar != bar);
-	} else {
-		zpci_iomap_start[idx].fh = zdev->fh;
-		zpci_iomap_start[idx].bar = bar;
-	}
 	/* Detect overrun */
-	BUG_ON(!zpci_iomap_start[idx].count);
+	WARN_ON(!++zpci_iomap_start[idx].count);
+	zpci_iomap_start[idx].fh = zdev->fh;
+	zpci_iomap_start[idx].bar = bar;
 	spin_unlock(&zpci_iomap_lock);
 
-	addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48);
+	return (void __iomem *) ZPCI_ADDR(idx) + offset;
-	return (void __iomem *) addr + offset;
 }
 EXPORT_SYMBOL(pci_iomap_range);
 
@@ -297,12 +293,11 @@ EXPORT_SYMBOL(pci_iomap);
 
 void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
 {
-	unsigned int idx;
+	unsigned int idx = ZPCI_IDX(addr);
 
-	idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48;
 	spin_lock(&zpci_iomap_lock);
 	/* Detect underrun */
-	BUG_ON(!zpci_iomap_start[idx].count);
+	WARN_ON(!zpci_iomap_start[idx].count);
 	if (!--zpci_iomap_start[idx].count) {
 		zpci_iomap_start[idx].fh = 0;
 		zpci_iomap_start[idx].bar = 0;
@@ -544,15 +539,15 @@ static void zpci_irq_exit(void)
 
 static int zpci_alloc_iomap(struct zpci_dev *zdev)
 {
-	int entry;
+	unsigned long entry;
 
 	spin_lock(&zpci_iomap_lock);
-	entry = find_first_zero_bit(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES);
+	entry = find_first_zero_bit(zpci_iomap_bitmap, ZPCI_IOMAP_ENTRIES);
-	if (entry == ZPCI_IOMAP_MAX_ENTRIES) {
+	if (entry == ZPCI_IOMAP_ENTRIES) {
 		spin_unlock(&zpci_iomap_lock);
 		return -ENOSPC;
 	}
-	set_bit(entry, zpci_iomap);
+	set_bit(entry, zpci_iomap_bitmap);
 	spin_unlock(&zpci_iomap_lock);
 	return entry;
 }
@@ -561,7 +556,7 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry)
 {
 	spin_lock(&zpci_iomap_lock);
 	memset(&zpci_iomap_start[entry], 0, sizeof(struct zpci_iomap_entry));
-	clear_bit(entry, zpci_iomap);
+	clear_bit(entry, zpci_iomap_bitmap);
 	spin_unlock(&zpci_iomap_lock);
 }
 
@@ -611,8 +606,7 @@ static int zpci_setup_bus_resources(struct zpci_dev *zdev,
 		if (zdev->bars[i].val & 4)
 			flags |= IORESOURCE_MEM_64;
 
-		addr = ZPCI_IOMAP_ADDR_BASE + ((u64) entry << 48);
+		addr = ZPCI_ADDR(entry);
-
 		size = 1UL << zdev->bars[i].size;
 
 		res = __alloc_res(zdev, addr, size, flags);
@@ -873,23 +867,30 @@ static int zpci_mem_init(void)
 	zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb),
 				16, 0, NULL);
 	if (!zdev_fmb_cache)
-		goto error_zdev;
+		goto error_fmb;
 
-	/* TODO: use realloc */
+	zpci_iomap_start = kcalloc(ZPCI_IOMAP_ENTRIES,
-	zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start),
+				   sizeof(*zpci_iomap_start), GFP_KERNEL);
-				   GFP_KERNEL);
 	if (!zpci_iomap_start)
 		goto error_iomap;
-	return 0;
 
+	zpci_iomap_bitmap = kcalloc(BITS_TO_LONGS(ZPCI_IOMAP_ENTRIES),
+				    sizeof(*zpci_iomap_bitmap), GFP_KERNEL);
+	if (!zpci_iomap_bitmap)
+		goto error_iomap_bitmap;
+
+	return 0;
+error_iomap_bitmap:
+	kfree(zpci_iomap_start);
 error_iomap:
 	kmem_cache_destroy(zdev_fmb_cache);
-error_zdev:
+error_fmb:
 	return -ENOMEM;
 }
 
 static void zpci_mem_exit(void)
 {
+	kfree(zpci_iomap_bitmap);
 	kfree(zpci_iomap_start);
 	kmem_cache_destroy(zdev_fmb_cache);
 }

arch/s390/pci/pci_event.c

@@ -53,6 +53,11 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 
 	pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n",
 	       pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid);
+
+	if (!pdev)
+		return;
+
+	pdev->error_state = pci_channel_io_perm_failure;
 }
 
 void zpci_event_error(void *data)

arch/sh/include/asm/barrier.h

@@ -33,7 +33,6 @@
 #endif
 
 #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#define smp_store_mb(var, value) __smp_store_mb(var, value)
 
 #include <asm-generic/barrier.h>
 

arch/x86/Kconfig

@@ -509,11 +509,10 @@ config X86_INTEL_CE
 
 config X86_INTEL_MID
 	bool "Intel MID platform support"
-	depends on X86_32
 	depends on X86_EXTENDED_PLATFORM
 	depends on X86_PLATFORM_DEVICES
 	depends on PCI
-	depends on PCI_GOANY
+	depends on X86_64 || (PCI_GOANY && X86_32)
 	depends on X86_IO_APIC
 	select SFI
 	select I2C

arch/x86/include/asm/irq.h

@@ -23,11 +23,13 @@ extern void irq_ctx_init(int cpu);
 
 #define __ARCH_HAS_DO_SOFTIRQ
 
+struct irq_desc;
+
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern int check_irq_vectors_for_cpu_disable(void);
 extern void fixup_irqs(void);
-extern void irq_force_complete_move(int);
+extern void irq_force_complete_move(struct irq_desc *desc);
 #endif
 
 #ifdef CONFIG_HAVE_KVM
@@ -37,7 +39,6 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
 extern void (*x86_platform_ipi_callback)(void);
 extern void native_init_IRQ(void);
 
-struct irq_desc;
 extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs);
 
 extern __visible unsigned int do_IRQ(struct pt_regs *regs);

arch/x86/include/asm/pgtable_types.h

@@ -366,20 +366,18 @@ static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot)
 }
 static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot)
 {
+	pgprotval_t val = pgprot_val(pgprot);
 	pgprot_t new;
-	unsigned long val;
 
-	val = pgprot_val(pgprot);
 	pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
 		((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
 	return new;
 }
 static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot)
 {
+	pgprotval_t val = pgprot_val(pgprot);
 	pgprot_t new;
-	unsigned long val;
 
-	val = pgprot_val(pgprot);
 	pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
 			  ((val & _PAGE_PAT_LARGE) >>
 			   (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));

arch/x86/kernel/apic/io_apic.c

@@ -2521,6 +2521,7 @@ void __init setup_ioapic_dest(void)
 {
 	int pin, ioapic, irq, irq_entry;
 	const struct cpumask *mask;
+	struct irq_desc *desc;
 	struct irq_data *idata;
 	struct irq_chip *chip;
 
@@ -2536,7 +2537,9 @@ void __init setup_ioapic_dest(void)
 		if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq))
 			continue;
 
-		idata = irq_get_irq_data(irq);
+		desc = irq_to_desc(irq);
+		raw_spin_lock_irq(&desc->lock);
+		idata = irq_desc_get_irq_data(desc);
 
 		/*
 		 * Honour affinities which have been set in early boot
@@ -2550,6 +2553,7 @@ void __init setup_ioapic_dest(void)
 		/* Might be lapic_chip for irq 0 */
 		if (chip->irq_set_affinity)
 			chip->irq_set_affinity(idata, mask, false);
+		raw_spin_unlock_irq(&desc->lock);
 	}
 }
 #endif

arch/x86/kernel/apic/vector.c

@@ -31,7 +31,7 @@ struct apic_chip_data {
 struct irq_domain *x86_vector_domain;
 EXPORT_SYMBOL_GPL(x86_vector_domain);
 static DEFINE_RAW_SPINLOCK(vector_lock);
-static cpumask_var_t vector_cpumask;
+static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask;
 static struct irq_chip lapic_controller;
 #ifdef	CONFIG_X86_IO_APIC
 static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY];
@@ -118,35 +118,47 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d,
 	 */
 	static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
 	static int current_offset = VECTOR_OFFSET_START % 16;
-	int cpu, err;
+	int cpu, vector;
 
-	if (d->move_in_progress)
+	/*
+	 * If there is still a move in progress or the previous move has not
+	 * been cleaned up completely, tell the caller to come back later.
+	 */
+	if (d->move_in_progress ||
+	    cpumask_intersects(d->old_domain, cpu_online_mask))
 		return -EBUSY;
 
 	/* Only try and allocate irqs on cpus that are present */
-	err = -ENOSPC;
 	cpumask_clear(d->old_domain);
+	cpumask_clear(searched_cpumask);
 	cpu = cpumask_first_and(mask, cpu_online_mask);
 	while (cpu < nr_cpu_ids) {
-		int new_cpu, vector, offset;
+		int new_cpu, offset;
 
+		/* Get the possible target cpus for @mask/@cpu from the apic */
 		apic->vector_allocation_domain(cpu, vector_cpumask, mask);
 
+		/*
+		 * Clear the offline cpus from @vector_cpumask for searching
+		 * and verify whether the result overlaps with @mask. If true,
+		 * then the call to apic->cpu_mask_to_apicid_and() will
+		 * succeed as well. If not, no point in trying to find a
+		 * vector in this mask.
+		 */
+		cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask);
+		if (!cpumask_intersects(vector_searchmask, mask))
+			goto next_cpu;
+
 		if (cpumask_subset(vector_cpumask, d->domain)) {
-			err = 0;
 			if (cpumask_equal(vector_cpumask, d->domain))
-				break;
+				goto success;
 			/*
-			 * New cpumask using the vector is a proper subset of
+			 * Mark the cpus which are not longer in the mask for
-			 * the current in use mask. So cleanup the vector
+			 * cleanup.
-			 * allocation for the members that are not used anymore.
 			 */
-			cpumask_andnot(d->old_domain, d->domain,
+			cpumask_andnot(d->old_domain, d->domain, vector_cpumask);
-				       vector_cpumask);
+			vector = d->cfg.vector;
-			d->move_in_progress =
+			goto update;
-			   cpumask_intersects(d->old_domain, cpu_online_mask);
-			cpumask_and(d->domain, d->domain, vector_cpumask);
-			break;
 		}
 
 		vector = current_vector;
@@ -158,45 +170,60 @@ next:
 			vector = FIRST_EXTERNAL_VECTOR + offset;
 		}
 
-		if (unlikely(current_vector == vector)) {
+		/* If the search wrapped around, try the next cpu */
-			cpumask_or(d->old_domain, d->old_domain,
+		if (unlikely(current_vector == vector))
-				   vector_cpumask);
+			goto next_cpu;
-			cpumask_andnot(vector_cpumask, mask, d->old_domain);
-			cpu = cpumask_first_and(vector_cpumask,
-						cpu_online_mask);
-			continue;
-		}
 
 		if (test_bit(vector, used_vectors))
 			goto next;
 
-		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
+		for_each_cpu(new_cpu, vector_searchmask) {
 			if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector]))
 				goto next;
 		}
 		/* Found one! */
 		current_vector = vector;
 		current_offset = offset;
-		if (d->cfg.vector) {
+		/* Schedule the old vector for cleanup on all cpus */
+		if (d->cfg.vector)
 			cpumask_copy(d->old_domain, d->domain);
-			d->move_in_progress =
+		for_each_cpu(new_cpu, vector_searchmask)
-			   cpumask_intersects(d->old_domain, cpu_online_mask);
-		}
-		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
 			per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq);
-		d->cfg.vector = vector;
+		goto update;
-		cpumask_copy(d->domain, vector_cpumask);
-		err = 0;
-		break;
-	}
 
-	if (!err) {
+next_cpu:
-		/* cache destination APIC IDs into cfg->dest_apicid */
+		/*
-		err = apic->cpu_mask_to_apicid_and(mask, d->domain,
+		 * We exclude the current @vector_cpumask from the requested
-						   &d->cfg.dest_apicid);
+		 * @mask and try again with the next online cpu in the
+		 * result. We cannot modify @mask, so we use @vector_cpumask
+		 * as a temporary buffer here as it will be reassigned when
+		 * calling apic->vector_allocation_domain() above.
+		 */
+		cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask);
+		cpumask_andnot(vector_cpumask, mask, searched_cpumask);
+		cpu = cpumask_first_and(vector_cpumask, cpu_online_mask);
+		continue;
 	}
+	return -ENOSPC;
 
-	return err;
+update:
+	/*
+	 * Exclude offline cpus from the cleanup mask and set the
+	 * move_in_progress flag when the result is not empty.
+	 */
+	cpumask_and(d->old_domain, d->old_domain, cpu_online_mask);
+	d->move_in_progress = !cpumask_empty(d->old_domain);
+	d->cfg.vector = vector;
+	cpumask_copy(d->domain, vector_cpumask);
+success:
+	/*
+	 * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail
+	 * as we already established, that mask & d->domain & cpu_online_mask
+	 * is not empty.
+	 */
+	BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain,
+					    &d->cfg.dest_apicid));
+	return 0;
 }
 
 static int assign_irq_vector(int irq, struct apic_chip_data *data,
@@ -226,10 +253,8 @@ static int assign_irq_vector_policy(int irq, int node,
 static void clear_irq_vector(int irq, struct apic_chip_data *data)
 {
 	struct irq_desc *desc;
-	unsigned long flags;
 	int cpu, vector;
 
-	raw_spin_lock_irqsave(&vector_lock, flags);
 	BUG_ON(!data->cfg.vector);
 
 	vector = data->cfg.vector;
@@ -239,10 +264,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 	data->cfg.vector = 0;
 	cpumask_clear(data->domain);
 
-	if (likely(!data->move_in_progress)) {
+	/*
-		raw_spin_unlock_irqrestore(&vector_lock, flags);
+	 * If move is in progress or the old_domain mask is not empty,
+	 * i.e. the cleanup IPI has not been processed yet, we need to remove
+	 * the old references to desc from all cpus vector tables.
+	 */
+	if (!data->move_in_progress && cpumask_empty(data->old_domain))
 		return;
-	}
 
 	desc = irq_to_desc(irq);
 	for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
@@ -255,7 +283,6 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 		}
 	}
 	data->move_in_progress = 0;
-	raw_spin_unlock_irqrestore(&vector_lock, flags);
 }
 
 void init_irq_alloc_info(struct irq_alloc_info *info,
@@ -276,19 +303,24 @@ void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src)
 static void x86_vector_free_irqs(struct irq_domain *domain,
 				 unsigned int virq, unsigned int nr_irqs)
 {
+	struct apic_chip_data *apic_data;
 	struct irq_data *irq_data;
+	unsigned long flags;
 	int i;
 
 	for (i = 0; i < nr_irqs; i++) {
 		irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i);
 		if (irq_data && irq_data->chip_data) {
+			raw_spin_lock_irqsave(&vector_lock, flags);
 			clear_irq_vector(virq + i, irq_data->chip_data);
-			free_apic_chip_data(irq_data->chip_data);
+			apic_data = irq_data->chip_data;
+			irq_domain_reset_irq_data(irq_data);
+			raw_spin_unlock_irqrestore(&vector_lock, flags);
+			free_apic_chip_data(apic_data);
 #ifdef	CONFIG_X86_IO_APIC
 			if (virq + i < nr_legacy_irqs())
 				legacy_irq_data[virq + i] = NULL;
 #endif
-			irq_domain_reset_irq_data(irq_data);
 		}
 	}
 }
@@ -406,6 +438,8 @@ int __init arch_early_irq_init(void)
 	arch_init_htirq_domain(x86_vector_domain);
 
 	BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL));
+	BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
+	BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL));
 
 	return arch_early_ioapic_init();
 }
@@ -494,14 +528,7 @@ static int apic_set_affinity(struct irq_data *irq_data,
 		return -EINVAL;
 
 	err = assign_irq_vector(irq, data, dest);
-	if (err) {
+	return err ? err : IRQ_SET_MASK_OK;
-		if (assign_irq_vector(irq, data,
-				      irq_data_get_affinity_mask(irq_data)))
-			pr_err("Failed to recover vector for irq %d\n", irq);
-		return err;
-	}
-
-	return IRQ_SET_MASK_OK;
 }
 
 static struct irq_chip lapic_controller = {
@@ -513,20 +540,12 @@ static struct irq_chip lapic_controller = {
 #ifdef CONFIG_SMP
 static void __send_cleanup_vector(struct apic_chip_data *data)
 {
-	cpumask_var_t cleanup_mask;
+	raw_spin_lock(&vector_lock);
-
+	cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
-	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
-		unsigned int i;
-
-		for_each_cpu_and(i, data->old_domain, cpu_online_mask)
-			apic->send_IPI_mask(cpumask_of(i),
-					    IRQ_MOVE_CLEANUP_VECTOR);
-	} else {
-		cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask);
-		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
-		free_cpumask_var(cleanup_mask);
-	}
 	data->move_in_progress = 0;
+	if (!cpumask_empty(data->old_domain))
+		apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR);
+	raw_spin_unlock(&vector_lock);
 }
 
 void send_cleanup_vector(struct irq_cfg *cfg)
@@ -570,12 +589,25 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 			goto unlock;
 
 		/*
-		 * Check if the irq migration is in progress. If so, we
+		 * Nothing to cleanup if irq migration is in progress
-		 * haven't received the cleanup request yet for this irq.
+		 * or this cpu is not set in the cleanup mask.
 		 */
-		if (data->move_in_progress)
+		if (data->move_in_progress ||
+		    !cpumask_test_cpu(me, data->old_domain))
 			goto unlock;
 
+		/*
+		 * We have two cases to handle here:
+		 * 1) vector is unchanged but the target mask got reduced
+		 * 2) vector and the target mask has changed
+		 *
+		 * #1 is obvious, but in #2 we have two vectors with the same
+		 * irq descriptor: the old and the new vector. So we need to
+		 * make sure that we only cleanup the old vector. The new
+		 * vector has the current @vector number in the config and
+		 * this cpu is part of the target mask. We better leave that
+		 * one alone.
+		 */
 		if (vector == data->cfg.vector &&
 		    cpumask_test_cpu(me, data->domain))
 			goto unlock;
@@ -593,6 +625,7 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 			goto unlock;
 		}
 		__this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
+		cpumask_clear_cpu(me, data->old_domain);
 unlock:
 		raw_spin_unlock(&desc->lock);
 	}
@@ -621,12 +654,48 @@ void irq_complete_move(struct irq_cfg *cfg)
 	__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
 }
 
-void irq_force_complete_move(int irq)
+/*
+ * Called with @desc->lock held and interrupts disabled.
+ */
+void irq_force_complete_move(struct irq_desc *desc)
 {
-	struct irq_cfg *cfg = irq_cfg(irq);
+	struct irq_data *irqdata = irq_desc_get_irq_data(desc);
+	struct apic_chip_data *data = apic_chip_data(irqdata);
+	struct irq_cfg *cfg = data ? &data->cfg : NULL;
 
-	if (cfg)
+	if (!cfg)
-		__irq_complete_move(cfg, cfg->vector);
+		return;
+
+	__irq_complete_move(cfg, cfg->vector);
+
+	/*
+	 * This is tricky. If the cleanup of @data->old_domain has not been
+	 * done yet, then the following setaffinity call will fail with
+	 * -EBUSY. This can leave the interrupt in a stale state.
+	 *
+	 * The cleanup cannot make progress because we hold @desc->lock. So in
+	 * case @data->old_domain is not yet cleaned up, we need to drop the
+	 * lock and acquire it again. @desc cannot go away, because the
+	 * hotplug code holds the sparse irq lock.
+	 */
+	raw_spin_lock(&vector_lock);
+	/* Clean out all offline cpus (including ourself) first. */
+	cpumask_and(data->old_domain, data->old_domain, cpu_online_mask);
+	while (!cpumask_empty(data->old_domain)) {
+		raw_spin_unlock(&vector_lock);
+		raw_spin_unlock(&desc->lock);
+		cpu_relax();
+		raw_spin_lock(&desc->lock);
+		/*
+		 * Reevaluate apic_chip_data. It might have been cleared after
+		 * we dropped @desc->lock.
+		 */
+		data = apic_chip_data(irqdata);
+		if (!data)
+			return;
+		raw_spin_lock(&vector_lock);
+	}
+	raw_spin_unlock(&vector_lock);
 }
 #endif
 

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -889,7 +889,10 @@ void __init uv_system_init(void)
 		return;
 	}
 	pr_info("UV: Found %s hub\n", hub);
-	map_low_mmrs();
+
+	/* We now only need to map the MMRs on UV1 */
+	if (is_uv1_hub())
+		map_low_mmrs();
 
 	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
 	m_val = m_n_config.s.m_skt;

arch/x86/kernel/cpu/perf_event_intel.c

@@ -1960,7 +1960,8 @@ intel_bts_constraints(struct perf_event *event)
 
 static int intel_alt_er(int idx, u64 config)
 {
-	int alt_idx;
+	int alt_idx = idx;
+
 	if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1))
 		return idx;
 
@@ -2897,14 +2898,12 @@ static void intel_pmu_cpu_starting(int cpu)
 		return;
 
 	if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) {
-		void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED];
-
 		for_each_cpu(i, topology_sibling_cpumask(cpu)) {
 			struct intel_shared_regs *pc;
 
 			pc = per_cpu(cpu_hw_events, i).shared_regs;
 			if (pc && pc->core_id == core_id) {
-				*onln = cpuc->shared_regs;
+				cpuc->kfree_on_online[0] = cpuc->shared_regs;
 				cpuc->shared_regs = pc;
 				break;
 			}

arch/x86/kernel/cpu/perf_event_intel_uncore.c

@@ -995,6 +995,9 @@ static int __init uncore_pci_init(void)
 	case 87: /* Knights Landing */
 		ret = knl_uncore_pci_init();
 		break;
+	case 94: /* SkyLake */
+		ret = skl_uncore_pci_init();
+		break;
 	default:
 		return 0;
 	}

arch/x86/kernel/cpu/perf_event_intel_uncore.h

@@ -336,6 +336,7 @@ int snb_uncore_pci_init(void);
 int ivb_uncore_pci_init(void);
 int hsw_uncore_pci_init(void);
 int bdw_uncore_pci_init(void);
+int skl_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
 int snb_pci2phy_map_init(int devid);

arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c

@@ -8,6 +8,7 @@
 #define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
 #define PCI_DEVICE_ID_INTEL_BDW_IMC	0x1604
+#define PCI_DEVICE_ID_INTEL_SKL_IMC	0x191f
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -524,6 +525,14 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = {
 	{ /* end: all zeroes */ },
 };
 
+static const struct pci_device_id skl_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
 static struct pci_driver snb_uncore_pci_driver = {
 	.name		= "snb_uncore",
 	.id_table	= snb_uncore_pci_ids,
@@ -544,6 +553,11 @@ static struct pci_driver bdw_uncore_pci_driver = {
 	.id_table	= bdw_uncore_pci_ids,
 };
 
+static struct pci_driver skl_uncore_pci_driver = {
+	.name		= "skl_uncore",
+	.id_table	= skl_uncore_pci_ids,
+};
+
 struct imc_uncore_pci_dev {
 	__u32 pci_id;
 	struct pci_driver *driver;
@@ -558,6 +572,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
 	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
 	IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver),    /* 5th Gen Core U */
+	IMC_DEV(SKL_IMC, &skl_uncore_pci_driver),    /* 6th Gen Core */
 	{  /* end marker */ }
 };
 
@@ -610,6 +625,11 @@ int bdw_uncore_pci_init(void)
 	return imc_uncore_pci_init();
 }
 
+int skl_uncore_pci_init(void)
+{
+	return imc_uncore_pci_init();
+}
+
 /* end of Sandy Bridge uncore support */
 
 /* Nehalem uncore support */

arch/x86/kernel/head64.c

@@ -192,5 +192,13 @@ void __init x86_64_start_reservations(char *real_mode_data)
 
 	reserve_ebda_region();
 
+	switch (boot_params.hdr.hardware_subarch) {
+	case X86_SUBARCH_INTEL_MID:
+		x86_intel_mid_early_setup();
+		break;
+	default:
+		break;
+	}
+
 	start_kernel();
 }

arch/x86/kernel/irq.c

@@ -462,7 +462,7 @@ void fixup_irqs(void)
 		 * non intr-remapping case, we can't wait till this interrupt
 		 * arrives at this cpu before completing the irq move.
 		 */
-		irq_force_complete_move(irq);
+		irq_force_complete_move(desc);
 
 		if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
 			break_affinity = 1;
@@ -470,6 +470,15 @@ void fixup_irqs(void)
 		}
 
 		chip = irq_data_get_irq_chip(data);
+		/*
+		 * The interrupt descriptor might have been cleaned up
+		 * already, but it is not yet removed from the radix tree
+		 */
+		if (!chip) {
+			raw_spin_unlock(&desc->lock);
+			continue;
+		}
+
 		if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
 			chip->irq_mask(data);
 

arch/x86/mm/pageattr.c

@@ -33,7 +33,7 @@ struct cpa_data {
 	pgd_t		*pgd;
 	pgprot_t	mask_set;
 	pgprot_t	mask_clr;
-	int		numpages;
+	unsigned long	numpages;
 	int		flags;
 	unsigned long	pfn;
 	unsigned	force_split : 1;
@@ -1350,7 +1350,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 		 * CPA operation. Either a large page has been
 		 * preserved or a single page update happened.
 		 */
-		BUG_ON(cpa->numpages > numpages);
+		BUG_ON(cpa->numpages > numpages || !cpa->numpages);
 		numpages -= cpa->numpages;
 		if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY))
 			cpa->curpage++;

arch/x86/platform/efi/quirks.c

@@ -8,6 +8,7 @@
 #include <linux/memblock.h>
 #include <linux/bootmem.h>
 #include <linux/acpi.h>
+#include <linux/dmi.h>
 #include <asm/efi.h>
 #include <asm/uv/uv.h>
 
@@ -248,6 +249,16 @@ out:
 	return ret;
 }
 
+static const struct dmi_system_id sgi_uv1_dmi[] = {
+	{ NULL, "SGI UV1",
+		{	DMI_MATCH(DMI_PRODUCT_NAME,	"Stoutland Platform"),
+			DMI_MATCH(DMI_PRODUCT_VERSION,	"1.0"),
+			DMI_MATCH(DMI_BIOS_VENDOR,	"SGI.COM"),
+		}
+	},
+	{ } /* NULL entry stops DMI scanning */
+};
+
 void __init efi_apply_memmap_quirks(void)
 {
 	/*
@@ -260,10 +271,8 @@ void __init efi_apply_memmap_quirks(void)
 		efi_unmap_memmap();
 	}
 
-	/*
+	/* UV2+ BIOS has a fix for this issue.  UV1 still needs the quirk. */
-	 * UV doesn't support the new EFI pagetable mapping yet.
+	if (dmi_check_system(sgi_uv1_dmi))
-	 */
-	if (is_uv_system())
 		set_bit(EFI_OLD_MEMMAP, &efi.flags);
 }
 

arch/x86/platform/intel-mid/intel-mid.c

@@ -138,7 +138,7 @@ static void intel_mid_arch_setup(void)
 		intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip]();
 	else {
 		intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL]();
-		pr_info("ARCH: Unknown SoC, assuming PENWELL!\n");
+		pr_info("ARCH: Unknown SoC, assuming Penwell!\n");
 	}
 
 out:
@@ -214,12 +214,10 @@ static inline int __init setup_x86_intel_mid_timer(char *arg)
 	else if (strcmp("lapic_and_apbt", arg) == 0)
 		intel_mid_timer_options = INTEL_MID_TIMER_LAPIC_APBT;
 	else {
-		pr_warn("X86 INTEL_MID timer option %s not recognised"
+		pr_warn("X86 INTEL_MID timer option %s not recognised use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n",
-			   " use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n",
+			arg);
-			   arg);
 		return -EINVAL;
 	}
 	return 0;
 }
 __setup("x86_intel_mid_timer=", setup_x86_intel_mid_timer);
-

arch/x86/platform/intel-quark/imr.c

@@ -220,11 +220,12 @@ static int imr_dbgfs_state_show(struct seq_file *s, void *unused)
 		if (imr_is_enabled(&imr)) {
 			base = imr_to_phys(imr.addr_lo);
 			end = imr_to_phys(imr.addr_hi) + IMR_MASK;
+			size = end - base + 1;
 		} else {
 			base = 0;
 			end = 0;
+			size = 0;
 		}
-		size = end - base;
 		seq_printf(s, "imr%02i: base=%pa, end=%pa, size=0x%08zx "
 			   "rmask=0x%08x, wmask=0x%08x, %s, %s\n", i,
 			   &base, &end, size, imr.rmask, imr.wmask,
@@ -579,6 +580,7 @@ static void __init imr_fixup_memmap(struct imr_device *idev)
 {
 	phys_addr_t base = virt_to_phys(&_text);
 	size_t size = virt_to_phys(&__end_rodata) - base;
+	unsigned long start, end;
 	int i;
 	int ret;
 
@@ -586,18 +588,24 @@ static void __init imr_fixup_memmap(struct imr_device *idev)
 	for (i = 0; i < idev->max_imr; i++)
 		imr_clear(i);
 
+	start = (unsigned long)_text;
+	end = (unsigned long)__end_rodata - 1;
+
 	/*
 	 * Setup a locked IMR around the physical extent of the kernel
 	 * from the beginning of the .text secton to the end of the
 	 * .rodata section as one physically contiguous block.
+	 *
+	 * We don't round up @size since it is already PAGE_SIZE aligned.
+	 * See vmlinux.lds.S for details.
 	 */
 	ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true);
 	if (ret < 0) {
-		pr_err("unable to setup IMR for kernel: (%p - %p)\n",
+		pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n",
-			&_text, &__end_rodata);
+			size / 1024, start, end);
 	} else {
-		pr_info("protecting kernel .text - .rodata: %zu KiB (%p - %p)\n",
+		pr_info("protecting kernel .text - .rodata: %zu KiB (%lx - %lx)\n",
-			size / 1024, &_text, &__end_rodata);
+			size / 1024, start, end);
 	}
 
 }

block/blk-merge.c

@@ -70,6 +70,18 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q,
 	return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
 }
 
+static inline unsigned get_max_io_size(struct request_queue *q,
+				       struct bio *bio)
+{
+	unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
+	unsigned mask = queue_logical_block_size(q) - 1;
+
+	/* aligned to logical block size */
+	sectors &= ~(mask >> 9);
+
+	return sectors;
+}
+
 static struct bio *blk_bio_segment_split(struct request_queue *q,
 					 struct bio *bio,
 					 struct bio_set *bs,
@@ -81,6 +93,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	unsigned front_seg_size = bio->bi_seg_front_size;
 	bool do_split = true;
 	struct bio *new = NULL;
+	const unsigned max_sectors = get_max_io_size(q, bio);
 
 	bio_for_each_segment(bv, bio, iter) {
 		/*
@@ -90,20 +103,19 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 		if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset))
 			goto split;
 
-		if (sectors + (bv.bv_len >> 9) >
+		if (sectors + (bv.bv_len >> 9) > max_sectors) {
-				blk_max_size_offset(q, bio->bi_iter.bi_sector)) {
 			/*
 			 * Consider this a new segment if we're splitting in
 			 * the middle of this vector.
 			 */
 			if (nsegs < queue_max_segments(q) &&
-			    sectors < blk_max_size_offset(q,
+			    sectors < max_sectors) {
-						bio->bi_iter.bi_sector)) {
 				nsegs++;
-				sectors = blk_max_size_offset(q,
+				sectors = max_sectors;
-						bio->bi_iter.bi_sector);
 			}
-			goto split;
+			if (sectors)
+				goto split;
+			/* Make this single bvec as the 1st segment */
 		}
 
 		if (bvprvp && blk_queue_cluster(q)) {

drivers/acpi/video_detect.c

@@ -135,14 +135,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"),
 		},
 	},
-	{
-	.callback = video_detect_force_vendor,
-	.ident = "Dell Inspiron 5737",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5737"),
-		},
-	},
 
 	/*
 	 * These models have a working acpi_video backlight control, and using

drivers/base/platform-msi.c

@@ -284,6 +284,7 @@ out_free_priv_data:
 
 	return err;
 }
+EXPORT_SYMBOL_GPL(platform_msi_domain_alloc_irqs);
 
 /**
  * platform_msi_domain_free_irqs - Free MSI interrupts for @dev
@@ -301,6 +302,7 @@ void platform_msi_domain_free_irqs(struct device *dev)
 	msi_domain_free_irqs(dev->msi_domain, dev);
 	platform_msi_free_descs(dev, 0, MAX_DEV_MSIS);
 }
+EXPORT_SYMBOL_GPL(platform_msi_domain_free_irqs);
 
 /**
  * platform_msi_get_host_data - Query the private data associated with

drivers/base/platform.c

@@ -558,10 +558,15 @@ static int platform_drv_probe(struct device *_dev)
 		return ret;
 
 	ret = dev_pm_domain_attach(_dev, true);
-	if (ret != -EPROBE_DEFER && drv->probe) {
+	if (ret != -EPROBE_DEFER) {
-		ret = drv->probe(dev);
+		if (drv->probe) {
-		if (ret)
+			ret = drv->probe(dev);
-			dev_pm_domain_detach(_dev, true);
+			if (ret)
+				dev_pm_domain_detach(_dev, true);
+		} else {
+			/* don't fail if just dev_pm_domain_attach failed */
+			ret = 0;
+		}
 	}
 
 	if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) {

drivers/base/power/domain.c

@@ -162,7 +162,7 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 
 /**
  * genpd_queue_power_off_work - Queue up the execution of genpd_poweroff().
- * @genpd: PM domait to power off.
+ * @genpd: PM domain to power off.
  *
  * Queue up the execution of genpd_poweroff() unless it's already been done
  * before.
@@ -172,16 +172,15 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
 	queue_work(pm_wq, &genpd->power_off_work);
 }
 
-static int genpd_poweron(struct generic_pm_domain *genpd);
-
 /**
  * __genpd_poweron - Restore power to a given PM domain and its masters.
  * @genpd: PM domain to power up.
+ * @depth: nesting count for lockdep.
  *
  * Restore power to @genpd and all of its masters so that it is possible to
  * resume a device belonging to it.
  */
-static int __genpd_poweron(struct generic_pm_domain *genpd)
+static int __genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
 {
 	struct gpd_link *link;
 	int ret = 0;
@@ -196,11 +195,16 @@ static int __genpd_poweron(struct generic_pm_domain *genpd)
 	 * with it.
 	 */
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		genpd_sd_counter_inc(link->master);
+		struct generic_pm_domain *master = link->master;
+
+		genpd_sd_counter_inc(master);
+
+		mutex_lock_nested(&master->lock, depth + 1);
+		ret = __genpd_poweron(master, depth + 1);
+		mutex_unlock(&master->lock);
 
-		ret = genpd_poweron(link->master);
 		if (ret) {
-			genpd_sd_counter_dec(link->master);
+			genpd_sd_counter_dec(master);
 			goto err;
 		}
 	}
@@ -232,11 +236,12 @@ static int genpd_poweron(struct generic_pm_domain *genpd)
 	int ret;
 
 	mutex_lock(&genpd->lock);
-	ret = __genpd_poweron(genpd);
+	ret = __genpd_poweron(genpd, 0);
 	mutex_unlock(&genpd->lock);
 	return ret;
 }
 
+
 static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev)
 {
 	return GENPD_DEV_CALLBACK(genpd, int, save_state, dev);
@@ -484,7 +489,7 @@ static int pm_genpd_runtime_resume(struct device *dev)
 	}
 
 	mutex_lock(&genpd->lock);
-	ret = __genpd_poweron(genpd);
+	ret = __genpd_poweron(genpd, 0);
 	mutex_unlock(&genpd->lock);
 
 	if (ret)
@@ -1339,8 +1344,8 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 	if (!link)
 		return -ENOMEM;
 
-	mutex_lock(&genpd->lock);
+	mutex_lock(&subdomain->lock);
-	mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
+	mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING);
 
 	if (genpd->status == GPD_STATE_POWER_OFF
 	    &&  subdomain->status != GPD_STATE_POWER_OFF) {
@@ -1363,8 +1368,8 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 		genpd_sd_counter_inc(genpd);
 
  out:
-	mutex_unlock(&subdomain->lock);
 	mutex_unlock(&genpd->lock);
+	mutex_unlock(&subdomain->lock);
 	if (ret)
 		kfree(link);
 	return ret;
@@ -1385,7 +1390,8 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain))
 		return -EINVAL;
 
-	mutex_lock(&genpd->lock);
+	mutex_lock(&subdomain->lock);
+	mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING);
 
 	if (!list_empty(&subdomain->slave_links) || subdomain->device_count) {
 		pr_warn("%s: unable to remove subdomain %s\n", genpd->name,
@@ -1398,22 +1404,19 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 		if (link->slave != subdomain)
 			continue;
 
-		mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING);
-
 		list_del(&link->master_node);
 		list_del(&link->slave_node);
 		kfree(link);
 		if (subdomain->status != GPD_STATE_POWER_OFF)
 			genpd_sd_counter_dec(genpd);
 
-		mutex_unlock(&subdomain->lock);
-
 		ret = 0;
 		break;
 	}
 
 out:
 	mutex_unlock(&genpd->lock);
+	mutex_unlock(&subdomain->lock);
 
 	return ret;
 }

drivers/clocksource/Kconfig

@@ -30,6 +30,8 @@ config CLKSRC_MMIO
 config DIGICOLOR_TIMER
 	bool "Digicolor timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	select CLKSRC_MMIO
+	depends on HAS_IOMEM
 	help
 	  Enables the support for the digicolor timer driver.
 
@@ -55,6 +57,7 @@ config ARMADA_370_XP_TIMER
 	bool "Armada 370 and XP timer driver" if COMPILE_TEST
 	depends on ARM
 	select CLKSRC_OF
+	select CLKSRC_MMIO
 	help
 	  Enables the support for the Armada 370 and XP timer driver.
 
@@ -76,6 +79,7 @@ config ORION_TIMER
 config SUN4I_TIMER
 	bool "Sun4i timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	select CLKSRC_MMIO
 	help
 	  Enables support for the Sun4i timer.
@@ -89,6 +93,7 @@ config SUN5I_HSTIMER
 
 config TEGRA_TIMER
 	bool "Tegra timer driver" if COMPILE_TEST
+	select CLKSRC_MMIO
 	depends on ARM
 	help
 	  Enables support for the Tegra driver.
@@ -96,6 +101,7 @@ config TEGRA_TIMER
 config VT8500_TIMER
 	bool "VT8500 timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	help
 	  Enables support for the VT8500 driver.
 
@@ -131,6 +137,7 @@ config CLKSRC_NOMADIK_MTU_SCHED_CLOCK
 config CLKSRC_DBX500_PRCMU
 	bool "Clocksource PRCMU Timer" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	help
 	  Use the always on PRCMU Timer as clocksource
 
@@ -248,6 +255,7 @@ config CLKSRC_EXYNOS_MCT
 config CLKSRC_SAMSUNG_PWM
 	bool "PWM timer drvier for Samsung S3C, S5P" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	help
 	  This is a new clocksource driver for the PWM timer found in
 	  Samsung S3C, S5P and Exynos SoCs, replacing an earlier driver
@@ -257,12 +265,14 @@ config CLKSRC_SAMSUNG_PWM
 config FSL_FTM_TIMER
 	bool "Freescale FlexTimer Module driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	select CLKSRC_MMIO
 	help
 	  Support for Freescale FlexTimer Module (FTM) timer.
 
 config VF_PIT_TIMER
 	bool
+	select CLKSRC_MMIO
 	help
 	  Support for Period Interrupt Timer on Freescale Vybrid Family SoCs.
 
@@ -360,6 +370,7 @@ config CLKSRC_TANGO_XTAL
 config CLKSRC_PXA
 	bool "Clocksource for PXA or SA-11x0 platform" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
 	select CLKSRC_MMIO
 	help
 	  This enables OST0 support available on PXA and SA-11x0
@@ -394,6 +405,7 @@ config CLKSRC_ST_LPC
 	bool "Low power clocksource found in the LPC" if COMPILE_TEST
 	select CLKSRC_OF if OF
 	depends on HAS_IOMEM
+	select CLKSRC_MMIO
 	help
 	  Enable this option to use the Low Power controller timer
 	  as clocksource.

drivers/clocksource/tcb_clksrc.c

@@ -98,7 +98,8 @@ static int tc_shutdown(struct clock_event_device *d)
 
 	__raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR));
 	__raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR));
-	clk_disable(tcd->clk);
+	if (!clockevent_state_detached(d))
+		clk_disable(tcd->clk);
 
 	return 0;
 }

drivers/cpufreq/cpufreq-dt.c

@@ -142,15 +142,16 @@ static int allocate_resources(int cpu, struct device **cdev,
 
 try_again:
 	cpu_reg = regulator_get_optional(cpu_dev, reg);
-	if (IS_ERR(cpu_reg)) {
+	ret = PTR_ERR_OR_ZERO(cpu_reg);
+	if (ret) {
 		/*
 		 * If cpu's regulator supply node is present, but regulator is
 		 * not yet registered, we should try defering probe.
 		 */
-		if (PTR_ERR(cpu_reg) == -EPROBE_DEFER) {
+		if (ret == -EPROBE_DEFER) {
 			dev_dbg(cpu_dev, "cpu%d regulator not ready, retry\n",
 				cpu);
-			return -EPROBE_DEFER;
+			return ret;
 		}
 
 		/* Try with "cpu-supply" */
@@ -159,18 +160,16 @@ try_again:
 			goto try_again;
 		}
 
-		dev_dbg(cpu_dev, "no regulator for cpu%d: %ld\n",
+		dev_dbg(cpu_dev, "no regulator for cpu%d: %d\n", cpu, ret);
-			cpu, PTR_ERR(cpu_reg));
 	}
 
 	cpu_clk = clk_get(cpu_dev, NULL);
-	if (IS_ERR(cpu_clk)) {
+	ret = PTR_ERR_OR_ZERO(cpu_clk);
+	if (ret) {
 		/* put regulator */
 		if (!IS_ERR(cpu_reg))
 			regulator_put(cpu_reg);
 
-		ret = PTR_ERR(cpu_clk);
-
 		/*
 		 * If cpu's clk node is present, but clock is not yet
 		 * registered, we should try defering probe.

drivers/cpufreq/cpufreq.c

@@ -48,11 +48,11 @@ static struct cpufreq_policy *next_policy(struct cpufreq_policy *policy,
 					  bool active)
 {
 	do {
-		policy = list_next_entry(policy, policy_list);
-
 		/* No more policies in the list */
-		if (&policy->policy_list == &cpufreq_policy_list)
+		if (list_is_last(&policy->policy_list, &cpufreq_policy_list))
 			return NULL;
+
+		policy = list_next_entry(policy, policy_list);
 	} while (!suitable_policy(policy, active));
 
 	return policy;

drivers/cpufreq/cpufreq_governor.c

@@ -387,16 +387,18 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy,
 	if (!have_governor_per_policy())
 		cdata->gdbs_data = dbs_data;
 
+	policy->governor_data = dbs_data;
+
 	ret = sysfs_create_group(get_governor_parent_kobj(policy),
 				 get_sysfs_attr(dbs_data));
 	if (ret)
 		goto reset_gdbs_data;
 
-	policy->governor_data = dbs_data;
-
 	return 0;
 
 reset_gdbs_data:
+	policy->governor_data = NULL;
+
 	if (!have_governor_per_policy())
 		cdata->gdbs_data = NULL;
 	cdata->exit(dbs_data, !policy->governor->initialized);
@@ -417,16 +419,19 @@ static int cpufreq_governor_exit(struct cpufreq_policy *policy,
 	if (!cdbs->shared || cdbs->shared->policy)
 		return -EBUSY;
 
-	policy->governor_data = NULL;
 	if (!--dbs_data->usage_count) {
 		sysfs_remove_group(get_governor_parent_kobj(policy),
 				   get_sysfs_attr(dbs_data));
 
+		policy->governor_data = NULL;
+
 		if (!have_governor_per_policy())
 			cdata->gdbs_data = NULL;
 
 		cdata->exit(dbs_data, policy->governor->initialized == 1);
 		kfree(dbs_data);
+	} else {
+		policy->governor_data = NULL;
 	}
 
 	free_common_dbs_info(policy, cdata);

drivers/cpufreq/pxa2xx-cpufreq.c

@@ -202,7 +202,7 @@ static void __init pxa_cpufreq_init_voltages(void)
 	}
 }
 #else
-static int pxa_cpufreq_change_voltage(struct pxa_freqs *pxa_freq)
+static int pxa_cpufreq_change_voltage(const struct pxa_freqs *pxa_freq)
 {
 	return 0;
 }

drivers/cpuidle/coupled.c

@@ -119,7 +119,6 @@ struct cpuidle_coupled {
 
 #define CPUIDLE_COUPLED_NOT_IDLE	(-1)
 
-static DEFINE_MUTEX(cpuidle_coupled_lock);
 static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb);
 
 /*

drivers/cpuidle/cpuidle.c

@@ -153,7 +153,7 @@ int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * be frozen safely.
 	 */
 	index = find_deepest_state(drv, dev, UINT_MAX, 0, true);
-	if (index >= 0)
+	if (index > 0)
 		enter_freeze_proper(drv, dev, index);
 
 	return index;

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -2278,60 +2278,60 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_dpm_enable_bapm(adev, e) (adev)->pm.funcs->enable_bapm((adev), (e))
 
 #define amdgpu_dpm_get_temperature(adev) \
-	(adev)->pp_enabled ?						\
+	((adev)->pp_enabled ?						\
 	      (adev)->powerplay.pp_funcs->get_temperature((adev)->powerplay.pp_handle) : \
-	      (adev)->pm.funcs->get_temperature((adev))
+	      (adev)->pm.funcs->get_temperature((adev)))
 
 #define amdgpu_dpm_set_fan_control_mode(adev, m) \
-	(adev)->pp_enabled ?						\
+	((adev)->pp_enabled ?						\
 	      (adev)->powerplay.pp_funcs->set_fan_control_mode((adev)->powerplay.pp_handle, (m)) : \
-	      (adev)->pm.funcs->set_fan_control_mode((adev), (m))
+	      (adev)->pm.funcs->set_fan_control_mode((adev), (m)))
 
 #define amdgpu_dpm_get_fan_control_mode(adev) \
-	(adev)->pp_enabled ?						\
+	((adev)->pp_enabled ?						\
 	      (adev)->powerplay.pp_funcs->get_fan_control_mode((adev)->powerplay.pp_handle) : \
-	      (adev)->pm.funcs->get_fan_control_mode((adev))
+	      (adev)->pm.funcs->get_fan_control_mode((adev)))
 
 #define amdgpu_dpm_set_fan_speed_percent(adev, s) \
-	(adev)->pp_enabled ?						\
+	((adev)->pp_enabled ?						\
 	      (adev)->powerplay.pp_funcs->set_fan_speed_percent((adev)->powerplay.pp_handle, (s)) : \
-	      (adev)->pm.funcs->set_fan_speed_percent((adev), (s))
+	      (adev)->pm.funcs->set_fan_speed_percent((adev), (s)))
 
 #define amdgpu_dpm_get_fan_speed_percent(adev, s) \
-	(adev)->pp_enabled ?						\
+	((adev)->pp_enabled ?						\
 	      (adev)->powerplay.pp_funcs->get_fan_speed_percent((adev)->powerplay.pp_handle, (s)) : \
-	      (adev)->pm.funcs->get_fan_speed_percent((adev), (s))
+	      (adev)->pm.funcs->get_fan_speed_percent((adev), (s)))
 
 #define amdgpu_dpm_get_sclk(adev, l) \
-	(adev)->pp_enabled ?						\
+	((adev)->pp_enabled ?						\
 	      (adev)->powerplay.pp_funcs->get_sclk((adev)->powerplay.pp_handle, (l)) : \
-		(adev)->pm.funcs->get_sclk((adev), (l))
+		(adev)->pm.funcs->get_sclk((adev), (l)))
 
 #define amdgpu_dpm_get_mclk(adev, l)  \
-	(adev)->pp_enabled ?						\
+	((adev)->pp_enabled ?						\
 	      (adev)->powerplay.pp_funcs->get_mclk((adev)->powerplay.pp_handle, (l)) : \
-	      (adev)->pm.funcs->get_mclk((adev), (l))
+	      (adev)->pm.funcs->get_mclk((adev), (l)))
 
 
 #define amdgpu_dpm_force_performance_level(adev, l) \
-	(adev)->pp_enabled ?						\
+	((adev)->pp_enabled ?						\
 	      (adev)->powerplay.pp_funcs->force_performance_level((adev)->powerplay.pp_handle, (l)) : \
-	      (adev)->pm.funcs->force_performance_level((adev), (l))
+	      (adev)->pm.funcs->force_performance_level((adev), (l)))
 
 #define amdgpu_dpm_powergate_uvd(adev, g) \
-	(adev)->pp_enabled ?						\
+	((adev)->pp_enabled ?						\
 	      (adev)->powerplay.pp_funcs->powergate_uvd((adev)->powerplay.pp_handle, (g)) : \
-	      (adev)->pm.funcs->powergate_uvd((adev), (g))
+	      (adev)->pm.funcs->powergate_uvd((adev), (g)))
 
 #define amdgpu_dpm_powergate_vce(adev, g) \
-	(adev)->pp_enabled ?						\
+	((adev)->pp_enabled ?						\
 	      (adev)->powerplay.pp_funcs->powergate_vce((adev)->powerplay.pp_handle, (g)) : \
-	      (adev)->pm.funcs->powergate_vce((adev), (g))
+	      (adev)->pm.funcs->powergate_vce((adev), (g)))
 
 #define amdgpu_dpm_debugfs_print_current_performance_level(adev, m) \
-	(adev)->pp_enabled ?						\
+	((adev)->pp_enabled ?						\
 	      (adev)->powerplay.pp_funcs->print_current_performance_level((adev)->powerplay.pp_handle, (m)) : \
-	      (adev)->pm.funcs->debugfs_print_current_performance_level((adev), (m))
+	      (adev)->pm.funcs->debugfs_print_current_performance_level((adev), (m)))
 
 #define amdgpu_dpm_get_current_power_state(adev) \
 	(adev)->powerplay.pp_funcs->get_current_power_state((adev)->powerplay.pp_handle)