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

Documentation/ABI/obsolete/sysfs-class-dax

@@ -0,0 +1,22 @@
+What:           /sys/class/dax/
+Date:           May, 2016
+KernelVersion:  v4.7
+Contact:        linux-nvdimm@lists.01.org
+Description:	Device DAX is the device-centric analogue of Filesystem
+		DAX (CONFIG_FS_DAX).  It allows memory ranges to be
+		allocated and mapped without need of an intervening file
+		system.  Device DAX is strict, precise and predictable.
+		Specifically this interface:
+
+		1/ Guarantees fault granularity with respect to a given
+		page size (pte, pmd, or pud) set at configuration time.
+
+		2/ Enforces deterministic behavior by being strict about
+		what fault scenarios are supported.
+
+		The /sys/class/dax/ interface enumerates all the
+		device-dax instances in the system. The ABI is
+		deprecated and will be removed after 2020. It is
+		replaced with the DAX bus interface /sys/bus/dax/ where
+		device-dax instances can be found under
+		/sys/bus/dax/devices/

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -86,6 +86,13 @@ Description:
 		The unit size is one block, now only support configuring in range
 		of [1, 512].
 
+What:          /sys/fs/f2fs/<disk>/umount_discard_timeout
+Date:          January 2019
+Contact:       "Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		Set timeout to issue discard commands during umount.
+		Default: 5 secs
+
 What:		/sys/fs/f2fs/<disk>/max_victim_search
 Date:		January 2014
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>

Documentation/admin-guide/md.rst

@@ -756,3 +756,6 @@ These currently include:
       The cache mode for raid5. raid5 could include an extra disk for
       caching. The mode can be "write-throuth" and "write-back". The
       default is "write-through".
+
+  ppl_write_hint
+      NVMe stream ID to be set for each PPL write request.

Documentation/arm/kernel_mode_neon.txt

@@ -6,7 +6,7 @@ TL;DR summary
 * Use only NEON instructions, or VFP instructions that don't rely on support
   code
 * Isolate your NEON code in a separate compilation unit, and compile it with
-  '-mfpu=neon -mfloat-abi=softfp'
+  '-march=armv7-a -mfpu=neon -mfloat-abi=softfp'
 * Put kernel_neon_begin() and kernel_neon_end() calls around the calls into your
   NEON code
 * Don't sleep in your NEON code, and be aware that it will be executed with
@@ -87,7 +87,7 @@ instructions appearing in unexpected places if no special care is taken.
 Therefore, the recommended and only supported way of using NEON/VFP in the
 kernel is by adhering to the following rules:
 * isolate the NEON code in a separate compilation unit and compile it with
-  '-mfpu=neon -mfloat-abi=softfp';
+  '-march=armv7-a -mfpu=neon -mfloat-abi=softfp';
 * issue the calls to kernel_neon_begin(), kernel_neon_end() as well as the calls
   into the unit containing the NEON code from a compilation unit which is *not*
   built with the GCC flag '-mfpu=neon' set.

Documentation/devicetree/bindings/display/ssd1307fb.txt

@@ -36,7 +36,6 @@ ssd1307: oled@3c {
         reg = <0x3c>;
         pwms = <&pwm 4 3000>;
         reset-gpios = <&gpio2 7>;
-        reset-active-low;
 };
 
 ssd1306: oled@3c {
@@ -44,7 +43,6 @@ ssd1306: oled@3c {
         reg = <0x3c>;
         pwms = <&pwm 4 3000>;
         reset-gpios = <&gpio2 7>;
-        reset-active-low;
         solomon,com-lrremap;
         solomon,com-invdir;
         solomon,com-offset = <32>;

Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt

@@ -16,6 +16,7 @@ Required properties:
     - "renesas,irqc-r8a7793" (R-Car M2-N)
     - "renesas,irqc-r8a7794" (R-Car E2)
     - "renesas,intc-ex-r8a774a1" (RZ/G2M)
+    - "renesas,intc-ex-r8a774c0" (RZ/G2E)
     - "renesas,intc-ex-r8a7795" (R-Car H3)
     - "renesas,intc-ex-r8a7796" (R-Car M3-W)
     - "renesas,intc-ex-r8a77965" (R-Car M3-N)

Documentation/devicetree/bindings/net/dsa/qca8k.txt

@@ -12,10 +12,15 @@ Required properties:
 Subnodes:
 
 The integrated switch subnode should be specified according to the binding
-described in dsa/dsa.txt. As the QCA8K switches do not have a N:N mapping of
+described in dsa/dsa.txt. If the QCA8K switch is connect to a SoC's external
-port and PHY id, each subnode describing a port needs to have a valid phandle
+mdio-bus each subnode describing a port needs to have a valid phandle
-referencing the internal PHY connected to it. The CPU port of this switch is
+referencing the internal PHY it is connected to. This is because there's no
-always port 0.
+N:N mapping of port and PHY id.
+
+Don't use mixed external and internal mdio-bus configurations, as this is
+not supported by the hardware.
+
+The CPU port of this switch is always port 0.
 
 A CPU port node has the following optional node:
 
@@ -31,8 +36,9 @@ For QCA8K the 'fixed-link' sub-node supports only the following properties:
 - 'full-duplex' (boolean, optional), to indicate that full duplex is
   used. When absent, half duplex is assumed.
 
-Example:
+Examples:
 
+for the external mdio-bus configuration:
 
 	&mdio0 {
 		phy_port1: phy@0 {
@@ -55,12 +61,12 @@ Example:
 			reg = <4>;
 		};
 
-		switch0@0 {
+		switch@10 {
 			compatible = "qca,qca8337";
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			reg = <0>;
+			reg = <0x10>;
 
 			ports {
 				#address-cells = <1>;
@@ -108,3 +114,56 @@ Example:
 			};
 		};
 	};
+
+for the internal master mdio-bus configuration:
+
+	&mdio0 {
+		switch@10 {
+			compatible = "qca,qca8337";
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			reg = <0x10>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					label = "cpu";
+					ethernet = <&gmac1>;
+					phy-mode = "rgmii";
+					fixed-link {
+						speed = 1000;
+						full-duplex;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					label = "lan1";
+				};
+
+				port@2 {
+					reg = <2>;
+					label = "lan2";
+				};
+
+				port@3 {
+					reg = <3>;
+					label = "lan3";
+				};
+
+				port@4 {
+					reg = <4>;
+					label = "lan4";
+				};
+
+				port@5 {
+					reg = <5>;
+					label = "wan";
+				};
+			};
+		};
+	};

Documentation/filesystems/cifs/TODO

@@ -111,7 +111,8 @@ negotiated size) and send larger write sizes to modern servers.
 
 5) Continue to extend the smb3 "buildbot" which does automated xfstesting
 against Windows, Samba and Azure currently - to add additional tests and
-to allow the buildbot to execute the tests faster.
+to allow the buildbot to execute the tests faster. The URL for the
+buildbot is: http://smb3-test-rhel-75.southcentralus.cloudapp.azure.com
 
 6) Address various coverity warnings (most are not bugs per-se, but
 the more warnings are addressed, the easier it is to spot real

Documentation/filesystems/cifs/cifs.txt

@@ -1,16 +1,21 @@
   This is the client VFS module for the SMB3 NAS protocol as well
-  older dialects such as the Common Internet File System (CIFS)
+  as for older dialects such as the Common Internet File System (CIFS)
   protocol which was the successor to the Server Message Block
   (SMB) protocol, the native file sharing mechanism for most early
   PC operating systems. New and improved versions of CIFS are now
-  called SMB2 and SMB3. These dialects are also supported by the
+  called SMB2 and SMB3. Use of SMB3 (and later, including SMB3.1.1)
-  CIFS VFS module. CIFS is fully supported by network
+  is strongly preferred over using older dialects like CIFS due to
-  file servers such as Windows 2000, 2003, 2008, 2012 and 2016
+  security reaasons. All modern dialects, including the most recent,
-  as well by Samba (which provides excellent CIFS
+  SMB3.1.1 are supported by the CIFS VFS module. The SMB3 protocol
-  server support for Linux and many other operating systems), Apple
+  is implemented and supported by all major file servers
-  systems, as well as most Network Attached Storage vendors, so
+  such as all modern versions of Windows (including Windows 2016
-  this network filesystem client can mount to a wide variety of
+  Server), as well as by Samba (which provides excellent
-  servers.
+  CIFS/SMB2/SMB3 server support and tools for Linux and many other
+  operating systems).  Apple systems also support SMB3 well, as
+  do most Network Attached Storage vendors, so this network
+  filesystem client can mount to a wide variety of systems.
+  It also supports mounting to the cloud (for example
+  Microsoft Azure), including the necessary security features.
 
   The intent of this module is to provide the most advanced network
   file system function for SMB3 compliant servers, including advanced
@@ -24,12 +29,17 @@
   cluster file systems for fileserving in some Linux to Linux environments,
   not just in Linux to Windows (or Linux to Mac) environments.
 
-  This filesystem has an mount utility (mount.cifs) that can be obtained from
+  This filesystem has a mount utility (mount.cifs) and various user space
+  tools (including smbinfo and setcifsacl) that can be obtained from
 
-      https://ftp.samba.org/pub/linux-cifs/cifs-utils/
+      https://git.samba.org/?p=cifs-utils.git
+  or
+      git://git.samba.org/cifs-utils.git
 
-  It must be installed in the directory with the other mount helpers.
+  mount.cifs should be installed in the directory with the other mount helpers.
 
   For more information on the module see the project wiki page at
 
+      https://wiki.samba.org/index.php/LinuxCIFS
+  and
       https://wiki.samba.org/index.php/LinuxCIFS_utils

Documentation/filesystems/f2fs.txt

@@ -126,6 +126,8 @@ disable_ext_identify   Disable the extension list configured by mkfs, so f2fs
                        does not aware of cold files such as media files.
 inline_xattr           Enable the inline xattrs feature.
 noinline_xattr         Disable the inline xattrs feature.
+inline_xattr_size=%u   Support configuring inline xattr size, it depends on
+		       flexible inline xattr feature.
 inline_data            Enable the inline data feature: New created small(<~3.4k)
                        files can be written into inode block.
 inline_dentry          Enable the inline dir feature: data in new created

Documentation/kbuild/makefiles.txt

@@ -1274,7 +1274,7 @@ See subsequent chapter for the syntax of the Kbuild file.
 
 --- 7.4 mandatory-y
 
-	mandatory-y is essentially used by include/(uapi/)asm-generic/Kbuild.asm
+	mandatory-y is essentially used by include/(uapi/)asm-generic/Kbuild
 	to define the minimum set of ASM headers that all architectures must have.
 
 	This works like optional generic-y. If a mandatory header is missing

Documentation/networking/nf_flowtable.txt

@@ -44,10 +44,10 @@ including the Netfilter hooks and the flowtable fastpath bypass.
      /         \    /          \     |Routing |   /            \
   -->  ingress  ---> prerouting ---> |decision|   | postrouting |--> neigh_xmit
      \_________/    \__________/     ----------   \____________/          ^
-       |      ^          |               |               ^                |
+       |      ^                          |               ^                |
-   flowtable  |          |          ____\/___            |                |
+   flowtable  |                     ____\/___            |                |
-       |      |          |         /         \           |                |
+       |      |                    /         \           |                |
-    __\/___   |          --------->| forward |------------                |
+    __\/___   |                    | forward |------------                |
     |-----|   |                    \_________/                            |
     |-----|   |                 'flow offload' rule                       |
     |-----|   |                   adds entry to                           |

Documentation/virtual/kvm/api.txt

@@ -45,6 +45,23 @@ the API.  The only supported use is one virtual machine per process,
 and one vcpu per thread.
 
 
+It is important to note that althought VM ioctls may only be issued from
+the process that created the VM, a VM's lifecycle is associated with its
+file descriptor, not its creator (process).  In other words, the VM and
+its resources, *including the associated address space*, are not freed
+until the last reference to the VM's file descriptor has been released.
+For example, if fork() is issued after ioctl(KVM_CREATE_VM), the VM will
+not be freed until both the parent (original) process and its child have
+put their references to the VM's file descriptor.
+
+Because a VM's resources are not freed until the last reference to its
+file descriptor is released, creating additional references to a VM via
+via fork(), dup(), etc... without careful consideration is strongly
+discouraged and may have unwanted side effects, e.g. memory allocated
+by and on behalf of the VM's process may not be freed/unaccounted when
+the VM is shut down.
+
+
 3. Extensions
 -------------
 

Documentation/virtual/kvm/halt-polling.txt

@@ -53,7 +53,8 @@ the global max polling interval then the polling interval can be increased in
 the hope that next time during the longer polling interval the wake up source
 will be received while the host is polling and the latency benefits will be
 received. The polling interval is grown in the function grow_halt_poll_ns() and
-is multiplied by the module parameter halt_poll_ns_grow.
+is multiplied by the module parameters halt_poll_ns_grow and
+halt_poll_ns_grow_start.
 
 In the event that the total block time was greater than the global max polling
 interval then the host will never poll for long enough (limited by the global
@@ -80,22 +81,30 @@ shrunk. These variables are defined in include/linux/kvm_host.h and as module
 parameters in virt/kvm/kvm_main.c, or arch/powerpc/kvm/book3s_hv.c in the
 powerpc kvm-hv case.
 
-Module Parameter    |	     Description	      |	     Default Value
+Module Parameter	|   Description		    |	     Default Value
 --------------------------------------------------------------------------------
-halt_poll_ns	    | The global max polling interval | KVM_HALT_POLL_NS_DEFAULT
+halt_poll_ns		| The global max polling    | KVM_HALT_POLL_NS_DEFAULT
-		    | which defines the ceiling value |
+			| interval which defines    |
-		    | of the polling interval for     | (per arch value)
+			| the ceiling value of the  |
-		    | each vcpu. 		      |
+			| polling interval for      | (per arch value)
+			| each vcpu.		    |
 --------------------------------------------------------------------------------
-halt_poll_ns_grow   | The value by which the halt     |	2
+halt_poll_ns_grow	| The value by which the    | 2
-		    | polling interval is multiplied  |
+			| halt polling interval is  |
-		    | in the grow_halt_poll_ns()      |
+			| multiplied in the	    |
-		    | function.			      |
+			| grow_halt_poll_ns()	    |
+			| function.		    |
 --------------------------------------------------------------------------------
-halt_poll_ns_shrink | The value by which the halt     |	0
+halt_poll_ns_grow_start | The initial value to grow | 10000
-		    | polling interval is divided in  |
+			| to from zero in the	    |
-		    | the shrink_halt_poll_ns()	      |
+			| grow_halt_poll_ns()	    |
-		    | function.			      |
+			| function.		    |
+--------------------------------------------------------------------------------
+halt_poll_ns_shrink	| The value by which the    | 0
+			| halt polling interval is  |
+			| divided in the	    |
+			| shrink_halt_poll_ns()	    |
+			| function.		    |
 --------------------------------------------------------------------------------
 
 These module parameters can be set from the debugfs files in:

Documentation/virtual/kvm/mmu.txt

@@ -224,10 +224,6 @@ Shadow pages contain the following information:
     A bitmap indicating which sptes in spt point (directly or indirectly) at
     pages that may be unsynchronized.  Used to quickly locate all unsychronized
     pages reachable from a given page.
-  mmu_valid_gen:
-    Generation number of the page.  It is compared with kvm->arch.mmu_valid_gen
-    during hash table lookup, and used to skip invalidated shadow pages (see
-    "Zapping all pages" below.)
   clear_spte_count:
     Only present on 32-bit hosts, where a 64-bit spte cannot be written
     atomically.  The reader uses this while running out of the MMU lock
@@ -402,27 +398,6 @@ causes its disallow_lpage to be incremented, thus preventing instantiation of
 a large spte.  The frames at the end of an unaligned memory slot have
 artificially inflated ->disallow_lpages so they can never be instantiated.
 
-Zapping all pages (page generation count)
-=========================================
-
-For the large memory guests, walking and zapping all pages is really slow
-(because there are a lot of pages), and also blocks memory accesses of
-all VCPUs because it needs to hold the MMU lock.
-
-To make it be more scalable, kvm maintains a global generation number
-which is stored in kvm->arch.mmu_valid_gen.  Every shadow page stores
-the current global generation-number into sp->mmu_valid_gen when it
-is created.  Pages with a mismatching generation number are "obsolete".
-
-When KVM need zap all shadow pages sptes, it just simply increases the global
-generation-number then reload root shadow pages on all vcpus.  As the VCPUs
-create new shadow page tables, the old pages are not used because of the
-mismatching generation number.
-
-KVM then walks through all pages and zaps obsolete pages.  While the zap
-operation needs to take the MMU lock, the lock can be released periodically
-so that the VCPUs can make progress.
-
 Fast invalidation of MMIO sptes
 ===============================
 
@@ -435,8 +410,7 @@ shadow pages, and is made more scalable with a similar technique.
 MMIO sptes have a few spare bits, which are used to store a
 generation number.  The global generation number is stored in
 kvm_memslots(kvm)->generation, and increased whenever guest memory info
-changes.  This generation number is distinct from the one described in
+changes.
-the previous section.
 
 When KVM finds an MMIO spte, it checks the generation number of the spte.
 If the generation number of the spte does not equal the global generation
@@ -452,13 +426,16 @@ stored into the MMIO spte.  Thus, the MMIO spte might be created based on
 out-of-date information, but with an up-to-date generation number.
 
 To avoid this, the generation number is incremented again after synchronize_srcu
-returns; thus, the low bit of kvm_memslots(kvm)->generation is only 1 during a
+returns; thus, bit 63 of kvm_memslots(kvm)->generation set to 1 only during a
 memslot update, while some SRCU readers might be using the old copy.  We do not
 want to use an MMIO sptes created with an odd generation number, and we can do
-this without losing a bit in the MMIO spte.  The low bit of the generation
+this without losing a bit in the MMIO spte.  The "update in-progress" bit of the
-is not stored in MMIO spte, and presumed zero when it is extracted out of the
+generation is not stored in MMIO spte, and is so is implicitly zero when the
-spte.  If KVM is unlucky and creates an MMIO spte while the low bit is 1,
+generation is extracted out of the spte.  If KVM is unlucky and creates an MMIO
-the next access to the spte will always be a cache miss.
+spte while an update is in-progress, the next access to the spte will always be
+a cache miss.  For example, a subsequent access during the update window will
+miss due to the in-progress flag diverging, while an access after the update
+window closes will have a higher generation number (as compared to the spte).
 
 
 Further reading

MAINTAINERS

@@ -5278,7 +5278,7 @@ DRM DRIVERS FOR VIVANTE GPU IP
 M:	Lucas Stach <l.stach@pengutronix.de>
 R:	Russell King <linux+etnaviv@armlinux.org.uk>
 R:	Christian Gmeiner <christian.gmeiner@gmail.com>
-L:	etnaviv@lists.freedesktop.org
+L:	etnaviv@lists.freedesktop.org (moderated for non-subscribers)
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
 F:	drivers/gpu/drm/etnaviv/
@@ -8096,6 +8096,16 @@ F:	include/linux/iommu.h
 F:	include/linux/of_iommu.h
 F:	include/linux/iova.h
 
+IO_URING
+M:	Jens Axboe <axboe@kernel.dk>
+L:	linux-block@vger.kernel.org
+L:	linux-fsdevel@vger.kernel.org
+T:	git git://git.kernel.dk/linux-block
+T:	git git://git.kernel.dk/liburing
+S:	Maintained
+F:	fs/io_uring.c
+F:	include/uapi/linux/io_uring.h
+
 IP MASQUERADING
 M:	Juanjo Ciarlante <jjciarla@raiz.uncu.edu.ar>
 S:	Maintained
@@ -8461,6 +8471,7 @@ F:	include/linux/kvm*
 F:	include/kvm/iodev.h
 F:	virt/kvm/*
 F:	tools/kvm/
+F:	tools/testing/selftests/kvm/
 
 KERNEL VIRTUAL MACHINE FOR AMD-V (KVM/amd)
 M:	Joerg Roedel <joro@8bytes.org>
@@ -8470,29 +8481,25 @@ S:	Maintained
 F:	arch/x86/include/asm/svm.h
 F:	arch/x86/kvm/svm.c
 
-KERNEL VIRTUAL MACHINE FOR ARM (KVM/arm)
+KERNEL VIRTUAL MACHINE FOR ARM/ARM64 (KVM/arm, KVM/arm64)
 M:	Christoffer Dall <christoffer.dall@arm.com>
 M:	Marc Zyngier <marc.zyngier@arm.com>
+R:	James Morse <james.morse@arm.com>
+R:	Julien Thierry <julien.thierry@arm.com>
+R:	Suzuki K Pouloze <suzuki.poulose@arm.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	kvmarm@lists.cs.columbia.edu
 W:	http://systems.cs.columbia.edu/projects/kvm-arm
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git
-S:	Supported
+S:	Maintained
 F:	arch/arm/include/uapi/asm/kvm*
 F:	arch/arm/include/asm/kvm*
 F:	arch/arm/kvm/
-F:	virt/kvm/arm/
-F:	include/kvm/arm_*
-
-KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
-M:	Christoffer Dall <christoffer.dall@arm.com>
-M:	Marc Zyngier <marc.zyngier@arm.com>
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-L:	kvmarm@lists.cs.columbia.edu
-S:	Maintained
 F:	arch/arm64/include/uapi/asm/kvm*
 F:	arch/arm64/include/asm/kvm*
 F:	arch/arm64/kvm/
+F:	virt/kvm/arm/
+F:	include/kvm/arm_*
 
 KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips)
 M:	James Hogan <jhogan@kernel.org>

Makefile

@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
-PATCHLEVEL = 0
+PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc2
 NAME = Shy Crocodile
 
 # *DOCUMENTATION*
@@ -31,6 +31,16 @@ _all:
 # descending is started. They are now explicitly listed as the
 # prepare rule.
 
+# Ugly workaround for Debian make-kpkg:
+# make-kpkg directly includes the top Makefile of Linux kernel. In such a case,
+# skip sub-make to support debian_* targets in ruleset/kernel_version.mk, but
+# displays warning to discourage such abusage.
+ifneq ($(word 2, $(MAKEFILE_LIST)),)
+$(warning Do not include top Makefile of Linux Kernel)
+sub-make-done := 1
+MAKEFLAGS += -rR
+endif
+
 ifneq ($(sub-make-done),1)
 
 # Do not use make's built-in rules and variables
@@ -402,7 +412,7 @@ CHECK		= sparse
 
 CHECKFLAGS     := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \
 		  -Wbitwise -Wno-return-void -Wno-unknown-attribute $(CF)
-NOSTDINC_FLAGS  =
+NOSTDINC_FLAGS :=
 CFLAGS_MODULE   =
 AFLAGS_MODULE   =
 LDFLAGS_MODULE  =
@@ -1088,9 +1098,11 @@ asm-generic := -f $(srctree)/scripts/Makefile.asm-generic obj
 
 PHONY += asm-generic uapi-asm-generic
 asm-generic: uapi-asm-generic
-	$(Q)$(MAKE) $(asm-generic)=arch/$(SRCARCH)/include/generated/asm
+	$(Q)$(MAKE) $(asm-generic)=arch/$(SRCARCH)/include/generated/asm \
+	generic=include/asm-generic
 uapi-asm-generic:
-	$(Q)$(MAKE) $(asm-generic)=arch/$(SRCARCH)/include/generated/uapi/asm
+	$(Q)$(MAKE) $(asm-generic)=arch/$(SRCARCH)/include/generated/uapi/asm \
+	generic=include/uapi/asm-generic
 
 PHONY += prepare-objtool
 prepare-objtool: $(objtool_target)

arch/alpha/include/uapi/asm/Kbuild

@@ -1,3 +1 @@
-include include/uapi/asm-generic/Kbuild.asm
-
 generated-y += unistd_32.h

arch/arc/Kconfig

@@ -144,11 +144,11 @@ config ARC_CPU_770
 	  Support for ARC770 core introduced with Rel 4.10 (Summer 2011)
 	  This core has a bunch of cool new features:
 	  -MMU-v3: Variable Page Sz (4k, 8k, 16k), bigger J-TLB (128x4)
-                   Shared Address Spaces (for sharing TLB entries in MMU)
+	           Shared Address Spaces (for sharing TLB entries in MMU)
 	  -Caches: New Prog Model, Region Flush
 	  -Insns: endian swap, load-locked/store-conditional, time-stamp-ctr
 
-endif	#ISA_ARCOMPACT
+endif #ISA_ARCOMPACT
 
 config ARC_CPU_HS
 	bool "ARC-HS"
@@ -198,7 +198,7 @@ config ARC_SMP_HALT_ON_RESET
 	  at designated entry point. For other case, all jump to common
 	  entry point and spin wait for Master's signal.
 
-endif	#SMP
+endif #SMP
 
 config ARC_MCIP
 	bool "ARConnect Multicore IP (MCIP) Support "
@@ -249,7 +249,7 @@ config ARC_CACHE_VIPT_ALIASING
 	bool "Support VIPT Aliasing D$"
 	depends on ARC_HAS_DCACHE && ISA_ARCOMPACT
 
-endif	#ARC_CACHE
+endif #ARC_CACHE
 
 config ARC_HAS_ICCM
 	bool "Use ICCM"
@@ -370,7 +370,7 @@ config ARC_FPU_SAVE_RESTORE
 	  based on actual usage of FPU by a task. Thus our implemn does
 	  this for all tasks in system.
 
-endif	#ISA_ARCOMPACT
+endif #ISA_ARCOMPACT
 
 config ARC_CANT_LLSC
 	def_bool n
@@ -386,6 +386,15 @@ config ARC_HAS_SWAPE
 
 if ISA_ARCV2
 
+config ARC_USE_UNALIGNED_MEM_ACCESS
+	bool "Enable unaligned access in HW"
+	default y
+	select HAVE_EFFICIENT_UNALIGNED_ACCESS
+	help
+	  The ARC HS architecture supports unaligned memory access
+	  which is disabled by default. Enable unaligned access in
+	  hardware and use software to use it
+
 config ARC_HAS_LL64
 	bool "Insn: 64bit LDD/STD"
 	help
@@ -414,7 +423,7 @@ config ARC_IRQ_NO_AUTOSAVE
 	  This is programmable and can be optionally disabled in which case
 	  software INTERRUPT_PROLOGUE/EPILGUE do the needed work
 
-endif	# ISA_ARCV2
+endif # ISA_ARCV2
 
 endmenu   # "ARC CPU Configuration"
 

arch/arc/Makefile

@@ -28,6 +28,12 @@ cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
 
 ifdef CONFIG_ISA_ARCV2
 
+ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
+cflags-y				+= -munaligned-access
+else
+cflags-y				+= -mno-unaligned-access
+endif
+
 ifndef CONFIG_ARC_HAS_LL64
 cflags-y				+= -mno-ll64
 endif

arch/arc/boot/dts/abilis_tb100.dtsi

@@ -38,7 +38,7 @@ ahb_clk: clkdiv_ahb {
 			clock-div = <6>;
 		};
 
-		iomux: iomux@FF10601c {
+		iomux: iomux@ff10601c {
 			/* Port 1 */
 			pctl_tsin_s0: pctl-tsin-s0 {   /* Serial TS-in 0 */
 				abilis,function = "mis0";
@@ -162,182 +162,182 @@ pctl_gpio_i: pctl-gpio-i {
 			};
 		};
 
-		gpioa: gpio@FF140000 {
+		gpioa: gpio@ff140000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF140000 0x1000>;
+			reg = <0xff140000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <3>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioa";
 		};
-		gpiob: gpio@FF141000 {
+		gpiob: gpio@ff141000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF141000 0x1000>;
+			reg = <0xff141000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <2>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiob";
 		};
-		gpioc: gpio@FF142000 {
+		gpioc: gpio@ff142000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF142000 0x1000>;
+			reg = <0xff142000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <3>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioc";
 		};
-		gpiod: gpio@FF143000 {
+		gpiod: gpio@ff143000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF143000 0x1000>;
+			reg = <0xff143000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <2>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiod";
 		};
-		gpioe: gpio@FF144000 {
+		gpioe: gpio@ff144000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF144000 0x1000>;
+			reg = <0xff144000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <3>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioe";
 		};
-		gpiof: gpio@FF145000 {
+		gpiof: gpio@ff145000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF145000 0x1000>;
+			reg = <0xff145000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <2>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiof";
 		};
-		gpiog: gpio@FF146000 {
+		gpiog: gpio@ff146000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF146000 0x1000>;
+			reg = <0xff146000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <3>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiog";
 		};
-		gpioh: gpio@FF147000 {
+		gpioh: gpio@ff147000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF147000 0x1000>;
+			reg = <0xff147000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <2>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioh";
 		};
-		gpioi: gpio@FF148000 {
+		gpioi: gpio@ff148000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF148000 0x1000>;
+			reg = <0xff148000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <12>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioi";
 		};
-		gpioj: gpio@FF149000 {
+		gpioj: gpio@ff149000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF149000 0x1000>;
+			reg = <0xff149000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <32>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioj";
 		};
-		gpiok: gpio@FF14a000 {
+		gpiok: gpio@ff14a000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF14A000 0x1000>;
+			reg = <0xff14a000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <22>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiok";
 		};
-		gpiol: gpio@FF14b000 {
+		gpiol: gpio@ff14b000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF14B000 0x1000>;
+			reg = <0xff14b000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <4>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiol";
 		};
-		gpiom: gpio@FF14c000 {
+		gpiom: gpio@ff14c000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF14C000 0x1000>;
+			reg = <0xff14c000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <4>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiom";
 		};
-		gpion: gpio@FF14d000 {
+		gpion: gpio@ff14d000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF14D000 0x1000>;
+			reg = <0xff14d000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <5>;

arch/arc/boot/dts/abilis_tb100_dvk.dts

@@ -37,27 +37,27 @@ memory {
 	};
 
 	soc100 {
-		uart@FF100000 {
+		uart@ff100000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&pctl_uart0>;
 		};
-		ethernet@FE100000 {
+		ethernet@fe100000 {
 			phy-mode = "rgmii";
 		};
 
-		i2c0: i2c@FF120000 {
+		i2c0: i2c@ff120000 {
 			i2c-sda-hold-time-ns = <432>;
 		};
-		i2c1: i2c@FF121000 {
+		i2c1: i2c@ff121000 {
 			i2c-sda-hold-time-ns = <432>;
 		};
-		i2c2: i2c@FF122000 {
+		i2c2: i2c@ff122000 {
 			i2c-sda-hold-time-ns = <432>;
 		};
-		i2c3: i2c@FF123000 {
+		i2c3: i2c@ff123000 {
 			i2c-sda-hold-time-ns = <432>;
 		};
-		i2c4: i2c@FF124000 {
+		i2c4: i2c@ff124000 {
 			i2c-sda-hold-time-ns = <432>;
 		};
 

arch/arc/boot/dts/abilis_tb101.dtsi

@@ -38,7 +38,7 @@ ahb_clk: clkdiv_ahb {
 			clock-div = <6>;
 		};
 
-		iomux: iomux@FF10601c {
+		iomux: iomux@ff10601c {
 			/* Port 1 */
 			pctl_tsin_s0: pctl-tsin-s0 {   /* Serial TS-in 0 */
 				abilis,function = "mis0";
@@ -171,182 +171,182 @@ pctl_gpio_i: pctl-gpio-i {
 			};
 		};
 
-		gpioa: gpio@FF140000 {
+		gpioa: gpio@ff140000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF140000 0x1000>;
+			reg = <0xff140000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <3>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioa";
 		};
-		gpiob: gpio@FF141000 {
+		gpiob: gpio@ff141000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF141000 0x1000>;
+			reg = <0xff141000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <2>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiob";
 		};
-		gpioc: gpio@FF142000 {
+		gpioc: gpio@ff142000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF142000 0x1000>;
+			reg = <0xff142000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <3>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioc";
 		};
-		gpiod: gpio@FF143000 {
+		gpiod: gpio@ff143000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF143000 0x1000>;
+			reg = <0xff143000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <2>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiod";
 		};
-		gpioe: gpio@FF144000 {
+		gpioe: gpio@ff144000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF144000 0x1000>;
+			reg = <0xff144000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <3>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioe";
 		};
-		gpiof: gpio@FF145000 {
+		gpiof: gpio@ff145000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF145000 0x1000>;
+			reg = <0xff145000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <2>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiof";
 		};
-		gpiog: gpio@FF146000 {
+		gpiog: gpio@ff146000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF146000 0x1000>;
+			reg = <0xff146000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <3>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiog";
 		};
-		gpioh: gpio@FF147000 {
+		gpioh: gpio@ff147000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF147000 0x1000>;
+			reg = <0xff147000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <2>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioh";
 		};
-		gpioi: gpio@FF148000 {
+		gpioi: gpio@ff148000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF148000 0x1000>;
+			reg = <0xff148000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <12>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioi";
 		};
-		gpioj: gpio@FF149000 {
+		gpioj: gpio@ff149000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF149000 0x1000>;
+			reg = <0xff149000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <32>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpioj";
 		};
-		gpiok: gpio@FF14a000 {
+		gpiok: gpio@ff14a000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF14A000 0x1000>;
+			reg = <0xff14a000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <22>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiok";
 		};
-		gpiol: gpio@FF14b000 {
+		gpiol: gpio@ff14b000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF14B000 0x1000>;
+			reg = <0xff14b000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <4>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiol";
 		};
-		gpiom: gpio@FF14c000 {
+		gpiom: gpio@ff14c000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF14C000 0x1000>;
+			reg = <0xff14c000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <4>;
 			gpio-ranges = <&iomux 0 0 0>;
 			gpio-ranges-group-names = "gpiom";
 		};
-		gpion: gpio@FF14d000 {
+		gpion: gpio@ff14d000 {
 			compatible = "abilis,tb10x-gpio";
 			interrupt-controller;
 			#interrupt-cells = <1>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <27 2>;
-			reg = <0xFF14D000 0x1000>;
+			reg = <0xff14d000 0x1000>;
 			gpio-controller;
 			#gpio-cells = <2>;
 			abilis,ngpio = <5>;

arch/arc/boot/dts/abilis_tb101_dvk.dts

@@ -37,27 +37,27 @@ memory {
 	};
 
 	soc100 {
-		uart@FF100000 {
+		uart@ff100000 {
 			pinctrl-names = "default";
 			pinctrl-0 = <&pctl_uart0>;
 		};
-		ethernet@FE100000 {
+		ethernet@fe100000 {
 			phy-mode = "rgmii";
 		};
 
-		i2c0: i2c@FF120000 {
+		i2c0: i2c@ff120000 {
 			i2c-sda-hold-time-ns = <432>;
 		};
-		i2c1: i2c@FF121000 {
+		i2c1: i2c@ff121000 {
 			i2c-sda-hold-time-ns = <432>;
 		};
-		i2c2: i2c@FF122000 {
+		i2c2: i2c@ff122000 {
 			i2c-sda-hold-time-ns = <432>;
 		};
-		i2c3: i2c@FF123000 {
+		i2c3: i2c@ff123000 {
 			i2c-sda-hold-time-ns = <432>;
 		};
-		i2c4: i2c@FF124000 {
+		i2c4: i2c@ff124000 {
 			i2c-sda-hold-time-ns = <432>;
 		};
 

arch/arc/boot/dts/abilis_tb10x.dtsi

@@ -54,7 +54,7 @@ soc100 {
 		#size-cells	= <1>;
 		device_type	= "soc";
 		ranges		= <0xfe000000 0xfe000000 0x02000000
-				0x000F0000 0x000F0000 0x00010000>;
+				0x000f0000 0x000f0000 0x00010000>;
 		compatible	= "abilis,tb10x", "simple-bus";
 
 		pll0: oscillator {
@@ -75,10 +75,10 @@ ahb_clk: clkdiv_ahb {
 			clock-output-names = "ahb_clk";
 		};
 
-		iomux: iomux@FF10601c {
+		iomux: iomux@ff10601c {
 			compatible = "abilis,tb10x-iomux";
 			#gpio-range-cells = <3>;
-			reg = <0xFF10601c 0x4>;
+			reg = <0xff10601c 0x4>;
 		};
 
 		intc: interrupt-controller {
@@ -88,7 +88,7 @@ intc: interrupt-controller {
 		};
 		tb10x_ictl: pic@fe002000 {
 			compatible = "abilis,tb10x-ictl";
-			reg = <0xFE002000 0x20>;
+			reg = <0xfe002000 0x20>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
 			interrupt-parent = <&intc>;
@@ -96,27 +96,27 @@ tb10x_ictl: pic@fe002000 {
 					20 21 22 23 24 25 26 27 28 29 30 31>;
 		};
 
-		uart@FF100000 {
+		uart@ff100000 {
 			compatible = "snps,dw-apb-uart";
-			reg = <0xFF100000 0x100>;
+			reg = <0xff100000 0x100>;
 			clock-frequency = <166666666>;
 			interrupts = <25 8>;
 			reg-shift = <2>;
 			reg-io-width = <4>;
 			interrupt-parent = <&tb10x_ictl>;
 		};
-		ethernet@FE100000 {
+		ethernet@fe100000 {
 			compatible = "snps,dwmac-3.70a","snps,dwmac";
-			reg = <0xFE100000 0x1058>;
+			reg = <0xfe100000 0x1058>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <6 8>;
 			interrupt-names = "macirq";
 			clocks = <&ahb_clk>;
 			clock-names = "stmmaceth";
 		};
-		dma@FE000000 {
+		dma@fe000000 {
 			compatible = "snps,dma-spear1340";
-			reg = <0xFE000000 0x400>;
+			reg = <0xfe000000 0x400>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <14 8>;
 			dma-channels = <6>;
@@ -132,70 +132,70 @@ dma@FE000000 {
 			multi-block = <1 1 1 1 1 1>;
 		};
 
-		i2c0: i2c@FF120000 {
+		i2c0: i2c@ff120000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "snps,designware-i2c";
-			reg = <0xFF120000 0x1000>;
+			reg = <0xff120000 0x1000>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <12 8>;
 			clocks = <&ahb_clk>;
 		};
-		i2c1: i2c@FF121000 {
+		i2c1: i2c@ff121000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "snps,designware-i2c";
-			reg = <0xFF121000 0x1000>;
+			reg = <0xff121000 0x1000>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <12 8>;
 			clocks = <&ahb_clk>;
 		};
-		i2c2: i2c@FF122000 {
+		i2c2: i2c@ff122000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "snps,designware-i2c";
-			reg = <0xFF122000 0x1000>;
+			reg = <0xff122000 0x1000>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <12 8>;
 			clocks = <&ahb_clk>;
 		};
-		i2c3: i2c@FF123000 {
+		i2c3: i2c@ff123000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "snps,designware-i2c";
-			reg = <0xFF123000 0x1000>;
+			reg = <0xff123000 0x1000>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <12 8>;
 			clocks = <&ahb_clk>;
 		};
-		i2c4: i2c@FF124000 {
+		i2c4: i2c@ff124000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "snps,designware-i2c";
-			reg = <0xFF124000 0x1000>;
+			reg = <0xff124000 0x1000>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <12 8>;
 			clocks = <&ahb_clk>;
 		};
 
-		spi0: spi@0xFE010000 {
+		spi0: spi@fe010000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			cell-index = <0>;
 			compatible = "abilis,tb100-spi";
 			num-cs = <1>;
-			reg = <0xFE010000 0x20>;
+			reg = <0xfe010000 0x20>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <26 8>;
 			clocks = <&ahb_clk>;
 		};
-		spi1: spi@0xFE011000 {
+		spi1: spi@fe011000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			cell-index = <1>;
 			compatible = "abilis,tb100-spi";
 			num-cs = <2>;
-			reg = <0xFE011000 0x20>;
+			reg = <0xfe011000 0x20>;
 			interrupt-parent = <&tb10x_ictl>;
 			interrupts = <10 8>;
 			clocks = <&ahb_clk>;
@@ -226,23 +226,23 @@ tb10x_stream_proc: tb10x-stream-proc {
 			interrupts = <20 2>, <19 2>;
 			interrupt-names = "cmd_irq", "event_irq";
 		};
-		tb10x_mdsc0: tb10x-mdscr@FF300000 {
+		tb10x_mdsc0: tb10x-mdscr@ff300000 {
 			compatible = "abilis,tb100-mdscr";
-			reg = <0xFF300000 0x7000>;
+			reg = <0xff300000 0x7000>;
 			tb100-mdscr-manage-tsin;
 		};
-		tb10x_mscr0: tb10x-mdscr@FF307000 {
+		tb10x_mscr0: tb10x-mdscr@ff307000 {
 			compatible = "abilis,tb100-mdscr";
-			reg = <0xFF307000 0x7000>;
+			reg = <0xff307000 0x7000>;
 		};
 		tb10x_scr0: tb10x-mdscr@ff30e000 {
 			compatible = "abilis,tb100-mdscr";
-			reg = <0xFF30e000 0x4000>;
+			reg = <0xff30e000 0x4000>;
 			tb100-mdscr-manage-tsin;
 		};
 		tb10x_scr1: tb10x-mdscr@ff312000 {
 			compatible = "abilis,tb100-mdscr";
-			reg = <0xFF312000 0x4000>;
+			reg = <0xff312000 0x4000>;
 			tb100-mdscr-manage-tsin;
 		};
 		tb10x_wfb: tb10x-wfb@ff319000 {

arch/arc/boot/dts/axc001.dtsi

@@ -41,7 +41,7 @@ core_intc: arc700-intc@cpu {
 		 * this GPIO block ORs all interrupts on CPU card (creg,..)
 		 * to uplink only 1 IRQ to ARC core intc
 		 */
-		dw-apb-gpio@0x2000 {
+		dw-apb-gpio@2000 {
 			compatible = "snps,dw-apb-gpio";
 			reg = < 0x2000 0x80 >;
 			#address-cells = <1>;
@@ -60,7 +60,7 @@ ictl_intc: gpio-controller@0 {
 			};
 		};
 
-		debug_uart: dw-apb-uart@0x5000 {
+		debug_uart: dw-apb-uart@5000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x5000 0x100>;
 			clock-frequency = <33333000>;
@@ -88,7 +88,7 @@ arcpct0: pct {
 	 * avoid duplicating the MB dtsi file given that IRQ from
 	 * this intc to cpu intc are different for axs101 and axs103
 	 */
-	mb_intc: dw-apb-ictl@0xe0012000 {
+	mb_intc: dw-apb-ictl@e0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
 		reg = < 0x0 0xe0012000 0x0 0x200 >;

arch/arc/boot/dts/axc003.dtsi

@@ -55,7 +55,7 @@ core_intc: archs-intc@cpu {
 		 * this GPIO block ORs all interrupts on CPU card (creg,..)
 		 * to uplink only 1 IRQ to ARC core intc
 		 */
-		dw-apb-gpio@0x2000 {
+		dw-apb-gpio@2000 {
 			compatible = "snps,dw-apb-gpio";
 			reg = < 0x2000 0x80 >;
 			#address-cells = <1>;
@@ -74,7 +74,7 @@ ictl_intc: gpio-controller@0 {
 			};
 		};
 
-		debug_uart: dw-apb-uart@0x5000 {
+		debug_uart: dw-apb-uart@5000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x5000 0x100>;
 			clock-frequency = <33333000>;
@@ -102,19 +102,19 @@ arcpct0: pct {
 	 * external DMA buffer located outside of IOC aperture.
 	 */
 	axs10x_mb {
-		ethernet@0x18000 {
+		ethernet@18000 {
 			dma-coherent;
 		};
 
-		ehci@0x40000 {
+		ehci@40000 {
 			dma-coherent;
 		};
 
-		ohci@0x60000 {
+		ohci@60000 {
 			dma-coherent;
 		};
 
-		mmc@0x15000 {
+		mmc@15000 {
 			dma-coherent;
 		};
 	};
@@ -132,7 +132,7 @@ mmc@0x15000 {
 	 * avoid duplicating the MB dtsi file given that IRQ from
 	 * this intc to cpu intc are different for axs101 and axs103
 	 */
-	mb_intc: dw-apb-ictl@0xe0012000 {
+	mb_intc: dw-apb-ictl@e0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
 		reg = < 0x0 0xe0012000 0x0 0x200 >;
@@ -153,7 +153,7 @@ reserved-memory {
 		#size-cells = <2>;
 		ranges;
 		/*
-		 * Move frame buffer out of IOC aperture (0x8z-0xAz).
+		 * Move frame buffer out of IOC aperture (0x8z-0xaz).
 		 */
 		frame_buffer: frame_buffer@be000000 {
 			compatible = "shared-dma-pool";

arch/arc/boot/dts/axc003_idu.dtsi

@@ -62,7 +62,7 @@ idu_intc: idu-interrupt-controller {
 		 * this GPIO block ORs all interrupts on CPU card (creg,..)
 		 * to uplink only 1 IRQ to ARC core intc
 		 */
-		dw-apb-gpio@0x2000 {
+		dw-apb-gpio@2000 {
 			compatible = "snps,dw-apb-gpio";
 			reg = < 0x2000 0x80 >;
 			#address-cells = <1>;
@@ -81,7 +81,7 @@ ictl_intc: gpio-controller@0 {
 			};
 		};
 
-		debug_uart: dw-apb-uart@0x5000 {
+		debug_uart: dw-apb-uart@5000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x5000 0x100>;
 			clock-frequency = <33333000>;
@@ -109,19 +109,19 @@ arcpct0: pct {
 	 * external DMA buffer located outside of IOC aperture.
 	 */
 	axs10x_mb {
-		ethernet@0x18000 {
+		ethernet@18000 {
 			dma-coherent;
 		};
 
-		ehci@0x40000 {
+		ehci@40000 {
 			dma-coherent;
 		};
 
-		ohci@0x60000 {
+		ohci@60000 {
 			dma-coherent;
 		};
 
-		mmc@0x15000 {
+		mmc@15000 {
 			dma-coherent;
 		};
 	};
@@ -138,7 +138,7 @@ mmc@0x15000 {
 	 * avoid duplicating the MB dtsi file given that IRQ from
 	 * this intc to cpu intc are different for axs101 and axs103
 	 */
-	mb_intc: dw-apb-ictl@0xe0012000 {
+	mb_intc: dw-apb-ictl@e0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
 		reg = < 0x0 0xe0012000 0x0 0x200 >;
@@ -159,7 +159,7 @@ reserved-memory {
 		#size-cells = <2>;
 		ranges;
 		/*
-		 * Move frame buffer out of IOC aperture (0x8z-0xAz).
+		 * Move frame buffer out of IOC aperture (0x8z-0xaz).
 		 */
 		frame_buffer: frame_buffer@be000000 {
 			compatible = "shared-dma-pool";

arch/arc/boot/dts/axs10x_mb.dtsi

@@ -72,7 +72,7 @@ pguclk: pguclk {
 			};
 		};
 
-		gmac: ethernet@0x18000 {
+		gmac: ethernet@18000 {
 			#interrupt-cells = <1>;
 			compatible = "snps,dwmac";
 			reg = < 0x18000 0x2000 >;
@@ -88,13 +88,13 @@ gmac: ethernet@0x18000 {
 			mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */
 		};
 
-		ehci@0x40000 {
+		ehci@40000 {
 			compatible = "generic-ehci";
 			reg = < 0x40000 0x100 >;
 			interrupts = < 8 >;
 		};
 
-		ohci@0x60000 {
+		ohci@60000 {
 			compatible = "generic-ohci";
 			reg = < 0x60000 0x100 >;
 			interrupts = < 8 >;
@@ -118,7 +118,7 @@ ohci@0x60000 {
 		 * dw_mci_pltfm_prepare_command() is used in generic platform
 		 * code.
 		 */
-		mmc@0x15000 {
+		mmc@15000 {
 			compatible = "altr,socfpga-dw-mshc";
 			reg = < 0x15000 0x400 >;
 			fifo-depth = < 16 >;
@@ -129,7 +129,7 @@ mmc@0x15000 {
 			bus-width = < 4 >;
 		};
 
-		uart@0x20000 {
+		uart@20000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x20000 0x100>;
 			clock-frequency = <33333333>;
@@ -139,7 +139,7 @@ uart@0x20000 {
 			reg-io-width = <4>;
 		};
 
-		uart@0x21000 {
+		uart@21000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x21000 0x100>;
 			clock-frequency = <33333333>;
@@ -150,7 +150,7 @@ uart@0x21000 {
 		};
 
 		/* UART muxed with USB data port (ttyS3) */
-		uart@0x22000 {
+		uart@22000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x22000 0x100>;
 			clock-frequency = <33333333>;
@@ -160,7 +160,7 @@ uart@0x22000 {
 			reg-io-width = <4>;
 		};
 
-		i2c@0x1d000 {
+		i2c@1d000 {
 			compatible = "snps,designware-i2c";
 			reg = <0x1d000 0x100>;
 			clock-frequency = <400000>;
@@ -177,7 +177,7 @@ i2s: i2s@1e000 {
 			#sound-dai-cells = <0>;
 		};
 
-		i2c@0x1f000 {
+		i2c@1f000 {
 			compatible = "snps,designware-i2c";
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -218,13 +218,13 @@ adv7511_output: endpoint {
 				};
 			};
 
-			eeprom@0x54{
+			eeprom@54{
 				compatible = "atmel,24c01";
 				reg = <0x54>;
 				pagesize = <0x8>;
 			};
 
-			eeprom@0x57{
+			eeprom@57{
 				compatible = "atmel,24c04";
 				reg = <0x57>;
 				pagesize = <0x8>;

arch/arc/boot/dts/hsdk.dts

@@ -110,12 +110,12 @@ soc {
 		cgu_rst: reset-controller@8a0 {
 			compatible = "snps,hsdk-reset";
 			#reset-cells = <1>;
-			reg = <0x8A0 0x4>, <0xFF0 0x4>;
+			reg = <0x8a0 0x4>, <0xff0 0x4>;
 		};
 
 		core_clk: core-clk@0 {
 			compatible = "snps,hsdk-core-pll-clock";
-			reg = <0x00 0x10>, <0x14B8 0x4>;
+			reg = <0x00 0x10>, <0x14b8 0x4>;
 			#clock-cells = <0>;
 			clocks = <&input_clk>;
 
@@ -167,6 +167,18 @@ mmcclk_biu: mmcclk-biu {
 			#clock-cells = <0>;
 		};
 
+		dmac_core_clk: dmac-core-clk {
+			compatible = "fixed-clock";
+			clock-frequency = <400000000>;
+			#clock-cells = <0>;
+		};
+
+		dmac_cfg_clk: dmac-gpu-cfg-clk {
+			compatible = "fixed-clock";
+			clock-frequency = <200000000>;
+			#clock-cells = <0>;
+		};
+
 		gmac: ethernet@8000 {
 			#interrupt-cells = <1>;
 			compatible = "snps,dwmac";
@@ -200,6 +212,7 @@ ohci@60000 {
 			compatible = "snps,hsdk-v1.0-ohci", "generic-ohci";
 			reg = <0x60000 0x100>;
 			interrupts = <15>;
+			resets = <&cgu_rst HSDK_USB_RESET>;
 			dma-coherent;
 		};
 
@@ -207,6 +220,7 @@ ehci@40000 {
 			compatible = "snps,hsdk-v1.0-ehci", "generic-ehci";
 			reg = <0x40000 0x100>;
 			interrupts = <15>;
+			resets = <&cgu_rst HSDK_USB_RESET>;
 			dma-coherent;
 		};
 
@@ -237,6 +251,21 @@ gpio_port_a: gpio-controller@0 {
 				reg = <0>;
 			};
 		};
+
+		dmac: dmac@80000 {
+			compatible = "snps,axi-dma-1.01a";
+			reg = <0x80000 0x400>;
+			interrupts = <27>;
+			clocks = <&dmac_core_clk>, <&dmac_cfg_clk>;
+			clock-names = "core-clk", "cfgr-clk";
+
+			dma-channels = <4>;
+			snps,dma-masters = <2>;
+			snps,data-width = <3>;
+			snps,block-size = <4096 4096 4096 4096>;
+			snps,priority = <0 1 2 3>;
+			snps,axi-max-burst-len = <16>;
+		};
 	};
 
 	memory@80000000 {

arch/arc/boot/dts/vdk_axc003.dtsi

@@ -36,7 +36,7 @@ core_intc: archs-intc@cpu {
 			#interrupt-cells = <1>;
 		};
 
-		debug_uart: dw-apb-uart@0x5000 {
+		debug_uart: dw-apb-uart@5000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x5000 0x100>;
 			clock-frequency = <2403200>;
@@ -49,7 +49,7 @@ debug_uart: dw-apb-uart@0x5000 {
 
 	};
 
-	mb_intc: dw-apb-ictl@0xe0012000 {
+	mb_intc: dw-apb-ictl@e0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
 		reg = < 0xe0012000 0x200 >;

arch/arc/boot/dts/vdk_axc003_idu.dtsi

@@ -44,7 +44,7 @@ idu_intc: idu-interrupt-controller {
 			#interrupt-cells = <1>;
 		};
 
-		debug_uart: dw-apb-uart@0x5000 {
+		debug_uart: dw-apb-uart@5000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x5000 0x100>;
 			clock-frequency = <2403200>;
@@ -57,7 +57,7 @@ debug_uart: dw-apb-uart@0x5000 {
 
 	};
 
-	mb_intc: dw-apb-ictl@0xe0012000 {
+	mb_intc: dw-apb-ictl@e0012000 {
 		#interrupt-cells = <1>;
 		compatible = "snps,dw-apb-ictl";
 		reg = < 0xe0012000 0x200 >;

arch/arc/boot/dts/vdk_axs10x_mb.dtsi

@@ -36,7 +36,7 @@ pguclk: pguclk {
 			};
 		};
 
-		ethernet@0x18000 {
+		ethernet@18000 {
 			#interrupt-cells = <1>;
 			compatible = "snps,dwmac";
 			reg = < 0x18000 0x2000 >;
@@ -49,13 +49,13 @@ ethernet@0x18000 {
 			clock-names = "stmmaceth";
 		};
 
-		ehci@0x40000 {
+		ehci@40000 {
 			compatible = "generic-ehci";
 			reg = < 0x40000 0x100 >;
 			interrupts = < 8 >;
 		};
 
-		uart@0x20000 {
+		uart@20000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x20000 0x100>;
 			clock-frequency = <2403200>;
@@ -65,7 +65,7 @@ uart@0x20000 {
 			reg-io-width = <4>;
 		};
 
-		uart@0x21000 {
+		uart@21000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x21000 0x100>;
 			clock-frequency = <2403200>;
@@ -75,7 +75,7 @@ uart@0x21000 {
 			reg-io-width = <4>;
 		};
 
-		uart@0x22000 {
+		uart@22000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x22000 0x100>;
 			clock-frequency = <2403200>;
@@ -101,7 +101,7 @@ ps2: ps2@e0017400 {
 			interrupt-names = "arc_ps2_irq";
 		};
 
-		mmc@0x15000 {
+		mmc@15000 {
 			compatible = "snps,dw-mshc";
 			reg = <0x15000 0x400>;
 			fifo-depth = <1024>;
@@ -117,11 +117,11 @@ mmc@0x15000 {
 	 * Embedded Vision subsystem UIO mappings; only relevant for EV VDK
 	 *
 	 * This node is intentionally put outside of MB above becase
-	 * it maps areas outside of MB's 0xEz-0xFz.
+	 * it maps areas outside of MB's 0xez-0xfz.
 	 */
-	uio_ev: uio@0xD0000000 {
+	uio_ev: uio@d0000000 {
 		compatible = "generic-uio";
-		reg = <0xD0000000 0x2000 0xD1000000 0x2000 0x90000000 0x10000000 0xC0000000 0x10000000>;
+		reg = <0xd0000000 0x2000 0xd1000000 0x2000 0x90000000 0x10000000 0xc0000000 0x10000000>;
 		reg-names = "ev_gsa", "ev_ctrl", "ev_shared_mem", "ev_code_mem";
 		interrupt-parent = <&mb_intc>;
 		interrupts = <23>;

arch/arc/configs/hsdk_defconfig

@@ -8,6 +8,7 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_BLK_DEV_RAM=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set

arch/arc/include/asm/arcregs.h

@@ -82,6 +82,7 @@
 #define ECR_V_DTLB_MISS			0x05
 #define ECR_V_PROTV			0x06
 #define ECR_V_TRAP			0x09
+#define ECR_V_MISALIGN			0x0d
 #endif
 
 /* DTLB Miss and Protection Violation Cause Codes */
@@ -167,14 +168,6 @@ struct bcr_mpy {
 #endif
 };
 
-struct bcr_extn_xymem {
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int ram_org:2, num_banks:4, bank_sz:4, ver:8;
-#else
-	unsigned int ver:8, bank_sz:4, num_banks:4, ram_org:2;
-#endif
-};
-
 struct bcr_iccm_arcompact {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	unsigned int base:16, pad:5, sz:3, ver:8;
@@ -312,7 +305,7 @@ struct cpuinfo_arc {
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
 	struct bcr_isa_arcv2 isa;
-	const char *details, *name;
+	const char *release, *name;
 	unsigned int vec_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
@@ -322,7 +315,6 @@ struct cpuinfo_arc {
 			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
 	} extn;
 	struct bcr_mpy extn_mpy;
-	struct bcr_extn_xymem extn_xymem;
 };
 
 extern struct cpuinfo_arc cpuinfo_arc700[];

arch/arc/include/asm/irqflags-arcv2.h

@@ -44,7 +44,13 @@
 #define ARCV2_IRQ_DEF_PRIO	1
 
 /* seed value for status register */
-#define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | STATUS_AD_MASK | \
+#ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
+#define __AD_ENB	STATUS_AD_MASK
+#else
+#define __AD_ENB	0
+#endif
+
+#define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | __AD_ENB | \
 					(ARCV2_IRQ_DEF_PRIO << 1))
 
 #ifndef __ASSEMBLY__

arch/arc/include/asm/perf_event.h

@@ -105,10 +105,10 @@ static const char * const arc_pmu_ev_hw_map[] = {
 	[PERF_COUNT_HW_INSTRUCTIONS] = "iall",
 	/* All jump instructions that are taken */
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak",
-	[PERF_COUNT_ARC_BPOK]         = "bpok",	  /* NP-NT, PT-T, PNT-NT */
 #ifdef CONFIG_ISA_ARCV2
 	[PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
 #else
+	[PERF_COUNT_ARC_BPOK]         = "bpok",	  /* NP-NT, PT-T, PNT-NT */
 	[PERF_COUNT_HW_BRANCH_MISSES] = "bpfail", /* NP-T, PT-NT, PNT-T */
 #endif
 	[PERF_COUNT_ARC_LDC] = "imemrdc",	/* Instr: mem read cached */

arch/arc/include/asm/spinlock.h

@@ -21,8 +21,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned int val;
 
-	smp_mb();
-
 	__asm__ __volatile__(
 	"1:	llock	%[val], [%[slock]]	\n"
 	"	breq	%[val], %[LOCKED], 1b	\n"	/* spin while LOCKED */
@@ -34,6 +32,14 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
 	: "memory", "cc");
 
+	/*
+	 * ACQUIRE barrier to ensure load/store after taking the lock
+	 * don't "bleed-up" out of the critical section (leak-in is allowed)
+	 * http://www.spinics.net/lists/kernel/msg2010409.html
+	 *
+	 * ARCv2 only has load-load, store-store and all-all barrier
+	 * thus need the full all-all barrier
+	 */
 	smp_mb();
 }
 
@@ -42,8 +48,6 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned int val, got_it = 0;
 
-	smp_mb();
-
 	__asm__ __volatile__(
 	"1:	llock	%[val], [%[slock]]	\n"
 	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
@@ -67,9 +71,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	smp_mb();
 
-	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+	WRITE_ONCE(lock->slock, __ARCH_SPIN_LOCK_UNLOCKED__);
-
-	smp_mb();
 }
 
 /*
@@ -81,8 +83,6 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	unsigned int val;
 
-	smp_mb();
-
 	/*
 	 * zero means writer holds the lock exclusively, deny Reader.
 	 * Otherwise grant lock to first/subseq reader
@@ -113,8 +113,6 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
 	unsigned int val, got_it = 0;
 
-	smp_mb();
-
 	__asm__ __volatile__(
 	"1:	llock	%[val], [%[rwlock]]	\n"
 	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
@@ -140,8 +138,6 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	unsigned int val;
 
-	smp_mb();
-
 	/*
 	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
 	 * deny writer. Otherwise if unlocked grant to writer
@@ -175,8 +171,6 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	unsigned int val, got_it = 0;
 
-	smp_mb();
-
 	__asm__ __volatile__(
 	"1:	llock	%[val], [%[rwlock]]	\n"
 	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
@@ -217,17 +211,13 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 	: [val]		"=&r"	(val)
 	: [rwlock]	"r"	(&(rw->counter))
 	: "memory", "cc");
-
-	smp_mb();
 }
 
 static inline void arch_write_unlock(arch_rwlock_t *rw)
 {
 	smp_mb();
 
-	rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+	WRITE_ONCE(rw->counter, __ARCH_RW_LOCK_UNLOCKED__);
-
-	smp_mb();
 }
 
 #else	/* !CONFIG_ARC_HAS_LLSC */
@@ -237,10 +227,9 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
 
 	/*
-	 * This smp_mb() is technically superfluous, we only need the one
+	 * Per lkmm, smp_mb() is only required after _lock (and before_unlock)
-	 * after the lock for providing the ACQUIRE semantics.
+	 * for ACQ and REL semantics respectively. However EX based spinlocks
-	 * However doing the "right" thing was regressing hackbench
+	 * need the extra smp_mb to workaround a hardware quirk.
-	 * so keeping this, pending further investigation
 	 */
 	smp_mb();
 
@@ -257,14 +246,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 #endif
 	: "memory");
 
-	/*
-	 * ACQUIRE barrier to ensure load/store after taking the lock
-	 * don't "bleed-up" out of the critical section (leak-in is allowed)
-	 * http://www.spinics.net/lists/kernel/msg2010409.html
-	 *
-	 * ARCv2 only has load-load, store-store and all-all barrier
-	 * thus need the full all-all barrier
-	 */
 	smp_mb();
 }
 
@@ -309,8 +290,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	: "memory");
 
 	/*
-	 * superfluous, but keeping for now - see pairing version in
+	 * see pairing version/comment in arch_spin_lock above
-	 * arch_spin_lock above
 	 */
 	smp_mb();
 }
@@ -344,7 +324,6 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 	arch_spin_unlock(&(rw->lock_mutex));
 	local_irq_restore(flags);
 
-	smp_mb();
 	return ret;
 }
 

arch/arc/include/uapi/asm/Kbuild

@@ -1,4 +1,2 @@
-include include/uapi/asm-generic/Kbuild.asm
-
 generic-y += kvm_para.h
 generic-y += ucontext.h

arch/arc/kernel/head.S

@@ -54,7 +54,12 @@
 	; gcc 7.3.1 (ARC GNU 2018.03) onwards generates unaligned access
 	; by default
 	lr	r5, [status32]
+#ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
 	bset	r5, r5, STATUS_AD_BIT
+#else
+	; Although disabled at reset, bootloader might have enabled it
+	bclr	r5, r5, STATUS_AD_BIT
+#endif
 	kflag	r5
 #endif
 .endm
@@ -106,6 +111,7 @@ ENTRY(stext)
 	;    r2 = pointer to uboot provided cmdline or external DTB in mem
 	; These are handled later in handle_uboot_args()
 	st	r0, [@uboot_tag]
+	st      r1, [@uboot_magic]
 	st	r2, [@uboot_arg]
 
 	; setup "current" tsk and optionally cache it in dedicated r25

arch/arc/kernel/intc-arcv2.c

@@ -95,7 +95,7 @@ void arc_init_IRQ(void)
 
 	/* setup status32, don't enable intr yet as kernel doesn't want */
 	tmp = read_aux_reg(ARC_REG_STATUS32);
-	tmp |= STATUS_AD_MASK | (ARCV2_IRQ_DEF_PRIO << 1);
+	tmp |= ARCV2_IRQ_DEF_PRIO << 1;
 	tmp &= ~STATUS_IE_MASK;
 	asm volatile("kflag %0	\n"::"r"(tmp));
 }

arch/arc/kernel/setup.c

@@ -36,6 +36,7 @@ unsigned int intr_to_DE_cnt;
 
 /* Part of U-boot ABI: see head.S */
 int __initdata uboot_tag;
+int __initdata uboot_magic;
 char __initdata *uboot_arg;
 
 const struct machine_desc *machine_desc;
@@ -44,29 +45,24 @@ struct task_struct *_current_task[NR_CPUS];	/* For stack switching */
 
 struct cpuinfo_arc cpuinfo_arc700[NR_CPUS];
 
-static const struct id_to_str arc_cpu_rel[] = {
+static const struct id_to_str arc_legacy_rel[] = {
+	/* ID.ARCVER,	Release */
 #ifdef CONFIG_ISA_ARCOMPACT
-	{ 0x34, "R4.10"},
+	{ 0x34, 	"R4.10"},
-	{ 0x35, "R4.11"},
+	{ 0x35, 	"R4.11"},
 #else
-	{ 0x51, "R2.0" },
+	{ 0x51, 	"R2.0" },
-	{ 0x52, "R2.1" },
+	{ 0x52, 	"R2.1" },
-	{ 0x53, "R3.0" },
+	{ 0x53,		"R3.0" },
-	{ 0x54, "R3.10a" },
 #endif
-	{ 0x00, NULL   }
+	{ 0x00,		NULL   }
 };
 
-static const struct id_to_str arc_cpu_nm[] = {
+static const struct id_to_str arc_cpu_rel[] = {
-#ifdef CONFIG_ISA_ARCOMPACT
+	/* UARCH.MAJOR,	Release */
-	{ 0x20, "ARC 600"   },
+	{  0,		"R3.10a"},
-	{ 0x30, "ARC 770"   },  /* 750 identified seperately */
+	{  1,		"R3.50a"},
-#else
+	{  0xFF,	NULL   }
-	{ 0x40, "ARC EM"  },
-	{ 0x50, "ARC HS38"  },
-	{ 0x54, "ARC HS48"  },
-#endif
-	{ 0x00, "Unknown"   }
 };
 
 static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
@@ -116,31 +112,72 @@ static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu)
 	}
 }
 
+static void decode_arc_core(struct cpuinfo_arc *cpu)
+{
+	struct bcr_uarch_build_arcv2 uarch;
+	const struct id_to_str *tbl;
+
+	/*
+	 * Up until (including) the first core4 release (0x54) things were
+	 * simple: AUX IDENTITY.ARCVER was sufficient to identify arc family
+	 * and release: 0x50 to 0x53 was HS38, 0x54 was HS48 (dual issue)
+	 */
+
+	if (cpu->core.family < 0x54) { /* includes arc700 */
+
+		for (tbl = &arc_legacy_rel[0]; tbl->id != 0; tbl++) {
+			if (cpu->core.family == tbl->id) {
+				cpu->release = tbl->str;
+				break;
+			}
+		}
+
+		if (is_isa_arcompact())
+			cpu->name = "ARC700";
+		else if (tbl->str)
+			cpu->name = "HS38";
+		else
+			cpu->name = cpu->release = "Unknown";
+
+		return;
+	}
+
+	/*
+	 * However the subsequent HS release (same 0x54) allow HS38 or HS48
+	 * configurations and encode this info in a different BCR.
+	 * The BCR was introduced in 0x54 so can't be read unconditionally.
+	 */
+
+	READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch);
+
+	if (uarch.prod == 4) {
+		cpu->name = "HS48";
+		cpu->extn.dual = 1;
+
+	} else {
+		cpu->name = "HS38";
+	}
+
+	for (tbl = &arc_cpu_rel[0]; tbl->id != 0xFF; tbl++) {
+		if (uarch.maj == tbl->id) {
+			cpu->release = tbl->str;
+			break;
+		}
+	}
+}
+
 static void read_arc_build_cfg_regs(void)
 {
 	struct bcr_timer timer;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
-	const struct id_to_str *tbl;
 	struct bcr_isa_arcv2 isa;
 	struct bcr_actionpoint ap;
 
 	FIX_PTR(cpu);
 
 	READ_BCR(AUX_IDENTITY, cpu->core);
-
+	decode_arc_core(cpu);
-	for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) {
-		if (cpu->core.family == tbl->id) {
-			cpu->details = tbl->str;
-			break;
-		}
-	}
-
-	for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) {
-		if ((cpu->core.family & 0xF4) == tbl->id)
-			break;
-	}
-	cpu->name = tbl->str;
 
 	READ_BCR(ARC_REG_TIMERS_BCR, timer);
 	cpu->extn.timer0 = timer.t0;
@@ -151,16 +188,6 @@ static void read_arc_build_cfg_regs(void)
 
 	READ_BCR(ARC_REG_MUL_BCR, cpu->extn_mpy);
 
-	cpu->extn.norm = read_aux_reg(ARC_REG_NORM_BCR) > 1 ? 1 : 0; /* 2,3 */
-	cpu->extn.barrel = read_aux_reg(ARC_REG_BARREL_BCR) > 1 ? 1 : 0; /* 2,3 */
-	cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0;        /* 1,3 */
-	cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0;
-	cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */
-	cpu->extn.swape = (cpu->core.family >= 0x34) ? 1 :
-				IS_ENABLED(CONFIG_ARC_HAS_SWAPE);
-
-	READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem);
-
 	/* Read CCM BCRs for boot reporting even if not enabled in Kconfig */
 	read_decode_ccm_bcr(cpu);
 
@@ -198,30 +225,12 @@ static void read_arc_build_cfg_regs(void)
 		cpu->bpu.num_pred = 2048 << bpu.pte;
 		cpu->bpu.ret_stk = 4 << bpu.rse;
 
-		if (cpu->core.family >= 0x54) {
+		/* if dual issue hardware, is it enabled ? */
+		if (cpu->extn.dual) {
+			unsigned int exec_ctrl;
 
-			struct bcr_uarch_build_arcv2 uarch;
+			READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
-
+			cpu->extn.dual_enb = !(exec_ctrl & 1);
-			/*
-			 * The first 0x54 core (uarch maj:min 0:1 or 0:2) was
-			 * dual issue only (HS4x). But next uarch rev (1:0)
-			 * allows it be configured for single issue (HS3x)
-			 * Ensure we fiddle with dual issue only on HS4x
-			 */
-			READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch);
-
-			if (uarch.prod == 4) {
-				unsigned int exec_ctrl;
-
-				/* dual issue hardware always present */
-				cpu->extn.dual = 1;
-
-				READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
-
-				/* dual issue hardware enabled ? */
-				cpu->extn.dual_enb = !(exec_ctrl & 1);
-
-			}
 		}
 	}
 
@@ -263,7 +272,8 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 {
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id];
 	struct bcr_identity *core = &cpu->core;
-	int i, n = 0, ua = 0;
+	char mpy_opt[16];
+	int n = 0;
 
 	FIX_PTR(cpu);
 
@@ -272,7 +282,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 		       core->family, core->cpu_id, core->chip_id);
 
 	n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s%s%s\n",
-		       cpu_id, cpu->name, cpu->details,
+		       cpu_id, cpu->name, cpu->release,
 		       is_isa_arcompact() ? "ARCompact" : "ARCv2",
 		       IS_AVAIL1(cpu->isa.be, "[Big-Endian]"),
 		       IS_AVAIL3(cpu->extn.dual, cpu->extn.dual_enb, " Dual-Issue "));
@@ -283,61 +293,50 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 		       IS_AVAIL2(cpu->extn.rtc, "RTC [UP 64-bit] ", CONFIG_ARC_TIMERS_64BIT),
 		       IS_AVAIL2(cpu->extn.gfrc, "GFRC [SMP 64-bit] ", CONFIG_ARC_TIMERS_64BIT));
 
-#ifdef __ARC_UNALIGNED__
-	ua = 1;
-#endif
-	n += i = scnprintf(buf + n, len - n, "%s%s%s%s%s%s",
-			   IS_AVAIL2(cpu->isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
-			   IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64),
-			   IS_AVAIL1(cpu->isa.unalign, "unalign "), IS_USED_RUN(ua));
-
-	if (i)
-		n += scnprintf(buf + n, len - n, "\n\t\t: ");
-
 	if (cpu->extn_mpy.ver) {
-		if (cpu->extn_mpy.ver <= 0x2) {	/* ARCompact */
+		if (is_isa_arcompact()) {
-			n += scnprintf(buf + n, len - n, "mpy ");
+			scnprintf(mpy_opt, 16, "mpy");
 		} else {
+
 			int opt = 2;	/* stock MPY/MPYH */
 
 			if (cpu->extn_mpy.dsp)	/* OPT 7-9 */
 				opt = cpu->extn_mpy.dsp + 6;
 
-			n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt);
+			scnprintf(mpy_opt, 16, "mpy[opt %d] ", opt);
 		}
 	}
 
 	n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n",
-		       IS_AVAIL1(cpu->isa.div_rem, "div_rem "),
+		       IS_AVAIL2(cpu->isa.atomic, "atomic ", CONFIG_ARC_HAS_LLSC),
-		       IS_AVAIL1(cpu->extn.norm, "norm "),
+		       IS_AVAIL2(cpu->isa.ldd, "ll64 ", CONFIG_ARC_HAS_LL64),
-		       IS_AVAIL1(cpu->extn.barrel, "barrel-shift "),
+		       IS_AVAIL2(cpu->isa.unalign, "unalign ", CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS),
-		       IS_AVAIL1(cpu->extn.swap, "swap "),
+		       IS_AVAIL1(cpu->extn_mpy.ver, mpy_opt),
-		       IS_AVAIL1(cpu->extn.minmax, "minmax "),
+		       IS_AVAIL1(cpu->isa.div_rem, "div_rem "));
-		       IS_AVAIL1(cpu->extn.crc, "crc "),
-		       IS_AVAIL2(cpu->extn.swape, "swape", CONFIG_ARC_HAS_SWAPE));
 
-	if (cpu->bpu.ver)
+	if (cpu->bpu.ver) {
 		n += scnprintf(buf + n, len - n,
 			      "BPU\t\t: %s%s match, cache:%d, Predict Table:%d Return stk: %d",
 			      IS_AVAIL1(cpu->bpu.full, "full"),
 			      IS_AVAIL1(!cpu->bpu.full, "partial"),
 			      cpu->bpu.num_cache, cpu->bpu.num_pred, cpu->bpu.ret_stk);
 
-	if (is_isa_arcv2()) {
+		if (is_isa_arcv2()) {
-		struct bcr_lpb lpb;
+			struct bcr_lpb lpb;
 
-		READ_BCR(ARC_REG_LPB_BUILD, lpb);
+			READ_BCR(ARC_REG_LPB_BUILD, lpb);
-		if (lpb.ver) {
+			if (lpb.ver) {
-			unsigned int ctl;
+				unsigned int ctl;
-			ctl = read_aux_reg(ARC_REG_LPB_CTRL);
+				ctl = read_aux_reg(ARC_REG_LPB_CTRL);
 
-			n += scnprintf(buf + n, len - n, " Loop Buffer:%d %s",
+				n += scnprintf(buf + n, len - n, " Loop Buffer:%d %s",
-				lpb.entries,
+					       lpb.entries,
-				IS_DISABLED_RUN(!ctl));
+					       IS_DISABLED_RUN(!ctl));
+			}
 		}
+		n += scnprintf(buf + n, len - n, "\n");
 	}
 
-	n += scnprintf(buf + n, len - n, "\n");
 	return buf;
 }
 
@@ -390,11 +389,6 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 		}
 	}
 
-	n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n",
-			EF_ARC_OSABI_CURRENT >> 8,
-			EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ?
-			"no-legacy-syscalls" : "64-bit data any register aligned");
-
 	return buf;
 }
 
@@ -497,6 +491,8 @@ static inline bool uboot_arg_invalid(unsigned long addr)
 #define UBOOT_TAG_NONE		0
 #define UBOOT_TAG_CMDLINE	1
 #define UBOOT_TAG_DTB		2
+/* We always pass 0 as magic from U-boot */
+#define UBOOT_MAGIC_VALUE	0
 
 void __init handle_uboot_args(void)
 {
@@ -511,6 +507,11 @@ void __init handle_uboot_args(void)
 		goto ignore_uboot_args;
 	}
 
+	if (uboot_magic != UBOOT_MAGIC_VALUE) {
+		pr_warn(IGNORE_ARGS "non zero uboot magic\n");
+		goto ignore_uboot_args;
+	}
+
 	if (uboot_tag != UBOOT_TAG_NONE &&
             uboot_arg_invalid((unsigned long)uboot_arg)) {
 		pr_warn(IGNORE_ARGS "invalid uboot arg: '%px'\n", uboot_arg);

arch/arc/kernel/troubleshoot.c

@@ -145,7 +145,8 @@ static void show_ecr_verbose(struct pt_regs *regs)
 	} else if (vec == ECR_V_PROTV) {
 		if (cause_code == ECR_C_PROTV_INST_FETCH)
 			pr_cont("Execute from Non-exec Page\n");
-		else if (cause_code == ECR_C_PROTV_MISALIG_DATA)
+		else if (cause_code == ECR_C_PROTV_MISALIG_DATA &&
+		         IS_ENABLED(CONFIG_ISA_ARCOMPACT))
 			pr_cont("Misaligned r/w from 0x%08lx\n", address);
 		else
 			pr_cont("%s access not allowed on page\n",
@@ -161,6 +162,8 @@ static void show_ecr_verbose(struct pt_regs *regs)
 			pr_cont("Bus Error from Data Mem\n");
 		else
 			pr_cont("Bus Error, check PRM\n");
+	} else if (vec == ECR_V_MISALIGN) {
+		pr_cont("Misaligned r/w from 0x%08lx\n", address);
 #endif
 	} else if (vec == ECR_V_TRAP) {
 		if (regs->ecr_param == 5)

arch/arc/lib/Makefile

@@ -8,4 +8,10 @@
 lib-y	:= strchr-700.o strcpy-700.o strlen.o memcmp.o
 
 lib-$(CONFIG_ISA_ARCOMPACT)	+= memcpy-700.o memset.o strcmp.o
-lib-$(CONFIG_ISA_ARCV2)		+= memcpy-archs.o memset-archs.o strcmp-archs.o
+lib-$(CONFIG_ISA_ARCV2)		+= memset-archs.o strcmp-archs.o
+
+ifdef CONFIG_ARC_USE_UNALIGNED_MEM_ACCESS
+lib-$(CONFIG_ISA_ARCV2)		+=memcpy-archs-unaligned.o
+else
+lib-$(CONFIG_ISA_ARCV2)		+=memcpy-archs.o
+endif

arch/arc/lib/memcpy-archs-unaligned.S

@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * ARCv2 memcpy implementation optimized for unaligned memory access using.
+ *
+ * Copyright (C) 2019 Synopsys
+ * Author: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
+ */
+
+#include <linux/linkage.h>
+
+#ifdef CONFIG_ARC_HAS_LL64
+# define LOADX(DST,RX)		ldd.ab	DST, [RX, 8]
+# define STOREX(SRC,RX)		std.ab	SRC, [RX, 8]
+# define ZOLSHFT		5
+# define ZOLAND			0x1F
+#else
+# define LOADX(DST,RX)		ld.ab	DST, [RX, 4]
+# define STOREX(SRC,RX)		st.ab	SRC, [RX, 4]
+# define ZOLSHFT		4
+# define ZOLAND			0xF
+#endif
+
+ENTRY_CFI(memcpy)
+	mov	r3, r0		; don;t clobber ret val
+
+	lsr.f	lp_count, r2, ZOLSHFT
+	lpnz	@.Lcopy32_64bytes
+	;; LOOP START
+	LOADX	(r6, r1)
+	LOADX	(r8, r1)
+	LOADX	(r10, r1)
+	LOADX	(r4, r1)
+	STOREX	(r6, r3)
+	STOREX	(r8, r3)
+	STOREX	(r10, r3)
+	STOREX	(r4, r3)
+.Lcopy32_64bytes:
+
+	and.f	lp_count, r2, ZOLAND ;Last remaining 31 bytes
+	lpnz	@.Lcopyremainingbytes
+	;; LOOP START
+	ldb.ab	r5, [r1, 1]
+	stb.ab	r5, [r3, 1]
+.Lcopyremainingbytes:
+
+	j	[blink]
+END_CFI(memcpy)

arch/arc/plat-eznps/Kconfig

@@ -26,8 +26,8 @@ config EZNPS_MTM_EXT
 	help
 	  Here we add new hierarchy for CPUs topology.
 	  We got:
-		Core
+	    Core
-		Thread
+	    Thread
 	  At the new thread level each CPU represent one HW thread.
 	  At highest hierarchy each core contain 16 threads,
 	  any of them seem like CPU from Linux point of view.
@@ -35,10 +35,10 @@ config EZNPS_MTM_EXT
 	  core and HW scheduler round robin between them.
 
 config EZNPS_MEM_ERROR_ALIGN
-       bool "ARC-EZchip Memory error as an exception"
+	bool "ARC-EZchip Memory error as an exception"
-       depends on EZNPS_MTM_EXT
+	depends on EZNPS_MTM_EXT
-       default n
+	default n
-       help
+	help
 	  On the real chip of the NPS, user memory errors are handled
 	  as a machine check exception, which is fatal, whereas on
 	  simulator platform for NPS, is handled as a Level 2 interrupt

arch/arm/Kconfig

@@ -1310,7 +1310,7 @@ config SCHED_SMT
 config HAVE_ARM_SCU
 	bool
 	help
-	  This option enables support for the ARM system coherency unit
+	  This option enables support for the ARM snoop control unit
 
 config HAVE_ARM_ARCH_TIMER
 	bool "Architected timer support"
@@ -1322,7 +1322,6 @@ config HAVE_ARM_ARCH_TIMER
 
 config HAVE_ARM_TWD
 	bool
-	select TIMER_OF if OF
 	help
 	  This options enables support for the ARM timer and watchdog unit
 

arch/arm/Kconfig-nommu

@@ -20,10 +20,12 @@ config DRAM_SIZE
 
 config FLASH_MEM_BASE
 	hex 'FLASH Base Address' if SET_MEM_PARAM
+	depends on CPU_ARM740T || CPU_ARM946E || CPU_ARM940T
 	default 0x00400000
 
 config FLASH_SIZE
 	hex 'FLASH Size' if SET_MEM_PARAM
+	depends on CPU_ARM740T || CPU_ARM946E || CPU_ARM940T
 	default 0x00400000
 
 config PROCESSOR_ID

arch/arm/Makefile

@@ -10,7 +10,7 @@
 #
 # Copyright (C) 1995-2001 by Russell King
 
-LDFLAGS_vmlinux	:=-p --no-undefined -X --pic-veneer
+LDFLAGS_vmlinux	:= --no-undefined -X --pic-veneer
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux	+= --be8
 KBUILD_LDFLAGS_MODULE	+= --be8

arch/arm/boot/bootp/Makefile

@@ -8,7 +8,7 @@
 
 GCOV_PROFILE	:= n
 
-LDFLAGS_bootp	:=-p --no-undefined -X \
+LDFLAGS_bootp	:= --no-undefined -X \
 		 --defsym initrd_phys=$(INITRD_PHYS) \
 		 --defsym params_phys=$(PARAMS_PHYS) -T
 AFLAGS_initrd.o :=-DINITRD=\"$(INITRD)\"

arch/arm/boot/bootp/init.S

@@ -44,7 +44,7 @@ _start:		add	lr, pc, #-0x8		@ lr = current load addr
  */
 		movne	r10, #0			@ terminator
 		movne	r4, #2			@ Size of this entry (2 words)
-		stmneia	r9, {r4, r5, r10}	@ Size, ATAG_CORE, terminator
+		stmiane	r9, {r4, r5, r10}	@ Size, ATAG_CORE, terminator
 
 /*
  * find the end of the tag list, and then add an INITRD tag on the end.

arch/arm/boot/compressed/Makefile

@@ -132,8 +132,6 @@ endif
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux += --be8
 endif
-# ?
-LDFLAGS_vmlinux += -p
 # Report unresolved symbol references
 LDFLAGS_vmlinux += --no-undefined
 # Delete all temporary local symbols

arch/arm/boot/compressed/ll_char_wr.S

@@ -75,7 +75,7 @@ Lrow4bpplp:
 	tst	r1, #7				@ avoid using r7 directly after
 	str	r7, [r0, -r5]!
 	subne	r1, r1, #1
-	ldrneb	r7, [r6, r1]
+	ldrbne	r7, [r6, r1]
 	bne	Lrow4bpplp
 	ldmfd	sp!, {r4 - r7, pc}
 
@@ -103,7 +103,7 @@ Lrow8bpplp:
 	sub	r0, r0, r5			@ avoid ip
 	stmia	r0, {r4, ip}
 	subne	r1, r1, #1
-	ldrneb	r7, [r6, r1]
+	ldrbne	r7, [r6, r1]
 	bne	Lrow8bpplp
 	ldmfd	sp!, {r4 - r7, pc}
 

arch/arm/boot/dts/imx28-cfa10036.dts

@@ -11,6 +11,7 @@
 
 /dts-v1/;
 #include "imx28.dtsi"
+#include <dt-bindings/gpio/gpio.h>
 
 / {
 	model = "Crystalfontz CFA-10036 Board";
@@ -96,7 +97,7 @@ ssd1306: oled@3c {
 					pinctrl-names = "default";
 					pinctrl-0 = <&ssd1306_cfa10036>;
 					reg = <0x3c>;
-					reset-gpios = <&gpio2 7 0>;
+					reset-gpios = <&gpio2 7 GPIO_ACTIVE_LOW>;
 					solomon,height = <32>;
 					solomon,width = <128>;
 					solomon,page-offset = <0>;

arch/arm/common/mcpm_entry.c

@@ -381,7 +381,7 @@ static int __init nocache_trampoline(unsigned long _arg)
 	unsigned int cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 	phys_reset_t phys_reset;
 
-	mcpm_set_entry_vector(cpu, cluster, cpu_resume);
+	mcpm_set_entry_vector(cpu, cluster, cpu_resume_no_hyp);
 	setup_mm_for_reboot();
 
 	__mcpm_cpu_going_down(cpu, cluster);

arch/arm/include/asm/Kbuild

@@ -18,7 +18,6 @@ generic-y += segment.h
 generic-y += serial.h
 generic-y += simd.h
 generic-y += sizes.h
-generic-y += timex.h
 generic-y += trace_clock.h
 
 generated-y += mach-types.h

arch/arm/include/asm/arch_gicv3.h

@@ -55,7 +55,7 @@
 #define ICH_VTR				__ACCESS_CP15(c12, 4, c11, 1)
 #define ICH_MISR			__ACCESS_CP15(c12, 4, c11, 2)
 #define ICH_EISR			__ACCESS_CP15(c12, 4, c11, 3)
-#define ICH_ELSR			__ACCESS_CP15(c12, 4, c11, 5)
+#define ICH_ELRSR			__ACCESS_CP15(c12, 4, c11, 5)
 #define ICH_VMCR			__ACCESS_CP15(c12, 4, c11, 7)
 
 #define __LR0(x)			__ACCESS_CP15(c12, 4, c12, x)
@@ -152,7 +152,7 @@ CPUIF_MAP(ICH_HCR, ICH_HCR_EL2)
 CPUIF_MAP(ICH_VTR, ICH_VTR_EL2)
 CPUIF_MAP(ICH_MISR, ICH_MISR_EL2)
 CPUIF_MAP(ICH_EISR, ICH_EISR_EL2)
-CPUIF_MAP(ICH_ELSR, ICH_ELSR_EL2)
+CPUIF_MAP(ICH_ELRSR, ICH_ELRSR_EL2)
 CPUIF_MAP(ICH_VMCR, ICH_VMCR_EL2)
 CPUIF_MAP(ICH_AP0R3, ICH_AP0R3_EL2)
 CPUIF_MAP(ICH_AP0R2, ICH_AP0R2_EL2)

arch/arm/include/asm/assembler.h

@@ -376,9 +376,9 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort, t=TUSER()
 9999:
 	.if	\inc == 1
-	\instr\cond\()b\()\t\().w \reg, [\ptr, #\off]
+	\instr\()b\t\cond\().w \reg, [\ptr, #\off]
 	.elseif	\inc == 4
-	\instr\cond\()\t\().w \reg, [\ptr, #\off]
+	\instr\t\cond\().w \reg, [\ptr, #\off]
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -417,9 +417,9 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.rept	\rept
 9999:
 	.if	\inc == 1
-	\instr\cond\()b\()\t \reg, [\ptr], #\inc
+	\instr\()b\t\cond \reg, [\ptr], #\inc
 	.elseif	\inc == 4
-	\instr\cond\()\t \reg, [\ptr], #\inc
+	\instr\t\cond \reg, [\ptr], #\inc
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -460,7 +460,7 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
 #ifndef CONFIG_CPU_USE_DOMAINS
 	adds	\tmp, \addr, #\size - 1
-	sbcccs	\tmp, \tmp, \limit
+	sbcscc	\tmp, \tmp, \limit
 	bcs	\bad
 #ifdef CONFIG_CPU_SPECTRE
 	movcs	\addr, #0
@@ -474,7 +474,7 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	sub	\tmp, \limit, #1
 	subs	\tmp, \tmp, \addr	@ tmp = limit - 1 - addr
 	addhs	\tmp, \tmp, #1		@ if (tmp >= 0) {
-	subhss	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
+	subshs	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
 	movlo	\addr, #0		@ if (tmp < 0) addr = NULL
 	csdb
 #endif

arch/arm/include/asm/barrier.h

@@ -11,6 +11,8 @@
 #define sev()	__asm__ __volatile__ ("sev" : : : "memory")
 #define wfe()	__asm__ __volatile__ ("wfe" : : : "memory")
 #define wfi()	__asm__ __volatile__ ("wfi" : : : "memory")
+#else
+#define wfe()	do { } while (0)
 #endif
 
 #if __LINUX_ARM_ARCH__ >= 7

arch/arm/include/asm/hardware/entry-macro-iomd.S

@@ -16,25 +16,25 @@
 		ldr	\tmp, =irq_prio_h
 		teq	\irqstat, #0
 #ifdef IOMD_BASE
-		ldreqb	\irqstat, [\base, #IOMD_DMAREQ]	@ get dma
+		ldrbeq	\irqstat, [\base, #IOMD_DMAREQ]	@ get dma
 		addeq	\tmp, \tmp, #256		@ irq_prio_h table size
 		teqeq	\irqstat, #0
 		bne	2406f
 #endif
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQA]	@ get low priority
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQA]	@ get low priority
 		addeq	\tmp, \tmp, #256		@ irq_prio_d table size
 		teqeq	\irqstat, #0
 #ifdef IOMD_IRQREQC
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQC]
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQC]
 		addeq	\tmp, \tmp, #256		@ irq_prio_l table size
 		teqeq	\irqstat, #0
 #endif
 #ifdef IOMD_IRQREQD
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQD]
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQD]
 		addeq	\tmp, \tmp, #256		@ irq_prio_lc table size
 		teqeq	\irqstat, #0
 #endif
-2406:		ldrneb	\irqnr, [\tmp, \irqstat]	@ get IRQ number
+2406:		ldrbne	\irqnr, [\tmp, \irqstat]	@ get IRQ number
 		.endm
 
 /*

arch/arm/include/asm/kvm_emulate.h

@@ -265,6 +265,14 @@ static inline bool kvm_vcpu_dabt_isextabt(struct kvm_vcpu *vcpu)
 	}
 }
 
+static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_trap_is_iabt(vcpu))
+		return false;
+
+	return kvm_vcpu_dabt_iswrite(vcpu);
+}
+
 static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK;

arch/arm/include/asm/kvm_host.h

@@ -26,6 +26,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_mmio.h>
 #include <asm/fpstate.h>
+#include <asm/smp_plat.h>
 #include <kvm/arm_arch_timer.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
@@ -57,10 +58,13 @@ int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 void kvm_reset_coprocs(struct kvm_vcpu *vcpu);
 
-struct kvm_arch {
+struct kvm_vmid {
-	/* VTTBR value associated with below pgd and vmid */
+	/* The VMID generation used for the virt. memory system */
-	u64    vttbr;
+	u64    vmid_gen;
+	u32    vmid;
+};
 
+struct kvm_arch {
 	/* The last vcpu id that ran on each physical CPU */
 	int __percpu *last_vcpu_ran;
 
@@ -70,11 +74,11 @@ struct kvm_arch {
 	 */
 
 	/* The VMID generation used for the virt. memory system */
-	u64    vmid_gen;
+	struct kvm_vmid vmid;
-	u32    vmid;
 
 	/* Stage-2 page table */
 	pgd_t *pgd;
+	phys_addr_t pgd_phys;
 
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
@@ -148,6 +152,13 @@ struct kvm_cpu_context {
 
 typedef struct kvm_cpu_context kvm_cpu_context_t;
 
+static inline void kvm_init_host_cpu_context(kvm_cpu_context_t *cpu_ctxt,
+					     int cpu)
+{
+	/* The host's MPIDR is immutable, so let's set it up at boot time */
+	cpu_ctxt->cp15[c0_MPIDR] = cpu_logical_map(cpu);
+}
+
 struct vcpu_reset_state {
 	unsigned long	pc;
 	unsigned long	r0;
@@ -224,7 +235,35 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
 int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
-unsigned long kvm_call_hyp(void *hypfn, ...);
+
+unsigned long __kvm_call_hyp(void *hypfn, ...);
+
+/*
+ * The has_vhe() part doesn't get emitted, but is used for type-checking.
+ */
+#define kvm_call_hyp(f, ...)						\
+	do {								\
+		if (has_vhe()) {					\
+			f(__VA_ARGS__);					\
+		} else {						\
+			__kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \
+		}							\
+	} while(0)
+
+#define kvm_call_hyp_ret(f, ...)					\
+	({								\
+		typeof(f(__VA_ARGS__)) ret;				\
+									\
+		if (has_vhe()) {					\
+			ret = f(__VA_ARGS__);				\
+		} else {						\
+			ret = __kvm_call_hyp(kvm_ksym_ref(f),		\
+					     ##__VA_ARGS__);		\
+		}							\
+									\
+		ret;							\
+	})
+
 void force_vm_exit(const cpumask_t *mask);
 int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu,
 			      struct kvm_vcpu_events *events);
@@ -275,7 +314,7 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 	 * compliant with the PCS!).
 	 */
 
-	kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
+	__kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
 }
 
 static inline void __cpu_init_stage2(void)

arch/arm/include/asm/kvm_hyp.h

@@ -40,6 +40,7 @@
 #define TTBR1		__ACCESS_CP15_64(1, c2)
 #define VTTBR		__ACCESS_CP15_64(6, c2)
 #define PAR		__ACCESS_CP15_64(0, c7)
+#define CNTP_CVAL	__ACCESS_CP15_64(2, c14)
 #define CNTV_CVAL	__ACCESS_CP15_64(3, c14)
 #define CNTVOFF		__ACCESS_CP15_64(4, c14)
 
@@ -85,6 +86,7 @@
 #define TID_PRIV	__ACCESS_CP15(c13, 0, c0, 4)
 #define HTPIDR		__ACCESS_CP15(c13, 4, c0, 2)
 #define CNTKCTL		__ACCESS_CP15(c14, 0, c1, 0)
+#define CNTP_CTL	__ACCESS_CP15(c14, 0, c2, 1)
 #define CNTV_CTL	__ACCESS_CP15(c14, 0, c3, 1)
 #define CNTHCTL		__ACCESS_CP15(c14, 4, c1, 0)
 
@@ -94,6 +96,8 @@
 #define read_sysreg_el0(r)		read_sysreg(r##_el0)
 #define write_sysreg_el0(v, r)		write_sysreg(v, r##_el0)
 
+#define cntp_ctl_el0			CNTP_CTL
+#define cntp_cval_el0			CNTP_CVAL
 #define cntv_ctl_el0			CNTV_CTL
 #define cntv_cval_el0			CNTV_CVAL
 #define cntvoff_el2			CNTVOFF

arch/arm/include/asm/kvm_mmu.h

@@ -421,9 +421,14 @@ static inline int hyp_map_aux_data(void)
 
 static inline void kvm_set_ipa_limit(void) {}
 
-static inline bool kvm_cpu_has_cnp(void)
+static __always_inline u64 kvm_get_vttbr(struct kvm *kvm)
 {
-	return false;
+	struct kvm_vmid *vmid = &kvm->arch.vmid;
+	u64 vmid_field, baddr;
+
+	baddr = kvm->arch.pgd_phys;
+	vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT;
+	return kvm_phys_to_vttbr(baddr) | vmid_field;
 }
 
 #endif	/* !__ASSEMBLY__ */

arch/arm/include/asm/pgtable.h

@@ -125,6 +125,9 @@ extern pgprot_t		pgprot_s2_device;
 #define pgprot_stronglyordered(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
 
+#define pgprot_device(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_DEV_SHARED | L_PTE_SHARED | L_PTE_DIRTY | L_PTE_XN)
+
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE | L_PTE_XN)

arch/arm/include/asm/processor.h

@@ -89,7 +89,11 @@ extern void release_thread(struct task_struct *);
 unsigned long get_wchan(struct task_struct *p);
 
 #if __LINUX_ARM_ARCH__ == 6 || defined(CONFIG_ARM_ERRATA_754327)
-#define cpu_relax()			smp_mb()
+#define cpu_relax()						\
+	do {							\
+		smp_mb();					\
+		__asm__ __volatile__("nop; nop; nop; nop; nop; nop; nop; nop; nop; nop;");	\
+	} while (0)
 #else
 #define cpu_relax()			barrier()
 #endif

arch/arm/include/asm/smp.h

@@ -67,7 +67,6 @@ struct secondary_data {
 	void *stack;
 };
 extern struct secondary_data secondary_data;
-extern volatile int pen_release;
 extern void secondary_startup(void);
 extern void secondary_startup_arm(void);
 

arch/arm/include/asm/smp_twd.h

@@ -19,20 +19,4 @@
 #define TWD_TIMER_CONTROL_PERIODIC	(1 << 1)
 #define TWD_TIMER_CONTROL_IT_ENABLE	(1 << 2)
 
-#include <linux/ioport.h>
-
-struct twd_local_timer {
-	struct resource	res[2];
-};
-
-#define DEFINE_TWD_LOCAL_TIMER(name,base,irq)	\
-struct twd_local_timer name __initdata = {	\
-	.res	= {				\
-		DEFINE_RES_MEM(base, 0x10),	\
-		DEFINE_RES_IRQ(irq),		\
-	},					\
-};
-
-int twd_local_timer_register(struct twd_local_timer *);
-
 #endif

arch/arm/include/asm/spinlock.h

@@ -210,11 +210,12 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 
 	prefetchw(&rw->lock);
 	__asm__ __volatile__(
+"	.syntax unified\n"
 "1:	ldrex	%0, [%2]\n"
 "	adds	%0, %0, #1\n"
 "	strexpl	%1, %0, [%2]\n"
 	WFE("mi")
-"	rsbpls	%0, %1, #0\n"
+"	rsbspl	%0, %1, #0\n"
 "	bmi	1b"
 	: "=&r" (tmp), "=&r" (tmp2)
 	: "r" (&rw->lock)

arch/arm/include/asm/suspend.h

@@ -10,6 +10,7 @@ struct sleep_save_sp {
 };
 
 extern void cpu_resume(void);
+extern void cpu_resume_no_hyp(void);
 extern void cpu_resume_arm(void);
 extern int cpu_suspend(unsigned long, int (*)(unsigned long));
 

arch/arm/include/asm/uaccess.h

@@ -85,7 +85,8 @@ static inline void set_fs(mm_segment_t fs)
 #define __range_ok(addr, size) ({ \
 	unsigned long flag, roksum; \
 	__chk_user_ptr(addr);	\
-	__asm__("adds %1, %2, %3; sbcccs %1, %1, %0; movcc %0, #0" \
+	__asm__(".syntax unified\n" \
+		"adds %1, %2, %3; sbcscc %1, %1, %0; movcc %0, #0" \
 		: "=&r" (flag), "=&r" (roksum) \
 		: "r" (addr), "Ir" (size), "0" (current_thread_info()->addr_limit) \
 		: "cc"); \

arch/arm/include/asm/v7m.h

@@ -49,7 +49,7 @@
  * (0 -> msp; 1 -> psp). Bits [1:0] are fixed to 0b01.
  */
 #define EXC_RET_STACK_MASK			0x00000004
-#define EXC_RET_THREADMODE_PROCESSSTACK		0xfffffffd
+#define EXC_RET_THREADMODE_PROCESSSTACK		(3 << 2)
 
 /* Cache related definitions */
 

arch/arm/include/asm/vfpmacros.h

@@ -29,13 +29,13 @@
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
 	tst	\tmp, #HWCAP_VFPD32
-	ldcnel	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	ldclne	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
 	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
 	cmp	\tmp, #2			    @ 32 x 64bit registers?
-	ldceql	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	ldcleq	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
 #endif
@@ -53,13 +53,13 @@
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
 	tst	\tmp, #HWCAP_VFPD32
-	stcnel	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	stclne	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
 	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
 	cmp	\tmp, #2			    @ 32 x 64bit registers?
-	stceql	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	stcleq	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
 #endif

arch/arm/include/debug/tegra.S

@@ -173,7 +173,7 @@
 
 		.macro	senduart, rd, rx
 		cmp	\rx, #0
-		strneb	\rd, [\rx, #UART_TX << UART_SHIFT]
+		strbne	\rd, [\rx, #UART_TX << UART_SHIFT]
 1001:
 		.endm
 

arch/arm/include/uapi/asm/Kbuild

@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-include include/uapi/asm-generic/Kbuild.asm
 
 generated-y += unistd-common.h
 generated-y += unistd-oabi.h

arch/arm/kernel/debug.S

@@ -86,7 +86,7 @@ hexbuf_rel:	.long	hexbuf_addr - .
 ENTRY(printascii)
 		addruart_current r3, r1, r2
 1:		teq	r0, #0
-		ldrneb	r1, [r0], #1
+		ldrbne	r1, [r0], #1
 		teqne	r1, #0
 		reteq	lr
 2:		teq     r1, #'\n'

arch/arm/kernel/entry-armv.S

@@ -636,7 +636,7 @@ call_fpe:
 	@ Test if we need to give access to iWMMXt coprocessors
 	ldr	r5, [r10, #TI_FLAGS]
 	rsbs	r7, r8, #(1 << 8)		@ CP 0 or 1 only
-	movcss	r7, r5, lsr #(TIF_USING_IWMMXT + 1)
+	movscs	r7, r5, lsr #(TIF_USING_IWMMXT + 1)
 	bcs	iwmmxt_task_enable
 #endif
  ARM(	add	pc, pc, r8, lsr #6	)
@@ -872,7 +872,7 @@ __kuser_cmpxchg64:				@ 0xffff0f60
 	smp_dmb	arm
 1:	ldrexd	r0, r1, [r2]			@ load current val
 	eors	r3, r0, r4			@ compare with oldval (1)
-	eoreqs	r3, r1, r5			@ compare with oldval (2)
+	eorseq	r3, r1, r5			@ compare with oldval (2)
 	strexdeq r3, r6, r7, [r2]		@ store newval if eq
 	teqeq	r3, #1				@ success?
 	beq	1b				@ if no then retry
@@ -896,8 +896,8 @@ __kuser_cmpxchg64:				@ 0xffff0f60
 	ldmia	r1, {r6, lr}			@ load new val
 1:	ldmia	r2, {r0, r1}			@ load current val
 	eors	r3, r0, r4			@ compare with oldval (1)
-	eoreqs	r3, r1, r5			@ compare with oldval (2)
+	eorseq	r3, r1, r5			@ compare with oldval (2)
-2:	stmeqia	r2, {r6, lr}			@ store newval if eq
+2:	stmiaeq	r2, {r6, lr}			@ store newval if eq
 	rsbs	r0, r3, #0			@ set return val and C flag
 	ldmfd	sp!, {r4, r5, r6, pc}
 
@@ -911,7 +911,7 @@ kuser_cmpxchg64_fixup:
 	mov	r7, #0xffff0fff
 	sub	r7, r7, #(0xffff0fff - (0xffff0f60 + (1b - __kuser_cmpxchg64)))
 	subs	r8, r4, r7
-	rsbcss	r8, r8, #(2b - 1b)
+	rsbscs	r8, r8, #(2b - 1b)
 	strcs	r7, [sp, #S_PC]
 #if __LINUX_ARM_ARCH__ < 6
 	bcc	kuser_cmpxchg32_fixup
@@ -969,7 +969,7 @@ kuser_cmpxchg32_fixup:
 	mov	r7, #0xffff0fff
 	sub	r7, r7, #(0xffff0fff - (0xffff0fc0 + (1b - __kuser_cmpxchg)))
 	subs	r8, r4, r7
-	rsbcss	r8, r8, #(2b - 1b)
+	rsbscs	r8, r8, #(2b - 1b)
 	strcs	r7, [sp, #S_PC]
 	ret	lr
 	.previous

arch/arm/kernel/entry-common.S

@@ -373,7 +373,7 @@ sys_syscall:
 		movhs	scno, #0
 		csdb
 #endif
-		stmloia	sp, {r5, r6}		@ shuffle args
+		stmialo	sp, {r5, r6}		@ shuffle args
 		movlo	r0, r1
 		movlo	r1, r2
 		movlo	r2, r3

arch/arm/kernel/entry-header.S

@@ -127,7 +127,8 @@
          */
 	.macro	v7m_exception_slow_exit ret_r0
 	cpsid	i
-	ldr	lr, =EXC_RET_THREADMODE_PROCESSSTACK
+	ldr	lr, =exc_ret
+	ldr	lr, [lr]
 
 	@ read original r12, sp, lr, pc and xPSR
 	add	r12, sp, #S_IP
@@ -387,8 +388,8 @@
 	badr	lr, \ret			@ return address
 	.if	\reload
 	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
-	ldmccia	r1, {r0 - r6}			@ reload r0-r6
+	ldmiacc	r1, {r0 - r6}			@ reload r0-r6
-	stmccia	sp, {r4, r5}			@ update stack arguments
+	stmiacc	sp, {r4, r5}			@ update stack arguments
 	.endif
 	ldrcc	pc, [\table, \tmp, lsl #2]	@ call sys_* routine
 #else
@@ -396,8 +397,8 @@
 	badr	lr, \ret			@ return address
 	.if	\reload
 	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
-	ldmccia	r1, {r0 - r6}			@ reload r0-r6
+	ldmiacc	r1, {r0 - r6}			@ reload r0-r6
-	stmccia	sp, {r4, r5}			@ update stack arguments
+	stmiacc	sp, {r4, r5}			@ update stack arguments
 	.endif
 	ldrcc	pc, [\table, \nr, lsl #2]	@ call sys_* routine
 #endif

arch/arm/kernel/entry-v7m.S

@@ -146,3 +146,7 @@ ENTRY(vector_table)
 	.rept	CONFIG_CPU_V7M_NUM_IRQ
 	.long	__irq_entry		@ External Interrupts
 	.endr
+	.align	2
+	.globl	exc_ret
+exc_ret:
+	.space	4

arch/arm/kernel/head-nommu.S

@@ -439,8 +439,8 @@ M_CLASS(str	r6, [r12, #PMSAv8_RLAR_A(3)])
 	str	r5, [r12, #PMSAv8_RBAR_A(0)]
 	str	r6, [r12, #PMSAv8_RLAR_A(0)]
 #else
-	mcr	p15, 0, r5, c6, c10, 1			@ PRBAR4
+	mcr	p15, 0, r5, c6, c10, 0			@ PRBAR4
-	mcr	p15, 0, r6, c6, c10, 2			@ PRLAR4
+	mcr	p15, 0, r6, c6, c10, 1			@ PRLAR4
 #endif
 #endif
 	ret	lr

arch/arm/kernel/hyp-stub.S

@@ -180,8 +180,8 @@ ARM_BE8(orr	r7, r7, #(1 << 25))     @ HSCTLR.EE
 	@ Check whether GICv3 system registers are available
 	mrc	p15, 0, r7, c0, c1, 1	@ ID_PFR1
 	ubfx	r7, r7, #28, #4
-	cmp	r7, #1
+	teq	r7, #0
-	bne	2f
+	beq	2f
 
 	@ Enable system register accesses
 	mrc	p15, 4, r7, c12, c9, 5	@ ICC_HSRE

arch/arm/kernel/machine_kexec.c

@@ -91,8 +91,11 @@ void machine_crash_nonpanic_core(void *unused)
 
 	set_cpu_online(smp_processor_id(), false);
 	atomic_dec(&waiting_for_crash_ipi);
-	while (1)
+
+	while (1) {
 		cpu_relax();
+		wfe();
+	}
 }
 
 void crash_smp_send_stop(void)

arch/arm/kernel/patch.c

@@ -16,7 +16,7 @@ struct patch {
 	unsigned int insn;
 };
 
-static DEFINE_SPINLOCK(patch_lock);
+static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
 	__acquires(&patch_lock)
@@ -33,7 +33,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
 		return addr;
 
 	if (flags)
-		spin_lock_irqsave(&patch_lock, *flags);
+		raw_spin_lock_irqsave(&patch_lock, *flags);
 	else
 		__acquire(&patch_lock);
 
@@ -48,7 +48,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
 	clear_fixmap(fixmap);
 
 	if (flags)
-		spin_unlock_irqrestore(&patch_lock, *flags);
+		raw_spin_unlock_irqrestore(&patch_lock, *flags);
 	else
 		__release(&patch_lock);
 }

arch/arm/kernel/sleep.S

@@ -120,6 +120,14 @@ ENDPROC(cpu_resume_after_mmu)
 	.text
 	.align
 
+#ifdef CONFIG_MCPM
+	.arm
+THUMB(	.thumb			)
+ENTRY(cpu_resume_no_hyp)
+ARM_BE8(setend be)			@ ensure we are in BE mode
+	b	no_hyp
+#endif
+
 #ifdef CONFIG_MMU
 	.arm
 ENTRY(cpu_resume_arm)
@@ -135,6 +143,7 @@ ARM_BE8(setend be)			@ ensure we are in BE mode
 	bl	__hyp_stub_install_secondary
 #endif
 	safe_svcmode_maskall r1
+no_hyp:
 	mov	r1, #0
 	ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
 	ALT_UP_B(1f)
@@ -163,6 +172,9 @@ ENDPROC(cpu_resume)
 
 #ifdef CONFIG_MMU
 ENDPROC(cpu_resume_arm)
+#endif
+#ifdef CONFIG_MCPM
+ENDPROC(cpu_resume_no_hyp)
 #endif
 
 	.align 2

arch/arm/kernel/smp.c

@@ -62,12 +62,6 @@
  */
 struct secondary_data secondary_data;
 
-/*
- * control for which core is the next to come out of the secondary
- * boot "holding pen"
- */
-volatile int pen_release = -1;
-
 enum ipi_msg_type {
 	IPI_WAKEUP,
 	IPI_TIMER,
@@ -604,8 +598,10 @@ static void ipi_cpu_stop(unsigned int cpu)
 	local_fiq_disable();
 	local_irq_disable();
 
-	while (1)
+	while (1) {
 		cpu_relax();
+		wfe();
+	}
 }
 
 static DEFINE_PER_CPU(struct completion *, cpu_completion);

arch/arm/kernel/smp_twd.c

@@ -100,8 +100,6 @@ static void twd_timer_stop(void)
 	disable_percpu_irq(clk->irq);
 }
 
-#ifdef CONFIG_COMMON_CLK
-
 /*
  * Updates clockevent frequency when the cpu frequency changes.
  * Called on the cpu that is changing frequency with interrupts disabled.
@@ -143,54 +141,6 @@ static int twd_clk_init(void)
 }
 core_initcall(twd_clk_init);
 
-#elif defined (CONFIG_CPU_FREQ)
-
-#include <linux/cpufreq.h>
-
-/*
- * Updates clockevent frequency when the cpu frequency changes.
- * Called on the cpu that is changing frequency with interrupts disabled.
- */
-static void twd_update_frequency(void *data)
-{
-	twd_timer_rate = clk_get_rate(twd_clk);
-
-	clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate);
-}
-
-static int twd_cpufreq_transition(struct notifier_block *nb,
-	unsigned long state, void *data)
-{
-	struct cpufreq_freqs *freqs = data;
-
-	/*
-	 * The twd clock events must be reprogrammed to account for the new
-	 * frequency.  The timer is local to a cpu, so cross-call to the
-	 * changing cpu.
-	 */
-	if (state == CPUFREQ_POSTCHANGE)
-		smp_call_function_single(freqs->cpu, twd_update_frequency,
-			NULL, 1);
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block twd_cpufreq_nb = {
-	.notifier_call = twd_cpufreq_transition,
-};
-
-static int twd_cpufreq_init(void)
-{
-	if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
-		return cpufreq_register_notifier(&twd_cpufreq_nb,
-			CPUFREQ_TRANSITION_NOTIFIER);
-
-	return 0;
-}
-core_initcall(twd_cpufreq_init);
-
-#endif
-
 static void twd_calibrate_rate(void)
 {
 	unsigned long count;
@@ -366,21 +316,6 @@ static int __init twd_local_timer_common_register(struct device_node *np)
 	return err;
 }
 
-int __init twd_local_timer_register(struct twd_local_timer *tlt)
-{
-	if (twd_base || twd_evt)
-		return -EBUSY;
-
-	twd_ppi	= tlt->res[1].start;
-
-	twd_base = ioremap(tlt->res[0].start, resource_size(&tlt->res[0]));
-	if (!twd_base)
-		return -ENOMEM;
-
-	return twd_local_timer_common_register(NULL);
-}
-
-#ifdef CONFIG_OF
 static int __init twd_local_timer_of_register(struct device_node *np)
 {
 	int err;
@@ -406,4 +341,3 @@ static int __init twd_local_timer_of_register(struct device_node *np)
 TIMER_OF_DECLARE(arm_twd_a9, "arm,cortex-a9-twd-timer", twd_local_timer_of_register);
 TIMER_OF_DECLARE(arm_twd_a5, "arm,cortex-a5-twd-timer", twd_local_timer_of_register);
 TIMER_OF_DECLARE(arm_twd_11mp, "arm,arm11mp-twd-timer", twd_local_timer_of_register);
-#endif

arch/arm/kernel/unwind.c

@@ -93,7 +93,7 @@ extern const struct unwind_idx __start_unwind_idx[];
 static const struct unwind_idx *__origin_unwind_idx;
 extern const struct unwind_idx __stop_unwind_idx[];
 
-static DEFINE_SPINLOCK(unwind_lock);
+static DEFINE_RAW_SPINLOCK(unwind_lock);
 static LIST_HEAD(unwind_tables);
 
 /* Convert a prel31 symbol to an absolute address */
@@ -201,7 +201,7 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
 		/* module unwind tables */
 		struct unwind_table *table;
 
-		spin_lock_irqsave(&unwind_lock, flags);
+		raw_spin_lock_irqsave(&unwind_lock, flags);
 		list_for_each_entry(table, &unwind_tables, list) {
 			if (addr >= table->begin_addr &&
 			    addr < table->end_addr) {
@@ -213,7 +213,7 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr)
 				break;
 			}
 		}
-		spin_unlock_irqrestore(&unwind_lock, flags);
+		raw_spin_unlock_irqrestore(&unwind_lock, flags);
 	}
 
 	pr_debug("%s: idx = %p\n", __func__, idx);
@@ -529,9 +529,9 @@ struct unwind_table *unwind_table_add(unsigned long start, unsigned long size,
 	tab->begin_addr = text_addr;
 	tab->end_addr = text_addr + text_size;
 
-	spin_lock_irqsave(&unwind_lock, flags);
+	raw_spin_lock_irqsave(&unwind_lock, flags);
 	list_add_tail(&tab->list, &unwind_tables);
-	spin_unlock_irqrestore(&unwind_lock, flags);
+	raw_spin_unlock_irqrestore(&unwind_lock, flags);
 
 	return tab;
 }
@@ -543,9 +543,9 @@ void unwind_table_del(struct unwind_table *tab)
 	if (!tab)
 		return;
 
-	spin_lock_irqsave(&unwind_lock, flags);
+	raw_spin_lock_irqsave(&unwind_lock, flags);
 	list_del(&tab->list);
-	spin_unlock_irqrestore(&unwind_lock, flags);
+	raw_spin_unlock_irqrestore(&unwind_lock, flags);
 
 	kfree(tab);
 }

arch/arm/kvm/Makefile

@@ -8,9 +8,8 @@ ifeq ($(plus_virt),+virt)
 	plus_virt_def := -DREQUIRES_VIRT=1
 endif
 
-ccflags-y += -Iarch/arm/kvm -Ivirt/kvm/arm/vgic
+ccflags-y += -I $(srctree)/$(src) -I $(srctree)/virt/kvm/arm/vgic
-CFLAGS_arm.o := -I. $(plus_virt_def)
+CFLAGS_arm.o := $(plus_virt_def)
-CFLAGS_mmu.o := -I.
 
 AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt)
 AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)

arch/arm/kvm/coproc.c

@@ -293,15 +293,16 @@ static bool access_cntp_tval(struct kvm_vcpu *vcpu,
 			     const struct coproc_params *p,
 			     const struct coproc_reg *r)
 {
-	u64 now = kvm_phys_timer_read();
+	u32 val;
-	u64 val;
 
 	if (p->is_write) {
 		val = *vcpu_reg(vcpu, p->Rt1);
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, val + now);
+		kvm_arm_timer_write_sysreg(vcpu,
+					   TIMER_PTIMER, TIMER_REG_TVAL, val);
 	} else {
-		val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
+		val = kvm_arm_timer_read_sysreg(vcpu,
-		*vcpu_reg(vcpu, p->Rt1) = val - now;
+						TIMER_PTIMER, TIMER_REG_TVAL);
+		*vcpu_reg(vcpu, p->Rt1) = val;
 	}
 
 	return true;
@@ -315,9 +316,11 @@ static bool access_cntp_ctl(struct kvm_vcpu *vcpu,
 
 	if (p->is_write) {
 		val = *vcpu_reg(vcpu, p->Rt1);
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CTL, val);
+		kvm_arm_timer_write_sysreg(vcpu,
+					   TIMER_PTIMER, TIMER_REG_CTL, val);
 	} else {
-		val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CTL);
+		val = kvm_arm_timer_read_sysreg(vcpu,
+						TIMER_PTIMER, TIMER_REG_CTL);
 		*vcpu_reg(vcpu, p->Rt1) = val;
 	}
 
@@ -333,9 +336,11 @@ static bool access_cntp_cval(struct kvm_vcpu *vcpu,
 	if (p->is_write) {
 		val = (u64)*vcpu_reg(vcpu, p->Rt2) << 32;
 		val |= *vcpu_reg(vcpu, p->Rt1);
-		kvm_arm_timer_set_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL, val);
+		kvm_arm_timer_write_sysreg(vcpu,
+					   TIMER_PTIMER, TIMER_REG_CVAL, val);
 	} else {
-		val = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_PTIMER_CVAL);
+		val = kvm_arm_timer_read_sysreg(vcpu,
+						TIMER_PTIMER, TIMER_REG_CVAL);
 		*vcpu_reg(vcpu, p->Rt1) = val;
 		*vcpu_reg(vcpu, p->Rt2) = val >> 32;
 	}

arch/arm/kvm/hyp/cp15-sr.c

@@ -27,7 +27,6 @@ static u64 *cp15_64(struct kvm_cpu_context *ctxt, int idx)
 
 void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt->cp15[c0_MPIDR]		= read_sysreg(VMPIDR);
 	ctxt->cp15[c0_CSSELR]		= read_sysreg(CSSELR);
 	ctxt->cp15[c1_SCTLR]		= read_sysreg(SCTLR);
 	ctxt->cp15[c1_CPACR]		= read_sysreg(CPACR);

arch/arm/kvm/hyp/hyp-entry.S

@@ -176,7 +176,7 @@ THUMB(	orr	lr, lr, #PSR_T_BIT	)
 	msr	spsr_cxsf, lr
 	ldr	lr, =panic
 	msr	ELR_hyp, lr
-	ldr	lr, =kvm_call_hyp
+	ldr	lr, =__kvm_call_hyp
 	clrex
 	eret
 ENDPROC(__hyp_do_panic)

arch/arm/kvm/hyp/switch.c

@@ -77,7 +77,7 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
-	write_sysreg(kvm->arch.vttbr, VTTBR);
+	write_sysreg(kvm_get_vttbr(kvm), VTTBR);
 	write_sysreg(vcpu->arch.midr, VPIDR);
 }
 

arch/arm/kvm/hyp/tlb.c

@@ -41,7 +41,7 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	write_sysreg(kvm->arch.vttbr, VTTBR);
+	write_sysreg(kvm_get_vttbr(kvm), VTTBR);
 	isb();
 
 	write_sysreg(0, TLBIALLIS);
@@ -61,7 +61,7 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
 
 	/* Switch to requested VMID */
-	write_sysreg(kvm->arch.vttbr, VTTBR);
+	write_sysreg(kvm_get_vttbr(kvm), VTTBR);
 	isb();
 
 	write_sysreg(0, TLBIALL);

arch/arm/kvm/interrupts.S

@@ -42,7 +42,7 @@
  *   r12:     caller save
  *   rest:    callee save
  */
-ENTRY(kvm_call_hyp)
+ENTRY(__kvm_call_hyp)
 	hvc	#0
 	bx	lr
-ENDPROC(kvm_call_hyp)
+ENDPROC(__kvm_call_hyp)

arch/arm/lib/Makefile

@@ -39,7 +39,7 @@ $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
 
 ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
-  NEON_FLAGS			:= -mfloat-abi=softfp -mfpu=neon
+  NEON_FLAGS			:= -march=armv7-a -mfloat-abi=softfp -mfpu=neon
   CFLAGS_xor-neon.o		+= $(NEON_FLAGS)
   obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
 endif

arch/arm/lib/bitops.h

@@ -7,7 +7,7 @@
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
 	and	r3, r0, #31		@ Get bit offset
 	mov	r0, r0, lsr #5
@@ -32,7 +32,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
 	and	r3, r0, #31		@ Get bit offset
 	mov	r0, r0, lsr #5
@@ -62,7 +62,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	and	r2, r0, #31
 	mov	r0, r0, lsr #5
 	mov	r3, #1
@@ -89,7 +89,7 @@ ENDPROC(\name		)
 ENTRY(	\name		)
 UNWIND(	.fnstart	)
 	ands	ip, r1, #3
-	strneb	r1, [ip]		@ assert word-aligned
+	strbne	r1, [ip]		@ assert word-aligned
 	and	r3, r0, #31
 	mov	r0, r0, lsr #5
 	save_and_disable_irqs ip

arch/arm/lib/clear_user.S

@@ -44,7 +44,7 @@ UNWIND(.save {r1, lr})
 		strusr	r2, r0, 1, ne, rept=2
 		tst	r1, #1			@ x1 x0 x1 x0 x1 x0 x1
 		it	ne			@ explicit IT needed for the label
-USER(		strnebt	r2, [r0])
+USER(		strbtne	r2, [r0])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
 UNWIND(.fnend)

arch/arm/lib/copy_from_user.S

@@ -91,7 +91,7 @@
 	.endm
 
 	.macro str1b ptr reg cond=al abort
-	str\cond\()b \reg, [\ptr], #1
+	strb\cond \reg, [\ptr], #1
 	.endm
 
 	.macro enter reg1 reg2

arch/arm/lib/copy_page.S

@@ -39,9 +39,9 @@ ENTRY(copy_page)
 	.endr
 		subs	r2, r2, #1			@	1
 		stmia	r0!, {r3, r4, ip, lr}		@	4
-		ldmgtia	r1!, {r3, r4, ip, lr}		@	4
+		ldmiagt	r1!, {r3, r4, ip, lr}		@	4
 		bgt	1b				@	1
-	PLD(	ldmeqia r1!, {r3, r4, ip, lr}	)
+	PLD(	ldmiaeq r1!, {r3, r4, ip, lr}	)
 	PLD(	beq	2b			)
 		ldmfd	sp!, {r4, pc}			@	3
 ENDPROC(copy_page)