Merge 4.19-rc4 into usb-next

We need the USB fixes in here as well.

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

Documentation/ABI/stable/sysfs-devices-system-xen_memory

@@ -75,3 +75,12 @@ Contact:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
 Description:
 		Amount (in KiB) of low (or normal) memory in the
 		balloon.
+
+What:		/sys/devices/system/xen_memory/xen_memory0/scrub_pages
+Date:		September 2018
+KernelVersion:	4.20
+Contact:	xen-devel@lists.xenproject.org
+Description:
+		Control scrubbing pages before returning them to Xen for others domains
+		use. Can be set with xen_scrub_pages cmdline
+		parameter. Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.

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]
@@ -4994,6 +5000,12 @@
 			Disables the PV optimizations forcing the HVM guest to
 			run as generic HVM guest with no PV drivers.
 
+	xen_scrub_pages=	[XEN]
+			Boolean option to control scrubbing pages before giving them back
+			to Xen, for use by other domains. Can be also changed at runtime
+			with /sys/devices/system/xen_memory/xen_memory0/scrub_pages.
+			Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.
+
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]

Documentation/device-mapper/dm-raid.txt

@@ -348,3 +348,7 @@ Version History
 1.13.1  Fix deadlock caused by early md_stop_writes().  Also fix size an
 	state races.
 1.13.2  Fix raid redundancy validation and avoid keeping raid set frozen
+1.14.0  Fix reshape race on small devices.  Fix stripe adding reshape
+	deadlock/potential data corruption.  Update superblock when
+	specific devices are requested via rebuild.  Fix RAID leg
+	rebuild errors.

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/devicetree/bindings/net/cpsw.txt

@@ -19,6 +19,10 @@ Required properties:
 - slaves		: Specifies number for slaves
 - active_slave		: Specifies the slave to use for time stamping,
 			  ethtool and SIOCGMIIPHY
+- cpsw-phy-sel		: Specifies the phandle to the CPSW phy mode selection
+			  device. See also cpsw-phy-sel.txt for it's binding.
+			  Note that in legacy cases cpsw-phy-sel may be
+			  a child device instead of a phandle.
 
 Optional properties:
 - ti,hwmods		: Must be "cpgmac0"
@@ -75,6 +79,7 @@ Examples:
 		cpts_clock_mult = <0x80000000>;
 		cpts_clock_shift = <29>;
 		syscon = <&cm>;
+		cpsw-phy-sel = <&phy_sel>;
 		cpsw_emac0: slave@0 {
 			phy_id = <&davinci_mdio>, <0>;
 			phy-mode = "rgmii-txid";
@@ -103,6 +108,7 @@ Examples:
 		cpts_clock_mult = <0x80000000>;
 		cpts_clock_shift = <29>;
 		syscon = <&cm>;
+		cpsw-phy-sel = <&phy_sel>;
 		cpsw_emac0: slave@0 {
 			phy_id = <&davinci_mdio>, <0>;
 			phy-mode = "rgmii-txid";

Documentation/devicetree/bindings/net/sh_eth.txt

@@ -16,6 +16,7 @@ Required properties:
 	      "renesas,ether-r8a7794"  if the device is a part of R8A7794 SoC.
 	      "renesas,gether-r8a77980" if the device is a part of R8A77980 SoC.
 	      "renesas,ether-r7s72100" if the device is a part of R7S72100 SoC.
+	      "renesas,ether-r7s9210" if the device is a part of R7S9210 SoC.
 	      "renesas,rcar-gen1-ether" for a generic R-Car Gen1 device.
 	      "renesas,rcar-gen2-ether" for a generic R-Car Gen2 or RZ/G1
 	                                device.

Documentation/filesystems/vfs.txt

@@ -848,7 +848,7 @@ struct file_operations
 ----------------------
 
 This describes how the VFS can manipulate an open file. As of kernel
-4.1, the following members are defined:
+4.18, the following members are defined:
 
 struct file_operations {
 	struct module *owner;
@@ -858,11 +858,11 @@ struct file_operations {
 	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
+	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
-	int (*mremap)(struct file *, struct vm_area_struct *);
 	int (*open) (struct inode *, struct file *);
 	int (*flush) (struct file *, fl_owner_t id);
 	int (*release) (struct inode *, struct file *);
@@ -882,6 +882,10 @@ struct file_operations {
 #ifndef CONFIG_MMU
 	unsigned (*mmap_capabilities)(struct file *);
 #endif
+	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int);
+	int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, u64);
+	int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64);
+	int (*fadvise)(struct file *, loff_t, loff_t, int);
 };
 
 Again, all methods are called without any locks being held, unless
@@ -899,6 +903,9 @@ otherwise noted.
 
   iterate: called when the VFS needs to read the directory contents
 
+  iterate_shared: called when the VFS needs to read the directory contents
+	when filesystem supports concurrent dir iterators
+
   poll: called by the VFS when a process wants to check if there is
 	activity on this file and (optionally) go to sleep until there
 	is activity. Called by the select(2) and poll(2) system calls
@@ -951,6 +958,16 @@ otherwise noted.
 
   fallocate: called by the VFS to preallocate blocks or punch a hole.
 
+  copy_file_range: called by the copy_file_range(2) system call.
+
+  clone_file_range: called by the ioctl(2) system call for FICLONERANGE and
+	FICLONE commands.
+
+  dedupe_file_range: called by the ioctl(2) system call for FIDEDUPERANGE
+	command.
+
+  fadvise: possibly called by the fadvise64() system call.
+
 Note that the file operations are implemented by the specific
 filesystem in which the inode resides. When opening a device node
 (character or block special) most filesystems will call special

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/process/code-of-conduct.rst

@@ -0,0 +1,81 @@
+Contributor Covenant Code of Conduct
+++++++++++++++++++++++++++++++++++++
+
+Our Pledge
+==========
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, sex characteristics, gender identity and
+expression, level of experience, education, socio-economic status, nationality,
+personal appearance, race, religion, or sexual identity and orientation.
+
+Our Standards
+=============
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+  advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others’ private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+
+Our Responsibilities
+====================
+
+Maintainers are responsible for clarifying the standards of acceptable behavior
+and are expected to take appropriate and fair corrective action in response to
+any instances of unacceptable behavior.
+
+Maintainers have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, or to ban temporarily or permanently any
+contributor for other behaviors that they deem inappropriate, threatening,
+offensive, or harmful.
+
+Scope
+=====
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+Enforcement
+===========
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the Technical Advisory Board (TAB) at
+<tab@lists.linux-foundation.org>. All complaints will be reviewed and
+investigated and will result in a response that is deemed necessary and
+appropriate to the circumstances. The TAB is obligated to maintain
+confidentiality with regard to the reporter of an incident.  Further details of
+specific enforcement policies may be posted separately.
+
+Maintainers who do not follow or enforce the Code of Conduct in good faith may
+face temporary or permanent repercussions as determined by other members of the
+project’s leadership.
+
+Attribution
+===========
+
+This Code of Conduct is adapted from the Contributor Covenant, version 1.4,
+available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html

Documentation/process/code-of-conflict.rst

@@ -1,28 +0,0 @@
-Code of Conflict
-----------------
-
-The Linux kernel development effort is a very personal process compared
-to "traditional" ways of developing software.  Your code and ideas
-behind it will be carefully reviewed, often resulting in critique and
-criticism.  The review will almost always require improvements to the
-code before it can be included in the kernel.  Know that this happens
-because everyone involved wants to see the best possible solution for
-the overall success of Linux.  This development process has been proven
-to create the most robust operating system kernel ever, and we do not
-want to do anything to cause the quality of submission and eventual
-result to ever decrease.
-
-If however, anyone feels personally abused, threatened, or otherwise
-uncomfortable due to this process, that is not acceptable.  If so,
-please contact the Linux Foundation's Technical Advisory Board at
-<tab@lists.linux-foundation.org>, or the individual members, and they
-will work to resolve the issue to the best of their ability.  For more
-information on who is on the Technical Advisory Board and what their
-role is, please see:
-
-	- http://www.linuxfoundation.org/projects/linux/tab
-
-As a reviewer of code, please strive to keep things civil and focused on
-the technical issues involved.  We are all humans, and frustrations can
-be high on both sides of the process.  Try to keep in mind the immortal
-words of Bill and Ted, "Be excellent to each other."

Documentation/process/index.rst

@@ -20,7 +20,7 @@ Below are the essential guides that every developer should read.
    :maxdepth: 1
 
    howto
-   code-of-conflict
+   code-of-conduct
    development-process
    submitting-patches
    coding-style

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.
 

Documentation/x86/earlyprintk.txt

@@ -35,25 +35,25 @@ and two USB cables, connected like this:
 ( If your system does not list a debug port capability then you probably
   won't be able to use the USB debug key. )
 
- b.) You also need a Netchip USB debug cable/key:
+ b.) You also need a NetChip USB debug cable/key:
 
         http://www.plxtech.com/products/NET2000/NET20DC/default.asp
 
-     This is a small blue plastic connector with two USB connections,
+     This is a small blue plastic connector with two USB connections;
      it draws power from its USB connections.
 
  c.) You need a second client/console system with a high speed USB 2.0
      port.
 
- d.) The Netchip device must be plugged directly into the physical
+ d.) The NetChip device must be plugged directly into the physical
      debug port on the "host/target" system.  You cannot use a USB hub in
      between the physical debug port and the "host/target" system.
 
      The EHCI debug controller is bound to a specific physical USB
-     port and the Netchip device will only work as an early printk
+     port and the NetChip device will only work as an early printk
      device in this port.  The EHCI host controllers are electrically
      wired such that the EHCI debug controller is hooked up to the
-     first physical and there is no way to change this via software.
+     first physical port and there is no way to change this via software.
      You can find the physical port through experimentation by trying
      each physical port on the system and rebooting.  Or you can try
      and use lsusb or look at the kernel info messages emitted by the
@@ -65,9 +65,9 @@ and two USB cables, connected like this:
      to the hardware vendor, because there is no reason not to wire
      this port into one of the physically accessible ports.
 
- e.) It is also important to note, that many versions of the Netchip
+ e.) It is also important to note, that many versions of the NetChip
      device require the "client/console" system to be plugged into the
-     right and side of the device (with the product logo facing up and
+     right hand side of the device (with the product logo facing up and
      readable left to right).  The reason being is that the 5 volt
      power supply is taken from only one side of the device and it
      must be the side that does not get rebooted.
@@ -81,13 +81,18 @@ and two USB cables, connected like this:
       CONFIG_EARLY_PRINTK_DBGP=y
 
     And you need to add the boot command line: "earlyprintk=dbgp".
+
     (If you are using Grub, append it to the 'kernel' line in
-     /etc/grub.conf)
+     /etc/grub.conf.  If you are using Grub2 on a BIOS firmware system,
+     append it to the 'linux' line in /boot/grub2/grub.cfg. If you are
+     using Grub2 on an EFI firmware system, append it to the 'linux'
+     or 'linuxefi' line in /boot/grub2/grub.cfg or
+     /boot/efi/EFI/<distro>/grub.cfg.)
 
     On systems with more than one EHCI debug controller you must
     specify the correct EHCI debug controller number.  The ordering
     comes from the PCI bus enumeration of the EHCI controllers.  The
-    default with no number argument is "0" the first EHCI debug
+    default with no number argument is "0" or the first EHCI debug
     controller.  To use the second EHCI debug controller, you would
     use the command line: "earlyprintk=dbgp1"
 
@@ -111,7 +116,7 @@ and two USB cables, connected like this:
     see the raw output.
 
  c.) On Nvidia Southbridge based systems: the kernel will try to probe
-     and find out which port has debug device connected.
+     and find out which port has a debug device connected.
 
 3. Testing that it works fine:
 

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>
@@ -5624,6 +5625,8 @@ F:	lib/fault-inject.c
 
 FBTFT Framebuffer drivers
 M:	Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+L:	dri-devel@lists.freedesktop.org
+L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/staging/fbtft/
 
@@ -6059,7 +6062,7 @@ F:	Documentation/gcc-plugins.txt
 
 GASKET DRIVER FRAMEWORK
 M:	Rob Springer <rspringer@google.com>
-M:	John Joseph <jnjoseph@google.com>
+M:	Todd Poynor <toddpoynor@google.com>
 M:	Ben Chan <benchan@chromium.org>
 S:	Maintained
 F:	drivers/staging/gasket/
@@ -7015,6 +7018,20 @@ F:	drivers/crypto/vmx/aes*
 F:	drivers/crypto/vmx/ghash*
 F:	drivers/crypto/vmx/ppc-xlate.pl
 
+IBM Power PCI Hotplug Driver for RPA-compliant PPC64 platform
+M:	Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
+L:	linux-pci@vger.kernel.org
+L:	linuxppc-dev@lists.ozlabs.org
+S:	Supported
+F:	drivers/pci/hotplug/rpaphp*
+
+IBM Power IO DLPAR Driver for RPA-compliant PPC64 platform
+M:	Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
+L:	linux-pci@vger.kernel.org
+L:	linuxppc-dev@lists.ozlabs.org
+S:	Supported
+F:	drivers/pci/hotplug/rpadlpar*
+
 IBM ServeRAID RAID DRIVER
 S:	Orphan
 F:	drivers/scsi/ips.*
@@ -8299,7 +8316,7 @@ F:	include/linux/libata.h
 F:	Documentation/devicetree/bindings/ata/
 
 LIBLOCKDEP
-M:	Sasha Levin <alexander.levin@verizon.com>
+M:	Sasha Levin <alexander.levin@microsoft.com>
 S:	Maintained
 F:	tools/lib/lockdep/
 
@@ -11153,7 +11170,7 @@ F:	drivers/pci/controller/dwc/pci-exynos.c
 
 PCI DRIVER FOR SYNOPSYS DESIGNWARE
 M:	Jingoo Han <jingoohan1@gmail.com>
-M:	Joao Pinto <Joao.Pinto@synopsys.com>
+M:	Gustavo Pimentel <gustavo.pimentel@synopsys.com>
 L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/pci/designware-pcie.txt
@@ -11345,10 +11362,10 @@ S:	Maintained
 F:	drivers/platform/x86/peaq-wmi.c
 
 PER-CPU MEMORY ALLOCATOR
+M:	Dennis Zhou <dennis@kernel.org>
 M:	Tejun Heo <tj@kernel.org>
 M:	Christoph Lameter <cl@linux.com>
-M:	Dennis Zhou <dennisszhou@gmail.com>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu.git
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git
 S:	Maintained
 F:	include/linux/percpu*.h
 F:	mm/percpu*.c

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 19
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
 NAME = Merciless Moray
 
 # *DOCUMENTATION*
@@ -616,6 +616,11 @@ CFLAGS_GCOV	:= -fprofile-arcs -ftest-coverage \
 	$(call cc-disable-warning,maybe-uninitialized,)
 export CFLAGS_GCOV
 
+# The arch Makefiles can override CC_FLAGS_FTRACE. We may also append it later.
+ifdef CONFIG_FUNCTION_TRACER
+  CC_FLAGS_FTRACE := -pg
+endif
+
 # The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default
 # values of the respective KBUILD_* variables
 ARCH_CPPFLAGS :=
@@ -755,9 +760,6 @@ KBUILD_CFLAGS 	+= $(call cc-option, -femit-struct-debug-baseonly) \
 endif
 
 ifdef CONFIG_FUNCTION_TRACER
-ifndef CC_FLAGS_FTRACE
-CC_FLAGS_FTRACE := -pg
-endif
 ifdef CONFIG_FTRACE_MCOUNT_RECORD
   # gcc 5 supports generating the mcount tables directly
   ifeq ($(call cc-option-yn,-mrecord-mcount),y)

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)
+cflags-y				+= -fsection-anchors
-atleast_gcc44 :=  $(call cc-ifversion, -ge, 0404, y)
-
-cflags-$(atleast_gcc44)			+= -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 (vma->vm_file) {
-		if (file) {
+			nm = file_path(vma->vm_file, buf, PAGE_SIZE - 1);
-			nm = file_path(file, buf, PAGE_SIZE - 1);
+			if (IS_ERR(nm))
-			inode = file_inode(vma->vm_file);
+				nm = "?";
-			dev = inode->i_sb->s_dev;
-			ino = inode->i_ino;
 		}
 		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) {
+	if (is_isa_arcv2() && l2_line_sz && slc_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) {
 		__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;
+	bool need_coh = !(attrs & DMA_ATTR_NON_CONSISTENT);
+
+	/*
+	 * __GFP_HIGHMEM flag is cleared by upper layer functions
+	 * (in include/linux/dma-mapping.h) so we should never get a
+	 * __GFP_HIGHMEM here.
+	 */
+	BUG_ON(gfp & __GFP_HIGHMEM);
 
 	page = alloc_pages(gfp, order);
 	if (!page)
 		return NULL;
 
-	/*
-	 * 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)
-	 */
-	if ((is_isa_arcv2() && ioc_enable) ||
-	    (attrs & DMA_ATTR_NON_CONSISTENT))
-		need_coh = 0;
-
-	/*
-	 * - 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;
-
 	/* 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) ||
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT))
-			(is_isa_arcv2() && ioc_enable);
-
-	if (PageHighMem(page) || !is_non_coh)
 		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/jump_label.h

@@ -28,7 +28,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
-	asm goto("1: nop\n\t"
+	asm_volatile_goto("1: nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align 3\n\t"
 		 ".quad 1b, %l[l_yes], %c0\n\t"
@@ -42,7 +42,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
-	asm goto("1: b %l[l_yes]\n\t"
+	asm_volatile_goto("1: b %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".align 3\n\t"
 		 ".quad 1b, %l[l_yes], %c0\n\t"

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 */
+	/* 1-level 2nd stage table, protected by kvm->mmu_lock */
-	spinlock_t pgd_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/kernel/Makefile

@@ -54,6 +54,7 @@ arm64-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o	\
 arm64-obj-$(CONFIG_ARM64_RELOC_TEST)	+= arm64-reloc-test.o
 arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
 arm64-obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o
+arm64-obj-$(CONFIG_CRASH_CORE)		+= crash_core.o
 arm64-obj-$(CONFIG_ARM_SDE_INTERFACE)	+= sdei.o
 arm64-obj-$(CONFIG_ARM64_SSBD)		+= ssbd.o
 

arch/arm64/kernel/crash_core.c

@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) Linaro.
+ * Copyright (C) Huawei Futurewei Technologies.
+ */
+
+#include <linux/crash_core.h>
+#include <asm/memory.h>
+
+void arch_crash_save_vmcoreinfo(void)
+{
+	VMCOREINFO_NUMBER(VA_BITS);
+	/* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */
+	vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n",
+						kimage_voffset);
+	vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
+						PHYS_OFFSET);
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+}

arch/arm64/kernel/machine_kexec.c

@@ -358,14 +358,3 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
 	}
 }
 #endif /* CONFIG_HIBERNATION */
-
-void arch_crash_save_vmcoreinfo(void)
-{
-	VMCOREINFO_NUMBER(VA_BITS);
-	/* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */
-	vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n",
-						kimage_voffset);
-	vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
-						PHYS_OFFSET);
-	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
-}

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))
-	if (!pmd_present(pmd) || !pmd_table(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))
-	if (!pud_present(pud) || !pud_table(pud)) {
+		return 1;
+	if (!pud_table(pud)) {
 		VM_WARN_ON(!pud_table(pud));
 		return 1;
 	}

arch/hexagon/include/asm/bitops.h

@@ -211,7 +211,7 @@ static inline long ffz(int x)
  * This is defined the same way as ffs.
  * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
  */
-static inline long fls(int x)
+static inline int fls(int x)
 {
 	int r;
 
@@ -232,7 +232,7 @@ static inline long fls(int x)
  * the libc and compiler builtin ffs routines, therefore
  * differs in spirit from the above ffz (man ffs).
  */
-static inline long ffs(int x)
+static inline int ffs(int x)
 {
 	int r;
 

arch/hexagon/kernel/dma.c

@@ -60,7 +60,7 @@ static void *hexagon_dma_alloc_coherent(struct device *dev, size_t size,
 			panic("Can't create %s() memory pool!", __func__);
 		else
 			gen_pool_add(coherent_pool,
-				pfn_to_virt(max_low_pfn),
+				(unsigned long)pfn_to_virt(max_low_pfn),
 				hexagon_coherent_pool_size, -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)							\
+#define get_user	__get_user					\
-({									\
+
-	long __e = -EFAULT;						\
+#define __get_user(x, ptr)						\
-	if(likely(access_ok(VERIFY_READ,  p, sizeof(*p)))) {		\
-		__e = __get_user(x,p);					\
-	} else								\
-		x = 0;							\
-	__e;								\
-})
-#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);					\
+	__get_user_check((x), (ptr), (err));				\
-	(void) 0;							\
+	(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)					\
+#define __get_user_asm(inst, x, addr, err)				\
-	asm volatile(							\
+	__asm__ __volatile__ (						\
-	"1:	"inst"	%1,[%2]\n"					\
+		"1:	"inst"	%1,[%2]\n"				\
-	"2:\n"								\
+		"2:\n"							\
-	"	.section .fixup,\"ax\"\n"				\
+		"	.section .fixup,\"ax\"\n"			\
-	"	.align	2\n"						\
+		"	.align	2\n"					\
-	"3:	move %0, %3\n"						\
+		"3:	move %0, %3\n"					\
-	"	move %1, #0\n"						\
+		"	move %1, #0\n"					\
-	"	b	2b\n"						\
+		"	b	2b\n"					\
-	"	.previous\n"						\
+		"	.previous\n"					\
-	"	.section __ex_table,\"a\"\n"				\
+		"	.section __ex_table,\"a\"\n"			\
-	"	.align	3\n"						\
+		"	.align	3\n"					\
-	"	.long	1b, 3b\n"					\
+		"	.long	1b, 3b\n"				\
-	"	.previous"						\
+		"	.previous"					\
-	: "+r" (err), "=&r" (x)						\
+		: "+r" (err), "=&r" (x)					\
-	: "r" (addr), "i" (-EFAULT)					\
+		: "r" (addr), "i" (-EFAULT)				\
-	: "cc")
+		: "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(			    				\
+	__asm__ __volatile__ (						\
-	"\n1:\tlwi " __gu_reg_oper0 ",[%2]\n"				\
+		"\n1:\tlwi " __gu_reg_oper0 ",[%2]\n"			\
-	"\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n"				\
+		"\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n"			\
-	"3:\n"								\
+		"3:\n"							\
-	"	.section .fixup,\"ax\"\n"				\
+		"	.section .fixup,\"ax\"\n"			\
-	"	.align	2\n"						\
+		"	.align	2\n"					\
-	"4:	move	%0, %3\n"					\
+		"4:	move	%0, %3\n"				\
-	"	b	3b\n"						\
+		"	b	3b\n"					\
-	"	.previous\n"						\
+		"	.previous\n"					\
-	"	.section __ex_table,\"a\"\n"				\
+		"	.section __ex_table,\"a\"\n"			\
-	"	.align	3\n"						\
+		"	.align	3\n"					\
-	"	.long	1b, 4b\n"					\
+		"	.long	1b, 4b\n"				\
-	"	.long	2b, 4b\n"					\
+		"	.long	2b, 4b\n"				\
-	"	.previous"						\
+		"	.previous"					\
-	: "+r"(err), "=&r"(x)                				\
+		: "+r"(err), "=&r"(x)					\
-	: "r"(addr), "i"(-EFAULT) 					\
+		: "r"(addr), "i"(-EFAULT)				\
-	: "cc")
+		: "cc")
-#define put_user(x,p)							\
+
-({									\
+#define put_user	__put_user					\
-	long __e = -EFAULT;						\
+
-	if(likely(access_ok(VERIFY_WRITE,  p, sizeof(*p)))) {		\
+#define __put_user(x, ptr)						\
-		__e = __put_user(x,p);					\
-	}								\
-	__e;								\
-})
-#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);					\
+	__put_user_err((x), (ptr), (err));				\
-	(void) 0;							\
+	(void)0;							\
 })
 
-#define __put_user_err(x,ptr,err)					\
+#define __put_user_check(x, ptr, err)					\
+({									\
+	__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)					\
 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)					\
+#define __put_user_asm(inst, x, addr, err)				\
-	asm volatile(							\
+	__asm__ __volatile__ (						\
-	"1:	"inst"	%1,[%2]\n"					\
+		"1:	"inst"	%1,[%2]\n"				\
-	"2:\n"								\
+		"2:\n"							\
-	"	.section .fixup,\"ax\"\n"				\
+		"	.section .fixup,\"ax\"\n"			\
-	"	.align	2\n"						\
+		"	.align	2\n"					\
-	"3:	move	%0, %3\n"					\
+		"3:	move	%0, %3\n"				\
-	"	b	2b\n"						\
+		"	b	2b\n"					\
-	"	.previous\n"						\
+		"	.previous\n"					\
-	"	.section __ex_table,\"a\"\n"				\
+		"	.section __ex_table,\"a\"\n"			\
-	"	.align	3\n"						\
+		"	.align	3\n"					\
-	"	.long	1b, 3b\n"					\
+		"	.long	1b, 3b\n"				\
-	"	.previous"						\
+		"	.previous"					\
-	: "+r" (err)							\
+		: "+r" (err)						\
-	: "r" (x), "r" (addr), "i" (-EFAULT)				\
+		: "r" (x), "r" (addr), "i" (-EFAULT)			\
-	: "cc")
+		: "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(			    				\
+	__asm__ __volatile__ (						\
-	"\n1:\tswi " __pu_reg_oper0 ",[%1]\n"				\
+		"\n1:\tswi " __pu_reg_oper0 ",[%1]\n"			\
-	"\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n"				\
+		"\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n"			\
-	"3:\n"								\
+		"3:\n"							\
-	"	.section .fixup,\"ax\"\n"				\
+		"	.section .fixup,\"ax\"\n"			\
-	"	.align	2\n"						\
+		"	.align	2\n"					\
-	"4:	move	%0, %3\n"					\
+		"4:	move	%0, %3\n"				\
-	"	b	3b\n"						\
+		"	b	3b\n"					\
-	"	.previous\n"						\
+		"	.previous\n"					\
-	"	.section __ex_table,\"a\"\n"				\
+		"	.section __ex_table,\"a\"\n"			\
-	"	.align	3\n"						\
+		"	.align	3\n"					\
-	"	.long	1b, 4b\n"					\
+		"	.long	1b, 4b\n"				\
-	"	.long	2b, 4b\n"					\
+		"	.long	2b, 4b\n"				\
-	"	.previous"						\
+		"	.previous"					\
-	: "+r"(err)                					\
+		: "+r"(err)						\
-	: "r"(addr), "r"(x), "i"(-EFAULT) 				\
+		: "r"(addr), "r"(x), "i"(-EFAULT)			\
-	: "cc")
+		: "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	$r10, __trace_hardirqs_off
-	la	$r9, trace_hardirqs_on
+	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[LP_OFFSET];
-			ret_addr = base_reg[0];
-			next_fp = base_reg[1];
-#else
-			ret_addr = base_reg[-1];
 			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,
+		dump_mem("Stack: ", regs->sp, (regs->sp + PAGE_SIZE) & PAGE_MASK);
-			 THREAD_SIZE + (unsigned long)task_thread_info(tsk));
 		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);
+				psize = 1ul << shift;
-			kvmppc_update_dirty_map(memslot, gfn, npages);
+			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/crypto/paes_s390.c

@@ -208,7 +208,7 @@ static int cbc_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier,
 			      walk->dst.virt.addr, walk->src.virt.addr, n);
 		if (k)
 			ret = blkcipher_walk_done(desc, walk, nbytes - k);
-		if (n < k) {
+		if (k < n) {
 			if (__cbc_paes_set_key(ctx) != 0)
 				return blkcipher_walk_done(desc, walk, -EIO);
 			memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);

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);
-
+		if (rc < 0)
-		up_read(&current->mm->mmap_sem);
+			return rc;
-		if (rc >= 0)
+		start += PAGE_SIZE;
-			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);
-
+			if (rc == -EAGAIN)
-			up_read(&current->mm->mmap_sem);
+				continue;
-			if (rc >= 0)
+			if (rc < 0)
-				start += PAGE_SIZE;
+				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/sparc/kernel/of_device_32.c

@@ -9,6 +9,7 @@
 #include <linux/irq.h>
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
+#include <linux/dma-mapping.h>
 #include <asm/leon.h>
 #include <asm/leon_amba.h>
 
@@ -381,6 +382,9 @@ static struct platform_device * __init scan_one_device(struct device_node *dp,
 	else
 		dev_set_name(&op->dev, "%08x", dp->phandle);
 
+	op->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+	op->dev.dma_mask = &op->dev.coherent_dma_mask;
+
 	if (of_device_register(op)) {
 		printk("%s: Could not register of device.\n",
 		       dp->full_name);

arch/sparc/kernel/of_device_64.c

@@ -2,6 +2,7 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
+#include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/mod_devicetable.h>
@@ -675,6 +676,8 @@ static struct platform_device * __init scan_one_device(struct device_node *dp,
 		dev_set_name(&op->dev, "root");
 	else
 		dev_set_name(&op->dev, "%08x", dp->phandle);
+	op->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+	op->dev.dma_mask = &op->dev.coherent_dma_mask;
 
 	if (of_device_register(op)) {
 		printk("%s: Could not register of device.\n",

arch/x86/events/intel/lbr.c

@@ -1272,4 +1272,8 @@ void intel_pmu_lbr_init_knl(void)
 
 	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
 	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
+
+	/* Knights Landing does have MISPREDICT bit */
+	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP)
+		x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_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_ALLOW_RETRY	    (1 << 3)
-#define EMULTYPE_NO_REEXECUTE	    (1 << 4)
+#define EMULTYPE_NO_UD_ON_FAIL	    (1 << 4)
-#define EMULTYPE_NO_UD_ON_FAIL	    (1 << 5)
+#define EMULTYPE_VMWARE		    (1 << 5)
-#define EMULTYPE_VMWARE		    (1 << 6)
+int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type);
-int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
+int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
-			    int emulation_type, void *insn, int insn_len);
+					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);
-}
 
 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-2level.h

@@ -19,9 +19,6 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte)
 
 static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-	pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd);
-#endif
 	*pmdp = pmd;
 }
 
@@ -61,9 +58,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #ifdef CONFIG_SMP
 static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 {
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-	pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0));
-#endif
 	return __pmd(xchg((pmdval_t *)xp, 0));
 }
 #else
@@ -73,9 +67,6 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #ifdef CONFIG_SMP
 static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 {
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-	pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0));
-#endif
 	return __pud(xchg((pudval_t *)xp, 0));
 }
 #else

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_set_pte(pte_t *ptep, pte_t pte)
+{
+	WRITE_ONCE(*ptep, pte);
+}
+
 static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
 				    pte_t *ptep)
 {
-	*ptep = native_make_pte(0);
+	native_set_pte(ptep, native_make_pte(0));
-}
-
-static inline void native_set_pte(pte_t *ptep, pte_t pte)
-{
-	*ptep = pte;
 }
 
 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/apm_32.c

@@ -1640,6 +1640,7 @@ static int do_open(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+#ifdef CONFIG_PROC_FS
 static int proc_apm_show(struct seq_file *m, void *v)
 {
 	unsigned short	bx;
@@ -1719,6 +1720,7 @@ static int proc_apm_show(struct seq_file *m, void *v)
 		   units);
 	return 0;
 }
+#endif
 
 static int apm(void *unused)
 {

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;
+		ret = UCODE_OK;
-		uci->cpu_sig.rev = rev;
+		goto out;
-		return UCODE_OK;
 	}
 
 	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;
+	rev = mc_amd->hdr.patch_id;
-	c->microcode = mc_amd->hdr.patch_id;
+	ret = UCODE_UPDATED;
 
-	return UCODE_UPDATED;
+	pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev);
+
+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;
+		ret = UCODE_OK;
-		c->microcode = rev;
+		goto out;
-		return UCODE_OK;
 	}
 
 	/*
@@ -848,10 +848,17 @@ static enum ucode_state apply_microcode_intel(int cpu)
 		prev_rev = rev;
 	}
 
-	uci->cpu_sig.rev = rev;
+	ret = UCODE_UPDATED;
-	c->microcode = 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 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))
+	__show_regs(regs, user_mode(regs) ? SHOW_REGS_USER : SHOW_REGS_ALL);
-		all = !user_mode(regs);
-
-	__show_regs(regs, all);
 
 	/*
 	 * When in-kernel, we also print out the stack at the time of the fault..

arch/x86/kernel/eisa.c

@@ -7,11 +7,17 @@
 #include <linux/eisa.h>
 #include <linux/io.h>
 
+#include <xen/xen.h>
+
 static __init int eisa_bus_probe(void)
 {
-	void __iomem *p = ioremap(0x0FFFD9, 4);
+	void __iomem *p;
 
-	if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24))
+	if (xen_pv_domain() && !xen_initial_domain())
+		return 0;
+
+	p = ioremap(0x0FFFD9, 4);
+	if (p && readl(p) == 'E' + ('I' << 8) + ('S' << 16) + ('A' << 24))
 		EISA_bus = 1;
 	iounmap(p);
 	return 0;

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();