Merge 6.13-rc3 into staging-next

We need the gpib build fixes in here as well.

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

Documentation/ABI/testing/sysfs-class-watchdog

@@ -76,7 +76,7 @@ Description:
 		timeout when the pretimeout interrupt is delivered.  Pretimeout
 		is an optional feature.
 
-What:		/sys/class/watchdog/watchdogn/pretimeout_avaialable_governors
+What:		/sys/class/watchdog/watchdogn/pretimeout_available_governors
 Date:		February 2017
 Contact:	Wim Van Sebroeck <wim@iguana.be>
 Description:

Documentation/admin-guide/kernel-parameters.txt

@@ -4822,6 +4822,11 @@
 			       can be preempted anytime.  Tasks will also yield
 			       contended spinlocks (if the critical section isn't
 			       explicitly preempt disabled beyond the lock itself).
+			lazy - Scheduler controlled. Similar to full but instead
+			       of preempting the task immediately, the task gets
+			       one HZ tick time to yield itself before the
+			       preemption will be forced. One preemption is when the
+			       task returns to user space.
 
 	print-fatal-signals=
 			[KNL] debug: print fatal signals

Documentation/arch/arm64/silicon-errata.rst

@@ -255,8 +255,9 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | Hisilicon      | Hip08 SMMU PMCG | #162001800      | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
-| Hisilicon      | Hip{08,09,10,10C| #162001900      | N/A                         |
+| Hisilicon      | Hip{08,09,09A,10| #162001900      | N/A                         |
-|                | ,11} SMMU PMCG  |                 |                             |
+|                | ,10C,11}        |                 |                             |
+|                | SMMU PMCG       |                 |                             |
 +----------------+-----------------+-----------------+-----------------------------+
 | Hisilicon      | Hip09           | #162100801      | HISILICON_ERRATUM_162100801 |
 +----------------+-----------------+-----------------+-----------------------------+

Documentation/core-api/symbol-namespaces.rst

@@ -68,7 +68,7 @@ is to define the default namespace in the ``Makefile`` of the subsystem. E.g. to
 export all symbols defined in usb-common into the namespace USB_COMMON, add a
 line like this to drivers/usb/common/Makefile::
 
-	ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=USB_COMMON
+	ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE='"USB_COMMON"'
 
 That will affect all EXPORT_SYMBOL() and EXPORT_SYMBOL_GPL() statements. A
 symbol exported with EXPORT_SYMBOL_NS() while this definition is present, will
@@ -79,7 +79,7 @@ A second option to define the default namespace is directly in the compilation
 unit as preprocessor statement. The above example would then read::
 
 	#undef  DEFAULT_SYMBOL_NAMESPACE
-	#define DEFAULT_SYMBOL_NAMESPACE USB_COMMON
+	#define DEFAULT_SYMBOL_NAMESPACE "USB_COMMON"
 
 within the corresponding compilation unit before any EXPORT_SYMBOL macro is
 used.
@@ -106,7 +106,7 @@ inspected with modinfo::
 	[...]
 
 
-It is advisable to add the MODULE_IMPORT_NS("") statement close to other module
+It is advisable to add the MODULE_IMPORT_NS() statement close to other module
 metadata definitions like MODULE_AUTHOR() or MODULE_LICENSE(). Refer to section
 5. for a way to create missing import statements automatically.
 
@@ -128,7 +128,7 @@ enable loading regardless, but will emit a warning.
 Missing namespaces imports can easily be detected at build time. In fact,
 modpost will emit a warning if a module uses a symbol from a namespace
 without importing it.
-MODULE_IMPORT_NS("") statements will usually be added at a definite location
+MODULE_IMPORT_NS() statements will usually be added at a definite location
 (along with other module meta data). To make the life of module authors (and
 subsystem maintainers) easier, a script and make target is available to fixup
 missing imports. Fixing missing imports can be done with::

Documentation/devicetree/bindings/phy/fsl,imx8mq-usb-phy.yaml

@@ -113,11 +113,8 @@ allOf:
           maxItems: 1
 
   - if:
-      properties:
+      required:
-        compatible:
+        - orientation-switch
-          contains:
-            enum:
-              - fsl,imx95-usb-phy
     then:
       $ref: /schemas/usb/usb-switch.yaml#
 

Documentation/devicetree/bindings/power/mediatek,power-controller.yaml

@@ -55,6 +55,10 @@ patternProperties:
             patternProperties:
               "^power-domain@[0-9a-f]+$":
                 $ref: "#/$defs/power-domain-node"
+                patternProperties:
+                  "^power-domain@[0-9a-f]+$":
+                    $ref: "#/$defs/power-domain-node"
+                    unevaluatedProperties: false
                 unevaluatedProperties: false
             unevaluatedProperties: false
         unevaluatedProperties: false

Documentation/devicetree/bindings/regulator/qcom,qca6390-pmu.yaml

@@ -18,6 +18,7 @@ properties:
   compatible:
     enum:
       - qcom,qca6390-pmu
+      - qcom,wcn6750-pmu
       - qcom,wcn6855-pmu
       - qcom,wcn7850-pmu
 
@@ -27,6 +28,9 @@ properties:
   vddaon-supply:
     description: VDD_AON supply regulator handle
 
+  vddasd-supply:
+    description: VDD_ASD supply regulator handle
+
   vdddig-supply:
     description: VDD_DIG supply regulator handle
 
@@ -42,6 +46,9 @@ properties:
   vddio1p2-supply:
     description: VDD_IO_1P2 supply regulator handle
 
+  vddrfa0p8-supply:
+    description: VDD_RFA_0P8 supply regulator handle
+
   vddrfa0p95-supply:
     description: VDD_RFA_0P95 supply regulator handle
 
@@ -51,12 +58,18 @@ properties:
   vddrfa1p3-supply:
     description: VDD_RFA_1P3 supply regulator handle
 
+  vddrfa1p7-supply:
+    description: VDD_RFA_1P7 supply regulator handle
+
   vddrfa1p8-supply:
     description: VDD_RFA_1P8 supply regulator handle
 
   vddrfa1p9-supply:
     description: VDD_RFA_1P9 supply regulator handle
 
+  vddrfa2p2-supply:
+    description: VDD_RFA_2P2 supply regulator handle
+
   vddpcie1p3-supply:
     description: VDD_PCIE_1P3 supply regulator handle
 
@@ -119,6 +132,20 @@ allOf:
         - vddpcie1p3-supply
         - vddpcie1p9-supply
         - vddio-supply
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: qcom,wcn6750-pmu
+    then:
+      required:
+        - vddaon-supply
+        - vddasd-supply
+        - vddpmu-supply
+        - vddrfa0p8-supply
+        - vddrfa1p2-supply
+        - vddrfa1p7-supply
+        - vddrfa2p2-supply
   - if:
       properties:
         compatible:

Documentation/devicetree/bindings/watchdog/airoha,en7581-wdt.yaml

@@ -0,0 +1,47 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/watchdog/airoha,en7581-wdt.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Airoha EN7581 Watchdog Timer
+
+maintainers:
+  - Christian Marangi <ansuelsmth@gmail.com>
+
+allOf:
+  - $ref: watchdog.yaml#
+
+properties:
+  compatible:
+    const: airoha,en7581-wdt
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    description: BUS clock (timer ticks at half the BUS clock)
+    maxItems: 1
+
+  clock-names:
+    const: bus
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/en7523-clk.h>
+
+    watchdog@1fbf0100 {
+        compatible = "airoha,en7581-wdt";
+        reg = <0x1fbf0100 0x3c>;
+
+        clocks = <&scuclk EN7523_CLK_BUS>;
+        clock-names = "bus";
+    };

Documentation/devicetree/bindings/watchdog/fsl-imx-wdt.yaml

@@ -48,6 +48,8 @@ properties:
   clocks:
     maxItems: 1
 
+  big-endian: true
+
   fsl,ext-reset-output:
     $ref: /schemas/types.yaml#/definitions/flag
     description: |
@@ -93,6 +95,18 @@ allOf:
       properties:
         fsl,suspend-in-wait: false
 
+  - if:
+      not:
+        properties:
+          compatible:
+            contains:
+              enum:
+                - fsl,ls1012a-wdt
+                - fsl,ls1043a-wdt
+    then:
+      properties:
+        big-endian: false
+
 unevaluatedProperties: false
 
 examples:

Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml

@@ -26,6 +26,8 @@ properties:
               - qcom,apss-wdt-msm8994
               - qcom,apss-wdt-qcm2290
               - qcom,apss-wdt-qcs404
+              - qcom,apss-wdt-qcs615
+              - qcom,apss-wdt-qcs8300
               - qcom,apss-wdt-sa8255p
               - qcom,apss-wdt-sa8775p
               - qcom,apss-wdt-sc7180

Documentation/devicetree/bindings/watchdog/samsung-wdt.yaml

@@ -26,6 +26,7 @@ properties:
           - samsung,exynos7-wdt                   # for Exynos7
           - samsung,exynos850-wdt                 # for Exynos850
           - samsung,exynosautov9-wdt              # for Exynosautov9
+          - samsung,exynosautov920-wdt            # for Exynosautov920
       - items:
           - enum:
               - tesla,fsd-wdt
@@ -77,6 +78,7 @@ allOf:
               - samsung,exynos7-wdt
               - samsung,exynos850-wdt
               - samsung,exynosautov9-wdt
+              - samsung,exynosautov920-wdt
     then:
       required:
         - samsung,syscon-phandle
@@ -88,6 +90,7 @@ allOf:
               - google,gs101-wdt
               - samsung,exynos850-wdt
               - samsung,exynosautov9-wdt
+              - samsung,exynosautov920-wdt
     then:
       properties:
         clocks:

Documentation/networking/bareudp.rst

@@ -6,16 +6,17 @@ Bare UDP Tunnelling Module Documentation
 
 There are various L3 encapsulation standards using UDP being discussed to
 leverage the UDP based load balancing capability of different networks.
-MPLSoUDP (__ https://tools.ietf.org/html/rfc7510) is one among them.
+MPLSoUDP (https://tools.ietf.org/html/rfc7510) is one among them.
 
 The Bareudp tunnel module provides a generic L3 encapsulation support for
 tunnelling different L3 protocols like MPLS, IP, NSH etc. inside a UDP tunnel.
 
 Special Handling
 ----------------
+
 The bareudp device supports special handling for MPLS & IP as they can have
 multiple ethertypes.
-MPLS procotcol can have ethertypes ETH_P_MPLS_UC  (unicast) & ETH_P_MPLS_MC (multicast).
+The MPLS protocol can have ethertypes ETH_P_MPLS_UC (unicast) & ETH_P_MPLS_MC (multicast).
 IP protocol can have ethertypes ETH_P_IP (v4) & ETH_P_IPV6 (v6).
 This special handling can be enabled only for ethertypes ETH_P_IP & ETH_P_MPLS_UC
 with a flag called multiproto mode.
@@ -52,7 +53,7 @@ be enabled explicitly with the "multiproto" flag.
 3) Device Usage
 
 The bareudp device could be used along with OVS or flower filter in TC.
-The OVS or TC flower layer must set the tunnel information in SKB dst field before
+The OVS or TC flower layer must set the tunnel information in the SKB dst field before
-sending packet buffer to the bareudp device for transmission. On reception the
+sending the packet buffer to the bareudp device for transmission. On reception, the
-bareudp device extracts and stores the tunnel information in SKB dst field before
+bareUDP device extracts and stores the tunnel information in the SKB dst field before
 passing the packet buffer to the network stack.

Documentation/networking/ip-sysctl.rst

@@ -2170,6 +2170,12 @@ nexthop_compat_mode - BOOLEAN
 	understands the new API, this sysctl can be disabled to achieve full
 	performance benefits of the new API by disabling the nexthop expansion
 	and extraneous notifications.
+
+	Note that as a backward-compatible mode, dumping of modern features
+	might be incomplete or wrong. For example, resilient groups will not be
+	shown as such, but rather as just a list of next hops. Also weights that
+	do not fit into 8 bits will show incorrectly.
+
 	Default: true (backward compat mode)
 
 fib_notify_on_flag_change - INTEGER

Documentation/power/runtime_pm.rst

@@ -347,7 +347,9 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
 
   `int pm_runtime_resume_and_get(struct device *dev);`
     - run pm_runtime_resume(dev) and if successful, increment the device's
-      usage counter; return the result of pm_runtime_resume
+      usage counter; returns 0 on success (whether or not the device's
+      runtime PM status was already 'active') or the error code from
+      pm_runtime_resume() on failure.
 
   `int pm_request_idle(struct device *dev);`
     - submit a request to execute the subsystem-level idle callback for the

Documentation/translations/it_IT/core-api/symbol-namespaces.rst

@@ -69,7 +69,7 @@ Per esempio per esportare tutti i simboli definiti in usb-common nello spazio
 dei nomi USB_COMMON, si può aggiungere la seguente linea in
 drivers/usb/common/Makefile::
 
-	ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=USB_COMMON
+	ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE='"USB_COMMON"'
 
 Questo cambierà tutte le macro EXPORT_SYMBOL() ed EXPORT_SYMBOL_GPL(). Invece,
 un simbolo esportato con EXPORT_SYMBOL_NS() non verrà cambiato e il simbolo
@@ -79,7 +79,7 @@ Una seconda possibilità è quella di definire il simbolo di preprocessore
 direttamente nei file da compilare. L'esempio precedente diventerebbe::
 
 	#undef  DEFAULT_SYMBOL_NAMESPACE
-	#define DEFAULT_SYMBOL_NAMESPACE USB_COMMON
+	#define DEFAULT_SYMBOL_NAMESPACE "USB_COMMON"
 
 Questo va messo prima di un qualsiasi uso di EXPORT_SYMBOL.
 
@@ -107,7 +107,7 @@ modinfo::
 	[...]
 
 
-Si consiglia di posizionare la dichiarazione MODULE_IMPORT_NS("") vicino
+Si consiglia di posizionare la dichiarazione MODULE_IMPORT_NS() vicino
 ai metadati del modulo come MODULE_AUTHOR() o MODULE_LICENSE(). Fate
 riferimento alla sezione 5. per creare automaticamente le importazioni
 mancanti.
@@ -131,7 +131,7 @@ emetterà un avviso.
 La mancanza di un'importazione può essere individuata facilmente al momento
 della compilazione. Infatti, modpost emetterà un avviso se il modulo usa
 un simbolo da uno spazio dei nomi che non è stato importato.
-La dichiarazione MODULE_IMPORT_NS("") viene solitamente aggiunta in un posto
+La dichiarazione MODULE_IMPORT_NS() viene solitamente aggiunta in un posto
 ben definito (assieme agli altri metadati del modulo). Per facilitare
 la vita di chi scrive moduli (e i manutentori di sottosistemi), esistono uno
 script e un target make per correggere le importazioni mancanti. Questo può

Documentation/translations/zh_CN/core-api/symbol-namespaces.rst

@@ -66,7 +66,7 @@
 子系统的 ``Makefile`` 中定义默认命名空间。例如，如果要将usb-common中定义的所有符号导
 出到USB_COMMON命名空间，可以在drivers/usb/common/Makefile中添加这样一行::
 
-       ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=USB_COMMON
+       ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE='"USB_COMMON"'
 
 这将影响所有 EXPORT_SYMBOL() 和 EXPORT_SYMBOL_GPL() 语句。当这个定义存在时，
 用EXPORT_SYMBOL_NS()导出的符号仍然会被导出到作为命名空间参数传递的命名空间中，
@@ -76,7 +76,7 @@
 成::
 
        #undef  DEFAULT_SYMBOL_NAMESPACE
-       #define DEFAULT_SYMBOL_NAMESPACE USB_COMMON
+       #define DEFAULT_SYMBOL_NAMESPACE "USB_COMMON"
 
 应置于相关编译单元中任何 EXPORT_SYMBOL 宏之前
 
@@ -99,7 +99,7 @@
        [...]
 
 
-建议将 MODULE_IMPORT_NS("") 语句添加到靠近其他模块元数据定义的地方，
+建议将 MODULE_IMPORT_NS() 语句添加到靠近其他模块元数据定义的地方，
 如 MODULE_AUTHOR() 或 MODULE_LICENSE() 。关于自动创建缺失的导入
 语句的方法，请参考第5节。
 
@@ -118,7 +118,7 @@ EINVAL方式失败。要允许加载不满足这个前提条件的模块，可
 
 缺少命名空间的导入可以在构建时很容易被检测到。事实上，如果一个模块
 使用了一个命名空间的符号而没有导入它，modpost会发出警告。
-MODULE_IMPORT_NS("")语句通常会被添加到一个明确的位置（和其他模块元
+MODULE_IMPORT_NS()语句通常会被添加到一个明确的位置（和其他模块元
 数据一起）。为了使模块作者（和子系统维护者）的生活更加轻松，我们提
 供了一个脚本和make目标来修复丢失的导入。修复丢失的导入可以用::
 

Documentation/watchdog/watchdog-parameters.rst

@@ -120,16 +120,6 @@ coh901327_wdt:
 
 -------------------------------------------------
 
-cpu5wdt:
-    port:
-	base address of watchdog card, default is 0x91
-    verbose:
-	be verbose, default is 0 (no)
-    ticks:
-	count down ticks, default is 10000
-
--------------------------------------------------
-
 cpwd:
     wd0_timeout:
 	Default watchdog0 timeout in 1/10secs

MAINTAINERS

@@ -3376,6 +3376,8 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git
 F:	Documentation/arch/arm64/
 F:	arch/arm64/
+F:	drivers/virt/coco/arm-cca-guest/
+F:	drivers/virt/coco/pkvm-guest/
 F:	tools/testing/selftests/arm64/
 X:	arch/arm64/boot/dts/
 
@@ -3891,7 +3893,7 @@ W:	http://www.baycom.org/~tom/ham/ham.html
 F:	drivers/net/hamradio/baycom*
 
 BCACHE (BLOCK LAYER CACHE)
-M:	Coly Li <colyli@suse.de>
+M:	Coly Li <colyli@kernel.org>
 M:	Kent Overstreet <kent.overstreet@linux.dev>
 L:	linux-bcache@vger.kernel.org
 S:	Maintained
@@ -15343,7 +15345,7 @@ M:	Daniel Machon <daniel.machon@microchip.com>
 M:	UNGLinuxDriver@microchip.com
 L:	netdev@vger.kernel.org
 S:	Maintained
-F:	drivers/net/ethernet/microchip/lan969x/*
+F:	drivers/net/ethernet/microchip/sparx5/lan969x/*
 
 MICROCHIP LCDFB DRIVER
 M:	Nicolas Ferre <nicolas.ferre@microchip.com>
@@ -16267,6 +16269,7 @@ F:	Documentation/devicetree/bindings/net/
 F:	Documentation/networking/net_cachelines/net_device.rst
 F:	drivers/connector/
 F:	drivers/net/
+F:	drivers/ptp/
 F:	include/dt-bindings/net/
 F:	include/linux/cn_proc.h
 F:	include/linux/etherdevice.h
@@ -16334,6 +16337,7 @@ F:	Documentation/networking/
 F:	Documentation/networking/net_cachelines/
 F:	Documentation/process/maintainer-netdev.rst
 F:	Documentation/userspace-api/netlink/
+F:	include/linux/ethtool.h
 F:	include/linux/framer/framer-provider.h
 F:	include/linux/framer/framer.h
 F:	include/linux/in.h
@@ -16348,6 +16352,7 @@ F:	include/linux/rtnetlink.h
 F:	include/linux/seq_file_net.h
 F:	include/linux/skbuff*
 F:	include/net/
+F:	include/uapi/linux/ethtool.h
 F:	include/uapi/linux/genetlink.h
 F:	include/uapi/linux/hsr_netlink.h
 F:	include/uapi/linux/in.h
@@ -22407,7 +22412,7 @@ F:	drivers/char/hw_random/jh7110-trng.c
 
 STARFIVE WATCHDOG DRIVER
 M:	Xingyu Wu <xingyu.wu@starfivetech.com>
-M:	Samin Guo <samin.guo@starfivetech.com>
+M:	Ziv Xu <ziv.xu@starfivetech.com>
 S:	Supported
 F:	Documentation/devicetree/bindings/watchdog/starfive*
 F:	drivers/watchdog/starfive-wdt.c

Makefile

@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 13
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

arch/arc/Kconfig

@@ -297,7 +297,6 @@ config ARC_PAGE_SIZE_16K
 config ARC_PAGE_SIZE_4K
 	bool "4KB"
 	select HAVE_PAGE_SIZE_4KB
-	depends on ARC_MMU_V3 || ARC_MMU_V4
 
 endchoice
 
@@ -474,7 +473,8 @@ config HIGHMEM
 
 config ARC_HAS_PAE40
 	bool "Support for the 40-bit Physical Address Extension"
-	depends on ISA_ARCV2
+	depends on ARC_MMU_V4
+	depends on !ARC_PAGE_SIZE_4K
 	select HIGHMEM
 	select PHYS_ADDR_T_64BIT
 	help

arch/arc/Makefile

@@ -6,7 +6,7 @@
 KBUILD_DEFCONFIG := haps_hs_smp_defconfig
 
 ifeq ($(CROSS_COMPILE),)
-CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux-)
+CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux- arc-linux-gnu-)
 endif
 
 cflags-y	+= -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__

arch/arc/boot/dts/axc001.dtsi

@@ -54,7 +54,7 @@ ictl_intc: gpio-controller@0 {
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <30>;
+				ngpios = <30>;
 				reg = <0>;
 				interrupt-controller;
 				#interrupt-cells = <2>;

arch/arc/boot/dts/axc003.dtsi

@@ -62,7 +62,7 @@ ictl_intc: gpio-controller@0 {
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <30>;
+				ngpios = <30>;
 				reg = <0>;
 				interrupt-controller;
 				#interrupt-cells = <2>;

arch/arc/boot/dts/axc003_idu.dtsi

@@ -69,7 +69,7 @@ ictl_intc: gpio-controller@0 {
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <30>;
+				ngpios = <30>;
 				reg = <0>;
 				interrupt-controller;
 				#interrupt-cells = <2>;

arch/arc/boot/dts/axs10x_mb.dtsi

@@ -250,7 +250,7 @@ gpio0_banka: gpio-controller@0 {
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <32>;
+				ngpios = <32>;
 				reg = <0>;
 			};
 
@@ -258,7 +258,7 @@ gpio0_bankb: gpio-controller@1 {
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <8>;
+				ngpios = <8>;
 				reg = <1>;
 			};
 
@@ -266,7 +266,7 @@ gpio0_bankc: gpio-controller@2 {
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <8>;
+				ngpios = <8>;
 				reg = <2>;
 			};
 		};
@@ -281,7 +281,7 @@ gpio1_banka: gpio-controller@0 {
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <30>;
+				ngpios = <30>;
 				reg = <0>;
 			};
 
@@ -289,7 +289,7 @@ gpio1_bankb: gpio-controller@1 {
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <10>;
+				ngpios = <10>;
 				reg = <1>;
 			};
 
@@ -297,7 +297,7 @@ gpio1_bankc: gpio-controller@2 {
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <8>;
+				ngpios = <8>;
 				reg = <2>;
 			};
 		};

arch/arc/boot/dts/hsdk.dts

@@ -308,7 +308,7 @@ gpio_port_a: gpio-controller@0 {
 				compatible = "snps,dw-apb-gpio-port";
 				gpio-controller;
 				#gpio-cells = <2>;
-				snps,nr-gpios = <24>;
+				ngpios = <24>;
 				reg = <0>;
 			};
 		};

arch/arc/include/asm/arcregs.h

@@ -146,7 +146,7 @@
 
 #ifndef __ASSEMBLY__
 
-#include <soc/arc/aux.h>
+#include <soc/arc/arc_aux.h>
 
 /* Helpers */
 #define TO_KB(bytes)		((bytes) >> 10)

arch/arc/include/asm/cmpxchg.h

@@ -48,7 +48,7 @@
 									\
 	switch(sizeof((_p_))) {						\
 	case 1:								\
-		_prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)_p_, (uintptr_t)_o_, (uintptr_t)_n_);	\
+		_prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *__force)_p_, (uintptr_t)_o_, (uintptr_t)_n_);	\
 		break;							\
 	case 4:								\
 		_prev_ = __cmpxchg(_p_, _o_, _n_);			\

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

@@ -9,7 +9,7 @@
 #ifndef _ASM_ARC_MMU_ARCV2_H
 #define _ASM_ARC_MMU_ARCV2_H
 
-#include <soc/arc/aux.h>
+#include <soc/arc/arc_aux.h>
 
 /*
  * TLB Management regs

arch/arc/net/bpf_jit_arcv2.c

@@ -2916,7 +2916,7 @@ bool check_jmp_32(u32 curr_off, u32 targ_off, u8 cond)
 	addendum = (cond == ARC_CC_AL) ? 0 : INSN_len_normal;
 	disp = get_displacement(curr_off + addendum, targ_off);
 
-	if (ARC_CC_AL)
+	if (cond == ARC_CC_AL)
 		return is_valid_far_disp(disp);
 	else
 		return is_valid_near_disp(disp);

arch/arm64/include/asm/cpucaps.h

@@ -44,6 +44,8 @@ cpucap_is_possible(const unsigned int cap)
 		return IS_ENABLED(CONFIG_ARM64_TLB_RANGE);
 	case ARM64_HAS_S1POE:
 		return IS_ENABLED(CONFIG_ARM64_POE);
+	case ARM64_HAS_GCS:
+		return IS_ENABLED(CONFIG_ARM64_GCS);
 	case ARM64_UNMAP_KERNEL_AT_EL0:
 		return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0);
 	case ARM64_WORKAROUND_843419:

arch/arm64/include/asm/cpufeature.h

@@ -847,8 +847,7 @@ static inline bool system_supports_poe(void)
 
 static inline bool system_supports_gcs(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_GCS) &&
+	return alternative_has_cap_unlikely(ARM64_HAS_GCS);
-		alternative_has_cap_unlikely(ARM64_HAS_GCS);
 }
 
 static inline bool system_supports_haft(void)

arch/arm64/include/asm/el2_setup.h

@@ -87,7 +87,7 @@
 		      1 << PMSCR_EL2_PA_SHIFT)
 	msr_s	SYS_PMSCR_EL2, x0		// addresses and physical counter
 .Lskip_spe_el2_\@:
-	mov	x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
+	mov	x0, #MDCR_EL2_E2PB_MASK
 	orr	x2, x2, x0			// If we don't have VHE, then
 						// use EL1&0 translation.
 
@@ -100,7 +100,7 @@
 	and	x0, x0, TRBIDR_EL1_P
 	cbnz	x0, .Lskip_trace_\@		// If TRBE is available at EL2
 
-	mov	x0, #(MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT)
+	mov	x0, #MDCR_EL2_E2TB_MASK
 	orr	x2, x2, x0			// allow the EL1&0 translation
 						// to own it.
 

arch/arm64/include/asm/mman.h

@@ -7,6 +7,7 @@
 #ifndef BUILD_VDSO
 #include <linux/compiler.h>
 #include <linux/fs.h>
+#include <linux/hugetlb.h>
 #include <linux/shmem_fs.h>
 #include <linux/types.h>
 
@@ -44,7 +45,7 @@ static inline unsigned long arch_calc_vm_flag_bits(struct file *file,
 	if (system_supports_mte()) {
 		if (flags & (MAP_ANONYMOUS | MAP_HUGETLB))
 			return VM_MTE_ALLOWED;
-		if (shmem_file(file))
+		if (shmem_file(file) || is_file_hugepages(file))
 			return VM_MTE_ALLOWED;
 	}
 

arch/arm64/kernel/hyp-stub.S

@@ -114,8 +114,8 @@ SYM_CODE_START_LOCAL(__finalise_el2)
 
 	// Use EL2 translations for SPE & TRBE and disable access from EL1
 	mrs	x0, mdcr_el2
-	bic	x0, x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT)
+	bic	x0, x0, #MDCR_EL2_E2PB_MASK
-	bic	x0, x0, #(MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT)
+	bic	x0, x0, #MDCR_EL2_E2TB_MASK
 	msr	mdcr_el2, x0
 
 	// Transfer the MM state from EL1 to EL2

arch/arm64/kernel/patching.c

@@ -30,20 +30,17 @@ static bool is_image_text(unsigned long addr)
 
 static void __kprobes *patch_map(void *addr, int fixmap)
 {
-	unsigned long uintaddr = (uintptr_t) addr;
+	phys_addr_t phys;
-	bool image = is_image_text(uintaddr);
-	struct page *page;
-
-	if (image)
-		page = phys_to_page(__pa_symbol(addr));
-	else if (IS_ENABLED(CONFIG_EXECMEM))
-		page = vmalloc_to_page(addr);
-	else
-		return addr;
 
+	if (is_image_text((unsigned long)addr)) {
+		phys = __pa_symbol(addr);
+	} else {
+		struct page *page = vmalloc_to_page(addr);
 		BUG_ON(!page);
-	return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
+		phys = page_to_phys(page) + offset_in_page(addr);
-			(uintaddr & ~PAGE_MASK));
+	}
+
+	return (void *)set_fixmap_offset(fixmap, phys);
 }
 
 static void __kprobes patch_unmap(int fixmap)

arch/arm64/kernel/ptrace.c

@@ -720,6 +720,8 @@ static int fpmr_set(struct task_struct *target, const struct user_regset *regset
 	if (!system_supports_fpmr())
 		return -EINVAL;
 
+	fpmr = target->thread.uw.fpmr;
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpmr, 0, count);
 	if (ret)
 		return ret;
@@ -1427,7 +1429,7 @@ static int tagged_addr_ctrl_get(struct task_struct *target,
 {
 	long ctrl = get_tagged_addr_ctrl(target);
 
-	if (IS_ERR_VALUE(ctrl))
+	if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl)))
 		return ctrl;
 
 	return membuf_write(&to, &ctrl, sizeof(ctrl));
@@ -1441,6 +1443,10 @@ static int tagged_addr_ctrl_set(struct task_struct *target, const struct
 	int ret;
 	long ctrl;
 
+	ctrl = get_tagged_addr_ctrl(target);
+	if (WARN_ON_ONCE(IS_ERR_VALUE(ctrl)))
+		return ctrl;
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1);
 	if (ret)
 		return ret;
@@ -1472,6 +1478,8 @@ static int poe_set(struct task_struct *target, const struct
 	if (!system_supports_poe())
 		return -EINVAL;
 
+	ctrl = target->thread.por_el0;
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1);
 	if (ret)
 		return ret;
@@ -1483,6 +1491,22 @@ static int poe_set(struct task_struct *target, const struct
 #endif
 
 #ifdef CONFIG_ARM64_GCS
+static void task_gcs_to_user(struct user_gcs *user_gcs,
+			     const struct task_struct *target)
+{
+	user_gcs->features_enabled = target->thread.gcs_el0_mode;
+	user_gcs->features_locked = target->thread.gcs_el0_locked;
+	user_gcs->gcspr_el0 = target->thread.gcspr_el0;
+}
+
+static void task_gcs_from_user(struct task_struct *target,
+			       const struct user_gcs *user_gcs)
+{
+	target->thread.gcs_el0_mode = user_gcs->features_enabled;
+	target->thread.gcs_el0_locked = user_gcs->features_locked;
+	target->thread.gcspr_el0 = user_gcs->gcspr_el0;
+}
+
 static int gcs_get(struct task_struct *target,
 		   const struct user_regset *regset,
 		   struct membuf to)
@@ -1495,9 +1519,7 @@ static int gcs_get(struct task_struct *target,
 	if (target == current)
 		gcs_preserve_current_state();
 
-	user_gcs.features_enabled = target->thread.gcs_el0_mode;
+	task_gcs_to_user(&user_gcs, target);
-	user_gcs.features_locked = target->thread.gcs_el0_locked;
-	user_gcs.gcspr_el0 = target->thread.gcspr_el0;
 
 	return membuf_write(&to, &user_gcs, sizeof(user_gcs));
 }
@@ -1513,6 +1535,8 @@ static int gcs_set(struct task_struct *target, const struct
 	if (!system_supports_gcs())
 		return -EINVAL;
 
+	task_gcs_to_user(&user_gcs, target);
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_gcs, 0, -1);
 	if (ret)
 		return ret;
@@ -1520,9 +1544,7 @@ static int gcs_set(struct task_struct *target, const struct
 	if (user_gcs.features_enabled & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK)
 		return -EINVAL;
 
-	target->thread.gcs_el0_mode = user_gcs.features_enabled;
+	task_gcs_from_user(target, &user_gcs);
-	target->thread.gcs_el0_locked = user_gcs.features_locked;
-	target->thread.gcspr_el0 = user_gcs.gcspr_el0;
 
 	return 0;
 }

arch/arm64/kernel/signal.c

@@ -1462,10 +1462,33 @@ static int setup_return(struct pt_regs *regs, struct ksignal *ksig,
 			 struct rt_sigframe_user_layout *user, int usig)
 {
 	__sigrestore_t sigtramp;
+	int err;
+
+	if (ksig->ka.sa.sa_flags & SA_RESTORER)
+		sigtramp = ksig->ka.sa.sa_restorer;
+	else
+		sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp);
+
+	err = gcs_signal_entry(sigtramp, ksig);
+	if (err)
+		return err;
+
+	/*
+	 * We must not fail from this point onwards. We are going to update
+	 * registers, including SP, in order to invoke the signal handler. If
+	 * we failed and attempted to deliver a nested SIGSEGV to a handler
+	 * after that point, the subsequent sigreturn would end up restoring
+	 * the (partial) state for the original signal handler.
+	 */
 
 	regs->regs[0] = usig;
+	if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
+		regs->regs[1] = (unsigned long)&user->sigframe->info;
+		regs->regs[2] = (unsigned long)&user->sigframe->uc;
+	}
 	regs->sp = (unsigned long)user->sigframe;
 	regs->regs[29] = (unsigned long)&user->next_frame->fp;
+	regs->regs[30] = (unsigned long)sigtramp;
 	regs->pc = (unsigned long)ksig->ka.sa.sa_handler;
 
 	/*
@@ -1506,14 +1529,7 @@ static int setup_return(struct pt_regs *regs, struct ksignal *ksig,
 		sme_smstop();
 	}
 
-	if (ksig->ka.sa.sa_flags & SA_RESTORER)
+	return 0;
-		sigtramp = ksig->ka.sa.sa_restorer;
-	else
-		sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp);
-
-	regs->regs[30] = (unsigned long)sigtramp;
-
-	return gcs_signal_entry(sigtramp, ksig);
 }
 
 static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
@@ -1537,14 +1553,16 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
 
 	err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
 	err |= setup_sigframe(&user, regs, set, &ua_state);
-	if (err == 0) {
+	if (ksig->ka.sa.sa_flags & SA_SIGINFO)
-		err = setup_return(regs, ksig, &user, usig);
-		if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
 		err |= copy_siginfo_to_user(&frame->info, &ksig->info);
-			regs->regs[1] = (unsigned long)&frame->info;
+
-			regs->regs[2] = (unsigned long)&frame->uc;
+	if (err == 0)
-		}
+		err = setup_return(regs, ksig, &user, usig);
-	}
+
+	/*
+	 * We must not fail if setup_return() succeeded - see comment at the
+	 * beginning of setup_return().
+	 */
 
 	if (err == 0)
 		set_handler_user_access_state();

arch/arm64/kernel/stacktrace.c

@@ -26,7 +26,6 @@ enum kunwind_source {
 	KUNWIND_SOURCE_CALLER,
 	KUNWIND_SOURCE_TASK,
 	KUNWIND_SOURCE_REGS_PC,
-	KUNWIND_SOURCE_REGS_LR,
 };
 
 union unwind_flags {
@@ -138,8 +137,10 @@ kunwind_recover_return_address(struct kunwind_state *state)
 		orig_pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
 						state->common.pc,
 						(void *)state->common.fp);
-		if (WARN_ON_ONCE(state->common.pc == orig_pc))
+		if (state->common.pc == orig_pc) {
+			WARN_ON_ONCE(state->task == current);
 			return -EINVAL;
+		}
 		state->common.pc = orig_pc;
 		state->flags.fgraph = 1;
 	}
@@ -178,23 +179,8 @@ int kunwind_next_regs_pc(struct kunwind_state *state)
 	state->regs = regs;
 	state->common.pc = regs->pc;
 	state->common.fp = regs->regs[29];
-	state->source = KUNWIND_SOURCE_REGS_PC;
-	return 0;
-}
-
-static __always_inline int
-kunwind_next_regs_lr(struct kunwind_state *state)
-{
-	/*
-	 * The stack for the regs was consumed by kunwind_next_regs_pc(), so we
-	 * cannot consume that again here, but we know the regs are safe to
-	 * access.
-	 */
-	state->common.pc = state->regs->regs[30];
-	state->common.fp = state->regs->regs[29];
 	state->regs = NULL;
-	state->source = KUNWIND_SOURCE_REGS_LR;
+	state->source = KUNWIND_SOURCE_REGS_PC;
-
 	return 0;
 }
 
@@ -215,12 +201,12 @@ kunwind_next_frame_record_meta(struct kunwind_state *state)
 	case FRAME_META_TYPE_FINAL:
 		if (meta == &task_pt_regs(tsk)->stackframe)
 			return -ENOENT;
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(tsk == current);
 		return -EINVAL;
 	case FRAME_META_TYPE_PT_REGS:
 		return kunwind_next_regs_pc(state);
 	default:
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(tsk == current);
 		return -EINVAL;
 	}
 }
@@ -274,11 +260,8 @@ kunwind_next(struct kunwind_state *state)
 	case KUNWIND_SOURCE_FRAME:
 	case KUNWIND_SOURCE_CALLER:
 	case KUNWIND_SOURCE_TASK:
-	case KUNWIND_SOURCE_REGS_LR:
-		err = kunwind_next_frame_record(state);
-		break;
 	case KUNWIND_SOURCE_REGS_PC:
-		err = kunwind_next_regs_lr(state);
+		err = kunwind_next_frame_record(state);
 		break;
 	default:
 		err = -EINVAL;
@@ -436,7 +419,6 @@ static const char *state_source_string(const struct kunwind_state *state)
 	case KUNWIND_SOURCE_CALLER:	return "C";
 	case KUNWIND_SOURCE_TASK:	return "T";
 	case KUNWIND_SOURCE_REGS_PC:	return "P";
-	case KUNWIND_SOURCE_REGS_LR:	return "L";
 	default:			return "U";
 	}
 }

arch/arm64/kvm/at.c

@@ -739,8 +739,15 @@ static u64 compute_par_s12(struct kvm_vcpu *vcpu, u64 s1_par,
 			final_attr = s1_parattr;
 			break;
 		default:
-			/* MemAttr[2]=0, Device from S2 */
+			/*
-			final_attr = s2_memattr & GENMASK(1,0) << 2;
+			 * MemAttr[2]=0, Device from S2.
+			 *
+			 * FWB does not influence the way that stage 1
+			 * memory types and attributes are combined
+			 * with stage 2 Device type and attributes.
+			 */
+			final_attr = min(s2_memattr_to_attr(s2_memattr),
+					 s1_parattr);
 		}
 	} else {
 		/* Combination of R_HMNDG, R_TNHFM and R_GQFSF */

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

@@ -126,7 +126,7 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
 	/* Trap SPE */
 	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMSVer), feature_ids)) {
 		mdcr_set |= MDCR_EL2_TPMS;
-		mdcr_clear |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
+		mdcr_clear |= MDCR_EL2_E2PB_MASK;
 	}
 
 	/* Trap Trace Filter */
@@ -143,7 +143,7 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
 
 	/* Trap External Trace */
 	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_ExtTrcBuff), feature_ids))
-		mdcr_clear |= MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT;
+		mdcr_clear |= MDCR_EL2_E2TB_MASK;
 
 	vcpu->arch.mdcr_el2 |= mdcr_set;
 	vcpu->arch.mdcr_el2 &= ~mdcr_clear;

arch/arm64/kvm/sys_regs.c

@@ -2618,7 +2618,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_WRITABLE(ID_AA64MMFR0_EL1, ~(ID_AA64MMFR0_EL1_RES0 |
 					ID_AA64MMFR0_EL1_TGRAN4_2 |
 					ID_AA64MMFR0_EL1_TGRAN64_2 |
-					ID_AA64MMFR0_EL1_TGRAN16_2)),
+					ID_AA64MMFR0_EL1_TGRAN16_2 |
+					ID_AA64MMFR0_EL1_ASIDBITS)),
 	ID_WRITABLE(ID_AA64MMFR1_EL1, ~(ID_AA64MMFR1_EL1_RES0 |
 					ID_AA64MMFR1_EL1_HCX |
 					ID_AA64MMFR1_EL1_TWED |

arch/arm64/kvm/vgic/vgic-its.c

@@ -608,12 +608,22 @@ static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its,
 	lockdep_assert_held(&its->its_lock);
 	vgic_get_irq_kref(irq);
 
+	old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT);
+
+	/*
+	 * Put the reference taken on @irq if the store fails. Intentionally do
+	 * not return the error as the translation cache is best effort.
+	 */
+	if (xa_is_err(old)) {
+		vgic_put_irq(kvm, irq);
+		return;
+	}
+
 	/*
 	 * We could have raced with another CPU caching the same
 	 * translation behind our back, ensure we don't leak a
 	 * reference if that is the case.
 	 */
-	old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT);
 	if (old)
 		vgic_put_irq(kvm, old);
 }

arch/arm64/mm/context.c

@@ -32,9 +32,9 @@ static unsigned long nr_pinned_asids;
 static unsigned long *pinned_asid_map;
 
 #define ASID_MASK		(~GENMASK(asid_bits - 1, 0))
-#define ASID_FIRST_VERSION	(1UL << asid_bits)
+#define ASID_FIRST_VERSION	(1UL << 16)
 
-#define NUM_USER_ASIDS		ASID_FIRST_VERSION
+#define NUM_USER_ASIDS		(1UL << asid_bits)
 #define ctxid2asid(asid)	((asid) & ~ASID_MASK)
 #define asid2ctxid(asid, genid)	((asid) | (genid))
 

arch/arm64/mm/copypage.c

@@ -30,11 +30,13 @@ void copy_highpage(struct page *to, struct page *from)
 	if (!system_supports_mte())
 		return;
 
-	if (folio_test_hugetlb(src) &&
+	if (folio_test_hugetlb(src)) {
-	    folio_test_hugetlb_mte_tagged(src)) {
+		if (!folio_test_hugetlb_mte_tagged(src) ||
-		if (!folio_try_hugetlb_mte_tagging(dst))
+		    from != folio_page(src, 0))
 			return;
 
+		WARN_ON_ONCE(!folio_try_hugetlb_mte_tagging(dst));
+
 		/*
 		 * Populate tags for all subpages.
 		 *

arch/arm64/mm/init.c

@@ -117,15 +117,6 @@ static void __init arch_reserve_crashkernel(void)
 
 static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit)
 {
-	/**
-	 * Information we get from firmware (e.g. DT dma-ranges) describe DMA
-	 * bus constraints. Devices using DMA might have their own limitations.
-	 * Some of them rely on DMA zone in low 32-bit memory. Keep low RAM
-	 * DMA zone on platforms that have RAM there.
-	 */
-	if (memblock_start_of_DRAM() < U32_MAX)
-		zone_limit = min(zone_limit, U32_MAX);
-
 	return min(zone_limit, memblock_end_of_DRAM() - 1) + 1;
 }
 
@@ -141,6 +132,14 @@ static void __init zone_sizes_init(void)
 	acpi_zone_dma_limit = acpi_iort_dma_get_max_cpu_address();
 	dt_zone_dma_limit = of_dma_get_max_cpu_address(NULL);
 	zone_dma_limit = min(dt_zone_dma_limit, acpi_zone_dma_limit);
+	/*
+	 * Information we get from firmware (e.g. DT dma-ranges) describe DMA
+	 * bus constraints. Devices using DMA might have their own limitations.
+	 * Some of them rely on DMA zone in low 32-bit memory. Keep low RAM
+	 * DMA zone on platforms that have RAM there.
+	 */
+	if (memblock_start_of_DRAM() < U32_MAX)
+		zone_dma_limit = min(zone_dma_limit, U32_MAX);
 	arm64_dma_phys_limit = max_zone_phys(zone_dma_limit);
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
 #endif

arch/loongarch/include/asm/hugetlb.h

@@ -24,6 +24,16 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
+#define __HAVE_ARCH_HUGE_PTE_CLEAR
+static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+				  pte_t *ptep, unsigned long sz)
+{
+	pte_t clear;
+
+	pte_val(clear) = (unsigned long)invalid_pte_table;
+	set_pte_at(mm, addr, ptep, clear);
+}
+
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)

arch/loongarch/include/asm/inst.h

@@ -683,7 +683,17 @@ DEF_EMIT_REG2I16_FORMAT(blt, blt_op)
 DEF_EMIT_REG2I16_FORMAT(bge, bge_op)
 DEF_EMIT_REG2I16_FORMAT(bltu, bltu_op)
 DEF_EMIT_REG2I16_FORMAT(bgeu, bgeu_op)
-DEF_EMIT_REG2I16_FORMAT(jirl, jirl_op)
+
+static inline void emit_jirl(union loongarch_instruction *insn,
+			     enum loongarch_gpr rd,
+			     enum loongarch_gpr rj,
+			     int offset)
+{
+	insn->reg2i16_format.opcode = jirl_op;
+	insn->reg2i16_format.immediate = offset;
+	insn->reg2i16_format.rd = rd;
+	insn->reg2i16_format.rj = rj;
+}
 
 #define DEF_EMIT_REG2BSTRD_FORMAT(NAME, OP)				\
 static inline void emit_##NAME(union loongarch_instruction *insn,	\

arch/loongarch/kernel/efi.c

@@ -95,7 +95,7 @@ static void __init init_screen_info(void)
 	memset(si, 0, sizeof(*si));
 	early_memunmap(si, sizeof(*si));
 
-	memblock_reserve(screen_info.lfb_base, screen_info.lfb_size);
+	memblock_reserve(__screen_info_lfb_base(&screen_info), screen_info.lfb_size);
 }
 
 void __init efi_init(void)

arch/loongarch/kernel/inst.c

@@ -332,7 +332,7 @@ u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm)
 		return INSN_BREAK;
 	}
 
-	emit_jirl(&insn, rj, rd, imm >> 2);
+	emit_jirl(&insn, rd, rj, imm >> 2);
 
 	return insn.word;
 }

arch/loongarch/kernel/smp.c

@@ -82,7 +82,7 @@ void show_ipi_list(struct seq_file *p, int prec)
 	for (i = 0; i < NR_IPI; i++) {
 		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i, prec >= 4 ? " " : "");
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ", per_cpu(irq_stat, cpu).ipi_irqs[i]);
+			seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, cpu).ipi_irqs[i], 10);
 		seq_printf(p, " LoongArch  %d  %s\n", i + 1, ipi_types[i]);
 	}
 }

arch/loongarch/kvm/exit.c

@@ -156,7 +156,7 @@ static int kvm_handle_csr(struct kvm_vcpu *vcpu, larch_inst inst)
 
 int kvm_emu_iocsr(larch_inst inst, struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
-	int ret;
+	int idx, ret;
 	unsigned long *val;
 	u32 addr, rd, rj, opcode;
 
@@ -167,7 +167,6 @@ int kvm_emu_iocsr(larch_inst inst, struct kvm_run *run, struct kvm_vcpu *vcpu)
 	rj = inst.reg2_format.rj;
 	opcode = inst.reg2_format.opcode;
 	addr = vcpu->arch.gprs[rj];
-	ret = EMULATE_DO_IOCSR;
 	run->iocsr_io.phys_addr = addr;
 	run->iocsr_io.is_write = 0;
 	val = &vcpu->arch.gprs[rd];
@@ -207,20 +206,28 @@ int kvm_emu_iocsr(larch_inst inst, struct kvm_run *run, struct kvm_vcpu *vcpu)
 	}
 
 	if (run->iocsr_io.is_write) {
-		if (!kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, run->iocsr_io.len, val))
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, run->iocsr_io.len, val);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		if (ret == 0)
 			ret = EMULATE_DONE;
-		else
+		else {
+			ret = EMULATE_DO_IOCSR;
 			/* Save data and let user space to write it */
 			memcpy(run->iocsr_io.data, val, run->iocsr_io.len);
-
+		}
 		trace_kvm_iocsr(KVM_TRACE_IOCSR_WRITE, run->iocsr_io.len, addr, val);
 	} else {
-		if (!kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, run->iocsr_io.len, val))
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, run->iocsr_io.len, val);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		if (ret == 0)
 			ret = EMULATE_DONE;
-		else
+		else {
+			ret = EMULATE_DO_IOCSR;
 			/* Save register id for iocsr read completion */
 			vcpu->arch.io_gpr = rd;
-
+		}
 		trace_kvm_iocsr(KVM_TRACE_IOCSR_READ, run->iocsr_io.len, addr, NULL);
 	}
 
@@ -359,7 +366,7 @@ static int kvm_handle_gspr(struct kvm_vcpu *vcpu)
 
 int kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst)
 {
-	int ret;
+	int idx, ret;
 	unsigned int op8, opcode, rd;
 	struct kvm_run *run = vcpu->run;
 
@@ -464,8 +471,10 @@ int kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst)
 		 * it need not return to user space to handle the mmio
 		 * exception.
 		 */
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, vcpu->arch.badv,
 				      run->mmio.len, &vcpu->arch.gprs[rd]);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		if (!ret) {
 			update_pc(&vcpu->arch);
 			vcpu->mmio_needed = 0;
@@ -531,7 +540,7 @@ int kvm_complete_mmio_read(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 int kvm_emu_mmio_write(struct kvm_vcpu *vcpu, larch_inst inst)
 {
-	int ret;
+	int idx, ret;
 	unsigned int rd, op8, opcode;
 	unsigned long curr_pc, rd_val = 0;
 	struct kvm_run *run = vcpu->run;
@@ -631,7 +640,9 @@ int kvm_emu_mmio_write(struct kvm_vcpu *vcpu, larch_inst inst)
 		 * it need not return to user space to handle the mmio
 		 * exception.
 		 */
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, vcpu->arch.badv, run->mmio.len, data);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		if (!ret)
 			return EMULATE_DONE;
 

arch/loongarch/kvm/intc/ipi.c

@@ -98,7 +98,7 @@ static void write_mailbox(struct kvm_vcpu *vcpu, int offset, uint64_t data, int
 
 static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 {
-	int i, ret;
+	int i, idx, ret;
 	uint32_t val = 0, mask = 0;
 
 	/*
@@ -107,7 +107,9 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 	 */
 	if ((data >> 27) & 0xf) {
 		/* Read the old val */
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		if (unlikely(ret)) {
 			kvm_err("%s: : read date from addr %llx failed\n", __func__, addr);
 			return ret;
@@ -121,7 +123,9 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 		val &= mask;
 	}
 	val |= ((uint32_t)(data >> 32) & ~mask);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	if (unlikely(ret))
 		kvm_err("%s: : write date to addr %llx failed\n", __func__, addr);
 

arch/loongarch/kvm/vcpu.c

@@ -240,7 +240,7 @@ static void kvm_late_check_requests(struct kvm_vcpu *vcpu)
  */
 static int kvm_enter_guest_check(struct kvm_vcpu *vcpu)
 {
-	int ret;
+	int idx, ret;
 
 	/*
 	 * Check conditions before entering the guest
@@ -249,7 +249,9 @@ static int kvm_enter_guest_check(struct kvm_vcpu *vcpu)
 	if (ret < 0)
 		return ret;
 
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	ret = kvm_check_requests(vcpu);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
 	return ret;
 }

arch/loongarch/net/bpf_jit.c

@@ -181,13 +181,13 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call)
 		/* Set return value */
 		emit_insn(ctx, addiw, LOONGARCH_GPR_A0, regmap[BPF_REG_0], 0);
 		/* Return to the caller */
-		emit_insn(ctx, jirl, LOONGARCH_GPR_RA, LOONGARCH_GPR_ZERO, 0);
+		emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_RA, 0);
 	} else {
 		/*
 		 * Call the next bpf prog and skip the first instruction
 		 * of TCC initialization.
 		 */
-		emit_insn(ctx, jirl, LOONGARCH_GPR_T3, LOONGARCH_GPR_ZERO, 1);
+		emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 1);
 	}
 }
 
@@ -904,7 +904,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 			return ret;
 
 		move_addr(ctx, t1, func_addr);
-		emit_insn(ctx, jirl, t1, LOONGARCH_GPR_RA, 0);
+		emit_insn(ctx, jirl, LOONGARCH_GPR_RA, t1, 0);
 		move_reg(ctx, regmap[BPF_REG_0], LOONGARCH_GPR_A0);
 		break;
 

arch/openrisc/kernel/entry.S

@@ -239,6 +239,8 @@ handler:							;\
 
 /* =====================================================[ exceptions] === */
 
+	__REF
+
 /* ---[ 0x100: RESET exception ]----------------------------------------- */
 
 EXCEPTION_ENTRY(_tng_kernel_start)

arch/openrisc/kernel/head.S

@@ -357,6 +357,8 @@
 
 /* =====================================================[ exceptions] === */
 
+	__HEAD
+
 /* ---[ 0x100: RESET exception ]----------------------------------------- */
     .org 0x100
 	/* Jump to .init code at _start which lives in the .head section
@@ -394,7 +396,7 @@ _dispatch_do_ipage_fault:
     .org 0x500
 	EXCEPTION_HANDLE(_timer_handler)
 
-/* ---[ 0x600: Alignment exception ]-------------------------------------- */
+/* ---[ 0x600: Alignment exception ]------------------------------------- */
     .org 0x600
 	EXCEPTION_HANDLE(_alignment_handler)
 
@@ -424,7 +426,7 @@ _dispatch_do_ipage_fault:
     .org 0xc00
 	EXCEPTION_HANDLE(_sys_call_handler)
 
-/* ---[ 0xd00: Floating point exception ]--------------------------------- */
+/* ---[ 0xd00: Floating point exception ]-------------------------------- */
     .org 0xd00
 	EXCEPTION_HANDLE(_fpe_trap_handler)
 
@@ -506,10 +508,10 @@ _dispatch_do_ipage_fault:
 
 /*    .text*/
 
-/* This early stuff belongs in HEAD, but some of the functions below definitely
+/* This early stuff belongs in the .init.text section, but some of the functions below definitely
  * don't... */
 
-	__HEAD
+	__INIT
 	.global _start
 _start:
 	/* Init r0 to zero as per spec */
@@ -816,7 +818,7 @@ secondary_start:
 
 #endif
 
-/* ========================================[ cache ]=== */
+/* ==========================================================[ cache ]=== */
 
 	/* alignment here so we don't change memory offsets with
 	 * memory controller defined

arch/openrisc/kernel/vmlinux.lds.S

@@ -50,6 +50,7 @@ SECTIONS
         .text                   : AT(ADDR(.text) - LOAD_OFFSET)
 	{
           _stext = .;
+	  HEAD_TEXT
 	  TEXT_TEXT
 	  SCHED_TEXT
 	  LOCK_TEXT
@@ -83,8 +84,6 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	__init_begin = .;
 
-	HEAD_TEXT_SECTION
-
 	/* Page aligned */
 	INIT_TEXT_SECTION(PAGE_SIZE)
 

arch/riscv/include/asm/kfence.h

@@ -22,7 +22,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 	else
 		set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT));
 
-	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+	preempt_disable();
+	local_flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+	preempt_enable();
 
 	return true;
 }

arch/riscv/kernel/jump_label.c

@@ -36,9 +36,15 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
 		insn = RISCV_INSN_NOP;
 	}
 
+	if (early_boot_irqs_disabled) {
+		riscv_patch_in_stop_machine = 1;
+		patch_insn_write(addr, &insn, sizeof(insn));
+		riscv_patch_in_stop_machine = 0;
+	} else {
 		mutex_lock(&text_mutex);
 		patch_insn_write(addr, &insn, sizeof(insn));
 		mutex_unlock(&text_mutex);
+	}
 
 	return true;
 }

arch/riscv/kernel/setup.c

@@ -227,7 +227,7 @@ static void __init init_resources(void)
 static void __init parse_dtb(void)
 {
 	/* Early scan of device tree from init memory */
-	if (early_init_dt_scan(dtb_early_va, __pa(dtb_early_va))) {
+	if (early_init_dt_scan(dtb_early_va, dtb_early_pa)) {
 		const char *name = of_flat_dt_get_machine_name();
 
 		if (name) {

arch/riscv/kvm/aia.c

@@ -590,7 +590,7 @@ void kvm_riscv_aia_enable(void)
 	csr_set(CSR_HIE, BIT(IRQ_S_GEXT));
 	/* Enable IRQ filtering for overflow interrupt only if sscofpmf is present */
 	if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF))
-		csr_write(CSR_HVIEN, BIT(IRQ_PMU_OVF));
+		csr_set(CSR_HVIEN, BIT(IRQ_PMU_OVF));
 }
 
 void kvm_riscv_aia_disable(void)

arch/riscv/mm/init.c

@@ -1566,7 +1566,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
 	pmd_clear(pmd);
 }
 
-static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
+static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, bool is_vmemmap)
 {
 	struct page *page = pud_page(*pud);
 	struct ptdesc *ptdesc = page_ptdesc(page);
@@ -1579,6 +1579,7 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
 			return;
 	}
 
+	if (!is_vmemmap)
 		pagetable_pmd_dtor(ptdesc);
 	if (PageReserved(page))
 		free_reserved_page(page);
@@ -1703,7 +1704,7 @@ static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, un
 		remove_pmd_mapping(pmd_base, addr, next, is_vmemmap, altmap);
 
 		if (pgtable_l4_enabled)
-			free_pmd_table(pmd_base, pudp);
+			free_pmd_table(pmd_base, pudp, is_vmemmap);
 	}
 }
 

arch/x86/events/intel/core.c

@@ -7135,6 +7135,7 @@ __init int intel_pmu_init(void)
 
 	case INTEL_METEORLAKE:
 	case INTEL_METEORLAKE_L:
+	case INTEL_ARROWLAKE_U:
 		intel_pmu_init_hybrid(hybrid_big_small);
 
 		x86_pmu.pebs_latency_data = cmt_latency_data;

arch/x86/events/intel/ds.c

@@ -1489,7 +1489,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 			 * hence we need to drain when changing said
 			 * size.
 			 */
-			intel_pmu_drain_large_pebs(cpuc);
+			intel_pmu_drain_pebs_buffer();
 			adaptive_pebs_record_size_update();
 			wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg);
 			cpuc->active_pebs_data_cfg = pebs_data_cfg;

arch/x86/include/asm/pgtable_types.h

@@ -36,10 +36,12 @@
 #define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
 #ifdef CONFIG_X86_64
-#define _PAGE_BIT_SAVED_DIRTY	_PAGE_BIT_SOFTW5 /* Saved Dirty bit */
+#define _PAGE_BIT_SAVED_DIRTY	_PAGE_BIT_SOFTW5 /* Saved Dirty bit (leaf) */
+#define _PAGE_BIT_NOPTISHADOW	_PAGE_BIT_SOFTW5 /* No PTI shadow (root PGD) */
 #else
 /* Shared with _PAGE_BIT_UFFD_WP which is not supported on 32 bit */
-#define _PAGE_BIT_SAVED_DIRTY	_PAGE_BIT_SOFTW2 /* Saved Dirty bit */
+#define _PAGE_BIT_SAVED_DIRTY	_PAGE_BIT_SOFTW2 /* Saved Dirty bit (leaf) */
+#define _PAGE_BIT_NOPTISHADOW	_PAGE_BIT_SOFTW2 /* No PTI shadow (root PGD) */
 #endif
 
 /* If _PAGE_BIT_PRESENT is clear, we use these: */
@@ -139,6 +141,8 @@
 
 #define _PAGE_PROTNONE	(_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
 
+#define _PAGE_NOPTISHADOW (_AT(pteval_t, 1) << _PAGE_BIT_NOPTISHADOW)
+
 /*
  * Set of bits not changed in pte_modify.  The pte's
  * protection key is treated like _PAGE_RW, for

arch/x86/kernel/cpu/amd.c

@@ -1065,7 +1065,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	 */
 	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
 	    cpu_has(c, X86_FEATURE_AUTOIBRS))
-		WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS));
+		WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS) < 0);
 
 	/* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
 	clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);

arch/x86/kernel/cpu/cacheinfo.c

@@ -178,8 +178,6 @@ struct _cpuid4_info_regs {
 	struct amd_northbridge *nb;
 };
 
-static unsigned short num_cache_leaves;
-
 /* AMD doesn't have CPUID4. Emulate it here to report the same
    information to the user.  This makes some assumptions about the machine:
    L2 not shared, no SMT etc. that is currently true on AMD CPUs.
@@ -717,20 +715,23 @@ void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c)
 
 void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 {
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
 
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
-		num_cache_leaves = find_num_cache_leaves(c);
+		ci->num_leaves = find_num_cache_leaves(c);
 	} else if (c->extended_cpuid_level >= 0x80000006) {
 		if (cpuid_edx(0x80000006) & 0xf000)
-			num_cache_leaves = 4;
+			ci->num_leaves = 4;
 		else
-			num_cache_leaves = 3;
+			ci->num_leaves = 3;
 	}
 }
 
 void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
 {
-	num_cache_leaves = find_num_cache_leaves(c);
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
+
+	ci->num_leaves = find_num_cache_leaves(c);
 }
 
 void init_intel_cacheinfo(struct cpuinfo_x86 *c)
@@ -740,21 +741,21 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
 	unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
 	unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
 
 	if (c->cpuid_level > 3) {
-		static int is_initialized;
+		/*
-
+		 * There should be at least one leaf. A non-zero value means
-		if (is_initialized == 0) {
+		 * that the number of leaves has been initialized.
-			/* Init num_cache_leaves from boot CPU */
+		 */
-			num_cache_leaves = find_num_cache_leaves(c);
+		if (!ci->num_leaves)
-			is_initialized++;
+			ci->num_leaves = find_num_cache_leaves(c);
-		}
 
 		/*
 		 * Whenever possible use cpuid(4), deterministic cache
 		 * parameters cpuid leaf to find the cache details
 		 */
-		for (i = 0; i < num_cache_leaves; i++) {
+		for (i = 0; i < ci->num_leaves; i++) {
 			struct _cpuid4_info_regs this_leaf = {};
 			int retval;
 
@@ -790,14 +791,14 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	 * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for
 	 * trace cache
 	 */
-	if ((num_cache_leaves == 0 || c->x86 == 15) && c->cpuid_level > 1) {
+	if ((!ci->num_leaves || c->x86 == 15) && c->cpuid_level > 1) {
 		/* supports eax=2  call */
 		int j, n;
 		unsigned int regs[4];
 		unsigned char *dp = (unsigned char *)regs;
 		int only_trace = 0;
 
-		if (num_cache_leaves != 0 && c->x86 == 15)
+		if (ci->num_leaves && c->x86 == 15)
 			only_trace = 1;
 
 		/* Number of times to iterate */
@@ -991,14 +992,12 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,
 
 int init_cache_level(unsigned int cpu)
 {
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
 
-	if (!num_cache_leaves)
+	/* There should be at least one leaf. */
+	if (!ci->num_leaves)
 		return -ENOENT;
-	if (!this_cpu_ci)
+
-		return -EINVAL;
-	this_cpu_ci->num_levels = 3;
-	this_cpu_ci->num_leaves = num_cache_leaves;
 	return 0;
 }
 

arch/x86/kernel/cpu/intel.c

@@ -555,7 +555,9 @@ static void init_intel(struct cpuinfo_x86 *c)
 	     c->x86_vfm == INTEL_WESTMERE_EX))
 		set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
 
-	if (boot_cpu_has(X86_FEATURE_MWAIT) && c->x86_vfm == INTEL_ATOM_GOLDMONT)
+	if (boot_cpu_has(X86_FEATURE_MWAIT) &&
+	    (c->x86_vfm == INTEL_ATOM_GOLDMONT ||
+	     c->x86_vfm == INTEL_LUNARLAKE_M))
 		set_cpu_bug(c, X86_BUG_MONITOR);
 
 #ifdef CONFIG_X86_64

arch/x86/kernel/cpu/topology.c

@@ -428,8 +428,8 @@ void __init topology_apply_cmdline_limits_early(void)
 {
 	unsigned int possible = nr_cpu_ids;
 
-	/* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' 'noapic' */
+	/* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' */
-	if (!setup_max_cpus || ioapic_is_disabled || apic_is_disabled)
+	if (!setup_max_cpus || apic_is_disabled)
 		possible = 1;
 
 	/* 'possible_cpus=N' */
@@ -443,7 +443,7 @@ void __init topology_apply_cmdline_limits_early(void)
 
 static __init bool restrict_to_up(void)
 {
-	if (!smp_found_config || ioapic_is_disabled)
+	if (!smp_found_config)
 		return true;
 	/*
 	 * XEN PV is special as it does not advertise the local APIC

arch/x86/kernel/fpu/signal.c

@@ -63,16 +63,6 @@ static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
 	return true;
 }
 
-/*
- * Update the value of PKRU register that was already pushed onto the signal frame.
- */
-static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru)
-{
-	if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
-		return 0;
-	return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU));
-}
-
 /*
  * Signal frame handlers.
  */
@@ -168,14 +158,8 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 
 static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pkru)
 {
-	int err = 0;
+	if (use_xsave())
-
+		return xsave_to_user_sigframe(buf, pkru);
-	if (use_xsave()) {
-		err = xsave_to_user_sigframe(buf);
-		if (!err)
-			err = update_pkru_in_sigframe(buf, pkru);
-		return err;
-	}
 
 	if (use_fxsr())
 		return fxsave_to_user_sigframe((struct fxregs_state __user *) buf);

arch/x86/kernel/fpu/xstate.h

@@ -69,6 +69,28 @@ static inline u64 xfeatures_mask_independent(void)
 	return fpu_kernel_cfg.independent_features;
 }
 
+/*
+ * Update the value of PKRU register that was already pushed onto the signal frame.
+ */
+static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 mask, u32 pkru)
+{
+	u64 xstate_bv;
+	int err;
+
+	if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
+		return 0;
+
+	/* Mark PKRU as in-use so that it is restored correctly. */
+	xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU;
+
+	err =  __put_user(xstate_bv, &buf->header.xfeatures);
+	if (err)
+		return err;
+
+	/* Update PKRU value in the userspace xsave buffer. */
+	return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU));
+}
+
 /* XSAVE/XRSTOR wrapper functions */
 
 #ifdef CONFIG_X86_64
@@ -256,7 +278,7 @@ static inline u64 xfeatures_need_sigframe_write(void)
  * The caller has to zero buf::header before calling this because XSAVE*
  * does not touch the reserved fields in the header.
  */
-static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
+static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkru)
 {
 	/*
 	 * Include the features which are not xsaved/rstored by the kernel
@@ -281,6 +303,9 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
 	XSTATE_OP(XSAVE, buf, lmask, hmask, err);
 	clac();
 
+	if (!err)
+		err = update_pkru_in_sigframe(buf, mask, pkru);
+
 	return err;
 }
 

arch/x86/kernel/relocate_kernel_64.S

@@ -13,6 +13,7 @@
 #include <asm/pgtable_types.h>
 #include <asm/nospec-branch.h>
 #include <asm/unwind_hints.h>
+#include <asm/asm-offsets.h>
 
 /*
  * Must be relocatable PIC code callable as a C function, in particular
@@ -242,6 +243,13 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
 	movq	CR0(%r8), %r8
 	movq	%rax, %cr3
 	movq	%r8, %cr0
+
+#ifdef CONFIG_KEXEC_JUMP
+	/* Saved in save_processor_state. */
+	movq    $saved_context, %rax
+	lgdt    saved_context_gdt_desc(%rax)
+#endif
+
 	movq	%rbp, %rax
 
 	popf

arch/x86/kvm/cpuid.c

@@ -36,6 +36,26 @@
 u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly;
 EXPORT_SYMBOL_GPL(kvm_cpu_caps);
 
+struct cpuid_xstate_sizes {
+	u32 eax;
+	u32 ebx;
+	u32 ecx;
+};
+
+static struct cpuid_xstate_sizes xstate_sizes[XFEATURE_MAX] __ro_after_init;
+
+void __init kvm_init_xstate_sizes(void)
+{
+	u32 ign;
+	int i;
+
+	for (i = XFEATURE_YMM; i < ARRAY_SIZE(xstate_sizes); i++) {
+		struct cpuid_xstate_sizes *xs = &xstate_sizes[i];
+
+		cpuid_count(0xD, i, &xs->eax, &xs->ebx, &xs->ecx, &ign);
+	}
+}
+
 u32 xstate_required_size(u64 xstate_bv, bool compacted)
 {
 	int feature_bit = 0;
@@ -44,14 +64,15 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted)
 	xstate_bv &= XFEATURE_MASK_EXTEND;
 	while (xstate_bv) {
 		if (xstate_bv & 0x1) {
-		        u32 eax, ebx, ecx, edx, offset;
+			struct cpuid_xstate_sizes *xs = &xstate_sizes[feature_bit];
-		        cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx);
+			u32 offset;
+
 			/* ECX[1]: 64B alignment in compacted form */
 			if (compacted)
-				offset = (ecx & 0x2) ? ALIGN(ret, 64) : ret;
+				offset = (xs->ecx & 0x2) ? ALIGN(ret, 64) : ret;
 			else
-				offset = ebx;
+				offset = xs->ebx;
-			ret = max(ret, offset + eax);
+			ret = max(ret, offset + xs->eax);
 		}
 
 		xstate_bv >>= 1;

arch/x86/kvm/cpuid.h

@@ -31,6 +31,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
 bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 	       u32 *ecx, u32 *edx, bool exact_only);
 
+void __init kvm_init_xstate_sizes(void);
 u32 xstate_required_size(u64 xstate_bv, bool compacted);
 
 int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu);

arch/x86/kvm/x86.c

@@ -13997,6 +13997,8 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault);
 
 static int __init kvm_x86_init(void)
 {
+	kvm_init_xstate_sizes();
+
 	kvm_mmu_x86_module_init();
 	mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible();
 	return 0;

arch/x86/mm/ident_map.c

@@ -174,7 +174,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page,
 		if (result)
 			return result;
 
-		set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag));
+		set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag | _PAGE_NOPTISHADOW));
 	}
 
 	return 0;
@@ -218,14 +218,14 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 		if (result)
 			return result;
 		if (pgtable_l5_enabled()) {
-			set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag));
+			set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag | _PAGE_NOPTISHADOW));
 		} else {
 			/*
 			 * With p4d folded, pgd is equal to p4d.
 			 * The pgd entry has to point to the pud page table in this case.
 			 */
 			pud_t *pud = pud_offset(p4d, 0);
-			set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag));
+			set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag | _PAGE_NOPTISHADOW));
 		}
 	}
 

arch/x86/mm/pti.c

@@ -132,7 +132,7 @@ pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 	 * Top-level entries added to init_mm's usermode pgd after boot
 	 * will not be automatically propagated to other mms.
 	 */
-	if (!pgdp_maps_userspace(pgdp))
+	if (!pgdp_maps_userspace(pgdp) || (pgd.pgd & _PAGE_NOPTISHADOW))
 		return pgd;
 
 	/*

block/bio.c

@@ -1171,7 +1171,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
 
-void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
+void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter)
 {
 	WARN_ON_ONCE(bio->bi_max_vecs);
 

block/blk-cgroup.c

@@ -1324,10 +1324,14 @@ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css)
 	struct blkcg *blkcg = css_to_blkcg(blkcg_css);
 
 	do {
+		struct blkcg *parent;
+
 		if (!refcount_dec_and_test(&blkcg->online_pin))
 			break;
+
+		parent = blkcg_parent(blkcg);
 		blkcg_destroy_blkgs(blkcg);
-		blkcg = blkcg_parent(blkcg);
+		blkcg = parent;
 	} while (blkcg);
 }
 

block/blk-iocost.c

@@ -1098,7 +1098,14 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse,
 		inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum,
 					   iocg->child_active_sum);
 	} else {
-		inuse = clamp_t(u32, inuse, 1, active);
+		/*
+		 * It may be tempting to turn this into a clamp expression with
+		 * a lower limit of 1 but active may be 0, which cannot be used
+		 * as an upper limit in that situation. This expression allows
+		 * active to clamp inuse unless it is 0, in which case inuse
+		 * becomes 1.
+		 */
+		inuse = min(inuse, active) ?: 1;
 	}
 
 	iocg->last_inuse = iocg->inuse;

block/blk-map.c

@@ -574,7 +574,7 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter)
 	bio = blk_rq_map_bio_alloc(rq, 0, GFP_KERNEL);
 	if (!bio)
 		return -ENOMEM;
-	bio_iov_bvec_set(bio, (struct iov_iter *)iter);
+	bio_iov_bvec_set(bio, iter);
 
 	/* check that the data layout matches the hardware restrictions */
 	ret = bio_split_rw_at(bio, lim, &nsegs, max_bytes);

block/blk-mq-sysfs.c

@@ -275,15 +275,13 @@ void blk_mq_sysfs_unregister_hctxs(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	unsigned long i;
 
-	mutex_lock(&q->sysfs_dir_lock);
+	lockdep_assert_held(&q->sysfs_dir_lock);
+
 	if (!q->mq_sysfs_init_done)
-		goto unlock;
+		return;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
-
-unlock:
-	mutex_unlock(&q->sysfs_dir_lock);
 }
 
 int blk_mq_sysfs_register_hctxs(struct request_queue *q)
@@ -292,9 +290,10 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q)
 	unsigned long i;
 	int ret = 0;
 
-	mutex_lock(&q->sysfs_dir_lock);
+	lockdep_assert_held(&q->sysfs_dir_lock);
+
 	if (!q->mq_sysfs_init_done)
-		goto unlock;
+		return ret;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
@@ -302,8 +301,5 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q)
 			break;
 	}
 
-unlock:
-	mutex_unlock(&q->sysfs_dir_lock);
-
 	return ret;
 }

block/blk-mq.c

@@ -43,6 +43,7 @@
 
 static DEFINE_PER_CPU(struct llist_head, blk_cpu_done);
 static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd);
+static DEFINE_MUTEX(blk_mq_cpuhp_lock);
 
 static void blk_mq_insert_request(struct request *rq, blk_insert_t flags);
 static void blk_mq_request_bypass_insert(struct request *rq,
@@ -1543,20 +1544,18 @@ static void blk_mq_requeue_work(struct work_struct *work)
 
 	while (!list_empty(&rq_list)) {
 		rq = list_entry(rq_list.next, struct request, queuelist);
+		list_del_init(&rq->queuelist);
 		/*
-		 * If RQF_DONTPREP ist set, the request has been started by the
+		 * If RQF_DONTPREP is set, the request has been started by the
 		 * driver already and might have driver-specific data allocated
 		 * already.  Insert it into the hctx dispatch list to avoid
 		 * block layer merges for the request.
 		 */
-		if (rq->rq_flags & RQF_DONTPREP) {
+		if (rq->rq_flags & RQF_DONTPREP)
-			list_del_init(&rq->queuelist);
 			blk_mq_request_bypass_insert(rq, 0);
-		} else {
+		else
-			list_del_init(&rq->queuelist);
 			blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD);
 	}
-	}
 
 	while (!list_empty(&flush_list)) {
 		rq = list_entry(flush_list.next, struct request, queuelist);
@@ -3739,13 +3738,91 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 	return 0;
 }
 
-static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
+static void __blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
 {
-	if (!(hctx->flags & BLK_MQ_F_STACKING))
+	lockdep_assert_held(&blk_mq_cpuhp_lock);
+
+	if (!(hctx->flags & BLK_MQ_F_STACKING) &&
+	    !hlist_unhashed(&hctx->cpuhp_online)) {
 		cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
 						    &hctx->cpuhp_online);
+		INIT_HLIST_NODE(&hctx->cpuhp_online);
+	}
+
+	if (!hlist_unhashed(&hctx->cpuhp_dead)) {
 		cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD,
 						    &hctx->cpuhp_dead);
+		INIT_HLIST_NODE(&hctx->cpuhp_dead);
+	}
+}
+
+static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx)
+{
+	mutex_lock(&blk_mq_cpuhp_lock);
+	__blk_mq_remove_cpuhp(hctx);
+	mutex_unlock(&blk_mq_cpuhp_lock);
+}
+
+static void __blk_mq_add_cpuhp(struct blk_mq_hw_ctx *hctx)
+{
+	lockdep_assert_held(&blk_mq_cpuhp_lock);
+
+	if (!(hctx->flags & BLK_MQ_F_STACKING) &&
+	    hlist_unhashed(&hctx->cpuhp_online))
+		cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
+				&hctx->cpuhp_online);
+
+	if (hlist_unhashed(&hctx->cpuhp_dead))
+		cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD,
+				&hctx->cpuhp_dead);
+}
+
+static void __blk_mq_remove_cpuhp_list(struct list_head *head)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	lockdep_assert_held(&blk_mq_cpuhp_lock);
+
+	list_for_each_entry(hctx, head, hctx_list)
+		__blk_mq_remove_cpuhp(hctx);
+}
+
+/*
+ * Unregister cpuhp callbacks from exited hw queues
+ *
+ * Safe to call if this `request_queue` is live
+ */
+static void blk_mq_remove_hw_queues_cpuhp(struct request_queue *q)
+{
+	LIST_HEAD(hctx_list);
+
+	spin_lock(&q->unused_hctx_lock);
+	list_splice_init(&q->unused_hctx_list, &hctx_list);
+	spin_unlock(&q->unused_hctx_lock);
+
+	mutex_lock(&blk_mq_cpuhp_lock);
+	__blk_mq_remove_cpuhp_list(&hctx_list);
+	mutex_unlock(&blk_mq_cpuhp_lock);
+
+	spin_lock(&q->unused_hctx_lock);
+	list_splice(&hctx_list, &q->unused_hctx_list);
+	spin_unlock(&q->unused_hctx_lock);
+}
+
+/*
+ * Register cpuhp callbacks from all hw queues
+ *
+ * Safe to call if this `request_queue` is live
+ */
+static void blk_mq_add_hw_queues_cpuhp(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned long i;
+
+	mutex_lock(&blk_mq_cpuhp_lock);
+	queue_for_each_hw_ctx(q, hctx, i)
+		__blk_mq_add_cpuhp(hctx);
+	mutex_unlock(&blk_mq_cpuhp_lock);
 }
 
 /*
@@ -3796,8 +3873,6 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
 
-	blk_mq_remove_cpuhp(hctx);
-
 	xa_erase(&q->hctx_table, hctx_idx);
 
 	spin_lock(&q->unused_hctx_lock);
@@ -3814,6 +3889,7 @@ static void blk_mq_exit_hw_queues(struct request_queue *q,
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (i == nr_queue)
 			break;
+		blk_mq_remove_cpuhp(hctx);
 		blk_mq_exit_hctx(q, set, hctx, i);
 	}
 }
@@ -3824,16 +3900,11 @@ static int blk_mq_init_hctx(struct request_queue *q,
 {
 	hctx->queue_num = hctx_idx;
 
-	if (!(hctx->flags & BLK_MQ_F_STACKING))
-		cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE,
-				&hctx->cpuhp_online);
-	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
-
 	hctx->tags = set->tags[hctx_idx];
 
 	if (set->ops->init_hctx &&
 	    set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
-		goto unregister_cpu_notifier;
+		goto fail;
 
 	if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx,
 				hctx->numa_node))
@@ -3850,8 +3921,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
  exit_hctx:
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
- unregister_cpu_notifier:
+ fail:
-	blk_mq_remove_cpuhp(hctx);
 	return -1;
 }
 
@@ -3877,6 +3947,8 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 	INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
 	spin_lock_init(&hctx->lock);
 	INIT_LIST_HEAD(&hctx->dispatch);
+	INIT_HLIST_NODE(&hctx->cpuhp_dead);
+	INIT_HLIST_NODE(&hctx->cpuhp_online);
 	hctx->queue = q;
 	hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED;
 
@@ -4381,7 +4453,8 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	unsigned long i, j;
 
 	/* protect against switching io scheduler  */
-	mutex_lock(&q->sysfs_lock);
+	lockdep_assert_held(&q->sysfs_lock);
+
 	for (i = 0; i < set->nr_hw_queues; i++) {
 		int old_node;
 		int node = blk_mq_get_hctx_node(set, i);
@@ -4414,7 +4487,12 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 
 	xa_for_each_start(&q->hctx_table, j, hctx, j)
 		blk_mq_exit_hctx(q, set, hctx, j);
-	mutex_unlock(&q->sysfs_lock);
+
+	/* unregister cpuhp callbacks for exited hctxs */
+	blk_mq_remove_hw_queues_cpuhp(q);
+
+	/* register cpuhp for new initialized hctxs */
+	blk_mq_add_hw_queues_cpuhp(q);
 }
 
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
@@ -4440,10 +4518,14 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 
 	xa_init(&q->hctx_table);
 
+	mutex_lock(&q->sysfs_lock);
+
 	blk_mq_realloc_hw_ctxs(set, q);
 	if (!q->nr_hw_queues)
 		goto err_hctxs;
 
+	mutex_unlock(&q->sysfs_lock);
+
 	INIT_WORK(&q->timeout_work, blk_mq_timeout_work);
 	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
 
@@ -4462,6 +4544,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	return 0;
 
 err_hctxs:
+	mutex_unlock(&q->sysfs_lock);
 	blk_mq_release(q);
 err_exit:
 	q->mq_ops = NULL;
@@ -4842,12 +4925,12 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 		return false;
 
 	/* q->elevator needs protection from ->sysfs_lock */
-	mutex_lock(&q->sysfs_lock);
+	lockdep_assert_held(&q->sysfs_lock);
 
 	/* the check has to be done with holding sysfs_lock */
 	if (!q->elevator) {
 		kfree(qe);
-		goto unlock;
+		goto out;
 	}
 
 	INIT_LIST_HEAD(&qe->node);
@@ -4857,9 +4940,7 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 	__elevator_get(qe->type);
 	list_add(&qe->node, head);
 	elevator_disable(q);
-unlock:
+out:
-	mutex_unlock(&q->sysfs_lock);
-
 	return true;
 }
 
@@ -4888,11 +4969,9 @@ static void blk_mq_elv_switch_back(struct list_head *head,
 	list_del(&qe->node);
 	kfree(qe);
 
-	mutex_lock(&q->sysfs_lock);
 	elevator_switch(q, t);
 	/* drop the reference acquired in blk_mq_elv_switch_none */
 	elevator_put(t);
-	mutex_unlock(&q->sysfs_lock);
 }
 
 static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
@@ -4912,8 +4991,11 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues)
 		return;
 
-	list_for_each_entry(q, &set->tag_list, tag_set_list)
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		mutex_lock(&q->sysfs_dir_lock);
+		mutex_lock(&q->sysfs_lock);
 		blk_mq_freeze_queue(q);
+	}
 	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done
@@ -4969,8 +5051,11 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_elv_switch_back(&head, q);
 
-	list_for_each_entry(q, &set->tag_list, tag_set_list)
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_unfreeze_queue(q);
+		mutex_unlock(&q->sysfs_lock);
+		mutex_unlock(&q->sysfs_dir_lock);
+	}
 
 	/* Free the excess tags when nr_hw_queues shrink. */
 	for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++)

block/blk-sysfs.c

@@ -263,7 +263,7 @@ static ssize_t queue_nr_zones_show(struct gendisk *disk, char *page)
 
 static ssize_t queue_iostats_passthrough_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show(blk_queue_passthrough_stat(disk->queue), page);
+	return queue_var_show(!!blk_queue_passthrough_stat(disk->queue), page);
 }
 
 static ssize_t queue_iostats_passthrough_store(struct gendisk *disk,
@@ -706,11 +706,11 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 	if (entry->load_module)
 		entry->load_module(disk, page, length);
 
-	blk_mq_freeze_queue(q);
 	mutex_lock(&q->sysfs_lock);
+	blk_mq_freeze_queue(q);
 	res = entry->store(disk, page, length);
-	mutex_unlock(&q->sysfs_lock);
 	blk_mq_unfreeze_queue(q);
+	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
 

block/blk-zoned.c

@@ -41,7 +41,6 @@ static const char *const zone_cond_name[] = {
 /*
  * Per-zone write plug.
  * @node: hlist_node structure for managing the plug using a hash table.
- * @link: To list the plug in the zone write plug error list of the disk.
  * @ref: Zone write plug reference counter. A zone write plug reference is
  *       always at least 1 when the plug is hashed in the disk plug hash table.
  *       The reference is incremented whenever a new BIO needing plugging is
@@ -63,7 +62,6 @@ static const char *const zone_cond_name[] = {
  */
 struct blk_zone_wplug {
 	struct hlist_node	node;
-	struct list_head	link;
 	refcount_t		ref;
 	spinlock_t		lock;
 	unsigned int		flags;
@@ -80,8 +78,8 @@ struct blk_zone_wplug {
  *  - BLK_ZONE_WPLUG_PLUGGED: Indicates that the zone write plug is plugged,
  *    that is, that write BIOs are being throttled due to a write BIO already
  *    being executed or the zone write plug bio list is not empty.
- *  - BLK_ZONE_WPLUG_ERROR: Indicates that a write error happened which will be
+ *  - BLK_ZONE_WPLUG_NEED_WP_UPDATE: Indicates that we lost track of a zone
- *    recovered with a report zone to update the zone write pointer offset.
+ *    write pointer offset and need to update it.
  *  - BLK_ZONE_WPLUG_UNHASHED: Indicates that the zone write plug was removed
  *    from the disk hash table and that the initial reference to the zone
  *    write plug set when the plug was first added to the hash table has been
@@ -91,11 +89,9 @@ struct blk_zone_wplug {
  *    freed once all remaining references from BIOs or functions are dropped.
  */
 #define BLK_ZONE_WPLUG_PLUGGED		(1U << 0)
-#define BLK_ZONE_WPLUG_ERROR		(1U << 1)
+#define BLK_ZONE_WPLUG_NEED_WP_UPDATE	(1U << 1)
 #define BLK_ZONE_WPLUG_UNHASHED		(1U << 2)
 
-#define BLK_ZONE_WPLUG_BUSY	(BLK_ZONE_WPLUG_PLUGGED | BLK_ZONE_WPLUG_ERROR)
-
 /**
  * blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX.
  * @zone_cond: BLK_ZONE_COND_XXX.
@@ -115,6 +111,30 @@ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond)
 }
 EXPORT_SYMBOL_GPL(blk_zone_cond_str);
 
+struct disk_report_zones_cb_args {
+	struct gendisk	*disk;
+	report_zones_cb	user_cb;
+	void		*user_data;
+};
+
+static void disk_zone_wplug_sync_wp_offset(struct gendisk *disk,
+					   struct blk_zone *zone);
+
+static int disk_report_zones_cb(struct blk_zone *zone, unsigned int idx,
+				void *data)
+{
+	struct disk_report_zones_cb_args *args = data;
+	struct gendisk *disk = args->disk;
+
+	if (disk->zone_wplugs_hash)
+		disk_zone_wplug_sync_wp_offset(disk, zone);
+
+	if (!args->user_cb)
+		return 0;
+
+	return args->user_cb(zone, idx, args->user_data);
+}
+
 /**
  * blkdev_report_zones - Get zones information
  * @bdev:	Target block device
@@ -139,6 +159,11 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 {
 	struct gendisk *disk = bdev->bd_disk;
 	sector_t capacity = get_capacity(disk);
+	struct disk_report_zones_cb_args args = {
+		.disk = disk,
+		.user_cb = cb,
+		.user_data = data,
+	};
 
 	if (!bdev_is_zoned(bdev) || WARN_ON_ONCE(!disk->fops->report_zones))
 		return -EOPNOTSUPP;
@@ -146,7 +171,8 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 	if (!nr_zones || sector >= capacity)
 		return 0;
 
-	return disk->fops->report_zones(disk, sector, nr_zones, cb, data);
+	return disk->fops->report_zones(disk, sector, nr_zones,
+					disk_report_zones_cb, &args);
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
@@ -427,7 +453,7 @@ static inline void disk_put_zone_wplug(struct blk_zone_wplug *zwplug)
 {
 	if (refcount_dec_and_test(&zwplug->ref)) {
 		WARN_ON_ONCE(!bio_list_empty(&zwplug->bio_list));
-		WARN_ON_ONCE(!list_empty(&zwplug->link));
+		WARN_ON_ONCE(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED);
 		WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_UNHASHED));
 
 		call_rcu(&zwplug->rcu_head, disk_free_zone_wplug_rcu);
@@ -441,8 +467,8 @@ static inline bool disk_should_remove_zone_wplug(struct gendisk *disk,
 	if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED)
 		return false;
 
-	/* If the zone write plug is still busy, it cannot be removed. */
+	/* If the zone write plug is still plugged, it cannot be removed. */
-	if (zwplug->flags & BLK_ZONE_WPLUG_BUSY)
+	if (zwplug->flags & BLK_ZONE_WPLUG_PLUGGED)
 		return false;
 
 	/*
@@ -525,12 +551,11 @@ static struct blk_zone_wplug *disk_get_and_lock_zone_wplug(struct gendisk *disk,
 		return NULL;
 
 	INIT_HLIST_NODE(&zwplug->node);
-	INIT_LIST_HEAD(&zwplug->link);
 	refcount_set(&zwplug->ref, 2);
 	spin_lock_init(&zwplug->lock);
 	zwplug->flags = 0;
 	zwplug->zone_no = zno;
-	zwplug->wp_offset = sector & (disk->queue->limits.chunk_sectors - 1);
+	zwplug->wp_offset = bdev_offset_from_zone_start(disk->part0, sector);
 	bio_list_init(&zwplug->bio_list);
 	INIT_WORK(&zwplug->bio_work, blk_zone_wplug_bio_work);
 	zwplug->disk = disk;
@@ -574,115 +599,22 @@ static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug)
 }
 
 /*
- * Abort (fail) all plugged BIOs of a zone write plug that are not aligned
+ * Set a zone write plug write pointer offset to the specified value.
- * with the assumed write pointer location of the zone when the BIO will
+ * This aborts all plugged BIOs, which is fine as this function is called for
- * be unplugged.
+ * a zone reset operation, a zone finish operation or if the zone needs a wp
- */
+ * update from a report zone after a write error.
-static void disk_zone_wplug_abort_unaligned(struct gendisk *disk,
-					    struct blk_zone_wplug *zwplug)
-{
-	unsigned int wp_offset = zwplug->wp_offset;
-	struct bio_list bl = BIO_EMPTY_LIST;
-	struct bio *bio;
-
-	while ((bio = bio_list_pop(&zwplug->bio_list))) {
-		if (disk_zone_is_full(disk, zwplug->zone_no, wp_offset) ||
-		    (bio_op(bio) != REQ_OP_ZONE_APPEND &&
-		     bio_offset_from_zone_start(bio) != wp_offset)) {
-			blk_zone_wplug_bio_io_error(zwplug, bio);
-			continue;
-		}
-
-		wp_offset += bio_sectors(bio);
-		bio_list_add(&bl, bio);
-	}
-
-	bio_list_merge(&zwplug->bio_list, &bl);
-}
-
-static inline void disk_zone_wplug_set_error(struct gendisk *disk,
-					     struct blk_zone_wplug *zwplug)
-{
-	unsigned long flags;
-
-	if (zwplug->flags & BLK_ZONE_WPLUG_ERROR)
-		return;
-
-	/*
-	 * At this point, we already have a reference on the zone write plug.
-	 * However, since we are going to add the plug to the disk zone write
-	 * plugs work list, increase its reference count. This reference will
-	 * be dropped in disk_zone_wplugs_work() once the error state is
-	 * handled, or in disk_zone_wplug_clear_error() if the zone is reset or
-	 * finished.
-	 */
-	zwplug->flags |= BLK_ZONE_WPLUG_ERROR;
-	refcount_inc(&zwplug->ref);
-
-	spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
-	list_add_tail(&zwplug->link, &disk->zone_wplugs_err_list);
-	spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
-}
-
-static inline void disk_zone_wplug_clear_error(struct gendisk *disk,
-					       struct blk_zone_wplug *zwplug)
-{
-	unsigned long flags;
-
-	if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR))
-		return;
-
-	/*
-	 * We are racing with the error handling work which drops the reference
-	 * on the zone write plug after handling the error state. So remove the
-	 * plug from the error list and drop its reference count only if the
-	 * error handling has not yet started, that is, if the zone write plug
-	 * is still listed.
-	 */
-	spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
-	if (!list_empty(&zwplug->link)) {
-		list_del_init(&zwplug->link);
-		zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR;
-		disk_put_zone_wplug(zwplug);
-	}
-	spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
-}
-
-/*
- * Set a zone write plug write pointer offset to either 0 (zone reset case)
- * or to the zone size (zone finish case). This aborts all plugged BIOs, which
- * is fine to do as doing a zone reset or zone finish while writes are in-flight
- * is a mistake from the user which will most likely cause all plugged BIOs to
- * fail anyway.
  */
 static void disk_zone_wplug_set_wp_offset(struct gendisk *disk,
 					  struct blk_zone_wplug *zwplug,
 					  unsigned int wp_offset)
 {
-	unsigned long flags;
+	lockdep_assert_held(&zwplug->lock);
-
-	spin_lock_irqsave(&zwplug->lock, flags);
-
-	/*
-	 * Make sure that a BIO completion or another zone reset or finish
-	 * operation has not already removed the plug from the hash table.
-	 */
-	if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) {
-		spin_unlock_irqrestore(&zwplug->lock, flags);
-		return;
-	}
 
 	/* Update the zone write pointer and abort all plugged BIOs. */
+	zwplug->flags &= ~BLK_ZONE_WPLUG_NEED_WP_UPDATE;
 	zwplug->wp_offset = wp_offset;
 	disk_zone_wplug_abort(zwplug);
 
-	/*
-	 * Updating the write pointer offset puts back the zone
-	 * in a good state. So clear the error flag and decrement the
-	 * error count if we were in error state.
-	 */
-	disk_zone_wplug_clear_error(disk, zwplug);
-
 	/*
 	 * The zone write plug now has no BIO plugged: remove it from the
 	 * hash table so that it cannot be seen. The plug will be freed
@@ -690,8 +622,58 @@ static void disk_zone_wplug_set_wp_offset(struct gendisk *disk,
 	 */
 	if (disk_should_remove_zone_wplug(disk, zwplug))
 		disk_remove_zone_wplug(disk, zwplug);
+}
 
+static unsigned int blk_zone_wp_offset(struct blk_zone *zone)
+{
+	switch (zone->cond) {
+	case BLK_ZONE_COND_IMP_OPEN:
+	case BLK_ZONE_COND_EXP_OPEN:
+	case BLK_ZONE_COND_CLOSED:
+		return zone->wp - zone->start;
+	case BLK_ZONE_COND_FULL:
+		return zone->len;
+	case BLK_ZONE_COND_EMPTY:
+		return 0;
+	case BLK_ZONE_COND_NOT_WP:
+	case BLK_ZONE_COND_OFFLINE:
+	case BLK_ZONE_COND_READONLY:
+	default:
+		/*
+		 * Conventional, offline and read-only zones do not have a valid
+		 * write pointer.
+		 */
+		return UINT_MAX;
+	}
+}
+
+static void disk_zone_wplug_sync_wp_offset(struct gendisk *disk,
+					   struct blk_zone *zone)
+{
+	struct blk_zone_wplug *zwplug;
+	unsigned long flags;
+
+	zwplug = disk_get_zone_wplug(disk, zone->start);
+	if (!zwplug)
+		return;
+
+	spin_lock_irqsave(&zwplug->lock, flags);
+	if (zwplug->flags & BLK_ZONE_WPLUG_NEED_WP_UPDATE)
+		disk_zone_wplug_set_wp_offset(disk, zwplug,
+					      blk_zone_wp_offset(zone));
 	spin_unlock_irqrestore(&zwplug->lock, flags);
+
+	disk_put_zone_wplug(zwplug);
+}
+
+static int disk_zone_sync_wp_offset(struct gendisk *disk, sector_t sector)
+{
+	struct disk_report_zones_cb_args args = {
+		.disk = disk,
+	};
+
+	return disk->fops->report_zones(disk, sector, 1,
+					disk_report_zones_cb, &args);
 }
 
 static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio,
@@ -700,6 +682,7 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio,
 	struct gendisk *disk = bio->bi_bdev->bd_disk;
 	sector_t sector = bio->bi_iter.bi_sector;
 	struct blk_zone_wplug *zwplug;
+	unsigned long flags;
 
 	/* Conventional zones cannot be reset nor finished. */
 	if (!bdev_zone_is_seq(bio->bi_bdev, sector)) {
@@ -707,6 +690,15 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio,
 		return true;
 	}
 
+	/*
+	 * No-wait reset or finish BIOs do not make much sense as the callers
+	 * issue these as blocking operations in most cases. To avoid issues
+	 * the BIO execution potentially failing with BLK_STS_AGAIN, warn about
+	 * REQ_NOWAIT being set and ignore that flag.
+	 */
+	if (WARN_ON_ONCE(bio->bi_opf & REQ_NOWAIT))
+		bio->bi_opf &= ~REQ_NOWAIT;
+
 	/*
 	 * If we have a zone write plug, set its write pointer offset to 0
 	 * (reset case) or to the zone size (finish case). This will abort all
@@ -716,7 +708,9 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio,
 	 */
 	zwplug = disk_get_zone_wplug(disk, sector);
 	if (zwplug) {
+		spin_lock_irqsave(&zwplug->lock, flags);
 		disk_zone_wplug_set_wp_offset(disk, zwplug, wp_offset);
+		spin_unlock_irqrestore(&zwplug->lock, flags);
 		disk_put_zone_wplug(zwplug);
 	}
 
@@ -727,6 +721,7 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio)
 {
 	struct gendisk *disk = bio->bi_bdev->bd_disk;
 	struct blk_zone_wplug *zwplug;
+	unsigned long flags;
 	sector_t sector;
 
 	/*
@@ -738,7 +733,9 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio)
 	     sector += disk->queue->limits.chunk_sectors) {
 		zwplug = disk_get_zone_wplug(disk, sector);
 		if (zwplug) {
+			spin_lock_irqsave(&zwplug->lock, flags);
 			disk_zone_wplug_set_wp_offset(disk, zwplug, 0);
+			spin_unlock_irqrestore(&zwplug->lock, flags);
 			disk_put_zone_wplug(zwplug);
 		}
 	}
@@ -746,9 +743,25 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio)
 	return false;
 }
 
-static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug,
+static void disk_zone_wplug_schedule_bio_work(struct gendisk *disk,
+					      struct blk_zone_wplug *zwplug)
+{
+	/*
+	 * Take a reference on the zone write plug and schedule the submission
+	 * of the next plugged BIO. blk_zone_wplug_bio_work() will release the
+	 * reference we take here.
+	 */
+	WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED));
+	refcount_inc(&zwplug->ref);
+	queue_work(disk->zone_wplugs_wq, &zwplug->bio_work);
+}
+
+static inline void disk_zone_wplug_add_bio(struct gendisk *disk,
+				struct blk_zone_wplug *zwplug,
 				struct bio *bio, unsigned int nr_segs)
 {
+	bool schedule_bio_work = false;
+
 	/*
 	 * Grab an extra reference on the BIO request queue usage counter.
 	 * This reference will be reused to submit a request for the BIO for
@@ -764,6 +777,16 @@ static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug,
 	 */
 	bio_clear_polled(bio);
 
+	/*
+	 * REQ_NOWAIT BIOs are always handled using the zone write plug BIO
+	 * work, which can block. So clear the REQ_NOWAIT flag and schedule the
+	 * work if this is the first BIO we are plugging.
+	 */
+	if (bio->bi_opf & REQ_NOWAIT) {
+		schedule_bio_work = !(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED);
+		bio->bi_opf &= ~REQ_NOWAIT;
+	}
+
 	/*
 	 * Reuse the poll cookie field to store the number of segments when
 	 * split to the hardware limits.
@@ -777,6 +800,11 @@ static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug,
 	 * at the tail of the list to preserve the sequential write order.
 	 */
 	bio_list_add(&zwplug->bio_list, bio);
+
+	zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED;
+
+	if (schedule_bio_work)
+		disk_zone_wplug_schedule_bio_work(disk, zwplug);
 }
 
 /*
@@ -889,13 +917,23 @@ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug,
 {
 	struct gendisk *disk = bio->bi_bdev->bd_disk;
 
+	/*
+	 * If we lost track of the zone write pointer due to a write error,
+	 * the user must either execute a report zones, reset the zone or finish
+	 * the to recover a reliable write pointer position. Fail BIOs if the
+	 * user did not do that as we cannot handle emulated zone append
+	 * otherwise.
+	 */
+	if (zwplug->flags & BLK_ZONE_WPLUG_NEED_WP_UPDATE)
+		return false;
+
 	/*
 	 * Check that the user is not attempting to write to a full zone.
 	 * We know such BIO will fail, and that would potentially overflow our
 	 * write pointer offset beyond the end of the zone.
 	 */
 	if (disk_zone_wplug_is_full(disk, zwplug))
-		goto err;
+		return false;
 
 	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
 		/*
@@ -914,24 +952,18 @@ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug,
 		bio_set_flag(bio, BIO_EMULATES_ZONE_APPEND);
 	} else {
 		/*
-		 * Check for non-sequential writes early because we avoid a
+		 * Check for non-sequential writes early as we know that BIOs
-		 * whole lot of error handling trouble if we don't send it off
+		 * with a start sector not unaligned to the zone write pointer
-		 * to the driver.
+		 * will fail.
 		 */
 		if (bio_offset_from_zone_start(bio) != zwplug->wp_offset)
-			goto err;
+			return false;
 	}
 
 	/* Advance the zone write pointer offset. */
 	zwplug->wp_offset += bio_sectors(bio);
 
 	return true;
-
-err:
-	/* We detected an invalid write BIO: schedule error recovery. */
-	disk_zone_wplug_set_error(disk, zwplug);
-	kblockd_schedule_work(&disk->zone_wplugs_work);
-	return false;
 }
 
 static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs)
@@ -970,6 +1002,9 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs)
 
 	zwplug = disk_get_and_lock_zone_wplug(disk, sector, gfp_mask, &flags);
 	if (!zwplug) {
+		if (bio->bi_opf & REQ_NOWAIT)
+			bio_wouldblock_error(bio);
+		else
 			bio_io_error(bio);
 		return true;
 	}
@@ -978,18 +1013,20 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs)
 	bio_set_flag(bio, BIO_ZONE_WRITE_PLUGGING);
 
 	/*
-	 * If the zone is already plugged or has a pending error, add the BIO
+	 * If the zone is already plugged, add the BIO to the plug BIO list.
-	 * to the plug BIO list. Otherwise, plug and let the BIO execute.
+	 * Do the same for REQ_NOWAIT BIOs to ensure that we will not see a
+	 * BLK_STS_AGAIN failure if we let the BIO execute.
+	 * Otherwise, plug and let the BIO execute.
 	 */
-	if (zwplug->flags & BLK_ZONE_WPLUG_BUSY)
+	if ((zwplug->flags & BLK_ZONE_WPLUG_PLUGGED) ||
+	    (bio->bi_opf & REQ_NOWAIT))
 		goto plug;
 
-	/*
+	if (!blk_zone_wplug_prepare_bio(zwplug, bio)) {
-	 * If an error is detected when preparing the BIO, add it to the BIO
+		spin_unlock_irqrestore(&zwplug->lock, flags);
-	 * list so that error recovery can deal with it.
+		bio_io_error(bio);
-	 */
+		return true;
-	if (!blk_zone_wplug_prepare_bio(zwplug, bio))
+	}
-		goto plug;
 
 	zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED;
 
@@ -998,8 +1035,7 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs)
 	return false;
 
 plug:
-	zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED;
+	disk_zone_wplug_add_bio(disk, zwplug, bio, nr_segs);
-	blk_zone_wplug_add_bio(zwplug, bio, nr_segs);
 
 	spin_unlock_irqrestore(&zwplug->lock, flags);
 
@@ -1083,19 +1119,6 @@ bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
 }
 EXPORT_SYMBOL_GPL(blk_zone_plug_bio);
 
-static void disk_zone_wplug_schedule_bio_work(struct gendisk *disk,
-					      struct blk_zone_wplug *zwplug)
-{
-	/*
-	 * Take a reference on the zone write plug and schedule the submission
-	 * of the next plugged BIO. blk_zone_wplug_bio_work() will release the
-	 * reference we take here.
-	 */
-	WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED));
-	refcount_inc(&zwplug->ref);
-	queue_work(disk->zone_wplugs_wq, &zwplug->bio_work);
-}
-
 static void disk_zone_wplug_unplug_bio(struct gendisk *disk,
 				       struct blk_zone_wplug *zwplug)
 {
@@ -1103,16 +1126,6 @@ static void disk_zone_wplug_unplug_bio(struct gendisk *disk,
 
 	spin_lock_irqsave(&zwplug->lock, flags);
 
-	/*
-	 * If we had an error, schedule error recovery. The recovery work
-	 * will restart submission of plugged BIOs.
-	 */
-	if (zwplug->flags & BLK_ZONE_WPLUG_ERROR) {
-		spin_unlock_irqrestore(&zwplug->lock, flags);
-		kblockd_schedule_work(&disk->zone_wplugs_work);
-		return;
-	}
-
 	/* Schedule submission of the next plugged BIO if we have one. */
 	if (!bio_list_empty(&zwplug->bio_list)) {
 		disk_zone_wplug_schedule_bio_work(disk, zwplug);
@@ -1155,12 +1168,13 @@ void blk_zone_write_plug_bio_endio(struct bio *bio)
 	}
 
 	/*
-	 * If the BIO failed, mark the plug as having an error to trigger
+	 * If the BIO failed, abort all plugged BIOs and mark the plug as
-	 * recovery.
+	 * needing a write pointer update.
 	 */
 	if (bio->bi_status != BLK_STS_OK) {
 		spin_lock_irqsave(&zwplug->lock, flags);
-		disk_zone_wplug_set_error(disk, zwplug);
+		disk_zone_wplug_abort(zwplug);
+		zwplug->flags |= BLK_ZONE_WPLUG_NEED_WP_UPDATE;
 		spin_unlock_irqrestore(&zwplug->lock, flags);
 	}
 
@@ -1216,6 +1230,7 @@ static void blk_zone_wplug_bio_work(struct work_struct *work)
 	 */
 	spin_lock_irqsave(&zwplug->lock, flags);
 
+again:
 	bio = bio_list_pop(&zwplug->bio_list);
 	if (!bio) {
 		zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED;
@@ -1224,10 +1239,8 @@ static void blk_zone_wplug_bio_work(struct work_struct *work)
 	}
 
 	if (!blk_zone_wplug_prepare_bio(zwplug, bio)) {
-		/* Error recovery will decide what to do with the BIO. */
+		blk_zone_wplug_bio_io_error(zwplug, bio);
-		bio_list_add_head(&zwplug->bio_list, bio);
+		goto again;
-		spin_unlock_irqrestore(&zwplug->lock, flags);
-		goto put_zwplug;
 	}
 
 	spin_unlock_irqrestore(&zwplug->lock, flags);
@@ -1249,120 +1262,6 @@ static void blk_zone_wplug_bio_work(struct work_struct *work)
 	disk_put_zone_wplug(zwplug);
 }
 
-static unsigned int blk_zone_wp_offset(struct blk_zone *zone)
-{
-	switch (zone->cond) {
-	case BLK_ZONE_COND_IMP_OPEN:
-	case BLK_ZONE_COND_EXP_OPEN:
-	case BLK_ZONE_COND_CLOSED:
-		return zone->wp - zone->start;
-	case BLK_ZONE_COND_FULL:
-		return zone->len;
-	case BLK_ZONE_COND_EMPTY:
-		return 0;
-	case BLK_ZONE_COND_NOT_WP:
-	case BLK_ZONE_COND_OFFLINE:
-	case BLK_ZONE_COND_READONLY:
-	default:
-		/*
-		 * Conventional, offline and read-only zones do not have a valid
-		 * write pointer.
-		 */
-		return UINT_MAX;
-	}
-}
-
-static int blk_zone_wplug_report_zone_cb(struct blk_zone *zone,
-					 unsigned int idx, void *data)
-{
-	struct blk_zone *zonep = data;
-
-	*zonep = *zone;
-	return 0;
-}
-
-static void disk_zone_wplug_handle_error(struct gendisk *disk,
-					 struct blk_zone_wplug *zwplug)
-{
-	sector_t zone_start_sector =
-		bdev_zone_sectors(disk->part0) * zwplug->zone_no;
-	unsigned int noio_flag;
-	struct blk_zone zone;
-	unsigned long flags;
-	int ret;
-
-	/* Get the current zone information from the device. */
-	noio_flag = memalloc_noio_save();
-	ret = disk->fops->report_zones(disk, zone_start_sector, 1,
-				       blk_zone_wplug_report_zone_cb, &zone);
-	memalloc_noio_restore(noio_flag);
-
-	spin_lock_irqsave(&zwplug->lock, flags);
-
-	/*
-	 * A zone reset or finish may have cleared the error already. In such
-	 * case, do nothing as the report zones may have seen the "old" write
-	 * pointer value before the reset/finish operation completed.
-	 */
-	if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR))
-		goto unlock;
-
-	zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR;
-
-	if (ret != 1) {
-		/*
-		 * We failed to get the zone information, meaning that something
-		 * is likely really wrong with the device. Abort all remaining
-		 * plugged BIOs as otherwise we could endup waiting forever on
-		 * plugged BIOs to complete if there is a queue freeze on-going.
-		 */
-		disk_zone_wplug_abort(zwplug);
-		goto unplug;
-	}
-
-	/* Update the zone write pointer offset. */
-	zwplug->wp_offset = blk_zone_wp_offset(&zone);
-	disk_zone_wplug_abort_unaligned(disk, zwplug);
-
-	/* Restart BIO submission if we still have any BIO left. */
-	if (!bio_list_empty(&zwplug->bio_list)) {
-		disk_zone_wplug_schedule_bio_work(disk, zwplug);
-		goto unlock;
-	}
-
-unplug:
-	zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED;
-	if (disk_should_remove_zone_wplug(disk, zwplug))
-		disk_remove_zone_wplug(disk, zwplug);
-
-unlock:
-	spin_unlock_irqrestore(&zwplug->lock, flags);
-}
-
-static void disk_zone_wplugs_work(struct work_struct *work)
-{
-	struct gendisk *disk =
-		container_of(work, struct gendisk, zone_wplugs_work);
-	struct blk_zone_wplug *zwplug;
-	unsigned long flags;
-
-	spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
-
-	while (!list_empty(&disk->zone_wplugs_err_list)) {
-		zwplug = list_first_entry(&disk->zone_wplugs_err_list,
-					  struct blk_zone_wplug, link);
-		list_del_init(&zwplug->link);
-		spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
-
-		disk_zone_wplug_handle_error(disk, zwplug);
-		disk_put_zone_wplug(zwplug);
-
-		spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
-	}
-
-	spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
-}
-
 static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk)
 {
 	return 1U << disk->zone_wplugs_hash_bits;
@@ -1371,8 +1270,6 @@ static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk)
 void disk_init_zone_resources(struct gendisk *disk)
 {
 	spin_lock_init(&disk->zone_wplugs_lock);
-	INIT_LIST_HEAD(&disk->zone_wplugs_err_list);
-	INIT_WORK(&disk->zone_wplugs_work, disk_zone_wplugs_work);
 }
 
 /*
@@ -1471,8 +1368,6 @@ void disk_free_zone_resources(struct gendisk *disk)
 	if (!disk->zone_wplugs_pool)
 		return;
 
-	cancel_work_sync(&disk->zone_wplugs_work);
-
 	if (disk->zone_wplugs_wq) {
 		destroy_workqueue(disk->zone_wplugs_wq);
 		disk->zone_wplugs_wq = NULL;
@@ -1669,6 +1564,8 @@ static int blk_revalidate_seq_zone(struct blk_zone *zone, unsigned int idx,
 	if (!disk->zone_wplugs_hash)
 		return 0;
 
+	disk_zone_wplug_sync_wp_offset(disk, zone);
+
 	wp_offset = blk_zone_wp_offset(zone);
 	if (!wp_offset || wp_offset >= zone->capacity)
 		return 0;
@@ -1799,6 +1696,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 		memalloc_noio_restore(noio_flag);
 		return ret;
 	}
+
 	ret = disk->fops->report_zones(disk, 0, UINT_MAX,
 				       blk_revalidate_zone_cb, &args);
 	if (!ret) {
@@ -1835,6 +1733,48 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
 
+/**
+ * blk_zone_issue_zeroout - zero-fill a block range in a zone
+ * @bdev:	blockdev to write
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to write
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ *  Zero-fill a block range in a zone (@sector must be equal to the zone write
+ *  pointer), handling potential errors due to the (initially unknown) lack of
+ *  hardware offload (See blkdev_issue_zeroout()).
+ */
+int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector,
+			   sector_t nr_sects, gfp_t gfp_mask)
+{
+	int ret;
+
+	if (WARN_ON_ONCE(!bdev_is_zoned(bdev)))
+		return -EIO;
+
+	ret = blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask,
+				   BLKDEV_ZERO_NOFALLBACK);
+	if (ret != -EOPNOTSUPP)
+		return ret;
+
+	/*
+	 * The failed call to blkdev_issue_zeroout() advanced the zone write
+	 * pointer. Undo this using a report zone to update the zone write
+	 * pointer to the correct current value.
+	 */
+	ret = disk_zone_sync_wp_offset(bdev->bd_disk, sector);
+	if (ret != 1)
+		return ret < 0 ? ret : -EIO;
+
+	/*
+	 * Retry without BLKDEV_ZERO_NOFALLBACK to force the fallback to a
+	 * regular write with zero-pages.
+	 */
+	return blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask, 0);
+}
+EXPORT_SYMBOL_GPL(blk_zone_issue_zeroout);
+
 #ifdef CONFIG_BLK_DEBUG_FS
 
 int queue_zone_wplugs_show(void *data, struct seq_file *m)

block/mq-deadline.c

@@ -698,8 +698,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		list_add(&rq->queuelist, &per_prio->dispatch);
 		rq->fifo_time = jiffies;
 	} else {
-		struct list_head *insert_before;
-
 		deadline_add_rq_rb(per_prio, rq);
 
 		if (rq_mergeable(rq)) {
@@ -712,8 +710,7 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		 * set expire time and add to fifo list
 		 */
 		rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
-		insert_before = &per_prio->fifo_list[data_dir];
+		list_add_tail(&rq->queuelist, &per_prio->fifo_list[data_dir]);
-		list_add_tail(&rq->queuelist, insert_before);
 	}
 }
 

crypto/rsassa-pkcs1.c

@@ -163,10 +163,6 @@ static int rsassa_pkcs1_sign(struct crypto_sig *tfm,
 	struct rsassa_pkcs1_inst_ctx *ictx = sig_instance_ctx(inst);
 	const struct hash_prefix *hash_prefix = ictx->hash_prefix;
 	struct rsassa_pkcs1_ctx *ctx = crypto_sig_ctx(tfm);
-	unsigned int child_reqsize = crypto_akcipher_reqsize(ctx->child);
-	struct akcipher_request *child_req __free(kfree_sensitive) = NULL;
-	struct scatterlist in_sg[3], out_sg;
-	struct crypto_wait cwait;
 	unsigned int pad_len;
 	unsigned int ps_end;
 	unsigned int len;
@@ -187,37 +183,25 @@ static int rsassa_pkcs1_sign(struct crypto_sig *tfm,
 
 	pad_len = ctx->key_size - slen - hash_prefix->size - 1;
 
-	child_req = kmalloc(sizeof(*child_req) + child_reqsize + pad_len,
-			    GFP_KERNEL);
-	if (!child_req)
-		return -ENOMEM;
-
 	/* RFC 8017 sec 8.2.1 step 1 - EMSA-PKCS1-v1_5 encoding generation */
-	in_buf = (u8 *)(child_req + 1) + child_reqsize;
+	in_buf = dst;
+	memmove(in_buf + pad_len + hash_prefix->size, src, slen);
+	memcpy(in_buf + pad_len, hash_prefix->data, hash_prefix->size);
+
 	ps_end = pad_len - 1;
 	in_buf[0] = 0x01;
 	memset(in_buf + 1, 0xff, ps_end - 1);
 	in_buf[ps_end] = 0x00;
 
-	/* RFC 8017 sec 8.2.1 step 2 - RSA signature */
-	crypto_init_wait(&cwait);
-	sg_init_table(in_sg, 3);
-	sg_set_buf(&in_sg[0], in_buf, pad_len);
-	sg_set_buf(&in_sg[1], hash_prefix->data, hash_prefix->size);
-	sg_set_buf(&in_sg[2], src, slen);
-	sg_init_one(&out_sg, dst, dlen);
-	akcipher_request_set_tfm(child_req, ctx->child);
-	akcipher_request_set_crypt(child_req, in_sg, &out_sg,
-				   ctx->key_size - 1, dlen);
-	akcipher_request_set_callback(child_req, CRYPTO_TFM_REQ_MAY_SLEEP,
-				      crypto_req_done, &cwait);
 
-	err = crypto_akcipher_decrypt(child_req);
+	/* RFC 8017 sec 8.2.1 step 2 - RSA signature */
-	err = crypto_wait_req(err, &cwait);
+	err = crypto_akcipher_sync_decrypt(ctx->child, in_buf,
-	if (err)
+					   ctx->key_size - 1, in_buf,
+					   ctx->key_size);
+	if (err < 0)
 		return err;
 
-	len = child_req->dst_len;
+	len = err;
 	pad_len = ctx->key_size - len;
 
 	/* Four billion to one */
@@ -239,8 +223,8 @@ static int rsassa_pkcs1_verify(struct crypto_sig *tfm,
 	struct rsassa_pkcs1_ctx *ctx = crypto_sig_ctx(tfm);
 	unsigned int child_reqsize = crypto_akcipher_reqsize(ctx->child);
 	struct akcipher_request *child_req __free(kfree_sensitive) = NULL;
-	struct scatterlist in_sg, out_sg;
 	struct crypto_wait cwait;
+	struct scatterlist sg;
 	unsigned int dst_len;
 	unsigned int pos;
 	u8 *out_buf;
@@ -259,13 +243,12 @@ static int rsassa_pkcs1_verify(struct crypto_sig *tfm,
 		return -ENOMEM;
 
 	out_buf = (u8 *)(child_req + 1) + child_reqsize;
+	memcpy(out_buf, src, slen);
 
 	crypto_init_wait(&cwait);
-	sg_init_one(&in_sg, src, slen);
+	sg_init_one(&sg, out_buf, slen);
-	sg_init_one(&out_sg, out_buf, ctx->key_size);
 	akcipher_request_set_tfm(child_req, ctx->child);
-	akcipher_request_set_crypt(child_req, &in_sg, &out_sg,
+	akcipher_request_set_crypt(child_req, &sg, &sg, slen, slen);
-				   slen, ctx->key_size);
 	akcipher_request_set_callback(child_req, CRYPTO_TFM_REQ_MAY_SLEEP,
 				      crypto_req_done, &cwait);
 

drivers/acpi/acpica/evxfregn.c

@@ -232,8 +232,6 @@ acpi_remove_address_space_handler(acpi_handle device,
 
 			/* Now we can delete the handler object */
 
-			acpi_os_release_mutex(handler_obj->address_space.
-					      context_mutex);
 			acpi_ut_remove_reference(handler_obj);
 			goto unlock_and_exit;
 		}

drivers/acpi/arm64/iort.c

@@ -1716,6 +1716,8 @@ static struct acpi_platform_list pmcg_plat_info[] __initdata = {
 	/* HiSilicon Hip09 Platform */
 	{"HISI  ", "HIP09   ", 0, ACPI_SIG_IORT, greater_than_or_equal,
 	 "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09},
+	{"HISI  ", "HIP09A  ", 0, ACPI_SIG_IORT, greater_than_or_equal,
+	 "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09},
 	/* HiSilicon Hip10/11 Platform uses the same SMMU IP with Hip09 */
 	{"HISI  ", "HIP10   ", 0, ACPI_SIG_IORT, greater_than_or_equal,
 	 "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09},

drivers/acpi/nfit/core.c

@@ -454,8 +454,13 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 	if (cmd_rc)
 		*cmd_rc = -EINVAL;
 
-	if (cmd == ND_CMD_CALL)
+	if (cmd == ND_CMD_CALL) {
+		if (!buf || buf_len < sizeof(*call_pkg))
+			return -EINVAL;
+
 		call_pkg = buf;
+	}
+
 	func = cmd_to_func(nfit_mem, cmd, call_pkg, &family);
 	if (func < 0)
 		return func;

drivers/acpi/resource.c

@@ -250,6 +250,9 @@ static bool acpi_decode_space(struct resource_win *win,
 	switch (addr->resource_type) {
 	case ACPI_MEMORY_RANGE:
 		acpi_dev_memresource_flags(res, len, wp);
+
+		if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY)
+			res->flags |= IORESOURCE_PREFETCH;
 		break;
 	case ACPI_IO_RANGE:
 		acpi_dev_ioresource_flags(res, len, iodec,
@@ -265,9 +268,6 @@ static bool acpi_decode_space(struct resource_win *win,
 	if (addr->producer_consumer == ACPI_PRODUCER)
 		res->flags |= IORESOURCE_WINDOW;
 
-	if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY)
-		res->flags |= IORESOURCE_PREFETCH;
-
 	return !(res->flags & IORESOURCE_DISABLED);
 }
 

drivers/ata/sata_highbank.c

@@ -348,6 +348,7 @@ static int highbank_initialize_phys(struct device *dev, void __iomem *addr)
 			phy_nodes[phy] = phy_data.np;
 			cphy_base[phy] = of_iomap(phy_nodes[phy], 0);
 			if (cphy_base[phy] == NULL) {
+				of_node_put(phy_data.np);
 				return 0;
 			}
 			phy_count += 1;

drivers/base/arch_numa.c

@@ -208,6 +208,10 @@ static int __init numa_register_nodes(void)
 {
 	int nid;
 
+	/* Check the validity of the memblock/node mapping */
+	if (!memblock_validate_numa_coverage(0))
+		return -EINVAL;
+
 	/* Finally register nodes. */
 	for_each_node_mask(nid, numa_nodes_parsed) {
 		unsigned long start_pfn, end_pfn;

drivers/base/cacheinfo.c

@@ -58,7 +58,7 @@ bool last_level_cache_is_valid(unsigned int cpu)
 {
 	struct cacheinfo *llc;
 
-	if (!cache_leaves(cpu))
+	if (!cache_leaves(cpu) || !per_cpu_cacheinfo(cpu))
 		return false;
 
 	llc = per_cpu_cacheinfo_idx(cpu, cache_leaves(cpu) - 1);
@@ -458,11 +458,9 @@ int __weak populate_cache_leaves(unsigned int cpu)
 	return -ENOENT;
 }
 
-static inline
+static inline int allocate_cache_info(int cpu)
-int allocate_cache_info(int cpu)
 {
-	per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu),
+	per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu), sizeof(struct cacheinfo), GFP_ATOMIC);
-					 sizeof(struct cacheinfo), GFP_ATOMIC);
 	if (!per_cpu_cacheinfo(cpu)) {
 		cache_leaves(cpu) = 0;
 		return -ENOMEM;
@@ -534,7 +532,11 @@ static inline int init_level_allocate_ci(unsigned int cpu)
 	 */
 	ci_cacheinfo(cpu)->early_ci_levels = false;
 
-	if (cache_leaves(cpu) <= early_leaves)
+	/*
+	 * Some architectures (e.g., x86) do not use early initialization.
+	 * Allocate memory now in such case.
+	 */
+	if (cache_leaves(cpu) <= early_leaves && per_cpu_cacheinfo(cpu))
 		return 0;
 
 	kfree(per_cpu_cacheinfo(cpu));

drivers/base/regmap/regmap.c

@@ -598,6 +598,17 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 }
 EXPORT_SYMBOL_GPL(regmap_attach_dev);
 
+static int dev_get_regmap_match(struct device *dev, void *res, void *data);
+
+static int regmap_detach_dev(struct device *dev, struct regmap *map)
+{
+	if (!dev)
+		return 0;
+
+	return devres_release(dev, dev_get_regmap_release,
+			      dev_get_regmap_match, (void *)map->name);
+}
+
 static enum regmap_endian regmap_get_reg_endian(const struct regmap_bus *bus,
 					const struct regmap_config *config)
 {
@@ -1052,13 +1063,13 @@ struct regmap *__regmap_init(struct device *dev,
 
 		/* Sanity check */
 		if (range_cfg->range_max < range_cfg->range_min) {
-			dev_err(map->dev, "Invalid range %d: %d < %d\n", i,
+			dev_err(map->dev, "Invalid range %d: %u < %u\n", i,
 				range_cfg->range_max, range_cfg->range_min);
 			goto err_range;
 		}
 
 		if (range_cfg->range_max > map->max_register) {
-			dev_err(map->dev, "Invalid range %d: %d > %d\n", i,
+			dev_err(map->dev, "Invalid range %d: %u > %u\n", i,
 				range_cfg->range_max, map->max_register);
 			goto err_range;
 		}
@@ -1445,6 +1456,7 @@ void regmap_exit(struct regmap *map)
 {
 	struct regmap_async *async;
 
+	regmap_detach_dev(map->dev, map);
 	regcache_exit(map);
 
 	regmap_debugfs_exit(map);

drivers/block/rnull.rs

@@ -28,6 +28,7 @@
     type: NullBlkModule,
     name: "rnull_mod",
     author: "Andreas Hindborg",
+    description: "Rust implementation of the C null block driver",
     license: "GPL v2",
 }
 

drivers/block/virtio_blk.c

@@ -1586,9 +1586,12 @@ static void virtblk_remove(struct virtio_device *vdev)
 static int virtblk_freeze(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
+	struct request_queue *q = vblk->disk->queue;
 
 	/* Ensure no requests in virtqueues before deleting vqs. */
-	blk_mq_freeze_queue(vblk->disk->queue);
+	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue_nowait(q);
+	blk_mq_unfreeze_queue(q);
 
 	/* Ensure we don't receive any more interrupts */
 	virtio_reset_device(vdev);
@@ -1612,8 +1615,8 @@ static int virtblk_restore(struct virtio_device *vdev)
 		return ret;
 
 	virtio_device_ready(vdev);
+	blk_mq_unquiesce_queue(vblk->disk->queue);
 
-	blk_mq_unfreeze_queue(vblk->disk->queue);
 	return 0;
 }
 #endif

drivers/bluetooth/btmtk.c

@@ -395,6 +395,7 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct btmtk_data *data = hci_get_priv(hdev);
 	int err;
+	bool complete = false;
 
 	if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) {
 		kfree_skb(skb);
@@ -416,16 +417,19 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb)
 		fallthrough;
 	case HCI_DEVCOREDUMP_ACTIVE:
 	default:
+		/* Mediatek coredump data would be more than MTK_COREDUMP_NUM */
+		if (data->cd_info.cnt >= MTK_COREDUMP_NUM &&
+		    skb->len > MTK_COREDUMP_END_LEN)
+			if (!memcmp((char *)&skb->data[skb->len - MTK_COREDUMP_END_LEN],
+				    MTK_COREDUMP_END, MTK_COREDUMP_END_LEN - 1))
+				complete = true;
+
 		err = hci_devcd_append(hdev, skb);
 		if (err < 0)
 			break;
 		data->cd_info.cnt++;
 
-		/* Mediatek coredump data would be more than MTK_COREDUMP_NUM */
+		if (complete) {
-		if (data->cd_info.cnt > MTK_COREDUMP_NUM &&
-		    skb->len > MTK_COREDUMP_END_LEN)
-			if (!memcmp((char *)&skb->data[skb->len - MTK_COREDUMP_END_LEN],
-				    MTK_COREDUMP_END, MTK_COREDUMP_END_LEN - 1)) {
 			bt_dev_info(hdev, "Mediatek coredump end");
 			hci_devcd_complete(hdev);
 		}

drivers/cdx/Makefile

@@ -5,7 +5,7 @@
 # Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
 #
 
-ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=CDX_BUS
+ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE='"CDX_BUS"'
 
 obj-$(CONFIG_CDX_BUS) += cdx.o controller/