Linux 5.15

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix compilation of callchain related code on powerpc with gcc11+

 - Fix PERF_SAMPLE_WEIGHT_STRUCT support in 'perf script'

 - Check session->header.env.arch before using it, fixing a segmentation
   fault

 - Suppress 'rm dlfilter' build messages

* tag 'perf-tools-fixes-for-v5.15-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf script: Fix PERF_SAMPLE_WEIGHT_STRUCT support
  perf callchain: Fix compilation on powerpc with gcc11+
  perf script: Check session->header.env.arch before using it
  perf build: Suppress 'rm dlfilter' build message

.mailmap

@@ -33,6 +33,8 @@ Al Viro <viro@zenIV.linux.org.uk>
 Andi Kleen <ak@linux.intel.com> <ak@suse.de>
 Andi Shyti <andi@etezian.org> <andi.shyti@samsung.com>
 Andreas Herrmann <aherrman@de.ibm.com>
+Andrej Shadura <andrew.shadura@collabora.co.uk>
+Andrej Shadura <andrew@shadura.me> <andrew@beldisplaytech.com>
 Andrew Morton <akpm@linux-foundation.org>
 Andrew Murray <amurray@thegoodpenguin.co.uk> <amurray@embedded-bits.co.uk>
 Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com>

Documentation/admin-guide/cgroup-v2.rst

@@ -1226,7 +1226,7 @@ PAGE_SIZE multiple when read back.
 
 	Note that all fields in this file are hierarchical and the
 	file modified event can be generated due to an event down the
-	hierarchy. For for the local events at the cgroup level see
+	hierarchy. For the local events at the cgroup level see
 	memory.events.local.
 
 	  low
@@ -2170,19 +2170,19 @@ existing device files.
 
 Cgroup v2 device controller has no interface files and is implemented
 on top of cgroup BPF. To control access to device files, a user may
-create bpf programs of the BPF_CGROUP_DEVICE type and attach them
-to cgroups. On an attempt to access a device file, corresponding
-BPF programs will be executed, and depending on the return value
-the attempt will succeed or fail with -EPERM.
+create bpf programs of type BPF_PROG_TYPE_CGROUP_DEVICE and attach
+them to cgroups with BPF_CGROUP_DEVICE flag. On an attempt to access a
+device file, corresponding BPF programs will be executed, and depending
+on the return value the attempt will succeed or fail with -EPERM.
 
-A BPF_CGROUP_DEVICE program takes a pointer to the bpf_cgroup_dev_ctx
-structure, which describes the device access attempt: access type
-(mknod/read/write) and device (type, major and minor numbers).
-If the program returns 0, the attempt fails with -EPERM, otherwise
-it succeeds.
+A BPF_PROG_TYPE_CGROUP_DEVICE program takes a pointer to the
+bpf_cgroup_dev_ctx structure, which describes the device access attempt:
+access type (mknod/read/write) and device (type, major and minor numbers).
+If the program returns 0, the attempt fails with -EPERM, otherwise it
+succeeds.
 
-An example of BPF_CGROUP_DEVICE program may be found in the kernel
-source tree in the tools/testing/selftests/bpf/progs/dev_cgroup.c file.
+An example of BPF_PROG_TYPE_CGROUP_DEVICE program may be found in
+tools/testing/selftests/bpf/progs/dev_cgroup.c in the kernel source tree.
 
 
 RDMA

Documentation/devicetree/bindings/mfd/brcm,cru.yaml

@@ -32,13 +32,13 @@ properties:
   "#size-cells":
     const: 1
 
-  pinctrl:
-    $ref: ../pinctrl/brcm,ns-pinmux.yaml
-
 patternProperties:
   '^clock-controller@[a-f0-9]+$':
     $ref: ../clock/brcm,iproc-clocks.yaml
 
+  '^pin-controller@[a-f0-9]+$':
+    $ref: ../pinctrl/brcm,ns-pinmux.yaml
+
   '^thermal@[a-f0-9]+$':
     $ref: ../thermal/brcm,ns-thermal.yaml
 
@@ -73,9 +73,10 @@ examples:
                                  "iprocfast", "sata1", "sata2";
         };
 
-        pinctrl {
+        pin-controller@1c0 {
             compatible = "brcm,bcm4708-pinmux";
-            offset = <0x1c0>;
+            reg = <0x1c0 0x24>;
+            reg-names = "cru_gpio_control";
         };
 
         thermal@2c0 {

Documentation/devicetree/bindings/net/snps,dwmac.yaml

@@ -21,6 +21,7 @@ select:
       contains:
         enum:
           - snps,dwmac
+          - snps,dwmac-3.40a
           - snps,dwmac-3.50a
           - snps,dwmac-3.610
           - snps,dwmac-3.70a
@@ -76,6 +77,7 @@ properties:
         - rockchip,rk3399-gmac
         - rockchip,rv1108-gmac
         - snps,dwmac
+        - snps,dwmac-3.40a
         - snps,dwmac-3.50a
         - snps,dwmac-3.610
         - snps,dwmac-3.70a

Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml

@@ -17,9 +17,6 @@ description:
 
   A list of pins varies across chipsets so few bindings are available.
 
-  Node of the pinmux must be nested in the CRU (Central Resource Unit) "syscon"
-  node.
-
 properties:
   compatible:
     enum:
@@ -27,10 +24,11 @@ properties:
       - brcm,bcm4709-pinmux
       - brcm,bcm53012-pinmux
 
-  offset:
-    description: offset of pin registers in the CRU block
+  reg:
     maxItems: 1
-    $ref: /schemas/types.yaml#/definitions/uint32-array
+
+  reg-names:
+    const: cru_gpio_control
 
 patternProperties:
   '-pins$':
@@ -72,23 +70,20 @@ allOf:
                         uart1_grp ]
 
 required:
-  - offset
+  - reg
+  - reg-names
 
 additionalProperties: false
 
 examples:
   - |
-    cru@1800c100 {
-        compatible = "syscon", "simple-mfd";
-        reg = <0x1800c100 0x1a4>;
+    pin-controller@1800c1c0 {
+        compatible = "brcm,bcm4708-pinmux";
+        reg = <0x1800c1c0 0x24>;
+        reg-names = "cru_gpio_control";
 
-        pinctrl {
-            compatible = "brcm,bcm4708-pinmux";
-            offset = <0xc0>;
-
-            spi-pins {
-                function = "spi";
-                groups = "spi_grp";
-            };
+        spi-pins {
+            function = "spi";
+            groups = "spi_grp";
         };
     };

Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml

@@ -171,7 +171,7 @@ examples:
       cs-gpios = <&gpio0 13 0>,
                  <&gpio0 14 0>;
       rx-sample-delay-ns = <3>;
-      spi-flash@1 {
+      flash@1 {
         compatible = "spi-nand";
         reg = <1>;
         rx-sample-delay-ns = <7>;

Documentation/filesystems/ntfs3.rst

@@ -4,103 +4,112 @@
 NTFS3
 =====
 
-
 Summary and Features
 ====================
 
-NTFS3 is fully functional NTFS Read-Write driver. The driver works with
-NTFS versions up to 3.1, normal/compressed/sparse files
-and journal replaying. File system type to use on mount is 'ntfs3'.
+NTFS3 is fully functional NTFS Read-Write driver. The driver works with NTFS
+versions up to 3.1. File system type to use on mount is *ntfs3*.
 
 - This driver implements NTFS read/write support for normal, sparse and
   compressed files.
-- Supports native journal replaying;
-- Supports extended attributes
-	Predefined extended attributes:
-	- 'system.ntfs_security' gets/sets security
-			descriptor (SECURITY_DESCRIPTOR_RELATIVE)
-	- 'system.ntfs_attrib' gets/sets ntfs file/dir attributes.
-		Note: applied to empty files, this allows to switch type between
-		sparse(0x200), compressed(0x800) and normal;
+- Supports native journal replaying.
 - Supports NFS export of mounted NTFS volumes.
+- Supports extended attributes. Predefined extended attributes:
+
+	- *system.ntfs_security* gets/sets security
+
+		Descriptor: SECURITY_DESCRIPTOR_RELATIVE
+
+	- *system.ntfs_attrib* gets/sets ntfs file/dir attributes.
+
+	  Note: Applied to empty files, this allows to switch type between
+	  sparse(0x200), compressed(0x800) and normal.
 
 Mount Options
 =============
 
 The list below describes mount options supported by NTFS3 driver in addition to
-generic ones.
+generic ones. You can use every mount option with **no** option. If it is in
+this table marked with no it means default is without **no**.
 
-===============================================================================
+.. flat-table::
+   :widths: 1 5
+   :fill-cells:
 
-nls=name		This option informs the driver how to interpret path
-			strings and translate them to Unicode and back. If
-			this option is not set, the default codepage will be
-			used (CONFIG_NLS_DEFAULT).
-			Examples:
-				'nls=utf8'
+   * - iocharset=name
+     - This option informs the driver how to interpret path strings and
+       translate them to Unicode and back. If this option is not set, the
+       default codepage will be used (CONFIG_NLS_DEFAULT).
 
-uid=
-gid=
-umask=			Controls the default permissions for files/directories created
-			after the NTFS volume is mounted.
+       Example: iocharset=utf8
 
-fmask=
-dmask=			Instead of specifying umask which applies both to
-			files and directories, fmask applies only to files and
-			dmask only to directories.
+   * - uid=
+     - :rspan:`1`
+   * - gid=
 
-nohidden		Files with the Windows-specific HIDDEN (FILE_ATTRIBUTE_HIDDEN)
-			attribute will not be shown under Linux.
+   * - umask=
+     - Controls the default permissions for files/directories created after
+       the NTFS volume is mounted.
 
-sys_immutable		Files with the Windows-specific SYSTEM
-			(FILE_ATTRIBUTE_SYSTEM) attribute will be marked as system
-			immutable files.
+   * - dmask=
+     - :rspan:`1` Instead of specifying umask which applies both to files and
+       directories, fmask applies only to files and dmask only to directories.
+   * - fmask=
 
-discard			Enable support of the TRIM command for improved performance
-			on delete operations, which is recommended for use with the
-			solid-state drives (SSD).
+   * - noacsrules
+     - "No access rules" mount option sets access rights for files/folders to
+       777 and owner/group to root. This mount option absorbs all other
+       permissions.
 
-force			Forces the driver to mount partitions even if 'dirty' flag
-			(volume dirty) is set. Not recommended for use.
+       - Permissions change for files/folders will be reported as successful,
+	 but they will remain 777.
 
-sparse			Create new files as "sparse".
+       - Owner/group change will be reported as successful, butthey will stay
+	 as root.
 
-showmeta		Use this parameter to show all meta-files (System Files) on
-			a mounted NTFS partition.
-			By default, all meta-files are hidden.
+   * - nohidden
+     - Files with the Windows-specific HIDDEN (FILE_ATTRIBUTE_HIDDEN) attribute
+       will not be shown under Linux.
 
-prealloc		Preallocate space for files excessively when file size is
-			increasing on writes. Decreases fragmentation in case of
-			parallel write operations to different files.
+   * - sys_immutable
+     - Files with the Windows-specific SYSTEM (FILE_ATTRIBUTE_SYSTEM) attribute
+       will be marked as system immutable files.
 
-no_acs_rules		"No access rules" mount option sets access rights for
-			files/folders to 777 and owner/group to root. This mount
-			option absorbs all other permissions:
-			- permissions change for files/folders will be reported
-				as successful, but they will remain 777;
-			- owner/group change will be reported as successful, but
-				they will stay as root
+   * - discard
+     - Enable support of the TRIM command for improved performance on delete
+       operations, which is recommended for use with the solid-state drives
+       (SSD).
 
-acl			Support POSIX ACLs (Access Control Lists). Effective if
-			supported by Kernel. Not to be confused with NTFS ACLs.
-			The option specified as acl enables support for POSIX ACLs.
+   * - force
+     - Forces the driver to mount partitions even if volume is marked dirty.
+       Not recommended for use.
 
-noatime			All files and directories will not update their last access
-			time attribute if a partition is mounted with this parameter.
-			This option can speed up file system operation.
+   * - sparse
+     - Create new files as sparse.
 
-===============================================================================
+   * - showmeta
+     - Use this parameter to show all meta-files (System Files) on a mounted
+       NTFS partition. By default, all meta-files are hidden.
 
-ToDo list
+   * - prealloc
+     - Preallocate space for files excessively when file size is increasing on
+       writes. Decreases fragmentation in case of parallel write operations to
+       different files.
+
+   * - acl
+     - Support POSIX ACLs (Access Control Lists). Effective if supported by
+       Kernel. Not to be confused with NTFS ACLs. The option specified as acl
+       enables support for POSIX ACLs.
+
+Todo list
 =========
-
-- Full journaling support (currently journal replaying is supported) over JBD.
-
+- Full journaling support over JBD. Currently journal replaying is supported
+  which is not necessarily as effectice as JBD would be.
 
 References
 ==========
-https://www.paragon-software.com/home/ntfs-linux-professional/
-	- Commercial version of the NTFS driver for Linux.
+- Commercial version of the NTFS driver for Linux.
+	https://www.paragon-software.com/home/ntfs-linux-professional/
 
-almaz.alexandrovich@paragon-software.com
-	- Direct e-mail address for feedback and requests on the NTFS3 implementation.
+- Direct e-mail address for feedback and requests on the NTFS3 implementation.
+	almaz.alexandrovich@paragon-software.com

Documentation/networking/devlink/ice.rst

@@ -30,10 +30,11 @@ The ``ice`` driver reports the following versions
         PHY, link, etc.
     * - ``fw.mgmt.api``
       - running
-      - 1.5
-      - 2-digit version number of the API exported over the AdminQ by the
-        management firmware. Used by the driver to identify what commands
-        are supported.
+      - 1.5.1
+      - 3-digit version number (major.minor.patch) of the API exported over
+        the AdminQ by the management firmware. Used by the driver to
+        identify what commands are supported. Historical versions of the
+        kernel only displayed a 2-digit version number (major.minor).
     * - ``fw.mgmt.build``
       - running
       - 0x305d955f

Documentation/networking/mctp.rst

@@ -59,11 +59,11 @@ specified with a ``sockaddr`` type, with a single-byte endpoint address:
     };
 
     struct sockaddr_mctp {
-            unsigned short int	smctp_family;
-            int			smctp_network;
-            struct mctp_addr	smctp_addr;
-            __u8		smctp_type;
-            __u8		smctp_tag;
+            __kernel_sa_family_t smctp_family;
+            unsigned int         smctp_network;
+            struct mctp_addr     smctp_addr;
+            __u8                 smctp_type;
+            __u8                 smctp_tag;
     };
 
     #define MCTP_NET_ANY	0x0

Documentation/userspace-api/ioctl/ioctl-number.rst

@@ -104,6 +104,7 @@ Code  Seq#    Include File                                           Comments
 '8'   all                                                            SNP8023 advanced NIC card
                                                                      <mailto:mcr@solidum.com>
 ';'   64-7F  linux/vfio.h
+'='   00-3f  uapi/linux/ptp_clock.h                                  <mailto:richardcochran@gmail.com>
 '@'   00-0F  linux/radeonfb.h                                        conflict!
 '@'   00-0F  drivers/video/aty/aty128fb.c                            conflict!
 'A'   00-1F  linux/apm_bios.h                                        conflict!

Documentation/userspace-api/vduse.rst

@@ -18,7 +18,7 @@ types can be added after the security issue of corresponding device driver
 is clarified or fixed in the future.
 
 Create/Destroy VDUSE devices
-------------------------
+----------------------------
 
 VDUSE devices are created as follows:
 

MAINTAINERS

@@ -5458,6 +5458,19 @@ F:	include/net/devlink.h
 F:	include/uapi/linux/devlink.h
 F:	net/core/devlink.c
 
+DH ELECTRONICS IMX6 DHCOM BOARD SUPPORT
+M:	Christoph Niedermaier <cniedermaier@dh-electronics.com>
+L:	kernel@dh-electronics.com
+S:	Maintained
+F:	arch/arm/boot/dts/imx6*-dhcom-*
+
+DH ELECTRONICS STM32MP1 DHCOM/DHCOR BOARD SUPPORT
+M:	Marek Vasut <marex@denx.de>
+L:	kernel@dh-electronics.com
+S:	Maintained
+F:	arch/arm/boot/dts/stm32mp1*-dhcom-*
+F:	arch/arm/boot/dts/stm32mp1*-dhcor-*
+
 DIALOG SEMICONDUCTOR DRIVERS
 M:	Support Opensource <support.opensource@diasemi.com>
 S:	Supported
@@ -6147,8 +6160,7 @@ T:	git git://anongit.freedesktop.org/drm/drm
 F:	Documentation/devicetree/bindings/display/
 F:	Documentation/devicetree/bindings/gpu/
 F:	Documentation/gpu/
-F:	drivers/gpu/drm/
-F:	drivers/gpu/vga/
+F:	drivers/gpu/
 F:	include/drm/
 F:	include/linux/vga*
 F:	include/uapi/drm/
@@ -7343,10 +7355,11 @@ F:	include/uapi/linux/fpga-dfl.h
 
 FPGA MANAGER FRAMEWORK
 M:	Moritz Fischer <mdf@kernel.org>
+M:	Wu Hao <hao.wu@intel.com>
+M:	Xu Yilun <yilun.xu@intel.com>
 R:	Tom Rix <trix@redhat.com>
 L:	linux-fpga@vger.kernel.org
 S:	Maintained
-W:	http://www.rocketboards.org
 Q:	http://patchwork.kernel.org/project/linux-fpga/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mdf/linux-fpga.git
 F:	Documentation/devicetree/bindings/fpga/
@@ -7440,7 +7453,7 @@ FREESCALE IMX / MXC FEC DRIVER
 M:	Joakim Zhang <qiangqing.zhang@nxp.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
-F:	Documentation/devicetree/bindings/net/fsl-fec.txt
+F:	Documentation/devicetree/bindings/net/fsl,fec.yaml
 F:	drivers/net/ethernet/freescale/fec.h
 F:	drivers/net/ethernet/freescale/fec_main.c
 F:	drivers/net/ethernet/freescale/fec_ptp.c
@@ -9307,7 +9320,7 @@ S:	Maintained
 F:	drivers/platform/x86/intel/atomisp2/led.c
 
 INTEL BIOS SAR INT1092 DRIVER
-M:	Shravan S <s.shravan@intel.com>
+M:	Shravan Sudhakar <s.shravan@intel.com>
 M:	Intel Corporation <linuxwwan@intel.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
@@ -9629,7 +9642,7 @@ F:	include/uapi/linux/isst_if.h
 F:	tools/power/x86/intel-speed-select/
 
 INTEL STRATIX10 FIRMWARE DRIVERS
-M:	Richard Gong <richard.gong@linux.intel.com>
+M:	Dinh Nguyen <dinguyen@kernel.org>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-devices-platform-stratix10-rsu
@@ -10279,7 +10292,6 @@ KERNEL VIRTUAL MACHINE for s390 (KVM/s390)
 M:	Christian Borntraeger <borntraeger@de.ibm.com>
 M:	Janosch Frank <frankja@linux.ibm.com>
 R:	David Hildenbrand <david@redhat.com>
-R:	Cornelia Huck <cohuck@redhat.com>
 R:	Claudio Imbrenda <imbrenda@linux.ibm.com>
 L:	kvm@vger.kernel.org
 S:	Supported
@@ -11153,6 +11165,7 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/net/dsa/marvell.txt
 F:	Documentation/networking/devlink/mv88e6xxx.rst
 F:	drivers/net/dsa/mv88e6xxx/
+F:	include/linux/dsa/mv88e6xxx.h
 F:	include/linux/platform_data/mv88e6xxx.h
 
 MARVELL ARMADA 3700 PHY DRIVERS
@@ -11277,7 +11290,6 @@ F:	Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
 F:	drivers/net/ethernet/marvell/octeontx2/af/
 
 MARVELL PRESTERA ETHERNET SWITCH DRIVER
-M:	Vadym Kochan <vkochan@marvell.com>
 M:	Taras Chornyi <tchornyi@marvell.com>
 S:	Supported
 W:	https://github.com/Marvell-switching/switchdev-prestera
@@ -16301,6 +16313,7 @@ S390
 M:	Heiko Carstens <hca@linux.ibm.com>
 M:	Vasily Gorbik <gor@linux.ibm.com>
 M:	Christian Borntraeger <borntraeger@de.ibm.com>
+R:	Alexander Gordeev <agordeev@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
 W:	http://www.ibm.com/developerworks/linux/linux390/
@@ -16379,7 +16392,6 @@ F:	drivers/s390/crypto/vfio_ap_ops.c
 F:	drivers/s390/crypto/vfio_ap_private.h
 
 S390 VFIO-CCW DRIVER
-M:	Cornelia Huck <cohuck@redhat.com>
 M:	Eric Farman <farman@linux.ibm.com>
 M:	Matthew Rosato <mjrosato@linux.ibm.com>
 R:	Halil Pasic <pasic@linux.ibm.com>
@@ -17986,7 +17998,7 @@ F:	net/switchdev/
 SY8106A REGULATOR DRIVER
 M:	Icenowy Zheng <icenowy@aosc.io>
 S:	Maintained
-F:	Documentation/devicetree/bindings/regulator/sy8106a-regulator.txt
+F:	Documentation/devicetree/bindings/regulator/silergy,sy8106a.yaml
 F:	drivers/regulator/sy8106a-regulator.c
 
 SYNC FILE FRAMEWORK
@@ -20335,6 +20347,7 @@ X86 ARCHITECTURE (32-BIT AND 64-BIT)
 M:	Thomas Gleixner <tglx@linutronix.de>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Borislav Petkov <bp@alien8.de>
+M:	Dave Hansen <dave.hansen@linux.intel.com>
 M:	x86@kernel.org
 R:	"H. Peter Anvin" <hpa@zytor.com>
 L:	linux-kernel@vger.kernel.org

Makefile

@@ -2,8 +2,8 @@
 VERSION = 5
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
-NAME = Opossums on Parade
+EXTRAVERSION =
+NAME = Trick or Treat
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"

arch/arc/include/asm/pgtable.h

@@ -26,11 +26,6 @@ extern char empty_zero_page[PAGE_SIZE];
 
 extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE);
 
-/* Macro to mark a page protection as uncacheable */
-#define pgprot_noncached(prot)	(__pgprot(pgprot_val(prot) & ~_PAGE_CACHEABLE))
-
-extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE);
-
 /* to cope with aliasing VIPT cache */
 #define HAVE_ARCH_UNMAPPED_AREA
 

arch/arm/Kconfig

@@ -92,6 +92,7 @@ config ARM
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
+	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_GCC_PLUGINS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
 	select HAVE_IRQ_TIME_ACCOUNTING

arch/arm/boot/compressed/decompress.c

@@ -47,7 +47,10 @@ extern char * strchrnul(const char *, int);
 #endif
 
 #ifdef CONFIG_KERNEL_XZ
+/* Prevent KASAN override of string helpers in decompressor */
+#undef memmove
 #define memmove memmove
+#undef memcpy
 #define memcpy memcpy
 #include "../../../../lib/decompress_unxz.c"
 #endif

arch/arm/boot/dts/bcm2711-rpi-4-b.dts

@@ -40,8 +40,8 @@
 		regulator-always-on;
 		regulator-settling-time-us = <5000>;
 		gpios = <&expgpio 4 GPIO_ACTIVE_HIGH>;
-		states = <1800000 0x1
-			  3300000 0x0>;
+		states = <1800000 0x1>,
+			 <3300000 0x0>;
 		status = "okay";
 	};
 
@@ -217,15 +217,16 @@
 };
 
 &pcie0 {
-	pci@1,0 {
+	pci@0,0 {
+		device_type = "pci";
 		#address-cells = <3>;
 		#size-cells = <2>;
 		ranges;
 
 		reg = <0 0 0 0 0>;
 
-		usb@1,0 {
-			reg = <0x10000 0 0 0 0>;
+		usb@0,0 {
+			reg = <0 0 0 0 0>;
 			resets = <&reset RASPBERRYPI_FIRMWARE_RESET_ID_USB>;
 		};
 	};

arch/arm/boot/dts/bcm2711.dtsi

@@ -300,6 +300,14 @@
 			status = "disabled";
 		};
 
+		vec: vec@7ec13000 {
+			compatible = "brcm,bcm2711-vec";
+			reg = <0x7ec13000 0x1000>;
+			clocks = <&clocks BCM2835_CLOCK_VEC>;
+			interrupts = <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
+			status = "disabled";
+		};
+
 		dvp: clock@7ef00000 {
 			compatible = "brcm,brcm2711-dvp";
 			reg = <0x7ef00000 0x10>;
@@ -532,8 +540,8 @@
 				compatible = "brcm,genet-mdio-v5";
 				reg = <0xe14 0x8>;
 				reg-names = "mdio";
-				#address-cells = <0x0>;
-				#size-cells = <0x1>;
+				#address-cells = <0x1>;
+				#size-cells = <0x0>;
 			};
 		};
 	};

arch/arm/boot/dts/bcm2835-common.dtsi

@@ -106,6 +106,14 @@
 			status = "okay";
 		};
 
+		vec: vec@7e806000 {
+			compatible = "brcm,bcm2835-vec";
+			reg = <0x7e806000 0x1000>;
+			clocks = <&clocks BCM2835_CLOCK_VEC>;
+			interrupts = <2 27>;
+			status = "disabled";
+		};
+
 		pixelvalve@7e807000 {
 			compatible = "brcm,bcm2835-pixelvalve2";
 			reg = <0x7e807000 0x100>;

arch/arm/boot/dts/bcm283x.dtsi

@@ -464,14 +464,6 @@
 			status = "disabled";
 		};
 
-		vec: vec@7e806000 {
-			compatible = "brcm,bcm2835-vec";
-			reg = <0x7e806000 0x1000>;
-			clocks = <&clocks BCM2835_CLOCK_VEC>;
-			interrupts = <2 27>;
-			status = "disabled";
-		};
-
 		usb: usb@7e980000 {
 			compatible = "brcm,bcm2835-usb";
 			reg = <0x7e980000 0x10000>;

arch/arm/boot/dts/spear3xx.dtsi

@@ -47,7 +47,7 @@
 		};
 
 		gmac: eth@e0800000 {
-			compatible = "st,spear600-gmac";
+			compatible = "snps,dwmac-3.40a";
 			reg = <0xe0800000 0x8000>;
 			interrupts = <23 22>;
 			interrupt-names = "macirq", "eth_wake_irq";

arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts

@@ -112,7 +112,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&gmac_rgmii_pins>;
 	phy-handle = <&phy1>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	status = "okay";
 };
 

arch/arm/configs/multi_v7_defconfig

@@ -197,7 +197,6 @@ CONFIG_PCI_EPF_TEST=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_OMAP_OCP2SCP=y
-CONFIG_SIMPLE_PM_BUS=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y

arch/arm/configs/oxnas_v6_defconfig

@@ -46,7 +46,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=64
-CONFIG_SIMPLE_PM_BUS=y
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_BLOCK=y

arch/arm/configs/shmobile_defconfig

@@ -40,7 +40,6 @@ CONFIG_PCI_RCAR_GEN2=y
 CONFIG_PCIE_RCAR_HOST=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_SIMPLE_PM_BUS=y
 CONFIG_MTD=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y

arch/arm/include/asm/uaccess.h

@@ -176,6 +176,7 @@ extern int __get_user_64t_4(void *);
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		unsigned int __ua_flags = uaccess_save_and_enable();	\
+		int __tmp_e;						\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
 			if (sizeof((x)) >= 8)				\
@@ -203,9 +204,10 @@ extern int __get_user_64t_4(void *);
 			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
+		__tmp_e = __e;						\
 		uaccess_restore(__ua_flags);				\
 		x = (typeof(*(p))) __r2;				\
-		__e;							\
+		__tmp_e;						\
 	})
 
 #define get_user(x, p)							\

arch/arm/kernel/head.S

@@ -253,7 +253,7 @@ __create_page_tables:
 	add	r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ORDER)
 	ldr	r6, =(_end - 1)
 	adr_l	r5, kernel_sec_start		@ _pa(kernel_sec_start)
-#ifdef CONFIG_CPU_ENDIAN_BE8
+#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
 	str	r8, [r5, #4]			@ Save physical start of kernel (BE)
 #else
 	str	r8, [r5]			@ Save physical start of kernel (LE)
@@ -266,7 +266,7 @@ __create_page_tables:
 	bls	1b
 	eor	r3, r3, r7			@ Remove the MMU flags
 	adr_l	r5, kernel_sec_end		@ _pa(kernel_sec_end)
-#ifdef CONFIG_CPU_ENDIAN_BE8
+#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
 	str	r3, [r5, #4]			@ Save physical end of kernel (BE)
 #else
 	str	r3, [r5]			@ Save physical end of kernel (LE)

arch/arm/kernel/traps.c

@@ -136,7 +136,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
 		for (p = first, i = 0; i < 8 && p < top; i++, p += 4) {
 			if (p >= bottom && p < top) {
 				unsigned long val;
-				if (get_kernel_nofault(val, (unsigned long *)p))
+				if (!get_kernel_nofault(val, (unsigned long *)p))
 					sprintf(str + i * 9, " %08lx", val);
 				else
 					sprintf(str + i * 9, " ????????");

arch/arm/kernel/vmlinux-xip.lds.S

@@ -40,6 +40,10 @@ SECTIONS
 		ARM_DISCARD
 		*(.alt.smp.init)
 		*(.pv_table)
+#ifndef CONFIG_ARM_UNWIND
+		*(.ARM.exidx) *(.ARM.exidx.*)
+		*(.ARM.extab) *(.ARM.extab.*)
+#endif
 	}
 
 	. = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR);
@@ -172,7 +176,7 @@ ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
 ASSERT((_end - __bss_start) >= 12288, ".bss too small for CONFIG_XIP_DEFLATED_DATA")
 #endif
 
-#ifdef CONFIG_ARM_MPU
+#if defined(CONFIG_ARM_MPU) && !defined(CONFIG_COMPILE_TEST)
 /*
  * Due to PMSAv7 restriction on base address and size we have to
  * enforce minimal alignment restrictions. It was seen that weaker

arch/arm/mach-imx/src.c

@@ -9,6 +9,7 @@
 #include <linux/iopoll.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/platform_device.h>
 #include <linux/reset-controller.h>
 #include <linux/smp.h>
 #include <asm/smp_plat.h>
@@ -81,11 +82,6 @@ static const struct reset_control_ops imx_src_ops = {
 	.reset = imx_src_reset_module,
 };
 
-static struct reset_controller_dev imx_reset_controller = {
-	.ops = &imx_src_ops,
-	.nr_resets = ARRAY_SIZE(sw_reset_bits),
-};
-
 static void imx_gpcv2_set_m_core_pgc(bool enable, u32 offset)
 {
 	writel_relaxed(enable, gpc_base + offset);
@@ -177,10 +173,6 @@ void __init imx_src_init(void)
 	src_base = of_iomap(np, 0);
 	WARN_ON(!src_base);
 
-	imx_reset_controller.of_node = np;
-	if (IS_ENABLED(CONFIG_RESET_CONTROLLER))
-		reset_controller_register(&imx_reset_controller);
-
 	/*
 	 * force warm reset sources to generate cold reset
 	 * for a more reliable restart
@@ -214,3 +206,33 @@ void __init imx7_src_init(void)
 	if (!gpc_base)
 		return;
 }
+
+static const struct of_device_id imx_src_dt_ids[] = {
+	{ .compatible = "fsl,imx51-src" },
+	{ /* sentinel */ }
+};
+
+static int imx_src_probe(struct platform_device *pdev)
+{
+	struct reset_controller_dev *rcdev;
+
+	rcdev = devm_kzalloc(&pdev->dev, sizeof(*rcdev), GFP_KERNEL);
+	if (!rcdev)
+		return -ENOMEM;
+
+	rcdev->ops = &imx_src_ops;
+	rcdev->dev = &pdev->dev;
+	rcdev->of_node = pdev->dev.of_node;
+	rcdev->nr_resets = ARRAY_SIZE(sw_reset_bits);
+
+	return devm_reset_controller_register(&pdev->dev, rcdev);
+}
+
+static struct platform_driver imx_src_driver = {
+	.driver = {
+		.name = "imx-src",
+		.of_match_table = imx_src_dt_ids,
+	},
+	.probe = imx_src_probe,
+};
+builtin_platform_driver(imx_src_driver);

arch/arm/mach-omap2/Kconfig

@@ -112,7 +112,6 @@ config ARCH_OMAP2PLUS
 	select PM_GENERIC_DOMAINS
 	select PM_GENERIC_DOMAINS_OF
 	select RESET_CONTROLLER
-	select SIMPLE_PM_BUS
 	select SOC_BUS
 	select TI_SYSC
 	select OMAP_IRQCHIP

arch/arm/mm/proc-macros.S

@@ -340,6 +340,7 @@ ENTRY(\name\()_cache_fns)
 
 .macro define_tlb_functions name:req, flags_up:req, flags_smp
 	.type	\name\()_tlb_fns, #object
+	.align 2
 ENTRY(\name\()_tlb_fns)
 	.long	\name\()_flush_user_tlb_range
 	.long	\name\()_flush_kern_tlb_range

arch/arm/probes/kprobes/core.c

@@ -439,7 +439,7 @@ static struct undef_hook kprobes_arm_break_hook = {
 
 #endif /* !CONFIG_THUMB2_KERNEL */
 
-int __init arch_init_kprobes()
+int __init arch_init_kprobes(void)
 {
 	arm_probes_decode_init();
 #ifdef CONFIG_THUMB2_KERNEL

arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts

@@ -75,7 +75,7 @@
 	pinctrl-0 = <&emac_rgmii_pins>;
 	phy-supply = <&reg_gmac_3v3>;
 	phy-handle = <&ext_rgmii_phy>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	status = "okay";
 };
 

arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts

@@ -70,7 +70,9 @@
 		regulator-name = "rst-usb-eth2";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_usb_eth2>;
-		gpio = <&gpio3 2 GPIO_ACTIVE_LOW>;
+		gpio = <&gpio3 2 GPIO_ACTIVE_HIGH>;
+		enable-active-high;
+		regulator-always-on;
 	};
 
 	reg_vdd_5v: regulator-5v {
@@ -95,7 +97,7 @@
 		clocks = <&osc_can>;
 		interrupt-parent = <&gpio4>;
 		interrupts = <28 IRQ_TYPE_EDGE_FALLING>;
-		spi-max-frequency = <100000>;
+		spi-max-frequency = <10000000>;
 		vdd-supply = <&reg_vdd_3v3>;
 		xceiver-supply = <&reg_vdd_5v>;
 	};
@@ -111,7 +113,7 @@
 &fec1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet>;
-	phy-connection-type = "rgmii";
+	phy-connection-type = "rgmii-rxid";
 	phy-handle = <&ethphy>;
 	status = "okay";
 

arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi

@@ -91,10 +91,12 @@
 			reg_vdd_soc: BUCK1 {
 				regulator-name = "buck1";
 				regulator-min-microvolt = <800000>;
-				regulator-max-microvolt = <900000>;
+				regulator-max-microvolt = <850000>;
 				regulator-boot-on;
 				regulator-always-on;
 				regulator-ramp-delay = <3125>;
+				nxp,dvs-run-voltage = <850000>;
+				nxp,dvs-standby-voltage = <800000>;
 			};
 
 			reg_vdd_arm: BUCK2 {
@@ -111,7 +113,7 @@
 			reg_vdd_dram: BUCK3 {
 				regulator-name = "buck3";
 				regulator-min-microvolt = <850000>;
-				regulator-max-microvolt = <900000>;
+				regulator-max-microvolt = <950000>;
 				regulator-boot-on;
 				regulator-always-on;
 			};
@@ -150,7 +152,7 @@
 
 			reg_vdd_snvs: LDO2 {
 				regulator-name = "ldo2";
-				regulator-min-microvolt = <850000>;
+				regulator-min-microvolt = <800000>;
 				regulator-max-microvolt = <900000>;
 				regulator-boot-on;
 				regulator-always-on;

arch/arm64/boot/dts/qcom/sm8250.dtsi

@@ -2590,9 +2590,10 @@
 			power-domains = <&dispcc MDSS_GDSC>;
 
 			clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+				 <&gcc GCC_DISP_HF_AXI_CLK>,
 				 <&gcc GCC_DISP_SF_AXI_CLK>,
 				 <&dispcc DISP_CC_MDSS_MDP_CLK>;
-			clock-names = "iface", "nrt_bus", "core";
+			clock-names = "iface", "bus", "nrt_bus", "core";
 
 			assigned-clocks = <&dispcc DISP_CC_MDSS_MDP_CLK>;
 			assigned-clock-rates = <460000000>;

arch/arm64/configs/defconfig

@@ -245,7 +245,6 @@ CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_FW_LOADER_USER_HELPER=y
 CONFIG_FW_LOADER_USER_HELPER_FALLBACK=y
 CONFIG_HISILICON_LPC=y
-CONFIG_SIMPLE_PM_BUS=y
 CONFIG_FSL_MC_BUS=y
 CONFIG_TEGRA_ACONNECT=m
 CONFIG_GNSS=m

arch/arm64/kvm/hyp/include/nvhe/gfp.h

@@ -24,6 +24,7 @@ struct hyp_pool {
 
 /* Allocation */
 void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order);
+void hyp_split_page(struct hyp_page *page);
 void hyp_get_page(struct hyp_pool *pool, void *addr);
 void hyp_put_page(struct hyp_pool *pool, void *addr);
 

arch/arm64/kvm/hyp/nvhe/mem_protect.c

@@ -35,7 +35,18 @@ const u8 pkvm_hyp_id = 1;
 
 static void *host_s2_zalloc_pages_exact(size_t size)
 {
-	return hyp_alloc_pages(&host_s2_pool, get_order(size));
+	void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size));
+
+	hyp_split_page(hyp_virt_to_page(addr));
+
+	/*
+	 * The size of concatenated PGDs is always a power of two of PAGE_SIZE,
+	 * so there should be no need to free any of the tail pages to make the
+	 * allocation exact.
+	 */
+	WARN_ON(size != (PAGE_SIZE << get_order(size)));
+
+	return addr;
 }
 
 static void *host_s2_zalloc_page(void *pool)

arch/arm64/kvm/hyp/nvhe/page_alloc.c

@@ -152,6 +152,7 @@ static inline void hyp_page_ref_inc(struct hyp_page *p)
 
 static inline int hyp_page_ref_dec_and_test(struct hyp_page *p)
 {
+	BUG_ON(!p->refcount);
 	p->refcount--;
 	return (p->refcount == 0);
 }
@@ -193,6 +194,20 @@ void hyp_get_page(struct hyp_pool *pool, void *addr)
 	hyp_spin_unlock(&pool->lock);
 }
 
+void hyp_split_page(struct hyp_page *p)
+{
+	unsigned short order = p->order;
+	unsigned int i;
+
+	p->order = 0;
+	for (i = 1; i < (1 << order); i++) {
+		struct hyp_page *tail = p + i;
+
+		tail->order = 0;
+		hyp_set_page_refcounted(tail);
+	}
+}
+
 void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
 {
 	unsigned short i = order;

arch/arm64/kvm/mmu.c

@@ -1529,8 +1529,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		 * when updating the PG_mte_tagged page flag, see
 		 * sanitise_mte_tags for more details.
 		 */
-		if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED)
-			return -EINVAL;
+		if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED) {
+			ret = -EINVAL;
+			break;
+		}
 
 		if (vma->vm_flags & VM_PFNMAP) {
 			/* IO region dirty page logging not allowed */

arch/arm64/mm/hugetlbpage.c

@@ -43,7 +43,7 @@ void __init arm64_hugetlb_cma_reserve(void)
 #ifdef CONFIG_ARM64_4K_PAGES
 	order = PUD_SHIFT - PAGE_SHIFT;
 #else
-	order = CONT_PMD_SHIFT + PMD_SHIFT - PAGE_SHIFT;
+	order = CONT_PMD_SHIFT - PAGE_SHIFT;
 #endif
 	/*
 	 * HugeTLB CMA reservation is required for gigantic

arch/arm64/net/bpf_jit_comp.c

@@ -1136,6 +1136,11 @@ out:
 	return prog;
 }
 
+u64 bpf_jit_alloc_exec_limit(void)
+{
+	return BPF_JIT_REGION_SIZE;
+}
+
 void *bpf_jit_alloc_exec(unsigned long size)
 {
 	return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,

arch/csky/Kconfig

@@ -8,7 +8,7 @@ config CSKY
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_QUEUED_RWLOCKS
-	select ARCH_WANT_FRAME_POINTERS if !CPU_CK610
+	select ARCH_WANT_FRAME_POINTERS if !CPU_CK610 && $(cc-option,-mbacktrace)
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	select COMMON_CLK
 	select CLKSRC_MMIO
@@ -241,6 +241,7 @@ endchoice
 
 menuconfig HAVE_TCM
 	bool "Tightly-Coupled/Sram Memory"
+	depends on !COMPILE_TEST
 	help
 	  The implementation are not only used by TCM (Tightly-Coupled Meory)
 	  but also used by sram on SOC bus. It follow existed linux tcm

arch/csky/include/asm/bitops.h

@@ -74,7 +74,6 @@ static __always_inline unsigned long __fls(unsigned long x)
  * bug fix, why only could use atomic!!!!
  */
 #include <asm-generic/bitops/non-atomic.h>
-#define __clear_bit(nr, vaddr) clear_bit(nr, vaddr)
 
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/ext2-atomic.h>

arch/csky/kernel/ptrace.c

@@ -99,7 +99,8 @@ static int gpr_set(struct task_struct *target,
 	if (ret)
 		return ret;
 
-	regs.sr = task_pt_regs(target)->sr;
+	/* BIT(0) of regs.sr is Condition Code/Carry bit */
+	regs.sr = (regs.sr & BIT(0)) | (task_pt_regs(target)->sr & ~BIT(0));
 #ifdef CONFIG_CPU_HAS_HILO
 	regs.dcsr = task_pt_regs(target)->dcsr;
 #endif

arch/csky/kernel/signal.c

@@ -52,10 +52,14 @@ static long restore_sigcontext(struct pt_regs *regs,
 	struct sigcontext __user *sc)
 {
 	int err = 0;
+	unsigned long sr = regs->sr;
 
 	/* sc_pt_regs is structured the same as the start of pt_regs */
 	err |= __copy_from_user(regs, &sc->sc_pt_regs, sizeof(struct pt_regs));
 
+	/* BIT(0) of regs->sr is Condition Code/Carry bit */
+	regs->sr = (sr & ~1) | (regs->sr & 1);
+
 	/* Restore the floating-point state. */
 	err |= restore_fpu_state(sc);
 

arch/nds32/kernel/ftrace.c

@@ -6,7 +6,7 @@
 
 #ifndef CONFIG_DYNAMIC_FTRACE
 extern void (*ftrace_trace_function)(unsigned long, unsigned long,
-				     struct ftrace_ops*, struct pt_regs*);
+				     struct ftrace_ops*, struct ftrace_regs*);
 extern void ftrace_graph_caller(void);
 
 noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip,

arch/nios2/include/asm/irqflags.h

@@ -9,7 +9,7 @@
 
 static inline unsigned long arch_local_save_flags(void)
 {
-	return RDCTL(CTL_STATUS);
+	return RDCTL(CTL_FSTATUS);
 }
 
 /*
@@ -18,7 +18,7 @@ static inline unsigned long arch_local_save_flags(void)
  */
 static inline void arch_local_irq_restore(unsigned long flags)
 {
-	WRCTL(CTL_STATUS, flags);
+	WRCTL(CTL_FSTATUS, flags);
 }
 
 static inline void arch_local_irq_disable(void)

arch/nios2/include/asm/registers.h

@@ -11,7 +11,7 @@
 #endif
 
 /* control register numbers */
-#define CTL_STATUS	0
+#define CTL_FSTATUS	0
 #define CTL_ESTATUS	1
 #define CTL_BSTATUS	2
 #define CTL_IENABLE	3

arch/nios2/platform/Kconfig.platform

@@ -37,6 +37,7 @@ config NIOS2_DTB_PHYS_ADDR
 
 config NIOS2_DTB_SOURCE_BOOL
 	bool "Compile and link device tree into kernel image"
+	depends on !COMPILE_TEST
 	help
 	  This allows you to specify a dts (device tree source) file
 	  which will be compiled and linked into the kernel image.

arch/powerpc/kernel/idle_book3s.S

@@ -126,14 +126,16 @@ _GLOBAL(idle_return_gpr_loss)
 /*
  * This is the sequence required to execute idle instructions, as
  * specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0.
- *
- * The 0(r1) slot is used to save r2 in isa206, so use that here.
+ * We have to store a GPR somewhere, ptesync, then reload it, and create
+ * a false dependency on the result of the load. It doesn't matter which
+ * GPR we store, or where we store it. We have already stored r2 to the
+ * stack at -8(r1) in isa206_idle_insn_mayloss, so use that.
  */
 #define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST)			\
 	/* Magic NAP/SLEEP/WINKLE mode enter sequence */	\
-	std	r2,0(r1);					\
+	std	r2,-8(r1);					\
 	ptesync;						\
-	ld	r2,0(r1);					\
+	ld	r2,-8(r1);					\
 236:	cmpd	cr0,r2,r2;					\
 	bne	236b;						\
 	IDLE_INST;						\

arch/powerpc/kernel/smp.c

@@ -1730,8 +1730,6 @@ void __cpu_die(unsigned int cpu)
 
 void arch_cpu_idle_dead(void)
 {
-	sched_preempt_enable_no_resched();
-
 	/*
 	 * Disable on the down path. This will be re-enabled by
 	 * start_secondary() via start_secondary_resume() below

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -255,13 +255,16 @@ kvm_novcpu_exit:
  * r3 contains the SRR1 wakeup value, SRR1 is trashed.
  */
 _GLOBAL(idle_kvm_start_guest)
-	ld	r4,PACAEMERGSP(r13)
 	mfcr	r5
 	mflr	r0
-	std	r1,0(r4)
-	std	r5,8(r4)
-	std	r0,16(r4)
-	subi	r1,r4,STACK_FRAME_OVERHEAD
+	std	r5, 8(r1)	// Save CR in caller's frame
+	std	r0, 16(r1)	// Save LR in caller's frame
+	// Create frame on emergency stack
+	ld	r4, PACAEMERGSP(r13)
+	stdu	r1, -SWITCH_FRAME_SIZE(r4)
+	// Switch to new frame on emergency stack
+	mr	r1, r4
+	std	r3, 32(r1)	// Save SRR1 wakeup value
 	SAVE_NVGPRS(r1)
 
 	/*
@@ -313,6 +316,10 @@ kvm_unsplit_wakeup:
 
 kvm_secondary_got_guest:
 
+	// About to go to guest, clear saved SRR1
+	li	r0, 0
+	std	r0, 32(r1)
+
 	/* Set HSTATE_DSCR(r13) to something sensible */
 	ld	r6, PACA_DSCR_DEFAULT(r13)
 	std	r6, HSTATE_DSCR(r13)
@@ -392,13 +399,12 @@ kvm_no_guest:
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
 	mtspr	SPRN_LPCR, r4
-	/* set up r3 for return */
-	mfspr	r3,SPRN_SRR1
+	// Return SRR1 wakeup value, or 0 if we went into the guest
+	ld	r3, 32(r1)
 	REST_NVGPRS(r1)
-	addi	r1, r1, STACK_FRAME_OVERHEAD
-	ld	r0, 16(r1)
-	ld	r5, 8(r1)
-	ld	r1, 0(r1)
+	ld	r1, 0(r1)	// Switch back to caller stack
+	ld	r0, 16(r1)	// Reload LR
+	ld	r5, 8(r1)	// Reload CR
 	mtlr	r0
 	mtcr	r5
 	blr

arch/powerpc/platforms/pseries/iommu.c

@@ -1302,6 +1302,12 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		struct property *default_win;
 		int reset_win_ext;
 
+		/* DDW + IOMMU on single window may fail if there is any allocation */
+		if (iommu_table_in_use(tbl)) {
+			dev_warn(&dev->dev, "current IOMMU table in use, can't be replaced.\n");
+			goto out_failed;
+		}
+
 		default_win = of_find_property(pdn, "ibm,dma-window", NULL);
 		if (!default_win)
 			goto out_failed;
@@ -1356,12 +1362,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 			query.largest_available_block,
 			1ULL << page_shift);
 
-		/* DDW + IOMMU on single window may fail if there is any allocation */
-		if (default_win_removed && iommu_table_in_use(tbl)) {
-			dev_dbg(&dev->dev, "current IOMMU table in use, can't be replaced.\n");
-			goto out_failed;
-		}
-
 		len = order_base_2(query.largest_available_block << page_shift);
 		win_name = DMA64_PROPNAME;
 	} else {
@@ -1411,18 +1411,19 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	} else {
 		struct iommu_table *newtbl;
 		int i;
+		unsigned long start = 0, end = 0;
 
 		for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
 			const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
 
 			/* Look for MMIO32 */
-			if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM)
+			if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) {
+				start = pci->phb->mem_resources[i].start;
+				end = pci->phb->mem_resources[i].end;
 				break;
+			}
 		}
 
-		if (i == ARRAY_SIZE(pci->phb->mem_resources))
-			goto out_del_list;
-
 		/* New table for using DDW instead of the default DMA window */
 		newtbl = iommu_pseries_alloc_table(pci->phb->node);
 		if (!newtbl) {
@@ -1432,15 +1433,15 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 
 		iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, win_addr,
 					    1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
-		iommu_init_table(newtbl, pci->phb->node, pci->phb->mem_resources[i].start,
-				 pci->phb->mem_resources[i].end);
+		iommu_init_table(newtbl, pci->phb->node, start, end);
 
 		pci->table_group->tables[1] = newtbl;
 
 		/* Keep default DMA window stuct if removed */
 		if (default_win_removed) {
 			tbl->it_size = 0;
-			kfree(tbl->it_map);
+			vfree(tbl->it_map);
+			tbl->it_map = NULL;
 		}
 
 		set_iommu_table_base(&dev->dev, newtbl);

arch/powerpc/sysdev/xive/common.c

@@ -945,7 +945,8 @@ static int xive_get_irqchip_state(struct irq_data *data,
 		 * interrupt to be inactive in that case.
 		 */
 		*state = (pq != XIVE_ESB_INVALID) && !xd->stale_p &&
-			(xd->saved_p || !!(pq & XIVE_ESB_VAL_P));
+			(xd->saved_p || (!!(pq & XIVE_ESB_VAL_P) &&
+			 !irqd_irq_disabled(data)));
 		return 0;
 	default:
 		return -EINVAL;

arch/riscv/Kconfig

@@ -163,6 +163,12 @@ config PAGE_OFFSET
 	default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
 	default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
 
+config KASAN_SHADOW_OFFSET
+	hex
+	depends on KASAN_GENERIC
+	default 0xdfffffc800000000 if 64BIT
+	default 0xffffffff if 32BIT
+
 config ARCH_FLATMEM_ENABLE
 	def_bool !NUMA
 

arch/riscv/include/asm/kasan.h

@@ -30,8 +30,7 @@
 #define KASAN_SHADOW_SIZE	(UL(1) << ((CONFIG_VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT))
 #define KASAN_SHADOW_START	KERN_VIRT_START
 #define KASAN_SHADOW_END	(KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
-#define KASAN_SHADOW_OFFSET	(KASAN_SHADOW_END - (1ULL << \
-					(64 - KASAN_SHADOW_SCALE_SHIFT)))
+#define KASAN_SHADOW_OFFSET	_AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
 
 void kasan_init(void);
 asmlinkage void kasan_early_init(void);

arch/riscv/kernel/head.S

@@ -193,6 +193,7 @@ setup_trap_vector:
 	csrw CSR_SCRATCH, zero
 	ret
 
+.align 2
 .Lsecondary_park:
 	/* We lack SMP support or have too many harts, so park this hart */
 	wfi

arch/riscv/mm/kasan_init.c

@@ -17,6 +17,9 @@ asmlinkage void __init kasan_early_init(void)
 	uintptr_t i;
 	pgd_t *pgd = early_pg_dir + pgd_index(KASAN_SHADOW_START);
 
+	BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
+		KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
+
 	for (i = 0; i < PTRS_PER_PTE; ++i)
 		set_pte(kasan_early_shadow_pte + i,
 			mk_pte(virt_to_page(kasan_early_shadow_page),
@@ -172,21 +175,10 @@ void __init kasan_init(void)
 	phys_addr_t p_start, p_end;
 	u64 i;
 
-	/*
-	 * Populate all kernel virtual address space with kasan_early_shadow_page
-	 * except for the linear mapping and the modules/kernel/BPF mapping.
-	 */
-	kasan_populate_early_shadow((void *)KASAN_SHADOW_START,
-				    (void *)kasan_mem_to_shadow((void *)
-								VMEMMAP_END));
 	if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
 		kasan_shallow_populate(
 			(void *)kasan_mem_to_shadow((void *)VMALLOC_START),
 			(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
-	else
-		kasan_populate_early_shadow(
-			(void *)kasan_mem_to_shadow((void *)VMALLOC_START),
-			(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
 
 	/* Populate the linear mapping */
 	for_each_mem_range(i, &p_start, &p_end) {

arch/riscv/net/bpf_jit_core.c

@@ -125,7 +125,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (i == NR_JIT_ITERATIONS) {
 		pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
-		bpf_jit_binary_free(jit_data->header);
+		if (jit_data->header)
+			bpf_jit_binary_free(jit_data->header);
 		prog = orig_prog;
 		goto out_offset;
 	}
@@ -166,6 +167,11 @@ out:
 	return prog;
 }
 
+u64 bpf_jit_alloc_exec_limit(void)
+{
+	return BPF_JIT_REGION_SIZE;
+}
+
 void *bpf_jit_alloc_exec(unsigned long size)
 {
 	return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,

arch/s390/kvm/gaccess.c

@@ -894,6 +894,11 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
 
 /**
  * guest_translate_address - translate guest logical into guest absolute address
+ * @vcpu: virtual cpu
+ * @gva: Guest virtual address
+ * @ar: Access register
+ * @gpa: Guest physical address
+ * @mode: Translation access mode
  *
  * Parameter semantics are the same as the ones from guest_translate.
  * The memory contents at the guest address are not changed.
@@ -934,6 +939,11 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 
 /**
  * check_gva_range - test a range of guest virtual addresses for accessibility
+ * @vcpu: virtual cpu
+ * @gva: Guest virtual address
+ * @ar: Access register
+ * @length: Length of test range
+ * @mode: Translation access mode
  */
 int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 		    unsigned long length, enum gacc_mode mode)
@@ -956,6 +966,7 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
 
 /**
  * kvm_s390_check_low_addr_prot_real - check for low-address protection
+ * @vcpu: virtual cpu
  * @gra: Guest real address
  *
  * Checks whether an address is subject to low-address protection and set
@@ -979,6 +990,7 @@ int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra)
  * @pgt: pointer to the beginning of the page table for the given address if
  *	 successful (return value 0), or to the first invalid DAT entry in
  *	 case of exceptions (return value > 0)
+ * @dat_protection: referenced memory is write protected
  * @fake: pgt references contiguous guest memory block, not a pgtable
  */
 static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,

arch/s390/kvm/intercept.c

@@ -269,6 +269,7 @@ static int handle_prog(struct kvm_vcpu *vcpu)
 
 /**
  * handle_external_interrupt - used for external interruption interceptions
+ * @vcpu: virtual cpu
  *
  * This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if
  * the new PSW does not have external interrupts disabled. In the first case,
@@ -315,7 +316,8 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
 }
 
 /**
- * Handle MOVE PAGE partial execution interception.
+ * handle_mvpg_pei - Handle MOVE PAGE partial execution interception.
+ * @vcpu: virtual cpu
  *
  * This interception can only happen for guests with DAT disabled and
  * addresses that are currently not mapped in the host. Thus we try to

arch/s390/kvm/interrupt.c

@@ -3053,13 +3053,14 @@ static void __airqs_kick_single_vcpu(struct kvm *kvm, u8 deliverable_mask)
 	int vcpu_idx, online_vcpus = atomic_read(&kvm->online_vcpus);
 	struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
 	struct kvm_vcpu *vcpu;
+	u8 vcpu_isc_mask;
 
 	for_each_set_bit(vcpu_idx, kvm->arch.idle_mask, online_vcpus) {
 		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
 		if (psw_ioint_disabled(vcpu))
 			continue;
-		deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
-		if (deliverable_mask) {
+		vcpu_isc_mask = (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
+		if (deliverable_mask & vcpu_isc_mask) {
 			/* lately kicked but not yet running */
 			if (test_and_set_bit(vcpu_idx, gi->kicked_mask))
 				return;

arch/s390/kvm/kvm-s390.c

@@ -3363,6 +3363,7 @@ out_free_sie_block:
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
+	clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask);
 	return kvm_s390_vcpu_has_irq(vcpu, 0);
 }
 

arch/s390/lib/string.c

@@ -259,14 +259,13 @@ EXPORT_SYMBOL(strcmp);
 #ifdef __HAVE_ARCH_STRRCHR
 char *strrchr(const char *s, int c)
 {
-       size_t len = __strend(s) - s;
+	ssize_t len = __strend(s) - s;
 
-       if (len)
-	       do {
-		       if (s[len] == (char) c)
-			       return (char *) s + len;
-	       } while (--len > 0);
-       return NULL;
+	do {
+		if (s[len] == (char)c)
+			return (char *)s + len;
+	} while (--len >= 0);
+	return NULL;
 }
 EXPORT_SYMBOL(strrchr);
 #endif

arch/x86/Kconfig

@@ -1525,7 +1525,6 @@ config AMD_MEM_ENCRYPT
 
 config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT
 	bool "Activate AMD Secure Memory Encryption (SME) by default"
-	default y
 	depends on AMD_MEM_ENCRYPT
 	help
 	  Say yes to have system memory encrypted by default if running on

arch/x86/crypto/sm4-aesni-avx-asm_64.S

@@ -78,7 +78,7 @@
 	vpxor tmp0, x, x;
 
 
-.section	.rodata.cst164, "aM", @progbits, 164
+.section	.rodata.cst16, "aM", @progbits, 16
 .align 16
 
 /*
@@ -133,6 +133,10 @@
 .L0f0f0f0f:
 	.long 0x0f0f0f0f
 
+/* 12 bytes, only for padding */
+.Lpadding_deadbeef:
+	.long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef
+
 
 .text
 .align 16

arch/x86/crypto/sm4-aesni-avx2-asm_64.S

@@ -93,7 +93,7 @@
 	vpxor tmp0, x, x;
 
 
-.section	.rodata.cst164, "aM", @progbits, 164
+.section	.rodata.cst16, "aM", @progbits, 16
 .align 16
 
 /*
@@ -148,6 +148,10 @@
 .L0f0f0f0f:
 	.long 0x0f0f0f0f
 
+/* 12 bytes, only for padding */
+.Lpadding_deadbeef:
+	.long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef
+
 .text
 .align 16
 

arch/x86/events/msr.c

@@ -68,6 +68,7 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_BROADWELL_D:
 	case INTEL_FAM6_BROADWELL_G:
 	case INTEL_FAM6_BROADWELL_X:
+	case INTEL_FAM6_SAPPHIRERAPIDS_X:
 
 	case INTEL_FAM6_ATOM_SILVERMONT:
 	case INTEL_FAM6_ATOM_SILVERMONT_D:

arch/x86/include/asm/kvm_host.h

@@ -702,7 +702,8 @@ struct kvm_vcpu_arch {
 
 	struct kvm_pio_request pio;
 	void *pio_data;
-	void *guest_ins_data;
+	void *sev_pio_data;
+	unsigned sev_pio_count;
 
 	u8 event_exit_inst_len;
 
@@ -1097,7 +1098,7 @@ struct kvm_arch {
 	u64 cur_tsc_generation;
 	int nr_vcpus_matched_tsc;
 
-	spinlock_t pvclock_gtod_sync_lock;
+	raw_spinlock_t pvclock_gtod_sync_lock;
 	bool use_master_clock;
 	u64 master_kernel_ns;
 	u64 master_cycle_now;

arch/x86/kernel/fpu/signal.c

@@ -385,7 +385,7 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 				return -EINVAL;
 		} else {
 			/* Mask invalid bits out for historical reasons (broken hardware). */
-			fpu->state.fxsave.mxcsr &= ~mxcsr_feature_mask;
+			fpu->state.fxsave.mxcsr &= mxcsr_feature_mask;
 		}
 
 		/* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */

arch/x86/kvm/lapic.c

@@ -2321,13 +2321,14 @@ EXPORT_SYMBOL_GPL(kvm_apic_update_apicv);
 void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
+	u64 msr_val;
 	int i;
 
 	if (!init_event) {
-		vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE |
-				       MSR_IA32_APICBASE_ENABLE;
+		msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
 		if (kvm_vcpu_is_reset_bsp(vcpu))
-			vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP;
+			msr_val |= MSR_IA32_APICBASE_BSP;
+		kvm_lapic_set_base(vcpu, msr_val);
 	}
 
 	if (!apic)
@@ -2336,11 +2337,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
 
-	if (!init_event) {
-		apic->base_address = APIC_DEFAULT_PHYS_BASE;
-
+	/* The xAPIC ID is set at RESET even if the APIC was already enabled. */
+	if (!init_event)
 		kvm_apic_set_xapic_id(apic, vcpu->vcpu_id);
-	}
 	kvm_apic_set_version(apic->vcpu);
 
 	for (i = 0; i < KVM_APIC_LVT_NUM; i++)
@@ -2481,6 +2480,11 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 		lapic_timer_advance_dynamic = false;
 	}
 
+	/*
+	 * Stuff the APIC ENABLE bit in lieu of temporarily incrementing
+	 * apic_hw_disabled; the full RESET value is set by kvm_lapic_reset().
+	 */
+	vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
 	static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */
 	kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
 
@@ -2942,5 +2946,7 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 void kvm_lapic_exit(void)
 {
 	static_key_deferred_flush(&apic_hw_disabled);
+	WARN_ON(static_branch_unlikely(&apic_hw_disabled.key));
 	static_key_deferred_flush(&apic_sw_disabled);
+	WARN_ON(static_branch_unlikely(&apic_sw_disabled.key));
 }

arch/x86/kvm/mmu/mmu.c

@@ -4596,10 +4596,10 @@ static void update_pkru_bitmask(struct kvm_mmu *mmu)
 	unsigned bit;
 	bool wp;
 
-	if (!is_cr4_pke(mmu)) {
-		mmu->pkru_mask = 0;
+	mmu->pkru_mask = 0;
+
+	if (!is_cr4_pke(mmu))
 		return;
-	}
 
 	wp = is_cr0_wp(mmu);
 

arch/x86/kvm/svm/sev.c

@@ -618,7 +618,12 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
 	vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
 	vmsa.address = __sme_pa(svm->vmsa);
 	vmsa.len = PAGE_SIZE;
-	return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+	ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+	if (ret)
+	  return ret;
+
+	vcpu->arch.guest_state_protected = true;
+	return 0;
 }
 
 static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
@@ -1479,6 +1484,13 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 		goto e_free_trans;
 	}
 
+	/*
+	 * Flush (on non-coherent CPUs) before RECEIVE_UPDATE_DATA, the PSP
+	 * encrypts the written data with the guest's key, and the cache may
+	 * contain dirty, unencrypted data.
+	 */
+	sev_clflush_pages(guest_page, n);
+
 	/* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */
 	data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
 	data.guest_address |= sev_me_mask;
@@ -2579,11 +2591,20 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 
 int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 {
-	if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2))
+	int count;
+	int bytes;
+
+	if (svm->vmcb->control.exit_info_2 > INT_MAX)
 		return -EINVAL;
 
-	return kvm_sev_es_string_io(&svm->vcpu, size, port,
-				    svm->ghcb_sa, svm->ghcb_sa_len, in);
+	count = svm->vmcb->control.exit_info_2;
+	if (unlikely(check_mul_overflow(count, size, &bytes)))
+		return -EINVAL;
+
+	if (!setup_vmgexit_scratch(svm, in, bytes))
+		return -EINVAL;
+
+	return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in);
 }
 
 void sev_es_init_vmcb(struct vcpu_svm *svm)

arch/x86/kvm/svm/svm.h

@@ -191,7 +191,7 @@ struct vcpu_svm {
 
 	/* SEV-ES scratch area support */
 	void *ghcb_sa;
-	u64 ghcb_sa_len;
+	u32 ghcb_sa_len;
 	bool ghcb_sa_sync;
 	bool ghcb_sa_free;
 

arch/x86/kvm/vmx/vmx.c

@@ -5562,9 +5562,13 @@ static int handle_encls(struct kvm_vcpu *vcpu)
 
 static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu)
 {
-	vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
-	vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK;
-	return 0;
+	/*
+	 * Hardware may or may not set the BUS_LOCK_DETECTED flag on BUS_LOCK
+	 * VM-Exits. Unconditionally set the flag here and leave the handling to
+	 * vmx_handle_exit().
+	 */
+	to_vmx(vcpu)->exit_reason.bus_lock_detected = true;
+	return 1;
 }
 
 /*
@@ -6051,9 +6055,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	int ret = __vmx_handle_exit(vcpu, exit_fastpath);
 
 	/*
-	 * Even when current exit reason is handled by KVM internally, we
-	 * still need to exit to user space when bus lock detected to inform
-	 * that there is a bus lock in guest.
+	 * Exit to user space when bus lock detected to inform that there is
+	 * a bus lock in guest.
 	 */
 	if (to_vmx(vcpu)->exit_reason.bus_lock_detected) {
 		if (ret > 0)
@@ -6302,18 +6305,13 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 
 		/*
 		 * If we are running L2 and L1 has a new pending interrupt
-		 * which can be injected, we should re-evaluate
-		 * what should be done with this new L1 interrupt.
-		 * If L1 intercepts external-interrupts, we should
-		 * exit from L2 to L1. Otherwise, interrupt should be
-		 * delivered directly to L2.
+		 * which can be injected, this may cause a vmexit or it may
+		 * be injected into L2.  Either way, this interrupt will be
+		 * processed via KVM_REQ_EVENT, not RVI, because we do not use
+		 * virtual interrupt delivery to inject L1 interrupts into L2.
 		 */
-		if (is_guest_mode(vcpu) && max_irr_updated) {
-			if (nested_exit_on_intr(vcpu))
-				kvm_vcpu_exiting_guest_mode(vcpu);
-			else
-				kvm_make_request(KVM_REQ_EVENT, vcpu);
-		}
+		if (is_guest_mode(vcpu) && max_irr_updated)
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
 	} else {
 		max_irr = kvm_lapic_find_highest_irr(vcpu);
 	}

arch/x86/kvm/x86.c

@@ -2542,7 +2542,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
 	kvm_vcpu_write_tsc_offset(vcpu, offset);
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
-	spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
+	raw_spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
 	if (!matched) {
 		kvm->arch.nr_vcpus_matched_tsc = 0;
 	} else if (!already_matched) {
@@ -2550,7 +2550,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
 	}
 
 	kvm_track_tsc_matching(vcpu);
-	spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
+	raw_spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
 }
 
 static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
@@ -2780,9 +2780,9 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 	kvm_make_mclock_inprogress_request(kvm);
 
 	/* no guest entries from this point */
-	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	pvclock_update_vm_gtod_copy(kvm);
-	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -2800,15 +2800,15 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 	unsigned long flags;
 	u64 ret;
 
-	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	if (!ka->use_master_clock) {
-		spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+		raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 		return get_kvmclock_base_ns() + ka->kvmclock_offset;
 	}
 
 	hv_clock.tsc_timestamp = ka->master_cycle_now;
 	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
-	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	/* both __this_cpu_read() and rdtsc() should be on the same cpu */
 	get_cpu();
@@ -2902,13 +2902,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	 * If the host uses TSC clock, then passthrough TSC as stable
 	 * to the guest.
 	 */
-	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	use_master_clock = ka->use_master_clock;
 	if (use_master_clock) {
 		host_tsc = ka->master_cycle_now;
 		kernel_ns = ka->master_kernel_ns;
 	}
-	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+	raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
@@ -6100,13 +6100,13 @@ set_pit2_out:
 		 * is slightly ahead) here we risk going negative on unsigned
 		 * 'system_time' when 'user_ns.clock' is very small.
 		 */
-		spin_lock_irq(&ka->pvclock_gtod_sync_lock);
+		raw_spin_lock_irq(&ka->pvclock_gtod_sync_lock);
 		if (kvm->arch.use_master_clock)
 			now_ns = ka->master_kernel_ns;
 		else
 			now_ns = get_kvmclock_base_ns();
 		ka->kvmclock_offset = user_ns.clock - now_ns;
-		spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
+		raw_spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
 
 		kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
 		break;
@@ -6906,7 +6906,7 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
 }
 
 static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
-			       unsigned short port, void *val,
+			       unsigned short port,
 			       unsigned int count, bool in)
 {
 	vcpu->arch.pio.port = port;
@@ -6914,10 +6914,8 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
 	vcpu->arch.pio.count  = count;
 	vcpu->arch.pio.size = size;
 
-	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
-		vcpu->arch.pio.count = 0;
+	if (!kernel_pio(vcpu, vcpu->arch.pio_data))
 		return 1;
-	}
 
 	vcpu->run->exit_reason = KVM_EXIT_IO;
 	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
@@ -6929,26 +6927,39 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
 	return 0;
 }
 
+static int __emulator_pio_in(struct kvm_vcpu *vcpu, int size,
+			     unsigned short port, unsigned int count)
+{
+	WARN_ON(vcpu->arch.pio.count);
+	memset(vcpu->arch.pio_data, 0, size * count);
+	return emulator_pio_in_out(vcpu, size, port, count, true);
+}
+
+static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val)
+{
+	int size = vcpu->arch.pio.size;
+	unsigned count = vcpu->arch.pio.count;
+	memcpy(val, vcpu->arch.pio_data, size * count);
+	trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data);
+	vcpu->arch.pio.count = 0;
+}
+
 static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
 			   unsigned short port, void *val, unsigned int count)
 {
-	int ret;
+	if (vcpu->arch.pio.count) {
+		/* Complete previous iteration.  */
+	} else {
+		int r = __emulator_pio_in(vcpu, size, port, count);
+		if (!r)
+			return r;
 
-	if (vcpu->arch.pio.count)
-		goto data_avail;
-
-	memset(vcpu->arch.pio_data, 0, size * count);
-
-	ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
-	if (ret) {
-data_avail:
-		memcpy(val, vcpu->arch.pio_data, size * count);
-		trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data);
-		vcpu->arch.pio.count = 0;
-		return 1;
+		/* Results already available, fall through.  */
 	}
 
-	return 0;
+	WARN_ON(count != vcpu->arch.pio.count);
+	complete_emulator_pio_in(vcpu, val);
+	return 1;
 }
 
 static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
@@ -6963,9 +6974,15 @@ static int emulator_pio_out(struct kvm_vcpu *vcpu, int size,
 			    unsigned short port, const void *val,
 			    unsigned int count)
 {
+	int ret;
+
 	memcpy(vcpu->arch.pio_data, val, size * count);
 	trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data);
-	return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
+	ret = emulator_pio_in_out(vcpu, size, port, count, false);
+	if (ret)
+                vcpu->arch.pio.count = 0;
+
+        return ret;
 }
 
 static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
@@ -8139,9 +8156,9 @@ static void kvm_hyperv_tsc_notifier(void)
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		struct kvm_arch *ka = &kvm->arch;
 
-		spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+		raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 		pvclock_update_vm_gtod_copy(kvm);
-		spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+		raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 		kvm_for_each_vcpu(cpu, vcpu, kvm)
 			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -8783,9 +8800,17 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
+
+	/*
+	 * The call to kvm_ready_for_interrupt_injection() may end up in
+	 * kvm_xen_has_interrupt() which may require the srcu lock to be
+	 * held, to protect against changes in the vcpu_info address.
+	 */
+	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	kvm_run->ready_for_interrupt_injection =
 		pic_in_kernel(vcpu->kvm) ||
 		kvm_vcpu_ready_for_interrupt_injection(vcpu);
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 
 	if (is_smm(vcpu))
 		kvm_run->flags |= KVM_RUN_X86_SMM;
@@ -9643,14 +9668,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
 			break;
 
-                if (unlikely(kvm_vcpu_exit_request(vcpu))) {
+		if (vcpu->arch.apicv_active)
+			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+
+		if (unlikely(kvm_vcpu_exit_request(vcpu))) {
 			exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
 			break;
 		}
-
-		if (vcpu->arch.apicv_active)
-			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
-        }
+	}
 
 	/*
 	 * Do this here before restoring debug registers on the host.  And
@@ -11182,7 +11207,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	raw_spin_lock_init(&kvm->arch.tsc_write_lock);
 	mutex_init(&kvm->arch.apic_map_lock);
-	spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
+	raw_spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
 
 	kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
 	pvclock_update_vm_gtod_copy(kvm);
@@ -11392,7 +11417,8 @@ static int memslot_rmap_alloc(struct kvm_memory_slot *slot,
 		int level = i + 1;
 		int lpages = __kvm_mmu_slot_lpages(slot, npages, level);
 
-		WARN_ON(slot->arch.rmap[i]);
+		if (slot->arch.rmap[i])
+			continue;
 
 		slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT);
 		if (!slot->arch.rmap[i]) {
@@ -12367,44 +12393,81 @@ int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes,
 }
 EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read);
 
-static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
-{
-	memcpy(vcpu->arch.guest_ins_data, vcpu->arch.pio_data,
-	       vcpu->arch.pio.count * vcpu->arch.pio.size);
-	vcpu->arch.pio.count = 0;
+static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
+			   unsigned int port);
 
+static int complete_sev_es_emulated_outs(struct kvm_vcpu *vcpu)
+{
+	int size = vcpu->arch.pio.size;
+	int port = vcpu->arch.pio.port;
+
+	vcpu->arch.pio.count = 0;
+	if (vcpu->arch.sev_pio_count)
+		return kvm_sev_es_outs(vcpu, size, port);
 	return 1;
 }
 
 static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
-			   unsigned int port, void *data,  unsigned int count)
+			   unsigned int port)
 {
-	int ret;
+	for (;;) {
+		unsigned int count =
+			min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count);
+		int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count);
 
-	ret = emulator_pio_out_emulated(vcpu->arch.emulate_ctxt, size, port,
-					data, count);
-	if (ret)
-		return ret;
+		/* memcpy done already by emulator_pio_out.  */
+		vcpu->arch.sev_pio_count -= count;
+		vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size;
+		if (!ret)
+			break;
 
-	vcpu->arch.pio.count = 0;
+		/* Emulation done by the kernel.  */
+		if (!vcpu->arch.sev_pio_count)
+			return 1;
+	}
 
+	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_outs;
 	return 0;
 }
 
 static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
-			  unsigned int port, void *data, unsigned int count)
-{
-	int ret;
+			  unsigned int port);
 
-	ret = emulator_pio_in_emulated(vcpu->arch.emulate_ctxt, size, port,
-				       data, count);
-	if (ret) {
-		vcpu->arch.pio.count = 0;
-	} else {
-		vcpu->arch.guest_ins_data = data;
-		vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins;
+static void advance_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
+{
+	unsigned count = vcpu->arch.pio.count;
+	complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data);
+	vcpu->arch.sev_pio_count -= count;
+	vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size;
+}
+
+static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
+{
+	int size = vcpu->arch.pio.size;
+	int port = vcpu->arch.pio.port;
+
+	advance_sev_es_emulated_ins(vcpu);
+	if (vcpu->arch.sev_pio_count)
+		return kvm_sev_es_ins(vcpu, size, port);
+	return 1;
+}
+
+static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
+			  unsigned int port)
+{
+	for (;;) {
+		unsigned int count =
+			min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count);
+		if (!__emulator_pio_in(vcpu, size, port, count))
+			break;
+
+		/* Emulation done by the kernel.  */
+		advance_sev_es_emulated_ins(vcpu);
+		if (!vcpu->arch.sev_pio_count)
+			return 1;
 	}
 
+	vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins;
 	return 0;
 }
 
@@ -12412,8 +12475,10 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size,
 			 unsigned int port, void *data,  unsigned int count,
 			 int in)
 {
-	return in ? kvm_sev_es_ins(vcpu, size, port, data, count)
-		  : kvm_sev_es_outs(vcpu, size, port, data, count);
+	vcpu->arch.sev_pio_data = data;
+	vcpu->arch.sev_pio_count = count;
+	return in ? kvm_sev_es_ins(vcpu, size, port)
+		  : kvm_sev_es_outs(vcpu, size, port);
 }
 EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
 

arch/x86/kvm/xen.c

@@ -190,6 +190,7 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 
 int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
 {
+	int err;
 	u8 rc = 0;
 
 	/*
@@ -216,13 +217,29 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
 	if (likely(slots->generation == ghc->generation &&
 		   !kvm_is_error_hva(ghc->hva) && ghc->memslot)) {
 		/* Fast path */
-		__get_user(rc, (u8 __user *)ghc->hva + offset);
-	} else {
-		/* Slow path */
-		kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
-					     sizeof(rc));
+		pagefault_disable();
+		err = __get_user(rc, (u8 __user *)ghc->hva + offset);
+		pagefault_enable();
+		if (!err)
+			return rc;
 	}
 
+	/* Slow path */
+
+	/*
+	 * This function gets called from kvm_vcpu_block() after setting the
+	 * task to TASK_INTERRUPTIBLE, to see if it needs to wake immediately
+	 * from a HLT. So we really mustn't sleep. If the page ended up absent
+	 * at that point, just return 1 in order to trigger an immediate wake,
+	 * and we'll end up getting called again from a context where we *can*
+	 * fault in the page and wait for it.
+	 */
+	if (in_atomic() || !task_is_running(current))
+		return 1;
+
+	kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
+				     sizeof(rc));
+
 	return rc;
 }
 

block/bfq-cgroup.c

@@ -666,6 +666,12 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
 	bfqg_and_blkg_put(bfqq_group(bfqq));
 
+	if (entity->parent &&
+	    entity->parent->last_bfqq_created == bfqq)
+		entity->parent->last_bfqq_created = NULL;
+	else if (bfqd->last_bfqq_created == bfqq)
+		bfqd->last_bfqq_created = NULL;
+
 	entity->parent = bfqg->my_entity;
 	entity->sched_data = &bfqg->sched_data;
 	/* pin down bfqg and its associated blkg  */

block/blk-cgroup.c

@@ -1897,10 +1897,11 @@ void blk_cgroup_bio_start(struct bio *bio)
 {
 	int rwd = blk_cgroup_io_type(bio), cpu;
 	struct blkg_iostat_set *bis;
+	unsigned long flags;
 
 	cpu = get_cpu();
 	bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu);
-	u64_stats_update_begin(&bis->sync);
+	flags = u64_stats_update_begin_irqsave(&bis->sync);
 
 	/*
 	 * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split
@@ -1912,7 +1913,7 @@ void blk_cgroup_bio_start(struct bio *bio)
 	}
 	bis->cur.ios[rwd]++;
 
-	u64_stats_update_end(&bis->sync);
+	u64_stats_update_end_irqrestore(&bis->sync, flags);
 	if (cgroup_subsys_on_dfl(io_cgrp_subsys))
 		cgroup_rstat_updated(bio->bi_blkg->blkcg->css.cgroup, cpu);
 	put_cpu();

block/blk-core.c

@@ -49,7 +49,6 @@
 #include "blk-mq.h"
 #include "blk-mq-sched.h"
 #include "blk-pm.h"
-#include "blk-rq-qos.h"
 
 struct dentry *blk_debugfs_root;
 
@@ -337,23 +336,25 @@ void blk_put_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_put_queue);
 
-void blk_set_queue_dying(struct request_queue *q)
+void blk_queue_start_drain(struct request_queue *q)
 {
-	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
-
 	/*
 	 * When queue DYING flag is set, we need to block new req
 	 * entering queue, so we call blk_freeze_queue_start() to
 	 * prevent I/O from crossing blk_queue_enter().
 	 */
 	blk_freeze_queue_start(q);
-
 	if (queue_is_mq(q))
 		blk_mq_wake_waiters(q);
-
 	/* Make blk_queue_enter() reexamine the DYING flag. */
 	wake_up_all(&q->mq_freeze_wq);
 }
+
+void blk_set_queue_dying(struct request_queue *q)
+{
+	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
+	blk_queue_start_drain(q);
+}
 EXPORT_SYMBOL_GPL(blk_set_queue_dying);
 
 /**
@@ -385,13 +386,8 @@ void blk_cleanup_queue(struct request_queue *q)
 	 */
 	blk_freeze_queue(q);
 
-	rq_qos_exit(q);
-
 	blk_queue_flag_set(QUEUE_FLAG_DEAD, q);
 
-	/* for synchronous bio-based driver finish in-flight integrity i/o */
-	blk_flush_integrity();
-
 	blk_sync_queue(q);
 	if (queue_is_mq(q))
 		blk_mq_exit_queue(q);
@@ -416,6 +412,30 @@ void blk_cleanup_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_cleanup_queue);
 
+static bool blk_try_enter_queue(struct request_queue *q, bool pm)
+{
+	rcu_read_lock();
+	if (!percpu_ref_tryget_live(&q->q_usage_counter))
+		goto fail;
+
+	/*
+	 * The code that increments the pm_only counter must ensure that the
+	 * counter is globally visible before the queue is unfrozen.
+	 */
+	if (blk_queue_pm_only(q) &&
+	    (!pm || queue_rpm_status(q) == RPM_SUSPENDED))
+		goto fail_put;
+
+	rcu_read_unlock();
+	return true;
+
+fail_put:
+	percpu_ref_put(&q->q_usage_counter);
+fail:
+	rcu_read_unlock();
+	return false;
+}
+
 /**
  * blk_queue_enter() - try to increase q->q_usage_counter
  * @q: request queue pointer
@@ -425,40 +445,18 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 {
 	const bool pm = flags & BLK_MQ_REQ_PM;
 
-	while (true) {
-		bool success = false;
-
-		rcu_read_lock();
-		if (percpu_ref_tryget_live(&q->q_usage_counter)) {
-			/*
-			 * The code that increments the pm_only counter is
-			 * responsible for ensuring that that counter is
-			 * globally visible before the queue is unfrozen.
-			 */
-			if ((pm && queue_rpm_status(q) != RPM_SUSPENDED) ||
-			    !blk_queue_pm_only(q)) {
-				success = true;
-			} else {
-				percpu_ref_put(&q->q_usage_counter);
-			}
-		}
-		rcu_read_unlock();
-
-		if (success)
-			return 0;
-
+	while (!blk_try_enter_queue(q, pm)) {
 		if (flags & BLK_MQ_REQ_NOWAIT)
 			return -EBUSY;
 
 		/*
-		 * read pair of barrier in blk_freeze_queue_start(),
-		 * we need to order reading __PERCPU_REF_DEAD flag of
-		 * .q_usage_counter and reading .mq_freeze_depth or
-		 * queue dying flag, otherwise the following wait may
-		 * never return if the two reads are reordered.
+		 * read pair of barrier in blk_freeze_queue_start(), we need to
+		 * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and
+		 * reading .mq_freeze_depth or queue dying flag, otherwise the
+		 * following wait may never return if the two reads are
+		 * reordered.
 		 */
 		smp_rmb();
-
 		wait_event(q->mq_freeze_wq,
 			   (!q->mq_freeze_depth &&
 			    blk_pm_resume_queue(pm, q)) ||
@@ -466,23 +464,43 @@ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
 		if (blk_queue_dying(q))
 			return -ENODEV;
 	}
+
+	return 0;
 }
 
 static inline int bio_queue_enter(struct bio *bio)
 {
-	struct request_queue *q = bio->bi_bdev->bd_disk->queue;
-	bool nowait = bio->bi_opf & REQ_NOWAIT;
-	int ret;
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+	struct request_queue *q = disk->queue;
 
-	ret = blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0);
-	if (unlikely(ret)) {
-		if (nowait && !blk_queue_dying(q))
+	while (!blk_try_enter_queue(q, false)) {
+		if (bio->bi_opf & REQ_NOWAIT) {
+			if (test_bit(GD_DEAD, &disk->state))
+				goto dead;
 			bio_wouldblock_error(bio);
-		else
-			bio_io_error(bio);
+			return -EBUSY;
+		}
+
+		/*
+		 * read pair of barrier in blk_freeze_queue_start(), we need to
+		 * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and
+		 * reading .mq_freeze_depth or queue dying flag, otherwise the
+		 * following wait may never return if the two reads are
+		 * reordered.
+		 */
+		smp_rmb();
+		wait_event(q->mq_freeze_wq,
+			   (!q->mq_freeze_depth &&
+			    blk_pm_resume_queue(false, q)) ||
+			   test_bit(GD_DEAD, &disk->state));
+		if (test_bit(GD_DEAD, &disk->state))
+			goto dead;
 	}
 
-	return ret;
+	return 0;
+dead:
+	bio_io_error(bio);
+	return -ENODEV;
 }
 
 void blk_queue_exit(struct request_queue *q)
@@ -899,11 +917,18 @@ static blk_qc_t __submit_bio(struct bio *bio)
 	struct gendisk *disk = bio->bi_bdev->bd_disk;
 	blk_qc_t ret = BLK_QC_T_NONE;
 
-	if (blk_crypto_bio_prep(&bio)) {
-		if (!disk->fops->submit_bio)
-			return blk_mq_submit_bio(bio);
+	if (unlikely(bio_queue_enter(bio) != 0))
+		return BLK_QC_T_NONE;
+
+	if (!submit_bio_checks(bio) || !blk_crypto_bio_prep(&bio))
+		goto queue_exit;
+	if (disk->fops->submit_bio) {
 		ret = disk->fops->submit_bio(bio);
+		goto queue_exit;
 	}
+	return blk_mq_submit_bio(bio);
+
+queue_exit:
 	blk_queue_exit(disk->queue);
 	return ret;
 }
@@ -941,9 +966,6 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
 		struct request_queue *q = bio->bi_bdev->bd_disk->queue;
 		struct bio_list lower, same;
 
-		if (unlikely(bio_queue_enter(bio) != 0))
-			continue;
-
 		/*
 		 * Create a fresh bio_list for all subordinate requests.
 		 */
@@ -979,23 +1001,12 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio)
 static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
 {
 	struct bio_list bio_list[2] = { };
-	blk_qc_t ret = BLK_QC_T_NONE;
+	blk_qc_t ret;
 
 	current->bio_list = bio_list;
 
 	do {
-		struct gendisk *disk = bio->bi_bdev->bd_disk;
-
-		if (unlikely(bio_queue_enter(bio) != 0))
-			continue;
-
-		if (!blk_crypto_bio_prep(&bio)) {
-			blk_queue_exit(disk->queue);
-			ret = BLK_QC_T_NONE;
-			continue;
-		}
-
-		ret = blk_mq_submit_bio(bio);
+		ret = __submit_bio(bio);
 	} while ((bio = bio_list_pop(&bio_list[0])));
 
 	current->bio_list = NULL;
@@ -1013,9 +1024,6 @@ static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
  */
 blk_qc_t submit_bio_noacct(struct bio *bio)
 {
-	if (!submit_bio_checks(bio))
-		return BLK_QC_T_NONE;
-
 	/*
 	 * We only want one ->submit_bio to be active at a time, else stack
 	 * usage with stacked devices could be a problem.  Use current->bio_list

block/blk-mq.c

@@ -188,9 +188,11 @@ void blk_mq_freeze_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
-void blk_mq_unfreeze_queue(struct request_queue *q)
+void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic)
 {
 	mutex_lock(&q->mq_freeze_lock);
+	if (force_atomic)
+		q->q_usage_counter.data->force_atomic = true;
 	q->mq_freeze_depth--;
 	WARN_ON_ONCE(q->mq_freeze_depth < 0);
 	if (!q->mq_freeze_depth) {
@@ -199,6 +201,11 @@ void blk_mq_unfreeze_queue(struct request_queue *q)
 	}
 	mutex_unlock(&q->mq_freeze_lock);
 }
+
+void blk_mq_unfreeze_queue(struct request_queue *q)
+{
+	__blk_mq_unfreeze_queue(q, false);
+}
 EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
 
 /*
@@ -1318,6 +1325,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 	int errors, queued;
 	blk_status_t ret = BLK_STS_OK;
 	LIST_HEAD(zone_list);
+	bool needs_resource = false;
 
 	if (list_empty(list))
 		return false;
@@ -1363,6 +1371,8 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 			queued++;
 			break;
 		case BLK_STS_RESOURCE:
+			needs_resource = true;
+			fallthrough;
 		case BLK_STS_DEV_RESOURCE:
 			blk_mq_handle_dev_resource(rq, list);
 			goto out;
@@ -1373,6 +1383,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 			 * accept.
 			 */
 			blk_mq_handle_zone_resource(rq, &zone_list);
+			needs_resource = true;
 			break;
 		default:
 			errors++;
@@ -1399,7 +1410,6 @@ out:
 		/* For non-shared tags, the RESTART check will suffice */
 		bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
 			(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
-		bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET;
 
 		if (nr_budgets)
 			blk_mq_release_budgets(q, list);
@@ -1440,14 +1450,16 @@ out:
 		 * If driver returns BLK_STS_RESOURCE and SCHED_RESTART
 		 * bit is set, run queue after a delay to avoid IO stalls
 		 * that could otherwise occur if the queue is idle.  We'll do
-		 * similar if we couldn't get budget and SCHED_RESTART is set.
+		 * similar if we couldn't get budget or couldn't lock a zone
+		 * and SCHED_RESTART is set.
 		 */
 		needs_restart = blk_mq_sched_needs_restart(hctx);
+		if (prep == PREP_DISPATCH_NO_BUDGET)
+			needs_resource = true;
 		if (!needs_restart ||
 		    (no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
 			blk_mq_run_hw_queue(hctx, true);
-		else if (needs_restart && (ret == BLK_STS_RESOURCE ||
-					   no_budget_avail))
+		else if (needs_restart && needs_resource)
 			blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
 
 		blk_mq_update_dispatch_busy(hctx, true);

block/blk-settings.c

@@ -842,6 +842,24 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
 
+static bool disk_has_partitions(struct gendisk *disk)
+{
+	unsigned long idx;
+	struct block_device *part;
+	bool ret = false;
+
+	rcu_read_lock();
+	xa_for_each(&disk->part_tbl, idx, part) {
+		if (bdev_is_partition(part)) {
+			ret = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 /**
  * blk_queue_set_zoned - configure a disk queue zoned model.
  * @disk:	the gendisk of the queue to configure
@@ -876,7 +894,7 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
 		 * we do nothing special as far as the block layer is concerned.
 		 */
 		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
-		    !xa_empty(&disk->part_tbl))
+		    disk_has_partitions(disk))
 			model = BLK_ZONED_NONE;
 		break;
 	case BLK_ZONED_NONE:

block/blk.h

@@ -51,6 +51,8 @@ struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,
 void blk_free_flush_queue(struct blk_flush_queue *q);
 
 void blk_freeze_queue(struct request_queue *q);
+void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic);
+void blk_queue_start_drain(struct request_queue *q);
 
 #define BIO_INLINE_VECS 4
 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,

block/genhd.c

@@ -26,6 +26,7 @@
 #include <linux/badblocks.h>
 
 #include "blk.h"
+#include "blk-rq-qos.h"
 
 static struct kobject *block_depr;
 
@@ -559,6 +560,8 @@ EXPORT_SYMBOL(device_add_disk);
  */
 void del_gendisk(struct gendisk *disk)
 {
+	struct request_queue *q = disk->queue;
+
 	might_sleep();
 
 	if (WARN_ON_ONCE(!disk_live(disk) && !(disk->flags & GENHD_FL_HIDDEN)))
@@ -575,8 +578,17 @@ void del_gendisk(struct gendisk *disk)
 	fsync_bdev(disk->part0);
 	__invalidate_device(disk->part0, true);
 
+	/*
+	 * Fail any new I/O.
+	 */
+	set_bit(GD_DEAD, &disk->state);
 	set_capacity(disk, 0);
 
+	/*
+	 * Prevent new I/O from crossing bio_queue_enter().
+	 */
+	blk_queue_start_drain(q);
+
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
 
@@ -598,6 +610,18 @@ void del_gendisk(struct gendisk *disk)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
 	device_del(disk_to_dev(disk));
+
+	blk_mq_freeze_queue_wait(q);
+
+	rq_qos_exit(q);
+	blk_sync_queue(q);
+	blk_flush_integrity();
+	/*
+	 * Allow using passthrough request again after the queue is torn down.
+	 */
+	blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
+	__blk_mq_unfreeze_queue(q, true);
+
 }
 EXPORT_SYMBOL(del_gendisk);
 
@@ -1056,6 +1080,7 @@ static void disk_release(struct device *dev)
 	struct gendisk *disk = dev_to_disk(dev);
 
 	might_sleep();
+	WARN_ON_ONCE(disk_live(disk));
 
 	disk_release_events(disk);
 	kfree(disk->random);

block/kyber-iosched.c

@@ -151,6 +151,7 @@ struct kyber_ctx_queue {
 
 struct kyber_queue_data {
 	struct request_queue *q;
+	dev_t dev;
 
 	/*
 	 * Each scheduling domain has a limited number of in-flight requests
@@ -257,7 +258,7 @@ static int calculate_percentile(struct kyber_queue_data *kqd,
 	}
 	memset(buckets, 0, sizeof(kqd->latency_buckets[sched_domain][type]));
 
-	trace_kyber_latency(kqd->q, kyber_domain_names[sched_domain],
+	trace_kyber_latency(kqd->dev, kyber_domain_names[sched_domain],
 			    kyber_latency_type_names[type], percentile,
 			    bucket + 1, 1 << KYBER_LATENCY_SHIFT, samples);
 
@@ -270,7 +271,7 @@ static void kyber_resize_domain(struct kyber_queue_data *kqd,
 	depth = clamp(depth, 1U, kyber_depth[sched_domain]);
 	if (depth != kqd->domain_tokens[sched_domain].sb.depth) {
 		sbitmap_queue_resize(&kqd->domain_tokens[sched_domain], depth);
-		trace_kyber_adjust(kqd->q, kyber_domain_names[sched_domain],
+		trace_kyber_adjust(kqd->dev, kyber_domain_names[sched_domain],
 				   depth);
 	}
 }
@@ -366,6 +367,7 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
 		goto err;
 
 	kqd->q = q;
+	kqd->dev = disk_devt(q->disk);
 
 	kqd->cpu_latency = alloc_percpu_gfp(struct kyber_cpu_latency,
 					    GFP_KERNEL | __GFP_ZERO);
@@ -774,7 +776,7 @@ kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
 			list_del_init(&rq->queuelist);
 			return rq;
 		} else {
-			trace_kyber_throttled(kqd->q,
+			trace_kyber_throttled(kqd->dev,
 					      kyber_domain_names[khd->cur_domain]);
 		}
 	} else if (sbitmap_any_bit_set(&khd->kcq_map[khd->cur_domain])) {
@@ -787,7 +789,7 @@ kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
 			list_del_init(&rq->queuelist);
 			return rq;
 		} else {
-			trace_kyber_throttled(kqd->q,
+			trace_kyber_throttled(kqd->dev,
 					      kyber_domain_names[khd->cur_domain]);
 		}
 	}

block/partitions/core.c

@@ -423,6 +423,7 @@ out_del:
 	device_del(pdev);
 out_put:
 	put_device(pdev);
+	return ERR_PTR(err);
 out_put_disk:
 	put_disk(disk);
 	return ERR_PTR(err);

drivers/acpi/arm64/gtdt.c

@@ -36,7 +36,7 @@ struct acpi_gtdt_descriptor {
 
 static struct acpi_gtdt_descriptor acpi_gtdt_desc __initdata;
 
-static inline void *next_platform_timer(void *platform_timer)
+static inline __init void *next_platform_timer(void *platform_timer)
 {
 	struct acpi_gtdt_header *gh = platform_timer;
 

drivers/acpi/power.c

@@ -1035,13 +1035,8 @@ void acpi_turn_off_unused_power_resources(void)
 	list_for_each_entry_reverse(resource, &acpi_power_resource_list, list_node) {
 		mutex_lock(&resource->resource_lock);
 
-		/*
-		 * Turn off power resources in an unknown state too, because the
-		 * platform firmware on some system expects the OS to turn off
-		 * power resources without any users unconditionally.
-		 */
 		if (!resource->ref_count &&
-		    resource->state != ACPI_POWER_RESOURCE_STATE_OFF) {
+		    resource->state == ACPI_POWER_RESOURCE_STATE_ON) {
 			acpi_handle_debug(resource->device.handle, "Turning OFF\n");
 			__acpi_power_off(resource);
 		}

drivers/acpi/tables.c

@@ -21,6 +21,7 @@
 #include <linux/earlycpio.h>
 #include <linux/initrd.h>
 #include <linux/security.h>
+#include <linux/kmemleak.h>
 #include "internal.h"
 
 #ifdef CONFIG_ACPI_CUSTOM_DSDT
@@ -601,6 +602,8 @@ void __init acpi_table_upgrade(void)
 	 */
 	arch_reserve_mem_area(acpi_tables_addr, all_tables_size);
 
+	kmemleak_ignore_phys(acpi_tables_addr);
+
 	/*
 	 * early_ioremap only can remap 256k one time. If we map all
 	 * tables one time, we will hit the limit. Need to map chunks

drivers/acpi/x86/s2idle.c

@@ -371,7 +371,7 @@ static int lps0_device_attach(struct acpi_device *adev,
 		return 0;
 
 	if (acpi_s2idle_vendor_amd()) {
-		/* AMD0004, AMDI0005:
+		/* AMD0004, AMD0005, AMDI0005:
 		 * - Should use rev_id 0x0
 		 * - function mask > 0x3: Should use AMD method, but has off by one bug
 		 * - function mask = 0x3: Should use Microsoft method
@@ -390,6 +390,7 @@ static int lps0_device_attach(struct acpi_device *adev,
 					ACPI_LPS0_DSM_UUID_MICROSOFT, 0,
 					&lps0_dsm_guid_microsoft);
 		if (lps0_dsm_func_mask > 0x3 && (!strcmp(hid, "AMD0004") ||
+						 !strcmp(hid, "AMD0005") ||
 						 !strcmp(hid, "AMDI0005"))) {
 			lps0_dsm_func_mask = (lps0_dsm_func_mask << 1) | 0x1;
 			acpi_handle_debug(adev->handle, "_DSM UUID %s: Adjusted function mask: 0x%x\n",

drivers/ata/libahci_platform.c

@@ -440,10 +440,7 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
 	hpriv->phy_regulator = devm_regulator_get(dev, "phy");
 	if (IS_ERR(hpriv->phy_regulator)) {
 		rc = PTR_ERR(hpriv->phy_regulator);
-		if (rc == -EPROBE_DEFER)
-			goto err_out;
-		rc = 0;
-		hpriv->phy_regulator = NULL;
+		goto err_out;
 	}
 
 	if (flags & AHCI_PLATFORM_GET_RESETS) {

drivers/ata/pata_legacy.c

@@ -352,7 +352,8 @@ static unsigned int pdc_data_xfer_vlb(struct ata_queued_cmd *qc,
 			iowrite32_rep(ap->ioaddr.data_addr, buf, buflen >> 2);
 
 		if (unlikely(slop)) {
-			__le32 pad;
+			__le32 pad = 0;
+
 			if (rw == READ) {
 				pad = cpu_to_le32(ioread32(ap->ioaddr.data_addr));
 				memcpy(buf + buflen - slop, &pad, slop);
@@ -742,7 +743,8 @@ static unsigned int vlb32_data_xfer(struct ata_queued_cmd *qc,
 			ioread32_rep(ap->ioaddr.data_addr, buf, buflen >> 2);
 
 		if (unlikely(slop)) {
-			__le32 pad;
+			__le32 pad = 0;
+
 			if (rw == WRITE) {
 				memcpy(&pad, buf + buflen - slop, slop);
 				iowrite32(le32_to_cpu(pad), ap->ioaddr.data_addr);

drivers/ata/sata_mv.c

@@ -3896,8 +3896,8 @@ static int mv_chip_id(struct ata_host *host, unsigned int board_idx)
 		break;
 
 	default:
-		dev_err(host->dev, "BUG: invalid board index %u\n", board_idx);
-		return 1;
+		dev_alert(host->dev, "BUG: invalid board index %u\n", board_idx);
+		return -EINVAL;
 	}
 
 	hpriv->hp_flags = hp_flags;

drivers/base/core.c

@@ -687,7 +687,8 @@ struct device_link *device_link_add(struct device *consumer,
 {
 	struct device_link *link;
 
-	if (!consumer || !supplier || flags & ~DL_ADD_VALID_FLAGS ||
+	if (!consumer || !supplier || consumer == supplier ||
+	    flags & ~DL_ADD_VALID_FLAGS ||
 	    (flags & DL_FLAG_STATELESS && flags & DL_MANAGED_LINK_FLAGS) ||
 	    (flags & DL_FLAG_SYNC_STATE_ONLY &&
 	     (flags & ~DL_FLAG_INFERRED) != DL_FLAG_SYNC_STATE_ONLY) ||

drivers/base/regmap/regcache-rbtree.c

@@ -281,14 +281,14 @@ static int regcache_rbtree_insert_to_block(struct regmap *map,
 	if (!blk)
 		return -ENOMEM;
 
+	rbnode->block = blk;
+
 	if (BITS_TO_LONGS(blklen) > BITS_TO_LONGS(rbnode->blklen)) {
 		present = krealloc(rbnode->cache_present,
 				   BITS_TO_LONGS(blklen) * sizeof(*present),
 				   GFP_KERNEL);
-		if (!present) {
-			kfree(blk);
+		if (!present)
 			return -ENOMEM;
-		}
 
 		memset(present + BITS_TO_LONGS(rbnode->blklen), 0,
 		       (BITS_TO_LONGS(blklen) - BITS_TO_LONGS(rbnode->blklen))
@@ -305,7 +305,6 @@ static int regcache_rbtree_insert_to_block(struct regmap *map,
 	}
 
 	/* update the rbnode block, its size and the base register */
-	rbnode->block = blk;
 	rbnode->blklen = blklen;
 	rbnode->base_reg = base_reg;
 	rbnode->cache_present = present;

drivers/base/test/Makefile

@@ -2,4 +2,4 @@
 obj-$(CONFIG_TEST_ASYNC_DRIVER_PROBE)	+= test_async_driver_probe.o
 
 obj-$(CONFIG_DRIVER_PE_KUNIT_TEST) += property-entry-test.o
-CFLAGS_REMOVE_property-entry-test.o += -fplugin-arg-structleak_plugin-byref -fplugin-arg-structleak_plugin-byref-all
+CFLAGS_property-entry-test.o += $(DISABLE_STRUCTLEAK_PLUGIN)

drivers/block/brd.c

@@ -373,10 +373,22 @@ static int brd_alloc(int i)
 	struct gendisk *disk;
 	char buf[DISK_NAME_LEN];
 
+	mutex_lock(&brd_devices_mutex);
+	list_for_each_entry(brd, &brd_devices, brd_list) {
+		if (brd->brd_number == i) {
+			mutex_unlock(&brd_devices_mutex);
+			return -EEXIST;
+		}
+	}
 	brd = kzalloc(sizeof(*brd), GFP_KERNEL);
-	if (!brd)
+	if (!brd) {
+		mutex_unlock(&brd_devices_mutex);
 		return -ENOMEM;
+	}
 	brd->brd_number		= i;
+	list_add_tail(&brd->brd_list, &brd_devices);
+	mutex_unlock(&brd_devices_mutex);
+
 	spin_lock_init(&brd->brd_lock);
 	INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC);
 
@@ -411,37 +423,30 @@ static int brd_alloc(int i)
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue);
 	add_disk(disk);
-	list_add_tail(&brd->brd_list, &brd_devices);
 
 	return 0;
 
 out_free_dev:
+	mutex_lock(&brd_devices_mutex);
+	list_del(&brd->brd_list);
+	mutex_unlock(&brd_devices_mutex);
 	kfree(brd);
 	return -ENOMEM;
 }
 
 static void brd_probe(dev_t dev)
 {
-	int i = MINOR(dev) / max_part;
-	struct brd_device *brd;
-
-	mutex_lock(&brd_devices_mutex);
-	list_for_each_entry(brd, &brd_devices, brd_list) {
-		if (brd->brd_number == i)
-			goto out_unlock;
-	}
-
-	brd_alloc(i);
-out_unlock:
-	mutex_unlock(&brd_devices_mutex);
+	brd_alloc(MINOR(dev) / max_part);
 }
 
 static void brd_del_one(struct brd_device *brd)
 {
-	list_del(&brd->brd_list);
 	del_gendisk(brd->brd_disk);
 	blk_cleanup_disk(brd->brd_disk);
 	brd_free_pages(brd);
+	mutex_lock(&brd_devices_mutex);
+	list_del(&brd->brd_list);
+	mutex_unlock(&brd_devices_mutex);
 	kfree(brd);
 }
 
@@ -491,25 +496,21 @@ static int __init brd_init(void)
 
 	brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL);
 
-	mutex_lock(&brd_devices_mutex);
 	for (i = 0; i < rd_nr; i++) {
 		err = brd_alloc(i);
 		if (err)
 			goto out_free;
 	}
 
-	mutex_unlock(&brd_devices_mutex);
-
 	pr_info("brd: module loaded\n");
 	return 0;
 
 out_free:
+	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
 	debugfs_remove_recursive(brd_debugfs_dir);
 
 	list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
 		brd_del_one(brd);
-	mutex_unlock(&brd_devices_mutex);
-	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
 
 	pr_info("brd: module NOT loaded !!!\n");
 	return err;
@@ -519,13 +520,12 @@ static void __exit brd_exit(void)
 {
 	struct brd_device *brd, *next;
 
+	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
 	debugfs_remove_recursive(brd_debugfs_dir);
 
 	list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
 		brd_del_one(brd);
 
-	unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
-
 	pr_info("brd: module unloaded\n");
 }