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

Documentation/admin-guide/kernel-parameters.txt

@@ -3523,6 +3523,12 @@
 	ramdisk_size=	[RAM] Sizes of RAM disks in kilobytes
 			See Documentation/blockdev/ramdisk.txt.
 
+	random.trust_cpu={on,off}
+			[KNL] Enable or disable trusting the use of the
+			CPU's random number generator (if available) to
+			fully seed the kernel's CRNG. Default is controlled
+			by CONFIG_RANDOM_TRUST_CPU.
+
 	ras=option[,option,...]	[KNL] RAS-specific options
 
 		cec_disable	[X86]

Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt

@@ -3,7 +3,6 @@
 Required properties:
 - compatible :
   - "fsl,imx7ulp-lpi2c" for LPI2C compatible with the one integrated on i.MX7ULP soc
-  - "fsl,imx8dv-lpi2c" for LPI2C compatible with the one integrated on i.MX8DV soc
 - reg : address and length of the lpi2c master registers
 - interrupts : lpi2c interrupt
 - clocks : lpi2c clock specifier
@@ -11,7 +10,7 @@ Required properties:
 Examples:
 
 lpi2c7: lpi2c7@40a50000 {
-	compatible = "fsl,imx8dv-lpi2c";
+	compatible = "fsl,imx7ulp-lpi2c";
 	reg = <0x40A50000 0x10000>;
 	interrupt-parent = <&intc>;
 	interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;

Documentation/process/changes.rst

@@ -86,7 +86,7 @@ pkg-config
 
 The build system, as of 4.18, requires pkg-config to check for installed
 kconfig tools and to determine flags settings for use in
-'make {menu,n,g,x}config'.  Previously pkg-config was being used but not
+'make {g,x}config'.  Previously pkg-config was being used but not
 verified or documented.
 
 Flex

Documentation/scsi/scsi-parameters.txt

@@ -97,6 +97,11 @@ parameters may be changed at runtime by the command
 			allowing boot to proceed.  none ignores them, expecting
 			user space to do the scan.
 
+	scsi_mod.use_blk_mq=
+			[SCSI] use blk-mq I/O path by default
+			See SCSI_MQ_DEFAULT in drivers/scsi/Kconfig.
+			Format: <y/n>
+
 	sim710=		[SCSI,HW]
 			See header of drivers/scsi/sim710.c.
 

MAINTAINERS

@@ -2311,6 +2311,7 @@ F:	drivers/clocksource/cadence_ttc_timer.c
 F:	drivers/i2c/busses/i2c-cadence.c
 F:	drivers/mmc/host/sdhci-of-arasan.c
 F:	drivers/edac/synopsys_edac.c
+F:	drivers/i2c/busses/i2c-xiic.c
 
 ARM64 PORT (AARCH64 ARCHITECTURE)
 M:	Catalin Marinas <catalin.marinas@arm.com>

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 19
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Merciless Moray
 
 # *DOCUMENTATION*

arch/arc/Kconfig

@@ -9,6 +9,7 @@
 config ARC
 	def_bool y
 	select ARC_TIMERS
+	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_HAS_SG_CHAIN
@@ -28,8 +29,12 @@ config ARC
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_FUTEX_CMPXCHG if FUTEX
+	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_IOREMAP_PROT
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_LZMA
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
 	select HAVE_MEMBLOCK
@@ -44,11 +49,6 @@ config ARC
 	select OF_EARLY_FLATTREE
 	select OF_RESERVED_MEM
 	select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING
-	select HAVE_DEBUG_STACKOVERFLOW
-	select HAVE_GENERIC_DMA_COHERENT
-	select HAVE_KERNEL_GZIP
-	select HAVE_KERNEL_LZMA
-	select ARCH_HAS_PTE_SPECIAL
 
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y

arch/arc/Makefile

@@ -43,10 +43,7 @@ ifdef CONFIG_ARC_CURR_IN_REG
 LINUXINCLUDE	+=  -include ${src}/arch/arc/include/asm/current.h
 endif
 
-upto_gcc44    :=  $(call cc-ifversion, -le, 0404, y)
-atleast_gcc44 :=  $(call cc-ifversion, -ge, 0404, y)
-
-cflags-$(atleast_gcc44)			+= -fsection-anchors
+cflags-y				+= -fsection-anchors
 
 cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
 cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
@@ -82,11 +79,6 @@ cflags-$(disable_small_data)		+= -mno-sdata -fcall-used-gp
 cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= -mbig-endian
 ldflags-$(CONFIG_CPU_BIG_ENDIAN)	+= -EB
 
-# STAR 9000518362: (fixed with binutils shipping with gcc 4.8)
-# arc-linux-uclibc-ld (buildroot) or arceb-elf32-ld (EZChip) don't accept
-# --build-id w/o "-marclinux". Default arc-elf32-ld is OK
-ldflags-$(upto_gcc44)			+= -marclinux
-
 LIBGCC	:= $(shell $(CC) $(cflags-y) --print-libgcc-file-name)
 
 # Modules with short calls might break for calls into builtin-kernel

arch/arc/boot/dts/axc003.dtsi

@@ -93,6 +93,32 @@
 		};
 	};
 
+	/*
+	 * Mark DMA peripherals connected via IOC port as dma-coherent. We do
+	 * it via overlay because peripherals defined in axs10x_mb.dtsi are
+	 * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so
+	 * only AXS103 board has HW-coherent DMA peripherals)
+	 * We don't need to mark pgu@17000 as dma-coherent because it uses
+	 * external DMA buffer located outside of IOC aperture.
+	 */
+	axs10x_mb {
+		ethernet@0x18000 {
+			dma-coherent;
+		};
+
+		ehci@0x40000 {
+			dma-coherent;
+		};
+
+		ohci@0x60000 {
+			dma-coherent;
+		};
+
+		mmc@0x15000 {
+			dma-coherent;
+		};
+	};
+
 	/*
 	 * The DW APB ICTL intc on MB is connected to CPU intc via a
 	 * DT "invisible" DW APB GPIO block, configured to simply pass thru

arch/arc/boot/dts/axc003_idu.dtsi

@@ -100,6 +100,32 @@
 		};
 	};
 
+	/*
+	 * Mark DMA peripherals connected via IOC port as dma-coherent. We do
+	 * it via overlay because peripherals defined in axs10x_mb.dtsi are
+	 * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so
+	 * only AXS103 board has HW-coherent DMA peripherals)
+	 * We don't need to mark pgu@17000 as dma-coherent because it uses
+	 * external DMA buffer located outside of IOC aperture.
+	 */
+	axs10x_mb {
+		ethernet@0x18000 {
+			dma-coherent;
+		};
+
+		ehci@0x40000 {
+			dma-coherent;
+		};
+
+		ohci@0x60000 {
+			dma-coherent;
+		};
+
+		mmc@0x15000 {
+			dma-coherent;
+		};
+	};
+
 	/*
 	 * This INTC is actually connected to DW APB GPIO
 	 * which acts as a wire between MB INTC and CPU INTC.

arch/arc/boot/dts/axs10x_mb.dtsi

@@ -9,6 +9,10 @@
  */
 
 / {
+	aliases {
+		ethernet = &gmac;
+	};
+
 	axs10x_mb {
 		compatible = "simple-bus";
 		#address-cells = <1>;
@@ -68,7 +72,7 @@
 			};
 		};
 
-		ethernet@0x18000 {
+		gmac: ethernet@0x18000 {
 			#interrupt-cells = <1>;
 			compatible = "snps,dwmac";
 			reg = < 0x18000 0x2000 >;
@@ -81,6 +85,7 @@
 			max-speed = <100>;
 			resets = <&creg_rst 5>;
 			reset-names = "stmmaceth";
+			mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */
 		};
 
 		ehci@0x40000 {

arch/arc/boot/dts/hsdk.dts

@@ -25,6 +25,10 @@
 		bootargs = "earlycon=uart8250,mmio32,0xf0005000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
 	};
 
+	aliases {
+		ethernet = &gmac;
+	};
+
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
@@ -163,7 +167,7 @@
 			#clock-cells = <0>;
 		};
 
-		ethernet@8000 {
+		gmac: ethernet@8000 {
 			#interrupt-cells = <1>;
 			compatible = "snps,dwmac";
 			reg = <0x8000 0x2000>;
@@ -176,6 +180,8 @@
 			phy-handle = <&phy0>;
 			resets = <&cgu_rst HSDK_ETH_RESET>;
 			reset-names = "stmmaceth";
+			mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */
+			dma-coherent;
 
 			mdio {
 				#address-cells = <1>;
@@ -194,12 +200,14 @@
 			compatible = "snps,hsdk-v1.0-ohci", "generic-ohci";
 			reg = <0x60000 0x100>;
 			interrupts = <15>;
+			dma-coherent;
 		};
 
 		ehci@40000 {
 			compatible = "snps,hsdk-v1.0-ehci", "generic-ehci";
 			reg = <0x40000 0x100>;
 			interrupts = <15>;
+			dma-coherent;
 		};
 
 		mmc@a000 {
@@ -212,6 +220,7 @@
 			clock-names = "biu", "ciu";
 			interrupts = <12>;
 			bus-width = <4>;
+			dma-coherent;
 		};
 	};
 

arch/arc/configs/axs101_defconfig

@@ -1,5 +1,3 @@
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
-# CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_CROSS_MEMORY_ATTACH is not set
@@ -63,7 +61,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y
 CONFIG_MOUSE_SERIAL=y
 CONFIG_MOUSE_SYNAPTICS_USB=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y

arch/arc/configs/axs103_defconfig

@@ -1,5 +1,3 @@
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
-# CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_CROSS_MEMORY_ATTACH is not set
@@ -64,7 +62,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y
 CONFIG_MOUSE_SERIAL=y
 CONFIG_MOUSE_SYNAPTICS_USB=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y

arch/arc/configs/axs103_smp_defconfig

@@ -1,5 +1,3 @@
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
-# CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 # CONFIG_CROSS_MEMORY_ATTACH is not set
@@ -65,7 +63,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y
 CONFIG_MOUSE_SERIAL=y
 CONFIG_MOUSE_SYNAPTICS_USB=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y

arch/arc/configs/haps_hs_defconfig

@@ -1,4 +1,3 @@
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
@@ -57,7 +56,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIO_ARC_PS2=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=1

arch/arc/configs/haps_hs_smp_defconfig

@@ -1,4 +1,3 @@
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
@@ -60,7 +59,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIO_ARC_PS2=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=1

arch/arc/configs/hsdk_defconfig

@@ -1,4 +1,3 @@
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 CONFIG_SYSVIPC=y
 # CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_NO_HZ_IDLE=y

arch/arc/configs/nps_defconfig

@@ -59,7 +59,6 @@ CONFIG_NETCONSOLE=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=1

arch/arc/configs/nsim_700_defconfig

@@ -1,5 +1,4 @@
 # CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
@@ -44,7 +43,6 @@ CONFIG_LXT_PHY=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set

arch/arc/configs/nsim_hs_defconfig

@@ -1,5 +1,4 @@
 # CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
@@ -45,7 +44,6 @@ CONFIG_DEVTMPFS=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set

arch/arc/configs/nsim_hs_smp_defconfig

@@ -1,5 +1,4 @@
 # CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 # CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_HIGH_RES_TIMERS=y
@@ -44,7 +43,6 @@ CONFIG_DEVTMPFS=y
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_ARC=y
 CONFIG_SERIAL_ARC_CONSOLE=y
 # CONFIG_HW_RANDOM is not set

arch/arc/configs/nsimosci_defconfig

@@ -1,5 +1,4 @@
 # CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 # CONFIG_CROSS_MEMORY_ATTACH is not set
@@ -48,7 +47,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIO_ARC_PS2=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=1

arch/arc/configs/nsimosci_hs_defconfig

@@ -1,5 +1,4 @@
 # CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 # CONFIG_CROSS_MEMORY_ATTACH is not set
@@ -47,7 +46,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIO_ARC_PS2=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=1

arch/arc/configs/nsimosci_hs_smp_defconfig

@@ -1,4 +1,3 @@
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 # CONFIG_CROSS_MEMORY_ATTACH is not set
@@ -58,7 +57,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y
 # CONFIG_SERIO_SERPORT is not set
 CONFIG_SERIO_ARC_PS2=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=1

arch/arc/configs/tb10x_defconfig

@@ -57,7 +57,6 @@ CONFIG_STMMAC_ETH=y
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=1

arch/arc/configs/vdk_hs38_defconfig

@@ -1,5 +1,4 @@
 # CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
@@ -53,7 +52,6 @@ CONFIG_NATIONAL_PHY=y
 CONFIG_MOUSE_PS2_TOUCHKIT=y
 CONFIG_SERIO_ARC_PS2=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_DW=y

arch/arc/configs/vdk_hs38_smp_defconfig

@@ -1,5 +1,4 @@
 # CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_CROSS_MEMORY_ATTACH is not set
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y

arch/arc/include/asm/atomic.h

@@ -84,7 +84,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 	"1:	llock   %[orig], [%[ctr]]		\n"		\
 	"	" #asm_op " %[val], %[orig], %[i]	\n"		\
 	"	scond   %[val], [%[ctr]]		\n"		\
-	"						\n"		\
+	"	bnz     1b				\n"		\
 	: [val]	"=&r"	(val),						\
 	  [orig] "=&r" (orig)						\
 	: [ctr]	"r"	(&v->counter),					\

arch/arc/include/asm/dma-mapping.h

@@ -0,0 +1,13 @@
+// SPDX-License-Identifier:  GPL-2.0
+// (C) 2018 Synopsys, Inc. (www.synopsys.com)
+
+#ifndef ASM_ARC_DMA_MAPPING_H
+#define ASM_ARC_DMA_MAPPING_H
+
+#include <asm-generic/dma-mapping.h>
+
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+			const struct iommu_ops *iommu, bool coherent);
+#define arch_setup_dma_ops arch_setup_dma_ops
+
+#endif

arch/arc/kernel/troubleshoot.c

@@ -83,9 +83,6 @@ done:
 static void show_faulting_vma(unsigned long address, char *buf)
 {
 	struct vm_area_struct *vma;
-	struct inode *inode;
-	unsigned long ino = 0;
-	dev_t dev = 0;
 	char *nm = buf;
 	struct mm_struct *active_mm = current->active_mm;
 
@@ -99,12 +96,10 @@ static void show_faulting_vma(unsigned long address, char *buf)
 	 * if the container VMA is not found
 	 */
 	if (vma && (vma->vm_start <= address)) {
-		struct file *file = vma->vm_file;
-		if (file) {
-			nm = file_path(file, buf, PAGE_SIZE - 1);
-			inode = file_inode(vma->vm_file);
-			dev = inode->i_sb->s_dev;
-			ino = inode->i_ino;
+		if (vma->vm_file) {
+			nm = file_path(vma->vm_file, buf, PAGE_SIZE - 1);
+			if (IS_ERR(nm))
+				nm = "?";
 		}
 		pr_info("    @off 0x%lx in [%s]\n"
 			"    VMA: 0x%08lx to 0x%08lx\n",

arch/arc/mm/cache.c

@@ -65,7 +65,7 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len)
 
 	n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n",
 		       perip_base,
-		       IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency "));
+		       IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency (per-device) "));
 
 	return buf;
 }
@@ -896,15 +896,6 @@ static void __dma_cache_wback_slc(phys_addr_t start, unsigned long sz)
 	slc_op(start, sz, OP_FLUSH);
 }
 
-/*
- * DMA ops for systems with IOC
- * IOC hardware snoops all DMA traffic keeping the caches consistent with
- * memory - eliding need for any explicit cache maintenance of DMA buffers
- */
-static void __dma_cache_wback_inv_ioc(phys_addr_t start, unsigned long sz) {}
-static void __dma_cache_inv_ioc(phys_addr_t start, unsigned long sz) {}
-static void __dma_cache_wback_ioc(phys_addr_t start, unsigned long sz) {}
-
 /*
  * Exported DMA API
  */
@@ -1153,6 +1144,19 @@ noinline void __init arc_ioc_setup(void)
 {
 	unsigned int ioc_base, mem_sz;
 
+	/*
+	 * As for today we don't support both IOC and ZONE_HIGHMEM enabled
+	 * simultaneously. This happens because as of today IOC aperture covers
+	 * only ZONE_NORMAL (low mem) and any dma transactions outside this
+	 * region won't be HW coherent.
+	 * If we want to use both IOC and ZONE_HIGHMEM we can use
+	 * bounce_buffer to handle dma transactions to HIGHMEM.
+	 * Also it is possible to modify dma_direct cache ops or increase IOC
+	 * aperture size if we are planning to use HIGHMEM without PAE.
+	 */
+	if (IS_ENABLED(CONFIG_HIGHMEM))
+		panic("IOC and HIGHMEM can't be used simultaneously");
+
 	/* Flush + invalidate + disable L1 dcache */
 	__dc_disable();
 
@@ -1264,11 +1268,7 @@ void __init arc_cache_init_master(void)
 	if (is_isa_arcv2() && ioc_enable)
 		arc_ioc_setup();
 
-	if (is_isa_arcv2() && ioc_enable) {
-		__dma_cache_wback_inv = __dma_cache_wback_inv_ioc;
-		__dma_cache_inv = __dma_cache_inv_ioc;
-		__dma_cache_wback = __dma_cache_wback_ioc;
-	} else if (is_isa_arcv2() && l2_line_sz && slc_enable) {
+	if (is_isa_arcv2() && l2_line_sz && slc_enable) {
 		__dma_cache_wback_inv = __dma_cache_wback_inv_slc;
 		__dma_cache_inv = __dma_cache_inv_slc;
 		__dma_cache_wback = __dma_cache_wback_slc;
@@ -1277,6 +1277,12 @@ void __init arc_cache_init_master(void)
 		__dma_cache_inv = __dma_cache_inv_l1;
 		__dma_cache_wback = __dma_cache_wback_l1;
 	}
+	/*
+	 * In case of IOC (say IOC+SLC case), pointers above could still be set
+	 * but end up not being relevant as the first function in chain is not
+	 * called at all for @dma_direct_ops
+	 *     arch_sync_dma_for_cpu() -> dma_cache_*() -> __dma_cache_*()
+	 */
 }
 
 void __ref arc_cache_init(void)

arch/arc/mm/dma.c

@@ -6,20 +6,17 @@
  * published by the Free Software Foundation.
  */
 
-/*
- * DMA Coherent API Notes
- *
- * I/O is inherently non-coherent on ARC. So a coherent DMA buffer is
- * implemented by accessing it using a kernel virtual address, with
- * Cache bit off in the TLB entry.
- *
- * The default DMA address == Phy address which is 0x8000_0000 based.
- */
-
 #include <linux/dma-noncoherent.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 
+/*
+ * ARCH specific callbacks for generic noncoherent DMA ops (dma/noncoherent.c)
+ *  - hardware IOC not available (or "dma-coherent" not set for device in DT)
+ *  - But still handle both coherent and non-coherent requests from caller
+ *
+ * For DMA coherent hardware (IOC) generic code suffices
+ */
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs)
 {
@@ -27,42 +24,29 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	struct page *page;
 	phys_addr_t paddr;
 	void *kvaddr;
-	int need_coh = 1, need_kvaddr = 0;
-
-	page = alloc_pages(gfp, order);
-	if (!page)
-		return NULL;
+	bool need_coh = !(attrs & DMA_ATTR_NON_CONSISTENT);
 
 	/*
-	 * IOC relies on all data (even coherent DMA data) being in cache
-	 * Thus allocate normal cached memory
-	 *
-	 * The gains with IOC are two pronged:
-	 *   -For streaming data, elides need for cache maintenance, saving
-	 *    cycles in flush code, and bus bandwidth as all the lines of a
-	 *    buffer need to be flushed out to memory
-	 *   -For coherent data, Read/Write to buffers terminate early in cache
-	 *   (vs. always going to memory - thus are faster)
+	 * __GFP_HIGHMEM flag is cleared by upper layer functions
+	 * (in include/linux/dma-mapping.h) so we should never get a
+	 * __GFP_HIGHMEM here.
 	 */
-	if ((is_isa_arcv2() && ioc_enable) ||
-	    (attrs & DMA_ATTR_NON_CONSISTENT))
-		need_coh = 0;
+	BUG_ON(gfp & __GFP_HIGHMEM);
 
-	/*
-	 * - A coherent buffer needs MMU mapping to enforce non-cachability
-	 * - A highmem page needs a virtual handle (hence MMU mapping)
-	 *   independent of cachability
-	 */
-	if (PageHighMem(page) || need_coh)
-		need_kvaddr = 1;
+	page = alloc_pages(gfp, order);
+	if (!page)
+		return NULL;
 
 	/* This is linear addr (0x8000_0000 based) */
 	paddr = page_to_phys(page);
 
 	*dma_handle = paddr;
 
-	/* This is kernel Virtual address (0x7000_0000 based) */
-	if (need_kvaddr) {
+	/*
+	 * A coherent buffer needs MMU mapping to enforce non-cachability.
+	 * kvaddr is kernel Virtual address (0x7000_0000 based).
+	 */
+	if (need_coh) {
 		kvaddr = ioremap_nocache(paddr, size);
 		if (kvaddr == NULL) {
 			__free_pages(page, order);
@@ -93,12 +77,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 {
 	phys_addr_t paddr = dma_handle;
 	struct page *page = virt_to_page(paddr);
-	int is_non_coh = 1;
-
-	is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) ||
-			(is_isa_arcv2() && ioc_enable);
 
-	if (PageHighMem(page) || !is_non_coh)
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT))
 		iounmap((void __force __iomem *)vaddr);
 
 	__free_pages(page, get_order(size));
@@ -185,3 +165,23 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 		break;
 	}
 }
+
+/*
+ * Plug in coherent or noncoherent dma ops
+ */
+void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+			const struct iommu_ops *iommu, bool coherent)
+{
+	/*
+	 * IOC hardware snoops all DMA traffic keeping the caches consistent
+	 * with memory - eliding need for any explicit cache maintenance of
+	 * DMA buffers - so we can use dma_direct cache ops.
+	 */
+	if (is_isa_arcv2() && ioc_enable && coherent) {
+		set_dma_ops(dev, &dma_direct_ops);
+		dev_info(dev, "use dma_direct_ops cache ops\n");
+	} else {
+		set_dma_ops(dev, &dma_noncoherent_ops);
+		dev_info(dev, "use dma_noncoherent_ops cache ops\n");
+	}
+}

arch/arm/include/asm/kvm_host.h

@@ -223,7 +223,6 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 			      struct kvm_vcpu_events *events);
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end);
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);

arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts

@@ -46,6 +46,7 @@
 	pinctrl-0 = <&mmc0_pins>;
 	vmmc-supply = <&reg_cldo1>;
 	cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>;
+	bus-width = <4>;
 	status = "okay";
 };
 
@@ -56,6 +57,7 @@
 	vqmmc-supply = <&reg_bldo2>;
 	non-removable;
 	cap-mmc-hw-reset;
+	bus-width = <8>;
 	status = "okay";
 };
 

arch/arm64/include/asm/kvm_host.h

@@ -61,8 +61,7 @@ struct kvm_arch {
 	u64    vmid_gen;
 	u32    vmid;
 
-	/* 1-level 2nd stage table and lock */
-	spinlock_t pgd_lock;
+	/* 1-level 2nd stage table, protected by kvm->mmu_lock */
 	pgd_t *pgd;
 
 	/* VTTBR value associated with above pgd and vmid */
@@ -357,7 +356,6 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 			      struct kvm_vcpu_events *events);
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end);
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);

arch/arm64/kvm/hyp/switch.c

@@ -98,8 +98,10 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu)
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_EL1_TTA;
 	val &= ~CPACR_EL1_ZEN;
-	if (!update_fp_enabled(vcpu))
+	if (!update_fp_enabled(vcpu)) {
 		val &= ~CPACR_EL1_FPEN;
+		__activate_traps_fpsimd32(vcpu);
+	}
 
 	write_sysreg(val, cpacr_el1);
 
@@ -114,8 +116,10 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 
 	val = CPTR_EL2_DEFAULT;
 	val |= CPTR_EL2_TTA | CPTR_EL2_TZ;
-	if (!update_fp_enabled(vcpu))
+	if (!update_fp_enabled(vcpu)) {
 		val |= CPTR_EL2_TFP;
+		__activate_traps_fpsimd32(vcpu);
+	}
 
 	write_sysreg(val, cptr_el2);
 }
@@ -129,7 +133,6 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
 		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
 
-	__activate_traps_fpsimd32(vcpu);
 	if (has_vhe())
 		activate_traps_vhe(vcpu);
 	else

arch/arm64/mm/mmu.c

@@ -985,8 +985,9 @@ int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr)
 
 	pmd = READ_ONCE(*pmdp);
 
-	/* No-op for empty entry and WARN_ON for valid entry */
-	if (!pmd_present(pmd) || !pmd_table(pmd)) {
+	if (!pmd_present(pmd))
+		return 1;
+	if (!pmd_table(pmd)) {
 		VM_WARN_ON(!pmd_table(pmd));
 		return 1;
 	}
@@ -1007,8 +1008,9 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
 
 	pud = READ_ONCE(*pudp);
 
-	/* No-op for empty entry and WARN_ON for valid entry */
-	if (!pud_present(pud) || !pud_table(pud)) {
+	if (!pud_present(pud))
+		return 1;
+	if (!pud_table(pud)) {
 		VM_WARN_ON(!pud_table(pud));
 		return 1;
 	}

arch/m68k/mm/mcfmmu.c

@@ -172,7 +172,7 @@ void __init cf_bootmem_alloc(void)
 	high_memory = (void *)_ramend;
 
 	/* Reserve kernel text/data/bss */
-	memblock_reserve(memstart, memstart - _rambase);
+	memblock_reserve(_rambase, memstart - _rambase);
 
 	m68k_virt_to_node_shift = fls(_ramend - 1) - 6;
 	module_fixup(NULL, __start_fixup, __stop_fixup);

arch/mips/include/asm/kvm_host.h

@@ -931,7 +931,6 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu,
 						   bool write);
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end);
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);

arch/mips/include/asm/mach-lantiq/xway/xway_dma.h

@@ -40,6 +40,7 @@ struct ltq_dma_channel {
 	int desc;			/* the current descriptor */
 	struct ltq_dma_desc *desc_base; /* the descriptor base */
 	int phys;			/* physical addr */
+	struct device *dev;
 };
 
 enum {

arch/mips/kernel/vdso.c

@@ -13,6 +13,7 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
+#include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -20,6 +21,7 @@
 
 #include <asm/abi.h>
 #include <asm/mips-cps.h>
+#include <asm/page.h>
 #include <asm/vdso.h>
 
 /* Kernel-provided data used by the VDSO. */
@@ -128,12 +130,30 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	vvar_size = gic_size + PAGE_SIZE;
 	size = vvar_size + image->size;
 
+	/*
+	 * Find a region that's large enough for us to perform the
+	 * colour-matching alignment below.
+	 */
+	if (cpu_has_dc_aliases)
+		size += shm_align_mask + 1;
+
 	base = get_unmapped_area(NULL, 0, size, 0, 0);
 	if (IS_ERR_VALUE(base)) {
 		ret = base;
 		goto out;
 	}
 
+	/*
+	 * If we suffer from dcache aliasing, ensure that the VDSO data page
+	 * mapping is coloured the same as the kernel's mapping of that memory.
+	 * This ensures that when the kernel updates the VDSO data userland
+	 * will observe it without requiring cache invalidations.
+	 */
+	if (cpu_has_dc_aliases) {
+		base = __ALIGN_MASK(base, shm_align_mask);
+		base += ((unsigned long)&vdso_data - gic_size) & shm_align_mask;
+	}
+
 	data_addr = base + gic_size;
 	vdso_addr = data_addr + PAGE_SIZE;
 

arch/mips/kvm/mmu.c

@@ -512,16 +512,6 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end,
 	return 1;
 }
 
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
-{
-	unsigned long end = hva + PAGE_SIZE;
-
-	handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL);
-
-	kvm_mips_callbacks->flush_shadow_all(kvm);
-	return 0;
-}
-
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 {
 	handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL);

arch/mips/lantiq/xway/dma.c

@@ -130,7 +130,7 @@ ltq_dma_alloc(struct ltq_dma_channel *ch)
 	unsigned long flags;
 
 	ch->desc = 0;
-	ch->desc_base = dma_zalloc_coherent(NULL,
+	ch->desc_base = dma_zalloc_coherent(ch->dev,
 				LTQ_DESC_NUM * LTQ_DESC_SIZE,
 				&ch->phys, GFP_ATOMIC);
 
@@ -182,7 +182,7 @@ ltq_dma_free(struct ltq_dma_channel *ch)
 	if (!ch->desc_base)
 		return;
 	ltq_dma_close(ch);
-	dma_free_coherent(NULL, LTQ_DESC_NUM * LTQ_DESC_SIZE,
+	dma_free_coherent(ch->dev, LTQ_DESC_NUM * LTQ_DESC_SIZE,
 		ch->desc_base, ch->phys);
 }
 EXPORT_SYMBOL_GPL(ltq_dma_free);

arch/nds32/Kconfig

@@ -40,6 +40,10 @@ config NDS32
 	select NO_IOPORT_MAP
 	select RTC_LIB
 	select THREAD_INFO_IN_TASK
+	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_DYNAMIC_FTRACE
 	help
 	  Andes(nds32) Linux support.
 

arch/nds32/Makefile

@@ -5,6 +5,10 @@ KBUILD_DEFCONFIG := defconfig
 
 comma = ,
 
+ifdef CONFIG_FUNCTION_TRACER
+arch-y += -malways-save-lp -mno-relax
+endif
+
 KBUILD_CFLAGS	+= $(call cc-option, -mno-sched-prolog-epilog)
 KBUILD_CFLAGS	+= -mcmodel=large
 

arch/nds32/include/asm/elf.h

@@ -121,9 +121,9 @@ struct elf32_hdr;
  */
 #define ELF_CLASS	ELFCLASS32
 #ifdef __NDS32_EB__
-#define ELF_DATA	ELFDATA2MSB;
+#define ELF_DATA	ELFDATA2MSB
 #else
-#define ELF_DATA	ELFDATA2LSB;
+#define ELF_DATA	ELFDATA2LSB
 #endif
 #define ELF_ARCH	EM_NDS32
 #define USE_ELF_CORE_DUMP

arch/nds32/include/asm/ftrace.h

@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_NDS32_FTRACE_H
+#define __ASM_NDS32_FTRACE_H
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+#define HAVE_FUNCTION_GRAPH_FP_TEST
+
+#define MCOUNT_ADDR ((unsigned long)(_mcount))
+/* mcount call is composed of three instructions:
+ * sethi + ori + jral
+ */
+#define MCOUNT_INSN_SIZE 12
+
+extern void _mcount(unsigned long parent_ip);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+#define FTRACE_ADDR ((unsigned long)_ftrace_caller)
+
+#ifdef __NDS32_EL__
+#define INSN_NOP		0x09000040
+#define INSN_SIZE(insn)		(((insn & 0x00000080) == 0) ? 4 : 2)
+#define IS_SETHI(insn)		((insn & 0x000000fe) == 0x00000046)
+#define ENDIAN_CONVERT(insn)	be32_to_cpu(insn)
+#else /* __NDS32_EB__ */
+#define INSN_NOP		0x40000009
+#define INSN_SIZE(insn)		(((insn & 0x80000000) == 0) ? 4 : 2)
+#define IS_SETHI(insn)		((insn & 0xfe000000) == 0x46000000)
+#define ENDIAN_CONVERT(insn)	(insn)
+#endif
+
+extern void _ftrace_caller(unsigned long parent_ip);
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+struct dyn_arch_ftrace {
+};
+
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#endif /* __ASM_NDS32_FTRACE_H */

arch/nds32/include/asm/nds32.h

@@ -17,6 +17,7 @@
 #else
 #define FP_OFFSET (-2)
 #endif
+#define LP_OFFSET (-1)
 
 extern void __init early_trap_init(void);
 static inline void GIE_ENABLE(void)

arch/nds32/include/asm/uaccess.h

@@ -38,7 +38,7 @@ struct exception_table_entry {
 extern int fixup_exception(struct pt_regs *regs);
 
 #define KERNEL_DS 	((mm_segment_t) { ~0UL })
-#define USER_DS     	((mm_segment_t) {TASK_SIZE - 1})
+#define USER_DS		((mm_segment_t) {TASK_SIZE - 1})
 
 #define get_ds()	(KERNEL_DS)
 #define get_fs()	(current_thread_info()->addr_limit)
@@ -49,11 +49,11 @@ static inline void set_fs(mm_segment_t fs)
 	current_thread_info()->addr_limit = fs;
 }
 
-#define segment_eq(a, b)    ((a) == (b))
+#define segment_eq(a, b)	((a) == (b))
 
 #define __range_ok(addr, size) (size <= get_fs() && addr <= (get_fs() -size))
 
-#define access_ok(type, addr, size)                 \
+#define access_ok(type, addr, size)	\
 	__range_ok((unsigned long)addr, (unsigned long)size)
 /*
  * Single-value transfer routines.  They automatically use the right
@@ -75,70 +75,73 @@ static inline void set_fs(mm_segment_t fs)
  * versions are void (ie, don't return a value as such).
  */
 
-#define get_user(x,p)							\
-({									\
-	long __e = -EFAULT;						\
-	if(likely(access_ok(VERIFY_READ,  p, sizeof(*p)))) {		\
-		__e = __get_user(x,p);					\
-	} else								\
-		x = 0;							\
-	__e;								\
-})
-#define __get_user(x,ptr)						\
+#define get_user	__get_user					\
+
+#define __get_user(x, ptr)						\
 ({									\
 	long __gu_err = 0;						\
-	__get_user_err((x),(ptr),__gu_err);				\
+	__get_user_check((x), (ptr), __gu_err);				\
 	__gu_err;							\
 })
 
-#define __get_user_error(x,ptr,err)					\
+#define __get_user_error(x, ptr, err)					\
 ({									\
-	__get_user_err((x),(ptr),err);					\
-	(void) 0;							\
+	__get_user_check((x), (ptr), (err));				\
+	(void)0;							\
 })
 
-#define __get_user_err(x,ptr,err)					\
+#define __get_user_check(x, ptr, err)					\
+({									\
+	const __typeof__(*(ptr)) __user *__p = (ptr);			\
+	might_fault();							\
+	if (access_ok(VERIFY_READ, __p, sizeof(*__p))) {		\
+		__get_user_err((x), __p, (err));			\
+	} else {							\
+		(x) = 0; (err) = -EFAULT;				\
+	}								\
+})
+
+#define __get_user_err(x, ptr, err)					\
 do {									\
-	unsigned long __gu_addr = (unsigned long)(ptr);			\
 	unsigned long __gu_val;						\
 	__chk_user_ptr(ptr);						\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
-		__get_user_asm("lbi",__gu_val,__gu_addr,err);		\
+		__get_user_asm("lbi", __gu_val, (ptr), (err));		\
 		break;							\
 	case 2:								\
-		__get_user_asm("lhi",__gu_val,__gu_addr,err);		\
+		__get_user_asm("lhi", __gu_val, (ptr), (err));		\
 		break;							\
 	case 4:								\
-		__get_user_asm("lwi",__gu_val,__gu_addr,err);		\
+		__get_user_asm("lwi", __gu_val, (ptr), (err));		\
 		break;							\
 	case 8:								\
-		__get_user_asm_dword(__gu_val,__gu_addr,err);		\
+		__get_user_asm_dword(__gu_val, (ptr), (err));		\
 		break;							\
 	default:							\
 		BUILD_BUG(); 						\
 		break;							\
 	}								\
-	(x) = (__typeof__(*(ptr)))__gu_val;				\
+	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
 } while (0)
 
-#define __get_user_asm(inst,x,addr,err)					\
-	asm volatile(							\
-	"1:	"inst"	%1,[%2]\n"					\
-	"2:\n"								\
-	"	.section .fixup,\"ax\"\n"				\
-	"	.align	2\n"						\
-	"3:	move %0, %3\n"						\
-	"	move %1, #0\n"						\
-	"	b	2b\n"						\
-	"	.previous\n"						\
-	"	.section __ex_table,\"a\"\n"				\
-	"	.align	3\n"						\
-	"	.long	1b, 3b\n"					\
-	"	.previous"						\
-	: "+r" (err), "=&r" (x)						\
-	: "r" (addr), "i" (-EFAULT)					\
-	: "cc")
+#define __get_user_asm(inst, x, addr, err)				\
+	__asm__ __volatile__ (						\
+		"1:	"inst"	%1,[%2]\n"				\
+		"2:\n"							\
+		"	.section .fixup,\"ax\"\n"			\
+		"	.align	2\n"					\
+		"3:	move %0, %3\n"					\
+		"	move %1, #0\n"					\
+		"	b	2b\n"					\
+		"	.previous\n"					\
+		"	.section __ex_table,\"a\"\n"			\
+		"	.align	3\n"					\
+		"	.long	1b, 3b\n"				\
+		"	.previous"					\
+		: "+r" (err), "=&r" (x)					\
+		: "r" (addr), "i" (-EFAULT)				\
+		: "cc")
 
 #ifdef __NDS32_EB__
 #define __gu_reg_oper0 "%H1"
@@ -149,61 +152,66 @@ do {									\
 #endif
 
 #define __get_user_asm_dword(x, addr, err) 				\
-	asm volatile(			    				\
-	"\n1:\tlwi " __gu_reg_oper0 ",[%2]\n"				\
-	"\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n"				\
-	"3:\n"								\
-	"	.section .fixup,\"ax\"\n"				\
-	"	.align	2\n"						\
-	"4:	move	%0, %3\n"					\
-	"	b	3b\n"						\
-	"	.previous\n"						\
-	"	.section __ex_table,\"a\"\n"				\
-	"	.align	3\n"						\
-	"	.long	1b, 4b\n"					\
-	"	.long	2b, 4b\n"					\
-	"	.previous"						\
-	: "+r"(err), "=&r"(x)                				\
-	: "r"(addr), "i"(-EFAULT) 					\
-	: "cc")
-#define put_user(x,p)							\
-({									\
-	long __e = -EFAULT;						\
-	if(likely(access_ok(VERIFY_WRITE,  p, sizeof(*p)))) {		\
-		__e = __put_user(x,p);					\
-	}								\
-	__e;								\
-})
-#define __put_user(x,ptr)						\
+	__asm__ __volatile__ (						\
+		"\n1:\tlwi " __gu_reg_oper0 ",[%2]\n"			\
+		"\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n"			\
+		"3:\n"							\
+		"	.section .fixup,\"ax\"\n"			\
+		"	.align	2\n"					\
+		"4:	move	%0, %3\n"				\
+		"	b	3b\n"					\
+		"	.previous\n"					\
+		"	.section __ex_table,\"a\"\n"			\
+		"	.align	3\n"					\
+		"	.long	1b, 4b\n"				\
+		"	.long	2b, 4b\n"				\
+		"	.previous"					\
+		: "+r"(err), "=&r"(x)					\
+		: "r"(addr), "i"(-EFAULT)				\
+		: "cc")
+
+#define put_user	__put_user					\
+
+#define __put_user(x, ptr)						\
 ({									\
 	long __pu_err = 0;						\
-	__put_user_err((x),(ptr),__pu_err);				\
+	__put_user_err((x), (ptr), __pu_err);				\
 	__pu_err;							\
 })
 
-#define __put_user_error(x,ptr,err)					\
+#define __put_user_error(x, ptr, err)					\
+({									\
+	__put_user_err((x), (ptr), (err));				\
+	(void)0;							\
+})
+
+#define __put_user_check(x, ptr, err)					\
 ({									\
-	__put_user_err((x),(ptr),err);					\
-	(void) 0;							\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
+	might_fault();							\
+	if (access_ok(VERIFY_WRITE, __p, sizeof(*__p))) {		\
+		__put_user_err((x), __p, (err));			\
+	} else	{							\
+		(err) = -EFAULT;					\
+	}								\
 })
 
-#define __put_user_err(x,ptr,err)					\
+#define __put_user_err(x, ptr, err)					\
 do {									\
-	unsigned long __pu_addr = (unsigned long)(ptr);			\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
-		__put_user_asm("sbi",__pu_val,__pu_addr,err);		\
+		__put_user_asm("sbi", __pu_val, (ptr), (err));		\
 		break;							\
 	case 2: 							\
-		__put_user_asm("shi",__pu_val,__pu_addr,err);		\
+		__put_user_asm("shi", __pu_val, (ptr), (err));		\
 		break;							\
 	case 4: 							\
-		__put_user_asm("swi",__pu_val,__pu_addr,err);		\
+		__put_user_asm("swi", __pu_val, (ptr), (err));		\
 		break;							\
 	case 8:								\
-		__put_user_asm_dword(__pu_val,__pu_addr,err);		\
+		__put_user_asm_dword(__pu_val, (ptr), (err));		\
 		break;							\
 	default:							\
 		BUILD_BUG(); 						\
@@ -211,22 +219,22 @@ do {									\
 	}								\
 } while (0)
 
-#define __put_user_asm(inst,x,addr,err)					\
-	asm volatile(							\
-	"1:	"inst"	%1,[%2]\n"					\
-	"2:\n"								\
-	"	.section .fixup,\"ax\"\n"				\
-	"	.align	2\n"						\
-	"3:	move	%0, %3\n"					\
-	"	b	2b\n"						\
-	"	.previous\n"						\
-	"	.section __ex_table,\"a\"\n"				\
-	"	.align	3\n"						\
-	"	.long	1b, 3b\n"					\
-	"	.previous"						\
-	: "+r" (err)							\
-	: "r" (x), "r" (addr), "i" (-EFAULT)				\
-	: "cc")
+#define __put_user_asm(inst, x, addr, err)				\
+	__asm__ __volatile__ (						\
+		"1:	"inst"	%1,[%2]\n"				\
+		"2:\n"							\
+		"	.section .fixup,\"ax\"\n"			\
+		"	.align	2\n"					\
+		"3:	move	%0, %3\n"				\
+		"	b	2b\n"					\
+		"	.previous\n"					\
+		"	.section __ex_table,\"a\"\n"			\
+		"	.align	3\n"					\
+		"	.long	1b, 3b\n"				\
+		"	.previous"					\
+		: "+r" (err)						\
+		: "r" (x), "r" (addr), "i" (-EFAULT)			\
+		: "cc")
 
 #ifdef __NDS32_EB__
 #define __pu_reg_oper0 "%H2"
@@ -237,23 +245,24 @@ do {									\
 #endif
 
 #define __put_user_asm_dword(x, addr, err) 				\
-	asm volatile(			    				\
-	"\n1:\tswi " __pu_reg_oper0 ",[%1]\n"				\
-	"\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n"				\
-	"3:\n"								\
-	"	.section .fixup,\"ax\"\n"				\
-	"	.align	2\n"						\
-	"4:	move	%0, %3\n"					\
-	"	b	3b\n"						\
-	"	.previous\n"						\
-	"	.section __ex_table,\"a\"\n"				\
-	"	.align	3\n"						\
-	"	.long	1b, 4b\n"					\
-	"	.long	2b, 4b\n"					\
-	"	.previous"						\
-	: "+r"(err)                					\
-	: "r"(addr), "r"(x), "i"(-EFAULT) 				\
-	: "cc")
+	__asm__ __volatile__ (						\
+		"\n1:\tswi " __pu_reg_oper0 ",[%1]\n"			\
+		"\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n"			\
+		"3:\n"							\
+		"	.section .fixup,\"ax\"\n"			\
+		"	.align	2\n"					\
+		"4:	move	%0, %3\n"				\
+		"	b	3b\n"					\
+		"	.previous\n"					\
+		"	.section __ex_table,\"a\"\n"			\
+		"	.align	3\n"					\
+		"	.long	1b, 4b\n"				\
+		"	.long	2b, 4b\n"				\
+		"	.previous"					\
+		: "+r"(err)						\
+		: "r"(addr), "r"(x), "i"(-EFAULT)			\
+		: "cc")
+
 extern unsigned long __arch_clear_user(void __user * addr, unsigned long n);
 extern long strncpy_from_user(char *dest, const char __user * src, long count);
 extern __must_check long strlen_user(const char __user * str);

arch/nds32/kernel/Makefile

@@ -21,3 +21,9 @@ extra-y := head.o vmlinux.lds
 
 
 obj-y				+= vdso/
+
+obj-$(CONFIG_FUNCTION_TRACER)   += ftrace.o
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+endif

arch/nds32/kernel/atl2c.c

@@ -9,7 +9,8 @@
 
 void __iomem *atl2c_base;
 static const struct of_device_id atl2c_ids[] __initconst = {
-	{.compatible = "andestech,atl2c",}
+	{.compatible = "andestech,atl2c",},
+	{}
 };
 
 static int __init atl2c_of_init(void)

arch/nds32/kernel/ex-entry.S

@@ -118,7 +118,7 @@ common_exception_handler:
 	/* interrupt */
 2:
 #ifdef CONFIG_TRACE_IRQFLAGS
-	jal     trace_hardirqs_off
+	jal     __trace_hardirqs_off
 #endif
 	move	$r0, $sp
 	sethi	$lp, hi20(ret_from_intr)

arch/nds32/kernel/ex-exit.S

@@ -138,8 +138,8 @@ no_work_pending:
 #ifdef CONFIG_TRACE_IRQFLAGS
 	lwi	$p0, [$sp+(#IPSW_OFFSET)]
 	andi	$p0, $p0, #0x1
-	la	$r10, trace_hardirqs_off
-	la	$r9, trace_hardirqs_on
+	la	$r10, __trace_hardirqs_off
+	la	$r9, __trace_hardirqs_on
 	cmovz	$r9, $p0, $r10
 	jral	$r9
 #endif

arch/nds32/kernel/ftrace.c

@@ -0,0 +1,309 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/ftrace.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+extern void (*ftrace_trace_function)(unsigned long, unsigned long,
+				     struct ftrace_ops*, struct pt_regs*);
+extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace);
+extern void ftrace_graph_caller(void);
+
+noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip,
+				  struct ftrace_ops *op, struct pt_regs *regs)
+{
+	__asm__ ("");  /* avoid to optimize as pure function */
+}
+
+noinline void _mcount(unsigned long parent_ip)
+{
+	/* save all state by the compiler prologue */
+
+	unsigned long ip = (unsigned long)__builtin_return_address(0);
+
+	if (ftrace_trace_function != ftrace_stub)
+		ftrace_trace_function(ip - MCOUNT_INSN_SIZE, parent_ip,
+				      NULL, NULL);
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	if (ftrace_graph_return != (trace_func_graph_ret_t)ftrace_stub
+	    || ftrace_graph_entry != ftrace_graph_entry_stub)
+		ftrace_graph_caller();
+#endif
+
+	/* restore all state by the compiler epilogue */
+}
+EXPORT_SYMBOL(_mcount);
+
+#else /* CONFIG_DYNAMIC_FTRACE */
+
+noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip,
+				  struct ftrace_ops *op, struct pt_regs *regs)
+{
+	__asm__ ("");  /* avoid to optimize as pure function */
+}
+
+noinline void __naked _mcount(unsigned long parent_ip)
+{
+	__asm__ ("");  /* avoid to optimize as pure function */
+}
+EXPORT_SYMBOL(_mcount);
+
+#define XSTR(s) STR(s)
+#define STR(s) #s
+void _ftrace_caller(unsigned long parent_ip)
+{
+	/* save all state needed by the compiler prologue */
+
+	/*
+	 * prepare arguments for real tracing function
+	 * first  arg : __builtin_return_address(0) - MCOUNT_INSN_SIZE
+	 * second arg : parent_ip
+	 */
+	__asm__ __volatile__ (
+		"move $r1, %0				   \n\t"
+		"addi $r0, %1, #-" XSTR(MCOUNT_INSN_SIZE) "\n\t"
+		:
+		: "r" (parent_ip), "r" (__builtin_return_address(0)));
+
+	/* a placeholder for the call to a real tracing function */
+	__asm__ __volatile__ (
+		"ftrace_call:		\n\t"
+		"nop			\n\t"
+		"nop			\n\t"
+		"nop			\n\t");
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	/* a placeholder for the call to ftrace_graph_caller */
+	__asm__ __volatile__ (
+		"ftrace_graph_call:	\n\t"
+		"nop			\n\t"
+		"nop			\n\t"
+		"nop			\n\t");
+#endif
+	/* restore all state needed by the compiler epilogue */
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+	return 0;
+}
+
+int ftrace_arch_code_modify_prepare(void)
+{
+	set_all_modules_text_rw();
+	return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+	set_all_modules_text_ro();
+	return 0;
+}
+
+static unsigned long gen_sethi_insn(unsigned long addr)
+{
+	unsigned long opcode = 0x46000000;
+	unsigned long imm = addr >> 12;
+	unsigned long rt_num = 0xf << 20;
+
+	return ENDIAN_CONVERT(opcode | rt_num | imm);
+}
+
+static unsigned long gen_ori_insn(unsigned long addr)
+{
+	unsigned long opcode = 0x58000000;
+	unsigned long imm = addr & 0x0000fff;
+	unsigned long rt_num = 0xf << 20;
+	unsigned long ra_num = 0xf << 15;
+
+	return ENDIAN_CONVERT(opcode | rt_num | ra_num | imm);
+}
+
+static unsigned long gen_jral_insn(unsigned long addr)
+{
+	unsigned long opcode = 0x4a000001;
+	unsigned long rt_num = 0x1e << 20;
+	unsigned long rb_num = 0xf << 10;
+
+	return ENDIAN_CONVERT(opcode | rt_num | rb_num);
+}
+
+static void ftrace_gen_call_insn(unsigned long *call_insns,
+				 unsigned long addr)
+{
+	call_insns[0] = gen_sethi_insn(addr); /* sethi $r15, imm20u       */
+	call_insns[1] = gen_ori_insn(addr);   /* ori   $r15, $r15, imm15u */
+	call_insns[2] = gen_jral_insn(addr);  /* jral  $lp,  $r15         */
+}
+
+static int __ftrace_modify_code(unsigned long pc, unsigned long *old_insn,
+				unsigned long *new_insn, bool validate)
+{
+	unsigned long orig_insn[3];
+
+	if (validate) {
+		if (probe_kernel_read(orig_insn, (void *)pc, MCOUNT_INSN_SIZE))
+			return -EFAULT;
+		if (memcmp(orig_insn, old_insn, MCOUNT_INSN_SIZE))
+			return -EINVAL;
+	}
+
+	if (probe_kernel_write((void *)pc, new_insn, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+
+static int ftrace_modify_code(unsigned long pc, unsigned long *old_insn,
+			      unsigned long *new_insn, bool validate)
+{
+	int ret;
+
+	ret = __ftrace_modify_code(pc, old_insn, new_insn, validate);
+	if (ret)
+		return ret;
+
+	flush_icache_range(pc, pc + MCOUNT_INSN_SIZE);
+
+	return ret;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long pc = (unsigned long)&ftrace_call;
+	unsigned long old_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP};
+	unsigned long new_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP};
+
+	if (func != ftrace_stub)
+		ftrace_gen_call_insn(new_insn, (unsigned long)func);
+
+	return ftrace_modify_code(pc, old_insn, new_insn, false);
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long pc = rec->ip;
+	unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP};
+	unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP};
+
+	ftrace_gen_call_insn(call_insn, addr);
+
+	return ftrace_modify_code(pc, nop_insn, call_insn, true);
+}
+
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
+		    unsigned long addr)
+{
+	unsigned long pc = rec->ip;
+	unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP};
+	unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP};
+
+	ftrace_gen_call_insn(call_insn, addr);
+
+	return ftrace_modify_code(pc, call_insn, nop_insn, true);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	struct ftrace_graph_ent trace;
+	unsigned long old;
+	int err;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	old = *parent;
+
+	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace))
+		return;
+
+	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
+				       frame_pointer, NULL);
+
+	if (err == -EBUSY)
+		return;
+
+	*parent = return_hooker;
+}
+
+noinline void ftrace_graph_caller(void)
+{
+	unsigned long *parent_ip =
+		(unsigned long *)(__builtin_frame_address(2) - 4);
+
+	unsigned long selfpc =
+		(unsigned long)(__builtin_return_address(1) - MCOUNT_INSN_SIZE);
+
+	unsigned long frame_pointer =
+		(unsigned long)__builtin_frame_address(3);
+
+	prepare_ftrace_return(parent_ip, selfpc, frame_pointer);
+}
+
+extern unsigned long ftrace_return_to_handler(unsigned long frame_pointer);
+void __naked return_to_handler(void)
+{
+	__asm__ __volatile__ (
+		/* save state needed by the ABI     */
+		"smw.adm $r0,[$sp],$r1,#0x0  \n\t"
+
+		/* get original return address      */
+		"move $r0, $fp               \n\t"
+		"bal ftrace_return_to_handler\n\t"
+		"move $lp, $r0               \n\t"
+
+		/* restore state nedded by the ABI  */
+		"lmw.bim $r0,[$sp],$r1,#0x0  \n\t");
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern unsigned long ftrace_graph_call;
+
+static int ftrace_modify_graph_caller(bool enable)
+{
+	unsigned long pc = (unsigned long)&ftrace_graph_call;
+	unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP};
+	unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP};
+
+	ftrace_gen_call_insn(call_insn, (unsigned long)ftrace_graph_caller);
+
+	if (enable)
+		return ftrace_modify_code(pc, nop_insn, call_insn, true);
+	else
+		return ftrace_modify_code(pc, call_insn, nop_insn, true);
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_graph_caller(false);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+noinline void __trace_hardirqs_off(void)
+{
+	trace_hardirqs_off();
+}
+noinline void __trace_hardirqs_on(void)
+{
+	trace_hardirqs_on();
+}
+#endif /* CONFIG_TRACE_IRQFLAGS */

arch/nds32/kernel/module.c

@@ -40,7 +40,7 @@ void do_reloc16(unsigned int val, unsigned int *loc, unsigned int val_mask,
 
 	tmp2 = tmp & loc_mask;
 	if (partial_in_place) {
-		tmp &= (!loc_mask);
+		tmp &= (~loc_mask);
 		tmp =
 		    tmp2 | ((tmp + ((val & val_mask) >> val_shift)) & val_mask);
 	} else {
@@ -70,7 +70,7 @@ void do_reloc32(unsigned int val, unsigned int *loc, unsigned int val_mask,
 
 	tmp2 = tmp & loc_mask;
 	if (partial_in_place) {
-		tmp &= (!loc_mask);
+		tmp &= (~loc_mask);
 		tmp =
 		    tmp2 | ((tmp + ((val & val_mask) >> val_shift)) & val_mask);
 	} else {

arch/nds32/kernel/stacktrace.c

@@ -4,6 +4,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
+#include <linux/ftrace.h>
 
 void save_stack_trace(struct stack_trace *trace)
 {
@@ -16,6 +17,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	unsigned long *fpn;
 	int skip = trace->skip;
 	int savesched;
+	int graph_idx = 0;
 
 	if (tsk == current) {
 		__asm__ __volatile__("\tori\t%0, $fp, #0\n":"=r"(fpn));
@@ -29,10 +31,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	       && (fpn >= (unsigned long *)TASK_SIZE)) {
 		unsigned long lpp, fpp;
 
-		lpp = fpn[-1];
+		lpp = fpn[LP_OFFSET];
 		fpp = fpn[FP_OFFSET];
 		if (!__kernel_text_address(lpp))
 			break;
+		else
+			lpp = ftrace_graph_ret_addr(tsk, &graph_idx, lpp, NULL);
 
 		if (savesched || !in_sched_functions(lpp)) {
 			if (skip) {

arch/nds32/kernel/traps.c

@@ -8,6 +8,7 @@
 #include <linux/kdebug.h>
 #include <linux/sched/task_stack.h>
 #include <linux/uaccess.h>
+#include <linux/ftrace.h>
 
 #include <asm/proc-fns.h>
 #include <asm/unistd.h>
@@ -94,28 +95,6 @@ static void dump_instr(struct pt_regs *regs)
 	set_fs(fs);
 }
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-#include <linux/ftrace.h>
-static void
-get_real_ret_addr(unsigned long *addr, struct task_struct *tsk, int *graph)
-{
-	if (*addr == (unsigned long)return_to_handler) {
-		int index = tsk->curr_ret_stack;
-
-		if (tsk->ret_stack && index >= *graph) {
-			index -= *graph;
-			*addr = tsk->ret_stack[index].ret;
-			(*graph)++;
-		}
-	}
-}
-#else
-static inline void
-get_real_ret_addr(unsigned long *addr, struct task_struct *tsk, int *graph)
-{
-}
-#endif
-
 #define LOOP_TIMES (100)
 static void __dump(struct task_struct *tsk, unsigned long *base_reg)
 {
@@ -126,7 +105,8 @@ static void __dump(struct task_struct *tsk, unsigned long *base_reg)
 		while (!kstack_end(base_reg)) {
 			ret_addr = *base_reg++;
 			if (__kernel_text_address(ret_addr)) {
-				get_real_ret_addr(&ret_addr, tsk, &graph);
+				ret_addr = ftrace_graph_ret_addr(
+						tsk, &graph, ret_addr, NULL);
 				print_ip_sym(ret_addr);
 			}
 			if (--cnt < 0)
@@ -137,15 +117,12 @@ static void __dump(struct task_struct *tsk, unsigned long *base_reg)
 		       !((unsigned long)base_reg & 0x3) &&
 		       ((unsigned long)base_reg >= TASK_SIZE)) {
 			unsigned long next_fp;
-#if !defined(NDS32_ABI_2)
-			ret_addr = base_reg[0];
-			next_fp = base_reg[1];
-#else
-			ret_addr = base_reg[-1];
+			ret_addr = base_reg[LP_OFFSET];
 			next_fp = base_reg[FP_OFFSET];
-#endif
 			if (__kernel_text_address(ret_addr)) {
-				get_real_ret_addr(&ret_addr, tsk, &graph);
+
+				ret_addr = ftrace_graph_ret_addr(
+						tsk, &graph, ret_addr, NULL);
 				print_ip_sym(ret_addr);
 			}
 			if (--cnt < 0)
@@ -196,11 +173,10 @@ void die(const char *str, struct pt_regs *regs, int err)
 	pr_emerg("CPU: %i\n", smp_processor_id());
 	show_regs(regs);
 	pr_emerg("Process %s (pid: %d, stack limit = 0x%p)\n",
-		 tsk->comm, tsk->pid, task_thread_info(tsk) + 1);
+		 tsk->comm, tsk->pid, end_of_stack(tsk));
 
 	if (!user_mode(regs) || in_interrupt()) {
-		dump_mem("Stack: ", regs->sp,
-			 THREAD_SIZE + (unsigned long)task_thread_info(tsk));
+		dump_mem("Stack: ", regs->sp, (regs->sp + PAGE_SIZE) & PAGE_MASK);
 		dump_instr(regs);
 		dump_stack();
 	}

arch/nds32/kernel/vmlinux.lds.S

@@ -13,14 +13,26 @@ OUTPUT_ARCH(nds32)
 ENTRY(_stext_lma)
 jiffies = jiffies_64;
 
+#if defined(CONFIG_GCOV_KERNEL)
+#define NDS32_EXIT_KEEP(x)	x
+#else
+#define NDS32_EXIT_KEEP(x)
+#endif
+
 SECTIONS
 {
 	_stext_lma = TEXTADDR - LOAD_OFFSET;
 	. = TEXTADDR;
 	__init_begin = .;
 	HEAD_TEXT_SECTION
+	.exit.text : {
+		NDS32_EXIT_KEEP(EXIT_TEXT)
+	}
 	INIT_TEXT_SECTION(PAGE_SIZE)
 	INIT_DATA_SECTION(16)
+	.exit.data : {
+		NDS32_EXIT_KEEP(EXIT_DATA)
+	}
 	PERCPU_SECTION(L1_CACHE_BYTES)
 	__init_end = .;
 

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -358,7 +358,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	unsigned long pp, key;
 	unsigned long v, orig_v, gr;
 	__be64 *hptep;
-	int index;
+	long int index;
 	int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR);
 
 	if (kvm_is_radix(vcpu->kvm))

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -725,10 +725,10 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 					      gpa, shift);
 		kvmppc_radix_tlbie_page(kvm, gpa, shift);
 		if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap) {
-			unsigned long npages = 1;
+			unsigned long psize = PAGE_SIZE;
 			if (shift)
-				npages = 1ul << (shift - PAGE_SHIFT);
-			kvmppc_update_dirty_map(memslot, gfn, npages);
+				psize = 1ul << shift;
+			kvmppc_update_dirty_map(memslot, gfn, psize);
 		}
 	}
 	return 0;				

arch/riscv/kernel/setup.c

@@ -85,15 +85,8 @@ atomic_t hart_lottery;
 #ifdef CONFIG_BLK_DEV_INITRD
 static void __init setup_initrd(void)
 {
-	extern char __initramfs_start[];
-	extern unsigned long __initramfs_size;
 	unsigned long size;
 
-	if (__initramfs_size > 0) {
-		initrd_start = (unsigned long)(&__initramfs_start);
-		initrd_end = initrd_start + __initramfs_size;
-	}
-
 	if (initrd_start >= initrd_end) {
 		printk(KERN_INFO "initrd not found or empty");
 		goto disable;

arch/s390/include/asm/mmu.h

@@ -16,7 +16,13 @@ typedef struct {
 	unsigned long asce;
 	unsigned long asce_limit;
 	unsigned long vdso_base;
-	/* The mmu context allocates 4K page tables. */
+	/*
+	 * The following bitfields need a down_write on the mm
+	 * semaphore when they are written to. As they are only
+	 * written once, they can be read without a lock.
+	 *
+	 * The mmu context allocates 4K page tables.
+	 */
 	unsigned int alloc_pgste:1;
 	/* The mmu context uses extended page tables. */
 	unsigned int has_pgste:1;

arch/s390/kvm/kvm-s390.c

@@ -695,7 +695,9 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 			r = -EINVAL;
 		else {
 			r = 0;
+			down_write(&kvm->mm->mmap_sem);
 			kvm->mm->context.allow_gmap_hpage_1m = 1;
+			up_write(&kvm->mm->mmap_sem);
 			/*
 			 * We might have to create fake 4k page
 			 * tables. To avoid that the hardware works on

arch/s390/kvm/priv.c

@@ -280,9 +280,11 @@ retry:
 			goto retry;
 		}
 	}
-	if (rc)
-		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 	up_read(&current->mm->mmap_sem);
+	if (rc == -EFAULT)
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	if (rc < 0)
+		return rc;
 	vcpu->run->s.regs.gprs[reg1] &= ~0xff;
 	vcpu->run->s.regs.gprs[reg1] |= key;
 	return 0;
@@ -324,9 +326,11 @@ retry:
 			goto retry;
 		}
 	}
-	if (rc < 0)
-		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 	up_read(&current->mm->mmap_sem);
+	if (rc == -EFAULT)
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	if (rc < 0)
+		return rc;
 	kvm_s390_set_psw_cc(vcpu, rc);
 	return 0;
 }
@@ -390,12 +394,12 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 					      FAULT_FLAG_WRITE, &unlocked);
 			rc = !rc ? -EAGAIN : rc;
 		}
+		up_read(&current->mm->mmap_sem);
 		if (rc == -EFAULT)
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
-		up_read(&current->mm->mmap_sem);
-		if (rc >= 0)
-			start += PAGE_SIZE;
+		if (rc < 0)
+			return rc;
+		start += PAGE_SIZE;
 	}
 
 	if (m3 & (SSKE_MC | SSKE_MR)) {
@@ -1002,13 +1006,15 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 						      FAULT_FLAG_WRITE, &unlocked);
 				rc = !rc ? -EAGAIN : rc;
 			}
+			up_read(&current->mm->mmap_sem);
 			if (rc == -EFAULT)
 				return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
-			up_read(&current->mm->mmap_sem);
-			if (rc >= 0)
-				start += PAGE_SIZE;
+			if (rc == -EAGAIN)
+				continue;
+			if (rc < 0)
+				return rc;
 		}
+		start += PAGE_SIZE;
 	}
 	if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
 		if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) {

arch/s390/kvm/vsie.c

@@ -173,7 +173,8 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		return set_validity_icpt(scb_s, 0x0039U);
 
 	/* copy only the wrapping keys */
-	if (read_guest_real(vcpu, crycb_addr + 72, &vsie_page->crycb, 56))
+	if (read_guest_real(vcpu, crycb_addr + 72,
+			    vsie_page->crycb.dea_wrapping_key_mask, 56))
 		return set_validity_icpt(scb_s, 0x0035U);
 
 	scb_s->ecb3 |= ecb3_flags;

arch/x86/include/asm/atomic.h

@@ -80,11 +80,11 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-#define arch_atomic_sub_and_test arch_atomic_sub_and_test
 static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
 }
+#define arch_atomic_sub_and_test arch_atomic_sub_and_test
 
 /**
  * arch_atomic_inc - increment atomic variable
@@ -92,12 +92,12 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
  *
  * Atomically increments @v by 1.
  */
-#define arch_atomic_inc arch_atomic_inc
 static __always_inline void arch_atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
 		     : "+m" (v->counter));
 }
+#define arch_atomic_inc arch_atomic_inc
 
 /**
  * arch_atomic_dec - decrement atomic variable
@@ -105,12 +105,12 @@ static __always_inline void arch_atomic_inc(atomic_t *v)
  *
  * Atomically decrements @v by 1.
  */
-#define arch_atomic_dec arch_atomic_dec
 static __always_inline void arch_atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
 		     : "+m" (v->counter));
 }
+#define arch_atomic_dec arch_atomic_dec
 
 /**
  * arch_atomic_dec_and_test - decrement and test
@@ -120,11 +120,11 @@ static __always_inline void arch_atomic_dec(atomic_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-#define arch_atomic_dec_and_test arch_atomic_dec_and_test
 static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
 }
+#define arch_atomic_dec_and_test arch_atomic_dec_and_test
 
 /**
  * arch_atomic_inc_and_test - increment and test
@@ -134,11 +134,11 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-#define arch_atomic_inc_and_test arch_atomic_inc_and_test
 static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
 }
+#define arch_atomic_inc_and_test arch_atomic_inc_and_test
 
 /**
  * arch_atomic_add_negative - add and test if negative
@@ -149,11 +149,11 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-#define arch_atomic_add_negative arch_atomic_add_negative
 static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
 }
+#define arch_atomic_add_negative arch_atomic_add_negative
 
 /**
  * arch_atomic_add_return - add integer and return

arch/x86/include/asm/atomic64_32.h

@@ -205,12 +205,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
  *
  * Atomically increments @v by 1.
  */
-#define arch_atomic64_inc arch_atomic64_inc
 static inline void arch_atomic64_inc(atomic64_t *v)
 {
 	__alternative_atomic64(inc, inc_return, /* no output */,
 			       "S" (v) : "memory", "eax", "ecx", "edx");
 }
+#define arch_atomic64_inc arch_atomic64_inc
 
 /**
  * arch_atomic64_dec - decrement atomic64 variable
@@ -218,12 +218,12 @@ static inline void arch_atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
-#define arch_atomic64_dec arch_atomic64_dec
 static inline void arch_atomic64_dec(atomic64_t *v)
 {
 	__alternative_atomic64(dec, dec_return, /* no output */,
 			       "S" (v) : "memory", "eax", "ecx", "edx");
 }
+#define arch_atomic64_dec arch_atomic64_dec
 
 /**
  * arch_atomic64_add_unless - add unless the number is a given value
@@ -245,7 +245,6 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a,
 	return (int)a;
 }
 
-#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
 static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
@@ -253,8 +252,8 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 			     "S" (v) : "ecx", "edx", "memory");
 	return r;
 }
+#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
 
-#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
 static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	long long r;
@@ -262,6 +261,7 @@ static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
 			     "S" (v) : "ecx", "memory");
 	return r;
 }
+#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
 
 #undef alternative_atomic64
 #undef __alternative_atomic64

arch/x86/include/asm/atomic64_64.h

@@ -71,11 +71,11 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
 static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
 }
+#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
 
 /**
  * arch_atomic64_inc - increment atomic64 variable
@@ -83,13 +83,13 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
  *
  * Atomically increments @v by 1.
  */
-#define arch_atomic64_inc arch_atomic64_inc
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
 		     : "=m" (v->counter)
 		     : "m" (v->counter));
 }
+#define arch_atomic64_inc arch_atomic64_inc
 
 /**
  * arch_atomic64_dec - decrement atomic64 variable
@@ -97,13 +97,13 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
-#define arch_atomic64_dec arch_atomic64_dec
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
 		     : "=m" (v->counter)
 		     : "m" (v->counter));
 }
+#define arch_atomic64_dec arch_atomic64_dec
 
 /**
  * arch_atomic64_dec_and_test - decrement and test
@@ -113,11 +113,11 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
 static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
 }
+#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
 
 /**
  * arch_atomic64_inc_and_test - increment and test
@@ -127,11 +127,11 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
 static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
 }
+#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
 
 /**
  * arch_atomic64_add_negative - add and test if negative
@@ -142,11 +142,11 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-#define arch_atomic64_add_negative arch_atomic64_add_negative
 static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
 }
+#define arch_atomic64_add_negative arch_atomic64_add_negative
 
 /**
  * arch_atomic64_add_return - add and return

arch/x86/include/asm/kdebug.h

@@ -22,10 +22,20 @@ enum die_val {
 	DIE_NMIUNKNOWN,
 };
 
+enum show_regs_mode {
+	SHOW_REGS_SHORT,
+	/*
+	 * For when userspace crashed, but we don't think it's our fault, and
+	 * therefore don't print kernel registers.
+	 */
+	SHOW_REGS_USER,
+	SHOW_REGS_ALL
+};
+
 extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_stack_regs(struct pt_regs *regs);
-extern void __show_regs(struct pt_regs *regs, int all);
+extern void __show_regs(struct pt_regs *regs, enum show_regs_mode);
 extern void show_iret_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);

arch/x86/include/asm/kvm_host.h

@@ -1237,19 +1237,12 @@ enum emulation_result {
 #define EMULTYPE_NO_DECODE	    (1 << 0)
 #define EMULTYPE_TRAP_UD	    (1 << 1)
 #define EMULTYPE_SKIP		    (1 << 2)
-#define EMULTYPE_RETRY		    (1 << 3)
-#define EMULTYPE_NO_REEXECUTE	    (1 << 4)
-#define EMULTYPE_NO_UD_ON_FAIL	    (1 << 5)
-#define EMULTYPE_VMWARE		    (1 << 6)
-int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
-			    int emulation_type, void *insn, int insn_len);
-
-static inline int emulate_instruction(struct kvm_vcpu *vcpu,
-			int emulation_type)
-{
-	return x86_emulate_instruction(vcpu, 0,
-			emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0);
-}
+#define EMULTYPE_ALLOW_RETRY	    (1 << 3)
+#define EMULTYPE_NO_UD_ON_FAIL	    (1 << 4)
+#define EMULTYPE_VMWARE		    (1 << 5)
+int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type);
+int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
+					void *insn, int insn_len);
 
 void kvm_enable_efer_bits(u64);
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
@@ -1450,7 +1443,6 @@ asmlinkage void kvm_spurious_fault(void);
 	____kvm_handle_fault_on_reboot(insn, "")
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
@@ -1463,7 +1455,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
 
 int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
-    		    unsigned long ipi_bitmap_high, int min,
+		    unsigned long ipi_bitmap_high, u32 min,
 		    unsigned long icr, int op_64_bit);
 
 u64 kvm_get_arch_capabilities(void);

arch/x86/include/asm/pgtable.h

@@ -1195,7 +1195,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 		return xchg(pmdp, pmd);
 	} else {
 		pmd_t old = *pmdp;
-		*pmdp = pmd;
+		WRITE_ONCE(*pmdp, pmd);
 		return old;
 	}
 }

arch/x86/include/asm/pgtable_64.h

@@ -55,15 +55,15 @@ struct mm_struct;
 void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte);
 void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
 
-static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
-				    pte_t *ptep)
+static inline void native_set_pte(pte_t *ptep, pte_t pte)
 {
-	*ptep = native_make_pte(0);
+	WRITE_ONCE(*ptep, pte);
 }
 
-static inline void native_set_pte(pte_t *ptep, pte_t pte)
+static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
+				    pte_t *ptep)
 {
-	*ptep = pte;
+	native_set_pte(ptep, native_make_pte(0));
 }
 
 static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
@@ -73,7 +73,7 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
 
 static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
-	*pmdp = pmd;
+	WRITE_ONCE(*pmdp, pmd);
 }
 
 static inline void native_pmd_clear(pmd_t *pmd)
@@ -109,7 +109,7 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 
 static inline void native_set_pud(pud_t *pudp, pud_t pud)
 {
-	*pudp = pud;
+	WRITE_ONCE(*pudp, pud);
 }
 
 static inline void native_pud_clear(pud_t *pud)
@@ -137,13 +137,13 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 	pgd_t pgd;
 
 	if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
-		*p4dp = p4d;
+		WRITE_ONCE(*p4dp, p4d);
 		return;
 	}
 
 	pgd = native_make_pgd(native_p4d_val(p4d));
 	pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd);
-	*p4dp = native_make_p4d(native_pgd_val(pgd));
+	WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd)));
 }
 
 static inline void native_p4d_clear(p4d_t *p4d)
@@ -153,7 +153,7 @@ static inline void native_p4d_clear(p4d_t *p4d)
 
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
-	*pgdp = pti_set_user_pgtbl(pgdp, pgd);
+	WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd));
 }
 
 static inline void native_pgd_clear(pgd_t *pgd)

arch/x86/kernel/apic/vector.c

@@ -413,7 +413,7 @@ static int activate_managed(struct irq_data *irqd)
 	if (WARN_ON_ONCE(cpumask_empty(vector_searchmask))) {
 		/* Something in the core code broke! Survive gracefully */
 		pr_err("Managed startup for irq %u, but no CPU\n", irqd->irq);
-		return EINVAL;
+		return -EINVAL;
 	}
 
 	ret = assign_managed_vector(irqd, vector_searchmask);

arch/x86/kernel/cpu/microcode/amd.c

@@ -504,6 +504,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
 	struct microcode_amd *mc_amd;
 	struct ucode_cpu_info *uci;
 	struct ucode_patch *p;
+	enum ucode_state ret;
 	u32 rev, dummy;
 
 	BUG_ON(raw_smp_processor_id() != cpu);
@@ -521,9 +522,8 @@ static enum ucode_state apply_microcode_amd(int cpu)
 
 	/* need to apply patch? */
 	if (rev >= mc_amd->hdr.patch_id) {
-		c->microcode = rev;
-		uci->cpu_sig.rev = rev;
-		return UCODE_OK;
+		ret = UCODE_OK;
+		goto out;
 	}
 
 	if (__apply_microcode_amd(mc_amd)) {
@@ -531,13 +531,21 @@ static enum ucode_state apply_microcode_amd(int cpu)
 			cpu, mc_amd->hdr.patch_id);
 		return UCODE_ERROR;
 	}
-	pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
-		mc_amd->hdr.patch_id);
 
-	uci->cpu_sig.rev = mc_amd->hdr.patch_id;
-	c->microcode = mc_amd->hdr.patch_id;
+	rev = mc_amd->hdr.patch_id;
+	ret = UCODE_UPDATED;
+
+	pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev);
 
-	return UCODE_UPDATED;
+out:
+	uci->cpu_sig.rev = rev;
+	c->microcode	 = rev;
+
+	/* Update boot_cpu_data's revision too, if we're on the BSP: */
+	if (c->cpu_index == boot_cpu_data.cpu_index)
+		boot_cpu_data.microcode = rev;
+
+	return ret;
 }
 
 static int install_equiv_cpu_table(const u8 *buf)

arch/x86/kernel/cpu/microcode/intel.c

@@ -795,6 +795,7 @@ static enum ucode_state apply_microcode_intel(int cpu)
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_intel *mc;
+	enum ucode_state ret;
 	static int prev_rev;
 	u32 rev;
 
@@ -817,9 +818,8 @@ static enum ucode_state apply_microcode_intel(int cpu)
 	 */
 	rev = intel_get_microcode_revision();
 	if (rev >= mc->hdr.rev) {
-		uci->cpu_sig.rev = rev;
-		c->microcode = rev;
-		return UCODE_OK;
+		ret = UCODE_OK;
+		goto out;
 	}
 
 	/*
@@ -848,10 +848,17 @@ static enum ucode_state apply_microcode_intel(int cpu)
 		prev_rev = rev;
 	}
 
+	ret = UCODE_UPDATED;
+
+out:
 	uci->cpu_sig.rev = rev;
-	c->microcode = rev;
+	c->microcode	 = rev;
+
+	/* Update boot_cpu_data's revision too, if we're on the BSP: */
+	if (c->cpu_index == boot_cpu_data.cpu_index)
+		boot_cpu_data.microcode = rev;
 
-	return UCODE_UPDATED;
+	return ret;
 }
 
 static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,

arch/x86/kernel/dumpstack.c

@@ -146,7 +146,7 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs,
 	 * they can be printed in the right context.
 	 */
 	if (!partial && on_stack(info, regs, sizeof(*regs))) {
-		__show_regs(regs, 0);
+		__show_regs(regs, SHOW_REGS_SHORT);
 
 	} else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET,
 				       IRET_FRAME_SIZE)) {
@@ -344,7 +344,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 	oops_exit();
 
 	/* Executive summary in case the oops scrolled away */
-	__show_regs(&exec_summary_regs, true);
+	__show_regs(&exec_summary_regs, SHOW_REGS_ALL);
 
 	if (!signr)
 		return;
@@ -407,14 +407,9 @@ void die(const char *str, struct pt_regs *regs, long err)
 
 void show_regs(struct pt_regs *regs)
 {
-	bool all = true;
-
 	show_regs_print_info(KERN_DEFAULT);
 
-	if (IS_ENABLED(CONFIG_X86_32))
-		all = !user_mode(regs);
-
-	__show_regs(regs, all);
+	__show_regs(regs, user_mode(regs) ? SHOW_REGS_USER : SHOW_REGS_ALL);
 
 	/*
 	 * When in-kernel, we also print out the stack at the time of the fault..

arch/x86/kernel/process_32.c

@@ -59,7 +59,7 @@
 #include <asm/intel_rdt_sched.h>
 #include <asm/proto.h>
 
-void __show_regs(struct pt_regs *regs, int all)
+void __show_regs(struct pt_regs *regs, enum show_regs_mode mode)
 {
 	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
 	unsigned long d0, d1, d2, d3, d6, d7;
@@ -85,7 +85,7 @@ void __show_regs(struct pt_regs *regs, int all)
 	printk(KERN_DEFAULT "DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x EFLAGS: %08lx\n",
 	       (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss, regs->flags);
 
-	if (!all)
+	if (mode != SHOW_REGS_ALL)
 		return;
 
 	cr0 = read_cr0();

arch/x86/kernel/process_64.c

@@ -62,7 +62,7 @@
 __visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
 
 /* Prints also some state that isn't saved in the pt_regs */
-void __show_regs(struct pt_regs *regs, int all)
+void __show_regs(struct pt_regs *regs, enum show_regs_mode mode)
 {
 	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
 	unsigned long d0, d1, d2, d3, d6, d7;
@@ -87,9 +87,17 @@ void __show_regs(struct pt_regs *regs, int all)
 	printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
 	       regs->r13, regs->r14, regs->r15);
 
-	if (!all)
+	if (mode == SHOW_REGS_SHORT)
 		return;
 
+	if (mode == SHOW_REGS_USER) {
+		rdmsrl(MSR_FS_BASE, fs);
+		rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
+		printk(KERN_DEFAULT "FS:  %016lx GS:  %016lx\n",
+		       fs, shadowgs);
+		return;
+	}
+
 	asm("movl %%ds,%0" : "=r" (ds));
 	asm("movl %%cs,%0" : "=r" (cs));
 	asm("movl %%es,%0" : "=r" (es));

arch/x86/kernel/tsc.c

@@ -1415,7 +1415,7 @@ static bool __init determine_cpu_tsc_frequencies(bool early)
 
 static unsigned long __init get_loops_per_jiffy(void)
 {
-	unsigned long lpj = tsc_khz * KHZ;
+	u64 lpj = (u64)tsc_khz * KHZ;
 
 	do_div(lpj, HZ);
 	return lpj;

arch/x86/kvm/lapic.c

@@ -548,7 +548,7 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
 }
 
 int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
-    		    unsigned long ipi_bitmap_high, int min,
+		    unsigned long ipi_bitmap_high, u32 min,
 		    unsigned long icr, int op_64_bit)
 {
 	int i;
@@ -571,18 +571,31 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
 	rcu_read_lock();
 	map = rcu_dereference(kvm->arch.apic_map);
 
+	if (min > map->max_apic_id)
+		goto out;
 	/* Bits above cluster_size are masked in the caller.  */
-	for_each_set_bit(i, &ipi_bitmap_low, BITS_PER_LONG) {
-		vcpu = map->phys_map[min + i]->vcpu;
-		count += kvm_apic_set_irq(vcpu, &irq, NULL);
+	for_each_set_bit(i, &ipi_bitmap_low,
+		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
+		if (map->phys_map[min + i]) {
+			vcpu = map->phys_map[min + i]->vcpu;
+			count += kvm_apic_set_irq(vcpu, &irq, NULL);
+		}
 	}
 
 	min += cluster_size;
-	for_each_set_bit(i, &ipi_bitmap_high, BITS_PER_LONG) {
-		vcpu = map->phys_map[min + i]->vcpu;
-		count += kvm_apic_set_irq(vcpu, &irq, NULL);
+
+	if (min > map->max_apic_id)
+		goto out;
+
+	for_each_set_bit(i, &ipi_bitmap_high,
+		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
+		if (map->phys_map[min + i]) {
+			vcpu = map->phys_map[min + i]->vcpu;
+			count += kvm_apic_set_irq(vcpu, &irq, NULL);
+		}
 	}
 
+out:
 	rcu_read_unlock();
 	return count;
 }

arch/x86/kvm/mmu.c

@@ -1853,11 +1853,6 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 	return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
 }
 
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
-{
-	return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp);
-}
-
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 {
 	return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
@@ -5217,7 +5212,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 		       void *insn, int insn_len)
 {
-	int r, emulation_type = EMULTYPE_RETRY;
+	int r, emulation_type = 0;
 	enum emulation_result er;
 	bool direct = vcpu->arch.mmu.direct_map;
 
@@ -5230,10 +5225,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	r = RET_PF_INVALID;
 	if (unlikely(error_code & PFERR_RSVD_MASK)) {
 		r = handle_mmio_page_fault(vcpu, cr2, direct);
-		if (r == RET_PF_EMULATE) {
-			emulation_type = 0;
+		if (r == RET_PF_EMULATE)
 			goto emulate;
-		}
 	}
 
 	if (r == RET_PF_INVALID) {
@@ -5260,8 +5253,19 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 		return 1;
 	}
 
-	if (mmio_info_in_cache(vcpu, cr2, direct))
-		emulation_type = 0;
+	/*
+	 * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still
+	 * optimistically try to just unprotect the page and let the processor
+	 * re-execute the instruction that caused the page fault.  Do not allow
+	 * retrying MMIO emulation, as it's not only pointless but could also
+	 * cause us to enter an infinite loop because the processor will keep
+	 * faulting on the non-existent MMIO address.  Retrying an instruction
+	 * from a nested guest is also pointless and dangerous as we are only
+	 * explicitly shadowing L1's page tables, i.e. unprotecting something
+	 * for L1 isn't going to magically fix whatever issue cause L2 to fail.
+	 */
+	if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu))
+		emulation_type = EMULTYPE_ALLOW_RETRY;
 emulate:
 	/*
 	 * On AMD platforms, under certain conditions insn_len may be zero on #NPF.

arch/x86/kvm/svm.c

@@ -776,7 +776,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	}
 
 	if (!svm->next_rip) {
-		if (emulate_instruction(vcpu, EMULTYPE_SKIP) !=
+		if (kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) !=
 				EMULATE_DONE)
 			printk(KERN_DEBUG "%s: NOP\n", __func__);
 		return;
@@ -2715,7 +2715,7 @@ static int gp_interception(struct vcpu_svm *svm)
 
 	WARN_ON_ONCE(!enable_vmware_backdoor);
 
-	er = emulate_instruction(vcpu,
+	er = kvm_emulate_instruction(vcpu,
 		EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL);
 	if (er == EMULATE_USER_EXIT)
 		return 0;
@@ -2819,7 +2819,7 @@ static int io_interception(struct vcpu_svm *svm)
 	string = (io_info & SVM_IOIO_STR_MASK) != 0;
 	in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
 	if (string)
-		return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+		return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
 
 	port = io_info >> 16;
 	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
@@ -3861,7 +3861,7 @@ static int iret_interception(struct vcpu_svm *svm)
 static int invlpg_interception(struct vcpu_svm *svm)
 {
 	if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
-		return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
+		return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
 
 	kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1);
 	return kvm_skip_emulated_instruction(&svm->vcpu);
@@ -3869,13 +3869,13 @@ static int invlpg_interception(struct vcpu_svm *svm)
 
 static int emulate_on_interception(struct vcpu_svm *svm)
 {
-	return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
+	return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
 }
 
 static int rsm_interception(struct vcpu_svm *svm)
 {
-	return x86_emulate_instruction(&svm->vcpu, 0, 0,
-				       rsm_ins_bytes, 2) == EMULATE_DONE;
+	return kvm_emulate_instruction_from_buffer(&svm->vcpu,
+					rsm_ins_bytes, 2) == EMULATE_DONE;
 }
 
 static int rdpmc_interception(struct vcpu_svm *svm)
@@ -4700,7 +4700,7 @@ static int avic_unaccelerated_access_interception(struct vcpu_svm *svm)
 		ret = avic_unaccel_trap_write(svm);
 	} else {
 		/* Handling Fault */
-		ret = (emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE);
+		ret = (kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE);
 	}
 
 	return ret;
@@ -6747,7 +6747,7 @@ e_free:
 static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
 {
 	unsigned long vaddr, vaddr_end, next_vaddr;
-	unsigned long dst_vaddr, dst_vaddr_end;
+	unsigned long dst_vaddr;
 	struct page **src_p, **dst_p;
 	struct kvm_sev_dbg debug;
 	unsigned long n;
@@ -6763,7 +6763,6 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
 	size = debug.len;
 	vaddr_end = vaddr + size;
 	dst_vaddr = debug.dst_uaddr;
-	dst_vaddr_end = dst_vaddr + size;
 
 	for (; vaddr < vaddr_end; vaddr = next_vaddr) {
 		int len, s_off, d_off;

arch/x86/kvm/vmx.c

@@ -6983,7 +6983,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 	 * Cause the #SS fault with 0 error code in VM86 mode.
 	 */
 	if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) {
-		if (emulate_instruction(vcpu, 0) == EMULATE_DONE) {
+		if (kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE) {
 			if (vcpu->arch.halt_request) {
 				vcpu->arch.halt_request = 0;
 				return kvm_vcpu_halt(vcpu);
@@ -7054,7 +7054,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 
 	if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) {
 		WARN_ON_ONCE(!enable_vmware_backdoor);
-		er = emulate_instruction(vcpu,
+		er = kvm_emulate_instruction(vcpu,
 			EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL);
 		if (er == EMULATE_USER_EXIT)
 			return 0;
@@ -7157,7 +7157,7 @@ static int handle_io(struct kvm_vcpu *vcpu)
 	++vcpu->stat.io_exits;
 
 	if (string)
-		return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+		return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
 
 	port = exit_qualification >> 16;
 	size = (exit_qualification & 7) + 1;
@@ -7231,7 +7231,7 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val)
 static int handle_desc(struct kvm_vcpu *vcpu)
 {
 	WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP));
-	return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+	return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
 }
 
 static int handle_cr(struct kvm_vcpu *vcpu)
@@ -7480,7 +7480,7 @@ static int handle_vmcall(struct kvm_vcpu *vcpu)
 
 static int handle_invd(struct kvm_vcpu *vcpu)
 {
-	return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+	return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
 }
 
 static int handle_invlpg(struct kvm_vcpu *vcpu)
@@ -7547,7 +7547,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu)
 			return kvm_skip_emulated_instruction(vcpu);
 		}
 	}
-	return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+	return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE;
 }
 
 static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu)
@@ -7704,8 +7704,8 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 		if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
 			return kvm_skip_emulated_instruction(vcpu);
 		else
-			return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP,
-						       NULL, 0) == EMULATE_DONE;
+			return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) ==
+								EMULATE_DONE;
 	}
 
 	return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
@@ -7748,7 +7748,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		if (kvm_test_request(KVM_REQ_EVENT, vcpu))
 			return 1;
 
-		err = emulate_instruction(vcpu, 0);
+		err = kvm_emulate_instruction(vcpu, 0);
 
 		if (err == EMULATE_USER_EXIT) {
 			++vcpu->stat.mmio_exits;
@@ -12537,8 +12537,11 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	bool from_vmentry = !!exit_qual;
 	u32 dummy_exit_qual;
+	u32 vmcs01_cpu_exec_ctrl;
 	int r = 0;
 
+	vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+
 	enter_guest_mode(vcpu);
 
 	if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
@@ -12574,6 +12577,25 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
 		kvm_make_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
 	}
 
+	/*
+	 * If L1 had a pending IRQ/NMI until it executed
+	 * VMLAUNCH/VMRESUME which wasn't delivered because it was
+	 * disallowed (e.g. interrupts disabled), L0 needs to
+	 * evaluate if this pending event should cause an exit from L2
+	 * to L1 or delivered directly to L2 (e.g. In case L1 don't
+	 * intercept EXTERNAL_INTERRUPT).
+	 *
+	 * Usually this would be handled by L0 requesting a
+	 * IRQ/NMI window by setting VMCS accordingly. However,
+	 * this setting was done on VMCS01 and now VMCS02 is active
+	 * instead. Thus, we force L0 to perform pending event
+	 * evaluation by requesting a KVM_REQ_EVENT.
+	 */
+	if (vmcs01_cpu_exec_ctrl &
+		(CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING)) {
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+	}
+
 	/*
 	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
 	 * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet
@@ -13988,9 +14010,6 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	    check_vmentry_postreqs(vcpu, vmcs12, &exit_qual))
 		return -EINVAL;
 
-	if (kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING)
-		vmx->nested.nested_run_pending = 1;
-
 	vmx->nested.dirty_vmcs12 = true;
 	ret = enter_vmx_non_root_mode(vcpu, NULL);
 	if (ret)

arch/x86/kvm/x86.c

@@ -4987,7 +4987,7 @@ int handle_ud(struct kvm_vcpu *vcpu)
 		emul_type = 0;
 	}
 
-	er = emulate_instruction(vcpu, emul_type);
+	er = kvm_emulate_instruction(vcpu, emul_type);
 	if (er == EMULATE_USER_EXIT)
 		return 0;
 	if (er != EMULATE_DONE)
@@ -5870,7 +5870,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
 	gpa_t gpa = cr2;
 	kvm_pfn_t pfn;
 
-	if (emulation_type & EMULTYPE_NO_REEXECUTE)
+	if (!(emulation_type & EMULTYPE_ALLOW_RETRY))
+		return false;
+
+	if (WARN_ON_ONCE(is_guest_mode(vcpu)))
 		return false;
 
 	if (!vcpu->arch.mmu.direct_map) {
@@ -5958,7 +5961,10 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 	 */
 	vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0;
 
-	if (!(emulation_type & EMULTYPE_RETRY))
+	if (!(emulation_type & EMULTYPE_ALLOW_RETRY))
+		return false;
+
+	if (WARN_ON_ONCE(is_guest_mode(vcpu)))
 		return false;
 
 	if (x86_page_table_writing_insn(ctxt))
@@ -6276,7 +6282,19 @@ restart:
 
 	return r;
 }
-EXPORT_SYMBOL_GPL(x86_emulate_instruction);
+
+int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type)
+{
+	return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_instruction);
+
+int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
+					void *insn, int insn_len)
+{
+	return x86_emulate_instruction(vcpu, 0, 0, insn, insn_len);
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
 
 static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
 			    unsigned short port)
@@ -7734,7 +7752,7 @@ static inline int complete_emulated_io(struct kvm_vcpu *vcpu)
 {
 	int r;
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-	r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
+	r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	if (r != EMULATE_DONE)
 		return 0;

arch/x86/kvm/x86.h

@@ -274,6 +274,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
 bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
 					  int page_num);
 bool kvm_vector_hashing_enabled(void);
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
+			    int emulation_type, void *insn, int insn_len);
 
 #define KVM_SUPPORTED_XCR0     (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
 				| XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \

arch/x86/mm/pgtable.c

@@ -269,7 +269,7 @@ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp)
 	if (pgd_val(pgd) != 0) {
 		pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
 
-		*pgdp = native_make_pgd(0);
+		pgd_clear(pgdp);
 
 		paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
 		pmd_free(mm, pmd);
@@ -494,7 +494,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	int changed = !pte_same(*ptep, entry);
 
 	if (changed && dirty)
-		*ptep = entry;
+		set_pte(ptep, entry);
 
 	return changed;
 }
@@ -509,7 +509,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma,
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 
 	if (changed && dirty) {
-		*pmdp = entry;
+		set_pmd(pmdp, entry);
 		/*
 		 * We had a write-protection fault here and changed the pmd
 		 * to to more permissive. No need to flush the TLB for that,
@@ -529,7 +529,7 @@ int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 	VM_BUG_ON(address & ~HPAGE_PUD_MASK);
 
 	if (changed && dirty) {
-		*pudp = entry;
+		set_pud(pudp, entry);
 		/*
 		 * We had a write-protection fault here and changed the pud
 		 * to to more permissive. No need to flush the TLB for that,

block/bfq-cgroup.c

@@ -275,9 +275,9 @@ static void bfqg_and_blkg_get(struct bfq_group *bfqg)
 
 void bfqg_and_blkg_put(struct bfq_group *bfqg)
 {
-	bfqg_put(bfqg);
-
 	blkg_put(bfqg_to_blkg(bfqg));
+
+	bfqg_put(bfqg);
 }
 
 /* @stats = 0 */

block/bio.c

@@ -2015,7 +2015,8 @@ int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
 {
 	if (unlikely(bio->bi_blkg))
 		return -EBUSY;
-	blkg_get(blkg);
+	if (!blkg_try_get(blkg))
+		return -ENODEV;
 	bio->bi_blkg = blkg;
 	return 0;
 }

block/blk-cgroup.c

@@ -310,28 +310,11 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 	}
 }
 
-static void blkg_pd_offline(struct blkcg_gq *blkg)
-{
-	int i;
-
-	lockdep_assert_held(blkg->q->queue_lock);
-	lockdep_assert_held(&blkg->blkcg->lock);
-
-	for (i = 0; i < BLKCG_MAX_POLS; i++) {
-		struct blkcg_policy *pol = blkcg_policy[i];
-
-		if (blkg->pd[i] && !blkg->pd[i]->offline &&
-		    pol->pd_offline_fn) {
-			pol->pd_offline_fn(blkg->pd[i]);
-			blkg->pd[i]->offline = true;
-		}
-	}
-}
-
 static void blkg_destroy(struct blkcg_gq *blkg)
 {
 	struct blkcg *blkcg = blkg->blkcg;
 	struct blkcg_gq *parent = blkg->parent;
+	int i;
 
 	lockdep_assert_held(blkg->q->queue_lock);
 	lockdep_assert_held(&blkcg->lock);
@@ -340,6 +323,13 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 	WARN_ON_ONCE(list_empty(&blkg->q_node));
 	WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node));
 
+	for (i = 0; i < BLKCG_MAX_POLS; i++) {
+		struct blkcg_policy *pol = blkcg_policy[i];
+
+		if (blkg->pd[i] && pol->pd_offline_fn)
+			pol->pd_offline_fn(blkg->pd[i]);
+	}
+
 	if (parent) {
 		blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes);
 		blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios);
@@ -382,7 +372,6 @@ static void blkg_destroy_all(struct request_queue *q)
 		struct blkcg *blkcg = blkg->blkcg;
 
 		spin_lock(&blkcg->lock);
-		blkg_pd_offline(blkg);
 		blkg_destroy(blkg);
 		spin_unlock(&blkcg->lock);
 	}
@@ -1053,59 +1042,64 @@ static struct cftype blkcg_legacy_files[] = {
 	{ }	/* terminate */
 };
 
+/*
+ * blkcg destruction is a three-stage process.
+ *
+ * 1. Destruction starts.  The blkcg_css_offline() callback is invoked
+ *    which offlines writeback.  Here we tie the next stage of blkg destruction
+ *    to the completion of writeback associated with the blkcg.  This lets us
+ *    avoid punting potentially large amounts of outstanding writeback to root
+ *    while maintaining any ongoing policies.  The next stage is triggered when
+ *    the nr_cgwbs count goes to zero.
+ *
+ * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called
+ *    and handles the destruction of blkgs.  Here the css reference held by
+ *    the blkg is put back eventually allowing blkcg_css_free() to be called.
+ *    This work may occur in cgwb_release_workfn() on the cgwb_release
+ *    workqueue.  Any submitted ios that fail to get the blkg ref will be
+ *    punted to the root_blkg.
+ *
+ * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called.
+ *    This finally frees the blkcg.
+ */
+
 /**
  * blkcg_css_offline - cgroup css_offline callback
  * @css: css of interest
  *
- * This function is called when @css is about to go away and responsible
- * for offlining all blkgs pd and killing all wbs associated with @css.
- * blkgs pd offline should be done while holding both q and blkcg locks.
- * As blkcg lock is nested inside q lock, this function performs reverse
- * double lock dancing.
- *
- * This is the blkcg counterpart of ioc_release_fn().
+ * This function is called when @css is about to go away.  Here the cgwbs are
+ * offlined first and only once writeback associated with the blkcg has
+ * finished do we start step 2 (see above).
  */
 static void blkcg_css_offline(struct cgroup_subsys_state *css)
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
-	struct blkcg_gq *blkg;
-
-	spin_lock_irq(&blkcg->lock);
-
-	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
-		struct request_queue *q = blkg->q;
-
-		if (spin_trylock(q->queue_lock)) {
-			blkg_pd_offline(blkg);
-			spin_unlock(q->queue_lock);
-		} else {
-			spin_unlock_irq(&blkcg->lock);
-			cpu_relax();
-			spin_lock_irq(&blkcg->lock);
-		}
-	}
-
-	spin_unlock_irq(&blkcg->lock);
 
+	/* this prevents anyone from attaching or migrating to this blkcg */
 	wb_blkcg_offline(blkcg);
+
+	/* put the base cgwb reference allowing step 2 to be triggered */
+	blkcg_cgwb_put(blkcg);
 }
 
 /**
- * blkcg_destroy_all_blkgs - destroy all blkgs associated with a blkcg
+ * blkcg_destroy_blkgs - responsible for shooting down blkgs
  * @blkcg: blkcg of interest
  *
- * This function is called when blkcg css is about to free and responsible for
- * destroying all blkgs associated with @blkcg.
- * blkgs should be removed while holding both q and blkcg locks. As blkcg lock
+ * blkgs should be removed while holding both q and blkcg locks.  As blkcg lock
  * is nested inside q lock, this function performs reverse double lock dancing.
+ * Destroying the blkgs releases the reference held on the blkcg's css allowing
+ * blkcg_css_free to eventually be called.
+ *
+ * This is the blkcg counterpart of ioc_release_fn().
  */
-static void blkcg_destroy_all_blkgs(struct blkcg *blkcg)
+void blkcg_destroy_blkgs(struct blkcg *blkcg)
 {
 	spin_lock_irq(&blkcg->lock);
+
 	while (!hlist_empty(&blkcg->blkg_list)) {
 		struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first,
-						    struct blkcg_gq,
-						    blkcg_node);
+						struct blkcg_gq, blkcg_node);
 		struct request_queue *q = blkg->q;
 
 		if (spin_trylock(q->queue_lock)) {
@@ -1117,6 +1111,7 @@ static void blkcg_destroy_all_blkgs(struct blkcg *blkcg)
 			spin_lock_irq(&blkcg->lock);
 		}
 	}
+
 	spin_unlock_irq(&blkcg->lock);
 }
 
@@ -1125,8 +1120,6 @@ static void blkcg_css_free(struct cgroup_subsys_state *css)
 	struct blkcg *blkcg = css_to_blkcg(css);
 	int i;
 
-	blkcg_destroy_all_blkgs(blkcg);
-
 	mutex_lock(&blkcg_pol_mutex);
 
 	list_del(&blkcg->all_blkcgs_node);
@@ -1189,6 +1182,7 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 	INIT_HLIST_HEAD(&blkcg->blkg_list);
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&blkcg->cgwb_list);
+	refcount_set(&blkcg->cgwb_refcnt, 1);
 #endif
 	list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs);
 
@@ -1480,11 +1474,8 @@ void blkcg_deactivate_policy(struct request_queue *q,
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
 		if (blkg->pd[pol->plid]) {
-			if (!blkg->pd[pol->plid]->offline &&
-			    pol->pd_offline_fn) {
+			if (pol->pd_offline_fn)
 				pol->pd_offline_fn(blkg->pd[pol->plid]);
-				blkg->pd[pol->plid]->offline = true;
-			}
 			pol->pd_free_fn(blkg->pd[pol->plid]);
 			blkg->pd[pol->plid] = NULL;
 		}

block/blk-core.c

@@ -2163,9 +2163,12 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
 {
 	const int op = bio_op(bio);
 
-	if (part->policy && (op_is_write(op) && !op_is_flush(op))) {
+	if (part->policy && op_is_write(op)) {
 		char b[BDEVNAME_SIZE];
 
+		if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
+			return false;
+
 		WARN_ONCE(1,
 		       "generic_make_request: Trying to write "
 			"to read-only block-device %s (partno %d)\n",

block/blk-throttle.c

@@ -2129,8 +2129,9 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td)
 static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio)
 {
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	if (bio->bi_css)
-		bio_associate_blkg(bio, tg_to_blkg(tg));
+	/* fallback to root_blkg if we fail to get a blkg ref */
+	if (bio->bi_css && (bio_associate_blkg(bio, tg_to_blkg(tg)) == -ENODEV))
+		bio_associate_blkg(bio, bio->bi_disk->queue->root_blkg);
 	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
 #endif
 }

drivers/acpi/acpi_lpss.c

@@ -879,7 +879,7 @@ static void acpi_lpss_dismiss(struct device *dev)
 #define LPSS_GPIODEF0_DMA_LLP		BIT(13)
 
 static DEFINE_MUTEX(lpss_iosf_mutex);
-static bool lpss_iosf_d3_entered;
+static bool lpss_iosf_d3_entered = true;
 
 static void lpss_iosf_enter_d3_state(void)
 {

drivers/acpi/bus.c

@@ -35,11 +35,11 @@
 #include <linux/delay.h>
 #ifdef CONFIG_X86
 #include <asm/mpspec.h>
+#include <linux/dmi.h>
 #endif
 #include <linux/acpi_iort.h>
 #include <linux/pci.h>
 #include <acpi/apei.h>
-#include <linux/dmi.h>
 #include <linux/suspend.h>
 
 #include "internal.h"
@@ -82,10 +82,6 @@ static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
 	},
 	{}
 };
-#else
-static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
-	{}
-};
 #endif
 
 /* --------------------------------------------------------------------------
@@ -1033,11 +1029,16 @@ void __init acpi_early_init(void)
 
 	acpi_permanent_mmap = true;
 
+#ifdef CONFIG_X86
 	/*
 	 * If the machine falls into the DMI check table,
-	 * DSDT will be copied to memory
+	 * DSDT will be copied to memory.
+	 * Note that calling dmi_check_system() here on other architectures
+	 * would not be OK because only x86 initializes dmi early enough.
+	 * Thankfully only x86 systems need such quirks for now.
 	 */
 	dmi_check_system(dsdt_dmi_table);
+#endif
 
 	status = acpi_reallocate_root_table();
 	if (ACPI_FAILURE(status)) {

drivers/ata/libata-core.c

@@ -7394,4 +7394,4 @@ EXPORT_SYMBOL_GPL(ata_cable_unknown);
 EXPORT_SYMBOL_GPL(ata_cable_ignore);
 EXPORT_SYMBOL_GPL(ata_cable_sata);
 EXPORT_SYMBOL_GPL(ata_host_get);
-EXPORT_SYMBOL_GPL(ata_host_put);
+EXPORT_SYMBOL_GPL(ata_host_put);

drivers/base/memory.c

@@ -416,26 +416,24 @@ static ssize_t show_valid_zones(struct device *dev,
 	struct zone *default_zone;
 	int nid;
 
-	/*
-	 * The block contains more than one zone can not be offlined.
-	 * This can happen e.g. for ZONE_DMA and ZONE_DMA32
-	 */
-	if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, &valid_start_pfn, &valid_end_pfn))
-		return sprintf(buf, "none\n");
-
-	start_pfn = valid_start_pfn;
-	nr_pages = valid_end_pfn - start_pfn;
-
 	/*
 	 * Check the existing zone. Make sure that we do that only on the
 	 * online nodes otherwise the page_zone is not reliable
 	 */
 	if (mem->state == MEM_ONLINE) {
+		/*
+		 * The block contains more than one zone can not be offlined.
+		 * This can happen e.g. for ZONE_DMA and ZONE_DMA32
+		 */
+		if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages,
+					  &valid_start_pfn, &valid_end_pfn))
+			return sprintf(buf, "none\n");
+		start_pfn = valid_start_pfn;
 		strcat(buf, page_zone(pfn_to_page(start_pfn))->name);
 		goto out;
 	}
 
-	nid = pfn_to_nid(start_pfn);
+	nid = mem->nid;
 	default_zone = zone_for_pfn_range(MMOP_ONLINE_KEEP, nid, start_pfn, nr_pages);
 	strcat(buf, default_zone->name);
 

drivers/block/nbd.c

@@ -1239,6 +1239,9 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 	case NBD_SET_SOCK:
 		return nbd_add_socket(nbd, arg, false);
 	case NBD_SET_BLKSIZE:
+		if (!arg || !is_power_of_2(arg) || arg < 512 ||
+		    arg > PAGE_SIZE)
+			return -EINVAL;
 		nbd_size_set(nbd, arg,
 			     div_s64(config->bytesize, arg));
 		return 0;

drivers/block/rbd.c

@@ -4207,11 +4207,13 @@ static ssize_t rbd_parent_show(struct device *dev,
 
 		count += sprintf(&buf[count], "%s"
 			    "pool_id %llu\npool_name %s\n"
+			    "pool_ns %s\n"
 			    "image_id %s\nimage_name %s\n"
 			    "snap_id %llu\nsnap_name %s\n"
 			    "overlap %llu\n",
 			    !count ? "" : "\n", /* first? */
 			    spec->pool_id, spec->pool_name,
+			    spec->pool_ns ?: "",
 			    spec->image_id, spec->image_name ?: "(unknown)",
 			    spec->snap_id, spec->snap_name,
 			    rbd_dev->parent_overlap);
@@ -4584,47 +4586,177 @@ static int rbd_dev_v2_features(struct rbd_device *rbd_dev)
 						&rbd_dev->header.features);
 }
 
+struct parent_image_info {
+	u64		pool_id;
+	const char	*pool_ns;
+	const char	*image_id;
+	u64		snap_id;
+
+	bool		has_overlap;
+	u64		overlap;
+};
+
+/*
+ * The caller is responsible for @pii.
+ */
+static int decode_parent_image_spec(void **p, void *end,
+				    struct parent_image_info *pii)
+{
+	u8 struct_v;
+	u32 struct_len;
+	int ret;
+
+	ret = ceph_start_decoding(p, end, 1, "ParentImageSpec",
+				  &struct_v, &struct_len);
+	if (ret)
+		return ret;
+
+	ceph_decode_64_safe(p, end, pii->pool_id, e_inval);
+	pii->pool_ns = ceph_extract_encoded_string(p, end, NULL, GFP_KERNEL);
+	if (IS_ERR(pii->pool_ns)) {
+		ret = PTR_ERR(pii->pool_ns);
+		pii->pool_ns = NULL;
+		return ret;
+	}
+	pii->image_id = ceph_extract_encoded_string(p, end, NULL, GFP_KERNEL);
+	if (IS_ERR(pii->image_id)) {
+		ret = PTR_ERR(pii->image_id);
+		pii->image_id = NULL;
+		return ret;
+	}
+	ceph_decode_64_safe(p, end, pii->snap_id, e_inval);
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int __get_parent_info(struct rbd_device *rbd_dev,
+			     struct page *req_page,
+			     struct page *reply_page,
+			     struct parent_image_info *pii)
+{
+	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
+	size_t reply_len = PAGE_SIZE;
+	void *p, *end;
+	int ret;
+
+	ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc,
+			     "rbd", "parent_get", CEPH_OSD_FLAG_READ,
+			     req_page, sizeof(u64), reply_page, &reply_len);
+	if (ret)
+		return ret == -EOPNOTSUPP ? 1 : ret;
+
+	p = page_address(reply_page);
+	end = p + reply_len;
+	ret = decode_parent_image_spec(&p, end, pii);
+	if (ret)
+		return ret;
+
+	ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc,
+			     "rbd", "parent_overlap_get", CEPH_OSD_FLAG_READ,
+			     req_page, sizeof(u64), reply_page, &reply_len);
+	if (ret)
+		return ret;
+
+	p = page_address(reply_page);
+	end = p + reply_len;
+	ceph_decode_8_safe(&p, end, pii->has_overlap, e_inval);
+	if (pii->has_overlap)
+		ceph_decode_64_safe(&p, end, pii->overlap, e_inval);
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+/*
+ * The caller is responsible for @pii.
+ */
+static int __get_parent_info_legacy(struct rbd_device *rbd_dev,
+				    struct page *req_page,
+				    struct page *reply_page,
+				    struct parent_image_info *pii)
+{
+	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
+	size_t reply_len = PAGE_SIZE;
+	void *p, *end;
+	int ret;
+
+	ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc,
+			     "rbd", "get_parent", CEPH_OSD_FLAG_READ,
+			     req_page, sizeof(u64), reply_page, &reply_len);
+	if (ret)
+		return ret;
+
+	p = page_address(reply_page);
+	end = p + reply_len;
+	ceph_decode_64_safe(&p, end, pii->pool_id, e_inval);
+	pii->image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL);
+	if (IS_ERR(pii->image_id)) {
+		ret = PTR_ERR(pii->image_id);
+		pii->image_id = NULL;
+		return ret;
+	}
+	ceph_decode_64_safe(&p, end, pii->snap_id, e_inval);
+	pii->has_overlap = true;
+	ceph_decode_64_safe(&p, end, pii->overlap, e_inval);
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
+static int get_parent_info(struct rbd_device *rbd_dev,
+			   struct parent_image_info *pii)
+{
+	struct page *req_page, *reply_page;
+	void *p;
+	int ret;
+
+	req_page = alloc_page(GFP_KERNEL);
+	if (!req_page)
+		return -ENOMEM;
+
+	reply_page = alloc_page(GFP_KERNEL);
+	if (!reply_page) {
+		__free_page(req_page);
+		return -ENOMEM;
+	}
+
+	p = page_address(req_page);
+	ceph_encode_64(&p, rbd_dev->spec->snap_id);
+	ret = __get_parent_info(rbd_dev, req_page, reply_page, pii);
+	if (ret > 0)
+		ret = __get_parent_info_legacy(rbd_dev, req_page, reply_page,
+					       pii);
+
+	__free_page(req_page);
+	__free_page(reply_page);
+	return ret;
+}
+
 static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 {
 	struct rbd_spec *parent_spec;
-	size_t size;
-	void *reply_buf = NULL;
-	__le64 snapid;
-	void *p;
-	void *end;
-	u64 pool_id;
-	char *image_id;
-	u64 snap_id;
-	u64 overlap;
+	struct parent_image_info pii = { 0 };
 	int ret;
 
 	parent_spec = rbd_spec_alloc();
 	if (!parent_spec)
 		return -ENOMEM;
 
-	size = sizeof (__le64) +				/* pool_id */
-		sizeof (__le32) + RBD_IMAGE_ID_LEN_MAX +	/* image_id */
-		sizeof (__le64) +				/* snap_id */
-		sizeof (__le64);				/* overlap */
-	reply_buf = kmalloc(size, GFP_KERNEL);
-	if (!reply_buf) {
-		ret = -ENOMEM;
+	ret = get_parent_info(rbd_dev, &pii);
+	if (ret)
 		goto out_err;
-	}
 
-	snapid = cpu_to_le64(rbd_dev->spec->snap_id);
-	ret = rbd_obj_method_sync(rbd_dev, &rbd_dev->header_oid,
-				  &rbd_dev->header_oloc, "get_parent",
-				  &snapid, sizeof(snapid), reply_buf, size);
-	dout("%s: rbd_obj_method_sync returned %d\n", __func__, ret);
-	if (ret < 0)
-		goto out_err;
+	dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n",
+	     __func__, pii.pool_id, pii.pool_ns, pii.image_id, pii.snap_id,
+	     pii.has_overlap, pii.overlap);
 
-	p = reply_buf;
-	end = reply_buf + ret;
-	ret = -ERANGE;
-	ceph_decode_64_safe(&p, end, pool_id, out_err);
-	if (pool_id == CEPH_NOPOOL) {
+	if (pii.pool_id == CEPH_NOPOOL || !pii.has_overlap) {
 		/*
 		 * Either the parent never existed, or we have
 		 * record of it but the image got flattened so it no
@@ -4633,6 +4765,10 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 		 * overlap to 0.  The effect of this is that all new
 		 * requests will be treated as if the image had no
 		 * parent.
+		 *
+		 * If !pii.has_overlap, the parent image spec is not
+		 * applicable.  It's there to avoid duplication in each
+		 * snapshot record.
 		 */
 		if (rbd_dev->parent_overlap) {
 			rbd_dev->parent_overlap = 0;
@@ -4647,51 +4783,36 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 	/* The ceph file layout needs to fit pool id in 32 bits */
 
 	ret = -EIO;
-	if (pool_id > (u64)U32_MAX) {
+	if (pii.pool_id > (u64)U32_MAX) {
 		rbd_warn(NULL, "parent pool id too large (%llu > %u)",
-			(unsigned long long)pool_id, U32_MAX);
+			(unsigned long long)pii.pool_id, U32_MAX);
 		goto out_err;
 	}
 
-	image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL);
-	if (IS_ERR(image_id)) {
-		ret = PTR_ERR(image_id);
-		goto out_err;
-	}
-	ceph_decode_64_safe(&p, end, snap_id, out_err);
-	ceph_decode_64_safe(&p, end, overlap, out_err);
-
 	/*
 	 * The parent won't change (except when the clone is
 	 * flattened, already handled that).  So we only need to
 	 * record the parent spec we have not already done so.
 	 */
 	if (!rbd_dev->parent_spec) {
-		parent_spec->pool_id = pool_id;
-		parent_spec->image_id = image_id;
-		parent_spec->snap_id = snap_id;
-
-		/* TODO: support cloning across namespaces */
-		if (rbd_dev->spec->pool_ns) {
-			parent_spec->pool_ns = kstrdup(rbd_dev->spec->pool_ns,
-						       GFP_KERNEL);
-			if (!parent_spec->pool_ns) {
-				ret = -ENOMEM;
-				goto out_err;
-			}
+		parent_spec->pool_id = pii.pool_id;
+		if (pii.pool_ns && *pii.pool_ns) {
+			parent_spec->pool_ns = pii.pool_ns;
+			pii.pool_ns = NULL;
 		}
+		parent_spec->image_id = pii.image_id;
+		pii.image_id = NULL;
+		parent_spec->snap_id = pii.snap_id;
 
 		rbd_dev->parent_spec = parent_spec;
 		parent_spec = NULL;	/* rbd_dev now owns this */
-	} else {
-		kfree(image_id);
 	}
 
 	/*
 	 * We always update the parent overlap.  If it's zero we issue
 	 * a warning, as we will proceed as if there was no parent.
 	 */
-	if (!overlap) {
+	if (!pii.overlap) {
 		if (parent_spec) {
 			/* refresh, careful to warn just once */
 			if (rbd_dev->parent_overlap)
@@ -4702,14 +4823,14 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev)
 			rbd_warn(rbd_dev, "clone is standalone (overlap 0)");
 		}
 	}
-	rbd_dev->parent_overlap = overlap;
+	rbd_dev->parent_overlap = pii.overlap;
 
 out:
 	ret = 0;
 out_err:
-	kfree(reply_buf);
+	kfree(pii.pool_ns);
+	kfree(pii.image_id);
 	rbd_spec_put(parent_spec);
-
 	return ret;
 }
 

drivers/char/Kconfig

@@ -566,5 +566,5 @@ config RANDOM_TRUST_CPU
 	that CPU manufacturer (perhaps with the insistence or mandate
 	of a Nation State's intelligence or law enforcement agencies)
 	has not installed a hidden back door to compromise the CPU's
-	random number generation facilities.
-
+	random number generation facilities. This can also be configured
+	at boot with "random.trust_cpu=on/off".

drivers/char/random.c

@@ -779,6 +779,13 @@ static struct crng_state **crng_node_pool __read_mostly;
 
 static void invalidate_batched_entropy(void);
 
+static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU);
+static int __init parse_trust_cpu(char *arg)
+{
+	return kstrtobool(arg, &trust_cpu);
+}
+early_param("random.trust_cpu", parse_trust_cpu);
+
 static void crng_initialize(struct crng_state *crng)
 {
 	int		i;
@@ -799,12 +806,10 @@ static void crng_initialize(struct crng_state *crng)
 		}
 		crng->state[i] ^= rv;
 	}
-#ifdef CONFIG_RANDOM_TRUST_CPU
-	if (arch_init) {
+	if (trust_cpu && arch_init) {
 		crng_init = 2;
 		pr_notice("random: crng done (trusting CPU's manufacturer)\n");
 	}
-#endif
 	crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
 }