Merge tag 'i2c-host-fixes-6.15-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/andi.shyti/linux into i2c/for-current

i2c-host-fixes for v6.15-rc5

- imx-lpi2c: fix error handling sequence in probe

Documentation/admin-guide/xfs.rst

···
 Zoned Filesystems
 =================
 
-For zoned file systems, the following attribute is exposed in:
+For zoned file systems, the following attributes are exposed in:
 
   /sys/fs/xfs/<dev>/zoned/
 
···
 	is limited by the capabilities of the backing zoned device, file system
 	size and the max_open_zones mount option.
 
-Zoned Filesystems
-=================
-
-For zoned file systems, the following attributes are exposed in:
-
- /sys/fs/xfs/<dev>/zoned/
-
- max_open_zones                 (Min:  1  Default:  Varies  Max:  UINTMAX)
-        This read-only attribute exposes the maximum number of open zones
-        available for data placement. The value is determined at mount time and
-        is limited by the capabilities of the backing zoned device, file system
-        size and the max_open_zones mount option.
-
- zonegc_low_space               (Min:  0  Default:  0  Max:  100)
-        Define a percentage for how much of the unused space that GC should keep
-        available for writing. A high value will reclaim more of the space
-        occupied by unused blocks, creating a larger buffer against write
-        bursts at the cost of increased write amplification.  Regardless
-        of this value, garbage collection will always aim to free a minimum
-        amount of blocks to keep max_open_zones open for data placement purposes.
+  zonegc_low_space		(Min:  0  Default:  0  Max:  100)
+	Define a percentage for how much of the unused space that GC should keep
+	available for writing. A high value will reclaim more of the space
+	occupied by unused blocks, creating a larger buffer against write
+	bursts at the cost of increased write amplification.  Regardless
+	of this value, garbage collection will always aim to free a minimum
+	amount of blocks to keep max_open_zones open for data placement purposes.

Documentation/arch/openrisc/openrisc_port.rst

···
 
 For information about OpenRISC processors and ongoing development:
 
-	=======		=============================
+	=======		==============================
 	website		https://openrisc.io
-	email		[e-mail]
-	=======		=============================
+	email		[e-mail]
+	=======		==============================
 
 ---------------------------------------------------------------------
 
···
 Instructions for building the different toolchains can be found on openrisc.io
 or Stafford's toolchain build and release scripts.
 
-	==========	=================================================
-	binaries	https://github.com/openrisc/or1k-gcc/releases
+	==========	==========================================================
+	binaries	https://github.com/stffrdhrn/or1k-toolchain-build/releases
 	toolchains	https://openrisc.io/software
 	building	https://github.com/stffrdhrn/or1k-toolchain-build
-	==========	=================================================
+	==========	==========================================================
 
 2) Building
 

Documentation/bpf/bpf_devel_QA.rst

···
 into the Linux kernel, please implement support into LLVM's BPF back
 end. See LLVM_ section below for further information.
 
+Q: What "BPF_INTERNAL" symbol namespace is for?
+-----------------------------------------------
+A: Symbols exported as BPF_INTERNAL can only be used by BPF infrastructure
+like preload kernel modules with light skeleton. Most symbols outside
+of BPF_INTERNAL are not expected to be used by code outside of BPF either.
+Symbols may lack the designation because they predate the namespaces,
+or due to an oversight.
+
 Stable submission
 =================
 

Documentation/devicetree/bindings/nvmem/layouts/fixed-cell.yaml

···
     $ref: /schemas/types.yaml#/definitions/uint32-array
     items:
       - minimum: 0
-        maximum: 7
+        maximum: 31
         description:
           Offset in bit within the address range specified by reg.
       - minimum: 1

Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml

···
       - enum:
           - qcom,apq8064-qfprom
           - qcom,apq8084-qfprom
+          - qcom,ipq5018-qfprom
           - qcom,ipq5332-qfprom
           - qcom,ipq5424-qfprom
           - qcom,ipq6018-qfprom
···
           - qcom,msm8226-qfprom
           - qcom,msm8916-qfprom
           - qcom,msm8917-qfprom
+          - qcom,msm8937-qfprom
+          - qcom,msm8960-qfprom
           - qcom,msm8974-qfprom
           - qcom,msm8976-qfprom
           - qcom,msm8996-qfprom
···
           - qcom,sm8450-qfprom
           - qcom,sm8550-qfprom
           - qcom,sm8650-qfprom
+          - qcom,x1e80100-qfprom
       - const: qcom,qfprom
 
   reg:

Documentation/devicetree/bindings/nvmem/rockchip,otp.yaml

···
     enum:
       - rockchip,px30-otp
       - rockchip,rk3308-otp
+      - rockchip,rk3576-otp
       - rockchip,rk3588-otp
 
   reg:
···
       properties:
         clocks:
           maxItems: 3
+        clock-names:
+          maxItems: 3
         resets:
           maxItems: 1
         reset-names:
···
         compatible:
           contains:
             enum:
+              - rockchip,rk3576-otp
+    then:
+      properties:
+        clocks:
+          maxItems: 3
+        clock-names:
+          maxItems: 3
+        resets:
+          minItems: 2
+          maxItems: 2
+        reset-names:
+          items:
+            - const: otp
+            - const: apb
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
               - rockchip,rk3588-otp
     then:
       properties:
         clocks:
+          minItems: 4
+        clock-names:
           minItems: 4
         resets:
           minItems: 3

Documentation/translations/zh_CN/arch/openrisc/openrisc_port.rst

···
 
 关于OpenRISC处理器和正在进行中的开发的信息:
 
-	=======		=============================
+	=======		==============================
 	网站		https://openrisc.io
-	邮箱		[e-mail]
-	=======		=============================
+	邮箱		[e-mail]
+	=======		==============================
 
 ---------------------------------------------------------------------
 
···
 工具链的构建指南可以在openrisc.io或Stafford的工具链构建和发布脚本
 中找到。
 
-	======      =================================================
-	二进制      https://github.com/openrisc/or1k-gcc/releases
+	======      ==========================================================
+	二进制      https://github.com/stffrdhrn/or1k-toolchain-build/releases
 	工具链      https://openrisc.io/software
 	构建        https://github.com/stffrdhrn/or1k-toolchain-build
-	======      =================================================
+	======      ==========================================================
 
 2) 构建
 

Documentation/translations/zh_TW/arch/openrisc/openrisc_port.rst

···
 
 關於OpenRISC處理器和正在進行中的開發的信息:
 
-	=======		=============================
+	=======		==============================
 	網站		https://openrisc.io
-	郵箱		[e-mail]
-	=======		=============================
+	郵箱		[e-mail]
+	=======		==============================
 
 ---------------------------------------------------------------------
 
···
 工具鏈的構建指南可以在openrisc.io或Stafford的工具鏈構建和發佈腳本
 中找到。
 
-	======      =================================================
-	二進制      https://github.com/openrisc/or1k-gcc/releases
+	======      ==========================================================
+	二進制      https://github.com/stffrdhrn/or1k-toolchain-build/releases
 	工具鏈      https://openrisc.io/software
 	構建        https://github.com/stffrdhrn/or1k-toolchain-build
-	======      =================================================
+	======      ==========================================================
 
 2) 構建
 

MAINTAINERS

···
 S:	Maintained
 F:	drivers/clk/socfpga/
 
+ARM/SOCFPGA DWMAC GLUE LAYER
+M:	Maxime Chevallier <[e-mail]>
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/socfpga-dwmac.txt
+F:	drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+
 ARM/SOCFPGA EDAC BINDINGS
 M:	Matthew Gerlach <[e-mail]>
 S:	Maintained
···
 M:	Greg Kroah-Hartman <[e-mail]>
 R:	Dave Ertman <[e-mail]>
 R:	Ira Weiny <[e-mail]>
+R:	Leon Romanovsky <[e-mail]>
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
 F:	Documentation/driver-api/auxiliary_bus.rst
 F:	drivers/base/auxiliary.c
 F:	include/linux/auxiliary_bus.h
···
 M:	"Rafael J. Wysocki" <[e-mail]>
 M:	Danilo Krummrich <[e-mail]>
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
 F:	Documentation/core-api/kobject.rst
 F:	drivers/base/
 F:	fs/debugfs/
···
 F:	drivers/infiniband/hw/hfi1
 
 HFS FILESYSTEM
+M:	Viacheslav Dubeyko <[e-mail]>
+M:	John Paul Adrian Glaubitz <[e-mail]>
+M:	Yangtao Li <[e-mail]>
 L:	[e-mail]
-S:	Orphan
+S:	Maintained
 F:	Documentation/filesystems/hfs.rst
 F:	fs/hfs/
 
 HFSPLUS FILESYSTEM
+M:	Viacheslav Dubeyko <[e-mail]>
+M:	John Paul Adrian Glaubitz <[e-mail]>
+M:	Yangtao Li <[e-mail]>
 L:	[e-mail]
-S:	Orphan
+S:	Maintained
 F:	Documentation/filesystems/hfsplus.rst
 F:	fs/hfsplus/
 
···
 M:	Greg Kroah-Hartman <[e-mail]>
 M:	Tejun Heo <[e-mail]>
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
 F:	fs/kernfs/
 F:	include/linux/kernfs.h
 
···
 F:	drivers/connector/
 F:	drivers/net/
 F:	drivers/ptp/
+F:	drivers/s390/net/
 F:	include/dt-bindings/net/
 F:	include/linux/cn_proc.h
 F:	include/linux/etherdevice.h
···
 F:	include/linux/hippidevice.h
 F:	include/linux/if_*
 F:	include/linux/inetdevice.h
+F:	include/linux/ism.h
 F:	include/linux/netdev*
 F:	include/linux/platform_data/wiznet.h
 F:	include/uapi/linux/cn_proc.h
···
 PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS
 M:	Lorenzo Pieralisi <[e-mail]>
 M:	Krzysztof Wilczyński <[e-mail]>
-R:	Manivannan Sadhasivam <[e-mail]>
+M:	Manivannan Sadhasivam <[e-mail]>
 R:	Rob Herring <[e-mail]>
 L:	[e-mail]
 S:	Supported
···
 F:	include/linux/of_pci.h
 F:	include/linux/pci*
 F:	include/uapi/linux/pci*
+
+PCI SUBSYSTEM [RUST]
+M:	Danilo Krummrich <[e-mail]>
+R:	Bjorn Helgaas <[e-mail]>
+R:	Krzysztof Wilczyński <[e-mail]>
+L:	[e-mail]
+S:	Maintained
+C:	irc://irc.oftc.net/linux-pci
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git
+F:	rust/helpers/pci.c
 F:	rust/kernel/pci.rs
 F:	samples/rust/rust_driver_pci.rs
 
···
 L:	[e-mail]
 S:	Supported
 F:	drivers/s390/net/
+F:	include/linux/ism.h
 
 S390 PCI SUBSYSTEM
 M:	Niklas Schnelle <[e-mail]>
···
 F:	drivers/usb/typec/mux/pi3usb30532.c
 
 USB TYPEC PORT CONTROLLER DRIVERS
+M:	Badhri Jagan Sridharan <[e-mail]>
 L:	[e-mail]
-S:	Orphan
-F:	drivers/usb/typec/tcpm/
+S:	Maintained
+F:	drivers/usb/typec/tcpm/tcpci.c
+F:	drivers/usb/typec/tcpm/tcpm.c
+F:	include/linux/usb/tcpci.h
+F:	include/linux/usb/tcpm.h
 
 USB TYPEC TUSB1046 MUX DRIVER
 M:	Romain Gantois <[e-mail]>

Makefile

···
 VERSION = 6
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
···
 KBUILD_CFLAGS += $(call cc-option, -fstrict-flex-arrays=3)
 
 #Currently, disable -Wstringop-overflow for GCC 11, globally.
-KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow)
+KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-disable-warning, stringop-overflow)
 KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow)
 
-#Currently, disable -Wunterminated-string-initialization as an error
-KBUILD_CFLAGS += $(call cc-option, -Wno-error=unterminated-string-initialization)
+#Currently, disable -Wunterminated-string-initialization as broken
+KBUILD_CFLAGS += $(call cc-disable-warning, unterminated-string-initialization)
 
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= -fno-strict-overflow

arch/arm64/include/asm/kvm_host.h

···
 #define kvm_has_s1poe(k)				\
 	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
 
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+	return true;
+}
+
 #endif /* __ARM64_KVM_HOST_H__ */

arch/arm64/include/asm/mmu.h

···
 			return false;
 	}
 
-	/*
-	 * Systems affected by Cavium erratum 24756 are incompatible
-	 * with KPTI.
-	 */
-	if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) {
-		extern const struct midr_range cavium_erratum_27456_cpus[];
-
-		if (is_midr_in_range_list(cavium_erratum_27456_cpus))
-			return false;
-	}
-
 	return true;
 }
 

arch/arm64/kernel/cpu_errata.c

···
 #endif
 
 #ifdef CONFIG_CAVIUM_ERRATUM_27456
-const struct midr_range cavium_erratum_27456_cpus[] = {
+static const struct midr_range cavium_erratum_27456_cpus[] = {
 	/* Cavium ThunderX, T88 pass 1.x - 2.1 */
 	MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
 	/* Cavium ThunderX, T81 pass 1.0 */

arch/arm64/kernel/image-vars.h

···
 PROVIDE(__pi_id_aa64zfr0_override	= id_aa64zfr0_override);
 PROVIDE(__pi_arm64_sw_feature_override	= arm64_sw_feature_override);
 PROVIDE(__pi_arm64_use_ng_mappings	= arm64_use_ng_mappings);
-#ifdef CONFIG_CAVIUM_ERRATUM_27456
-PROVIDE(__pi_cavium_erratum_27456_cpus	= cavium_erratum_27456_cpus);
-PROVIDE(__pi_is_midr_in_range_list	= is_midr_in_range_list);
-#endif
 PROVIDE(__pi__ctype			= _ctype);
 PROVIDE(__pi_memstart_offset_seed	= memstart_offset_seed);
 

arch/arm64/kernel/pi/map_kernel.c

···
 	dsb(ishst);
 }
 
+/*
+ * PI version of the Cavium Eratum 27456 detection, which makes it
+ * impossible to use non-global mappings.
+ */
+static bool __init ng_mappings_allowed(void)
+{
+	static const struct midr_range cavium_erratum_27456_cpus[] __initconst = {
+		/* Cavium ThunderX, T88 pass 1.x - 2.1 */
+		MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1),
+		/* Cavium ThunderX, T81 pass 1.0 */
+		MIDR_REV(MIDR_THUNDERX_81XX, 0, 0),
+		{},
+	};
+
+	for (const struct midr_range *r = cavium_erratum_27456_cpus; r->model; r++) {
+		if (midr_is_cpu_model_range(read_cpuid_id(), r->model,
+					    r->rv_min, r->rv_max))
+			return false;
+	}
+
+	return true;
+}
+
 asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt)
 {
 	static char const chosen_str[] __initconst = "/chosen";
···
 		u64 kaslr_seed = kaslr_early_init(fdt, chosen);
 
 		if (kaslr_seed && kaslr_requires_kpti())
-			arm64_use_ng_mappings = true;
+			arm64_use_ng_mappings = ng_mappings_allowed();
 
 		kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1);
 	}

arch/arm64/kvm/arm.c

···
 	return irqchip_in_kernel(kvm);
 }
 
-bool kvm_arch_has_irq_bypass(void)
-{
-	return true;
-}
-
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 				      struct irq_bypass_producer *prod)
 {

arch/loongarch/Kconfig

···
 	select ARCH_SUPPORTS_RT
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_DEFAULT_BPF_JIT

arch/loongarch/include/asm/fpu.h

···
 struct sigcontext;
 
 #define kernel_fpu_available() cpu_has_fpu
-extern void kernel_fpu_begin(void);
-extern void kernel_fpu_end(void);
 
-extern void _init_fpu(unsigned int);
-extern void _save_fp(struct loongarch_fpu *);
-extern void _restore_fp(struct loongarch_fpu *);
+void kernel_fpu_begin(void);
+void kernel_fpu_end(void);
 
-extern void _save_lsx(struct loongarch_fpu *fpu);
-extern void _restore_lsx(struct loongarch_fpu *fpu);
-extern void _init_lsx_upper(void);
-extern void _restore_lsx_upper(struct loongarch_fpu *fpu);
+asmlinkage void _init_fpu(unsigned int);
+asmlinkage void _save_fp(struct loongarch_fpu *);
+asmlinkage void _restore_fp(struct loongarch_fpu *);
+asmlinkage int _save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
+asmlinkage int _restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
 
-extern void _save_lasx(struct loongarch_fpu *fpu);
-extern void _restore_lasx(struct loongarch_fpu *fpu);
-extern void _init_lasx_upper(void);
-extern void _restore_lasx_upper(struct loongarch_fpu *fpu);
+asmlinkage void _save_lsx(struct loongarch_fpu *fpu);
+asmlinkage void _restore_lsx(struct loongarch_fpu *fpu);
+asmlinkage void _init_lsx_upper(void);
+asmlinkage void _restore_lsx_upper(struct loongarch_fpu *fpu);
+asmlinkage int _save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+asmlinkage int _restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+
+asmlinkage void _save_lasx(struct loongarch_fpu *fpu);
+asmlinkage void _restore_lasx(struct loongarch_fpu *fpu);
+asmlinkage void _init_lasx_upper(void);
+asmlinkage void _restore_lasx_upper(struct loongarch_fpu *fpu);
+asmlinkage int _save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
+asmlinkage int _restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
 
 static inline void enable_lsx(void);
 static inline void disable_lsx(void);

arch/loongarch/include/asm/lbt.h

···
 #include <asm/loongarch.h>
 #include <asm/processor.h>
 
-extern void _init_lbt(void);
-extern void _save_lbt(struct loongarch_lbt *);
-extern void _restore_lbt(struct loongarch_lbt *);
+asmlinkage void _init_lbt(void);
+asmlinkage void _save_lbt(struct loongarch_lbt *);
+asmlinkage void _restore_lbt(struct loongarch_lbt *);
+asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
+asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
+asmlinkage int _save_ftop_context(void __user *ftop);
+asmlinkage int _restore_ftop_context(void __user *ftop);
 
 static inline int is_lbt_enabled(void)
 {

arch/loongarch/include/asm/ptrace.h

···
 	unsigned long __last[];
 } __aligned(8);
 
-static inline int regs_irqs_disabled(struct pt_regs *regs)
+static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
 {
-	return arch_irqs_disabled_flags(regs->csr_prmd);
+	return !(regs->csr_prmd & CSR_PRMD_PIE);
 }
 
 static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)

arch/loongarch/kernel/Makefile

···
 
 obj-$(CONFIG_ARCH_STRICT_ALIGN)	+= unaligned.o
 
-CFLAGS_module.o		+= $(call cc-option,-Wno-override-init,)
-CFLAGS_syscall.o	+= $(call cc-option,-Wno-override-init,)
-CFLAGS_traps.o		+= $(call cc-option,-Wno-override-init,)
-CFLAGS_perf_event.o	+= $(call cc-option,-Wno-override-init,)
+CFLAGS_module.o		+= $(call cc-disable-warning, override-init)
+CFLAGS_syscall.o	+= $(call cc-disable-warning, override-init)
+CFLAGS_traps.o		+= $(call cc-disable-warning, override-init)
+CFLAGS_perf_event.o	+= $(call cc-disable-warning, override-init)
 
 ifdef CONFIG_FUNCTION_TRACER
   ifndef CONFIG_DYNAMIC_FTRACE

arch/loongarch/kernel/fpu.S

···
 	li.w		a0, 0				# success
 	jr		ra
 SYM_FUNC_END(_save_fp_context)
+EXPORT_SYMBOL_GPL(_save_fp_context)
 
 /*
  * a0: fpregs
···
 	li.w		a0, 0				# success
 	jr		ra
 SYM_FUNC_END(_restore_fp_context)
+EXPORT_SYMBOL_GPL(_restore_fp_context)
 
 /*
  * a0: fpregs
···
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_save_lsx_context)
+EXPORT_SYMBOL_GPL(_save_lsx_context)
 
 /*
  * a0: fpregs
···
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_restore_lsx_context)
+EXPORT_SYMBOL_GPL(_restore_lsx_context)
 
 /*
  * a0: fpregs
···
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_save_lasx_context)
+EXPORT_SYMBOL_GPL(_save_lasx_context)
 
 /*
  * a0: fpregs
···
 	li.w	a0, 0					# success
 	jr	ra
 SYM_FUNC_END(_restore_lasx_context)
+EXPORT_SYMBOL_GPL(_restore_lasx_context)
 
 .L_fpu_fault:
 	li.w	a0, -EFAULT				# failure

arch/loongarch/kernel/lbt.S

···
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_save_lbt_context)
+EXPORT_SYMBOL_GPL(_save_lbt_context)
 
 /*
  * a0: scr
···
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_restore_lbt_context)
+EXPORT_SYMBOL_GPL(_restore_lbt_context)
 
 /*
  * a0: ftop
···
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_save_ftop_context)
+EXPORT_SYMBOL_GPL(_save_ftop_context)
 
 /*
  * a0: ftop
···
 	li.w		a0, 0			# success
 	jr		ra
 SYM_FUNC_END(_restore_ftop_context)
+EXPORT_SYMBOL_GPL(_restore_ftop_context)
 
 .L_lbt_fault:
 	li.w		a0, -EFAULT		# failure

arch/loongarch/kernel/signal.c

···
 #define lock_lbt_owner()	({ preempt_disable(); pagefault_disable(); })
 #define unlock_lbt_owner()	({ pagefault_enable(); preempt_enable(); })
 
-/* Assembly functions to move context to/from the FPU */
-extern asmlinkage int
-_save_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern asmlinkage int
-_restore_fp_context(void __user *fpregs, void __user *fcc, void __user *csr);
-extern asmlinkage int
-_save_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_restore_lsx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-extern asmlinkage int
-_restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
-
-#ifdef CONFIG_CPU_HAS_LBT
-extern asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
-extern asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
-extern asmlinkage int _save_ftop_context(void __user *ftop);
-extern asmlinkage int _restore_ftop_context(void __user *ftop);
-#endif
-
 struct rt_sigframe {
 	struct siginfo rs_info;
 	struct ucontext rs_uctx;

arch/loongarch/kernel/traps.c

···
 	die_if_kernel("Kernel ale access", regs);
 	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
 #else
+	bool pie = regs_irqs_disabled(regs);
 	unsigned int *pc;
 
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr);
···
 	die_if_kernel("Kernel ale access", regs);
 	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 #endif
 	irqentry_exit(regs, state);
···
 asmlinkage void noinstr do_bce(struct pt_regs *regs)
 {
 	bool user = user_mode(regs);
+	bool pie = regs_irqs_disabled(regs);
 	unsigned long era = exception_era(regs);
 	u64 badv = 0, lower = 0, upper = ULONG_MAX;
 	union loongarch_instruction insn;
 	irqentry_state_t state = irqentry_enter(regs);
 
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	current->thread.trap_nr = read_csr_excode();
···
 	force_sig_bnderr((void __user *)badv, (void __user *)lower, (void __user *)upper);
 
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 
 	irqentry_exit(regs, state);
···
 asmlinkage void noinstr do_bp(struct pt_regs *regs)
 {
 	bool user = user_mode(regs);
+	bool pie = regs_irqs_disabled(regs);
 	unsigned int opcode, bcode;
 	unsigned long era = exception_era(regs);
 	irqentry_state_t state = irqentry_enter(regs);
 
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	if (__get_inst(&opcode, (u32 *)era, user))
···
 	}
 
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 
 	irqentry_exit(regs, state);
···
 
 asmlinkage void noinstr do_lbt(struct pt_regs *regs)
 {
+	bool pie = regs_irqs_disabled(regs);
 	irqentry_state_t state = irqentry_enter(regs);
 
 	/*
···
 	 * (including the user using 'MOVGR2GCSR' to turn on TM, which
 	 * will not trigger the BTE), we need to check PRMD first.
 	 */
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_enable();
 
 	if (!cpu_has_lbt) {
···
 	preempt_enable();
 
 out:
-	if (regs->csr_prmd & CSR_PRMD_PIE)
+	if (!pie)
 		local_irq_disable();
 
 	irqentry_exit(regs, state);

arch/loongarch/kvm/Makefile

···
 kvm-y += intc/pch_pic.o
 kvm-y += irqfd.o
 
-CFLAGS_exit.o	+= $(call cc-option,-Wno-override-init,)
+CFLAGS_exit.o	+= $(call cc-disable-warning, override-init)

arch/loongarch/kvm/intc/ipi.c

···
 		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);
+			kvm_err("%s: : read data from addr %llx failed\n", __func__, addr);
 			return ret;
 		}
 		/* Construct the mask by scanning the bit 27-30 */
···
 	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);
+		kvm_err("%s: : write data to addr %llx failed\n", __func__, addr);
 
 	return ret;
 }

arch/loongarch/kvm/main.c

···
 	/*
 	 * Enable virtualization features granting guest direct control of
 	 * certain features:
-	 * GCI=2:       Trap on init or unimplement cache instruction.
+	 * GCI=2:       Trap on init or unimplemented cache instruction.
 	 * TORU=0:      Trap on Root Unimplement.
 	 * CACTRL=1:    Root control cache.
-	 * TOP=0:       Trap on Previlege.
+	 * TOP=0:       Trap on Privilege.
 	 * TOE=0:       Trap on Exception.
 	 * TIT=0:       Trap on Timer.
 	 */

arch/loongarch/kvm/vcpu.c

···
 		vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST;
 
 		if (kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending()) {
+			kvm_lose_pmu(vcpu);
 			/* make sure the vcpu mode has been written */
 			smp_store_mb(vcpu->mode, OUTSIDE_GUEST_MODE);
 			local_irq_enable();
···
 			vcpu->arch.st.guest_addr = 0;
 			memset(&vcpu->arch.irq_pending, 0, sizeof(vcpu->arch.irq_pending));
 			memset(&vcpu->arch.irq_clear, 0, sizeof(vcpu->arch.irq_clear));
+
+			/*
+			 * When vCPU reset, clear the ESTAT and GINTC registers
+			 * Other CSR registers are cleared with function _kvm_setcsr().
+			 */
+			kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_GINTC, 0);
+			kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_ESTAT, 0);
 			break;
 		default:
 			ret = -EINVAL;

arch/loongarch/mm/hugetlbpage.c

···
 				pmd = pmd_offset(pud, addr);
 		}
 	}
-	return (pte_t *) pmd;
+	return pmd_none(pmdp_get(pmd)) ? NULL : (pte_t *) pmd;
 }
 
 uint64_t pmd_to_entrylo(unsigned long pmd_val)

arch/loongarch/mm/init.c

···
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES];
 
-#ifdef CONFIG_ZONE_DMA
-	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
-#endif
 #ifdef CONFIG_ZONE_DMA32
 	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
 #endif

arch/openrisc/include/asm/cacheflush.h

···
  */
 extern void local_dcache_page_flush(struct page *page);
 extern void local_icache_page_inv(struct page *page);
+extern void local_dcache_range_flush(unsigned long start, unsigned long end);
+extern void local_dcache_range_inv(unsigned long start, unsigned long end);
+extern void local_icache_range_inv(unsigned long start, unsigned long end);
 
 /*
  * Data cache flushing always happen on the local cpu. Instruction cache
···
 #define icache_page_inv(page)        smp_icache_page_inv(page)
 extern void smp_icache_page_inv(struct page *page);
 #endif /* CONFIG_SMP */
+
+/*
+ * Even if the actual block size is larger than L1_CACHE_BYTES, paddr
+ * can be incremented by L1_CACHE_BYTES. When paddr is written to the
+ * invalidate register, the entire cache line encompassing this address
+ * is invalidated. Each subsequent reference to the same cache line will
+ * not affect the invalidation process.
+ */
+#define local_dcache_block_flush(addr) \
+	local_dcache_range_flush(addr, addr + L1_CACHE_BYTES)
+#define local_dcache_block_inv(addr) \
+	local_dcache_range_inv(addr, addr + L1_CACHE_BYTES)
+#define local_icache_block_inv(addr) \
+	local_icache_range_inv(addr, addr + L1_CACHE_BYTES)
 
 /*
  * Synchronizes caches. Whenever a cpu writes executable code to memory, this

arch/openrisc/include/asm/cpuinfo.h

···
 #ifndef __ASM_OPENRISC_CPUINFO_H
 #define __ASM_OPENRISC_CPUINFO_H
 
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
+struct cache_desc {
+	u32 size;
+	u32 sets;
+	u32 block_size;
+	u32 ways;
+};
+
 struct cpuinfo_or1k {
 	u32 clock_frequency;
 
-	u32 icache_size;
-	u32 icache_block_size;
-	u32 icache_ways;
-
-	u32 dcache_size;
-	u32 dcache_block_size;
-	u32 dcache_ways;
+	struct cache_desc icache;
+	struct cache_desc dcache;
 
 	u16 coreid;
 };
 
 extern struct cpuinfo_or1k cpuinfo_or1k[NR_CPUS];
 extern void setup_cpuinfo(void);
+
+/*
+ * Check if the cache component exists.
+ */
+extern bool cpu_cache_is_present(const unsigned int cache_type);
 
 #endif /* __ASM_OPENRISC_CPUINFO_H */

arch/openrisc/kernel/Makefile

···
 
 obj-y	:= head.o setup.o or32_ksyms.o process.o dma.o \
 	   traps.o time.o irq.o entry.o ptrace.o signal.o \
-	   sys_call_table.o unwinder.o
+	   sys_call_table.o unwinder.o cacheinfo.o
 
 obj-$(CONFIG_SMP)		+= smp.o sync-timer.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o

arch/openrisc/kernel/cacheinfo.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * OpenRISC cacheinfo support
+ *
+ * Based on work done for MIPS and LoongArch. All original copyrights
+ * apply as per the original source declaration.
+ *
+ * OpenRISC implementation:
+ * Copyright (C) 2025 Sahil Siddiq <[e-mail]>
+ */
+
+#include <linux/cacheinfo.h>
+#include <asm/cpuinfo.h>
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
+static inline void ci_leaf_init(struct cacheinfo *this_leaf, enum cache_type type,
+				unsigned int level, struct cache_desc *cache, int cpu)
+{
+	this_leaf->type = type;
+	this_leaf->level = level;
+	this_leaf->coherency_line_size = cache->block_size;
+	this_leaf->number_of_sets = cache->sets;
+	this_leaf->ways_of_associativity = cache->ways;
+	this_leaf->size = cache->size;
+	cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+}
+
+int init_cache_level(unsigned int cpu)
+{
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	int leaves = 0, levels = 0;
+	unsigned long upr = mfspr(SPR_UPR);
+	unsigned long iccfgr, dccfgr;
+
+	if (!(upr & SPR_UPR_UP)) {
+		printk(KERN_INFO
+		       "-- no UPR register... unable to detect configuration\n");
+		return -ENOENT;
+	}
+
+	if (cpu_cache_is_present(SPR_UPR_DCP)) {
+		dccfgr = mfspr(SPR_DCCFGR);
+		cpuinfo->dcache.ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
+		cpuinfo->dcache.sets = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
+		cpuinfo->dcache.block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
+		cpuinfo->dcache.size =
+		    cpuinfo->dcache.sets * cpuinfo->dcache.ways * cpuinfo->dcache.block_size;
+		leaves += 1;
+		printk(KERN_INFO
+		       "-- dcache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n",
+		       cpuinfo->dcache.size, cpuinfo->dcache.block_size,
+		       cpuinfo->dcache.sets, cpuinfo->dcache.ways);
+	} else
+		printk(KERN_INFO "-- dcache disabled\n");
+
+	if (cpu_cache_is_present(SPR_UPR_ICP)) {
+		iccfgr = mfspr(SPR_ICCFGR);
+		cpuinfo->icache.ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
+		cpuinfo->icache.sets = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
+		cpuinfo->icache.block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
+		cpuinfo->icache.size =
+		    cpuinfo->icache.sets * cpuinfo->icache.ways * cpuinfo->icache.block_size;
+		leaves += 1;
+		printk(KERN_INFO
+		       "-- icache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n",
+		       cpuinfo->icache.size, cpuinfo->icache.block_size,
+		       cpuinfo->icache.sets, cpuinfo->icache.ways);
+	} else
+		printk(KERN_INFO "-- icache disabled\n");
+
+	if (!leaves)
+		return -ENOENT;
+
+	levels = 1;
+
+	this_cpu_ci->num_leaves = leaves;
+	this_cpu_ci->num_levels = levels;
+
+	return 0;
+}
+
+int populate_cache_leaves(unsigned int cpu)
+{
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+	int level = 1;
+
+	if (cpu_cache_is_present(SPR_UPR_DCP)) {
+		ci_leaf_init(this_leaf, CACHE_TYPE_DATA, level, &cpuinfo->dcache, cpu);
+		this_leaf->attributes = ((mfspr(SPR_DCCFGR) & SPR_DCCFGR_CWS) >> 8) ?
+					CACHE_WRITE_BACK : CACHE_WRITE_THROUGH;
+		this_leaf++;
+	}
+
+	if (cpu_cache_is_present(SPR_UPR_ICP))
+		ci_leaf_init(this_leaf, CACHE_TYPE_INST, level, &cpuinfo->icache, cpu);
+
+	this_cpu_ci->cpu_map_populated = true;
+
+	return 0;
+}

arch/openrisc/kernel/dma.c

···
 #include <linux/pagewalk.h>
 
 #include <asm/cpuinfo.h>
+#include <asm/cacheflush.h>
 #include <asm/spr_defs.h>
 #include <asm/tlbflush.h>
 
···
 page_set_nocache(pte_t *pte, unsigned long addr,
 		 unsigned long next, struct mm_walk *walk)
 {
-	unsigned long cl;
-	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
 	pte_val(*pte) |= _PAGE_CI;
 
 	/*
···
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 
 	/* Flush page out of dcache */
-	for (cl = __pa(addr); cl < __pa(next); cl += cpuinfo->dcache_block_size)
-		mtspr(SPR_DCBFR, cl);
+	local_dcache_range_flush(__pa(addr), __pa(next));
 
 	return 0;
 }
···
 void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
 		enum dma_data_direction dir)
 {
-	unsigned long cl;
-	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
 	switch (dir) {
 	case DMA_TO_DEVICE:
 		/* Flush the dcache for the requested range */
-		for (cl = addr; cl < addr + size;
-		     cl += cpuinfo->dcache_block_size)
-			mtspr(SPR_DCBFR, cl);
+		local_dcache_range_flush(addr, addr + size);
 		break;
 	case DMA_FROM_DEVICE:
 		/* Invalidate the dcache for the requested range */
-		for (cl = addr; cl < addr + size;
-		     cl += cpuinfo->dcache_block_size)
-			mtspr(SPR_DCBIR, cl);
+		local_dcache_range_inv(addr, addr + size);
 		break;
 	default:
 		/*

arch/openrisc/kernel/setup.c

···
 		return;
 	}
 
-	if (upr & SPR_UPR_DCP)
-		printk(KERN_INFO
-		       "-- dcache: %4d bytes total, %2d bytes/line, %d way(s)\n",
-		       cpuinfo->dcache_size, cpuinfo->dcache_block_size,
-		       cpuinfo->dcache_ways);
-	else
-		printk(KERN_INFO "-- dcache disabled\n");
-	if (upr & SPR_UPR_ICP)
-		printk(KERN_INFO
-		       "-- icache: %4d bytes total, %2d bytes/line, %d way(s)\n",
-		       cpuinfo->icache_size, cpuinfo->icache_block_size,
-		       cpuinfo->icache_ways);
-	else
-		printk(KERN_INFO "-- icache disabled\n");
-
 	if (upr & SPR_UPR_DMP)
 		printk(KERN_INFO "-- dmmu: %4d entries, %lu way(s)\n",
 		       1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
···
 void __init setup_cpuinfo(void)
 {
 	struct device_node *cpu;
-	unsigned long iccfgr, dccfgr;
-	unsigned long cache_set_size;
 	int cpu_id = smp_processor_id();
 	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[cpu_id];
 
 	cpu = of_get_cpu_node(cpu_id, NULL);
 	if (!cpu)
 		panic("Couldn't find CPU%d in device tree...\n", cpu_id);
-
-	iccfgr = mfspr(SPR_ICCFGR);
-	cpuinfo->icache_ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
-	cache_set_size = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
-	cpuinfo->icache_block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
-	cpuinfo->icache_size =
-	    cache_set_size * cpuinfo->icache_ways * cpuinfo->icache_block_size;
-
-	dccfgr = mfspr(SPR_DCCFGR);
-	cpuinfo->dcache_ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
-	cache_set_size = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
-	cpuinfo->dcache_block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
-	cpuinfo->dcache_size =
-	    cache_set_size * cpuinfo->dcache_ways * cpuinfo->dcache_block_size;
 
 	if (of_property_read_u32(cpu, "clock-frequency",
 				 &cpuinfo->clock_frequency)) {
···
 	unsigned int vr, cpucfgr;
 	unsigned int avr;
 	unsigned int version;
+#ifdef CONFIG_SMP
 	struct cpuinfo_or1k *cpuinfo = v;
+	seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
+#endif
 
 	vr = mfspr(SPR_VR);
 	cpucfgr = mfspr(SPR_CPUCFGR);
 
-#ifdef CONFIG_SMP
-	seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
-#endif
 	if (vr & SPR_VR_UVRP) {
 		vr = mfspr(SPR_VR2);
 		version = vr & SPR_VR2_VER;
···
 		seq_printf(m, "revision\t\t: %d\n", vr & SPR_VR_REV);
 	}
 	seq_printf(m, "frequency\t\t: %ld\n", loops_per_jiffy * HZ);
-	seq_printf(m, "dcache size\t\t: %d bytes\n", cpuinfo->dcache_size);
-	seq_printf(m, "dcache block size\t: %d bytes\n",
-		   cpuinfo->dcache_block_size);
-	seq_printf(m, "dcache ways\t\t: %d\n", cpuinfo->dcache_ways);
-	seq_printf(m, "icache size\t\t: %d bytes\n", cpuinfo->icache_size);
-	seq_printf(m, "icache block size\t: %d bytes\n",
-		   cpuinfo->icache_block_size);
-	seq_printf(m, "icache ways\t\t: %d\n", cpuinfo->icache_ways);
 	seq_printf(m, "immu\t\t\t: %d entries, %lu ways\n",
 		   1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
 		   1 + (mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTW));

arch/openrisc/mm/cache.c

···
 #include <asm/spr_defs.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
+#include <asm/cpuinfo.h>
 #include <asm/tlbflush.h>
 
-static __always_inline void cache_loop(struct page *page, const unsigned int reg)
+/*
+ * Check if the cache component exists.
+ */
+bool cpu_cache_is_present(const unsigned int cache_type)
+{
+	unsigned long upr = mfspr(SPR_UPR);
+	unsigned long mask = SPR_UPR_UP | cache_type;
+
+	return !((upr & mask) ^ mask);
+}
+
+static __always_inline void cache_loop(unsigned long paddr, unsigned long end,
+				       const unsigned short reg, const unsigned int cache_type)
+{
+	if (!cpu_cache_is_present(cache_type))
+		return;
+
+	while (paddr < end) {
+		mtspr(reg, paddr);
+		paddr += L1_CACHE_BYTES;
+	}
+}
+
+static __always_inline void cache_loop_page(struct page *page, const unsigned short reg,
+					    const unsigned int cache_type)
 {
 	unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
-	unsigned long line = paddr & ~(L1_CACHE_BYTES - 1);
+	unsigned long end = paddr + PAGE_SIZE;
 
-	while (line < paddr + PAGE_SIZE) {
-		mtspr(reg, line);
-		line += L1_CACHE_BYTES;
-	}
+	paddr &= ~(L1_CACHE_BYTES - 1);
+
+	cache_loop(paddr, end, reg, cache_type);
 }
 
 void local_dcache_page_flush(struct page *page)
 {
-	cache_loop(page, SPR_DCBFR);
+	cache_loop_page(page, SPR_DCBFR, SPR_UPR_DCP);
 }
 EXPORT_SYMBOL(local_dcache_page_flush);
 
 void local_icache_page_inv(struct page *page)
 {
-	cache_loop(page, SPR_ICBIR);
+	cache_loop_page(page, SPR_ICBIR, SPR_UPR_ICP);
 }
 EXPORT_SYMBOL(local_icache_page_inv);
+
+void local_dcache_range_flush(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_DCBFR, SPR_UPR_DCP);
+}
+
+void local_dcache_range_inv(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_DCBIR, SPR_UPR_DCP);
+}
+
+void local_icache_range_inv(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_ICBIR, SPR_UPR_ICP);
+}
 
 void update_cache(struct vm_area_struct *vma, unsigned long address,
 	pte_t *pte)
···
 			sync_icache_dcache(folio_page(folio, nr));
 	}
 }
-

arch/openrisc/mm/init.c

···
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
+#include <asm/cacheflush.h>
 
 int mem_init_done;
 
···
 	barrier();
 
 	/* Invalidate instruction caches after code modification */
-	mtspr(SPR_ICBIR, 0x900);
-	mtspr(SPR_ICBIR, 0xa00);
+	local_icache_block_inv(0x900);
+	local_icache_block_inv(0xa00);
 
 	/* New TLB miss handlers and kernel page tables are in now place.
 	 * Make sure that page flags get updated for all pages in TLB by

arch/riscv/include/asm/cacheflush.h

···
 	flush_dcache_folio(page_folio(page));
 }
 
-/*
- * RISC-V doesn't have an instruction to flush parts of the instruction cache,
- * so instead we just flush the whole thing.
- */
-#define flush_icache_range(start, end) flush_icache_all()
 #define flush_icache_user_page(vma, pg, addr, len)	\
 do {							\
 	if (vma->vm_flags & VM_EXEC)			\
···
 void flush_icache_mm(struct mm_struct *mm, bool local);
 
 #endif /* CONFIG_SMP */
+
+/*
+ * RISC-V doesn't have an instruction to flush parts of the instruction cache,
+ * so instead we just flush the whole thing.
+ */
+#define flush_icache_range flush_icache_range
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+	flush_icache_all();
+}
 
 extern unsigned int riscv_cbom_block_size;
 extern unsigned int riscv_cboz_block_size;

arch/riscv/kernel/Makefile

···
 CFLAGS_REMOVE_sbi.o	= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_return_address.o	= $(CC_FLAGS_FTRACE)
 endif
-CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
-CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_table.o	+= $(call cc-disable-warning, override-init)
+CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init)
 
 ifdef CONFIG_KEXEC_CORE
 AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)

arch/riscv/kernel/probes/uprobes.c

···
 	/* Initialize the slot */
 	void *kaddr = kmap_atomic(page);
 	void *dst = kaddr + (vaddr & ~PAGE_MASK);
+	unsigned long start = (unsigned long)dst;
 
 	memcpy(dst, src, len);
 
···
 		*(uprobe_opcode_t *)dst = __BUG_INSN_32;
 	}
 
+	flush_icache_range(start, start + len);
 	kunmap_atomic(kaddr);
-
-	/*
-	 * We probably need flush_icache_user_page() but it needs vma.
-	 * This should work on most of architectures by default. If
-	 * architecture needs to do something different it can define
-	 * its own version of the function.
-	 */
-	flush_dcache_page(page);
 }

arch/x86/boot/Makefile

···
 $(obj)/bzImage: asflags-y  := $(SVGA_MODE)
 
 quiet_cmd_image = BUILD   $@
-      cmd_image = cp $< $@; truncate -s %4K $@; cat $(obj)/vmlinux.bin >>$@
+      cmd_image = (dd if=$< bs=4k conv=sync status=none; cat $(filter-out $<,$(real-prereqs))) >$@
 
 $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin FORCE
 	$(call if_changed,image)

arch/x86/events/core.c

···
 	if (event->attr.type == event->pmu->type)
 		event->hw.config |= x86_pmu_get_event_config(event);
 
-	if (!event->attr.freq && x86_pmu.limit_period) {
+	if (is_sampling_event(event) && !event->attr.freq && x86_pmu.limit_period) {
 		s64 left = event->attr.sample_period;
 		x86_pmu.limit_period(event, &left);
 		if (left > event->attr.sample_period)

arch/x86/include/asm/kvm_host.h

···
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
 #include <asm/asm.h>
+#include <asm/irq_remapping.h>
 #include <asm/kvm_page_track.h>
 #include <asm/kvm_vcpu_regs.h>
 #include <asm/reboot.h>
···
  * remaining 31 lower bits must be 0 to preserve ABI.
  */
 #define KVM_EXIT_HYPERCALL_MBZ		GENMASK_ULL(31, 1)
+
+static inline bool kvm_arch_has_irq_bypass(void)
+{
+	return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
+}
 
 #endif /* _ASM_X86_KVM_HOST_H */

arch/x86/include/asm/pgalloc.h

···
 #include <linux/mm.h>		/* for struct page */
 #include <linux/pagemap.h>
 
+#include <asm/cpufeature.h>
+
 #define __HAVE_ARCH_PTE_ALLOC_ONE
 #define __HAVE_ARCH_PGD_FREE
 #include <asm-generic/pgalloc.h>
···
 static inline void paravirt_release_p4d(unsigned long pfn) {}
 #endif
 
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
- * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
- * both 8k in size and 8k-aligned.  That lets us just flip bit 12
- * in a pointer to swap between the two 4k halves.
+ * In case of Page Table Isolation active, we acquire two PGDs instead of one.
+ * Being order-1, it is both 8k in size and 8k-aligned.  That lets us just
+ * flip bit 12 in a pointer to swap between the two 4k halves.
  */
-#define PGD_ALLOCATION_ORDER 1
-#else
-#define PGD_ALLOCATION_ORDER 0
-#endif
+static inline unsigned int pgd_allocation_order(void)
+{
+	if (cpu_feature_enabled(X86_FEATURE_PTI))
+		return 1;
+	return 0;
+}
 
 /*
  * Allocate and free page tables.

arch/x86/kernel/e820.c

···
 		memblock_add(entry->addr, entry->size);
 	}
 
+	/*
+	 * 32-bit systems are limited to 4BG of memory even with HIGHMEM and
+	 * to even less without it.
+	 * Discard memory after max_pfn - the actual limit detected at runtime.
+	 */
+	if (IS_ENABLED(CONFIG_X86_32))
+		memblock_remove(PFN_PHYS(max_pfn), -1);
+
 	/* Throw away partial pages: */
 	memblock_trim_memory(PAGE_SIZE);
 

arch/x86/kernel/machine_kexec_32.c

···
 
 static void machine_kexec_free_page_tables(struct kimage *image)
 {
-	free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
+	free_pages((unsigned long)image->arch.pgd, pgd_allocation_order());
 	image->arch.pgd = NULL;
 #ifdef CONFIG_X86_PAE
 	free_page((unsigned long)image->arch.pmd0);
···
 static int machine_kexec_alloc_page_tables(struct kimage *image)
 {
 	image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
-						    PGD_ALLOCATION_ORDER);
+						    pgd_allocation_order());
 #ifdef CONFIG_X86_PAE
 	image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
 	image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);

arch/x86/kvm/svm/avic.c

···
 	struct amd_svm_iommu_ir *ir;
 	u64 entry;
 
+	if (WARN_ON_ONCE(!pi->ir_data))
+		return -EINVAL;
+
 	/**
 	 * In some cases, the existing irte is updated and re-set,
 	 * so we need to check here if it's already been * added
 	 * to the ir_list.
 	 */
-	if (pi->ir_data && (pi->prev_ga_tag != 0)) {
+	if (pi->prev_ga_tag) {
 		struct kvm *kvm = svm->vcpu.kvm;
 		u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
 		struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
···
 	 * Allocating new amd_iommu_pi_data, which will get
 	 * add to the per-vcpu ir_list.
 	 */
-	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT);
+	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT);
 	if (!ir) {
 		ret = -ENOMEM;
 		goto out;
···
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
+	bool enable_remapped_mode = true;
 	int idx, ret = 0;
 
-	if (!kvm_arch_has_assigned_device(kvm) ||
-	    !irq_remapping_cap(IRQ_POSTING_CAP))
+	if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
 		return 0;
 
 	pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
···
 		    kvm_vcpu_apicv_active(&svm->vcpu)) {
 			struct amd_iommu_pi_data pi;
 
+			enable_remapped_mode = false;
+
 			/* Try to enable guest_mode in IRTE */
 			pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
 					    AVIC_HPA_MASK);
···
 			 */
 			if (!ret && pi.is_guest_mode)
 				svm_ir_list_add(svm, &pi);
-		} else {
-			/* Use legacy mode in IRTE */
-			struct amd_iommu_pi_data pi;
-
-			/**
-			 * Here, pi is used to:
-			 * - Tell IOMMU to use legacy mode for this interrupt.
-			 * - Retrieve ga_tag of prior interrupt remapping data.
-			 */
-			pi.prev_ga_tag = 0;
-			pi.is_guest_mode = false;
-			ret = irq_set_vcpu_affinity(host_irq, &pi);
-
-			/**
-			 * Check if the posted interrupt was previously
-			 * setup with the guest_mode by checking if the ga_tag
-			 * was cached. If so, we need to clean up the per-vcpu
-			 * ir_list.
-			 */
-			if (!ret && pi.prev_ga_tag) {
-				int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
-				struct kvm_vcpu *vcpu;
-
-				vcpu = kvm_get_vcpu_by_id(kvm, id);
-				if (vcpu)
-					svm_ir_list_del(to_svm(vcpu), &pi);
-			}
 		}
 
 		if (!ret && svm) {
···
 	}
 
 	ret = 0;
+	if (enable_remapped_mode) {
+		/* Use legacy mode in IRTE */
+		struct amd_iommu_pi_data pi;
+
+		/**
+		 * Here, pi is used to:
+		 * - Tell IOMMU to use legacy mode for this interrupt.
+		 * - Retrieve ga_tag of prior interrupt remapping data.
+		 */
+		pi.prev_ga_tag = 0;
+		pi.is_guest_mode = false;
+		ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+		/**
+		 * Check if the posted interrupt was previously
+		 * setup with the guest_mode by checking if the ga_tag
+		 * was cached. If so, we need to clean up the per-vcpu
+		 * ir_list.
+		 */
+		if (!ret && pi.prev_ga_tag) {
+			int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+			struct kvm_vcpu *vcpu;
+
+			vcpu = kvm_get_vcpu_by_id(kvm, id);
+			if (vcpu)
+				svm_ir_list_del(to_svm(vcpu), &pi);
+		}
+	}
 out:
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 	return ret;

arch/x86/kvm/trace.h

···
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
 
+#ifdef CREATE_TRACE_POINTS
+#define tracing_kvm_rip_read(vcpu) ({					\
+	typeof(vcpu) __vcpu = vcpu;					\
+	__vcpu->arch.guest_state_protected ? 0 : kvm_rip_read(__vcpu);	\
+	})
+#endif
+
 /*
  * Tracepoint for guest mode entry.
  */
···
 
 	TP_fast_assign(
 		__entry->vcpu_id        = vcpu->vcpu_id;
-		__entry->rip		= kvm_rip_read(vcpu);
+		__entry->rip		= tracing_kvm_rip_read(vcpu);
 		__entry->immediate_exit	= force_immediate_exit;
 
 		kvm_x86_call(get_entry_info)(vcpu, &__entry->intr_info,
···
 	),								     \
 									     \
 	TP_fast_assign(							     \
-		__entry->guest_rip	= kvm_rip_read(vcpu);		     \
+		__entry->guest_rip	= tracing_kvm_rip_read(vcpu);		     \
 		__entry->isa            = isa;				     \
 		__entry->vcpu_id        = vcpu->vcpu_id;		     \
 		__entry->requests       = READ_ONCE(vcpu->requests);	     \
···
 
 	TP_fast_assign(
 		__entry->vcpu_id	= vcpu->vcpu_id;
-		__entry->guest_rip	= kvm_rip_read(vcpu);
+		__entry->guest_rip	= tracing_kvm_rip_read(vcpu);
 		__entry->fault_address	= fault_address;
 		__entry->error_code	= error_code;
 	),

arch/x86/kvm/vmx/posted_intr.c

···
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
+	bool enable_remapped_mode = true;
 	struct kvm_lapic_irq irq;
 	struct kvm_vcpu *vcpu;
 	struct vcpu_data vcpu_info;
···
 
 		kvm_set_msi_irq(kvm, e, &irq);
 		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
-		    !kvm_irq_is_postable(&irq)) {
-			/*
-			 * Make sure the IRTE is in remapped mode if
-			 * we don't handle it in posted mode.
-			 */
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
-			if (ret < 0) {
-				printk(KERN_INFO
-				   "failed to back to remapped mode, irq: %u\n",
-				   host_irq);
-				goto out;
-			}
-
+		    !kvm_irq_is_postable(&irq))
 			continue;
-		}
 
 		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
 		vcpu_info.vector = irq.vector;
···
 		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
 				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
 
-		if (set)
-			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
-		else
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
+		if (!set)
+			continue;
 
+		enable_remapped_mode = false;
+
+		ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
 		if (ret < 0) {
 			printk(KERN_INFO "%s: failed to update PI IRTE\n",
 					__func__);
 			goto out;
 		}
 	}
+
+	if (enable_remapped_mode)
+		ret = irq_set_vcpu_affinity(host_irq, NULL);
 
 	ret = 0;
 out:

arch/x86/kvm/x86.c

···
 	/*
 	 * Profile KVM exit RIPs:
 	 */
-	if (unlikely(prof_on == KVM_PROFILING)) {
+	if (unlikely(prof_on == KVM_PROFILING &&
+		     !vcpu->arch.guest_state_protected)) {
 		unsigned long rip = kvm_rip_read(vcpu);
 		profile_hit(KVM_PROFILING, (void *)rip);
 	}
···
 }
 EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
 
-bool kvm_arch_has_irq_bypass(void)
-{
-	return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
-}
-
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 				      struct irq_bypass_producer *prod)
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	struct kvm *kvm = irqfd->kvm;
 	int ret;
 
-	irqfd->producer = prod;
 	kvm_arch_start_assignment(irqfd->kvm);
+
+	spin_lock_irq(&kvm->irqfds.lock);
+	irqfd->producer = prod;
+
 	ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
 					   prod->irq, irqfd->gsi, 1);
 	if (ret)
 		kvm_arch_end_assignment(irqfd->kvm);
+
+	spin_unlock_irq(&kvm->irqfds.lock);
+
 
 	return ret;
 }
···
 	int ret;
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
+	struct kvm *kvm = irqfd->kvm;
 
 	WARN_ON(irqfd->producer != prod);
-	irqfd->producer = NULL;
 
 	/*
 	 * When producer of consumer is unregistered, we change back to
···
 	 * when the irq is masked/disabled or the consumer side (KVM
 	 * int this case doesn't want to receive the interrupts.
 	*/
+	spin_lock_irq(&kvm->irqfds.lock);
+	irqfd->producer = NULL;
+
 	ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
 					   prod->irq, irqfd->gsi, 0);
 	if (ret)
 		printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
 		       " fails: %d\n", irqfd->consumer.token, ret);
+
+	spin_unlock_irq(&kvm->irqfds.lock);
+
 
 	kvm_arch_end_assignment(irqfd->kvm);
 }
···
 bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
 				  struct kvm_kernel_irq_routing_entry *new)
 {
-	if (new->type != KVM_IRQ_ROUTING_MSI)
+	if (old->type != KVM_IRQ_ROUTING_MSI ||
+	    new->type != KVM_IRQ_ROUTING_MSI)
 		return true;
 
 	return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));

arch/x86/lib/x86-opcode-map.txt

···
 83: Grp1 Ev,Ib (1A),(es)
 # CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
 #			     CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
 88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
 8f: POP2 Bq,Rq (000),(11B),(ev)
 a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)

arch/x86/mm/pgtable.c

···
 	 * We allocate one page for pgd.
 	 */
 	if (!SHARED_KERNEL_PMD)
-		return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+		return __pgd_alloc(mm, pgd_allocation_order());
 
 	/*
 	 * Now PAE kernel is not running as a Xen domain. We can allocate
···
 
 static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
 {
-	return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
+	return __pgd_alloc(mm, pgd_allocation_order());
 }
 
 static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)

arch/x86/platform/efi/efi_64.c

···
 	gfp_t gfp_mask;
 
 	gfp_mask = GFP_KERNEL | __GFP_ZERO;
-	efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
+	efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, pgd_allocation_order());
 	if (!efi_pgd)
 		goto fail;
 
···
 	if (pgtable_l5_enabled())
 		free_page((unsigned long)pgd_page_vaddr(*pgd));
 free_pgd:
-	free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
+	free_pages((unsigned long)efi_pgd, pgd_allocation_order());
 fail:
 	return -ENOMEM;
 }

block/bdev.c

···
 				    get_order(bsize));
 }
 
+/**
+ * bdev_validate_blocksize - check that this block size is acceptable
+ * @bdev:	blockdevice to check
+ * @block_size:	block size to check
+ *
+ * For block device users that do not use buffer heads or the block device
+ * page cache, make sure that this block size can be used with the device.
+ *
+ * Return: On success zero is returned, negative error code on failure.
+ */
+int bdev_validate_blocksize(struct block_device *bdev, int block_size)
+{
+	if (blk_validate_block_size(block_size))
+		return -EINVAL;
+
+	/* Size cannot be smaller than the size supported by the device */
+	if (block_size < bdev_logical_block_size(bdev))
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bdev_validate_blocksize);
+
 int set_blocksize(struct file *file, int size)
 {
 	struct inode *inode = file->f_mapping->host;
 	struct block_device *bdev = I_BDEV(inode);
+	int ret;
 
-	if (blk_validate_block_size(size))
-		return -EINVAL;
-
-	/* Size cannot be smaller than the size supported by the device */
-	if (size < bdev_logical_block_size(bdev))
-		return -EINVAL;
+	ret = bdev_validate_blocksize(bdev, size);
+	if (ret)
+		return ret;
 
 	if (!file->private_data)
 		return -EINVAL;
 
 	/* Don't change the size if it is same as current */
 	if (inode->i_blkbits != blksize_bits(size)) {
+		/*
+		 * Flush and truncate the pagecache before we reconfigure the
+		 * mapping geometry because folio sizes are variable now.  If a
+		 * reader has already allocated a folio whose size is smaller
+		 * than the new min_order but invokes readahead after the new
+		 * min_order becomes visible, readahead will think there are
+		 * "zero" blocks per folio and crash.  Take the inode and
+		 * invalidation locks to avoid racing with
+		 * read/write/fallocate.
+		 */
+		inode_lock(inode);
+		filemap_invalidate_lock(inode->i_mapping);
+
 		sync_blockdev(bdev);
+		kill_bdev(bdev);
+
 		inode->i_blkbits = blksize_bits(size);
 		mapping_set_folio_min_order(inode->i_mapping, get_order(size));
 		kill_bdev(bdev);
+		filemap_invalidate_unlock(inode->i_mapping);
+		inode_unlock(inode);
 	}
 	return 0;
 }
···
 	blkdev_put_whole(whole);
 }
 
-struct block_device *blkdev_get_no_open(dev_t dev)
+struct block_device *blkdev_get_no_open(dev_t dev, bool autoload)
 {
 	struct block_device *bdev;
 	struct inode *inode;
 
 	inode = ilookup(blockdev_superblock, dev);
-	if (!inode && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) {
+	if (!inode && autoload && IS_ENABLED(CONFIG_BLOCK_LEGACY_AUTOLOAD)) {
 		blk_request_module(dev);
 		inode = ilookup(blockdev_superblock, dev);
 		if (inode)
···
 	if (ret)
 		return ERR_PTR(ret);
 
-	bdev = blkdev_get_no_open(dev);
+	bdev = blkdev_get_no_open(dev, true);
 	if (!bdev)
 		return ERR_PTR(-ENXIO);
 
···
  */
 void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask)
 {
-	struct inode *backing_inode;
 	struct block_device *bdev;
 
-	backing_inode = d_backing_inode(path->dentry);
-
 	/*
-	 * Note that backing_inode is the inode of a block device node file,
-	 * not the block device's internal inode.  Therefore it is *not* valid
-	 * to use I_BDEV() here; the block device has to be looked up by i_rdev
+	 * Note that d_backing_inode() returns the block device node inode, not
+	 * the block device's internal inode.  Therefore it is *not* valid to
+	 * use I_BDEV() here; the block device has to be looked up by i_rdev
 	 * instead.
 	 */
-	bdev = blkdev_get_no_open(backing_inode->i_rdev);
+	bdev = blkdev_get_no_open(d_backing_inode(path->dentry)->i_rdev, false);
 	if (!bdev)
 		return;
 

block/blk-cgroup.c

···
 		return -EINVAL;
 	input = skip_spaces(input);
 
-	bdev = blkdev_get_no_open(MKDEV(major, minor));
+	bdev = blkdev_get_no_open(MKDEV(major, minor), false);
 	if (!bdev)
 		return -ENODEV;
 	if (bdev_is_partition(bdev)) {

block/blk-settings.c

···
 	/*
 	 * For read-ahead of large files to be effective, we need to read ahead
 	 * at least twice the optimal I/O size.
+	 *
+	 * There is no hardware limitation for the read-ahead size and the user
+	 * might have increased the read-ahead size through sysfs, so don't ever
+	 * decrease it.
 	 */
-	bdi->ra_pages = max(lim->io_opt * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
+	bdi->ra_pages = max3(bdi->ra_pages,
+				lim->io_opt * 2 / PAGE_SIZE,
+				VM_READAHEAD_PAGES);
 	bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
 }
 

block/blk-zoned.c

···
 		op = REQ_OP_ZONE_RESET;
 
 		/* Invalidate the page cache, including dirty pages. */
+		inode_lock(bdev->bd_mapping->host);
 		filemap_invalidate_lock(bdev->bd_mapping);
 		ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
 		if (ret)
···
 	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors);
 
 fail:
-	if (cmd == BLKRESETZONE)
+	if (cmd == BLKRESETZONE) {
 		filemap_invalidate_unlock(bdev->bd_mapping);
+		inode_unlock(bdev->bd_mapping->host);
+	}
 
 	return ret;
 }

block/blk.h

···
 		wait_for_completion_io(done);
 }
 
+struct block_device *blkdev_get_no_open(dev_t dev, bool autoload);
+void blkdev_put_no_open(struct block_device *bdev);
+
 #define BIO_INLINE_VECS 4
 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
 		gfp_t gfp_mask);

block/fops.c

···
 	if (ret)
 		return ret;
 
-	bdev = blkdev_get_no_open(inode->i_rdev);
+	bdev = blkdev_get_no_open(inode->i_rdev, true);
 	if (!bdev)
 		return -ENXIO;
 
···
 			ret = direct_write_fallback(iocb, from, ret,
 					blkdev_buffered_write(iocb, from));
 	} else {
+		/*
+		 * Take i_rwsem and invalidate_lock to avoid racing with
+		 * set_blocksize changing i_blkbits/folio order and punching
+		 * out the pagecache.
+		 */
+		inode_lock_shared(bd_inode);
 		ret = blkdev_buffered_write(iocb, from);
+		inode_unlock_shared(bd_inode);
 	}
 
 	if (ret > 0)
···
 
 static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	struct inode *bd_inode = bdev_file_inode(iocb->ki_filp);
 	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
 	loff_t size = bdev_nr_bytes(bdev);
 	loff_t pos = iocb->ki_pos;
···
 			goto reexpand;
 	}
 
+	/*
+	 * Take i_rwsem and invalidate_lock to avoid racing with set_blocksize
+	 * changing i_blkbits/folio order and punching out the pagecache.
+	 */
+	inode_lock_shared(bd_inode);
 	ret = filemap_read(iocb, to, ret);
+	inode_unlock_shared(bd_inode);
 
 reexpand:
 	if (unlikely(shorted))
···
 	if ((start | len) & (bdev_logical_block_size(bdev) - 1))
 		return -EINVAL;
 
+	inode_lock(inode);
 	filemap_invalidate_lock(inode->i_mapping);
 
 	/*
···
 
  fail:
 	filemap_invalidate_unlock(inode->i_mapping);
+	inode_unlock(inode);
 	return error;
 }
 

block/ioctl.c

···
 	if (err)
 		return err;
 
+	inode_lock(bdev->bd_mapping->host);
 	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
 	if (err)
···
 	blk_finish_plug(&plug);
 fail:
 	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
 	return err;
 }
 
···
 	    end > bdev_nr_bytes(bdev))
 		return -EINVAL;
 
+	inode_lock(bdev->bd_mapping->host);
 	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, end - 1);
 	if (!err)
 		err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9,
 						GFP_KERNEL);
 	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
 	return err;
 }
 
···
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages */
+	inode_lock(bdev->bd_mapping->host);
 	filemap_invalidate_lock(bdev->bd_mapping);
 	err = truncate_bdev_range(bdev, mode, start, end);
 	if (err)
···
 
 fail:
 	filemap_invalidate_unlock(bdev->bd_mapping);
+	inode_unlock(bdev->bd_mapping->host);
 	return err;
 }
 

crypto/scompress.c

···
 			spage = nth_page(spage, soff / PAGE_SIZE);
 			soff = offset_in_page(soff);
 
-			n = slen / PAGE_SIZE;
-			n += (offset_in_page(slen) + soff - 1) / PAGE_SIZE;
+			n = (slen - 1) / PAGE_SIZE;
+			n += (offset_in_page(slen - 1) + soff) / PAGE_SIZE;
 			if (PageHighMem(nth_page(spage, n)) &&
 			    size_add(soff, slen) > PAGE_SIZE)
 				break;
···
 			dpage = nth_page(dpage, doff / PAGE_SIZE);
 			doff = offset_in_page(doff);
 
-			n = dlen / PAGE_SIZE;
-			n += (offset_in_page(dlen) + doff - 1) / PAGE_SIZE;
-			if (PageHighMem(dpage + n) &&
+			n = (dlen - 1) / PAGE_SIZE;
+			n += (offset_in_page(dlen - 1) + doff) / PAGE_SIZE;
+			if (PageHighMem(nth_page(dpage, n)) &&
 			    size_add(doff, dlen) > PAGE_SIZE)
 				break;
 			dst = kmap_local_page(dpage) + doff;

crypto/testmgr.c

···
 MODULE_PARM_DESC(fuzz_iterations, "number of fuzz test iterations");
 #endif
 
-/* Multibuffer is unlimited.  Set arbitrary limit for testing. */
-#define MAX_MB_MSGS	16
-
 #ifdef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS
 
 /* a perfect nop */
···
 		      int ctcount, int dtcount)
 {
 	const char *algo = crypto_tfm_alg_driver_name(crypto_acomp_tfm(tfm));
-	struct scatterlist *src = NULL, *dst = NULL;
-	struct acomp_req *reqs[MAX_MB_MSGS] = {};
-	char *decomp_out[MAX_MB_MSGS] = {};
-	char *output[MAX_MB_MSGS] = {};
-	struct crypto_wait wait;
-	struct acomp_req *req;
-	int ret = -ENOMEM;
 	unsigned int i;
+	char *output, *decomp_out;
+	int ret;
+	struct scatterlist src, dst;
+	struct acomp_req *req;
+	struct crypto_wait wait;
 
-	src = kmalloc_array(MAX_MB_MSGS, sizeof(*src), GFP_KERNEL);
-	if (!src)
-		goto out;
-	dst = kmalloc_array(MAX_MB_MSGS, sizeof(*dst), GFP_KERNEL);
-	if (!dst)
-		goto out;
+	output = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
+	if (!output)
+		return -ENOMEM;
 
-	for (i = 0; i < MAX_MB_MSGS; i++) {
-		reqs[i] = acomp_request_alloc(tfm);
-		if (!reqs[i])
-			goto out;
-
-		acomp_request_set_callback(reqs[i],
-					   CRYPTO_TFM_REQ_MAY_SLEEP |
-					   CRYPTO_TFM_REQ_MAY_BACKLOG,
-					   crypto_req_done, &wait);
-		if (i)
-			acomp_request_chain(reqs[i], reqs[0]);
-
-		output[i] = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
-		if (!output[i])
-			goto out;
-
-		decomp_out[i] = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
-		if (!decomp_out[i])
-			goto out;
+	decomp_out = kmalloc(COMP_BUF_SIZE, GFP_KERNEL);
+	if (!decomp_out) {
+		kfree(output);
+		return -ENOMEM;
 	}
 
 	for (i = 0; i < ctcount; i++) {
 		unsigned int dlen = COMP_BUF_SIZE;
 		int ilen = ctemplate[i].inlen;
 		void *input_vec;
-		int j;
 
 		input_vec = kmemdup(ctemplate[i].input, ilen, GFP_KERNEL);
 		if (!input_vec) {
···
 			goto out;
 		}
 
+		memset(output, 0, dlen);
 		crypto_init_wait(&wait);
-		sg_init_one(src, input_vec, ilen);
+		sg_init_one(&src, input_vec, ilen);
+		sg_init_one(&dst, output, dlen);
 
-		for (j = 0; j < MAX_MB_MSGS; j++) {
-			sg_init_one(dst + j, output[j], dlen);
-			acomp_request_set_params(reqs[j], src, dst + j, ilen, dlen);
+		req = acomp_request_alloc(tfm);
+		if (!req) {
+			pr_err("alg: acomp: request alloc failed for %s\n",
+			       algo);
+			kfree(input_vec);
+			ret = -ENOMEM;
+			goto out;
 		}
 
-		req = reqs[0];
+		acomp_request_set_params(req, &src, &dst, ilen, dlen);
+		acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					   crypto_req_done, &wait);
+
 		ret = crypto_wait_req(crypto_acomp_compress(req), &wait);
 		if (ret) {
 			pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
 			       i + 1, algo, -ret);
 			kfree(input_vec);
+			acomp_request_free(req);
 			goto out;
 		}
 
 		ilen = req->dlen;
 		dlen = COMP_BUF_SIZE;
+		sg_init_one(&src, output, ilen);
+		sg_init_one(&dst, decomp_out, dlen);
 		crypto_init_wait(&wait);
-		for (j = 0; j < MAX_MB_MSGS; j++) {
-			sg_init_one(src + j, output[j], ilen);
-			sg_init_one(dst + j, decomp_out[j], dlen);
-			acomp_request_set_params(reqs[j], src + j, dst + j, ilen, dlen);
+		acomp_request_set_params(req, &src, &dst, ilen, dlen);
+
+		ret = crypto_wait_req(crypto_acomp_decompress(req), &wait);
+		if (ret) {
+			pr_err("alg: acomp: compression failed on test %d for %s: ret=%d\n",
+			       i + 1, algo, -ret);
+			kfree(input_vec);
+			acomp_request_free(req);
+			goto out;
 		}
 
-		crypto_wait_req(crypto_acomp_decompress(req), &wait);
-		for (j = 0; j < MAX_MB_MSGS; j++) {
-			ret = reqs[j]->base.err;
-			if (ret) {
-				pr_err("alg: acomp: compression failed on test %d (%d) for %s: ret=%d\n",
-				       i + 1, j, algo, -ret);
-				kfree(input_vec);
-				goto out;
-			}
+		if (req->dlen != ctemplate[i].inlen) {
+			pr_err("alg: acomp: Compression test %d failed for %s: output len = %d\n",
+			       i + 1, algo, req->dlen);
+			ret = -EINVAL;
+			kfree(input_vec);
+			acomp_request_free(req);
+			goto out;
+		}
 
-			if (reqs[j]->dlen != ctemplate[i].inlen) {
-				pr_err("alg: acomp: Compression test %d (%d) failed for %s: output len = %d\n",
-				       i + 1, j, algo, reqs[j]->dlen);
-				ret = -EINVAL;
-				kfree(input_vec);
-				goto out;
-			}
-
-			if (memcmp(input_vec, decomp_out[j], reqs[j]->dlen)) {
-				pr_err("alg: acomp: Compression test %d (%d) failed for %s\n",
-				       i + 1, j, algo);
-				hexdump(output[j], reqs[j]->dlen);
-				ret = -EINVAL;
-				kfree(input_vec);
-				goto out;
-			}
+		if (memcmp(input_vec, decomp_out, req->dlen)) {
+			pr_err("alg: acomp: Compression test %d failed for %s\n",
+			       i + 1, algo);
+			hexdump(output, req->dlen);
+			ret = -EINVAL;
+			kfree(input_vec);
+			acomp_request_free(req);
+			goto out;
 		}
 
 		kfree(input_vec);
+		acomp_request_free(req);
 	}
 
 	for (i = 0; i < dtcount; i++) {
···
 			goto out;
 		}
 
+		memset(output, 0, dlen);
 		crypto_init_wait(&wait);
-		sg_init_one(src, input_vec, ilen);
-		sg_init_one(dst, output[0], dlen);
+		sg_init_one(&src, input_vec, ilen);
+		sg_init_one(&dst, output, dlen);
 
 		req = acomp_request_alloc(tfm);
 		if (!req) {
···
 			goto out;
 		}
 
-		acomp_request_set_params(req, src, dst, ilen, dlen);
+		acomp_request_set_params(req, &src, &dst, ilen, dlen);
 		acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 					   crypto_req_done, &wait);
 
···
 			goto out;
 		}
 
-		if (memcmp(output[0], dtemplate[i].output, req->dlen)) {
+		if (memcmp(output, dtemplate[i].output, req->dlen)) {
 			pr_err("alg: acomp: Decompression test %d failed for %s\n",
 			       i + 1, algo);
-			hexdump(output[0], req->dlen);
+			hexdump(output, req->dlen);
 			ret = -EINVAL;
 			kfree(input_vec);
 			acomp_request_free(req);
···
 	ret = 0;
 
 out:
-	acomp_request_free(reqs[0]);
-	for (i = 0; i < MAX_MB_MSGS; i++) {
-		kfree(output[i]);
-		kfree(decomp_out[i]);
-	}
-	kfree(dst);
-	kfree(src);
+	kfree(decomp_out);
+	kfree(output);
 	return ret;
 }
 

drivers/acpi/tables.c

···
 }
 
 /* All but ACPI_SIG_RSDP and ACPI_SIG_FACS: */
-static const char table_sigs[][ACPI_NAMESEG_SIZE] __initconst __nonstring = {
+static const char table_sigs[][ACPI_NAMESEG_SIZE] __initconst = {
 	ACPI_SIG_BERT, ACPI_SIG_BGRT, ACPI_SIG_CPEP, ACPI_SIG_ECDT,
 	ACPI_SIG_EINJ, ACPI_SIG_ERST, ACPI_SIG_HEST, ACPI_SIG_MADT,
 	ACPI_SIG_MSCT, ACPI_SIG_SBST, ACPI_SIG_SLIT, ACPI_SIG_SRAT,

drivers/android/binder.c

···
 		seq_printf(m, " node %d", buffer->target_node->debug_id);
 	seq_printf(m, " size %zd:%zd offset %lx\n",
 		   buffer->data_size, buffer->offsets_size,
-		   proc->alloc.vm_start - buffer->user_data);
+		   buffer->user_data - proc->alloc.vm_start);
 }
 
 static void print_binder_work_ilocked(struct seq_file *m,

drivers/ata/libata-scsi.c

···
 	 */
 	put_unaligned_be16(ATA_FEATURE_SUB_MPAGE_LEN - 4, &buf[2]);
 
-	if (dev->flags & ATA_DFLAG_CDL)
-		buf[4] = 0x02; /* Support T2A and T2B pages */
+	if (dev->flags & ATA_DFLAG_CDL_ENABLED)
+		buf[4] = 0x02; /* T2A and T2B pages enabled */
 	else
 		buf[4] = 0;
 
···
 }
 
 /*
- * Translate MODE SELECT control mode page, sub-pages f2h (ATA feature mode
+ * Translate MODE SELECT control mode page, sub-page f2h (ATA feature mode
  * page) into a SET FEATURES command.
  */
-static unsigned int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
-						    const u8 *buf, int len,
-						    u16 *fp)
+static int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc,
+					   const u8 *buf, int len, u16 *fp)
 {
 	struct ata_device *dev = qc->dev;
 	struct ata_taskfile *tf = &qc->tf;
···
 	/* Check cdl_ctrl */
 	switch (buf[0] & 0x03) {
 	case 0:
-		/* Disable CDL */
+		/* Disable CDL if it is enabled */
+		if (!(dev->flags & ATA_DFLAG_CDL_ENABLED))
+			return 0;
+		ata_dev_dbg(dev, "Disabling CDL\n");
 		cdl_action = 0;
 		dev->flags &= ~ATA_DFLAG_CDL_ENABLED;
 		break;
 	case 0x02:
-		/* Enable CDL T2A/T2B: NCQ priority must be disabled */
+		/*
+		 * Enable CDL if not already enabled. Since this is mutually
+		 * exclusive with NCQ priority, allow this only if NCQ priority
+		 * is disabled.
+		 */
+		if (dev->flags & ATA_DFLAG_CDL_ENABLED)
+			return 0;
 		if (dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLED) {
 			ata_dev_err(dev,
 				"NCQ priority must be disabled to enable CDL\n");
 			return -EINVAL;
 		}
+		ata_dev_dbg(dev, "Enabling CDL\n");
 		cdl_action = 1;
 		dev->flags |= ATA_DFLAG_CDL_ENABLED;
 		break;

drivers/base/auxiliary.c

···
  *		},
  *		.ops = my_custom_ops,
  *	};
+ *
+ * Please note that such custom ops approach is valid, but it is hard to implement
+ * it right without global locks per-device to protect from auxiliary_drv removal
+ * during call to that ops. In addition, this implementation lacks proper module
+ * dependency, which causes to load/unload races between auxiliary parent and devices
+ * modules.
+ *
+ * The most easiest way to provide these ops reliably without needing to
+ * have a lock is to EXPORT_SYMBOL*() them and rely on already existing
+ * modules infrastructure for validity and correct dependencies chains.
  */
 
 static const struct auxiliary_device_id *auxiliary_match_id(const struct auxiliary_device_id *id,

drivers/base/base.h

···
 		kset_put(&sp->subsys);
 }
 
+struct subsys_private *bus_to_subsys(const struct bus_type *bus);
 struct subsys_private *class_to_subsys(const struct class *class);
 
 struct driver_private {
···
 int driver_add_groups(const struct device_driver *drv, const struct attribute_group **groups);
 void driver_remove_groups(const struct device_driver *drv, const struct attribute_group **groups);
 void device_driver_detach(struct device *dev);
+
+static inline void device_set_driver(struct device *dev, const struct device_driver *drv)
+{
+	/*
+	 * Majority (all?) read accesses to dev->driver happens either
+	 * while holding device lock or in bus/driver code that is only
+	 * invoked when the device is bound to a driver and there is no
+	 * concern of the pointer being changed while it is being read.
+	 * However when reading device's uevent file we read driver pointer
+	 * without taking device lock (so we do not block there for
+	 * arbitrary amount of time). We use WRITE_ONCE() here to prevent
+	 * tearing so that READ_ONCE() can safely be used in uevent code.
+	 */
+	// FIXME - this cast should not be needed "soon"
+	WRITE_ONCE(dev->driver, (struct device_driver *)drv);
+}
 
 int devres_release_all(struct device *dev);
 void device_block_probing(void);

drivers/base/bus.c

···
  * NULL.  A call to subsys_put() must be done when finished with the pointer in
  * order for it to be properly freed.
  */
-static struct subsys_private *bus_to_subsys(const struct bus_type *bus)
+struct subsys_private *bus_to_subsys(const struct bus_type *bus)
 {
 	struct subsys_private *sp = NULL;
 	struct kobject *kobj;

drivers/base/core.c

···
 	return NULL;
 }
 
+/*
+ * Try filling "DRIVER=<name>" uevent variable for a device. Because this
+ * function may race with binding and unbinding the device from a driver,
+ * we need to be careful. Binding is generally safe, at worst we miss the
+ * fact that the device is already bound to a driver (but the driver
+ * information that is delivered through uevents is best-effort, it may
+ * become obsolete as soon as it is generated anyways). Unbinding is more
+ * risky as driver pointer is transitioning to NULL, so READ_ONCE() should
+ * be used to make sure we are dealing with the same pointer, and to
+ * ensure that driver structure is not going to disappear from under us
+ * we take bus' drivers klist lock. The assumption that only registered
+ * driver can be bound to a device, and to unregister a driver bus code
+ * will take the same lock.
+ */
+static void dev_driver_uevent(const struct device *dev, struct kobj_uevent_env *env)
+{
+	struct subsys_private *sp = bus_to_subsys(dev->bus);
+
+	if (sp) {
+		scoped_guard(spinlock, &sp->klist_drivers.k_lock) {
+			struct device_driver *drv = READ_ONCE(dev->driver);
+			if (drv)
+				add_uevent_var(env, "DRIVER=%s", drv->name);
+		}
+
+		subsys_put(sp);
+	}
+}
+
 static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
 {
 	const struct device *dev = kobj_to_dev(kobj);
···
 	if (dev->type && dev->type->name)
 		add_uevent_var(env, "DEVTYPE=%s", dev->type->name);
 
-	if (dev->driver)
-		add_uevent_var(env, "DRIVER=%s", dev->driver->name);
+	/* Add "DRIVER=%s" variable if the device is bound to a driver */
+	dev_driver_uevent(dev, env);
 
 	/* Add common DT information about the device */
 	of_device_uevent(dev, env);
···
 	if (!env)
 		return -ENOMEM;
 
-	/* Synchronize with really_probe() */
-	device_lock(dev);
 	/* let the kset specific function add its keys */
 	retval = kset->uevent_ops->uevent(&dev->kobj, env);
-	device_unlock(dev);
 	if (retval)
 		goto out;
 
···
 	device_pm_remove(dev);
 	dpm_sysfs_remove(dev);
  DPMError:
-	dev->driver = NULL;
+	device_set_driver(dev, NULL);
 	bus_remove_device(dev);
  BusError:
 	device_remove_attrs(dev);

drivers/base/dd.c

···
 	arch_teardown_dma_ops(dev);
 	kfree(dev->dma_range_map);
 	dev->dma_range_map = NULL;
-	dev->driver = NULL;
+	device_set_driver(dev, NULL);
 	dev_set_drvdata(dev, NULL);
 	if (dev->pm_domain && dev->pm_domain->dismiss)
 		dev->pm_domain->dismiss(dev);
···
 	}
 
 re_probe:
-	// FIXME - this cast should not be needed "soon"
-	dev->driver = (struct device_driver *)drv;
+	device_set_driver(dev, drv);
 
 	/* If using pinctrl, bind pins now before probing */
 	ret = pinctrl_bind_pins(dev);
···
 		if (ret == 0)
 			ret = 1;
 		else {
-			dev->driver = NULL;
+			device_set_driver(dev, NULL);
 			ret = 0;
 		}
 	} else {

drivers/base/devtmpfs.c

···
 	return err;
 }
 
-static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *stat)
+static int dev_mynode(struct device *dev, struct inode *inode)
 {
 	/* did we create it */
 	if (inode->i_private != &thread)
···
 
 	/* does the dev_t match */
 	if (is_blockdev(dev)) {
-		if (!S_ISBLK(stat->mode))
+		if (!S_ISBLK(inode->i_mode))
 			return 0;
 	} else {
-		if (!S_ISCHR(stat->mode))
+		if (!S_ISCHR(inode->i_mode))
 			return 0;
 	}
-	if (stat->rdev != dev->devt)
+	if (inode->i_rdev != dev->devt)
 		return 0;
 
 	/* ours */
···
 {
 	struct path parent;
 	struct dentry *dentry;
-	struct kstat stat;
-	struct path p;
+	struct inode *inode;
 	int deleted = 0;
-	int err;
+	int err = 0;
 
 	dentry = kern_path_locked(nodename, &parent);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	p.mnt = parent.mnt;
-	p.dentry = dentry;
-	err = vfs_getattr(&p, &stat, STATX_TYPE | STATX_MODE,
-			  AT_STATX_SYNC_AS_STAT);
-	if (!err && dev_mynode(dev, d_inode(dentry), &stat)) {
+	inode = d_inode(dentry);
+	if (dev_mynode(dev, inode)) {
 		struct iattr newattrs;
 		/*
 		 * before unlinking this node, reset permissions
···
 		 */
 		newattrs.ia_uid = GLOBAL_ROOT_UID;
 		newattrs.ia_gid = GLOBAL_ROOT_GID;
-		newattrs.ia_mode = stat.mode & ~0777;
+		newattrs.ia_mode = inode->i_mode & ~0777;
 		newattrs.ia_valid =
 			ATTR_UID|ATTR_GID|ATTR_MODE;
 		inode_lock(d_inode(dentry));

drivers/base/memory.c

···
 	return 0;
 }
 
-static int __init add_boot_memory_block(unsigned long base_section_nr)
-{
-	unsigned long nr;
-
-	for_each_present_section_nr(base_section_nr, nr) {
-		if (nr >= (base_section_nr + sections_per_block))
-			break;
-
-		return add_memory_block(memory_block_id(base_section_nr),
-					MEM_ONLINE, NULL, NULL);
-	}
-
-	return 0;
-}
-
 static int add_hotplug_memory_block(unsigned long block_id,
 				    struct vmem_altmap *altmap,
 				    struct memory_group *group)
···
 void __init memory_dev_init(void)
 {
 	int ret;
-	unsigned long block_sz, nr;
+	unsigned long block_sz, block_id, nr;
 
 	/* Validate the configured memory block size */
 	block_sz = memory_block_size_bytes();
···
 		panic("%s() failed to register subsystem: %d\n", __func__, ret);
 
 	/*
-	 * Create entries for memory sections that were found
-	 * during boot and have been initialized
+	 * Create entries for memory sections that were found during boot
+	 * and have been initialized. Use @block_id to track the last
+	 * handled block and initialize it to an invalid value (ULONG_MAX)
+	 * to bypass the block ID matching check for the first present
+	 * block so that it can be covered.
 	 */
-	for (nr = 0; nr <= __highest_present_section_nr;
-	     nr += sections_per_block) {
-		ret = add_boot_memory_block(nr);
-		if (ret)
-			panic("%s() failed to add memory block: %d\n", __func__,
-			      ret);
+	block_id = ULONG_MAX;
+	for_each_present_section_nr(0, nr) {
+		if (block_id != ULONG_MAX && memory_block_id(nr) == block_id)
+			continue;
+
+		block_id = memory_block_id(nr);
+		ret = add_memory_block(block_id, MEM_ONLINE, NULL, NULL);
+		if (ret) {
+			panic("%s() failed to add memory block: %d\n",
+			      __func__, ret);
+		}
 	}
 }
 

drivers/base/swnode.c

···
 	if (!swnode)
 		return;
 
+	kobject_get(&swnode->kobj);
 	ret = sysfs_create_link(&dev->kobj, &swnode->kobj, "software_node");
 	if (ret)
 		return;
···
 		sysfs_remove_link(&dev->kobj, "software_node");
 		return;
 	}
-
-	kobject_get(&swnode->kobj);
 }
 
 void software_node_notify_remove(struct device *dev)

drivers/block/ublk_drv.c

···
 	ublk_put_disk(disk);
 }
 
-static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io,
+static void ublk_cancel_cmd(struct ublk_queue *ubq, unsigned tag,
 		unsigned int issue_flags)
 {
+	struct ublk_io *io = &ubq->ios[tag];
+	struct ublk_device *ub = ubq->dev;
+	struct request *req;
 	bool done;
 
 	if (!(io->flags & UBLK_IO_FLAG_ACTIVE))
+		return;
+
+	/*
+	 * Don't try to cancel this command if the request is started for
+	 * avoiding race between io_uring_cmd_done() and
+	 * io_uring_cmd_complete_in_task().
+	 *
+	 * Either the started request will be aborted via __ublk_abort_rq(),
+	 * then this uring_cmd is canceled next time, or it will be done in
+	 * task work function ublk_dispatch_req() because io_uring guarantees
+	 * that ublk_dispatch_req() is always called
+	 */
+	req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag);
+	if (req && blk_mq_request_started(req))
 		return;
 
 	spin_lock(&ubq->cancel_lock);
···
 	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
 	struct ublk_queue *ubq = pdu->ubq;
 	struct task_struct *task;
-	struct ublk_io *io;
 
 	if (WARN_ON_ONCE(!ubq))
 		return;
···
 	if (!ubq->canceling)
 		ublk_start_cancel(ubq);
 
-	io = &ubq->ios[pdu->tag];
-	WARN_ON_ONCE(io->cmd != cmd);
-	ublk_cancel_cmd(ubq, io, issue_flags);
+	WARN_ON_ONCE(ubq->ios[pdu->tag].cmd != cmd);
+	ublk_cancel_cmd(ubq, pdu->tag, issue_flags);
 }
 
 static inline bool ublk_queue_ready(struct ublk_queue *ubq)
···
 	int i;
 
 	for (i = 0; i < ubq->q_depth; i++)
-		ublk_cancel_cmd(ubq, &ubq->ios[i], IO_URING_F_UNLOCKED);
+		ublk_cancel_cmd(ubq, i, IO_URING_F_UNLOCKED);
 }
 
 /* Cancel all pending commands, must be called after del_gendisk() returns */
···
 		ublk_reset_io_flags(ub);
 		complete_all(&ub->completion);
 	}
-}
-
-static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id,
-		int tag)
-{
-	struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
-	struct request *req = blk_mq_tag_to_rq(ub->tag_set.tags[q_id], tag);
-
-	ublk_queue_cmd(ubq, req);
 }
 
 static inline int ublk_check_cmd_op(u32 cmd_op)
···
 		if (!(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV))
 			goto out;
 		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
-		ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag);
-		break;
+		req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag);
+		ublk_dispatch_req(ubq, req, issue_flags);
+		return -EIOCBQUEUED;
 	default:
 		goto out;
 	}

drivers/char/misc.c

···
 		goto fail_remove;
 
 	err = -EIO;
-	if (register_chrdev(MISC_MAJOR, "misc", &misc_fops))
+	if (__register_chrdev(MISC_MAJOR, 0, MINORMASK + 1, "misc", &misc_fops))
 		goto fail_printk;
 	return 0;
 

drivers/char/virtio_console.c

···
 		break;
 	case VIRTIO_CONSOLE_RESIZE: {
 		struct {
-			__u16 rows;
-			__u16 cols;
+			__virtio16 cols;
+			__virtio16 rows;
 		} size;
 
 		if (!is_console_port(port))
···
 
 		memcpy(&size, buf->buf + buf->offset + sizeof(*cpkt),
 		       sizeof(size));
-		set_console_size(port, size.rows, size.cols);
+		set_console_size(port, virtio16_to_cpu(vdev, size.rows),
+				 virtio16_to_cpu(vdev, size.cols));
 
 		port->cons.hvc->irq_requested = 1;
 		resize_console(port);

drivers/comedi/drivers/jr3_pci.c

···
 	struct jr3_pci_dev_private *devpriv = dev->private;
 
 	if (devpriv)
-		timer_delete_sync(&devpriv->timer);
+		timer_shutdown_sync(&devpriv->timer);
 
 	comedi_pci_detach(dev);
 }

drivers/cpufreq/Kconfig.arm

···
 config ARM_BRCMSTB_AVS_CPUFREQ
 	tristate "Broadcom STB AVS CPUfreq driver"
 	depends on (ARCH_BRCMSTB && !ARM_SCMI_CPUFREQ) || COMPILE_TEST
-	default y
+	default y if ARCH_BRCMSTB && !ARM_SCMI_CPUFREQ
 	help
 	  Some Broadcom STB SoCs use a co-processor running proprietary firmware
 	  ("AVS") to handle voltage and frequency scaling. This driver provides
···
 	tristate "Calxeda Highbank-based"
 	depends on ARCH_HIGHBANK || COMPILE_TEST
 	depends on CPUFREQ_DT && REGULATOR && PL320_MBOX
-	default m
+	default m if ARCH_HIGHBANK
 	help
 	  This adds the CPUFreq driver for Calxeda Highbank SoC
 	  based boards.
···
 config ARM_MEDIATEK_CPUFREQ_HW
 	tristate "MediaTek CPUFreq HW driver"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
-	default m
+	default m if ARCH_MEDIATEK
 	help
 	  Support for the CPUFreq HW driver.
 	  Some MediaTek chipsets have a HW engine to offload the steps
···
 config ARM_S3C64XX_CPUFREQ
 	bool "Samsung S3C64XX"
 	depends on CPU_S3C6410 || COMPILE_TEST
-	default y
+	default CPU_S3C6410
 	help
 	  This adds the CPUFreq driver for Samsung S3C6410 SoC.
 
···
 config ARM_S5PV210_CPUFREQ
 	bool "Samsung S5PV210 and S5PC110"
 	depends on CPU_S5PV210 || COMPILE_TEST
-	default y
+	default CPU_S5PV210
 	help
 	  This adds the CPUFreq driver for Samsung S5PV210 and
 	  S5PC110 SoCs.
···
 config ARM_SPEAR_CPUFREQ
 	bool "SPEAr CPUFreq support"
 	depends on PLAT_SPEAR || COMPILE_TEST
-	default y
+	default PLAT_SPEAR
 	help
 	  This adds the CPUFreq driver support for SPEAr SOCs.
 
···
 	tristate "Tegra20/30 CPUFreq support"
 	depends on ARCH_TEGRA || COMPILE_TEST
 	depends on CPUFREQ_DT
-	default y
+	default ARCH_TEGRA
 	help
 	  This adds the CPUFreq driver support for Tegra20/30 SOCs.
 
···
 	bool "Tegra124 CPUFreq support"
 	depends on ARCH_TEGRA || COMPILE_TEST
 	depends on CPUFREQ_DT
-	default y
+	default ARCH_TEGRA
 	help
 	  This adds the CPUFreq driver support for Tegra124 SOCs.
 
···
 	tristate "Tegra194 CPUFreq support"
 	depends on ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC || (64BIT && COMPILE_TEST)
 	depends on TEGRA_BPMP
-	default y
+	default ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC
 	help
 	  This adds CPU frequency driver support for Tegra194 SOCs.
 
 config ARM_TI_CPUFREQ
 	bool "Texas Instruments CPUFreq support"
 	depends on ARCH_OMAP2PLUS || ARCH_K3 || COMPILE_TEST
-	default y
+	default ARCH_OMAP2PLUS || ARCH_K3
 	help
 	  This driver enables valid OPPs on the running platform based on
 	  values contained within the SoC in use. Enable this in order to

drivers/cpufreq/apple-soc-cpufreq.c

···
 
 static unsigned int apple_soc_cpufreq_get_rate(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	struct apple_cpu_priv *priv = policy->driver_data;
+	struct cpufreq_policy *policy;
+	struct apple_cpu_priv *priv;
 	struct cpufreq_frequency_table *p;
 	unsigned int pstate;
+
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (unlikely(!policy))
+		return 0;
+
+	priv = policy->driver_data;
 
 	if (priv->info->cur_pstate_mask) {
 		u32 reg = readl_relaxed(priv->reg_base + APPLE_DVFS_STATUS);

drivers/cpufreq/cppc_cpufreq.c

···
 	int ret;
 
 	if (!policy)
-		return -ENODEV;
+		return 0;
 
 	cpu_data = policy->driver_data;
 

drivers/cpufreq/cpufreq-dt-platdev.c

···
 	{ .compatible = "qcom,sm8350", },
 	{ .compatible = "qcom,sm8450", },
 	{ .compatible = "qcom,sm8550", },
+	{ .compatible = "qcom,sm8650", },
 
 	{ .compatible = "st,stih407", },
 	{ .compatible = "st,stih410", },

drivers/cpufreq/scmi-cpufreq.c

···
 
 static unsigned int scmi_cpufreq_get_rate(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	struct scmi_data *priv = policy->driver_data;
+	struct cpufreq_policy *policy;
+	struct scmi_data *priv;
 	unsigned long rate;
 	int ret;
+
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (unlikely(!policy))
+		return 0;
+
+	priv = policy->driver_data;
 
 	ret = perf_ops->freq_get(ph, priv->domain_id, &rate, false);
 	if (ret)

drivers/cpufreq/scpi-cpufreq.c

···
 
 static unsigned int scpi_cpufreq_get_rate(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	struct scpi_data *priv = policy->driver_data;
-	unsigned long rate = clk_get_rate(priv->clk);
+	struct cpufreq_policy *policy;
+	struct scpi_data *priv;
+	unsigned long rate;
+
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (unlikely(!policy))
+		return 0;
+
+	priv = policy->driver_data;
+	rate = clk_get_rate(priv->clk);
 
 	return rate / 1000;
 }

drivers/cpufreq/sun50i-cpufreq-nvmem.c

···
 	struct nvmem_cell *speedbin_nvmem;
 	const struct of_device_id *match;
 	struct device *cpu_dev;
-	u32 *speedbin;
+	void *speedbin_ptr;
+	u32 speedbin = 0;
+	size_t len;
 	int ret;
 
 	cpu_dev = get_cpu_device(0);
···
 		return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem),
 				     "Could not get nvmem cell\n");
 
-	speedbin = nvmem_cell_read(speedbin_nvmem, NULL);
+	speedbin_ptr = nvmem_cell_read(speedbin_nvmem, &len);
 	nvmem_cell_put(speedbin_nvmem);
-	if (IS_ERR(speedbin))
-		return PTR_ERR(speedbin);
+	if (IS_ERR(speedbin_ptr))
+		return PTR_ERR(speedbin_ptr);
 
-	ret = opp_data->efuse_xlate(*speedbin);
+	if (len <= 4)
+		memcpy(&speedbin, speedbin_ptr, len);
+	speedbin = le32_to_cpu(speedbin);
 
-	kfree(speedbin);
+	ret = opp_data->efuse_xlate(speedbin);
+
+	kfree(speedbin_ptr);
 
 	return ret;
 };

drivers/crypto/atmel-sha204a.c

···
 	i2c_priv->hwrng.name = dev_name(&client->dev);
 	i2c_priv->hwrng.read = atmel_sha204a_rng_read;
 
+	/*
+	 * According to review by Bill Cox [1], this HWRNG has very low entropy.
+	 * [1] https://www.metzdowd.com/pipermail/cryptography/2014-December/023858.html
+	 */
+	i2c_priv->hwrng.quality = 1;
+
 	ret = devm_hwrng_register(&client->dev, &i2c_priv->hwrng);
 	if (ret)
 		dev_warn(&client->dev, "failed to register RNG (%d)\n", ret);

drivers/cxl/core/core.h

···
 
 int cxl_ras_init(void);
 void cxl_ras_exit(void);
-int cxl_gpf_port_setup(struct device *dport_dev, struct cxl_port *port);
+int cxl_gpf_port_setup(struct cxl_dport *dport);
 int cxl_acpi_get_extended_linear_cache_size(struct resource *backing_res,
 					    int nid, resource_size_t *size);
 

drivers/cxl/core/features.c

···
 	rc = cxl_set_feature(cxl_mbox, &feat_in->uuid,
 			     feat_in->version, feat_in->feat_data,
 			     data_size, flags, offset, &return_code);
+	*out_len = sizeof(*rpc_out);
 	if (rc) {
 		rpc_out->retval = return_code;
 		return no_free_ptr(rpc_out);
 	}
 
 	rpc_out->retval = CXL_MBOX_CMD_RC_SUCCESS;
-	*out_len = sizeof(*rpc_out);
 
 	return no_free_ptr(rpc_out);
 }
···
 	fwctl_put(fwctl_dev);
 }
 
-int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd)
+int devm_cxl_setup_fwctl(struct device *host, struct cxl_memdev *cxlmd)
 {
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
 	struct cxl_features_state *cxlfs;
···
 	if (rc)
 		return rc;
 
-	return devm_add_action_or_reset(&cxlmd->dev, free_memdev_fwctl,
+	return devm_add_action_or_reset(host, free_memdev_fwctl,
 					no_free_ptr(fwctl_dev));
 }
 EXPORT_SYMBOL_NS_GPL(devm_cxl_setup_fwctl, "CXL");

drivers/cxl/core/pci.c

···
 #define GPF_TIMEOUT_BASE_MAX 2
 #define GPF_TIMEOUT_SCALE_MAX 7 /* 10 seconds */
 
-u16 cxl_gpf_get_dvsec(struct device *dev, bool is_port)
+u16 cxl_gpf_get_dvsec(struct device *dev)
 {
+	struct pci_dev *pdev;
+	bool is_port = true;
 	u16 dvsec;
 
 	if (!dev_is_pci(dev))
 		return 0;
 
-	dvsec = pci_find_dvsec_capability(to_pci_dev(dev), PCI_VENDOR_ID_CXL,
+	pdev = to_pci_dev(dev);
+	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ENDPOINT)
+		is_port = false;
+
+	dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_CXL,
 			is_port ? CXL_DVSEC_PORT_GPF : CXL_DVSEC_DEVICE_GPF);
 	if (!dvsec)
 		dev_warn(dev, "%s GPF DVSEC not present\n",
···
 	return rc;
 }
 
-int cxl_gpf_port_setup(struct device *dport_dev, struct cxl_port *port)
+int cxl_gpf_port_setup(struct cxl_dport *dport)
 {
-	struct pci_dev *pdev;
-
-	if (!port)
+	if (!dport)
 		return -EINVAL;
 
-	if (!port->gpf_dvsec) {
+	if (!dport->gpf_dvsec) {
+		struct pci_dev *pdev;
 		int dvsec;
 
-		dvsec = cxl_gpf_get_dvsec(dport_dev, true);
+		dvsec = cxl_gpf_get_dvsec(dport->dport_dev);
 		if (!dvsec)
 			return -EINVAL;
 
-		port->gpf_dvsec = dvsec;
+		dport->gpf_dvsec = dvsec;
+		pdev = to_pci_dev(dport->dport_dev);
+		update_gpf_port_dvsec(pdev, dport->gpf_dvsec, 1);
+		update_gpf_port_dvsec(pdev, dport->gpf_dvsec, 2);
 	}
-
-	pdev = to_pci_dev(dport_dev);
-	update_gpf_port_dvsec(pdev, port->gpf_dvsec, 1);
-	update_gpf_port_dvsec(pdev, port->gpf_dvsec, 2);
 
 	return 0;
 }

drivers/cxl/core/port.c

···
 			if (rc && rc != -EBUSY)
 				return rc;
 
-			cxl_gpf_port_setup(dport_dev, port);
+			cxl_gpf_port_setup(dport);
 
 			/* Any more ports to add between this one and the root? */
 			if (!dev_is_cxl_root_child(&port->dev))

drivers/cxl/core/regs.c

···
 	resource_size_t rcrb = ri->base;
 	void __iomem *addr;
 	u32 bar0, bar1;
-	u16 cmd;
 	u32 id;
 
 	if (which == CXL_RCRB_UPSTREAM)
···
 	}
 
 	id = readl(addr + PCI_VENDOR_ID);
-	cmd = readw(addr + PCI_COMMAND);
 	bar0 = readl(addr + PCI_BASE_ADDRESS_0);
 	bar1 = readl(addr + PCI_BASE_ADDRESS_1);
 	iounmap(addr);
···
 			dev_err(dev, "Failed to access Downstream Port RCRB\n");
 		return CXL_RESOURCE_NONE;
 	}
-	if (!(cmd & PCI_COMMAND_MEMORY))
-		return CXL_RESOURCE_NONE;
 	/* The RCRB is a Memory Window, and the MEM_TYPE_1M bit is obsolete */
 	if (bar0 & (PCI_BASE_ADDRESS_MEM_TYPE_1M | PCI_BASE_ADDRESS_SPACE_IO))
 		return CXL_RESOURCE_NONE;

drivers/cxl/cxl.h

···
  * @cdat: Cached CDAT data
  * @cdat_available: Should a CDAT attribute be available in sysfs
  * @pci_latency: Upstream latency in picoseconds
- * @gpf_dvsec: Cached GPF port DVSEC
  */
 struct cxl_port {
 	struct device dev;
···
 	} cdat;
 	bool cdat_available;
 	long pci_latency;
-	int gpf_dvsec;
 };
 
 /**
···
  * @regs: Dport parsed register blocks
  * @coord: access coordinates (bandwidth and latency performance attributes)
  * @link_latency: calculated PCIe downstream latency
+ * @gpf_dvsec: Cached GPF port DVSEC
  */
 struct cxl_dport {
 	struct device *dport_dev;
···
 	struct cxl_regs regs;
 	struct access_coordinate coord[ACCESS_COORDINATE_MAX];
 	long link_latency;
+	int gpf_dvsec;
 };
 
 /**
···
 #define __mock static
 #endif
 
-u16 cxl_gpf_get_dvsec(struct device *dev, bool is_port);
+u16 cxl_gpf_get_dvsec(struct device *dev);
 
 #endif /* __CXL_H__ */

drivers/cxl/pci.c

···
 	if (rc)
 		return rc;
 
-	rc = devm_cxl_setup_fwctl(cxlmd);
+	rc = devm_cxl_setup_fwctl(&pdev->dev, cxlmd);
 	if (rc)
 		dev_dbg(&pdev->dev, "No CXL FWCTL setup\n");
 

drivers/cxl/pmem.c

···
 		return;
 	}
 
-	if (!cxl_gpf_get_dvsec(cxlds->dev, false))
+	if (!cxl_gpf_get_dvsec(cxlds->dev))
 		return;
 
 	if (cxl_get_dirty_count(mds, &count)) {

drivers/firmware/stratix10-svc.c

···
 	if (!svc->intel_svc_fcs) {
 		dev_err(dev, "failed to allocate %s device\n", INTEL_FCS);
 		ret = -ENOMEM;
-		goto err_unregister_dev;
+		goto err_unregister_rsu_dev;
 	}
 
 	ret = platform_device_add(svc->intel_svc_fcs);
 	if (ret) {
 		platform_device_put(svc->intel_svc_fcs);
-		goto err_unregister_dev;
+		goto err_unregister_rsu_dev;
 	}
+
+	ret = of_platform_default_populate(dev_of_node(dev), NULL, dev);
+	if (ret)
+		goto err_unregister_fcs_dev;
 
 	dev_set_drvdata(dev, svc);
 
···
 
 	return 0;
 
-err_unregister_dev:
+err_unregister_fcs_dev:
+	platform_device_unregister(svc->intel_svc_fcs);
+err_unregister_rsu_dev:
 	platform_device_unregister(svc->stratix10_svc_rsu);
 err_free_kfifo:
 	kfifo_free(&controller->svc_fifo);
···
 {
 	struct stratix10_svc *svc = dev_get_drvdata(&pdev->dev);
 	struct stratix10_svc_controller *ctrl = platform_get_drvdata(pdev);
+
+	of_platform_depopulate(ctrl->dev);
 
 	platform_device_unregister(svc->intel_svc_fcs);
 	platform_device_unregister(svc->stratix10_svc_rsu);

drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c

···
 #include <linux/dma-fence-array.h>
 #include <linux/pci-p2pdma.h>
 
+static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops;
+
+/**
+ * dma_buf_attach_adev - Helper to get adev of an attachment
+ *
+ * @attach: attachment
+ *
+ * Returns:
+ * A struct amdgpu_device * if the attaching device is an amdgpu device or
+ * partition, NULL otherwise.
+ */
+static struct amdgpu_device *dma_buf_attach_adev(struct dma_buf_attachment *attach)
+{
+	if (attach->importer_ops == &amdgpu_dma_buf_attach_ops) {
+		struct drm_gem_object *obj = attach->importer_priv;
+		struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+		return amdgpu_ttm_adev(bo->tbo.bdev);
+	}
+
+	return NULL;
+}
+
 /**
  * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
  *
···
 static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
 				 struct dma_buf_attachment *attach)
 {
+	struct amdgpu_device *attach_adev = dma_buf_attach_adev(attach);
 	struct drm_gem_object *obj = dmabuf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 
-	if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
+	if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) &&
+	    pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
 		attach->peer2peer = false;
 
 	amdgpu_vm_bo_update_shared(bo);
···
 {
 	struct dma_buf *dmabuf = attach->dmabuf;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(dmabuf->priv);
-	u32 domains = bo->preferred_domains;
+	u32 domains = bo->allowed_domains;
 
 	dma_resv_assert_held(dmabuf->resv);
 
-	/*
-	 * Try pinning into VRAM to allow P2P with RDMA NICs without ODP
+	/* Try pinning into VRAM to allow P2P with RDMA NICs without ODP
 	 * support if all attachments can do P2P. If any attachment can't do
 	 * P2P just pin into GTT instead.
+	 *
+	 * To avoid with conflicting pinnings between GPUs and RDMA when move
+	 * notifiers are disabled, only allow pinning in VRAM when move
+	 * notiers are enabled.
 	 */
-	list_for_each_entry(attach, &dmabuf->attachments, node)
-		if (!attach->peer2peer)
-			domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+	if (!IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)) {
+		domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+	} else {
+		list_for_each_entry(attach, &dmabuf->attachments, node)
+			if (!attach->peer2peer)
+				domains &= ~AMDGPU_GEM_DOMAIN_VRAM;
+	}
 
 	if (domains & AMDGPU_GEM_DOMAIN_VRAM)
 		bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+
+	if (WARN_ON(!domains))
+		return -EINVAL;
 
 	return amdgpu_bo_pin(bo, domains);
 }
···
 {
 	struct drm_gem_object *obj = &bo->tbo.base;
 	struct drm_gem_object *gobj;
+
+	if (!adev)
+		return false;
 
 	if (obj->import_attach) {
 		struct dma_buf *dma_buf = obj->import_attach->dmabuf;

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

···
 	switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) {
 	case IP_VERSION(3, 5, 0):
 	case IP_VERSION(3, 6, 0):
-		/*
-		 * On DCN35 systems with Z8 enabled, it's possible for IPS2 + Z8 to
-		 * cause a hard hang. A fix exists for newer PMFW.
-		 *
-		 * As a workaround, for non-fixed PMFW, force IPS1+RCG as the deepest
-		 * IPS state in all cases, except for s0ix and all displays off (DPMS),
-		 * where IPS2 is allowed.
-		 *
-		 * When checking pmfw version, use the major and minor only.
-		 */
-		if ((adev->pm.fw_version & 0x00FFFF00) < 0x005D6300)
-			ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
-		else if (amdgpu_ip_version(adev, GC_HWIP, 0) > IP_VERSION(11, 5, 0))
-			/*
-			 * Other ASICs with DCN35 that have residency issues with
-			 * IPS2 in idle.
-			 * We want them to use IPS2 only in display off cases.
-			 */
-			ret =  DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
-		break;
 	case IP_VERSION(3, 5, 1):
 		ret =  DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
 		break;
···
 	for (k = 0; k < dc_state->stream_count; k++) {
 		bundle->stream_update.stream = dc_state->streams[k];
 
-		for (m = 0; m < dc_state->stream_status->plane_count; m++) {
+		for (m = 0; m < dc_state->stream_status[k].plane_count; m++) {
 			bundle->surface_updates[m].surface =
-				dc_state->stream_status->plane_states[m];
+				dc_state->stream_status[k].plane_states[m];
 			bundle->surface_updates[m].surface->force_full_update =
 				true;
 		}
 
 		update_planes_and_stream_adapter(dm->dc,
 					 UPDATE_TYPE_FULL,
-					 dc_state->stream_status->plane_count,
+					 dc_state->stream_status[k].plane_count,
 					 dc_state->streams[k],
 					 &bundle->stream_update,
 					 bundle->surface_updates);
···
 					const struct drm_display_mode *native_mode,
 					bool scale_enabled)
 {
-	if (scale_enabled) {
-		copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
-	} else if (native_mode->clock == drm_mode->clock &&
-			native_mode->htotal == drm_mode->htotal &&
-			native_mode->vtotal == drm_mode->vtotal) {
-		copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
+	if (scale_enabled || (
+	    native_mode->clock == drm_mode->clock &&
+	    native_mode->htotal == drm_mode->htotal &&
+	    native_mode->vtotal == drm_mode->vtotal)) {
+		if (native_mode->crtc_clock)
+			copy_crtc_timing_for_drm_display_mode(native_mode, drm_mode);
 	} else {
 		/* no scaling nor amdgpu inserted, no need to patch */
 	}
···
 	 */
 	if (amdgpu_ip_version(adev, DCE_HWIP, 0) < IP_VERSION(3, 2, 0) &&
 	    state->allow_modeset)
+		return true;
+
+	if (amdgpu_in_reset(adev) && state->allow_modeset)
 		return true;
 
 	/* Exit early if we know that we're adding or removing the plane. */

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c

···
 {
 	struct drm_connector *connector = data;
 	struct acpi_device *acpidev = ACPI_COMPANION(connector->dev->dev);
-	unsigned char start = block * EDID_LENGTH;
+	unsigned short start = block * EDID_LENGTH;
 	struct edid *edid;
 	int r;
 

drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c

···
 	.dcn_downspread_percent = 0.5,
 	.gpuvm_min_page_size_bytes = 4096,
 	.hostvm_min_page_size_bytes = 4096,
-	.do_urgent_latency_adjustment = 0,
+	.do_urgent_latency_adjustment = 1,
 	.urgent_latency_adjustment_fabric_clock_component_us = 0,
-	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+	.urgent_latency_adjustment_fabric_clock_reference_mhz = 3000,
 };
 
 void dcn35_build_wm_range_table_fpu(struct clk_mgr *clk_mgr)

drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c

···
 #define DC_LOGGER \
 	link->ctx->logger
 
+static void get_default_8b_10b_lttpr_aux_rd_interval(
+		union training_aux_rd_interval *training_rd_interval)
+{
+	/* LTTPR are required to program DPCD 0000Eh to 0x4 (16ms) upon AUX
+	 * read reply to this register. Since old sinks with DPCD rev 1.1
+	 * and earlier may not support this register, assume the mandatory
+	 * value is programmed by the LTTPR to avoid AUX timeout issues.
+	 */
+	training_rd_interval->raw = 0x4;
+}
+
 static int32_t get_cr_training_aux_rd_interval(struct dc_link *link,
 		const struct dc_link_settings *link_settings,
 		enum lttpr_mode lttpr_mode)
···
 	uint32_t wait_in_micro_secs = 100;
 
 	memset(&training_rd_interval, 0, sizeof(training_rd_interval));
-	if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING &&
-			link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) {
-		core_link_read_dpcd(
-				link,
-				DP_TRAINING_AUX_RD_INTERVAL,
-				(uint8_t *)&training_rd_interval,
-				sizeof(training_rd_interval));
-		if (lttpr_mode != LTTPR_MODE_NON_TRANSPARENT)
-			wait_in_micro_secs = 400;
-		if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL)
-			wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
+	if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) {
+		if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12)
+			core_link_read_dpcd(
+					link,
+					DP_TRAINING_AUX_RD_INTERVAL,
+					(uint8_t *)&training_rd_interval,
+					sizeof(training_rd_interval));
+		else if (dp_is_lttpr_present(link))
+			get_default_8b_10b_lttpr_aux_rd_interval(&training_rd_interval);
+
+		if (training_rd_interval.raw != 0) {
+			if (lttpr_mode != LTTPR_MODE_NON_TRANSPARENT)
+				wait_in_micro_secs = 400;
+			if (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL)
+				wait_in_micro_secs = training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL * 4000;
+		}
 	}
 	return wait_in_micro_secs;
 }
···
 				DP_128B132B_TRAINING_AUX_RD_INTERVAL,
 				(uint8_t *)&training_rd_interval,
 				sizeof(training_rd_interval));
-	} else if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING &&
-			link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12) {
-		core_link_read_dpcd(
-				link,
-				DP_TRAINING_AUX_RD_INTERVAL,
-				(uint8_t *)&training_rd_interval,
-				sizeof(training_rd_interval));
+	} else if (link_dp_get_encoding_format(link_settings) == DP_8b_10b_ENCODING) {
+		if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_12)
+			core_link_read_dpcd(
+					link,
+					DP_TRAINING_AUX_RD_INTERVAL,
+					(uint8_t *)&training_rd_interval,
+					sizeof(training_rd_interval));
+		else if (dp_is_lttpr_present(link))
+			get_default_8b_10b_lttpr_aux_rd_interval(&training_rd_interval);
 	}
 
 	switch (training_rd_interval.bits.TRAINIG_AUX_RD_INTERVAL) {

drivers/gpu/drm/exynos/exynos7_drm_decon.c

···
 	unsigned int wincon_burstlen_shift;
 };
 
-static struct decon_data exynos7_decon_data = {
+static const struct decon_data exynos7_decon_data = {
 	.vidw_buf_start_base = 0x80,
 	.shadowcon_win_protect_shift = 10,
 	.wincon_burstlen_shift = 11,
 };
 
-static struct decon_data exynos7870_decon_data = {
+static const struct decon_data exynos7870_decon_data = {
 	.vidw_buf_start_base = 0x880,
 	.shadowcon_win_protect_shift = 8,
 	.wincon_burstlen_shift = 10,

drivers/gpu/drm/exynos/exynos_drm_drv.c

···
 {
 	struct drm_device *drm = platform_get_drvdata(pdev);
 
-	if (drm)
-		drm_atomic_helper_shutdown(drm);
+	drm_atomic_helper_shutdown(drm);
 }
 
 static struct platform_driver exynos_drm_platform_driver = {

drivers/gpu/drm/exynos/exynos_drm_fimc.c

···
 	u32 buf_num;
 	u32 cfg;
 
-	DRM_DEV_DEBUG_KMS(ctx->dev, "buf_id[%d]enqueu[%d]\n", buf_id, enqueue);
+	DRM_DEV_DEBUG_KMS(ctx->dev, "buf_id[%d]enqueue[%d]\n", buf_id, enqueue);
 
 	spin_lock_irqsave(&ctx->lock, flags);
 

drivers/gpu/drm/exynos/exynos_drm_fimd.c

···
 	/*
 	 * Setting dma-burst to 16Word causes permanent tearing for very small
 	 * buffers, e.g. cursor buffer. Burst Mode switching which based on
-	 * plane size is not recommended as plane size varies alot towards the
+	 * plane size is not recommended as plane size varies a lot towards the
 	 * end of the screen and rapid movement causes unstable DMA, but it is
 	 * still better to change dma-burst than displaying garbage.
 	 */

drivers/gpu/drm/exynos/exynos_drm_vidi.c

···
 	else
 		drm_edid = drm_edid_alloc(fake_edid_info, sizeof(fake_edid_info));
 
-	if (!drm_edid)
-		return 0;
-
 	drm_edid_connector_update(connector, drm_edid);
 
 	count = drm_edid_connector_add_modes(connector);

drivers/gpu/drm/meson/meson_drv.c

···
 	/* S805X/S805Y HDMI PLL won't lock for HDMI PHY freq > 1,65GHz */
 	{
 		.limits = {
-			.max_hdmi_phy_freq = 1650000,
+			.max_hdmi_phy_freq = 1650000000,
 		},
 		.attrs = (const struct soc_device_attribute []) {
 			{ .soc_id = "GXL (S805*)", },

drivers/gpu/drm/meson/meson_drv.h

···
 };
 
 struct meson_drm_soc_limits {
-	unsigned int max_hdmi_phy_freq;
+	unsigned long long max_hdmi_phy_freq;
 };
 
 struct meson_drm {

drivers/gpu/drm/meson/meson_encoder_hdmi.c

···
 {
 	struct meson_drm *priv = encoder_hdmi->priv;
 	int vic = drm_match_cea_mode(mode);
-	unsigned int phy_freq;
-	unsigned int vclk_freq;
-	unsigned int venc_freq;
-	unsigned int hdmi_freq;
+	unsigned long long phy_freq;
+	unsigned long long vclk_freq;
+	unsigned long long venc_freq;
+	unsigned long long hdmi_freq;
 
-	vclk_freq = mode->clock;
+	vclk_freq = mode->clock * 1000;
 
 	/* For 420, pixel clock is half unlike venc clock */
 	if (encoder_hdmi->output_bus_fmt == MEDIA_BUS_FMT_UYYVYY8_0_5X24)
···
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		venc_freq /= 2;
 
-	dev_dbg(priv->dev, "vclk:%d phy=%d venc=%d hdmi=%d enci=%d\n",
+	dev_dbg(priv->dev,
+		"vclk:%lluHz phy=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n",
 		phy_freq, vclk_freq, venc_freq, hdmi_freq,
 		priv->venc.hdmi_use_enci);
 
···
 	struct meson_encoder_hdmi *encoder_hdmi = bridge_to_meson_encoder_hdmi(bridge);
 	struct meson_drm *priv = encoder_hdmi->priv;
 	bool is_hdmi2_sink = display_info->hdmi.scdc.supported;
-	unsigned int phy_freq;
-	unsigned int vclk_freq;
-	unsigned int venc_freq;
-	unsigned int hdmi_freq;
+	unsigned long long clock = mode->clock * 1000;
+	unsigned long long phy_freq;
+	unsigned long long vclk_freq;
+	unsigned long long venc_freq;
+	unsigned long long hdmi_freq;
 	int vic = drm_match_cea_mode(mode);
 	enum drm_mode_status status;
 
···
 		if (status != MODE_OK)
 			return status;
 
-		return meson_vclk_dmt_supported_freq(priv, mode->clock);
+		return meson_vclk_dmt_supported_freq(priv, clock);
 	/* Check against supported VIC modes */
 	} else if (!meson_venc_hdmi_supported_vic(vic))
 		return MODE_BAD;
 
-	vclk_freq = mode->clock;
+	vclk_freq = clock;
 
 	/* For 420, pixel clock is half unlike venc clock */
 	if (drm_mode_is_420_only(display_info, mode) ||
···
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		venc_freq /= 2;
 
-	dev_dbg(priv->dev, "%s: vclk:%d phy=%d venc=%d hdmi=%d\n",
+	dev_dbg(priv->dev,
+		"%s: vclk:%lluHz phy=%lluHz venc=%lluHz hdmi=%lluHz\n",
 		__func__, phy_freq, vclk_freq, venc_freq, hdmi_freq);
 
 	return meson_vclk_vic_supported_freq(priv, phy_freq, vclk_freq);

drivers/gpu/drm/meson/meson_vclk.c

···
 #define HDMI_PLL_LOCK		BIT(31)
 #define HDMI_PLL_LOCK_G12A	(3 << 30)
 
-#define FREQ_1000_1001(_freq)	DIV_ROUND_CLOSEST(_freq * 1000, 1001)
+#define PIXEL_FREQ_1000_1001(_freq)	\
+	DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL)
+#define PHY_FREQ_1000_1001(_freq)	\
+	(PIXEL_FREQ_1000_1001(DIV_ROUND_DOWN_ULL(_freq, 10ULL)) * 10)
 
 /* VID PLL Dividers */
 enum {
···
 };
 
 struct meson_vclk_params {
-	unsigned int pll_freq;
-	unsigned int phy_freq;
-	unsigned int vclk_freq;
-	unsigned int venc_freq;
-	unsigned int pixel_freq;
+	unsigned long long pll_freq;
+	unsigned long long phy_freq;
+	unsigned long long vclk_freq;
+	unsigned long long venc_freq;
+	unsigned long long pixel_freq;
 	unsigned int pll_od1;
 	unsigned int pll_od2;
 	unsigned int pll_od3;
···
 	unsigned int vclk_div;
 } params[] = {
 	[MESON_VCLK_HDMI_ENCI_54000] = {
-		.pll_freq = 4320000,
-		.phy_freq = 270000,
-		.vclk_freq = 54000,
-		.venc_freq = 54000,
-		.pixel_freq = 54000,
+		.pll_freq = 4320000000,
+		.phy_freq = 270000000,
+		.vclk_freq = 54000000,
+		.venc_freq = 54000000,
+		.pixel_freq = 54000000,
 		.pll_od1 = 4,
 		.pll_od2 = 4,
 		.pll_od3 = 1,
···
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_DDR_54000] = {
-		.pll_freq = 4320000,
-		.phy_freq = 270000,
-		.vclk_freq = 54000,
-		.venc_freq = 54000,
-		.pixel_freq = 27000,
+		.pll_freq = 4320000000,
+		.phy_freq = 270000000,
+		.vclk_freq = 54000000,
+		.venc_freq = 54000000,
+		.pixel_freq = 27000000,
 		.pll_od1 = 4,
 		.pll_od2 = 4,
 		.pll_od3 = 1,
···
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_DDR_148500] = {
-		.pll_freq = 2970000,
-		.phy_freq = 742500,
-		.vclk_freq = 148500,
-		.venc_freq = 148500,
-		.pixel_freq = 74250,
+		.pll_freq = 2970000000,
+		.phy_freq = 742500000,
+		.vclk_freq = 148500000,
+		.venc_freq = 148500000,
+		.pixel_freq = 74250000,
 		.pll_od1 = 4,
 		.pll_od2 = 1,
 		.pll_od3 = 1,
···
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_74250] = {
-		.pll_freq = 2970000,
-		.phy_freq = 742500,
-		.vclk_freq = 74250,
-		.venc_freq = 74250,
-		.pixel_freq = 74250,
+		.pll_freq = 2970000000,
+		.phy_freq = 742500000,
+		.vclk_freq = 74250000,
+		.venc_freq = 74250000,
+		.pixel_freq = 74250000,
 		.pll_od1 = 2,
 		.pll_od2 = 2,
 		.pll_od3 = 2,
···
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_148500] = {
-		.pll_freq = 2970000,
-		.phy_freq = 1485000,
-		.vclk_freq = 148500,
-		.venc_freq = 148500,
-		.pixel_freq = 148500,
+		.pll_freq = 2970000000,
+		.phy_freq = 1485000000,
+		.vclk_freq = 148500000,
+		.venc_freq = 148500000,
+		.pixel_freq = 148500000,
 		.pll_od1 = 1,
 		.pll_od2 = 2,
 		.pll_od3 = 2,
···
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_297000] = {
-		.pll_freq = 5940000,
-		.phy_freq = 2970000,
-		.venc_freq = 297000,
-		.vclk_freq = 297000,
-		.pixel_freq = 297000,
+		.pll_freq = 5940000000,
+		.phy_freq = 2970000000,
+		.venc_freq = 297000000,
+		.vclk_freq = 297000000,
+		.pixel_freq = 297000000,
 		.pll_od1 = 2,
 		.pll_od2 = 1,
 		.pll_od3 = 1,
···
 		.vclk_div = 2,
 	},
 	[MESON_VCLK_HDMI_594000] = {
-		.pll_freq = 5940000,
-		.phy_freq = 5940000,
-		.venc_freq = 594000,
-		.vclk_freq = 594000,
-		.pixel_freq = 594000,
+		.pll_freq = 5940000000,
+		.phy_freq = 5940000000,
+		.venc_freq = 594000000,
+		.vclk_freq = 594000000,
+		.pixel_freq = 594000000,
 		.pll_od1 = 1,
 		.pll_od2 = 1,
 		.pll_od3 = 2,
···
 		.vclk_div = 1,
 	},
 	[MESON_VCLK_HDMI_594000_YUV420] = {
-		.pll_freq = 5940000,
-		.phy_freq = 2970000,
-		.venc_freq = 594000,
-		.vclk_freq = 594000,
-		.pixel_freq = 297000,
+		.pll_freq = 5940000000,
+		.phy_freq = 2970000000,
+		.venc_freq = 594000000,
+		.vclk_freq = 594000000,
+		.pixel_freq = 297000000,
 		.pll_od1 = 2,
 		.pll_od2 = 1,
 		.pll_od3 = 1,
···
 				3 << 20, pll_od_to_reg(od3) << 20);
 }
 
-#define XTAL_FREQ 24000
+#define XTAL_FREQ (24 * 1000 * 1000)
 
 static unsigned int meson_hdmi_pll_get_m(struct meson_drm *priv,
-					 unsigned int pll_freq)
+					 unsigned long long pll_freq)
 {
 	/* The GXBB PLL has a /2 pre-multiplier */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB))
-		pll_freq /= 2;
+		pll_freq = DIV_ROUND_DOWN_ULL(pll_freq, 2);
 
-	return pll_freq / XTAL_FREQ;
+	return DIV_ROUND_DOWN_ULL(pll_freq, XTAL_FREQ);
 }
 
 #define HDMI_FRAC_MAX_GXBB	4096
···
 
 static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
 					    unsigned int m,
-					    unsigned int pll_freq)
+					    unsigned long long pll_freq)
 {
-	unsigned int parent_freq = XTAL_FREQ;
+	unsigned long long parent_freq = XTAL_FREQ;
 	unsigned int frac_max = HDMI_FRAC_MAX_GXL;
 	unsigned int frac_m;
 	unsigned int frac;
+	u32 remainder;
 
 	/* The GXBB PLL has a /2 pre-multiplier and a larger FRAC width */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
···
 		frac_max = HDMI_FRAC_MAX_G12A;
 
 	/* We can have a perfect match !*/
-	if (pll_freq / m == parent_freq &&
-	    pll_freq % m == 0)
+	if (div_u64_rem(pll_freq, m, &remainder) == parent_freq &&
+	    remainder == 0)
 		return 0;
 
-	frac = div_u64((u64)pll_freq * (u64)frac_max, parent_freq);
+	frac = mul_u64_u64_div_u64(pll_freq, frac_max, parent_freq);
 	frac_m = m * frac_max;
 	if (frac_m > frac)
 		return frac_max;
···
 }
 
 static bool meson_hdmi_pll_validate_params(struct meson_drm *priv,
-					   unsigned int m,
+					   unsigned long long m,
 					   unsigned int frac)
 {
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
···
 }
 
 static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
-				       unsigned int freq,
+				       unsigned long long freq,
 				       unsigned int *m,
 				       unsigned int *frac,
 				       unsigned int *od)
···
 			continue;
 		*frac = meson_hdmi_pll_get_frac(priv, *m, freq * *od);
 
-		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d\n",
+		DRM_DEBUG_DRIVER("PLL params for %lluHz: m=%x frac=%x od=%d\n",
 				 freq, *m, *frac, *od);
 
 		if (meson_hdmi_pll_validate_params(priv, *m, *frac))
···
 
 /* pll_freq is the frequency after the OD dividers */
 enum drm_mode_status
-meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq)
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned long long freq)
 {
 	unsigned int od, m, frac;
 
···
 
 /* pll_freq is the frequency after the OD dividers */
 static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
-				       unsigned int pll_freq)
+				       unsigned long long pll_freq)
 {
 	unsigned int od, m, frac, od1, od2, od3;
 
···
 			od1 = od / od2;
 		}
 
-		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d/%d/%d\n",
+		DRM_DEBUG_DRIVER("PLL params for %lluHz: m=%x frac=%x od=%d/%d/%d\n",
 				 pll_freq, m, frac, od1, od2, od3);
 
 		meson_hdmi_pll_set_params(priv, m, frac, od1, od2, od3);
···
 		return;
 	}
 
-	DRM_ERROR("Fatal, unable to find parameters for PLL freq %d\n",
+	DRM_ERROR("Fatal, unable to find parameters for PLL freq %lluHz\n",
 		  pll_freq);
 }
 
 enum drm_mode_status
-meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
-			      unsigned int vclk_freq)
+meson_vclk_vic_supported_freq(struct meson_drm *priv,
+			      unsigned long long phy_freq,
+			      unsigned long long vclk_freq)
 {
 	int i;
 
-	DRM_DEBUG_DRIVER("phy_freq = %d vclk_freq = %d\n",
+	DRM_DEBUG_DRIVER("phy_freq = %lluHz vclk_freq = %lluHz\n",
 			 phy_freq, vclk_freq);
 
 	/* Check against soc revision/package limits */
···
 	}
 
 	for (i = 0 ; params[i].pixel_freq ; ++i) {
-		DRM_DEBUG_DRIVER("i = %d pixel_freq = %d alt = %d\n",
+		DRM_DEBUG_DRIVER("i = %d pixel_freq = %lluHz alt = %lluHz\n",
 				 i, params[i].pixel_freq,
-				 FREQ_1000_1001(params[i].pixel_freq));
-		DRM_DEBUG_DRIVER("i = %d phy_freq = %d alt = %d\n",
+				 PIXEL_FREQ_1000_1001(params[i].pixel_freq));
+		DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n",
 				 i, params[i].phy_freq,
-				 FREQ_1000_1001(params[i].phy_freq/1000)*1000);
+				 PHY_FREQ_1000_1001(params[i].phy_freq));
 		/* Match strict frequency */
 		if (phy_freq == params[i].phy_freq &&
 		    vclk_freq == params[i].vclk_freq)
 			return MODE_OK;
 		/* Match 1000/1001 variant */
-		if (phy_freq == (FREQ_1000_1001(params[i].phy_freq/1000)*1000) &&
-		    vclk_freq == FREQ_1000_1001(params[i].vclk_freq))
+		if (phy_freq == PHY_FREQ_1000_1001(params[i].phy_freq) &&
+		    vclk_freq == PIXEL_FREQ_1000_1001(params[i].vclk_freq))
 			return MODE_OK;
 	}
 
···
 }
 EXPORT_SYMBOL_GPL(meson_vclk_vic_supported_freq);
 
-static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
-			   unsigned int od1, unsigned int od2, unsigned int od3,
+static void meson_vclk_set(struct meson_drm *priv,
+			   unsigned long long pll_base_freq, unsigned int od1,
+			   unsigned int od2, unsigned int od3,
 			   unsigned int vid_pll_div, unsigned int vclk_div,
 			   unsigned int hdmi_tx_div, unsigned int venc_div,
 			   bool hdmi_use_enci, bool vic_alternate_clock)
···
 		meson_hdmi_pll_generic_set(priv, pll_base_freq);
 	} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB)) {
 		switch (pll_base_freq) {
-		case 2970000:
+		case 2970000000:
 			m = 0x3d;
 			frac = vic_alternate_clock ? 0xd02 : 0xe00;
 			break;
-		case 4320000:
+		case 4320000000:
 			m = vic_alternate_clock ? 0x59 : 0x5a;
 			frac = vic_alternate_clock ? 0xe8f : 0;
 			break;
-		case 5940000:
+		case 5940000000:
 			m = 0x7b;
 			frac = vic_alternate_clock ? 0xa05 : 0xc00;
 			break;
···
 	} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) ||
 		   meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXL)) {
 		switch (pll_base_freq) {
-		case 2970000:
+		case 2970000000:
 			m = 0x7b;
 			frac = vic_alternate_clock ? 0x281 : 0x300;
 			break;
-		case 4320000:
+		case 4320000000:
 			m = vic_alternate_clock ? 0xb3 : 0xb4;
 			frac = vic_alternate_clock ? 0x347 : 0;
 			break;
-		case 5940000:
+		case 5940000000:
 			m = 0xf7;
 			frac = vic_alternate_clock ? 0x102 : 0x200;
 			break;
···
 		meson_hdmi_pll_set_params(priv, m, frac, od1, od2, od3);
 	} else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
 		switch (pll_base_freq) {
-		case 2970000:
+		case 2970000000:
 			m = 0x7b;
 			frac = vic_alternate_clock ? 0x140b4 : 0x18000;
 			break;
-		case 4320000:
+		case 4320000000:
 			m = vic_alternate_clock ? 0xb3 : 0xb4;
 			frac = vic_alternate_clock ? 0x1a3ee : 0;
 			break;
-		case 5940000:
+		case 5940000000:
 			m = 0xf7;
 			frac = vic_alternate_clock ? 0x8148 : 0x10000;
 			break;
···
 }
 
 void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
-		      unsigned int phy_freq, unsigned int vclk_freq,
-		      unsigned int venc_freq, unsigned int dac_freq,
+		      unsigned long long phy_freq, unsigned long long vclk_freq,
+		      unsigned long long venc_freq, unsigned long long dac_freq,
 		      bool hdmi_use_enci)
 {
 	bool vic_alternate_clock = false;
-	unsigned int freq;
-	unsigned int hdmi_tx_div;
-	unsigned int venc_div;
+	unsigned long long freq;
+	unsigned long long hdmi_tx_div;
+	unsigned long long venc_div;
 
 	if (target == MESON_VCLK_TARGET_CVBS) {
 		meson_venci_cvbs_clock_config(priv);
···
 		return;
 	}
 
-	hdmi_tx_div = vclk_freq / dac_freq;
+	hdmi_tx_div = DIV_ROUND_DOWN_ULL(vclk_freq, dac_freq);
 
 	if (hdmi_tx_div == 0) {
-		pr_err("Fatal Error, invalid HDMI-TX freq %d\n",
+		pr_err("Fatal Error, invalid HDMI-TX freq %lluHz\n",
 		       dac_freq);
 		return;
 	}
 
-	venc_div = vclk_freq / venc_freq;
+	venc_div = DIV_ROUND_DOWN_ULL(vclk_freq, venc_freq);
 
 	if (venc_div == 0) {
-		pr_err("Fatal Error, invalid HDMI venc freq %d\n",
+		pr_err("Fatal Error, invalid HDMI venc freq %lluHz\n",
 		       venc_freq);
 		return;
 	}
 
 	for (freq = 0 ; params[freq].pixel_freq ; ++freq) {
 		if ((phy_freq == params[freq].phy_freq ||
-		     phy_freq == FREQ_1000_1001(params[freq].phy_freq/1000)*1000) &&
+		     phy_freq == PHY_FREQ_1000_1001(params[freq].phy_freq)) &&
 		    (vclk_freq == params[freq].vclk_freq ||
-		     vclk_freq == FREQ_1000_1001(params[freq].vclk_freq))) {
+		     vclk_freq == PIXEL_FREQ_1000_1001(params[freq].vclk_freq))) {
 			if (vclk_freq != params[freq].vclk_freq)
 				vic_alternate_clock = true;
 			else
···
 	}
 
 	if (!params[freq].pixel_freq) {
-		pr_err("Fatal Error, invalid HDMI vclk freq %d\n", vclk_freq);
+		pr_err("Fatal Error, invalid HDMI vclk freq %lluHz\n",
+		       vclk_freq);
 		return;
 	}
 

drivers/gpu/drm/meson/meson_vclk.h

···
 };
 
 /* 27MHz is the CVBS Pixel Clock */
-#define MESON_VCLK_CVBS			27000
+#define MESON_VCLK_CVBS			(27 * 1000 * 1000)
 
 enum drm_mode_status
-meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq);
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned long long freq);
 enum drm_mode_status
-meson_vclk_vic_supported_freq(struct meson_drm *priv, unsigned int phy_freq,
-			      unsigned int vclk_freq);
+meson_vclk_vic_supported_freq(struct meson_drm *priv,
+			      unsigned long long phy_freq,
+			      unsigned long long vclk_freq);
 
 void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
-		      unsigned int phy_freq, unsigned int vclk_freq,
-		      unsigned int venc_freq, unsigned int dac_freq,
+		      unsigned long long phy_freq, unsigned long long vclk_freq,
+		      unsigned long long venc_freq, unsigned long long dac_freq,
 		      bool hdmi_use_enci);
 
 #endif /* __MESON_VCLK_H */

drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c

···
 {
 	struct jadard *jadard = panel_to_jadard(panel);
 
-	gpiod_set_value(jadard->reset, 1);
+	gpiod_set_value(jadard->reset, 0);
 	msleep(120);
 
 	if (jadard->desc->reset_before_power_off_vcioo) {
-		gpiod_set_value(jadard->reset, 0);
+		gpiod_set_value(jadard->reset, 1);
 
 		usleep_range(1000, 2000);
 	}

drivers/gpu/drm/virtio/virtgpu_drv.c

···
 	drm_dev_put(dev);
 }
 
+static void virtio_gpu_shutdown(struct virtio_device *vdev)
+{
+	/*
+	 * drm does its own synchronization on shutdown.
+	 * Do nothing here, opt out of device reset.
+	 */
+}
+
 static void virtio_gpu_config_changed(struct virtio_device *vdev)
 {
 	struct drm_device *dev = vdev->priv;
···
 	.id_table = id_table,
 	.probe = virtio_gpu_probe,
 	.remove = virtio_gpu_remove,
+	.shutdown = virtio_gpu_shutdown,
 	.config_changed = virtio_gpu_config_changed
 };
 

drivers/hwtracing/intel_th/Kconfig

···
 
 config INTEL_TH_MSU
 	tristate "Intel(R) Trace Hub Memory Storage Unit"
+	depends on MMU
 	help
 	  Memory Storage Unit (MSU) trace output device enables
 	  storing STP traces to system memory. It supports single

drivers/hwtracing/intel_th/msu.c

···
 #include <linux/io.h>
 #include <linux/workqueue.h>
 #include <linux/dma-mapping.h>
+#include <linux/pfn_t.h>
 
 #ifdef CONFIG_X86
 #include <asm/set_memory.h>
···
 	for (off = 0; off < msc->nr_pages << PAGE_SHIFT; off += PAGE_SIZE) {
 		struct page *page = virt_to_page(msc->base + off);
 
-		page->mapping = NULL;
 		__free_page(page);
 	}
 
···
 	int i;
 
 	for_each_sg(win->sgt->sgl, sg, win->nr_segs, i) {
-		struct page *page = msc_sg_page(sg);
-
-		page->mapping = NULL;
 		dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE,
 				  sg_virt(sg), sg_dma_address(sg));
 	}
···
 {
 	struct msc_iter *iter = vma->vm_file->private_data;
 	struct msc *msc = iter->msc;
-	unsigned long pg;
 
 	if (!atomic_dec_and_mutex_lock(&msc->mmap_count, &msc->buf_mutex))
 		return;
-
-	/* drop page _refcounts */
-	for (pg = 0; pg < msc->nr_pages; pg++) {
-		struct page *page = msc_buffer_get_page(msc, pg);
-
-		if (WARN_ON_ONCE(!page))
-			continue;
-
-		if (page->mapping)
-			page->mapping = NULL;
-	}
 
 	/* last mapping -- drop user_count */
 	atomic_dec(&msc->user_count);
···
 {
 	struct msc_iter *iter = vmf->vma->vm_file->private_data;
 	struct msc *msc = iter->msc;
+	struct page *page;
 
-	vmf->page = msc_buffer_get_page(msc, vmf->pgoff);
-	if (!vmf->page)
+	page = msc_buffer_get_page(msc, vmf->pgoff);
+	if (!page)
 		return VM_FAULT_SIGBUS;
 
-	get_page(vmf->page);
-	vmf->page->mapping = vmf->vma->vm_file->f_mapping;
-	vmf->page->index = vmf->pgoff;
-
-	return 0;
+	get_page(page);
+	return vmf_insert_mixed(vmf->vma, vmf->address, page_to_pfn_t(page));
 }
 
 static const struct vm_operations_struct msc_mmap_ops = {
···
 		atomic_dec(&msc->user_count);
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY);
+	vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY | VM_MIXEDMAP);
 	vma->vm_ops = &msc_mmap_ops;
 	return ret;
 }

drivers/i2c/busses/i2c-imx-lpi2c.c

···
 	return 0;
 
 rpm_disable:
-	pm_runtime_put(&pdev->dev);
-	pm_runtime_disable(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 
 	return ret;
 }

drivers/iommu/amd/iommu.c

···
 	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
 	struct iommu_dev_data *dev_data;
 
+	if (WARN_ON_ONCE(!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)))
+		return -EINVAL;
+
 	if (ir_data->iommu == NULL)
 		return -EINVAL;
 
···
 	 * we should not modify the IRTE
 	 */
 	if (!dev_data || !dev_data->use_vapic)
-		return 0;
+		return -EINVAL;
 
 	ir_data->cfg = irqd_cfg(data);
 	pi_data->ir_data = ir_data;
-
-	/* Note:
-	 * SVM tries to set up for VAPIC mode, but we are in
-	 * legacy mode. So, we force legacy mode instead.
-	 */
-	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) {
-		pr_debug("%s: Fall back to using intr legacy remap\n",
-			 __func__);
-		pi_data->is_guest_mode = false;
-	}
 
 	pi_data->prev_ga_tag = ir_data->cached_ga_tag;
 	if (pi_data->is_guest_mode) {

drivers/irqchip/irq-gic-v2m.c

···
 #ifdef CONFIG_ACPI
 static int acpi_num_msi;
 
-static __init struct fwnode_handle *gicv2m_get_fwnode(struct device *dev)
+static struct fwnode_handle *gicv2m_get_fwnode(struct device *dev)
 {
 	struct v2m_data *data;
 

drivers/mcb/mcb-parse.c

···
 
 	ret = mcb_device_register(bus, mdev);
 	if (ret < 0)
-		goto err;
+		return ret;
 
 	return 0;
 

drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c

···
 struct pci1xxxx_gpio {
 	struct auxiliary_device *aux_dev;
 	void __iomem *reg_base;
+	raw_spinlock_t wa_lock;
 	struct gpio_chip gpio;
 	spinlock_t lock;
 	int irq_base;
···
 	unsigned long flags;
 
 	spin_lock_irqsave(&priv->lock, flags);
-	pci1xxx_assign_bit(priv->reg_base, INTR_STAT_OFFSET(gpio), (gpio % 32), true);
+	writel(BIT(gpio % 32), priv->reg_base + INTR_STAT_OFFSET(gpio));
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
···
 	struct pci1xxxx_gpio *priv = dev_id;
 	struct gpio_chip *gc =  &priv->gpio;
 	unsigned long int_status = 0;
+	unsigned long wa_flags;
 	unsigned long flags;
 	u8 pincount;
 	int bit;
···
 			writel(BIT(bit), priv->reg_base + INTR_STATUS_OFFSET(gpiobank));
 			spin_unlock_irqrestore(&priv->lock, flags);
 			irq = irq_find_mapping(gc->irq.domain, (bit + (gpiobank * 32)));
-			handle_nested_irq(irq);
+			raw_spin_lock_irqsave(&priv->wa_lock, wa_flags);
+			generic_handle_irq(irq);
+			raw_spin_unlock_irqrestore(&priv->wa_lock, wa_flags);
 		}
 	}
 	spin_lock_irqsave(&priv->lock, flags);

drivers/misc/mei/hw-me-regs.h

···
 
 #define MEI_DEV_ID_LNL_M      0xA870  /* Lunar Lake Point M */
 
+#define MEI_DEV_ID_PTL_H      0xE370  /* Panther Lake H */
 #define MEI_DEV_ID_PTL_P      0xE470  /* Panther Lake P */
 
 /*

drivers/misc/mei/pci-me.c

···
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_LNL_M, MEI_ME_PCH15_CFG)},
 
+	{MEI_PCI_DEVICE(MEI_DEV_ID_PTL_H, MEI_ME_PCH15_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_PTL_P, MEI_ME_PCH15_CFG)},
 
 	/* required last entry */

drivers/misc/mei/vsc-tp.c

···
 #define VSC_TP_XFER_TIMEOUT_BYTES		700
 #define VSC_TP_PACKET_PADDING_SIZE		1
 #define VSC_TP_PACKET_SIZE(pkt) \
-	(sizeof(struct vsc_tp_packet) + le16_to_cpu((pkt)->len) + VSC_TP_CRC_SIZE)
+	(sizeof(struct vsc_tp_packet_hdr) + le16_to_cpu((pkt)->hdr.len) + VSC_TP_CRC_SIZE)
 #define VSC_TP_MAX_PACKET_SIZE \
-	(sizeof(struct vsc_tp_packet) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
+	(sizeof(struct vsc_tp_packet_hdr) + VSC_TP_MAX_MSG_SIZE + VSC_TP_CRC_SIZE)
 #define VSC_TP_MAX_XFER_SIZE \
 	(VSC_TP_MAX_PACKET_SIZE + VSC_TP_XFER_TIMEOUT_BYTES)
 #define VSC_TP_NEXT_XFER_LEN(len, offset) \
-	(len + sizeof(struct vsc_tp_packet) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
+	(len + sizeof(struct vsc_tp_packet_hdr) + VSC_TP_CRC_SIZE - offset + VSC_TP_PACKET_PADDING_SIZE)
 
-struct vsc_tp_packet {
+struct vsc_tp_packet_hdr {
 	__u8 sync;
 	__u8 cmd;
 	__le16 len;
 	__le32 seq;
-	__u8 buf[] __counted_by(len);
+};
+
+struct vsc_tp_packet {
+	struct vsc_tp_packet_hdr hdr;
+	__u8 buf[VSC_TP_MAX_XFER_SIZE - sizeof(struct vsc_tp_packet_hdr)];
 };
 
 struct vsc_tp {
···
 	u32 seq;
 
 	/* command buffer */
-	void *tx_buf;
-	void *rx_buf;
+	struct vsc_tp_packet *tx_buf;
+	struct vsc_tp_packet *rx_buf;
 
 	atomic_t assert_cnt;
 	wait_queue_head_t xfer_wait;
···
 static int vsc_tp_xfer_helper(struct vsc_tp *tp, struct vsc_tp_packet *pkt,
 			      void *ibuf, u16 ilen)
 {
-	int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet);
+	int ret, offset = 0, cpy_len, src_len, dst_len = sizeof(struct vsc_tp_packet_hdr);
 	int next_xfer_len = VSC_TP_PACKET_SIZE(pkt) + VSC_TP_XFER_TIMEOUT_BYTES;
-	u8 *src, *crc_src, *rx_buf = tp->rx_buf;
+	u8 *src, *crc_src, *rx_buf = (u8 *)tp->rx_buf;
 	int count_down = VSC_TP_MAX_XFER_COUNT;
 	u32 recv_crc = 0, crc = ~0;
-	struct vsc_tp_packet ack;
+	struct vsc_tp_packet_hdr ack;
 	u8 *dst = (u8 *)&ack;
 	bool synced = false;
 
···
 
 	guard(mutex)(&tp->mutex);
 
-	pkt->sync = VSC_TP_PACKET_SYNC;
-	pkt->cmd = cmd;
-	pkt->len = cpu_to_le16(olen);
-	pkt->seq = cpu_to_le32(++tp->seq);
+	pkt->hdr.sync = VSC_TP_PACKET_SYNC;
+	pkt->hdr.cmd = cmd;
+	pkt->hdr.len = cpu_to_le16(olen);
+	pkt->hdr.seq = cpu_to_le32(++tp->seq);
 	memcpy(pkt->buf, obuf, olen);
 
 	crc = ~crc32(~0, (u8 *)pkt, sizeof(pkt) + olen);
···
 	guard(mutex)(&tp->mutex);
 
 	/* rom xfer is big endian */
-	cpu_to_be32_array(tp->tx_buf, obuf, words);
+	cpu_to_be32_array((u32 *)tp->tx_buf, obuf, words);
 
 	ret = read_poll_timeout(gpiod_get_value_cansleep, ret,
 				!ret, VSC_TP_ROM_XFER_POLL_DELAY_US,
···
 		return ret;
 
 	if (ibuf)
-		be32_to_cpu_array(ibuf, tp->rx_buf, words);
+		be32_to_cpu_array(ibuf, (u32 *)tp->rx_buf, words);
 
 	return ret;
 }
···
 	if (!tp)
 		return -ENOMEM;
 
-	tp->tx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+	tp->tx_buf = devm_kzalloc(dev, sizeof(*tp->tx_buf), GFP_KERNEL);
 	if (!tp->tx_buf)
 		return -ENOMEM;
 
-	tp->rx_buf = devm_kzalloc(dev, VSC_TP_MAX_XFER_SIZE, GFP_KERNEL);
+	tp->rx_buf = devm_kzalloc(dev, sizeof(*tp->rx_buf), GFP_KERNEL);
 	if (!tp->rx_buf)
 		return -ENOMEM;
 

drivers/misc/pci_endpoint_test.c

···
 struct pci_endpoint_test_data {
 	enum pci_barno test_reg_bar;
 	size_t alignment;
-	int irq_type;
 };
 
 static inline u32 pci_endpoint_test_readl(struct pci_endpoint_test *test,
···
 		test_reg_bar = data->test_reg_bar;
 		test->test_reg_bar = test_reg_bar;
 		test->alignment = data->alignment;
-		test->irq_type = data->irq_type;
 	}
 
 	init_completion(&test->irq_raised);
···
 	}
 
 	pci_set_master(pdev);
-
-	ret = pci_endpoint_test_alloc_irq_vectors(test, test->irq_type);
-	if (ret)
-		goto err_disable_irq;
 
 	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
 		if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) {
···
 		goto err_ida_remove;
 	}
 
-	ret = pci_endpoint_test_request_irq(test);
-	if (ret)
-		goto err_kfree_test_name;
-
 	pci_endpoint_test_get_capabilities(test);
 
 	misc_device = &test->miscdev;
···
 	misc_device->name = kstrdup(name, GFP_KERNEL);
 	if (!misc_device->name) {
 		ret = -ENOMEM;
-		goto err_release_irq;
+		goto err_kfree_test_name;
 	}
 	misc_device->parent = &pdev->dev;
 	misc_device->fops = &pci_endpoint_test_fops;
···
 err_kfree_name:
 	kfree(misc_device->name);
 
-err_release_irq:
-	pci_endpoint_test_release_irq(test);
-
 err_kfree_test_name:
 	kfree(test->name);
 
···
 			pci_iounmap(pdev, test->bar[bar]);
 	}
 
-err_disable_irq:
-	pci_endpoint_test_free_irq_vectors(test);
 	pci_release_regions(pdev);
 
 err_disable_pdev:
···
 static const struct pci_endpoint_test_data default_data = {
 	.test_reg_bar = BAR_0,
 	.alignment = SZ_4K,
-	.irq_type = PCITEST_IRQ_TYPE_MSI,
 };
 
 static const struct pci_endpoint_test_data am654_data = {
 	.test_reg_bar = BAR_2,
 	.alignment = SZ_64K,
-	.irq_type = PCITEST_IRQ_TYPE_MSI,
 };
 
 static const struct pci_endpoint_test_data j721e_data = {
 	.alignment = 256,
-	.irq_type = PCITEST_IRQ_TYPE_MSI,
 };
 
 static const struct pci_endpoint_test_data rk3588_data = {
 	.alignment = SZ_64K,
-	.irq_type = PCITEST_IRQ_TYPE_MSI,
 };
 
 /*

drivers/net/dsa/mt7530.c

···
 	struct mt7530_priv *priv = ds->priv;
 	int ret, i;
 
+	ds->assisted_learning_on_cpu_port = true;
+	ds->mtu_enforcement_ingress = true;
+
 	mt753x_trap_frames(priv);
 
 	/* Enable and reset MIB counters */
···
 	ret = mt7531_setup_common(ds);
 	if (ret)
 		return ret;
-
-	ds->assisted_learning_on_cpu_port = true;
-	ds->mtu_enforcement_ingress = true;
 
 	return 0;
 }

drivers/net/ethernet/amd/pds_core/adminq.c

···
 
 #include "core.h"
 
-struct pdsc_wait_context {
-	struct pdsc_qcq *qcq;
-	struct completion wait_completion;
-};
-
 static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
 {
 	union pds_core_notifyq_comp *comp;
···
 		q_info = &q->info[q->tail_idx];
 		q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1);
 
-		/* Copy out the completion data */
-		memcpy(q_info->dest, comp, sizeof(*comp));
-
-		complete_all(&q_info->wc->wait_completion);
+		if (!completion_done(&q_info->completion)) {
+			memcpy(q_info->dest, comp, sizeof(*comp));
+			complete(&q_info->completion);
+		}
 
 		if (cq->tail_idx == cq->num_descs - 1)
 			cq->done_color = !cq->done_color;
···
 static int __pdsc_adminq_post(struct pdsc *pdsc,
 			      struct pdsc_qcq *qcq,
 			      union pds_core_adminq_cmd *cmd,
-			      union pds_core_adminq_comp *comp,
-			      struct pdsc_wait_context *wc)
+			      union pds_core_adminq_comp *comp)
 {
 	struct pdsc_queue *q = &qcq->q;
 	struct pdsc_q_info *q_info;
···
 	/* Post the request */
 	index = q->head_idx;
 	q_info = &q->info[index];
-	q_info->wc = wc;
 	q_info->dest = comp;
 	memcpy(q_info->desc, cmd, sizeof(*cmd));
+	reinit_completion(&q_info->completion);
 
 	dev_dbg(pdsc->dev, "head_idx %d tail_idx %d\n",
 		q->head_idx, q->tail_idx);
···
 		     union pds_core_adminq_comp *comp,
 		     bool fast_poll)
 {
-	struct pdsc_wait_context wc = {
-		.wait_completion =
-			COMPLETION_INITIALIZER_ONSTACK(wc.wait_completion),
-	};
 	unsigned long poll_interval = 1;
 	unsigned long poll_jiffies;
 	unsigned long time_limit;
 	unsigned long time_start;
 	unsigned long time_done;
 	unsigned long remaining;
+	struct completion *wc;
 	int err = 0;
 	int index;
 
···
 		return -ENXIO;
 	}
 
-	wc.qcq = &pdsc->adminqcq;
-	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
+	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp);
 	if (index < 0) {
 		err = index;
 		goto err_out;
 	}
 
+	wc = &pdsc->adminqcq.q.info[index].completion;
 	time_start = jiffies;
 	time_limit = time_start + HZ * pdsc->devcmd_timeout;
 	do {
 		/* Timeslice the actual wait to catch IO errors etc early */
 		poll_jiffies = msecs_to_jiffies(poll_interval);
-		remaining = wait_for_completion_timeout(&wc.wait_completion,
-							poll_jiffies);
+		remaining = wait_for_completion_timeout(wc, poll_jiffies);
 		if (remaining)
 			break;
 
···
 	dev_dbg(pdsc->dev, "%s: elapsed %d msecs\n",
 		__func__, jiffies_to_msecs(time_done - time_start));
 
-	/* Check the results */
-	if (time_after_eq(time_done, time_limit))
+	/* Check the results and clear an un-completed timeout */
+	if (time_after_eq(time_done, time_limit) && !completion_done(wc)) {
 		err = -ETIMEDOUT;
+		complete(wc);
+	}
 
 	dev_dbg(pdsc->dev, "read admin queue completion idx %d:\n", index);
 	dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1,

drivers/net/ethernet/amd/pds_core/auxbus.c

···
 	dev_dbg(pf->dev, "%s: %s opcode %d\n",
 		__func__, dev_name(&padev->aux_dev.dev), req->opcode);
 
-	if (pf->state)
-		return -ENXIO;
-
 	/* Wrap the client's request */
 	cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD;
 	cmd.client_request.client_id = cpu_to_le16(padev->client_id);

drivers/net/ethernet/amd/pds_core/core.c

···
 	q->base = base;
 	q->base_pa = base_pa;
 
-	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++)
+	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) {
 		cur->desc = base + (i * q->desc_size);
+		init_completion(&cur->completion);
+	}
 }
 
 static void pdsc_cq_map(struct pdsc_cq *cq, void *base, dma_addr_t base_pa)
···
 	size_t sz;
 	int err;
 
-	/* Scale the descriptor ring length based on number of CPUs and VFs */
-	numdescs = max_t(int, PDSC_ADMINQ_MIN_LENGTH, num_online_cpus());
-	numdescs += 2 * pci_sriov_get_totalvfs(pdsc->pdev);
-	numdescs = roundup_pow_of_two(numdescs);
+	numdescs = PDSC_ADMINQ_MAX_LENGTH;
 	err = pdsc_qcq_alloc(pdsc, PDS_CORE_QTYPE_ADMINQ, 0, "adminq",
 			     PDS_CORE_QCQ_F_CORE | PDS_CORE_QCQ_F_INTR,
 			     numdescs,

drivers/net/ethernet/amd/pds_core/core.h

···
 
 #define PDSC_WATCHDOG_SECS	5
 #define PDSC_QUEUE_NAME_MAX_SZ  16
-#define PDSC_ADMINQ_MIN_LENGTH	16	/* must be a power of two */
+#define PDSC_ADMINQ_MAX_LENGTH	16	/* must be a power of two */
 #define PDSC_NOTIFYQ_LENGTH	64	/* must be a power of two */
 #define PDSC_TEARDOWN_RECOVERY	false
 #define PDSC_TEARDOWN_REMOVING	true
···
 	unsigned int bytes;
 	unsigned int nbufs;
 	struct pdsc_buf_info bufs[PDS_CORE_MAX_FRAGS];
-	struct pdsc_wait_context *wc;
+	struct completion completion;
 	void *dest;
 };
 

drivers/net/ethernet/amd/pds_core/devlink.c

···
 		.fw_control.opcode = PDS_CORE_CMD_FW_CONTROL,
 		.fw_control.oper = PDS_CORE_FW_GET_LIST,
 	};
-	struct pds_core_fw_list_info fw_list;
+	struct pds_core_fw_list_info fw_list = {};
 	struct pdsc *pdsc = devlink_priv(dl);
 	union pds_core_dev_comp comp;
 	char buf[32];
···
 	if (!err)
 		memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
 	mutex_unlock(&pdsc->devcmd_lock);
-	if (err && err != -EIO)
-		return err;
 
 	listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names));
 	for (i = 0; i < listlen; i++) {

drivers/net/ethernet/freescale/enetc/enetc.c

···
 	}
 }
 
+static void enetc_bulk_flip_buff(struct enetc_bdr *rx_ring, int rx_ring_first,
+				 int rx_ring_last)
+{
+	while (rx_ring_first != rx_ring_last) {
+		enetc_flip_rx_buff(rx_ring,
+				   &rx_ring->rx_swbd[rx_ring_first]);
+		enetc_bdr_idx_inc(rx_ring, &rx_ring_first);
+	}
+}
+
 static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				   struct napi_struct *napi, int work_limit,
 				   struct bpf_prog *prog)
···
 
 	while (likely(rx_frm_cnt < work_limit)) {
 		union enetc_rx_bd *rxbd, *orig_rxbd;
-		int orig_i, orig_cleaned_cnt;
 		struct xdp_buff xdp_buff;
 		struct sk_buff *skb;
+		int orig_i, err;
 		u32 bd_status;
-		int err;
 
 		rxbd = enetc_rxbd(rx_ring, i);
 		bd_status = le32_to_cpu(rxbd->r.lstatus);
···
 			break;
 
 		orig_rxbd = rxbd;
-		orig_cleaned_cnt = cleaned_cnt;
 		orig_i = i;
 
 		enetc_build_xdp_buff(rx_ring, bd_status, &rxbd, &i,
···
 			rx_ring->stats.xdp_drops++;
 			break;
 		case XDP_PASS:
-			rxbd = orig_rxbd;
-			cleaned_cnt = orig_cleaned_cnt;
-			i = orig_i;
-
-			skb = enetc_build_skb(rx_ring, bd_status, &rxbd,
-					      &i, &cleaned_cnt,
-					      ENETC_RXB_DMA_SIZE_XDP);
-			if (unlikely(!skb))
+			skb = xdp_build_skb_from_buff(&xdp_buff);
+			/* Probably under memory pressure, stop NAPI */
+			if (unlikely(!skb)) {
+				enetc_xdp_drop(rx_ring, orig_i, i);
+				rx_ring->stats.xdp_drops++;
 				goto out;
+			}
+
+			enetc_get_offloads(rx_ring, orig_rxbd, skb);
+
+			/* These buffers are about to be owned by the stack.
+			 * Update our buffer cache (the rx_swbd array elements)
+			 * with their other page halves.
+			 */
+			enetc_bulk_flip_buff(rx_ring, orig_i, i);
 
 			napi_gro_receive(napi, skb);
 			break;
···
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				rx_ring->stats.xdp_redirect_failures++;
 			} else {
-				while (orig_i != i) {
-					enetc_flip_rx_buff(rx_ring,
-							   &rx_ring->rx_swbd[orig_i]);
-					enetc_bdr_idx_inc(rx_ring, &orig_i);
-				}
+				enetc_bulk_flip_buff(rx_ring, orig_i, i);
 				xdp_redirect_frm_cnt++;
 				rx_ring->stats.xdp_redirect++;
 			}
···
 	bdr->buffer_offset = ENETC_RXB_PAD;
 	priv->rx_ring[i] = bdr;
 
-	err = xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0);
+	err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0,
+				 ENETC_RXB_DMA_SIZE_XDP);
 	if (err)
 		goto free_vector;
 

drivers/net/ethernet/mediatek/mtk_eth_soc.c

···
 	mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);
 
 	if (mtk_is_netsys_v3_or_greater(eth)) {
-		/* PSE should not drop port1, port8 and port9 packets */
-		mtk_w32(eth, 0x00000302, PSE_DROP_CFG);
+		/* PSE dummy page mechanism */
+		mtk_w32(eth, PSE_DUMMY_WORK_GDM(1) | PSE_DUMMY_WORK_GDM(2) |
+			PSE_DUMMY_WORK_GDM(3) | DUMMY_PAGE_THR, PSE_DUMY_REQ);
+
+		/* PSE free buffer drop threshold */
+		mtk_w32(eth, 0x00600009, PSE_IQ_REV(8));
+
+		/* PSE should not drop port8, port9 and port13 packets from
+		 * WDMA Tx
+		 */
+		mtk_w32(eth, 0x00002300, PSE_DROP_CFG);
+
+		/* PSE should drop packets to port8, port9 and port13 on WDMA Rx
+		 * ring full
+		 */
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(0));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(1));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(2));
 
 		/* GDM and CDM Threshold */
-		mtk_w32(eth, 0x00000707, MTK_CDMW0_THRES);
+		mtk_w32(eth, 0x08000707, MTK_CDMW0_THRES);
 		mtk_w32(eth, 0x00000077, MTK_CDMW1_THRES);
 
 		/* Disable GDM1 RX CRC stripping */
···
 		mtk_w32(eth, 0x00000300, PSE_DROP_CFG);
 
 		/* PSE should drop packets to port 8/9 on WDMA Rx ring full */
-		mtk_w32(eth, 0x00000300, PSE_PPE0_DROP);
+		mtk_w32(eth, 0x00000300, PSE_PPE_DROP(0));
 
 		/* PSE Free Queue Flow Control  */
 		mtk_w32(eth, 0x01fa01f4, PSE_FQFC_CFG2);

drivers/net/ethernet/mediatek/mtk_eth_soc.h

···
 #define PSE_FQFC_CFG1		0x100
 #define PSE_FQFC_CFG2		0x104
 #define PSE_DROP_CFG		0x108
-#define PSE_PPE0_DROP		0x110
+#define PSE_PPE_DROP(x)		(0x110 + ((x) * 0x4))
+
+/* PSE Last FreeQ Page Request Control */
+#define PSE_DUMY_REQ		0x10C
+/* PSE_DUMY_REQ is not a typo but actually called like that also in
+ * MediaTek's datasheet
+ */
+#define PSE_DUMMY_WORK_GDM(x)	BIT(16 + (x))
+#define DUMMY_PAGE_THR		0x1
 
 /* PSE Input Queue Reservation Register*/
 #define PSE_IQ_REV(x)		(0x140 + (((x) - 1) << 2))

drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c

···
 	bool use_l4_type;
 	int err;
 
-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
···
 		return ERR_PTR(-EINVAL);
 	}
 
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	groups = use_l4_type ? &inner_ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
 			       &inner_ttc_groups[TTC_GROUPS_DEFAULT];
 
···
 	bool use_l4_type;
 	int err;
 
-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
···
 		return ERR_PTR(-EINVAL);
 	}
 
+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	groups = use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
 			       &ttc_groups[TTC_GROUPS_DEFAULT];
 

drivers/net/ethernet/stmicro/stmmac/dwmac1000.h

···
 
 /* PTP and timestamping registers */
 
-#define GMAC3_X_ATSNS       GENMASK(19, 16)
-#define GMAC3_X_ATSNS_SHIFT 16
+#define GMAC3_X_ATSNS       GENMASK(29, 25)
+#define GMAC3_X_ATSNS_SHIFT 25
 
 #define GMAC_PTP_TCR_ATSFC	BIT(24)
 #define GMAC_PTP_TCR_ATSEN0	BIT(25)

drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c

···
 	u64 ns;
 
 	ns = readl(ptpaddr + GMAC_PTP_ATNR);
-	ns += readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;
+	ns += (u64)readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;
 
 	*ptp_time = ns;
 }

drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c

···
 	u64 ns;
 
 	ns = readl(ptpaddr + PTP_ATNR);
-	ns += readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;
+	ns += (u64)readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;
 
 	*ptp_time = ns;
 }

drivers/net/phy/dp83822.c

···
 	return phydev->drv->config_init(phydev);
 }
 
-#ifdef CONFIG_OF_MDIO
+#if IS_ENABLED(CONFIG_OF_MDIO)
 static const u32 tx_amplitude_100base_tx_gain[] = {
 	80, 82, 83, 85, 87, 88, 90, 92,
 	93, 95, 97, 98, 100, 102, 103, 105,

drivers/net/phy/microchip.c

···
 	return __phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, page);
 }
 
-static int lan88xx_phy_config_intr(struct phy_device *phydev)
-{
-	int rc;
-
-	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
-		/* unmask all source and clear them before enable */
-		rc = phy_write(phydev, LAN88XX_INT_MASK, 0x7FFF);
-		rc = phy_read(phydev, LAN88XX_INT_STS);
-		rc = phy_write(phydev, LAN88XX_INT_MASK,
-			       LAN88XX_INT_MASK_MDINTPIN_EN_ |
-			       LAN88XX_INT_MASK_LINK_CHANGE_);
-	} else {
-		rc = phy_write(phydev, LAN88XX_INT_MASK, 0);
-		if (rc)
-			return rc;
-
-		/* Ack interrupts after they have been disabled */
-		rc = phy_read(phydev, LAN88XX_INT_STS);
-	}
-
-	return rc < 0 ? rc : 0;
-}
-
-static irqreturn_t lan88xx_handle_interrupt(struct phy_device *phydev)
-{
-	int irq_status;
-
-	irq_status = phy_read(phydev, LAN88XX_INT_STS);
-	if (irq_status < 0) {
-		phy_error(phydev);
-		return IRQ_NONE;
-	}
-
-	if (!(irq_status & LAN88XX_INT_STS_LINK_CHANGE_))
-		return IRQ_NONE;
-
-	phy_trigger_machine(phydev);
-
-	return IRQ_HANDLED;
-}
-
 static int lan88xx_suspend(struct phy_device *phydev)
 {
 	struct lan88xx_priv *priv = phydev->priv;
···
 	.config_aneg	= lan88xx_config_aneg,
 	.link_change_notify = lan88xx_link_change_notify,
 
-	.config_intr	= lan88xx_phy_config_intr,
-	.handle_interrupt = lan88xx_handle_interrupt,
+	/* Interrupt handling is broken, do not define related
+	 * functions to force polling.
+	 */
 
 	.suspend	= lan88xx_suspend,
 	.resume		= genphy_resume,

drivers/net/phy/phy_led_triggers.c

···
 	if (!phy->phy_num_led_triggers)
 		return 0;
 
-	phy->led_link_trigger = devm_kzalloc(&phy->mdio.dev,
-					     sizeof(*phy->led_link_trigger),
-					     GFP_KERNEL);
+	phy->led_link_trigger = kzalloc(sizeof(*phy->led_link_trigger),
+					GFP_KERNEL);
 	if (!phy->led_link_trigger) {
 		err = -ENOMEM;
 		goto out_clear;
···
 	if (err)
 		goto out_free_link;
 
-	phy->phy_led_triggers = devm_kcalloc(&phy->mdio.dev,
-					    phy->phy_num_led_triggers,
-					    sizeof(struct phy_led_trigger),
-					    GFP_KERNEL);
+	phy->phy_led_triggers = kcalloc(phy->phy_num_led_triggers,
+					sizeof(struct phy_led_trigger),
+					GFP_KERNEL);
 	if (!phy->phy_led_triggers) {
 		err = -ENOMEM;
 		goto out_unreg_link;
···
 out_unreg:
 	while (i--)
 		phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
-	devm_kfree(&phy->mdio.dev, phy->phy_led_triggers);
+	kfree(phy->phy_led_triggers);
 out_unreg_link:
 	phy_led_trigger_unregister(phy->led_link_trigger);
 out_free_link:
-	devm_kfree(&phy->mdio.dev, phy->led_link_trigger);
+	kfree(phy->led_link_trigger);
 	phy->led_link_trigger = NULL;
 out_clear:
 	phy->phy_num_led_triggers = 0;
···
 
 	for (i = 0; i < phy->phy_num_led_triggers; i++)
 		phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
+	kfree(phy->phy_led_triggers);
+	phy->phy_led_triggers = NULL;
 
-	if (phy->led_link_trigger)
+	if (phy->led_link_trigger) {
 		phy_led_trigger_unregister(phy->led_link_trigger);
+		kfree(phy->led_link_trigger);
+		phy->led_link_trigger = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(phy_led_triggers_unregister);

drivers/net/phy/phylink.c

···
 	unsigned int pcs_state;
 
 	bool link_failed;
+	bool suspend_link_up;
 	bool major_config_failed;
 	bool mac_supports_eee_ops;
 	bool mac_supports_eee;
···
 		/* Stop the resolver bringing the link up */
 		__set_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state);
 
-		/* Disable the carrier, to prevent transmit timeouts,
-		 * but one would hope all packets have been sent. This
-		 * also means phylink_resolve() will do nothing.
-		 */
-		if (pl->netdev)
-			netif_carrier_off(pl->netdev);
-		else
+		pl->suspend_link_up = phylink_link_is_up(pl);
+		if (pl->suspend_link_up) {
+			/* Disable the carrier, to prevent transmit timeouts,
+			 * but one would hope all packets have been sent. This
+			 * also means phylink_resolve() will do nothing.
+			 */
+			if (pl->netdev)
+				netif_carrier_off(pl->netdev);
 			pl->old_link_state = false;
+		}
 
 		/* We do not call mac_link_down() here as we want the
 		 * link to remain up to receive the WoL packets.
···
 	if (test_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state)) {
 		/* Wake-on-Lan enabled, MAC handling */
 
-		/* Call mac_link_down() so we keep the overall state balanced.
-		 * Do this under the state_mutex lock for consistency. This
-		 * will cause a "Link Down" message to be printed during
-		 * resume, which is harmless - the true link state will be
-		 * printed when we run a resolve.
-		 */
-		mutex_lock(&pl->state_mutex);
-		phylink_link_down(pl);
-		mutex_unlock(&pl->state_mutex);
+		if (pl->suspend_link_up) {
+			/* Call mac_link_down() so we keep the overall state
+			 * balanced. Do this under the state_mutex lock for
+			 * consistency. This will cause a "Link Down" message
+			 * to be printed during resume, which is harmless -
+			 * the true link state will be printed when we run a
+			 * resolve.
+			 */
+			mutex_lock(&pl->state_mutex);
+			phylink_link_down(pl);
+			mutex_unlock(&pl->state_mutex);
+		}
 
 		/* Re-apply the link parameters so that all the settings get
 		 * restored to the MAC.

drivers/net/virtio_net.c

···
 	return NETDEV_TX_OK;
 }
 
-static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
+static void __virtnet_rx_pause(struct virtnet_info *vi,
+			       struct receive_queue *rq)
 {
 	bool running = netif_running(vi->dev);
 
···
 	}
 }
 
-static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
+static void virtnet_rx_pause_all(struct virtnet_info *vi)
+{
+	int i;
+
+	/*
+	 * Make sure refill_work does not run concurrently to
+	 * avoid napi_disable race which leads to deadlock.
+	 */
+	disable_delayed_refill(vi);
+	cancel_delayed_work_sync(&vi->refill);
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		__virtnet_rx_pause(vi, &vi->rq[i]);
+}
+
+static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
+{
+	/*
+	 * Make sure refill_work does not run concurrently to
+	 * avoid napi_disable race which leads to deadlock.
+	 */
+	disable_delayed_refill(vi);
+	cancel_delayed_work_sync(&vi->refill);
+	__virtnet_rx_pause(vi, rq);
+}
+
+static void __virtnet_rx_resume(struct virtnet_info *vi,
+				struct receive_queue *rq,
+				bool refill)
 {
 	bool running = netif_running(vi->dev);
 
-	if (!try_fill_recv(vi, rq, GFP_KERNEL))
+	if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))
 		schedule_delayed_work(&vi->refill, 0);
 
 	if (running)
 		virtnet_napi_enable(rq);
+}
+
+static void virtnet_rx_resume_all(struct virtnet_info *vi)
+{
+	int i;
+
+	enable_delayed_refill(vi);
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		if (i < vi->curr_queue_pairs)
+			__virtnet_rx_resume(vi, &vi->rq[i], true);
+		else
+			__virtnet_rx_resume(vi, &vi->rq[i], false);
+	}
+}
+
+static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
+{
+	enable_delayed_refill(vi);
+	__virtnet_rx_resume(vi, rq, true);
 }
 
 static int virtnet_rx_resize(struct virtnet_info *vi,
···
 	if (prog)
 		bpf_prog_add(prog, vi->max_queue_pairs - 1);
 
+	virtnet_rx_pause_all(vi);
+
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_disable(&vi->rq[i]);
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_tx_disable(&vi->sq[i]);
-		}
 	}
 
 	if (!prog) {
···
 		vi->xdp_enabled = false;
 	}
 
+	virtnet_rx_resume_all(vi);
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (old_prog)
 			bpf_prog_put(old_prog);
-		if (netif_running(dev)) {
-			virtnet_napi_enable(&vi->rq[i]);
+		if (netif_running(dev))
 			virtnet_napi_tx_enable(&vi->sq[i]);
-		}
 	}
 
 	return 0;
···
 			rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);
 	}
 
+	virtnet_rx_resume_all(vi);
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_enable(&vi->rq[i]);
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_tx_enable(&vi->sq[i]);
-		}
 	}
 	if (prog)
 		bpf_prog_sub(prog, vi->max_queue_pairs - 1);

drivers/net/xen-netfront.c

···
 	act = bpf_prog_run_xdp(prog, xdp);
 	switch (act) {
 	case XDP_TX:
-		get_page(pdata);
 		xdpf = xdp_convert_buff_to_frame(xdp);
-		err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0);
-		if (unlikely(!err))
-			xdp_return_frame_rx_napi(xdpf);
-		else if (unlikely(err < 0))
+		if (unlikely(!xdpf)) {
 			trace_xdp_exception(queue->info->netdev, prog, act);
+			break;
+		}
+		get_page(pdata);
+		err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0);
+		if (unlikely(err <= 0)) {
+			if (err < 0)
+				trace_xdp_exception(queue->info->netdev, prog, act);
+			xdp_return_frame_rx_napi(xdpf);
+		}
 		break;
 	case XDP_REDIRECT:
 		get_page(pdata);
 		err = xdp_do_redirect(queue->info->netdev, xdp, prog);
 		*need_xdp_flush = true;
-		if (unlikely(err))
+		if (unlikely(err)) {
 			trace_xdp_exception(queue->info->netdev, prog, act);
+			xdp_return_buff(xdp);
+		}
 		break;
 	case XDP_PASS:
 	case XDP_DROP:

drivers/nvme/target/core.c

···
 
 	lockdep_assert_held(&nvmet_config_sem);
 
+	if (port->disc_addr.trtype == NVMF_TRTYPE_MAX)
+		return -EINVAL;
+
 	ops = nvmet_transports[port->disc_addr.trtype];
 	if (!ops) {
 		up_write(&nvmet_config_sem);

drivers/nvmem/core.c

···
 	cell->nbits = info->nbits;
 	cell->np = info->np;
 
-	if (cell->nbits)
+	if (cell->nbits) {
 		cell->bytes = DIV_ROUND_UP(cell->nbits + cell->bit_offset,
 					   BITS_PER_BYTE);
+		cell->raw_len = ALIGN(cell->bytes, nvmem->word_size);
+	}
 
 	if (!IS_ALIGNED(cell->offset, nvmem->stride)) {
 		dev_err(&nvmem->dev,
 			"cell %s unaligned to nvmem stride %d\n",
 			cell->name ?: "<unknown>", nvmem->stride);
 		return -EINVAL;
+	}
+
+	if (!IS_ALIGNED(cell->raw_len, nvmem->word_size)) {
+		dev_err(&nvmem->dev,
+			"cell %s raw len %zd unaligned to nvmem word size %d\n",
+			cell->name ?: "<unknown>", cell->raw_len,
+			nvmem->word_size);
+
+		if (info->raw_len)
+			return -EINVAL;
+
+		cell->raw_len = ALIGN(cell->raw_len, nvmem->word_size);
 	}
 
 	return 0;
···
 		if (addr && len == (2 * sizeof(u32))) {
 			info.bit_offset = be32_to_cpup(addr++);
 			info.nbits = be32_to_cpup(addr);
-			if (info.bit_offset >= BITS_PER_BYTE || info.nbits < 1) {
+			if (info.bit_offset >= BITS_PER_BYTE * info.bytes ||
+			    info.nbits < 1 ||
+			    info.bit_offset + info.nbits > BITS_PER_BYTE * info.bytes) {
 				dev_err(dev, "nvmem: invalid bits on %pOF\n", child);
 				of_node_put(child);
 				return -EINVAL;
···
 static void nvmem_shift_read_buffer_in_place(struct nvmem_cell_entry *cell, void *buf)
 {
 	u8 *p, *b;
-	int i, extra, bit_offset = cell->bit_offset;
+	int i, extra, bytes_offset;
+	int bit_offset = cell->bit_offset;
 
 	p = b = buf;
-	if (bit_offset) {
+
+	bytes_offset = bit_offset / BITS_PER_BYTE;
+	b += bytes_offset;
+	bit_offset %= BITS_PER_BYTE;
+
+	if (bit_offset % BITS_PER_BYTE) {
 		/* First shift */
-		*b++ >>= bit_offset;
+		*p = *b++ >> bit_offset;
 
 		/* setup rest of the bytes if any */
 		for (i = 1; i < cell->bytes; i++) {
 			/* Get bits from next byte and shift them towards msb */
-			*p |= *b << (BITS_PER_BYTE - bit_offset);
+			*p++ |= *b << (BITS_PER_BYTE - bit_offset);
 
-			p = b;
-			*b++ >>= bit_offset;
+			*p = *b++ >> bit_offset;
 		}
+	} else if (p != b) {
+		memmove(p, b, cell->bytes - bytes_offset);
+		p += cell->bytes - 1;
 	} else {
 		/* point to the msb */
 		p += cell->bytes - 1;

drivers/nvmem/qfprom.c

···
 			unsigned int reg, void *_val, size_t bytes)
 {
 	struct qfprom_priv *priv = context;
-	u8 *val = _val;
-	int i = 0, words = bytes;
+	u32 *val = _val;
 	void __iomem *base = priv->qfpcorrected;
+	int words = DIV_ROUND_UP(bytes, sizeof(u32));
+	int i;
 
 	if (read_raw_data && priv->qfpraw)
 		base = priv->qfpraw;
 
-	while (words--)
-		*val++ = readb(base + reg + i++);
+	for (i = 0; i < words; i++)
+		*val++ = readl(base + reg + i * sizeof(u32));
 
 	return 0;
+}
+
+/* Align reads to word boundary */
+static void qfprom_fixup_dt_cell_info(struct nvmem_device *nvmem,
+				      struct nvmem_cell_info *cell)
+{
+	unsigned int byte_offset = cell->offset % sizeof(u32);
+
+	cell->bit_offset += byte_offset * BITS_PER_BYTE;
+	cell->offset -= byte_offset;
+	if (byte_offset && !cell->nbits)
+		cell->nbits = cell->bytes * BITS_PER_BYTE;
 }
 
 static void qfprom_runtime_disable(void *data)
···
 	struct nvmem_config econfig = {
 		.name = "qfprom",
 		.add_legacy_fixed_of_cells = true,
-		.stride = 1,
-		.word_size = 1,
+		.stride = 4,
+		.word_size = 4,
 		.id = NVMEM_DEVID_AUTO,
 		.reg_read = qfprom_reg_read,
+		.fixup_dt_cell_info = qfprom_fixup_dt_cell_info,
 	};
 	struct device *dev = &pdev->dev;
 	struct resource *res;

drivers/nvmem/rockchip-otp.c

···
 #define RK3588_OTPC_AUTO_EN		0x08
 #define RK3588_OTPC_INT_ST		0x84
 #define RK3588_OTPC_DOUT0		0x20
-#define RK3588_NO_SECURE_OFFSET		0x300
 #define RK3588_NBYTES			4
 #define RK3588_BURST_NUM		1
 #define RK3588_BURST_SHIFT		8
···
 
 struct rockchip_data {
 	int size;
+	int read_offset;
 	const char * const *clks;
 	int num_clks;
 	nvmem_reg_read_t reg_read;
···
 	addr_start = round_down(offset, RK3588_NBYTES) / RK3588_NBYTES;
 	addr_end = round_up(offset + bytes, RK3588_NBYTES) / RK3588_NBYTES;
 	addr_len = addr_end - addr_start;
-	addr_start += RK3588_NO_SECURE_OFFSET;
+	addr_start += otp->data->read_offset / RK3588_NBYTES;
 
 	buf = kzalloc(array_size(addr_len, RK3588_NBYTES), GFP_KERNEL);
 	if (!buf)
···
 	.reg_read = px30_otp_read,
 };
 
+static const struct rockchip_data rk3576_data = {
+	.size = 0x100,
+	.read_offset = 0x700,
+	.clks = px30_otp_clocks,
+	.num_clks = ARRAY_SIZE(px30_otp_clocks),
+	.reg_read = rk3588_otp_read,
+};
+
 static const char * const rk3588_otp_clocks[] = {
 	"otp", "apb_pclk", "phy", "arb",
 };
 
 static const struct rockchip_data rk3588_data = {
 	.size = 0x400,
+	.read_offset = 0xc00,
 	.clks = rk3588_otp_clocks,
 	.num_clks = ARRAY_SIZE(rk3588_otp_clocks),
 	.reg_read = rk3588_otp_read,
···
 	{
 		.compatible = "rockchip,rk3308-otp",
 		.data = &px30_data,
+	},
+	{
+		.compatible = "rockchip,rk3576-otp",
+		.data = &rk3576_data,
 	},
 	{
 		.compatible = "rockchip,rk3588-otp",

drivers/pci/setup-bus.c

···
 			panic("%s: kzalloc() failed!\n", __func__);
 		tmp->res = r;
 		tmp->dev = dev;
+		tmp->start = r->start;
+		tmp->end = r->end;
+		tmp->flags = r->flags;
 
 		/* Fallback is smallest one or list is empty */
 		n = head;
···
 		pci_dbg(dev, "%s %pR: releasing\n", res_name, res);
 
 		release_resource(res);
+		restore_dev_resource(dev_res);
 	}
 	/* Restore start/end/flags from saved list */
 	list_for_each_entry(save_res, &save_head, list)

drivers/pps/generators/pps_gen_tio.c

···
 	hrtimer_setup(&tio->timer, hrtimer_callback, CLOCK_REALTIME,
 		      HRTIMER_MODE_ABS);
 	spin_lock_init(&tio->lock);
-	platform_set_drvdata(pdev, &tio);
+	platform_set_drvdata(pdev, tio);
 
 	return 0;
 }

drivers/scsi/mpi3mr/mpi3mr_fw.c

···
 	char *desc = NULL;
 	u16 event;
 
+	if (!(mrioc->logging_level & MPI3_DEBUG_EVENT))
+		return;
+
 	event = event_reply->event;
 
 	switch (event) {
···
 		return 0;
 	}
 
+	atomic_set(&mrioc->admin_pend_isr, 0);
 	reply_desc = (struct mpi3_default_reply_descriptor *)mrioc->admin_reply_base +
 	    admin_reply_ci;
 
···
 		WRITE_ONCE(op_req_q->ci, le16_to_cpu(reply_desc->request_queue_ci));
 		mpi3mr_process_op_reply_desc(mrioc, reply_desc, &reply_dma,
 		    reply_qidx);
-		atomic_dec(&op_reply_q->pend_ios);
+
 		if (reply_dma)
 			mpi3mr_repost_reply_buf(mrioc, reply_dma);
 		num_op_reply++;
···
 	mrioc->admin_reply_ci = 0;
 	mrioc->admin_reply_ephase = 1;
 	atomic_set(&mrioc->admin_reply_q_in_use, 0);
+	atomic_set(&mrioc->admin_pend_isr, 0);
 
 	if (!mrioc->admin_req_base) {
 		mrioc->admin_req_base = dma_alloc_coherent(&mrioc->pdev->dev,
···
 	if (mrioc->admin_reply_base)
 		memset(mrioc->admin_reply_base, 0, mrioc->admin_reply_q_sz);
 	atomic_set(&mrioc->admin_reply_q_in_use, 0);
+	atomic_set(&mrioc->admin_pend_isr, 0);
 
 	if (mrioc->init_cmds.reply) {
 		memset(mrioc->init_cmds.reply, 0, sizeof(*mrioc->init_cmds.reply));

drivers/scsi/scsi.c

···
  */
 int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
 {
-	struct scsi_mode_data data;
-	struct scsi_sense_hdr sshdr;
-	struct scsi_vpd *vpd;
-	bool is_ata = false;
 	char buf[64];
+	bool is_ata;
 	int ret;
 
 	if (!sdev->cdl_supported)
 		return -EOPNOTSUPP;
 
 	rcu_read_lock();
-	vpd = rcu_dereference(sdev->vpd_pg89);
-	if (vpd)
-		is_ata = true;
+	is_ata = rcu_dereference(sdev->vpd_pg89);
 	rcu_read_unlock();
 
 	/*
 	 * For ATA devices, CDL needs to be enabled with a SET FEATURES command.
 	 */
 	if (is_ata) {
+		struct scsi_mode_data data;
+		struct scsi_sense_hdr sshdr;
 		char *buf_data;
 		int len;
 
···
 		if (ret)
 			return -EINVAL;
 
-		/* Enable CDL using the ATA feature page */
+		/* Enable or disable CDL using the ATA feature page */
 		len = min_t(size_t, sizeof(buf),
 			    data.length - data.header_length -
 			    data.block_descriptor_length);
 		buf_data = buf + data.header_length +
 			data.block_descriptor_length;
-		if (enable)
-			buf_data[4] = 0x02;
-		else
-			buf_data[4] = 0;
+
+		/*
+		 * If we want to enable CDL and CDL is already enabled on the
+		 * device, do nothing. This avoids needlessly resetting the CDL
+		 * statistics on the device as that is implied by the CDL enable
+		 * action. Similar to this, there is no need to do anything if
+		 * we want to disable CDL and CDL is already disabled.
+		 */
+		if (enable) {
+			if ((buf_data[4] & 0x03) == 0x02)
+				goto out;
+			buf_data[4] &= ~0x03;
+			buf_data[4] |= 0x02;
+		} else {
+			if ((buf_data[4] & 0x03) == 0x00)
+				goto out;
+			buf_data[4] &= ~0x03;
+		}
 
 		ret = scsi_mode_select(sdev, 1, 0, buf_data, len, 5 * HZ, 3,
 				       &data, &sshdr);
···
 		}
 	}
 
+out:
 	sdev->cdl_enable = enable;
 
 	return 0;

drivers/scsi/scsi_lib.c

···
  */
 static void scsi_cleanup_rq(struct request *rq)
 {
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+	cmd->flags = 0;
+
 	if (rq->rq_flags & RQF_DONTPREP) {
-		scsi_mq_uninit_cmd(blk_mq_rq_to_pdu(rq));
+		scsi_mq_uninit_cmd(cmd);
 		rq->rq_flags &= ~RQF_DONTPREP;
 	}
 }

drivers/target/iscsi/iscsi_target.c

···
 	spin_unlock(&iscsit_global->ts_bitmap_lock);
 
 	iscsit_stop_timers_for_cmds(conn);
-	iscsit_stop_nopin_response_timer(conn);
 	iscsit_stop_nopin_timer(conn);
+	iscsit_stop_nopin_response_timer(conn);
 
 	if (conn->conn_transport->iscsit_wait_conn)
 		conn->conn_transport->iscsit_wait_conn(conn);

drivers/tty/serial/msm_serial.c

···
 	if (!device->port.membase)
 		return -ENODEV;
 
+	/* Disable DM / single-character modes */
+	msm_write(&device->port, 0, UARTDM_DMEN);
+	msm_write(&device->port, MSM_UART_CR_CMD_RESET_RX, MSM_UART_CR);
+	msm_write(&device->port, MSM_UART_CR_CMD_RESET_TX, MSM_UART_CR);
+	msm_write(&device->port, MSM_UART_CR_TX_ENABLE, MSM_UART_CR);
+
 	device->con->write = msm_serial_early_write_dm;
 	return 0;
 }

drivers/tty/serial/sifive.c

···
 static int sifive_serial_startup(struct uart_port *port)
 {
 	struct sifive_serial_port *ssp = port_to_sifive_serial_port(port);
+	unsigned long flags;
 
+	uart_port_lock_irqsave(&ssp->port, &flags);
 	__ssp_enable_rxwm(ssp);
+	uart_port_unlock_irqrestore(&ssp->port, flags);
 
 	return 0;
 }
···
 static void sifive_serial_shutdown(struct uart_port *port)
 {
 	struct sifive_serial_port *ssp = port_to_sifive_serial_port(port);
+	unsigned long flags;
 
+	uart_port_lock_irqsave(&ssp->port, &flags);
 	__ssp_disable_rxwm(ssp);
 	__ssp_disable_txwm(ssp);
+	uart_port_unlock_irqrestore(&ssp->port, flags);
 }
 
 /**

drivers/tty/vt/selection.c

···
 		return -EFAULT;
 
 	/*
-	 * TIOCL_SELCLEAR, TIOCL_SELPOINTER and TIOCL_SELMOUSEREPORT are OK to
-	 * use without CAP_SYS_ADMIN as they do not modify the selection.
+	 * TIOCL_SELCLEAR and TIOCL_SELPOINTER are OK to use without
+	 * CAP_SYS_ADMIN as they do not modify the selection.
 	 */
 	switch (v.sel_mode) {
 	case TIOCL_SELCLEAR:
 	case TIOCL_SELPOINTER:
-	case TIOCL_SELMOUSEREPORT:
 		break;
 	default:
 		if (!capable(CAP_SYS_ADMIN))

drivers/ufs/core/ufs-mcq.c

···
 	unsigned long flags;
 	int err;
 
-	if (!ufshcd_cmd_inflight(lrbp->cmd)) {
-		dev_err(hba->dev,
-			"%s: skip abort. cmd at tag %d already completed.\n",
-			__func__, tag);
-		return FAILED;
-	}
-
 	/* Skip task abort in case previous aborts failed and report failure */
 	if (lrbp->req_abort_skip) {
 		dev_err(hba->dev, "%s: skip abort. tag %d failed earlier\n",
···
 	}
 
 	hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+	if (!hwq) {
+		dev_err(hba->dev, "%s: skip abort. cmd at tag %d already completed.\n",
+			__func__, tag);
+		return FAILED;
+	}
 
 	if (ufshcd_mcq_sqe_search(hba, hwq, tag)) {
 		/*

drivers/ufs/core/ufshcd.c

···
 	  .model = UFS_ANY_MODEL,
 	  .quirk = UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM |
 		   UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE |
+		   UFS_DEVICE_QUIRK_PA_HIBER8TIME |
 		   UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS },
 	{ .wmanufacturerid = UFS_VENDOR_SKHYNIX,
 	  .model = UFS_ANY_MODEL,
···
 			continue;
 
 		hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+		if (!hwq)
+			continue;
 
 		if (force_compl) {
 			ufshcd_mcq_compl_all_cqes_lock(hba, hwq);
···
 	return ret;
 }
 
+/**
+ * ufshcd_quirk_override_pa_h8time - Ensures proper adjustment of PA_HIBERN8TIME.
+ * @hba: per-adapter instance
+ *
+ * Some UFS devices require specific adjustments to the PA_HIBERN8TIME parameter
+ * to ensure proper hibernation timing. This function retrieves the current
+ * PA_HIBERN8TIME value and increments it by 100us.
+ */
+static void ufshcd_quirk_override_pa_h8time(struct ufs_hba *hba)
+{
+	u32 pa_h8time;
+	int ret;
+
+	ret = ufshcd_dme_get(hba, UIC_ARG_MIB(PA_HIBERN8TIME), &pa_h8time);
+	if (ret) {
+		dev_err(hba->dev, "Failed to get PA_HIBERN8TIME: %d\n", ret);
+		return;
+	}
+
+	/* Increment by 1 to increase hibernation time by 100 µs */
+	ret = ufshcd_dme_set(hba, UIC_ARG_MIB(PA_HIBERN8TIME), pa_h8time + 1);
+	if (ret)
+		dev_err(hba->dev, "Failed updating PA_HIBERN8TIME: %d\n", ret);
+}
+
 static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
 {
 	ufshcd_vops_apply_dev_quirks(hba);
···
 
 	if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE)
 		ufshcd_quirk_tune_host_pa_tactivate(hba);
+
+	if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_HIBER8TIME)
+		ufshcd_quirk_override_pa_h8time(hba);
 }
 
 static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba)

drivers/ufs/host/ufs-qcom.c

···
 	((((c) >> 16) & MCQ_QCFGPTR_MASK) * MCQ_QCFGPTR_UNIT)
 #define MCQ_QCFG_SIZE	0x40
 
+/* De-emphasis for gear-5 */
+#define DEEMPHASIS_3_5_dB	0x04
+#define NO_DEEMPHASIS		0x0
+
 enum {
 	TSTBUS_UAWM,
 	TSTBUS_UARM,
···
 	return ufs_qcom_icc_set_bw(host, bw_table.mem_bw, bw_table.cfg_bw);
 }
 
+static void ufs_qcom_set_tx_hs_equalizer(struct ufs_hba *hba, u32 gear, u32 tx_lanes)
+{
+	u32 equalizer_val;
+	int ret, i;
+
+	/* Determine the equalizer value based on the gear */
+	equalizer_val = (gear == 5) ? DEEMPHASIS_3_5_dB : NO_DEEMPHASIS;
+
+	for (i = 0; i < tx_lanes; i++) {
+		ret = ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(TX_HS_EQUALIZER, i),
+				     equalizer_val);
+		if (ret)
+			dev_err(hba->dev, "%s: failed equalizer lane %d\n",
+				__func__, i);
+	}
+}
+
 static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba,
 				enum ufs_notify_change_status status,
 				const struct ufs_pa_layer_attr *dev_max_params,
···
 						dev_req_params->gear_tx,
 						PA_INITIAL_ADAPT);
 		}
+
+		if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING)
+			ufs_qcom_set_tx_hs_equalizer(hba,
+					dev_req_params->gear_tx, dev_req_params->lane_tx);
+
 		break;
 	case POST_CHANGE:
 		if (ufs_qcom_cfg_timers(hba, false)) {
···
 			    (pa_vs_config_reg1 | (1 << 12)));
 }
 
+static void ufs_qcom_override_pa_tx_hsg1_sync_len(struct ufs_hba *hba)
+{
+	int err;
+
+	err = ufshcd_dme_peer_set(hba, UIC_ARG_MIB(PA_TX_HSG1_SYNC_LENGTH),
+				  PA_TX_HSG1_SYNC_LENGTH_VAL);
+	if (err)
+		dev_err(hba->dev, "Failed (%d) set PA_TX_HSG1_SYNC_LENGTH\n", err);
+}
+
 static int ufs_qcom_apply_dev_quirks(struct ufs_hba *hba)
 {
 	int err = 0;
 
 	if (hba->dev_quirks & UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME)
 		err = ufs_qcom_quirk_host_pa_saveconfigtime(hba);
+
+	if (hba->dev_quirks & UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH)
+		ufs_qcom_override_pa_tx_hsg1_sync_len(hba);
 
 	return err;
 }
···
 	{ .wmanufacturerid = UFS_VENDOR_WDC,
 	  .model = UFS_ANY_MODEL,
 	  .quirk = UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE },
+	{ .wmanufacturerid = UFS_VENDOR_SAMSUNG,
+	  .model = UFS_ANY_MODEL,
+	  .quirk = UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH |
+		   UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING },
 	{}
 };
 

drivers/ufs/host/ufs-qcom.h

···
 				 TMRLUT_HW_CGC_EN | OCSC_HW_CGC_EN)
 
 /* QUniPro Vendor specific attributes */
+#define PA_TX_HSG1_SYNC_LENGTH	0x1552
 #define PA_VS_CONFIG_REG1	0x9000
 #define DME_VS_CORE_CLK_CTRL	0xD002
+#define TX_HS_EQUALIZER		0x0037
+
 /* bit and mask definitions for DME_VS_CORE_CLK_CTRL attribute */
 #define CLK_1US_CYCLES_MASK_V4				GENMASK(27, 16)
 #define CLK_1US_CYCLES_MASK				GENMASK(7, 0)
···
 #define UNIPRO_CORE_CLK_FREQ_300_MHZ           300
 #define UNIPRO_CORE_CLK_FREQ_201_5_MHZ         202
 #define UNIPRO_CORE_CLK_FREQ_403_MHZ           403
+
+/* TX_HSG1_SYNC_LENGTH attr value */
+#define PA_TX_HSG1_SYNC_LENGTH_VAL	0x4A
+
+/*
+ * Some ufs device vendors need a different TSync length.
+ * Enable this quirk to give an additional TX_HS_SYNC_LENGTH.
+ */
+#define UFS_DEVICE_QUIRK_PA_TX_HSG1_SYNC_LENGTH		BIT(16)
+
+/*
+ * Some ufs device vendors need a different Deemphasis setting.
+ * Enable this quirk to tune TX Deemphasis parameters.
+ */
+#define UFS_DEVICE_QUIRK_PA_TX_DEEMPHASIS_TUNING	BIT(17)
 
 /* ICE allocator type to share AES engines among TX stream and RX stream */
 #define ICE_ALLOCATOR_TYPE 2

drivers/usb/cdns3/cdns3-gadget.c

···
 	unsigned int bit;
 	unsigned long reg;
 
+	local_bh_disable();
 	spin_lock_irqsave(&priv_dev->lock, flags);
 
 	reg = readl(&priv_dev->regs->usb_ists);
···
 irqend:
 	writel(~0, &priv_dev->regs->ep_ien);
 	spin_unlock_irqrestore(&priv_dev->lock, flags);
+	local_bh_enable();
 
 	return ret;
 }

drivers/usb/chipidea/ci_hdrc_imx.c

···
 	return ret;
 }
 
+static void ci_hdrc_imx_disable_regulator(void *arg)
+{
+	struct ci_hdrc_imx_data *data = arg;
+
+	regulator_disable(data->hsic_pad_regulator);
+}
+
 static int ci_hdrc_imx_probe(struct platform_device *pdev)
 {
 	struct ci_hdrc_imx_data *data;
···
 					"Failed to enable HSIC pad regulator\n");
 				goto err_put;
 			}
+			ret = devm_add_action_or_reset(dev,
+					ci_hdrc_imx_disable_regulator, data);
+			if (ret) {
+				dev_err(dev,
+					"Failed to add regulator devm action\n");
+				goto err_put;
+			}
 		}
 	}
 
···
 
 	ret = imx_get_clks(dev);
 	if (ret)
-		goto disable_hsic_regulator;
+		goto qos_remove_request;
 
 	ret = imx_prepare_enable_clks(dev);
 	if (ret)
-		goto disable_hsic_regulator;
+		goto qos_remove_request;
 
 	ret = clk_prepare_enable(data->clk_wakeup);
 	if (ret)
···
 	    of_usb_get_phy_mode(np) == USBPHY_INTERFACE_MODE_ULPI) {
 		pdata.flags |= CI_HDRC_OVERRIDE_PHY_CONTROL;
 		data->override_phy_control = true;
-		usb_phy_init(pdata.usb_phy);
+		ret = usb_phy_init(pdata.usb_phy);
+		if (ret) {
+			dev_err(dev, "Failed to init phy\n");
+			goto err_clk;
+		}
 	}
 
 	if (pdata.flags & CI_HDRC_SUPPORTS_RUNTIME_PM)
···
 	ret = imx_usbmisc_init(data->usbmisc_data);
 	if (ret) {
 		dev_err(dev, "usbmisc init failed, ret=%d\n", ret);
-		goto err_clk;
+		goto phy_shutdown;
 	}
 
 	data->ci_pdev = ci_hdrc_add_device(dev,
···
 	if (IS_ERR(data->ci_pdev)) {
 		ret = PTR_ERR(data->ci_pdev);
 		dev_err_probe(dev, ret, "ci_hdrc_add_device failed\n");
-		goto err_clk;
+		goto phy_shutdown;
 	}
 
 	if (data->usbmisc_data) {
···
 
 disable_device:
 	ci_hdrc_remove_device(data->ci_pdev);
+phy_shutdown:
+	if (data->override_phy_control)
+		usb_phy_shutdown(data->phy);
 err_clk:
 	clk_disable_unprepare(data->clk_wakeup);
 err_wakeup_clk:
 	imx_disable_unprepare_clks(dev);
-disable_hsic_regulator:
-	if (data->hsic_pad_regulator)
-		/* don't overwrite original ret (cf. EPROBE_DEFER) */
-		regulator_disable(data->hsic_pad_regulator);
+qos_remove_request:
 	if (pdata.flags & CI_HDRC_PMQOS)
 		cpu_latency_qos_remove_request(&data->pm_qos_req);
 	data->ci_pdev = NULL;
 err_put:
-	put_device(data->usbmisc_data->dev);
+	if (data->usbmisc_data)
+		put_device(data->usbmisc_data->dev);
 	return ret;
 }
 
···
 		clk_disable_unprepare(data->clk_wakeup);
 		if (data->plat_data->flags & CI_HDRC_PMQOS)
 			cpu_latency_qos_remove_request(&data->pm_qos_req);
-		if (data->hsic_pad_regulator)
-			regulator_disable(data->hsic_pad_regulator);
 	}
-	put_device(data->usbmisc_data->dev);
+	if (data->usbmisc_data)
+		put_device(data->usbmisc_data->dev);
 }
 
 static void ci_hdrc_imx_shutdown(struct platform_device *pdev)

drivers/usb/class/cdc-wdm.c

···
 		rv = -EBUSY;
 		goto out;
 	}
-
+	smp_rmb(); /* ordered against wdm_wwan_port_stop() */
 	rv = usb_autopm_get_interface(desc->intf);
 	if (rv < 0) {
 		dev_err(&desc->intf->dev, "Error autopm - %d\n", rv);
···
 static int wdm_wwan_port_start(struct wwan_port *port)
 {
 	struct wdm_device *desc = wwan_port_get_drvdata(port);
+	int rv;
 
 	/* The interface is both exposed via the WWAN framework and as a
 	 * legacy usbmisc chardev. If chardev is already open, just fail
···
 	wwan_port_txon(port);
 
 	/* Start getting events */
-	return usb_submit_urb(desc->validity, GFP_KERNEL);
+	rv = usb_submit_urb(desc->validity, GFP_KERNEL);
+	if (rv < 0) {
+		wwan_port_txoff(port);
+		desc->manage_power(desc->intf, 0);
+		/* this must be last lest we race with chardev open */
+		clear_bit(WDM_WWAN_IN_USE, &desc->flags);
+	}
+
+	return rv;
 }
 
 static void wdm_wwan_port_stop(struct wwan_port *port)
···
 	poison_urbs(desc);
 	desc->manage_power(desc->intf, 0);
 	clear_bit(WDM_READ, &desc->flags);
-	clear_bit(WDM_WWAN_IN_USE, &desc->flags);
 	unpoison_urbs(desc);
+	smp_wmb(); /* ordered against wdm_open() */
+	/* this must be last lest we open a poisoned device */
+	clear_bit(WDM_WWAN_IN_USE, &desc->flags);
 }
 
 static void wdm_wwan_port_tx_complete(struct urb *urb)
···
 	struct sk_buff *skb = urb->context;
 	struct wdm_device *desc = skb_shinfo(skb)->destructor_arg;
 
-	usb_autopm_put_interface(desc->intf);
+	usb_autopm_put_interface_async(desc->intf);
 	wwan_port_txon(desc->wwanp);
 	kfree_skb(skb);
 }
···
 	req->bRequestType = (USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE);
 	req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND;
 	req->wValue = 0;
-	req->wIndex = desc->inum;
+	req->wIndex = desc->inum; /* already converted */
 	req->wLength = cpu_to_le16(skb->len);
 
 	skb_shinfo(skb)->destructor_arg = desc;

drivers/usb/core/quirks.c

···
 	{ USB_DEVICE(0x0781, 0x5583), .driver_info = USB_QUIRK_NO_LPM },
 	{ USB_DEVICE(0x0781, 0x5591), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* SanDisk Corp. SanDisk 3.2Gen1 */
+	{ USB_DEVICE(0x0781, 0x55a3), .driver_info = USB_QUIRK_DELAY_INIT },
+
 	/* Realforce 87U Keyboard */
 	{ USB_DEVICE(0x0853, 0x011b), .driver_info = USB_QUIRK_NO_LPM },
 
···
 			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
 	{ USB_DEVICE(0x0904, 0x6103), .driver_info =
 			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
+
+	/* Silicon Motion Flash Drive */
+	{ USB_DEVICE(0x090c, 0x1000), .driver_info = USB_QUIRK_DELAY_INIT },
 
 	/* Sound Devices USBPre2 */
 	{ USB_DEVICE(0x0926, 0x0202), .driver_info =
···
 	/* Hauppauge HVR-950q */
 	{ USB_DEVICE(0x2040, 0x7200), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
+
+	/* VLI disk */
+	{ USB_DEVICE(0x2109, 0x0711), .driver_info = USB_QUIRK_NO_LPM },
 
 	/* Raydium Touchscreen */
 	{ USB_DEVICE(0x2386, 0x3114), .driver_info = USB_QUIRK_NO_LPM },

drivers/usb/dwc3/dwc3-xilinx.c

···
 
 skip_usb3_phy:
 	/* ulpi reset via gpio-modepin or gpio-framework driver */
-	reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(reset_gpio)) {
 		return dev_err_probe(dev, PTR_ERR(reset_gpio),
 				     "Failed to request reset GPIO\n");
 	}
 
 	if (reset_gpio) {
-		/* Toggle ulpi to reset the phy. */
-		gpiod_set_value_cansleep(reset_gpio, 1);
 		usleep_range(5000, 10000);
 		gpiod_set_value_cansleep(reset_gpio, 0);
 		usleep_range(5000, 10000);

drivers/usb/dwc3/gadget.c

···
 	if (!count)
 		return IRQ_NONE;
 
+	if (count > evt->length) {
+		dev_err_ratelimited(dwc->dev, "invalid count(%u) > evt->length(%u)\n",
+			count, evt->length);
+		return IRQ_NONE;
+	}
+
 	evt->count = count;
 	evt->flags |= DWC3_EVENT_PENDING;
 

drivers/usb/host/ohci-pci.c

···
 	return 0;
 }
 
+static int ohci_quirk_loongson(struct usb_hcd *hcd)
+{
+	struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
+
+	/*
+	 * Loongson's LS7A OHCI controller (rev 0x02) has a
+	 * flaw. MMIO register with offset 0x60/64 is treated
+	 * as legacy PS2-compatible keyboard/mouse interface.
+	 * Since OHCI only use 4KB BAR resource, LS7A OHCI's
+	 * 32KB BAR is wrapped around (the 2nd 4KB BAR space
+	 * is the same as the 1st 4KB internally). So add 4KB
+	 * offset (0x1000) to the OHCI registers as a quirk.
+	 */
+	if (pdev->revision == 0x2)
+		hcd->regs += SZ_4K;	/* SZ_4K = 0x1000 */
+
+	return 0;
+}
+
 static int ohci_quirk_qemu(struct usb_hcd *hcd)
 {
 	struct ohci_hcd *ohci = hcd_to_ohci(hcd);
···
 	{
 		PCI_DEVICE(PCI_VENDOR_ID_ATI, 0x4399),
 		.driver_data = (unsigned long)ohci_quirk_amd700,
+	},
+	{
+		PCI_DEVICE(PCI_VENDOR_ID_LOONGSON, 0x7a24),
+		.driver_data = (unsigned long)ohci_quirk_loongson,
 	},
 	{
 		.vendor		= PCI_VENDOR_ID_APPLE,

drivers/usb/host/xhci-hub.c

···
 	int max_ports, port_index;
 	int sret;
 	u32 next_state;
-	u32 temp, portsc;
+	u32 portsc;
 	struct xhci_hub *rhub;
 	struct xhci_port **ports;
+	bool disabled_irq = false;
 
 	rhub = xhci_get_rhub(hcd);
 	ports = rhub->ports;
···
 		return -ESHUTDOWN;
 	}
 
-	/* delay the irqs */
-	temp = readl(&xhci->op_regs->command);
-	temp &= ~CMD_EIE;
-	writel(temp, &xhci->op_regs->command);
-
 	/* bus specific resume for ports we suspended at bus_suspend */
-	if (hcd->speed >= HCD_USB3)
+	if (hcd->speed >= HCD_USB3) {
 		next_state = XDEV_U0;
-	else
+	} else {
 		next_state = XDEV_RESUME;
-
+		if (bus_state->bus_suspended) {
+			/*
+			 * prevent port event interrupts from interfering
+			 * with usb2 port resume process
+			 */
+			xhci_disable_interrupter(xhci->interrupters[0]);
+			disabled_irq = true;
+		}
+	}
 	port_index = max_ports;
 	while (port_index--) {
 		portsc = readl(ports[port_index]->addr);
···
 	(void) readl(&xhci->op_regs->command);
 
 	bus_state->next_statechange = jiffies + msecs_to_jiffies(5);
-	/* re-enable irqs */
-	temp = readl(&xhci->op_regs->command);
-	temp |= CMD_EIE;
-	writel(temp, &xhci->op_regs->command);
-	temp = readl(&xhci->op_regs->command);
+	/* re-enable interrupter */
+	if (disabled_irq)
+		xhci_enable_interrupter(xhci->interrupters[0]);
 
 	spin_unlock_irqrestore(&xhci->lock, flags);
 	return 0;

drivers/usb/host/xhci-ring.c

···
 	 * pointer command pending because the device can choose to start any
 	 * stream once the endpoint is on the HW schedule.
 	 */
-	if (ep_state & (EP_STOP_CMD_PENDING | SET_DEQ_PENDING | EP_HALTED |
-			EP_CLEARING_TT | EP_STALLED))
+	if ((ep_state & EP_STOP_CMD_PENDING) || (ep_state & SET_DEQ_PENDING) ||
+	    (ep_state & EP_HALTED) || (ep_state & EP_CLEARING_TT))
 		return;
 
 	trace_xhci_ring_ep_doorbell(slot_id, DB_VALUE(ep_index, stream_id));
···
 
 		xhci_handle_halted_endpoint(xhci, ep, td, EP_SOFT_RESET);
 		return;
-	case COMP_STALL_ERROR:
-		ep->ep_state |= EP_STALLED;
-		break;
 	default:
 		/* do nothing */
 		break;
···
 			if (xhci_spurious_success_tx_event(xhci, ep_ring)) {
 				xhci_dbg(xhci, "Spurious event dma %pad, comp_code %u after %u\n",
 					 &ep_trb_dma, trb_comp_code, ep_ring->old_trb_comp_code);
-				ep_ring->old_trb_comp_code = trb_comp_code;
+				ep_ring->old_trb_comp_code = 0;
 				return 0;
 			}
 
···
 		 * enqueue a No Op TRB, this can prevent the Setup and Data Stage
 		 * TRB to be breaked by the Link TRB.
 		 */
-		if (trb_is_link(ep_ring->enqueue + 1)) {
+		if (last_trb_on_seg(ep_ring->enq_seg, ep_ring->enqueue + 1)) {
 			field = TRB_TYPE(TRB_TR_NOOP) | ep_ring->cycle_state;
 			queue_trb(xhci, ep_ring, false, 0, 0,
 					TRB_INTR_TARGET(0), field);

drivers/usb/host/xhci.c

···
 		xhci_info(xhci, "Fault detected\n");
 }
 
-static int xhci_enable_interrupter(struct xhci_interrupter *ir)
+int xhci_enable_interrupter(struct xhci_interrupter *ir)
 {
 	u32 iman;
 
···
 	return 0;
 }
 
-static int xhci_disable_interrupter(struct xhci_interrupter *ir)
+int xhci_disable_interrupter(struct xhci_interrupter *ir)
 {
 	u32 iman;
 
···
 		goto free_priv;
 	}
 
-	/* Class driver might not be aware ep halted due to async URB giveback */
-	if (*ep_state & EP_STALLED)
-		dev_dbg(&urb->dev->dev, "URB %p queued before clearing halt\n",
-			urb);
-
 	switch (usb_endpoint_type(&urb->ep->desc)) {
 
 	case USB_ENDPOINT_XFER_CONTROL:
···
 		goto done;
 	}
 
-	/* In these cases no commands are pending but the endpoint is stopped */
-	if (ep->ep_state & (EP_CLEARING_TT | EP_STALLED)) {
+	/* In this case no commands are pending but the endpoint is stopped */
+	if (ep->ep_state & EP_CLEARING_TT) {
 		/* and cancelled TDs can be given back right away */
 		xhci_dbg(xhci, "Invalidating TDs instantly on slot %d ep %d in state 0x%x\n",
 				urb->dev->slot_id, ep_index, ep->ep_state);
···
 
 	ep = &vdev->eps[ep_index];
 
-	spin_lock_irqsave(&xhci->lock, flags);
-
-	ep->ep_state &= ~EP_STALLED;
-
 	/* Bail out if toggle is already being cleared by a endpoint reset */
+	spin_lock_irqsave(&xhci->lock, flags);
 	if (ep->ep_state & EP_HARD_CLEAR_TOGGLE) {
 		ep->ep_state &= ~EP_HARD_CLEAR_TOGGLE;
 		spin_unlock_irqrestore(&xhci->lock, flags);

drivers/usb/host/xhci.h

···
 	unsigned int			err_count;
 	unsigned int			ep_state;
 #define SET_DEQ_PENDING		(1 << 0)
-#define EP_HALTED		(1 << 1)	/* Halted host ep handling */
+#define EP_HALTED		(1 << 1)	/* For stall handling */
 #define EP_STOP_CMD_PENDING	(1 << 2)	/* For URB cancellation */
 /* Transitioning the endpoint to using streams, don't enqueue URBs */
 #define EP_GETTING_STREAMS	(1 << 3)
···
 #define EP_SOFT_CLEAR_TOGGLE	(1 << 7)
 /* usb_hub_clear_tt_buffer is in progress */
 #define EP_CLEARING_TT		(1 << 8)
-#define EP_STALLED		(1 << 9)	/* For stall handling */
 	/* ----  Related to URB cancellation ---- */
 	struct list_head	cancelled_td_list;
 	struct xhci_hcd		*xhci;
···
 		struct usb_tt *tt, gfp_t mem_flags);
 int xhci_set_interrupter_moderation(struct xhci_interrupter *ir,
 				    u32 imod_interval);
+int xhci_enable_interrupter(struct xhci_interrupter *ir);
+int xhci_disable_interrupter(struct xhci_interrupter *ir);
 
 /* xHCI ring, segment, TRB, and TD functions */
 dma_addr_t xhci_trb_virt_to_dma(struct xhci_segment *seg, union xhci_trb *trb);

drivers/usb/serial/ftdi_sio.c

···
 	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 1) },
 	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 2) },
 	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 3) },
+	/* Abacus Electrics */
+	{ USB_DEVICE(FTDI_VID, ABACUS_OPTICAL_PROBE_PID) },
 	{ }					/* Terminating entry */
 };
 

drivers/usb/serial/ftdi_sio_ids.h

···
 #define LINX_FUTURE_2_PID   0xF44C	/* Linx future device */
 
 /*
+ * Abacus Electrics
+ */
+#define ABACUS_OPTICAL_PROBE_PID	0xf458 /* ABACUS ELECTRICS Optical Probe */
+
+/*
  * Oceanic product ids
  */
 #define FTDI_OCEANIC_PID	0xF460  /* Oceanic dive instrument */

drivers/usb/serial/option.c

···
 /* Sierra Wireless products */
 #define SIERRA_VENDOR_ID			0x1199
 #define SIERRA_PRODUCT_EM9191			0x90d3
+#define SIERRA_PRODUCT_EM9291			0x90e3
 
 /* UNISOC (Spreadtrum) products */
 #define UNISOC_VENDOR_ID			0x1782
···
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x30) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff),			/* TCL IK512 MBIM */

drivers/usb/serial/usb-serial-simple.c

···
 	{ USB_DEVICE(0x09d7, 0x0100) }	/* NovAtel FlexPack GPS */
 DEVICE_N(novatel_gps, NOVATEL_IDS, 3);
 
+/* OWON electronic test and measurement equipment driver */
+#define OWON_IDS()			\
+	{ USB_DEVICE(0x5345, 0x1234) } /* HDS200 oscilloscopes and others */
+DEVICE(owon, OWON_IDS);
+
 /* Siemens USB/MPI adapter */
 #define SIEMENS_IDS()			\
 	{ USB_DEVICE(0x908, 0x0004) }
···
 	&motorola_tetra_device,
 	&nokia_device,
 	&novatel_gps_device,
+	&owon_device,
 	&siemens_mpi_device,
 	&suunto_device,
 	&vivopay_device,
···
 	MOTOROLA_TETRA_IDS(),
 	NOKIA_IDS(),
 	NOVATEL_IDS(),
+	OWON_IDS(),
 	SIEMENS_IDS(),
 	SUUNTO_IDS(),
 	VIVOPAY_IDS(),

drivers/usb/storage/unusual_uas.h

···
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_REPORT_LUNS),
 
+/* Reported-by: Oliver Neukum <[e-mail]> */
+UNUSUAL_DEV(0x125f, 0xa94a, 0x0160, 0x0160,
+		"ADATA",
+		"Portable HDD CH94",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X),
+
 /* Reported-by: Benjamin Tissoires <[e-mail]> */
 UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999,
 		"Initio Corporation",

drivers/usb/typec/class.c

···
 		partner->usb_mode = USB_MODE_USB3;
 	}
 
+	mutex_lock(&port->partner_link_lock);
 	ret = device_register(&partner->dev);
 	if (ret) {
 		dev_err(&port->dev, "failed to register partner (%d)\n", ret);
+		mutex_unlock(&port->partner_link_lock);
 		put_device(&partner->dev);
 		return ERR_PTR(ret);
 	}
···
 		typec_partner_link_device(partner, port->usb2_dev);
 	if (port->usb3_dev)
 		typec_partner_link_device(partner, port->usb3_dev);
+	mutex_unlock(&port->partner_link_lock);
 
 	return partner;
 }
···
 
 	port = to_typec_port(partner->dev.parent);
 
-	if (port->usb2_dev)
+	mutex_lock(&port->partner_link_lock);
+	if (port->usb2_dev) {
 		typec_partner_unlink_device(partner, port->usb2_dev);
-	if (port->usb3_dev)
+		port->usb2_dev = NULL;
+	}
+	if (port->usb3_dev) {
 		typec_partner_unlink_device(partner, port->usb3_dev);
+		port->usb3_dev = NULL;
+	}
 
 	device_unregister(&partner->dev);
+	mutex_unlock(&port->partner_link_lock);
 }
 EXPORT_SYMBOL_GPL(typec_unregister_partner);
 
···
 static void typec_partner_attach(struct typec_connector *con, struct device *dev)
 {
 	struct typec_port *port = container_of(con, struct typec_port, con);
-	struct typec_partner *partner = typec_get_partner(port);
+	struct typec_partner *partner;
 	struct usb_device *udev = to_usb_device(dev);
 	enum usb_mode usb_mode;
 
+	mutex_lock(&port->partner_link_lock);
 	if (udev->speed < USB_SPEED_SUPER) {
 		usb_mode = USB_MODE_USB2;
 		port->usb2_dev = dev;
···
 		port->usb3_dev = dev;
 	}
 
+	partner = typec_get_partner(port);
 	if (partner) {
 		typec_partner_set_usb_mode(partner, usb_mode);
 		typec_partner_link_device(partner, dev);
 		put_device(&partner->dev);
 	}
+	mutex_unlock(&port->partner_link_lock);
 }
 
 static void typec_partner_deattach(struct typec_connector *con, struct device *dev)
 {
 	struct typec_port *port = container_of(con, struct typec_port, con);
-	struct typec_partner *partner = typec_get_partner(port);
+	struct typec_partner *partner;
 
+	mutex_lock(&port->partner_link_lock);
+	partner = typec_get_partner(port);
 	if (partner) {
 		typec_partner_unlink_device(partner, dev);
 		put_device(&partner->dev);
···
 		port->usb2_dev = NULL;
 	else if (port->usb3_dev == dev)
 		port->usb3_dev = NULL;
+	mutex_unlock(&port->partner_link_lock);
 }
 
 /**
···
 
 	ida_init(&port->mode_ids);
 	mutex_init(&port->port_type_lock);
+	mutex_init(&port->partner_link_lock);
 
 	port->id = id;
 	port->ops = cap->ops;

drivers/usb/typec/class.h

···
 	enum typec_port_type		port_type;
 	enum usb_mode			usb_mode;
 	struct mutex			port_type_lock;
+	struct mutex			partner_link_lock;
 
 	enum typec_orientation		orientation;
 	struct typec_switch		*sw;

drivers/vhost/scsi.c

···
 	int ret;
 
 	llnode = llist_del_all(&svq->completion_list);
+
+	mutex_lock(&svq->vq.mutex);
+
 	llist_for_each_entry_safe(cmd, t, llnode, tvc_completion_list) {
 		se_cmd = &cmd->tvc_se_cmd;
 
···
 
 		vhost_scsi_release_cmd_res(se_cmd);
 	}
+
+	mutex_unlock(&svq->vq.mutex);
 
 	if (signal)
 		vhost_signal(&svq->vs->dev, &svq->vq);
···
 
 static void
 vhost_scsi_send_status(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
-		       int head, unsigned int out, u8 status)
+		       struct vhost_scsi_ctx *vc, u8 status)
 {
-	struct virtio_scsi_cmd_resp __user *resp;
 	struct virtio_scsi_cmd_resp rsp;
+	struct iov_iter iov_iter;
 	int ret;
 
 	memset(&rsp, 0, sizeof(rsp));
 	rsp.status = status;
-	resp = vq->iov[out].iov_base;
-	ret = __copy_to_user(resp, &rsp, sizeof(rsp));
-	if (!ret)
-		vhost_add_used_and_signal(&vs->dev, vq, head, 0);
+
+	iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in,
+		      sizeof(rsp));
+
+	ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
+
+	if (likely(ret == sizeof(rsp)))
+		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
 	else
 		pr_err("Faulted on virtio_scsi_cmd_resp\n");
 }
 
+#define TYPE_IO_CMD    0
+#define TYPE_CTRL_TMF  1
+#define TYPE_CTRL_AN   2
+
 static void
 vhost_scsi_send_bad_target(struct vhost_scsi *vs,
 			   struct vhost_virtqueue *vq,
-			   int head, unsigned out)
+			   struct vhost_scsi_ctx *vc, int type)
 {
-	struct virtio_scsi_cmd_resp __user *resp;
-	struct virtio_scsi_cmd_resp rsp;
+	union {
+		struct virtio_scsi_cmd_resp cmd;
+		struct virtio_scsi_ctrl_tmf_resp tmf;
+		struct virtio_scsi_ctrl_an_resp an;
+	} rsp;
+	struct iov_iter iov_iter;
+	size_t rsp_size;
 	int ret;
 
 	memset(&rsp, 0, sizeof(rsp));
-	rsp.response = VIRTIO_SCSI_S_BAD_TARGET;
-	resp = vq->iov[out].iov_base;
-	ret = __copy_to_user(resp, &rsp, sizeof(rsp));
-	if (!ret)
-		vhost_add_used_and_signal(&vs->dev, vq, head, 0);
+
+	if (type == TYPE_IO_CMD) {
+		rsp_size = sizeof(struct virtio_scsi_cmd_resp);
+		rsp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET;
+	} else if (type == TYPE_CTRL_TMF) {
+		rsp_size = sizeof(struct virtio_scsi_ctrl_tmf_resp);
+		rsp.tmf.response = VIRTIO_SCSI_S_BAD_TARGET;
+	} else {
+		rsp_size = sizeof(struct virtio_scsi_ctrl_an_resp);
+		rsp.an.response = VIRTIO_SCSI_S_BAD_TARGET;
+	}
+
+	iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[vc->out], vc->in,
+		      rsp_size);
+
+	ret = copy_to_iter(&rsp, rsp_size, &iov_iter);
+
+	if (likely(ret == rsp_size))
+		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
 	else
-		pr_err("Faulted on virtio_scsi_cmd_resp\n");
+		pr_err("Faulted on virtio scsi type=%d\n", type);
 }
 
 static int
···
 		if (ret == -ENXIO)
 			break;
 		else if (ret == -EIO)
-			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+			vhost_scsi_send_bad_target(vs, vq, &vc, TYPE_IO_CMD);
 		else if (ret == -ENOMEM)
-			vhost_scsi_send_status(vs, vq, vc.head, vc.out,
+			vhost_scsi_send_status(vs, vq, &vc,
 					       SAM_STAT_TASK_SET_FULL);
 	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
 out:
···
 	else
 		resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED;
 
+	mutex_lock(&tmf->svq->vq.mutex);
 	vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs,
 				 tmf->vq_desc, &tmf->resp_iov, resp_code);
+	mutex_unlock(&tmf->svq->vq.mutex);
+
 	vhost_scsi_release_tmf_res(tmf);
 }
 
···
 		if (ret == -ENXIO)
 			break;
 		else if (ret == -EIO)
-			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
+			vhost_scsi_send_bad_target(vs, vq, &vc,
+						   v_req.type == VIRTIO_SCSI_T_TMF ?
+						   TYPE_CTRL_TMF :
+						   TYPE_CTRL_AN);
 	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
 out:
 	mutex_unlock(&vq->mutex);

drivers/virtio/virtio.c

···
 	if (!drv)
 		return;
 
+	/* If the driver has its own shutdown method, use that. */
+	if (drv->shutdown) {
+		drv->shutdown(dev);
+		return;
+	}
+
 	/*
 	 * Some devices get wedged if you kick them after they are
 	 * reset. Mark all vqs as broken to make sure we don't.

drivers/virtio/virtio_pci_modern.c

···
 	sg_init_one(&data_sg, get_data, sizeof(*get_data));
 	sg_init_one(&result_sg, result, sizeof(*result));
 	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET);
-	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF);
 	cmd.data_sg = &data_sg;
 	cmd.result_sg = &result_sg;
 	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);
···
 
 	sg_init_one(&result_sg, data, sizeof(*data));
 	cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY);
-	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV);
+	cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF);
 	cmd.result_sg = &result_sg;
 
 	ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd);

drivers/virtio/virtio_ring.c

···
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	if (vq->event_triggered)
-		vq->event_triggered = false;
+		data_race(vq->event_triggered = false);
 
 	return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) :
 				 virtqueue_enable_cb_delayed_split(_vq);

fs/bcachefs/alloc_foreground.c

···
 	open_bucket_for_each(c, &wp->ptrs, ob, i)
 		wp->sectors_free = min(wp->sectors_free, ob->sectors_free);
 
+	wp->sectors_free = rounddown(wp->sectors_free, block_sectors(c));
+
 	BUG_ON(!wp->sectors_free || wp->sectors_free == UINT_MAX);
 
 	return 0;

fs/bcachefs/alloc_foreground.h

···
 	unsigned i;
 
 	open_bucket_for_each(c, &wp->ptrs, ob, i)
-		ob_push(c, !ob->sectors_free ? &ptrs : &keep, ob);
+		ob_push(c, ob->sectors_free < block_sectors(c)
+			? &ptrs
+			: &keep, ob);
 	wp->ptrs = keep;
 
 	mutex_unlock(&wp->lock);

fs/bcachefs/bcachefs_format.h

···
 #define __BKEY_PADDED(key, pad)					\
 	struct bkey_i key; __u64 key ## _pad[pad]
 
+enum bch_bkey_type_flags {
+	BKEY_TYPE_strict_btree_checks	= BIT(0),
+};
+
 /*
  * - DELETED keys are used internally to mark keys that should be ignored but
  *   override keys in composition order.  Their version number is ignored.
···
  *
  * - WHITEOUT: for hash table btrees
  */
-#define BCH_BKEY_TYPES()				\
-	x(deleted,		0)			\
-	x(whiteout,		1)			\
-	x(error,		2)			\
-	x(cookie,		3)			\
-	x(hash_whiteout,	4)			\
-	x(btree_ptr,		5)			\
-	x(extent,		6)			\
-	x(reservation,		7)			\
-	x(inode,		8)			\
-	x(inode_generation,	9)			\
-	x(dirent,		10)			\
-	x(xattr,		11)			\
-	x(alloc,		12)			\
-	x(quota,		13)			\
-	x(stripe,		14)			\
-	x(reflink_p,		15)			\
-	x(reflink_v,		16)			\
-	x(inline_data,		17)			\
-	x(btree_ptr_v2,		18)			\
-	x(indirect_inline_data,	19)			\
-	x(alloc_v2,		20)			\
-	x(subvolume,		21)			\
-	x(snapshot,		22)			\
-	x(inode_v2,		23)			\
-	x(alloc_v3,		24)			\
-	x(set,			25)			\
-	x(lru,			26)			\
-	x(alloc_v4,		27)			\
-	x(backpointer,		28)			\
-	x(inode_v3,		29)			\
-	x(bucket_gens,		30)			\
-	x(snapshot_tree,	31)			\
-	x(logged_op_truncate,	32)			\
-	x(logged_op_finsert,	33)			\
-	x(accounting,		34)			\
-	x(inode_alloc_cursor,	35)
+#define BCH_BKEY_TYPES()						\
+	x(deleted,		0,	0)				\
+	x(whiteout,		1,	0)				\
+	x(error,		2,	0)				\
+	x(cookie,		3,	0)				\
+	x(hash_whiteout,	4,	BKEY_TYPE_strict_btree_checks)	\
+	x(btree_ptr,		5,	BKEY_TYPE_strict_btree_checks)	\
+	x(extent,		6,	BKEY_TYPE_strict_btree_checks)	\
+	x(reservation,		7,	BKEY_TYPE_strict_btree_checks)	\
+	x(inode,		8,	BKEY_TYPE_strict_btree_checks)	\
+	x(inode_generation,	9,	BKEY_TYPE_strict_btree_checks)	\
+	x(dirent,		10,	BKEY_TYPE_strict_btree_checks)	\
+	x(xattr,		11,	BKEY_TYPE_strict_btree_checks)	\
+	x(alloc,		12,	BKEY_TYPE_strict_btree_checks)	\
+	x(quota,		13,	BKEY_TYPE_strict_btree_checks)	\
+	x(stripe,		14,	BKEY_TYPE_strict_btree_checks)	\
+	x(reflink_p,		15,	BKEY_TYPE_strict_btree_checks)	\
+	x(reflink_v,		16,	BKEY_TYPE_strict_btree_checks)	\
+	x(inline_data,		17,	BKEY_TYPE_strict_btree_checks)	\
+	x(btree_ptr_v2,		18,	BKEY_TYPE_strict_btree_checks)	\
+	x(indirect_inline_data,	19,	BKEY_TYPE_strict_btree_checks)	\
+	x(alloc_v2,		20,	BKEY_TYPE_strict_btree_checks)	\
+	x(subvolume,		21,	BKEY_TYPE_strict_btree_checks)	\
+	x(snapshot,		22,	BKEY_TYPE_strict_btree_checks)	\
+	x(inode_v2,		23,	BKEY_TYPE_strict_btree_checks)	\
+	x(alloc_v3,		24,	BKEY_TYPE_strict_btree_checks)	\
+	x(set,			25,	0)				\
+	x(lru,			26,	BKEY_TYPE_strict_btree_checks)	\
+	x(alloc_v4,		27,	BKEY_TYPE_strict_btree_checks)	\
+	x(backpointer,		28,	BKEY_TYPE_strict_btree_checks)	\
+	x(inode_v3,		29,	BKEY_TYPE_strict_btree_checks)	\
+	x(bucket_gens,		30,	BKEY_TYPE_strict_btree_checks)	\
+	x(snapshot_tree,	31,	BKEY_TYPE_strict_btree_checks)	\
+	x(logged_op_truncate,	32,	BKEY_TYPE_strict_btree_checks)	\
+	x(logged_op_finsert,	33,	BKEY_TYPE_strict_btree_checks)	\
+	x(accounting,		34,	BKEY_TYPE_strict_btree_checks)	\
+	x(inode_alloc_cursor,	35,	BKEY_TYPE_strict_btree_checks)
 
 enum bch_bkey_type {
-#define x(name, nr) KEY_TYPE_##name	= nr,
+#define x(name, nr, ...) KEY_TYPE_##name	= nr,
 	BCH_BKEY_TYPES()
 #undef x
 	KEY_TYPE_MAX,
···
 LE64_BITMASK(BCH_SB_SHARD_INUMS_NBITS,	struct bch_sb, flags[6],  0,  4);
 LE64_BITMASK(BCH_SB_WRITE_ERROR_TIMEOUT,struct bch_sb, flags[6],  4, 14);
 LE64_BITMASK(BCH_SB_CSUM_ERR_RETRY_NR,	struct bch_sb, flags[6], 14, 20);
+LE64_BITMASK(BCH_SB_CASEFOLD,		struct bch_sb, flags[6], 22, 23);
 
 static inline __u64 BCH_SB_COMPRESSION_TYPE(const struct bch_sb *sb)
 {

fs/bcachefs/bkey_methods.c

···
 #include "xattr.h"
 
 const char * const bch2_bkey_types[] = {
-#define x(name, nr) #name,
+#define x(name, nr, ...) #name,
 	BCH_BKEY_TYPES()
 #undef x
 	NULL
···
 })
 
 const struct bkey_ops bch2_bkey_ops[] = {
-#define x(name, nr) [KEY_TYPE_##name]	= bch2_bkey_ops_##name,
+#define x(name, nr, ...) [KEY_TYPE_##name]	= bch2_bkey_ops_##name,
 	BCH_BKEY_TYPES()
 #undef x
 };
···
 #undef x
 };
 
+static const enum bch_bkey_type_flags bch2_bkey_type_flags[] = {
+#define x(name, nr, flags)	[KEY_TYPE_##name] = flags,
+	BCH_BKEY_TYPES()
+#undef x
+};
+
 const char *bch2_btree_node_type_str(enum btree_node_type type)
 {
 	return type == BKEY_TYPE_btree ? "internal btree node" : bch2_btree_id_str(type - 1);
···
 	if (type >= BKEY_TYPE_NR)
 		return 0;
 
-	bkey_fsck_err_on(k.k->type < KEY_TYPE_MAX &&
-			 (type == BKEY_TYPE_btree || (from.flags & BCH_VALIDATE_commit)) &&
+	enum bch_bkey_type_flags bkey_flags = k.k->type < KEY_TYPE_MAX
+		? bch2_bkey_type_flags[k.k->type]
+		: 0;
+
+	bool strict_key_type_allowed =
+		(from.flags & BCH_VALIDATE_commit) ||
+		type == BKEY_TYPE_btree ||
+		(from.btree < BTREE_ID_NR &&
+		 (bkey_flags & BKEY_TYPE_strict_btree_checks));
+
+	bkey_fsck_err_on(strict_key_type_allowed &&
+			 k.k->type < KEY_TYPE_MAX &&
 			 !(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)),
 			 c, bkey_invalid_type_for_btree,
 			 "invalid key type for btree %s (%s)",

fs/bcachefs/btree_iter.c

···
 					      struct bpos end)
 {
 	if ((iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots)) &&
-	   !bkey_eq(iter->pos, POS_MAX)) {
+	   !bkey_eq(iter->pos, POS_MAX) &&
+	   !((iter->flags & BTREE_ITER_is_extents) &&
+	     iter->pos.offset == U64_MAX)) {
+
 		/*
 		 * bkey_start_pos(), for extents, is not monotonically
 		 * increasing until after filtering for snapshots:
···
 
 	bch2_trans_verify_not_unlocked_or_in_restart(trans);
 	bch2_btree_iter_verify_entry_exit(iter);
-	EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && bpos_eq(end, POS_MIN));
+	EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && iter->pos.inode != end.inode);
 
 	int ret = trans_maybe_inject_restart(trans, _RET_IP_);
 	if (unlikely(ret)) {

fs/bcachefs/dirent.c

···
 
 #include <linux/dcache.h>
 
-static int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info,
-				const struct qstr *str, struct qstr *out_cf)
+int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info,
+		  const struct qstr *str, struct qstr *out_cf)
 {
 	*out_cf = (struct qstr) QSTR_INIT(NULL, 0);
 
···
 #else
 	return -EOPNOTSUPP;
 #endif
-}
-
-static inline int bch2_maybe_casefold(struct btree_trans *trans,
-				      const struct bch_hash_info *info,
-				      const struct qstr *str, struct qstr *out_cf)
-{
-	if (likely(!info->cf_encoding)) {
-		*out_cf = *str;
-		return 0;
-	} else {
-		return bch2_casefold(trans, info, str, out_cf);
-	}
 }
 
 static unsigned bch2_dirent_name_bytes(struct bkey_s_c_dirent d)

fs/bcachefs/dirent.h

···
 struct bch_hash_info;
 struct bch_inode_info;
 
+int bch2_casefold(struct btree_trans *, const struct bch_hash_info *,
+		  const struct qstr *, struct qstr *);
+
+static inline int bch2_maybe_casefold(struct btree_trans *trans,
+				      const struct bch_hash_info *info,
+				      const struct qstr *str, struct qstr *out_cf)
+{
+	if (likely(!info->cf_encoding)) {
+		*out_cf = *str;
+		return 0;
+	} else {
+		return bch2_casefold(trans, info, str, out_cf);
+	}
+}
+
 struct qstr bch2_dirent_get_name(struct bkey_s_c_dirent d);
 
 static inline unsigned dirent_val_u64s(unsigned len, unsigned cf_len)

fs/bcachefs/error.c

···
 {
 	struct fsck_err_state *s;
 
-	if (!test_bit(BCH_FS_fsck_running, &c->flags))
-		return NULL;
-
 	list_for_each_entry(s, &c->fsck_error_msgs, list)
 		if (s->id == id) {
 			/*
···
 	return ret;
 }
 
-void bch2_flush_fsck_errs(struct bch_fs *c)
+static void __bch2_flush_fsck_errs(struct bch_fs *c, bool print)
 {
 	struct fsck_err_state *s, *n;
 
 	mutex_lock(&c->fsck_error_msgs_lock);
 
 	list_for_each_entry_safe(s, n, &c->fsck_error_msgs, list) {
-		if (s->ratelimited && s->last_msg)
+		if (print && s->ratelimited && s->last_msg)
 			bch_err(c, "Saw %llu errors like:\n  %s", s->nr, s->last_msg);
 
 		list_del(&s->list);
···
 	}
 
 	mutex_unlock(&c->fsck_error_msgs_lock);
+}
+
+void bch2_flush_fsck_errs(struct bch_fs *c)
+{
+	__bch2_flush_fsck_errs(c, true);
+}
+
+void bch2_free_fsck_errs(struct bch_fs *c)
+{
+	__bch2_flush_fsck_errs(c, false);
 }
 
 int bch2_inum_offset_err_msg_trans(struct btree_trans *trans, struct printbuf *out,

fs/bcachefs/error.h

···
 			_flags, BCH_FSCK_ERR_##_err_type, __VA_ARGS__)
 
 void bch2_flush_fsck_errs(struct bch_fs *);
+void bch2_free_fsck_errs(struct bch_fs *);
 
 #define fsck_err_wrap(_do)						\
 ({									\

fs/bcachefs/fs-ioctl.c

···
 #define FSOP_GOING_FLAGS_LOGFLUSH	0x1	/* flush log but not data */
 #define FSOP_GOING_FLAGS_NOLOGFLUSH	0x2	/* don't flush log nor data */
 
-struct flags_set {
-	unsigned		mask;
-	unsigned		flags;
-
-	unsigned		projid;
-
-	bool			set_projinherit;
-	bool			projinherit;
-};
-
-static int bch2_inode_flags_set(struct btree_trans *trans,
-				struct bch_inode_info *inode,
-				struct bch_inode_unpacked *bi,
-				void *p)
-{
-	struct bch_fs *c = inode->v.i_sb->s_fs_info;
-	/*
-	 * We're relying on btree locking here for exclusion with other ioctl
-	 * calls - use the flags in the btree (@bi), not inode->i_flags:
-	 */
-	struct flags_set *s = p;
-	unsigned newflags = s->flags;
-	unsigned oldflags = bi->bi_flags & s->mask;
-
-	if (((newflags ^ oldflags) & (BCH_INODE_append|BCH_INODE_immutable)) &&
-	    !capable(CAP_LINUX_IMMUTABLE))
-		return -EPERM;
-
-	if (!S_ISREG(bi->bi_mode) &&
-	    !S_ISDIR(bi->bi_mode) &&
-	    (newflags & (BCH_INODE_nodump|BCH_INODE_noatime)) != newflags)
-		return -EINVAL;
-
-	if ((newflags ^ oldflags) & BCH_INODE_casefolded) {
-#ifdef CONFIG_UNICODE
-		int ret = 0;
-		/* Not supported on individual files. */
-		if (!S_ISDIR(bi->bi_mode))
-			return -EOPNOTSUPP;
-
-		/*
-		 * Make sure the dir is empty, as otherwise we'd need to
-		 * rehash everything and update the dirent keys.
-		 */
-		ret = bch2_empty_dir_trans(trans, inode_inum(inode));
-		if (ret < 0)
-			return ret;
-
-		ret = bch2_request_incompat_feature(c, bcachefs_metadata_version_casefolding);
-		if (ret)
-			return ret;
-
-		bch2_check_set_feature(c, BCH_FEATURE_casefolding);
-#else
-		printk(KERN_ERR "Cannot use casefolding on a kernel without CONFIG_UNICODE\n");
-		return -EOPNOTSUPP;
-#endif
-	}
-
-	if (s->set_projinherit) {
-		bi->bi_fields_set &= ~(1 << Inode_opt_project);
-		bi->bi_fields_set |= ((int) s->projinherit << Inode_opt_project);
-	}
-
-	bi->bi_flags &= ~s->mask;
-	bi->bi_flags |= newflags;
-
-	bi->bi_ctime = timespec_to_bch2_time(c, current_time(&inode->v));
-	return 0;
-}
-
-static int bch2_ioc_getflags(struct bch_inode_info *inode, int __user *arg)
-{
-	unsigned flags = map_flags(bch_flags_to_uflags, inode->ei_inode.bi_flags);
-
-	return put_user(flags, arg);
-}
-
-static int bch2_ioc_setflags(struct bch_fs *c,
-			     struct file *file,
-			     struct bch_inode_info *inode,
-			     void __user *arg)
-{
-	struct flags_set s = { .mask = map_defined(bch_flags_to_uflags) };
-	unsigned uflags;
-	int ret;
-
-	if (get_user(uflags, (int __user *) arg))
-		return -EFAULT;
-
-	s.flags = map_flags_rev(bch_flags_to_uflags, uflags);
-	if (uflags)
-		return -EOPNOTSUPP;
-
-	ret = mnt_want_write_file(file);
-	if (ret)
-		return ret;
-
-	inode_lock(&inode->v);
-	if (!inode_owner_or_capable(file_mnt_idmap(file), &inode->v)) {
-		ret = -EACCES;
-		goto setflags_out;
-	}
-
-	mutex_lock(&inode->ei_update_lock);
-	ret   = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
-		bch2_write_inode(c, inode, bch2_inode_flags_set, &s,
-			       ATTR_CTIME);
-	mutex_unlock(&inode->ei_update_lock);
-
-setflags_out:
-	inode_unlock(&inode->v);
-	mnt_drop_write_file(file);
-	return ret;
-}
-
-static int bch2_ioc_fsgetxattr(struct bch_inode_info *inode,
-			       struct fsxattr __user *arg)
-{
-	struct fsxattr fa = { 0 };
-
-	fa.fsx_xflags = map_flags(bch_flags_to_xflags, inode->ei_inode.bi_flags);
-
-	if (inode->ei_inode.bi_fields_set & (1 << Inode_opt_project))
-		fa.fsx_xflags |= FS_XFLAG_PROJINHERIT;
-
-	fa.fsx_projid = inode->ei_qid.q[QTYP_PRJ];
-
-	if (copy_to_user(arg, &fa, sizeof(fa)))
-		return -EFAULT;
-
-	return 0;
-}
-
-static int fssetxattr_inode_update_fn(struct btree_trans *trans,
-				      struct bch_inode_info *inode,
-				      struct bch_inode_unpacked *bi,
-				      void *p)
-{
-	struct flags_set *s = p;
-
-	if (s->projid != bi->bi_project) {
-		bi->bi_fields_set |= 1U << Inode_opt_project;
-		bi->bi_project = s->projid;
-	}
-
-	return bch2_inode_flags_set(trans, inode, bi, p);
-}
-
-static int bch2_ioc_fssetxattr(struct bch_fs *c,
-			       struct file *file,
-			       struct bch_inode_info *inode,
-			       struct fsxattr __user *arg)
-{
-	struct flags_set s = { .mask = map_defined(bch_flags_to_xflags) };
-	struct fsxattr fa;
-	int ret;
-
-	if (copy_from_user(&fa, arg, sizeof(fa)))
-		return -EFAULT;
-
-	s.set_projinherit = true;
-	s.projinherit = (fa.fsx_xflags & FS_XFLAG_PROJINHERIT) != 0;
-	fa.fsx_xflags &= ~FS_XFLAG_PROJINHERIT;
-
-	s.flags = map_flags_rev(bch_flags_to_xflags, fa.fsx_xflags);
-	if (fa.fsx_xflags)
-		return -EOPNOTSUPP;
-
-	if (fa.fsx_projid >= U32_MAX)
-		return -EINVAL;
-
-	/*
-	 * inode fields accessible via the xattr interface are stored with a +1
-	 * bias, so that 0 means unset:
-	 */
-	s.projid = fa.fsx_projid + 1;
-
-	ret = mnt_want_write_file(file);
-	if (ret)
-		return ret;
-
-	inode_lock(&inode->v);
-	if (!inode_owner_or_capable(file_mnt_idmap(file), &inode->v)) {
-		ret = -EACCES;
-		goto err;
-	}
-
-	mutex_lock(&inode->ei_update_lock);
-	ret   = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
-		bch2_set_projid(c, inode, fa.fsx_projid) ?:
-		bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s,
-			       ATTR_CTIME);
-	mutex_unlock(&inode->ei_update_lock);
-err:
-	inode_unlock(&inode->v);
-	mnt_drop_write_file(file);
-	return ret;
-}
-
 static int bch2_reinherit_attrs_fn(struct btree_trans *trans,
 				   struct bch_inode_info *inode,
 				   struct bch_inode_unpacked *bi,
···
 	long ret;
 
 	switch (cmd) {
-	case FS_IOC_GETFLAGS:
-		ret = bch2_ioc_getflags(inode, (int __user *) arg);
-		break;
-
-	case FS_IOC_SETFLAGS:
-		ret = bch2_ioc_setflags(c, file, inode, (int __user *) arg);
-		break;
-
-	case FS_IOC_FSGETXATTR:
-		ret = bch2_ioc_fsgetxattr(inode, (void __user *) arg);
-		break;
-
-	case FS_IOC_FSSETXATTR:
-		ret = bch2_ioc_fssetxattr(c, file, inode,
-					  (void __user *) arg);
-		break;
-
 	case BCHFS_IOC_REINHERIT_ATTRS:
 		ret = bch2_ioc_reinherit_attrs(c, file, inode,
 					       (void __user *) arg);

fs/bcachefs/fs-ioctl.h

···
 #ifndef _BCACHEFS_FS_IOCTL_H
 #define _BCACHEFS_FS_IOCTL_H
 
-/* Inode flags: */
-
-/* bcachefs inode flags -> vfs inode flags: */
-static const __maybe_unused unsigned bch_flags_to_vfs[] = {
-	[__BCH_INODE_sync]		= S_SYNC,
-	[__BCH_INODE_immutable]		= S_IMMUTABLE,
-	[__BCH_INODE_append]		= S_APPEND,
-	[__BCH_INODE_noatime]		= S_NOATIME,
-	[__BCH_INODE_casefolded]	= S_CASEFOLD,
-};
-
-/* bcachefs inode flags -> FS_IOC_GETFLAGS: */
-static const __maybe_unused unsigned bch_flags_to_uflags[] = {
-	[__BCH_INODE_sync]		= FS_SYNC_FL,
-	[__BCH_INODE_immutable]		= FS_IMMUTABLE_FL,
-	[__BCH_INODE_append]		= FS_APPEND_FL,
-	[__BCH_INODE_nodump]		= FS_NODUMP_FL,
-	[__BCH_INODE_noatime]		= FS_NOATIME_FL,
-	[__BCH_INODE_casefolded]	= FS_CASEFOLD_FL,
-};
-
-/* bcachefs inode flags -> FS_IOC_FSGETXATTR: */
-static const __maybe_unused unsigned bch_flags_to_xflags[] = {
-	[__BCH_INODE_sync]	= FS_XFLAG_SYNC,
-	[__BCH_INODE_immutable]	= FS_XFLAG_IMMUTABLE,
-	[__BCH_INODE_append]	= FS_XFLAG_APPEND,
-	[__BCH_INODE_nodump]	= FS_XFLAG_NODUMP,
-	[__BCH_INODE_noatime]	= FS_XFLAG_NOATIME,
-	//[__BCH_INODE_PROJINHERIT] = FS_XFLAG_PROJINHERIT;
-};
-
-#define set_flags(_map, _in, _out)					\
-do {									\
-	unsigned _i;							\
-									\
-	for (_i = 0; _i < ARRAY_SIZE(_map); _i++)			\
-		if ((_in) & (1 << _i))					\
-			(_out) |= _map[_i];				\
-		else							\
-			(_out) &= ~_map[_i];				\
-} while (0)
-
-#define map_flags(_map, _in)						\
-({									\
-	unsigned _out = 0;						\
-									\
-	set_flags(_map, _in, _out);					\
-	_out;								\
-})
-
-#define map_flags_rev(_map, _in)					\
-({									\
-	unsigned _i, _out = 0;						\
-									\
-	for (_i = 0; _i < ARRAY_SIZE(_map); _i++)			\
-		if ((_in) & _map[_i]) {					\
-			(_out) |= 1 << _i;				\
-			(_in) &= ~_map[_i];				\
-		}							\
-	(_out);								\
-})
-
-#define map_defined(_map)						\
-({									\
-	unsigned _in = ~0;						\
-									\
-	map_flags_rev(_map, _in);					\
-})
-
-/* Set VFS inode flags from bcachefs inode: */
-static inline void bch2_inode_flags_to_vfs(struct bch_inode_info *inode)
-{
-	set_flags(bch_flags_to_vfs, inode->ei_inode.bi_flags, inode->v.i_flags);
-}
-
 long bch2_fs_file_ioctl(struct file *, unsigned, unsigned long);
 long bch2_compat_fs_ioctl(struct file *, unsigned, unsigned long);
 

fs/bcachefs/fs.c

···
 #include <linux/backing-dev.h>
 #include <linux/exportfs.h>
 #include <linux/fiemap.h>
+#include <linux/fileattr.h>
 #include <linux/fs_context.h>
 #include <linux/module.h>
 #include <linux/pagemap.h>
···
 				struct bch_inode_info *,
 				struct bch_inode_unpacked *,
 				struct bch_subvolume *);
+
+/* Set VFS inode flags from bcachefs inode: */
+static inline void bch2_inode_flags_to_vfs(struct bch_fs *c, struct bch_inode_info *inode)
+{
+	static const __maybe_unused unsigned bch_flags_to_vfs[] = {
+		[__BCH_INODE_sync]		= S_SYNC,
+		[__BCH_INODE_immutable]		= S_IMMUTABLE,
+		[__BCH_INODE_append]		= S_APPEND,
+		[__BCH_INODE_noatime]		= S_NOATIME,
+	};
+
+	set_flags(bch_flags_to_vfs, inode->ei_inode.bi_flags, inode->v.i_flags);
+
+	if (bch2_inode_casefold(c, &inode->ei_inode))
+		inode->v.i_flags |= S_CASEFOLD;
+}
 
 void bch2_inode_update_after_write(struct btree_trans *trans,
 				   struct bch_inode_info *inode,
···
 
 	inode->ei_inode		= *bi;
 
-	bch2_inode_flags_to_vfs(inode);
+	bch2_inode_flags_to_vfs(c, inode);
 }
 
 int __must_check bch2_write_inode(struct bch_fs *c,
···
 			const struct qstr *name)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_iter dirent_iter = {};
 	subvol_inum inum = {};
 	struct printbuf buf = PRINTBUF;
 
+	struct qstr lookup_name;
+	int ret = bch2_maybe_casefold(trans, dir_hash_info, name, &lookup_name);
+	if (ret)
+		return ERR_PTR(ret);
+
+	struct btree_iter dirent_iter = {};
 	struct bkey_s_c k = bch2_hash_lookup(trans, &dirent_iter, bch2_dirent_hash_desc,
-					     dir_hash_info, dir, name, 0);
-	int ret = bkey_err(k);
+					     dir_hash_info, dir, &lookup_name, 0);
+	ret = bkey_err(k);
 	if (ret)
 		return ERR_PTR(ret);
 
···
 		 * the VFS that it's been deleted here:
 		 */
 		set_nlink(&inode->v, 0);
+	}
+
+	if (IS_CASEFOLDED(vdir)) {
+		d_invalidate(dentry);
+		d_prune_aliases(&inode->v);
 	}
 err:
 	bch2_trans_put(trans);
···
 	return finish_open_simple(file, 0);
 }
 
+struct bch_fiemap_extent {
+	struct bkey_buf	kbuf;
+	unsigned	flags;
+};
+
 static int bch2_fill_extent(struct bch_fs *c,
 			    struct fiemap_extent_info *info,
-			    struct bkey_s_c k, unsigned flags)
+			    struct bch_fiemap_extent *fe)
 {
+	struct bkey_s_c k = bkey_i_to_s_c(fe->kbuf.k);
+	unsigned flags = fe->flags;
+
+	BUG_ON(!k.k->size);
+
 	if (bkey_extent_is_direct_data(k.k)) {
 		struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
 		const union bch_extent_entry *entry;
···
 	}
 }
 
+/*
+ * Scan a range of an inode for data in pagecache.
+ *
+ * Intended to be retryable, so don't modify the output params until success is
+ * imminent.
+ */
+static int
+bch2_fiemap_hole_pagecache(struct inode *vinode, u64 *start, u64 *end,
+			   bool nonblock)
+{
+	loff_t	dstart, dend;
+
+	dstart = bch2_seek_pagecache_data(vinode, *start, *end, 0, nonblock);
+	if (dstart < 0)
+		return dstart;
+
+	if (dstart == *end) {
+		*start = dstart;
+		return 0;
+	}
+
+	dend = bch2_seek_pagecache_hole(vinode, dstart, *end, 0, nonblock);
+	if (dend < 0)
+		return dend;
+
+	/* race */
+	BUG_ON(dstart == dend);
+
+	*start = dstart;
+	*end = dend;
+	return 0;
+}
+
+/*
+ * Scan a range of pagecache that corresponds to a file mapping hole in the
+ * extent btree. If data is found, fake up an extent key so it looks like a
+ * delalloc extent to the rest of the fiemap processing code.
+ */
+static int
+bch2_next_fiemap_pagecache_extent(struct btree_trans *trans, struct bch_inode_info *inode,
+				  u64 start, u64 end, struct bch_fiemap_extent *cur)
+{
+	struct bch_fs		*c = trans->c;
+	struct bkey_i_extent	*delextent;
+	struct bch_extent_ptr	ptr = {};
+	loff_t			dstart = start << 9, dend = end << 9;
+	int			ret;
+
+	/*
+	 * We hold btree locks here so we cannot block on folio locks without
+	 * dropping trans locks first. Run a nonblocking scan for the common
+	 * case of no folios over holes and fall back on failure.
+	 *
+	 * Note that dropping locks like this is technically racy against
+	 * writeback inserting to the extent tree, but a non-sync fiemap scan is
+	 * fundamentally racy with writeback anyways. Therefore, just report the
+	 * range as delalloc regardless of whether we have to cycle trans locks.
+	 */
+	ret = bch2_fiemap_hole_pagecache(&inode->v, &dstart, &dend, true);
+	if (ret == -EAGAIN)
+		ret = drop_locks_do(trans,
+			bch2_fiemap_hole_pagecache(&inode->v, &dstart, &dend, false));
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Create a fake extent key in the buffer. We have to add a dummy extent
+	 * pointer for the fill code to add an extent entry. It's explicitly
+	 * zeroed to reflect delayed allocation (i.e. phys offset 0).
+	 */
+	bch2_bkey_buf_realloc(&cur->kbuf, c, sizeof(*delextent) / sizeof(u64));
+	delextent = bkey_extent_init(cur->kbuf.k);
+	delextent->k.p = POS(inode->ei_inum.inum, dend >> 9);
+	delextent->k.size = (dend - dstart) >> 9;
+	bch2_bkey_append_ptr(&delextent->k_i, ptr);
+
+	cur->flags = FIEMAP_EXTENT_DELALLOC;
+
+	return 0;
+}
+
+static int bch2_next_fiemap_extent(struct btree_trans *trans,
+				   struct bch_inode_info *inode,
+				   u64 start, u64 end,
+				   struct bch_fiemap_extent *cur)
+{
+	u32 snapshot;
+	int ret = bch2_subvolume_get_snapshot(trans, inode->ei_inum.subvol, &snapshot);
+	if (ret)
+		return ret;
+
+	struct btree_iter iter;
+	bch2_trans_iter_init(trans, &iter, BTREE_ID_extents,
+			     SPOS(inode->ei_inum.inum, start, snapshot), 0);
+
+	struct bkey_s_c k =
+		bch2_btree_iter_peek_max(trans, &iter, POS(inode->ei_inum.inum, end));
+	ret = bkey_err(k);
+	if (ret)
+		goto err;
+
+	ret = bch2_next_fiemap_pagecache_extent(trans, inode, start, end, cur);
+	if (ret)
+		goto err;
+
+	struct bpos pagecache_start = bkey_start_pos(&cur->kbuf.k->k);
+
+	/*
+	 * Does the pagecache or the btree take precedence?
+	 *
+	 * It _should_ be the pagecache, so that we correctly report delalloc
+	 * extents when dirty in the pagecache (we're COW, after all).
+	 *
+	 * But we'd have to add per-sector writeback tracking to
+	 * bch_folio_state, otherwise we report delalloc extents for clean
+	 * cached data in the pagecache.
+	 *
+	 * We should do this, but even then fiemap won't report stable mappings:
+	 * on bcachefs data moves around in the background (copygc, rebalance)
+	 * and we don't provide a way for userspace to lock that out.
+	 */
+	if (k.k &&
+	    bkey_le(bpos_max(iter.pos, bkey_start_pos(k.k)),
+		    pagecache_start)) {
+		bch2_bkey_buf_reassemble(&cur->kbuf, trans->c, k);
+		bch2_cut_front(iter.pos, cur->kbuf.k);
+		bch2_cut_back(POS(inode->ei_inum.inum, end), cur->kbuf.k);
+		cur->flags = 0;
+	} else if (k.k) {
+		bch2_cut_back(bkey_start_pos(k.k), cur->kbuf.k);
+	}
+
+	if (cur->kbuf.k->k.type == KEY_TYPE_reflink_p) {
+		unsigned sectors = cur->kbuf.k->k.size;
+		s64 offset_into_extent = 0;
+		enum btree_id data_btree = BTREE_ID_extents;
+		int ret = bch2_read_indirect_extent(trans, &data_btree, &offset_into_extent,
+						    &cur->kbuf);
+		if (ret)
+			goto err;
+
+		struct bkey_i *k = cur->kbuf.k;
+		sectors = min_t(unsigned, sectors, k->k.size - offset_into_extent);
+
+		bch2_cut_front(POS(k->k.p.inode,
+				   bkey_start_offset(&k->k) + offset_into_extent),
+			       k);
+		bch2_key_resize(&k->k, sectors);
+		k->k.p = iter.pos;
+		k->k.p.offset += k->k.size;
+	}
+err:
+	bch2_trans_iter_exit(trans, &iter);
+	return ret;
+}
+
 static int bch2_fiemap(struct inode *vinode, struct fiemap_extent_info *info,
 		       u64 start, u64 len)
 {
 	struct bch_fs *c = vinode->i_sb->s_fs_info;
 	struct bch_inode_info *ei = to_bch_ei(vinode);
 	struct btree_trans *trans;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bkey_buf cur, prev;
-	bool have_extent = false;
+	struct bch_fiemap_extent cur, prev;
 	int ret = 0;
 
-	ret = fiemap_prep(&ei->v, info, start, &len, FIEMAP_FLAG_SYNC);
+	ret = fiemap_prep(&ei->v, info, start, &len, 0);
 	if (ret)
 		return ret;
 
-	struct bpos end = POS(ei->v.i_ino, (start + len) >> 9);
 	if (start + len < start)
 		return -EINVAL;
 
 	start >>= 9;
+	u64 end = (start + len) >> 9;
 
-	bch2_bkey_buf_init(&cur);
-	bch2_bkey_buf_init(&prev);
+	bch2_bkey_buf_init(&cur.kbuf);
+	bch2_bkey_buf_init(&prev.kbuf);
+	bkey_init(&prev.kbuf.k->k);
+
 	trans = bch2_trans_get(c);
 
-	bch2_trans_iter_init(trans, &iter, BTREE_ID_extents,
-			     POS(ei->v.i_ino, start), 0);
-
-	while (!ret || bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
-		enum btree_id data_btree = BTREE_ID_extents;
-
-		bch2_trans_begin(trans);
-
-		u32 snapshot;
-		ret = bch2_subvolume_get_snapshot(trans, ei->ei_inum.subvol, &snapshot);
+	while (start < end) {
+		ret = lockrestart_do(trans,
+			bch2_next_fiemap_extent(trans, ei, start, end, &cur));
 		if (ret)
-			continue;
+			goto err;
 
-		bch2_btree_iter_set_snapshot(trans, &iter, snapshot);
+		BUG_ON(bkey_start_offset(&cur.kbuf.k->k) < start);
+		BUG_ON(cur.kbuf.k->k.p.offset > end);
 
-		k = bch2_btree_iter_peek_max(trans, &iter, end);
-		ret = bkey_err(k);
-		if (ret)
-			continue;
-
-		if (!k.k)
+		if (bkey_start_offset(&cur.kbuf.k->k) == end)
 			break;
 
-		if (!bkey_extent_is_data(k.k) &&
-		    k.k->type != KEY_TYPE_reservation) {
-			bch2_btree_iter_advance(trans, &iter);
-			continue;
-		}
+		start = cur.kbuf.k->k.p.offset;
 
-		s64 offset_into_extent	= iter.pos.offset - bkey_start_offset(k.k);
-		unsigned sectors	= k.k->size - offset_into_extent;
-
-		bch2_bkey_buf_reassemble(&cur, c, k);
-
-		ret = bch2_read_indirect_extent(trans, &data_btree,
-					&offset_into_extent, &cur);
-		if (ret)
-			continue;
-
-		k = bkey_i_to_s_c(cur.k);
-		bch2_bkey_buf_realloc(&prev, c, k.k->u64s);
-
-		sectors = min_t(unsigned, sectors, k.k->size - offset_into_extent);
-
-		bch2_cut_front(POS(k.k->p.inode,
-				   bkey_start_offset(k.k) +
-				   offset_into_extent),
-			       cur.k);
-		bch2_key_resize(&cur.k->k, sectors);
-		cur.k->k.p = iter.pos;
-		cur.k->k.p.offset += cur.k->k.size;
-
-		if (have_extent) {
+		if (!bkey_deleted(&prev.kbuf.k->k)) {
 			bch2_trans_unlock(trans);
-			ret = bch2_fill_extent(c, info,
-					bkey_i_to_s_c(prev.k), 0);
+			ret = bch2_fill_extent(c, info, &prev);
 			if (ret)
-				break;
+				goto err;
 		}
 
-		bkey_copy(prev.k, cur.k);
-		have_extent = true;
-
-		bch2_btree_iter_set_pos(trans, &iter,
-			POS(iter.pos.inode, iter.pos.offset + sectors));
+		bch2_bkey_buf_copy(&prev.kbuf, c, cur.kbuf.k);
+		prev.flags = cur.flags;
 	}
-	bch2_trans_iter_exit(trans, &iter);
 
-	if (!ret && have_extent) {
+	if (!bkey_deleted(&prev.kbuf.k->k)) {
 		bch2_trans_unlock(trans);
-		ret = bch2_fill_extent(c, info, bkey_i_to_s_c(prev.k),
-				       FIEMAP_EXTENT_LAST);
+		prev.flags |= FIEMAP_EXTENT_LAST;
+		ret = bch2_fill_extent(c, info, &prev);
 	}
-
+err:
 	bch2_trans_put(trans);
-	bch2_bkey_buf_exit(&cur, c);
-	bch2_bkey_buf_exit(&prev, c);
-	return ret < 0 ? ret : 0;
+	bch2_bkey_buf_exit(&cur.kbuf, c);
+	bch2_bkey_buf_exit(&prev.kbuf, c);
+
+	return bch2_err_class(ret < 0 ? ret : 0);
 }
 
 static const struct vm_operations_struct bch_vm_ops = {
···
 	return generic_file_open(vinode, file);
 }
 
+/* bcachefs inode flags -> FS_IOC_GETFLAGS: */
+static const __maybe_unused unsigned bch_flags_to_uflags[] = {
+	[__BCH_INODE_sync]		= FS_SYNC_FL,
+	[__BCH_INODE_immutable]		= FS_IMMUTABLE_FL,
+	[__BCH_INODE_append]		= FS_APPEND_FL,
+	[__BCH_INODE_nodump]		= FS_NODUMP_FL,
+	[__BCH_INODE_noatime]		= FS_NOATIME_FL,
+};
+
+/* bcachefs inode flags -> FS_IOC_FSGETXATTR: */
+static const __maybe_unused unsigned bch_flags_to_xflags[] = {
+	[__BCH_INODE_sync]	= FS_XFLAG_SYNC,
+	[__BCH_INODE_immutable]	= FS_XFLAG_IMMUTABLE,
+	[__BCH_INODE_append]	= FS_XFLAG_APPEND,
+	[__BCH_INODE_nodump]	= FS_XFLAG_NODUMP,
+	[__BCH_INODE_noatime]	= FS_XFLAG_NOATIME,
+};
+
+static int bch2_fileattr_get(struct dentry *dentry,
+			     struct fileattr *fa)
+{
+	struct bch_inode_info *inode = to_bch_ei(d_inode(dentry));
+	struct bch_fs *c = inode->v.i_sb->s_fs_info;
+
+	fileattr_fill_xflags(fa, map_flags(bch_flags_to_xflags, inode->ei_inode.bi_flags));
+
+	if (inode->ei_inode.bi_fields_set & (1 << Inode_opt_project))
+		fa->fsx_xflags |= FS_XFLAG_PROJINHERIT;
+
+	if (bch2_inode_casefold(c, &inode->ei_inode))
+		fa->flags |= FS_CASEFOLD_FL;
+
+	fa->fsx_projid = inode->ei_qid.q[QTYP_PRJ];
+	return 0;
+}
+
+struct flags_set {
+	unsigned		mask;
+	unsigned		flags;
+	unsigned		projid;
+	bool			set_project;
+	bool			set_casefold;
+	bool			casefold;
+};
+
+static int fssetxattr_inode_update_fn(struct btree_trans *trans,
+				      struct bch_inode_info *inode,
+				      struct bch_inode_unpacked *bi,
+				      void *p)
+{
+	struct bch_fs *c = trans->c;
+	struct flags_set *s = p;
+
+	/*
+	 * We're relying on btree locking here for exclusion with other ioctl
+	 * calls - use the flags in the btree (@bi), not inode->i_flags:
+	 */
+	if (!S_ISREG(bi->bi_mode) &&
+	    !S_ISDIR(bi->bi_mode) &&
+	    (s->flags & (BCH_INODE_nodump|BCH_INODE_noatime)) != s->flags)
+		return -EINVAL;
+
+	if (s->casefold != bch2_inode_casefold(c, bi)) {
+#ifdef CONFIG_UNICODE
+		int ret = 0;
+		/* Not supported on individual files. */
+		if (!S_ISDIR(bi->bi_mode))
+			return -EOPNOTSUPP;
+
+		/*
+		 * Make sure the dir is empty, as otherwise we'd need to
+		 * rehash everything and update the dirent keys.
+		 */
+		ret = bch2_empty_dir_trans(trans, inode_inum(inode));
+		if (ret < 0)
+			return ret;
+
+		ret = bch2_request_incompat_feature(c, bcachefs_metadata_version_casefolding);
+		if (ret)
+			return ret;
+
+		bch2_check_set_feature(c, BCH_FEATURE_casefolding);
+
+		bi->bi_casefold = s->casefold + 1;
+		bi->bi_fields_set |= BIT(Inode_opt_casefold);
+
+#else
+		printk(KERN_ERR "Cannot use casefolding on a kernel without CONFIG_UNICODE\n");
+		return -EOPNOTSUPP;
+#endif
+	}
+
+	if (s->set_project) {
+		bi->bi_project = s->projid;
+		bi->bi_fields_set |= BIT(Inode_opt_project);
+	}
+
+	bi->bi_flags &= ~s->mask;
+	bi->bi_flags |= s->flags;
+
+	bi->bi_ctime = timespec_to_bch2_time(c, current_time(&inode->v));
+	return 0;
+}
+
+static int bch2_fileattr_set(struct mnt_idmap *idmap,
+			     struct dentry *dentry,
+			     struct fileattr *fa)
+{
+	struct bch_inode_info *inode = to_bch_ei(d_inode(dentry));
+	struct bch_fs *c = inode->v.i_sb->s_fs_info;
+	struct flags_set s = {};
+	int ret;
+
+	if (fa->fsx_valid) {
+		fa->fsx_xflags &= ~FS_XFLAG_PROJINHERIT;
+
+		s.mask = map_defined(bch_flags_to_xflags);
+		s.flags |= map_flags_rev(bch_flags_to_xflags, fa->fsx_xflags);
+		if (fa->fsx_xflags)
+			return -EOPNOTSUPP;
+
+		if (fa->fsx_projid >= U32_MAX)
+			return -EINVAL;
+
+		/*
+		 * inode fields accessible via the xattr interface are stored with a +1
+		 * bias, so that 0 means unset:
+		 */
+		if ((inode->ei_inode.bi_project ||
+		     fa->fsx_projid) &&
+		    inode->ei_inode.bi_project != fa->fsx_projid + 1) {
+			s.projid = fa->fsx_projid + 1;
+			s.set_project = true;
+		}
+	}
+
+	if (fa->flags_valid) {
+		s.mask = map_defined(bch_flags_to_uflags);
+
+		s.set_casefold = true;
+		s.casefold = (fa->flags & FS_CASEFOLD_FL) != 0;
+		fa->flags &= ~FS_CASEFOLD_FL;
+
+		s.flags |= map_flags_rev(bch_flags_to_uflags, fa->flags);
+		if (fa->flags)
+			return -EOPNOTSUPP;
+	}
+
+	mutex_lock(&inode->ei_update_lock);
+	ret   = bch2_subvol_is_ro(c, inode->ei_inum.subvol) ?:
+		(s.set_project
+		 ? bch2_set_projid(c, inode, fa->fsx_projid)
+		 : 0) ?:
+		bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s,
+			       ATTR_CTIME);
+	mutex_unlock(&inode->ei_update_lock);
+	return ret;
+}
+
 static const struct file_operations bch_file_operations = {
 	.open		= bch2_open,
 	.llseek		= bch2_llseek,
···
 	.get_inode_acl	= bch2_get_acl,
 	.set_acl	= bch2_set_acl,
 #endif
+	.fileattr_get	= bch2_fileattr_get,
+	.fileattr_set	= bch2_fileattr_set,
 };
 
 static const struct inode_operations bch_dir_inode_operations = {
···
 	.get_inode_acl	= bch2_get_acl,
 	.set_acl	= bch2_set_acl,
 #endif
+	.fileattr_get	= bch2_fileattr_get,
+	.fileattr_set	= bch2_fileattr_set,
 };
 
 static const struct file_operations bch_dir_file_operations = {
···
 	.get_inode_acl	= bch2_get_acl,
 	.set_acl	= bch2_set_acl,
 #endif
+	.fileattr_get	= bch2_fileattr_get,
+	.fileattr_set	= bch2_fileattr_set,
 };
 
 static const struct inode_operations bch_special_inode_operations = {
···
 	.get_inode_acl	= bch2_get_acl,
 	.set_acl	= bch2_set_acl,
 #endif
+	.fileattr_get	= bch2_fileattr_get,
+	.fileattr_set	= bch2_fileattr_set,
 };
 
 static const struct address_space_operations bch_address_space_operations = {

fs/bcachefs/inode.h

···
 	}
 }
 
+static inline bool bch2_inode_casefold(struct bch_fs *c, const struct bch_inode_unpacked *bi)
+{
+	/* inode apts are stored with a +1 bias: 0 means "unset, use fs opt" */
+	return bi->bi_casefold
+		? bi->bi_casefold - 1
+		: c->opts.casefold;
+}
+
 /* i_nlink: */
 
 static inline unsigned nlink_bias(umode_t mode)

fs/bcachefs/inode_format.h

···
 	x(bi_parent_subvol,		32)	\
 	x(bi_nocow,			8)	\
 	x(bi_depth,			32)	\
-	x(bi_inodes_32bit,		8)
+	x(bi_inodes_32bit,		8)	\
+	x(bi_casefold,			8)
 
 /* subset of BCH_INODE_FIELDS */
 #define BCH_INODE_OPTS()			\
···
 	x(background_target,		16)	\
 	x(erasure_code,			16)	\
 	x(nocow,			8)	\
-	x(inodes_32bit,			8)
+	x(inodes_32bit,			8)	\
+	x(casefold,			8)
 
 enum inode_opt_id {
 #define x(name, ...)				\
···
 	x(i_sectors_dirty,		6)	\
 	x(unlinked,			7)	\
 	x(backptr_untrusted,		8)	\
-	x(has_child_snapshot,		9)	\
-	x(casefolded,			10)
+	x(has_child_snapshot,		9)
 
 /* bits 20+ reserved for packed fields below: */
 

fs/bcachefs/journal.c

···
 
 	sectors = vstruct_blocks_plus(buf->data, c->block_bits,
 				      buf->u64s_reserved) << c->block_bits;
-	BUG_ON(sectors > buf->sectors);
+	if (unlikely(sectors > buf->sectors)) {
+		struct printbuf err = PRINTBUF;
+		err.atomic++;
+
+		prt_printf(&err, "journal entry overran reserved space: %u > %u\n",
+			   sectors, buf->sectors);
+		prt_printf(&err, "buf u64s %u u64s reserved %u cur_entry_u64s %u block_bits %u\n",
+			   le32_to_cpu(buf->data->u64s), buf->u64s_reserved,
+			   j->cur_entry_u64s,
+			   c->block_bits);
+		prt_printf(&err, "fatal error - emergency read only");
+		bch2_journal_halt_locked(j);
+
+		bch_err(c, "%s", err.buf);
+		printbuf_exit(&err);
+		return;
+	}
+
 	buf->sectors = sectors;
 
 	/*
···
 		j->last_empty_seq = cur_seq - 1; /* to match j->seq */
 
 	spin_lock(&j->lock);
-
-	set_bit(JOURNAL_running, &j->flags);
 	j->last_flush_write = jiffies;
 
 	j->reservations.idx = journal_cur_seq(j);
···
 	spin_unlock(&j->lock);
 
 	return 0;
+}
+
+void bch2_journal_set_replay_done(struct journal *j)
+{
+	/*
+	 * journal_space_available must happen before setting JOURNAL_running
+	 * JOURNAL_running must happen before JOURNAL_replay_done
+	 */
+	spin_lock(&j->lock);
+	bch2_journal_space_available(j);
+
+	set_bit(JOURNAL_need_flush_write, &j->flags);
+	set_bit(JOURNAL_running, &j->flags);
+	set_bit(JOURNAL_replay_done, &j->flags);
+	spin_unlock(&j->lock);
 }
 
 /* init/exit: */

fs/bcachefs/journal.h

···
 
 struct bch_dev;
 
-static inline void bch2_journal_set_replay_done(struct journal *j)
-{
-	BUG_ON(!test_bit(JOURNAL_running, &j->flags));
-	set_bit(JOURNAL_replay_done, &j->flags);
-}
-
 void bch2_journal_unblock(struct journal *);
 void bch2_journal_block(struct journal *);
 struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *, u64, bool *);
···
 
 void bch2_fs_journal_stop(struct journal *);
 int bch2_fs_journal_start(struct journal *, u64);
+void bch2_journal_set_replay_done(struct journal *);
 
 void bch2_dev_journal_exit(struct bch_dev *);
 int bch2_dev_journal_init(struct bch_dev *, struct bch_sb *);

fs/bcachefs/journal_reclaim.c

···
 
 	bch2_journal_set_watermark(j);
 out:
-	j->cur_entry_sectors	= !ret ? j->space[journal_space_discarded].next_entry : 0;
+	j->cur_entry_sectors	= !ret
+		? round_down(j->space[journal_space_discarded].next_entry,
+			     block_sectors(c))
+		: 0;
 	j->cur_entry_error	= ret;
 
 	if (!ret)

fs/bcachefs/movinggc.c

···
 
 	set_freezable();
 
+	/*
+	 * Data move operations can't run until after check_snapshots has
+	 * completed, and bch2_snapshot_is_ancestor() is available.
+	 */
+	kthread_wait_freezable(c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots ||
+			       kthread_should_stop());
+
 	bch2_move_stats_init(&move_stats, "copygc");
 	bch2_moving_ctxt_init(&ctxt, c, NULL, &move_stats,
 			      writepoint_ptr(&c->copygc_write_point),

fs/bcachefs/movinggc.h

···
 unsigned long bch2_copygc_wait_amount(struct bch_fs *);
 void bch2_copygc_wait_to_text(struct printbuf *, struct bch_fs *);
 
+static inline void bch2_copygc_wakeup(struct bch_fs *c)
+{
+	rcu_read_lock();
+	struct task_struct *p = rcu_dereference(c->copygc_thread);
+	if (p)
+		wake_up_process(p);
+	rcu_read_unlock();
+}
+
 void bch2_copygc_stop(struct bch_fs *);
 int bch2_copygc_start(struct bch_fs *);
 void bch2_fs_copygc_init(struct bch_fs *);

fs/bcachefs/namei.c

···
 	if (ret)
 		goto err;
 
-	/* Inherit casefold state from parent. */
-	if (S_ISDIR(mode))
-		new_inode->bi_flags |= dir_u->bi_flags & BCH_INODE_casefolded;
-
 	if (!(flags & BCH_CREATE_SNAPSHOT)) {
 		/* Normal create path - allocate a new inode: */
 		bch2_inode_init_late(new_inode, now, uid, gid, mode, rdev, dir_u);

fs/bcachefs/opts.h

···
 	  OPT_BOOL(),							\
 	  BCH_SB_ERASURE_CODE,		false,				\
 	  NULL,		"Enable erasure coding (DO NOT USE YET)")	\
+	x(casefold,			u8,				\
+	  OPT_FS|OPT_INODE|OPT_FORMAT,					\
+	  OPT_BOOL(),							\
+	  BCH_SB_CASEFOLD,		false,				\
+	  NULL,		"Dirent lookups are casefolded")		\
 	x(inodes_32bit,			u8,				\
 	  OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME,		\
 	  OPT_BOOL(),							\

fs/bcachefs/rebalance.c

···
 	int ret = bch2_trans_commit_do(c, NULL, NULL,
 				       BCH_TRANS_COMMIT_no_enospc,
 			    bch2_set_rebalance_needs_scan_trans(trans, inum));
-	rebalance_wakeup(c);
+	bch2_rebalance_wakeup(c);
 	return ret;
 }
 
···
 
 	set_freezable();
 
+	/*
+	 * Data move operations can't run until after check_snapshots has
+	 * completed, and bch2_snapshot_is_ancestor() is available.
+	 */
+	kthread_wait_freezable(c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots ||
+			       kthread_should_stop());
+
 	bch2_moving_ctxt_init(&ctxt, c, NULL, &r->work_stats,
 			      writepoint_ptr(&c->rebalance_write_point),
 			      true);
···
 	c->rebalance.thread = NULL;
 
 	if (p) {
-		/* for sychronizing with rebalance_wakeup() */
+		/* for sychronizing with bch2_rebalance_wakeup() */
 		synchronize_rcu();
 
 		kthread_stop(p);

fs/bcachefs/rebalance.h

···
 int bch2_set_rebalance_needs_scan(struct bch_fs *, u64 inum);
 int bch2_set_fs_needs_rebalance(struct bch_fs *);
 
-static inline void rebalance_wakeup(struct bch_fs *c)
+static inline void bch2_rebalance_wakeup(struct bch_fs *c)
 {
 	struct task_struct *p;
 

fs/bcachefs/recovery.c

···
 #include "journal_seq_blacklist.h"
 #include "logged_ops.h"
 #include "move.h"
+#include "movinggc.h"
 #include "namei.h"
 #include "quota.h"
 #include "rebalance.h"
···
 	if (ret)
 		goto err;
 
-	set_bit(BCH_FS_accounting_replay_done, &c->flags);
-	bch2_journal_set_replay_done(&c->journal);
-
 	ret = bch2_fs_read_write_early(c);
 	if (ret)
 		goto err;
+
+	set_bit(BCH_FS_accounting_replay_done, &c->flags);
+	bch2_journal_set_replay_done(&c->journal);
 
 	for_each_member_device(c, ca) {
 		ret = bch2_dev_usage_init(ca, false);
···
 		goto err;
 
 	c->recovery_pass_done = BCH_RECOVERY_PASS_NR - 1;
+
+	bch2_copygc_wakeup(c);
+	bch2_rebalance_wakeup(c);
 
 	if (enabled_qtypes(c)) {
 		ret = bch2_fs_quota_read(c);

fs/bcachefs/recovery_passes.c

···
 #include "journal.h"
 #include "lru.h"
 #include "logged_ops.h"
+#include "movinggc.h"
 #include "rebalance.h"
 #include "recovery.h"
 #include "recovery_passes.h"
···
 	 */
 	c->opts.recovery_passes_exclude &= ~BCH_RECOVERY_PASS_set_may_go_rw;
 
-	while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns) && !ret) {
-		c->next_recovery_pass = c->curr_recovery_pass + 1;
+	spin_lock_irq(&c->recovery_pass_lock);
 
-		spin_lock_irq(&c->recovery_pass_lock);
+	while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns) && !ret) {
+		unsigned prev_done = c->recovery_pass_done;
 		unsigned pass = c->curr_recovery_pass;
 
+		c->next_recovery_pass = pass + 1;
+
 		if (c->opts.recovery_pass_last &&
-		    c->curr_recovery_pass > c->opts.recovery_pass_last) {
-			spin_unlock_irq(&c->recovery_pass_lock);
+		    c->curr_recovery_pass > c->opts.recovery_pass_last)
 			break;
-		}
 
-		if (!should_run_recovery_pass(c, pass)) {
-			c->curr_recovery_pass++;
-			c->recovery_pass_done = max(c->recovery_pass_done, pass);
+		if (should_run_recovery_pass(c, pass)) {
 			spin_unlock_irq(&c->recovery_pass_lock);
-			continue;
+			ret =   bch2_run_recovery_pass(c, pass) ?:
+				bch2_journal_flush(&c->journal);
+
+			if (!ret && !test_bit(BCH_FS_error, &c->flags))
+				bch2_clear_recovery_pass_required(c, pass);
+			spin_lock_irq(&c->recovery_pass_lock);
+
+			if (c->next_recovery_pass < c->curr_recovery_pass) {
+				/*
+				 * bch2_run_explicit_recovery_pass() was called: we
+				 * can't always catch -BCH_ERR_restart_recovery because
+				 * it may have been called from another thread (btree
+				 * node read completion)
+				 */
+				ret = 0;
+				c->recovery_passes_complete &= ~(~0ULL << c->curr_recovery_pass);
+			} else {
+				c->recovery_passes_complete |= BIT_ULL(pass);
+				c->recovery_pass_done = max(c->recovery_pass_done, pass);
+			}
 		}
-		spin_unlock_irq(&c->recovery_pass_lock);
 
-		ret =   bch2_run_recovery_pass(c, pass) ?:
-			bch2_journal_flush(&c->journal);
-
-		if (!ret && !test_bit(BCH_FS_error, &c->flags))
-			bch2_clear_recovery_pass_required(c, pass);
-
-		spin_lock_irq(&c->recovery_pass_lock);
-		if (c->next_recovery_pass < c->curr_recovery_pass) {
-			/*
-			 * bch2_run_explicit_recovery_pass() was called: we
-			 * can't always catch -BCH_ERR_restart_recovery because
-			 * it may have been called from another thread (btree
-			 * node read completion)
-			 */
-			ret = 0;
-			c->recovery_passes_complete &= ~(~0ULL << c->curr_recovery_pass);
-		} else {
-			c->recovery_passes_complete |= BIT_ULL(pass);
-			c->recovery_pass_done = max(c->recovery_pass_done, pass);
-		}
 		c->curr_recovery_pass = c->next_recovery_pass;
-		spin_unlock_irq(&c->recovery_pass_lock);
+
+		if (prev_done <= BCH_RECOVERY_PASS_check_snapshots &&
+		    c->recovery_pass_done > BCH_RECOVERY_PASS_check_snapshots) {
+			bch2_copygc_wakeup(c);
+			bch2_rebalance_wakeup(c);
+		}
 	}
+
+	spin_unlock_irq(&c->recovery_pass_lock);
 
 	return ret;
 }

fs/bcachefs/snapshot.c

···
 	u32 subvol = 0, s;
 
 	rcu_read_lock();
-	while (id) {
+	while (id && bch2_snapshot_exists(c, id)) {
 		s = snapshot_t(c, id)->subvol;
 
 		if (s && (!subvol || s < subvol))

fs/bcachefs/str_hash.h

···
 
 struct bch_hash_info {
 	u8			type;
-	struct unicode_map 	*cf_encoding;
+	struct unicode_map	*cf_encoding;
 	/*
 	 * For crc32 or crc64 string hashes the first key value of
 	 * the siphash_key (k0) is used as the key.
···
 static inline struct bch_hash_info
 bch2_hash_info_init(struct bch_fs *c, const struct bch_inode_unpacked *bi)
 {
-	/* XXX ick */
 	struct bch_hash_info info = {
 		.type = INODE_STR_HASH(bi),
 #ifdef CONFIG_UNICODE
-		.cf_encoding = !!(bi->bi_flags & BCH_INODE_casefolded) ? c->cf_encoding : NULL,
+		.cf_encoding = bch2_inode_casefold(c, bi) ? c->cf_encoding : NULL,
 #endif
 		.siphash_key = { .k0 = bi->bi_hash_seed }
 	};

fs/bcachefs/super-io.c

···
 		prt_str(&buf, ")");
 		bch2_fs_fatal_error(c, ": %s", buf.buf);
 		printbuf_exit(&buf);
-		return -BCH_ERR_sb_not_downgraded;
+		ret = -BCH_ERR_sb_not_downgraded;
+		goto out;
 	}
 
 	darray_for_each(online_devices, ca) {

fs/bcachefs/super.c

···
 	return ret;
 }
 
-static int bch2_fs_read_write_late(struct bch_fs *c)
-{
-	int ret;
-
-	/*
-	 * Data move operations can't run until after check_snapshots has
-	 * completed, and bch2_snapshot_is_ancestor() is available.
-	 *
-	 * Ideally we'd start copygc/rebalance earlier instead of waiting for
-	 * all of recovery/fsck to complete:
-	 */
-	ret = bch2_copygc_start(c);
-	if (ret) {
-		bch_err(c, "error starting copygc thread");
-		return ret;
-	}
-
-	ret = bch2_rebalance_start(c);
-	if (ret) {
-		bch_err(c, "error starting rebalance thread");
-		return ret;
-	}
-
-	return 0;
-}
-
 static int __bch2_fs_read_write(struct bch_fs *c, bool early)
 {
 	int ret;
···
 
 	clear_bit(BCH_FS_clean_shutdown, &c->flags);
 
-	/*
-	 * First journal write must be a flush write: after a clean shutdown we
-	 * don't read the journal, so the first journal write may end up
-	 * overwriting whatever was there previously, and there must always be
-	 * at least one non-flush write in the journal or recovery will fail:
-	 */
-	set_bit(JOURNAL_need_flush_write, &c->journal.flags);
-	set_bit(JOURNAL_running, &c->journal.flags);
-
 	__for_each_online_member(c, ca, BIT(BCH_MEMBER_STATE_rw), READ) {
 		bch2_dev_allocator_add(c, ca);
 		percpu_ref_reinit(&ca->io_ref[WRITE]);
 	}
 	bch2_recalc_capacity(c);
 
+	/*
+	 * First journal write must be a flush write: after a clean shutdown we
+	 * don't read the journal, so the first journal write may end up
+	 * overwriting whatever was there previously, and there must always be
+	 * at least one non-flush write in the journal or recovery will fail:
+	 */
+	spin_lock(&c->journal.lock);
+	set_bit(JOURNAL_need_flush_write, &c->journal.flags);
+	set_bit(JOURNAL_running, &c->journal.flags);
+	bch2_journal_space_available(&c->journal);
+	spin_unlock(&c->journal.lock);
+
 	ret = bch2_fs_mark_dirty(c);
 	if (ret)
 		goto err;
-
-	spin_lock(&c->journal.lock);
-	bch2_journal_space_available(&c->journal);
-	spin_unlock(&c->journal.lock);
 
 	ret = bch2_journal_reclaim_start(&c->journal);
 	if (ret)
···
 		atomic_long_inc(&c->writes[i]);
 	}
 #endif
-	if (!early) {
-		ret = bch2_fs_read_write_late(c);
-		if (ret)
-			goto err;
+
+	ret = bch2_copygc_start(c);
+	if (ret) {
+		bch_err_msg(c, ret, "error starting copygc thread");
+		goto err;
+	}
+
+	ret = bch2_rebalance_start(c);
+	if (ret) {
+		bch_err_msg(c, ret, "error starting rebalance thread");
+		goto err;
 	}
 
 	bch2_do_discards(c);
···
 
 	bch2_find_btree_nodes_exit(&c->found_btree_nodes);
 	bch2_free_pending_node_rewrites(c);
+	bch2_free_fsck_errs(c);
 	bch2_fs_accounting_exit(c);
 	bch2_fs_sb_errors_exit(c);
 	bch2_fs_counters_exit(c);
···
 	printbuf_exit(&p);
 }
 
+static bool bch2_fs_may_start(struct bch_fs *c)
+{
+	struct bch_dev *ca;
+	unsigned i, flags = 0;
+
+	if (c->opts.very_degraded)
+		flags |= BCH_FORCE_IF_DEGRADED|BCH_FORCE_IF_LOST;
+
+	if (c->opts.degraded)
+		flags |= BCH_FORCE_IF_DEGRADED;
+
+	if (!c->opts.degraded &&
+	    !c->opts.very_degraded) {
+		mutex_lock(&c->sb_lock);
+
+		for (i = 0; i < c->disk_sb.sb->nr_devices; i++) {
+			if (!bch2_member_exists(c->disk_sb.sb, i))
+				continue;
+
+			ca = bch2_dev_locked(c, i);
+
+			if (!bch2_dev_is_online(ca) &&
+			    (ca->mi.state == BCH_MEMBER_STATE_rw ||
+			     ca->mi.state == BCH_MEMBER_STATE_ro)) {
+				mutex_unlock(&c->sb_lock);
+				return false;
+			}
+		}
+		mutex_unlock(&c->sb_lock);
+	}
+
+	return bch2_have_enough_devs(c, bch2_online_devs(c), flags, true);
+}
+
 int bch2_fs_start(struct bch_fs *c)
 {
 	time64_t now = ktime_get_real_seconds();
 	int ret = 0;
 
 	print_mount_opts(c);
+
+	if (!bch2_fs_may_start(c))
+		return -BCH_ERR_insufficient_devices_to_start;
 
 	down_write(&c->state_lock);
 	mutex_lock(&c->sb_lock);
···
 	wake_up(&c->ro_ref_wait);
 
 	down_write(&c->state_lock);
-	if (c->opts.read_only) {
+	if (c->opts.read_only)
 		bch2_fs_read_only(c);
-	} else {
-		ret = !test_bit(BCH_FS_rw, &c->flags)
-			? bch2_fs_read_write(c)
-			: bch2_fs_read_write_late(c);
-	}
+	else if (!test_bit(BCH_FS_rw, &c->flags))
+		ret = bch2_fs_read_write(c);
 	up_write(&c->state_lock);
 
 err:
···
 
 	printbuf_exit(&name);
 
-	rebalance_wakeup(c);
+	bch2_rebalance_wakeup(c);
 	return 0;
 }
 
···
 	}
 }
 
-static bool bch2_fs_may_start(struct bch_fs *c)
-{
-	struct bch_dev *ca;
-	unsigned i, flags = 0;
-
-	if (c->opts.very_degraded)
-		flags |= BCH_FORCE_IF_DEGRADED|BCH_FORCE_IF_LOST;
-
-	if (c->opts.degraded)
-		flags |= BCH_FORCE_IF_DEGRADED;
-
-	if (!c->opts.degraded &&
-	    !c->opts.very_degraded) {
-		mutex_lock(&c->sb_lock);
-
-		for (i = 0; i < c->disk_sb.sb->nr_devices; i++) {
-			if (!bch2_member_exists(c->disk_sb.sb, i))
-				continue;
-
-			ca = bch2_dev_locked(c, i);
-
-			if (!bch2_dev_is_online(ca) &&
-			    (ca->mi.state == BCH_MEMBER_STATE_rw ||
-			     ca->mi.state == BCH_MEMBER_STATE_ro)) {
-				mutex_unlock(&c->sb_lock);
-				return false;
-			}
-		}
-		mutex_unlock(&c->sb_lock);
-	}
-
-	return bch2_have_enough_devs(c, bch2_online_devs(c), flags, true);
-}
-
 static void __bch2_dev_read_only(struct bch_fs *c, struct bch_dev *ca)
 {
 	bch2_dev_io_ref_stop(ca, WRITE);
···
 	if (new_state == BCH_MEMBER_STATE_rw)
 		__bch2_dev_read_write(c, ca);
 
-	rebalance_wakeup(c);
+	bch2_rebalance_wakeup(c);
 
 	return ret;
 }
···
 		}
 	}
 	up_write(&c->state_lock);
-
-	if (!bch2_fs_may_start(c)) {
-		ret = -BCH_ERR_insufficient_devices_to_start;
-		goto err_print;
-	}
 
 	if (!c->opts.nostart) {
 		ret = bch2_fs_start(c);

fs/bcachefs/sysfs.c

···
 		bch2_set_rebalance_needs_scan(c, 0);
 
 	if (v && id == Opt_rebalance_enabled)
-		rebalance_wakeup(c);
+		bch2_rebalance_wakeup(c);
 
-	if (v && id == Opt_copygc_enabled &&
-	    c->copygc_thread)
-		wake_up_process(c->copygc_thread);
+	if (v && id == Opt_copygc_enabled)
+		bch2_copygc_wakeup(c);
 
 	if (id == Opt_discard && !ca) {
 		mutex_lock(&c->sb_lock);

fs/bcachefs/tests.c

···
  */
 static int test_peek_end(struct bch_fs *c, u64 nr)
 {
+	delete_test_keys(c);
+
 	struct btree_trans *trans = bch2_trans_get(c);
 	struct btree_iter iter;
 	struct bkey_s_c k;
···
 
 static int test_peek_end_extents(struct bch_fs *c, u64 nr)
 {
+	delete_test_keys(c);
+
 	struct btree_trans *trans = bch2_trans_get(c);
 	struct btree_iter iter;
 	struct bkey_s_c k;

fs/bcachefs/util.h

···
 		*--dst = *src++;
 }
 
+#define set_flags(_map, _in, _out)					\
+do {									\
+	unsigned _i;							\
+									\
+	for (_i = 0; _i < ARRAY_SIZE(_map); _i++)			\
+		if ((_in) & (1 << _i))					\
+			(_out) |= _map[_i];				\
+		else							\
+			(_out) &= ~_map[_i];				\
+} while (0)
+
+#define map_flags(_map, _in)						\
+({									\
+	unsigned _out = 0;						\
+									\
+	set_flags(_map, _in, _out);					\
+	_out;								\
+})
+
+#define map_flags_rev(_map, _in)					\
+({									\
+	unsigned _i, _out = 0;						\
+									\
+	for (_i = 0; _i < ARRAY_SIZE(_map); _i++)			\
+		if ((_in) & _map[_i]) {					\
+			(_out) |= 1 << _i;				\
+			(_in) &= ~_map[_i];				\
+		}							\
+	(_out);								\
+})
+
+#define map_defined(_map)						\
+({									\
+	unsigned _in = ~0;						\
+									\
+	map_flags_rev(_map, _in);					\
+})
+
 #endif /* _BCACHEFS_UTIL_H */

fs/btrfs/file.c

···
 	 * will always return true.
 	 * So here we need to do extra page alignment for
 	 * filemap_range_has_page().
+	 *
+	 * And do not decrease page_lockend right now, as it can be 0.
 	 */
 	const u64 page_lockstart = round_up(lockstart, PAGE_SIZE);
-	const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE) - 1;
+	const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE);
 
 	while (1) {
 		truncate_pagecache_range(inode, lockstart, lockend);
 
 		lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			    cached_state);
+		/* The same page or adjacent pages. */
+		if (page_lockend <= page_lockstart)
+			break;
 		/*
 		 * We can't have ordered extents in the range, nor dirty/writeback
 		 * pages, because we have locked the inode's VFS lock in exclusive
···
 		 * we do, unlock the range and retry.
 		 */
 		if (!filemap_range_has_page(inode->i_mapping, page_lockstart,
-					    page_lockend))
+					    page_lockend - 1))
 			break;
 
 		unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,

fs/btrfs/relocation.c

···
 	if (ret) {
 		if (inode)
 			iput(&inode->vfs_inode);
-		inode = ERR_PTR(ret);
+		return ERR_PTR(ret);
 	}
 	return &inode->vfs_inode;
 }

fs/btrfs/subpage.c

···
 			   btrfs_blocks_per_folio(fs_info, folio);	\
 									\
 	btrfs_subpage_assert(fs_info, folio, start, len);		\
-	__start_bit = offset_in_page(start) >> fs_info->sectorsize_bits; \
+	__start_bit = offset_in_folio(folio, start) >> fs_info->sectorsize_bits; \
 	__start_bit += blocks_per_folio * btrfs_bitmap_nr_##name;	\
 	__start_bit;							\
 })
···
 				btrfs_blocks_per_folio(fs_info, folio);	\
 	const struct btrfs_subpage *subpage = folio_get_private(folio);	\
 									\
-	ASSERT(blocks_per_folio < BITS_PER_LONG);			\
+	ASSERT(blocks_per_folio <= BITS_PER_LONG);			\
 	*dst = bitmap_read(subpage->bitmaps,				\
 			   blocks_per_folio * btrfs_bitmap_nr_##name,	\
 			   blocks_per_folio);				\

fs/btrfs/tree-checker.c

···
 		btrfs_err(fs_info,
 "tree level mismatch detected, bytenr=%llu level expected=%u has=%u",
 			  eb->start, check->level, found_level);
-		return -EIO;
+		return -EUCLEAN;
 	}
 
 	if (!check->has_first_key)

fs/btrfs/zoned.c

···
 
 static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 				struct zone_info *info, unsigned long *active,
-				struct btrfs_chunk_map *map)
+				struct btrfs_chunk_map *map, bool new)
 {
 	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
 	struct btrfs_device *device;
···
 		return 0;
 	}
 
+	ASSERT(!new || btrfs_dev_is_empty_zone(device, info->physical));
+
 	/* This zone will be used for allocation, so mark this zone non-empty. */
 	btrfs_dev_clear_zone_empty(device, info->physical);
 
···
 	 * to determine the allocation offset within the zone.
 	 */
 	WARN_ON(!IS_ALIGNED(info->physical, fs_info->zone_size));
+
+	if (new) {
+		sector_t capacity;
+
+		capacity = bdev_zone_capacity(device->bdev, info->physical >> SECTOR_SHIFT);
+		up_read(&dev_replace->rwsem);
+		info->alloc_offset = 0;
+		info->capacity = capacity << SECTOR_SHIFT;
+
+		return 0;
+	}
+
 	nofs_flag = memalloc_nofs_save();
 	ret = btrfs_get_dev_zone(device, info->physical, &zone);
 	memalloc_nofs_restore(nofs_flag);
···
 	}
 
 	for (i = 0; i < map->num_stripes; i++) {
-		ret = btrfs_load_zone_info(fs_info, i, &zone_info[i], active, map);
+		ret = btrfs_load_zone_info(fs_info, i, &zone_info[i], active, map, new);
 		if (ret)
 			goto out;
 
···
 		 * stripe.
 		 */
 		cache->alloc_offset = cache->zone_capacity;
-		ret = 0;
 	}
 
 out:

fs/buffer.c

···
 }
 EXPORT_SYMBOL(end_buffer_write_sync);
 
-/*
- * Various filesystems appear to want __find_get_block to be non-blocking.
- * But it's the page lock which protects the buffers.  To get around this,
- * we get exclusion from try_to_free_buffers with the blockdev mapping's
- * i_private_lock.
- *
- * Hack idea: for the blockdev mapping, i_private_lock contention
- * may be quite high.  This code could TryLock the page, and if that
- * succeeds, there is no need to take i_private_lock.
- */
 static struct buffer_head *
-__find_get_block_slow(struct block_device *bdev, sector_t block)
+__find_get_block_slow(struct block_device *bdev, sector_t block, bool atomic)
 {
 	struct address_space *bd_mapping = bdev->bd_mapping;
 	const int blkbits = bd_mapping->host->i_blkbits;
···
 	if (IS_ERR(folio))
 		goto out;
 
-	spin_lock(&bd_mapping->i_private_lock);
+	/*
+	 * Folio lock protects the buffers. Callers that cannot block
+	 * will fallback to serializing vs try_to_free_buffers() via
+	 * the i_private_lock.
+	 */
+	if (atomic)
+		spin_lock(&bd_mapping->i_private_lock);
+	else
+		folio_lock(folio);
+
 	head = folio_buffers(folio);
 	if (!head)
 		goto out_unlock;
+	/*
+	 * Upon a noref migration, the folio lock serializes here;
+	 * otherwise bail.
+	 */
+	if (test_bit_acquire(BH_Migrate, &head->b_state)) {
+		WARN_ON(!atomic);
+		goto out_unlock;
+	}
+
 	bh = head;
 	do {
 		if (!buffer_mapped(bh))
···
 		       1 << blkbits);
 	}
 out_unlock:
-	spin_unlock(&bd_mapping->i_private_lock);
+	if (atomic)
+		spin_unlock(&bd_mapping->i_private_lock);
+	else
+		folio_unlock(folio);
 	folio_put(folio);
 out:
 	return ret;
···
 void write_boundary_block(struct block_device *bdev,
 			sector_t bblock, unsigned blocksize)
 {
-	struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
+	struct buffer_head *bh;
+
+	bh = __find_get_block_nonatomic(bdev, bblock + 1, blocksize);
 	if (bh) {
 		if (buffer_dirty(bh))
 			write_dirty_buffer(bh, 0);
···
 /*
  * Perform a pagecache lookup for the matching buffer.  If it's there, refresh
  * it in the LRU and mark it as accessed.  If it is not present then return
- * NULL
+ * NULL. Atomic context callers may also return NULL if the buffer is being
+ * migrated; similarly the page is not marked accessed either.
  */
-struct buffer_head *
-__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
+static struct buffer_head *
+find_get_block_common(struct block_device *bdev, sector_t block,
+			unsigned size, bool atomic)
 {
 	struct buffer_head *bh = lookup_bh_lru(bdev, block, size);
 
 	if (bh == NULL) {
 		/* __find_get_block_slow will mark the page accessed */
-		bh = __find_get_block_slow(bdev, block);
+		bh = __find_get_block_slow(bdev, block, atomic);
 		if (bh)
 			bh_lru_install(bh);
 	} else
···
 
 	return bh;
 }
+
+struct buffer_head *
+__find_get_block(struct block_device *bdev, sector_t block, unsigned size)
+{
+	return find_get_block_common(bdev, block, size, true);
+}
 EXPORT_SYMBOL(__find_get_block);
+
+/* same as __find_get_block() but allows sleeping contexts */
+struct buffer_head *
+__find_get_block_nonatomic(struct block_device *bdev, sector_t block,
+			   unsigned size)
+{
+	return find_get_block_common(bdev, block, size, false);
+}
+EXPORT_SYMBOL(__find_get_block_nonatomic);
 
 /**
  * bdev_getblk - Get a buffer_head in a block device's buffer cache.
···
 struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
 		unsigned size, gfp_t gfp)
 {
-	struct buffer_head *bh = __find_get_block(bdev, block, size);
+	struct buffer_head *bh;
+
+	if (gfpflags_allow_blocking(gfp))
+		bh = __find_get_block_nonatomic(bdev, block, size);
+	else
+		bh = __find_get_block(bdev, block, size);
 
 	might_alloc(gfp);
 	if (bh)

fs/ceph/inode.c

···
 
 	/* Try to writeback the dirty pagecaches */
 	if (issued & (CEPH_CAP_FILE_BUFFER)) {
-		loff_t lend = orig_pos + CEPH_FSCRYPT_BLOCK_SHIFT - 1;
+		loff_t lend = orig_pos + CEPH_FSCRYPT_BLOCK_SIZE - 1;
 
 		ret = filemap_write_and_wait_range(inode->i_mapping,
 						   orig_pos, lend);

fs/ext4/ialloc.c

···
 	if (!bh || !buffer_uptodate(bh))
 		/*
 		 * If the block is not in the buffer cache, then it
-		 * must have been written out.
+		 * must have been written out, or, most unlikely, is
+		 * being migrated - false failure should be OK here.
 		 */
 		goto out;
 

fs/ext4/mballoc.c

···
 		for (i = 0; i < count; i++) {
 			cond_resched();
 			if (is_metadata)
-				bh = sb_find_get_block(inode->i_sb, block + i);
+				bh = sb_find_get_block_nonatomic(inode->i_sb,
+								 block + i);
 			ext4_forget(handle, is_metadata, inode, bh, block + i);
 		}
 	}

fs/file.c

···
 
 #include "internal.h"
 
-bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
+static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
 {
 	/*
 	 * If the reference count was already in the dead zone, then this

fs/jbd2/revoke.c

···
 	bh = bh_in;
 
 	if (!bh) {
-		bh = __find_get_block(bdev, blocknr, journal->j_blocksize);
+		bh = __find_get_block_nonatomic(bdev, blocknr,
+						journal->j_blocksize);
 		if (bh)
 			BUFFER_TRACE(bh, "found on hash");
 	}
···
 
 		/* If there is a different buffer_head lying around in
 		 * memory anywhere... */
-		bh2 = __find_get_block(bdev, blocknr, journal->j_blocksize);
+		bh2 = __find_get_block_nonatomic(bdev, blocknr,
+						 journal->j_blocksize);
 		if (bh2) {
 			/* ... and it has RevokeValid status... */
 			if (bh2 != bh && buffer_revokevalid(bh2))
···
 	 * state machine will get very upset later on. */
 	if (need_cancel) {
 		struct buffer_head *bh2;
-		bh2 = __find_get_block(bh->b_bdev, bh->b_blocknr, bh->b_size);
+		bh2 = __find_get_block_nonatomic(bh->b_bdev, bh->b_blocknr,
+						 bh->b_size);
 		if (bh2) {
 			if (bh2 != bh)
 				clear_buffer_revoked(bh2);
···
 			struct jbd2_revoke_record_s *record;
 			struct buffer_head *bh;
 			record = (struct jbd2_revoke_record_s *)list_entry;
-			bh = __find_get_block(journal->j_fs_dev,
-					      record->blocknr,
-					      journal->j_blocksize);
+			bh = __find_get_block_nonatomic(journal->j_fs_dev,
+							record->blocknr,
+							journal->j_blocksize);
 			if (bh) {
 				clear_buffer_revoked(bh);
 				__brelse(bh);

fs/namespace.c

···
 	struct vfsmount *mnt = path->mnt;
 	struct dentry *dentry;
 	struct mountpoint *mp = ERR_PTR(-ENOENT);
+	struct path under = {};
 
 	for (;;) {
-		struct mount *m;
+		struct mount *m = real_mount(mnt);
 
 		if (beneath) {
-			m = real_mount(mnt);
+			path_put(&under);
 			read_seqlock_excl(&mount_lock);
-			dentry = dget(m->mnt_mountpoint);
+			under.mnt = mntget(&m->mnt_parent->mnt);
+			under.dentry = dget(m->mnt_mountpoint);
 			read_sequnlock_excl(&mount_lock);
+			dentry = under.dentry;
 		} else {
 			dentry = path->dentry;
 		}
 
 		inode_lock(dentry->d_inode);
-		if (unlikely(cant_mount(dentry))) {
-			inode_unlock(dentry->d_inode);
-			goto out;
-		}
-
 		namespace_lock();
 
-		if (beneath && (!is_mounted(mnt) || m->mnt_mountpoint != dentry)) {
+		if (unlikely(cant_mount(dentry) || !is_mounted(mnt)))
+			break;		// not to be mounted on
+
+		if (beneath && unlikely(m->mnt_mountpoint != dentry ||
+				        &m->mnt_parent->mnt != under.mnt)) {
 			namespace_unlock();
 			inode_unlock(dentry->d_inode);
-			goto out;
+			continue;	// got moved
 		}
 
 		mnt = lookup_mnt(path);
-		if (likely(!mnt))
+		if (unlikely(mnt)) {
+			namespace_unlock();
+			inode_unlock(dentry->d_inode);
+			path_put(path);
+			path->mnt = mnt;
+			path->dentry = dget(mnt->mnt_root);
+			continue;	// got overmounted
+		}
+		mp = get_mountpoint(dentry);
+		if (IS_ERR(mp))
 			break;
-
-		namespace_unlock();
-		inode_unlock(dentry->d_inode);
-		if (beneath)
-			dput(dentry);
-		path_put(path);
-		path->mnt = mnt;
-		path->dentry = dget(mnt->mnt_root);
+		if (beneath) {
+			/*
+			 * @under duplicates the references that will stay
+			 * at least until namespace_unlock(), so the path_put()
+			 * below is safe (and OK to do under namespace_lock -
+			 * we are not dropping the final references here).
+			 */
+			path_put(&under);
+		}
+		return mp;
 	}
-
-	mp = get_mountpoint(dentry);
-	if (IS_ERR(mp)) {
-		namespace_unlock();
-		inode_unlock(dentry->d_inode);
-	}
-
-out:
+	namespace_unlock();
+	inode_unlock(dentry->d_inode);
 	if (beneath)
-		dput(dentry);
-
+		path_put(&under);
 	return mp;
 }
 
···
 
 static void unlock_mount(struct mountpoint *where)
 {
-	struct dentry *dentry = where->m_dentry;
-
+	inode_unlock(where->m_dentry->d_inode);
 	read_seqlock_excl(&mount_lock);
 	put_mountpoint(where);
 	read_sequnlock_excl(&mount_lock);
-
 	namespace_unlock();
-	inode_unlock(dentry->d_inode);
 }
 
 static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)

fs/ocfs2/journal.c

···
 		}
 
 		for (i = 0; i < p_blocks; i++, p_blkno++) {
-			bh = __find_get_block(osb->sb->s_bdev, p_blkno,
+			bh = __find_get_block_nonatomic(osb->sb->s_bdev, p_blkno,
 					osb->sb->s_blocksize);
 			/* block not cached. */
 			if (!bh)

fs/splice.c

···
  * here if set to avoid blocking other users of this pipe if splice is
  * being done on it.
  */
-static noinline void noinline pipe_clear_nowait(struct file *file)
+static noinline void pipe_clear_nowait(struct file *file)
 {
 	fmode_t fmode = READ_ONCE(file->f_mode);
 

fs/xattr.c

···
 		return error;
 
 	filename = getname_maybe_null(pathname, at_flags);
-	if (!filename) {
+	if (!filename && dfd >= 0) {
 		CLASS(fd, f)(dfd);
 		if (fd_empty(f))
 			error = -EBADF;
···
 		return error;
 
 	filename = getname_maybe_null(pathname, at_flags);
-	if (!filename) {
+	if (!filename && dfd >= 0) {
 		CLASS(fd, f)(dfd);
 		if (fd_empty(f))
 			return -EBADF;

fs/xfs/xfs_zone_gc.c

···
 xfs_zoned_need_gc(
 	struct xfs_mount	*mp)
 {
-	s64			available, free;
+	s64			available, free, threshold;
+	s32			remainder;
 
 	if (!xfs_group_marked(mp, XG_TYPE_RTG, XFS_RTG_RECLAIMABLE))
 		return false;
···
 		return true;
 
 	free = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS);
-	if (available < mult_frac(free, mp->m_zonegc_low_space, 100))
+
+	threshold = div_s64_rem(free, 100, &remainder);
+	threshold = threshold * mp->m_zonegc_low_space +
+		    remainder * div_s64(mp->m_zonegc_low_space, 100);
+
+	if (available < threshold)
 		return true;
 
 	return false;

include/cxl/features.h

···
 #ifdef CONFIG_CXL_FEATURES
 inline struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds);
 int devm_cxl_setup_features(struct cxl_dev_state *cxlds);
-int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd);
+int devm_cxl_setup_fwctl(struct device *host, struct cxl_memdev *cxlmd);
 #else
 static inline struct cxl_features_state *to_cxlfs(struct cxl_dev_state *cxlds)
 {
···
 	return -EOPNOTSUPP;
 }
 
-static inline int devm_cxl_setup_fwctl(struct cxl_memdev *cxlmd)
+static inline int devm_cxl_setup_fwctl(struct device *host,
+				       struct cxl_memdev *cxlmd)
 {
 	return -EOPNOTSUPP;
 }

include/linux/blkdev.h

···
 		(q->limits.features & BLK_FEAT_ZONED);
 }
 
-#ifdef CONFIG_BLK_DEV_ZONED
-static inline unsigned int disk_nr_zones(struct gendisk *disk)
-{
-	return disk->nr_zones;
-}
-bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
-#else /* CONFIG_BLK_DEV_ZONED */
-static inline unsigned int disk_nr_zones(struct gendisk *disk)
-{
-	return 0;
-}
-static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
-{
-	return false;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
-
 static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 {
 	if (!blk_queue_is_zoned(disk->queue))
 		return 0;
 	return sector >> ilog2(disk->queue->limits.chunk_sectors);
-}
-
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	return disk_nr_zones(bdev->bd_disk);
 }
 
 static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
···
 {
 	return bdev_nr_sectors(sb->s_bdev) >>
 		(sb->s_blocksize_bits - SECTOR_SHIFT);
+}
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
+{
+	return disk->nr_zones;
+}
+bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
+
+/**
+ * disk_zone_capacity - returns the zone capacity of zone containing @sector
+ * @disk:	disk to work with
+ * @sector:	sector number within the querying zone
+ *
+ * Returns the zone capacity of a zone containing @sector. @sector can be any
+ * sector in the zone.
+ */
+static inline unsigned int disk_zone_capacity(struct gendisk *disk,
+					      sector_t sector)
+{
+	sector_t zone_sectors = disk->queue->limits.chunk_sectors;
+
+	if (sector + zone_sectors >= get_capacity(disk))
+		return disk->last_zone_capacity;
+	return disk->zone_capacity;
+}
+static inline unsigned int bdev_zone_capacity(struct block_device *bdev,
+					      sector_t pos)
+{
+	return disk_zone_capacity(bdev->bd_disk, pos);
+}
+#else /* CONFIG_BLK_DEV_ZONED */
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
+{
+	return 0;
+}
+static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
+{
+	return false;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
+
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
+{
+	return disk_nr_zones(bdev->bd_disk);
 }
 
 int bdev_disk_changed(struct gendisk *disk, bool invalidate);
···
 	return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev);
 }
 
+int bdev_validate_blocksize(struct block_device *bdev, int block_size);
 int set_blocksize(struct file *file, int size);
 
 int lookup_bdev(const char *pathname, dev_t *dev);
···
 int bd_prepare_to_claim(struct block_device *bdev, void *holder,
 		const struct blk_holder_ops *hops);
 void bd_abort_claiming(struct block_device *bdev, void *holder);
-
-/* just for blk-cgroup, don't use elsewhere */
-struct block_device *blkdev_get_no_open(dev_t dev);
-void blkdev_put_no_open(struct block_device *bdev);
 
 struct block_device *I_BDEV(struct inode *inode);
 struct block_device *file_bdev(struct file *bdev_file);

include/linux/buffer_head.h

···
 	BH_Meta,	/* Buffer contains metadata */
 	BH_Prio,	/* Buffer should be submitted with REQ_PRIO */
 	BH_Defer_Completion, /* Defer AIO completion to workqueue */
+	BH_Migrate,     /* Buffer is being migrated (norefs) */
 
 	BH_PrivateStart,/* not a state bit, but the first bit available
 			 * for private allocation by other entities
···
 wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
 struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
 			unsigned size);
+struct buffer_head *__find_get_block_nonatomic(struct block_device *bdev,
+			sector_t block, unsigned size);
 struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
 		unsigned size, gfp_t gfp);
 void __brelse(struct buffer_head *);
···
 sb_find_get_block(struct super_block *sb, sector_t block)
 {
 	return __find_get_block(sb->s_bdev, block, sb->s_blocksize);
+}
+
+static inline struct buffer_head *
+sb_find_get_block_nonatomic(struct super_block *sb, sector_t block)
+{
+	return __find_get_block_nonatomic(sb->s_bdev, block, sb->s_blocksize);
 }
 
 static inline void

include/linux/ceph/osd_client.h

···
 					struct page **pages, u64 length,
 					u32 alignment, bool pages_from_pool,
 					bool own_pages);
-extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *,
-					unsigned int which,
-					struct ceph_pagelist *pagelist);
 #ifdef CONFIG_BLOCK
 void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
 				    unsigned int which,
···
 void osd_req_op_extent_osd_iter(struct ceph_osd_request *osd_req,
 				unsigned int which, struct iov_iter *iter);
 
-extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *,
-					unsigned int which,
-					struct ceph_pagelist *pagelist);
 extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *,
 					unsigned int which,
 					struct page **pages, u64 length,

include/linux/dma-mapping.h

···
 #else
 #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME)
 #define DEFINE_DMA_UNMAP_LEN(LEN_NAME)
-#define dma_unmap_addr(PTR, ADDR_NAME)           (0)
-#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL)  do { } while (0)
-#define dma_unmap_len(PTR, LEN_NAME)             (0)
-#define dma_unmap_len_set(PTR, LEN_NAME, VAL)    do { } while (0)
+#define dma_unmap_addr(PTR, ADDR_NAME)           \
+	({ typeof(PTR) __p __maybe_unused = PTR; 0; })
+#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL)  \
+	do { typeof(PTR) __p __maybe_unused = PTR; } while (0)
+#define dma_unmap_len(PTR, LEN_NAME)             \
+	({ typeof(PTR) __p __maybe_unused = PTR; 0; })
+#define dma_unmap_len_set(PTR, LEN_NAME, VAL)    \
+	do { typeof(PTR) __p __maybe_unused = PTR; } while (0)
 #endif
 
 #endif /* _LINUX_DMA_MAPPING_H */

include/linux/file_ref.h

···
 	atomic_long_set(&ref->refcnt, cnt - 1);
 }
 
-bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt);
 bool __file_ref_put(file_ref_t *ref, unsigned long cnt);
 
 /**
···
  */
 static __always_inline __must_check bool file_ref_put_close(file_ref_t *ref)
 {
-	long old, new;
+	long old;
 
 	old = atomic_long_read(&ref->refcnt);
-	do {
-		if (unlikely(old < 0))
-			return __file_ref_put_badval(ref, old);
-
-		if (old == FILE_REF_ONEREF)
-			new = FILE_REF_DEAD;
-		else
-			new = old - 1;
-	} while (!atomic_long_try_cmpxchg(&ref->refcnt, &old, new));
-
-	return new == FILE_REF_DEAD;
+	if (likely(old == FILE_REF_ONEREF)) {
+		if (likely(atomic_long_try_cmpxchg(&ref->refcnt, &old, FILE_REF_DEAD)))
+			return true;
+	}
+	return file_ref_put(ref);
 }
 
 /**

include/linux/fwnode.h

···
 /*
  * fwnode.h - Firmware device node object handle type definition.
  *
+ * This header file provides low-level data types and definitions for firmware
+ * and device property providers. The respective API header files supplied by
+ * them should contain all of the requisite data types and definitions for end
+ * users, so including it directly should not be necessary.
+ *
  * Copyright (C) 2015, Intel Corporation
  * Author: Rafael J. Wysocki <[e-mail]>
  */

include/linux/local_lock_internal.h

···
 		l = (local_lock_t *)this_cpu_ptr(lock);			\
 		tl = (local_trylock_t *)l;				\
 		_Generic((lock),					\
-			local_trylock_t *: ({				\
+			__percpu local_trylock_t *: ({			\
 				lockdep_assert(tl->acquired == 0);	\
 				WRITE_ONCE(tl->acquired, 1);		\
 			}),						\
-			default:(void)0);				\
+			__percpu local_lock_t *: (void)0);		\
 		local_lock_acquire(l);					\
 	} while (0)
 
···
 		tl = (local_trylock_t *)l;				\
 		local_lock_release(l);					\
 		_Generic((lock),					\
-			local_trylock_t *: ({				\
+			__percpu local_trylock_t *: ({			\
 				lockdep_assert(tl->acquired == 1);	\
 				WRITE_ONCE(tl->acquired, 0);		\
 			}),						\
-			default:(void)0);				\
+			__percpu local_lock_t *: (void)0);		\
 	} while (0)
 
 #define __local_unlock(lock)					\

include/linux/phylink.h

···
 		phy_interface_t iface);
 
 /**
- * mac_link_down() - take the link down
+ * mac_link_down() - notification that the link has gone down
  * @config: a pointer to a &struct phylink_config.
  * @mode: link autonegotiation mode
  * @interface: link &typedef phy_interface_t mode
  *
- * If @mode is not an in-band negotiation mode (as defined by
- * phylink_autoneg_inband()), force the link down and disable any
- * Energy Efficient Ethernet MAC configuration. Interface type
- * selection must be done in mac_config().
+ * Notifies the MAC that the link has gone down. This will not be called
+ * unless mac_link_up() has been previously called.
+ *
+ * The MAC should stop processing packets for transmission and reception.
+ * phylink will have called netif_carrier_off() to notify the networking
+ * stack that the link has gone down, so MAC drivers should not make this
+ * call.
+ *
+ * If @mode is %MLO_AN_INBAND, then this function must not prevent the
+ * link coming up.
  */
 void mac_link_down(struct phylink_config *config, unsigned int mode,
 		   phy_interface_t interface);
 
 /**
- * mac_link_up() - allow the link to come up
+ * mac_link_up() - notification that the link has come up
  * @config: a pointer to a &struct phylink_config.
- * @phy: any attached phy
+ * @phy: any attached phy (deprecated - please use LPI interfaces)
  * @mode: link autonegotiation mode
  * @interface: link &typedef phy_interface_t mode
  * @speed: link speed
···
  * @tx_pause: link transmit pause enablement status
  * @rx_pause: link receive pause enablement status
  *
- * Configure the MAC for an established link.
+ * Notifies the MAC that the link has come up, and the parameters of the
+ * link as seen from the MACs point of view. If mac_link_up() has been
+ * called previously, there will be an intervening call to mac_link_down()
+ * before this method will be subsequently called.
  *
  * @speed, @duplex, @tx_pause and @rx_pause indicate the finalised link
  * settings, and should be used to configure the MAC block appropriately
···
  * that the user wishes to override the pause settings, and this should
  * be allowed when considering the implementation of this method.
  *
- * If in-band negotiation mode is disabled, allow the link to come up. If
- * @phy is non-%NULL, configure Energy Efficient Ethernet by calling
- * phy_init_eee() and perform appropriate MAC configuration for EEE.
+ * Once configured, the MAC may begin to process packets for transmission
+ * and reception.
+ *
  * Interface type selection must be done in mac_config().
  */
 void mac_link_up(struct phylink_config *config, struct phy_device *phy,

include/linux/virtio.h

···
  *    occurs.
  * @reset_done: optional function to call after transport specific reset
  *    operation has finished.
+ * @shutdown: synchronize with the device on shutdown. If provided, replaces
+ *    the virtio core implementation.
  */
 struct virtio_driver {
 	struct device_driver driver;
···
 	int (*restore)(struct virtio_device *dev);
 	int (*reset_prepare)(struct virtio_device *dev);
 	int (*reset_done)(struct virtio_device *dev);
+	void (*shutdown)(struct virtio_device *dev);
 };
 
 #define drv_to_virtio(__drv)	container_of_const(__drv, struct virtio_driver, driver)

include/uapi/linux/landlock.h

···
 	__u64 scoped;
 };
 
-/*
- * sys_landlock_create_ruleset() flags:
+/**
+ * DOC: landlock_create_ruleset_flags
  *
- * - %LANDLOCK_CREATE_RULESET_VERSION: Get the highest supported Landlock ABI
- *   version.
- * - %LANDLOCK_CREATE_RULESET_ERRATA: Get a bitmask of fixed issues.
+ * **Flags**
+ *
+ * %LANDLOCK_CREATE_RULESET_VERSION
+ *     Get the highest supported Landlock ABI version (starting at 1).
+ *
+ * %LANDLOCK_CREATE_RULESET_ERRATA
+ *     Get a bitmask of fixed issues for the current Landlock ABI version.
  */
 /* clang-format off */
 #define LANDLOCK_CREATE_RULESET_VERSION			(1U << 0)
 #define LANDLOCK_CREATE_RULESET_ERRATA			(1U << 1)
 /* clang-format on */
 
-/*
- * sys_landlock_restrict_self() flags:
+/**
+ * DOC: landlock_restrict_self_flags
  *
- * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF: Do not create any log related to the
- *   enforced restrictions.  This should only be set by tools launching unknown
- *   or untrusted programs (e.g. a sandbox tool, container runtime, system
- *   service manager).  Because programs sandboxing themselves should fix any
- *   denied access, they should not set this flag to be aware of potential
- *   issues reported by system's logs (i.e. audit).
- * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON: Explicitly ask to continue
- *   logging denied access requests even after an :manpage:`execve(2)` call.
- *   This flag should only be set if all the programs than can legitimately be
- *   executed will not try to request a denied access (which could spam audit
- *   logs).
- * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF: Do not create any log related
- *   to the enforced restrictions coming from future nested domains created by
- *   the caller or its descendants.  This should only be set according to a
- *   runtime configuration (i.e. not hardcoded) by programs launching other
- *   unknown or untrusted programs that may create their own Landlock domains
- *   and spam logs.  The main use case is for container runtimes to enable users
- *   to mute buggy sandboxed programs for a specific container image.  Other use
- *   cases include sandboxer tools and init systems.  Unlike
- *   %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF,
- *   %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF does not impact the requested
- *   restriction (if any) but only the future nested domains.
+ * **Flags**
+ *
+ * By default, denied accesses originating from programs that sandbox themselves
+ * are logged via the audit subsystem. Such events typically indicate unexpected
+ * behavior, such as bugs or exploitation attempts. However, to avoid excessive
+ * logging, access requests denied by a domain not created by the originating
+ * program are not logged by default. The rationale is that programs should know
+ * their own behavior, but not necessarily the behavior of other programs.  This
+ * default configuration is suitable for most programs that sandbox themselves.
+ * For specific use cases, the following flags allow programs to modify this
+ * default logging behavior.
+ *
+ * The %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF and
+ * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON flags apply to the newly created
+ * Landlock domain.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
+ *     Disables logging of denied accesses originating from the thread creating
+ *     the Landlock domain, as well as its children, as long as they continue
+ *     running the same executable code (i.e., without an intervening
+ *     :manpage:`execve(2)` call). This is intended for programs that execute
+ *     unknown code without invoking :manpage:`execve(2)`, such as script
+ *     interpreters. Programs that only sandbox themselves should not set this
+ *     flag, so users can be notified of unauthorized access attempts via system
+ *     logs.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
+ *     Enables logging of denied accesses after an :manpage:`execve(2)` call,
+ *     providing visibility into unauthorized access attempts by newly executed
+ *     programs within the created Landlock domain. This flag is recommended
+ *     only when all potential executables in the domain are expected to comply
+ *     with the access restrictions, as excessive audit log entries could make
+ *     it more difficult to identify critical events.
+ *
+ * %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
+ *     Disables logging of denied accesses originating from nested Landlock
+ *     domains created by the caller or its descendants. This flag should be set
+ *     according to runtime configuration, not hardcoded, to avoid suppressing
+ *     important security events. It is useful for container runtimes or
+ *     sandboxing tools that may launch programs which themselves create
+ *     Landlock domains and could otherwise generate excessive logs. Unlike
+ *     ``LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF``, this flag only affects
+ *     future nested domains, not the one being created. It can also be used
+ *     with a @ruleset_fd value of -1 to mute subdomain logs without creating a
+ *     domain.
  */
 /* clang-format off */
 #define LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF		(1U << 0)

include/uapi/linux/vhost.h

···
 
 /* Set current process as the (exclusive) owner of this file descriptor.  This
  * must be called before any other vhost command.  Further calls to
- * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+ * VHOST_SET_OWNER fail until VHOST_RESET_OWNER is called. */
 #define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
 /* Give up ownership, and reset the device to default values.
- * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+ * Allows subsequent call to VHOST_SET_OWNER to succeed. */
 #define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
 
 /* Set up/modify memory layout */

include/uapi/linux/virtio_pci.h

···
 #define VIRTIO_ADMIN_CMD_LIST_USE	0x1
 
 /* Admin command group type. */
+#define VIRTIO_ADMIN_GROUP_TYPE_SELF	0x0
 #define VIRTIO_ADMIN_GROUP_TYPE_SRIOV	0x1
 
 /* Transitional device admin command. */

include/ufs/ufs_quirks.h

···
  */
 #define UFS_DEVICE_QUIRK_DELAY_AFTER_LPM        (1 << 11)
 
+/*
+ * Some ufs devices may need more time to be in hibern8 before exiting.
+ * Enable this quirk to give it an additional 100us.
+ */
+#define UFS_DEVICE_QUIRK_PA_HIBER8TIME          (1 << 12)
+
 #endif /* UFS_QUIRKS_H_ */

io_uring/io_uring.c

···
 	lockdep_assert(!io_wq_current_is_worker());
 	lockdep_assert_held(&ctx->uring_lock);
 
-	__io_cq_lock(ctx);
-	posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+	if (!ctx->lockless_cq) {
+		spin_lock(&ctx->completion_lock);
+		posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+		spin_unlock(&ctx->completion_lock);
+	} else {
+		posted = io_fill_cqe_aux(ctx, req->cqe.user_data, res, cflags);
+	}
+
 	ctx->submit_state.cq_flush = true;
-	__io_cq_unlock_post(ctx);
 	return posted;
 }
 
···
 	while (node) {
 		req = container_of(node, struct io_kiocb, io_task_work.node);
 		node = node->next;
-		if (sync && last_ctx != req->ctx) {
+		if (last_ctx != req->ctx) {
 			if (last_ctx) {
-				flush_delayed_work(&last_ctx->fallback_work);
+				if (sync)
+					flush_delayed_work(&last_ctx->fallback_work);
 				percpu_ref_put(&last_ctx->refs);
 			}
 			last_ctx = req->ctx;
 			percpu_ref_get(&last_ctx->refs);
 		}
-		if (llist_add(&req->io_task_work.node,
-			      &req->ctx->fallback_llist))
-			schedule_delayed_work(&req->ctx->fallback_work, 1);
+		if (llist_add(&req->io_task_work.node, &last_ctx->fallback_llist))
+			schedule_delayed_work(&last_ctx->fallback_work, 1);
 	}
 
 	if (last_ctx) {
-		flush_delayed_work(&last_ctx->fallback_work);
+		if (sync)
+			flush_delayed_work(&last_ctx->fallback_work);
 		percpu_ref_put(&last_ctx->refs);
 	}
 }

kernel/bpf/hashtab.c

···
 		b = &htab->buckets[i];
 		rcu_read_lock();
 		head = &b->head;
-		hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) {
+		hlist_nulls_for_each_entry_safe(elem, n, head, hash_node) {
 			key = elem->key;
 			if (is_percpu) {
 				/* current cpu value for percpu map */

kernel/bpf/preload/bpf_preload_kern.c

···
 }
 late_initcall(load);
 module_exit(fini);
+MODULE_IMPORT_NS("BPF_INTERNAL");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Embedded BPF programs for introspection in bpffs");

kernel/bpf/syscall.c

···
 
 	return map;
 }
-EXPORT_SYMBOL(bpf_map_get);
+EXPORT_SYMBOL_NS(bpf_map_get, "BPF_INTERNAL");
 
 struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
···
 	bpf_link_inc(link);
 	return link;
 }
-EXPORT_SYMBOL(bpf_link_get_from_fd);
+EXPORT_SYMBOL_NS(bpf_link_get_from_fd, "BPF_INTERNAL");
 
 static void bpf_tracing_link_release(struct bpf_link *link)
 {
···
 		return ____bpf_sys_bpf(cmd, attr, size);
 	}
 }
-EXPORT_SYMBOL(kern_sys_bpf);
+EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL");
 
 static const struct bpf_func_proto bpf_sys_bpf_proto = {
 	.func		= bpf_sys_bpf,

kernel/cgroup/cgroup.c

···
 DEFINE_MUTEX(cgroup_mutex);
 DEFINE_SPINLOCK(css_set_lock);
 
-#ifdef CONFIG_PROVE_RCU
+#if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP)
 EXPORT_SYMBOL_GPL(cgroup_mutex);
 EXPORT_SYMBOL_GPL(css_set_lock);
 #endif
···
 };
 
 #ifdef CONFIG_CPUSETS_V1
+enum cpuset_param {
+	Opt_cpuset_v2_mode,
+};
+
+static const struct fs_parameter_spec cpuset_fs_parameters[] = {
+	fsparam_flag  ("cpuset_v2_mode", Opt_cpuset_v2_mode),
+	{}
+};
+
+static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, cpuset_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_cpuset_v2_mode:
+		ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE;
+		return 0;
+	}
+	return -EINVAL;
+}
+
 static const struct fs_context_operations cpuset_fs_context_ops = {
 	.get_tree	= cgroup1_get_tree,
 	.free		= cgroup_fs_context_free,
+	.parse_param	= cpuset_parse_param,
 };
 
 /*
···
 static struct file_system_type cpuset_fs_type = {
 	.name			= "cpuset",
 	.init_fs_context	= cpuset_init_fs_context,
+	.parameters		= cpuset_fs_parameters,
 	.fs_flags		= FS_USERNS_MOUNT,
 };
 #endif

kernel/dma/coherent.c

···
 
 static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
 {
-	if (!rmem->priv) {
-		struct dma_coherent_mem *mem;
+	struct dma_coherent_mem *mem = rmem->priv;
 
+	if (!mem) {
 		mem = dma_init_coherent_memory(rmem->base, rmem->base,
 					       rmem->size, true);
 		if (IS_ERR(mem))
 			return PTR_ERR(mem);
 		rmem->priv = mem;
 	}
-	dma_assign_coherent_memory(dev, rmem->priv);
+
+	/* Warn if the device potentially can't use the reserved memory */
+	if (mem->device_base + rmem->size - 1 >
+	    min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit))
+		dev_warn(dev, "reserved memory is beyond device's set DMA address range\n");
+
+	dma_assign_coherent_memory(dev, mem);
 	return 0;
 }
 

kernel/dma/contiguous.c

···
  * Users, who want to set the size of global CMA area for their system
  * should use cma= kernel parameter.
  */
-static const phys_addr_t size_bytes __initconst =
-	(phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
+#define size_bytes ((phys_addr_t)CMA_SIZE_MBYTES * SZ_1M)
 static phys_addr_t  size_cmdline __initdata = -1;
 static phys_addr_t base_cmdline __initdata;
 static phys_addr_t limit_cmdline __initdata;

kernel/dma/mapping.c

···
 }
 EXPORT_SYMBOL(dma_set_coherent_mask);
 
-/**
- * dma_addressing_limited - return if the device is addressing limited
- * @dev:	device to check
- *
- * Return %true if the devices DMA mask is too small to address all memory in
- * the system, else %false.  Lack of addressing bits is the prime reason for
- * bounce buffering, but might not be the only one.
- */
-bool dma_addressing_limited(struct device *dev)
+static bool __dma_addressing_limited(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
···
 	if (unlikely(ops) || use_dma_iommu(dev))
 		return false;
 	return !dma_direct_all_ram_mapped(dev);
+}
+
+/**
+ * dma_addressing_limited - return if the device is addressing limited
+ * @dev:	device to check
+ *
+ * Return %true if the devices DMA mask is too small to address all memory in
+ * the system, else %false.  Lack of addressing bits is the prime reason for
+ * bounce buffering, but might not be the only one.
+ */
+bool dma_addressing_limited(struct device *dev)
+{
+	if (!__dma_addressing_limited(dev))
+		return false;
+
+	dev_dbg(dev, "device is DMA addressing limited\n");
+	return true;
 }
 EXPORT_SYMBOL_GPL(dma_addressing_limited);
 

kernel/events/core.c

···
 			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
 
 			if (*perf_event_fasync(event))
-				event->pending_kill = POLL_HUP;
+				event->pending_kill = POLL_ERR;
 
 			perf_event_wakeup(event);
 		} else {
···
 
 	if (unlikely(READ_ONCE(event->state) == PERF_EVENT_STATE_ERROR &&
 		     event->attr.pinned))
-		return events;
+		return EPOLLERR;
 
 	/*
 	 * Pin the event->rb by taking event->mmap_mutex; otherwise

kernel/sched/ext.c

···
 	/*
 	 * CPU cgroup support flags
 	 */
-	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* cpu.weight */
+	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* DEPRECATED, will be removed on 6.18 */
 
 	SCX_OPS_ALL_FLAGS	= SCX_OPS_KEEP_BUILTIN_IDLE |
 				  SCX_OPS_ENQ_LAST |
···
 
 DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
 static bool scx_cgroup_enabled;
-static bool cgroup_warned_missing_weight;
-static bool cgroup_warned_missing_idle;
-
-static void scx_cgroup_warn_missing_weight(struct task_group *tg)
-{
-	if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
-	    cgroup_warned_missing_weight)
-		return;
-
-	if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent)
-		return;
-
-	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n",
-		scx_ops.name);
-	cgroup_warned_missing_weight = true;
-}
-
-static void scx_cgroup_warn_missing_idle(struct task_group *tg)
-{
-	if (!scx_cgroup_enabled || cgroup_warned_missing_idle)
-		return;
-
-	if (!tg->idle)
-		return;
-
-	pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n",
-		scx_ops.name);
-	cgroup_warned_missing_idle = true;
-}
 
 int scx_tg_online(struct task_group *tg)
 {
···
 	WARN_ON_ONCE(tg->scx_flags & (SCX_TG_ONLINE | SCX_TG_INITED));
 
 	percpu_down_read(&scx_cgroup_rwsem);
-
-	scx_cgroup_warn_missing_weight(tg);
 
 	if (scx_cgroup_enabled) {
 		if (SCX_HAS_OP(cgroup_init)) {
···
 
 void scx_group_set_idle(struct task_group *tg, bool idle)
 {
-	percpu_down_read(&scx_cgroup_rwsem);
-	scx_cgroup_warn_missing_idle(tg);
-	percpu_up_read(&scx_cgroup_rwsem);
+	/* TODO: Implement ops->cgroup_set_idle() */
 }
 
 static void scx_cgroup_lock(void)
···
 
 	percpu_rwsem_assert_held(&scx_cgroup_rwsem);
 
-	cgroup_warned_missing_weight = false;
-	cgroup_warned_missing_idle = false;
-
 	/*
 	 * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
 	 * cgroups and init, all online cgroups are initialized.
···
 	css_for_each_descendant_pre(css, &root_task_group.css) {
 		struct task_group *tg = css_tg(css);
 		struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
-
-		scx_cgroup_warn_missing_weight(tg);
-		scx_cgroup_warn_missing_idle(tg);
 
 		if ((tg->scx_flags &
 		     (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
···
 
 static void free_exit_info(struct scx_exit_info *ei)
 {
-	kfree(ei->dump);
+	kvfree(ei->dump);
 	kfree(ei->msg);
 	kfree(ei->bt);
 	kfree(ei);
···
 
 	ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL);
 	ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL);
-	ei->dump = kzalloc(exit_dump_len, GFP_KERNEL);
+	ei->dump = kvzalloc(exit_dump_len, GFP_KERNEL);
 
 	if (!ei->bt || !ei->msg || !ei->dump) {
 		free_exit_info(ei);
···
 		scx_ops_error("SCX_OPS_BUILTIN_IDLE_PER_NODE requires CPU idle selection enabled");
 		return -EINVAL;
 	}
+
+	if (ops->flags & SCX_OPS_HAS_CGROUP_WEIGHT)
+		pr_warn("SCX_OPS_HAS_CGROUP_WEIGHT is deprecated and a noop\n");
 
 	return 0;
 }

kernel/sched/fair.c

···
 		h_nr_idle = task_has_idle_policy(p);
 		if (task_sleep || task_delayed || !se->sched_delayed)
 			h_nr_runnable = 1;
-	} else {
-		cfs_rq = group_cfs_rq(se);
-		slice = cfs_rq_min_slice(cfs_rq);
 	}
 
 	for_each_sched_entity(se) {
···
 			if (p && &p->se == se)
 				return -1;
 
+			slice = cfs_rq_min_slice(cfs_rq);
 			break;
 		}
 

kernel/vhost_task.c

···
  * @arg: data to be passed to fn and handled_kill
  * @name: the thread's name
  *
- * This returns a specialized task for use by the vhost layer or NULL on
+ * This returns a specialized task for use by the vhost layer or ERR_PTR() on
  * failure. The returned task is inactive, and the caller must fire it up
  * through vhost_task_start().
  */

mm/migrate.c

···
 		return -EAGAIN;
 
 	if (check_refs) {
-		bool busy;
+		bool busy, migrating;
 		bool invalidated = false;
 
+		migrating = test_and_set_bit_lock(BH_Migrate, &head->b_state);
+		VM_WARN_ON_ONCE(migrating);
 recheck_buffers:
 		busy = false;
 		spin_lock(&mapping->i_private_lock);
···
 			}
 			bh = bh->b_this_page;
 		} while (bh != head);
+		spin_unlock(&mapping->i_private_lock);
 		if (busy) {
 			if (invalidated) {
 				rc = -EAGAIN;
 				goto unlock_buffers;
 			}
-			spin_unlock(&mapping->i_private_lock);
 			invalidate_bh_lrus();
 			invalidated = true;
 			goto recheck_buffers;
···
 
 unlock_buffers:
 	if (check_refs)
-		spin_unlock(&mapping->i_private_lock);
+		clear_bit_unlock(BH_Migrate, &head->b_state);
 	bh = head;
 	do {
 		unlock_buffer(bh);

net/ceph/osd_client.c

···
 }
 EXPORT_SYMBOL(osd_req_op_extent_osd_data_pages);
 
-void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *osd_req,
-			unsigned int which, struct ceph_pagelist *pagelist)
-{
-	struct ceph_osd_data *osd_data;
-
-	osd_data = osd_req_op_data(osd_req, which, extent, osd_data);
-	ceph_osd_data_pagelist_init(osd_data, pagelist);
-}
-EXPORT_SYMBOL(osd_req_op_extent_osd_data_pagelist);
-
 #ifdef CONFIG_BLOCK
 void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
 				    unsigned int which,
···
 	osd_data = osd_req_op_data(osd_req, which, cls, request_info);
 	ceph_osd_data_pagelist_init(osd_data, pagelist);
 }
-
-void osd_req_op_cls_request_data_pagelist(
-			struct ceph_osd_request *osd_req,
-			unsigned int which, struct ceph_pagelist *pagelist)
-{
-	struct ceph_osd_data *osd_data;
-
-	osd_data = osd_req_op_data(osd_req, which, cls, request_data);
-	ceph_osd_data_pagelist_init(osd_data, pagelist);
-	osd_req->r_ops[which].cls.indata_len += pagelist->length;
-	osd_req->r_ops[which].indata_len += pagelist->length;
-}
-EXPORT_SYMBOL(osd_req_op_cls_request_data_pagelist);
 
 void osd_req_op_cls_request_data_pages(struct ceph_osd_request *osd_req,
 			unsigned int which, struct page **pages, u64 length,

net/core/lwtunnel.c

···
 	struct dst_entry *dst;
 	int ret;
 
+	local_bh_disable();
+
 	if (dev_xmit_recursion()) {
 		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
 				     __func__);
···
 	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
-	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
-		return 0;
+	    lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+		ret = 0;
+		goto out;
+	}
 
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
···
 	if (ret == -EOPNOTSUPP)
 		goto drop;
 
-	return ret;
+	goto out;
 
 drop:
 	kfree_skb(skb);
 
+out:
+	local_bh_enable();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(lwtunnel_output);
···
 	struct lwtunnel_state *lwtstate;
 	struct dst_entry *dst;
 	int ret;
+
+	local_bh_disable();
 
 	if (dev_xmit_recursion()) {
 		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
···
 	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
-	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
-		return 0;
+	    lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+		ret = 0;
+		goto out;
+	}
 
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
···
 	if (ret == -EOPNOTSUPP)
 		goto drop;
 
-	return ret;
+	goto out;
 
 drop:
 	kfree_skb(skb);
 
+out:
+	local_bh_enable();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(lwtunnel_xmit);
···
 	struct lwtunnel_state *lwtstate;
 	struct dst_entry *dst;
 	int ret;
+
+	DEBUG_NET_WARN_ON_ONCE(!in_softirq());
 
 	if (dev_xmit_recursion()) {
 		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",

net/core/netdev-genl.c

···
 
 	mutex_lock(&priv->lock);
 
+	err = 0;
 	netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex);
-	if (!netdev || !netif_device_present(netdev)) {
+	if (!netdev) {
 		err = -ENODEV;
 		goto err_unlock_sock;
 	}
-
-	if (!netdev_need_ops_lock(netdev)) {
+	if (!netif_device_present(netdev))
+		err = -ENODEV;
+	else if (!netdev_need_ops_lock(netdev))
 		err = -EOPNOTSUPP;
+	if (err) {
 		NL_SET_BAD_ATTR(info->extack,
 				info->attrs[NETDEV_A_DEV_IFINDEX]);
 		goto err_unlock;

net/core/selftests.c

···
 	ehdr->h_proto = htons(ETH_P_IP);
 
 	if (attr->tcp) {
+		memset(thdr, 0, sizeof(*thdr));
 		thdr->source = htons(attr->sport);
 		thdr->dest = htons(attr->dport);
 		thdr->doff = sizeof(struct tcphdr) / 4;
-		thdr->check = 0;
 	} else {
 		uhdr->source = htons(attr->sport);
 		uhdr->dest = htons(attr->dport);
···
 	attr->id = net_test_next_id;
 	shdr->id = net_test_next_id++;
 
-	if (attr->size)
-		skb_put(skb, attr->size);
-	if (attr->max_size && attr->max_size > skb->len)
-		skb_put(skb, attr->max_size - skb->len);
+	if (attr->size) {
+		void *payload = skb_put(skb, attr->size);
+
+		memset(payload, 0, attr->size);
+	}
+
+	if (attr->max_size && attr->max_size > skb->len) {
+		size_t pad_len = attr->max_size - skb->len;
+		void *pad = skb_put(skb, pad_len);
+
+		memset(pad, 0, pad_len);
+	}
 
 	skb->csum = 0;
 	skb->ip_summed = CHECKSUM_PARTIAL;

net/mptcp/pm_userspace.c

···
 
 	release_sock(sk);
 
-	sock_kfree_s(sk, match, sizeof(*match));
+	kfree_rcu_mightsleep(match);
+	/* Adjust sk_omem_alloc like sock_kfree_s() does, to match
+	 * with allocation of this memory by sock_kmemdup()
+	 */
+	atomic_sub(sizeof(*match), &sk->sk_omem_alloc);
 
 	err = 0;
 out:

net/sched/sch_hfsc.c

···
 
 	if (cl != NULL) {
 		int old_flags;
+		int len = 0;
 
 		if (parentid) {
 			if (cl->cl_parent &&
···
 		if (usc != NULL)
 			hfsc_change_usc(cl, usc, cur_time);
 
+		if (cl->qdisc->q.qlen != 0)
+			len = qdisc_peek_len(cl->qdisc);
+		/* Check queue length again since some qdisc implementations
+		 * (e.g., netem/codel) might empty the queue during the peek
+		 * operation.
+		 */
 		if (cl->qdisc->q.qlen != 0) {
-			int len = qdisc_peek_len(cl->qdisc);
-
 			if (cl->cl_flags & HFSC_RSC) {
 				if (old_flags & HFSC_RSC)
 					update_ed(cl, len);
···
 		if (cl->qdisc->q.qlen != 0) {
 			/* update ed */
 			next_len = qdisc_peek_len(cl->qdisc);
-			if (realtime)
-				update_ed(cl, next_len);
-			else
-				update_d(cl, next_len);
+			/* Check queue length again since some qdisc implementations
+			 * (e.g., netem/codel) might empty the queue during the peek
+			 * operation.
+			 */
+			if (cl->qdisc->q.qlen != 0) {
+				if (realtime)
+					update_ed(cl, next_len);
+				else
+					update_d(cl, next_len);
+			}
 		} else {
 			/* the class becomes passive */
 			eltree_remove(cl);

net/sunrpc/cache.c

···
 	 * or by one second if it has already reached the current time.
 	 * Newly added cache entries will always have ->last_refresh greater
 	 * that ->flush_time, so they don't get flushed prematurely.
-	 *
-	 * If someone frequently calls the flush interface, we should
-	 * immediately clean the corresponding cache_detail instead of
-	 * continuously accumulating nextcheck.
 	 */
 
-	if (cd->flush_time >= now && cd->flush_time < (now + 5))
+	if (cd->flush_time >= now)
 		now = cd->flush_time + 1;
 
 	cd->flush_time = now;

net/tipc/monitor.c

···
 		if (!mon)
 			continue;
 		write_lock_bh(&mon->lock);
-		mon->self->addr = tipc_own_addr(net);
+		if (mon->self)
+			mon->self->addr = tipc_own_addr(net);
 		write_unlock_bh(&mon->lock);
 	}
 }

rust/kernel/firmware.rs

···
 //!
 //! C header: [`include/linux/firmware.h`](srctree/include/linux/firmware.h)
 
-use crate::{bindings, device::Device, error::Error, error::Result, str::CStr};
+use crate::{bindings, device::Device, error::Error, error::Result, ffi, str::CStr};
 use core::ptr::NonNull;
 
 /// # Invariants
···
 /// One of the following: `bindings::request_firmware`, `bindings::firmware_request_nowarn`,
 /// `bindings::firmware_request_platform`, `bindings::request_firmware_direct`.
 struct FwFunc(
-    unsafe extern "C" fn(*mut *const bindings::firmware, *const u8, *mut bindings::device) -> i32,
+    unsafe extern "C" fn(
+        *mut *const bindings::firmware,
+        *const ffi::c_char,
+        *mut bindings::device,
+    ) -> i32,
 );
 
 impl FwFunc {

samples/bpf/Makefile

···
 	@echo "  CLANG-bpf " $@
 	$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \
 		-I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \
-		-I$(LIBBPF_INCLUDE) \
+		-I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \
 		-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
 		-D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \

scripts/Makefile.extrawarn

···
 KBUILD_CFLAGS += -Werror=strict-prototypes
 KBUILD_CFLAGS += -Wno-format-security
 KBUILD_CFLAGS += -Wno-trigraphs
-KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,)
+KBUILD_CFLAGS += $(call cc-disable-warning, frame-address)
 KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 KBUILD_CFLAGS += -Wmissing-declarations
 KBUILD_CFLAGS += -Wmissing-prototypes

security/integrity/ima/ima_main.c

···
 				&allowed_algos);
 	violation_check = ((func == FILE_CHECK || func == MMAP_CHECK ||
 			    func == MMAP_CHECK_REQPROT) &&
-			   (ima_policy_flag & IMA_MEASURE));
+			   (ima_policy_flag & IMA_MEASURE) &&
+			   ((action & IMA_MEASURE) ||
+			    (file->f_mode & FMODE_WRITE)));
 	if (!action && !violation_check)
 		return 0;
 

security/landlock/domain.c

···
 #include <linux/path.h>
 #include <linux/pid.h>
 #include <linux/sched.h>
+#include <linux/signal.h>
 #include <linux/uidgid.h>
 
 #include "access.h"
···
 		return ERR_PTR(-ENOMEM);
 
 	memcpy(details->exe_path, path_str, path_size);
-	WARN_ON_ONCE(current_cred() != current_real_cred());
-	details->pid = get_pid(task_pid(current));
+	details->pid = get_pid(task_tgid(current));
 	details->uid = from_kuid(&init_user_ns, current_uid());
 	get_task_comm(details->comm, current);
 	return details;

security/landlock/domain.h

···
 static inline void
 landlock_free_hierarchy_details(struct landlock_hierarchy *const hierarchy)
 {
-	if (WARN_ON_ONCE(!hierarchy || !hierarchy->details))
+	if (!hierarchy || !hierarchy->details)
 		return;
 
 	put_pid(hierarchy->details->pid);

security/landlock/syscalls.c

···
  *        the new ruleset.
  * @size: Size of the pointed &struct landlock_ruleset_attr (needed for
  *        backward and forward compatibility).
- * @flags: Supported value:
+ * @flags: Supported values:
+ *
  *         - %LANDLOCK_CREATE_RULESET_VERSION
  *         - %LANDLOCK_CREATE_RULESET_ERRATA
  *
  * This system call enables to create a new Landlock ruleset, and returns the
  * related file descriptor on success.
  *
- * If @flags is %LANDLOCK_CREATE_RULESET_VERSION and @attr is NULL and @size is
- * 0, then the returned value is the highest supported Landlock ABI version
- * (starting at 1).
- *
- * If @flags is %LANDLOCK_CREATE_RULESET_ERRATA and @attr is NULL and @size is
- * 0, then the returned value is a bitmask of fixed issues for the current
- * Landlock ABI version.
+ * If %LANDLOCK_CREATE_RULESET_VERSION or %LANDLOCK_CREATE_RULESET_ERRATA is
+ * set, then @attr must be NULL and @size must be 0.
  *
  * Possible returned errors are:
  *
···
  * - %E2BIG: @attr or @size inconsistencies;
  * - %EFAULT: @attr or @size inconsistencies;
  * - %ENOMSG: empty &landlock_ruleset_attr.handled_access_fs.
+ *
+ * .. kernel-doc:: include/uapi/linux/landlock.h
+ *     :identifiers: landlock_create_ruleset_flags
  */
 SYSCALL_DEFINE3(landlock_create_ruleset,
 		const struct landlock_ruleset_attr __user *const, attr,
···
  * @ruleset_fd: File descriptor tied to the ruleset to merge with the target.
  * @flags: Supported values:
  *
- * - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
- * - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
- * - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
+ *         - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
+ *         - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
+ *         - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
  *
  * This system call enables to enforce a Landlock ruleset on the current
  * thread.  Enforcing a ruleset requires that the task has %CAP_SYS_ADMIN in its
  * namespace or is running with no_new_privs.  This avoids scenarios where
  * unprivileged tasks can affect the behavior of privileged children.
- *
- * It is allowed to only pass the %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
- * flag with a @ruleset_fd value of -1.
  *
  * Possible returned errors are:
  *
···
  *   %CAP_SYS_ADMIN in its namespace.
  * - %E2BIG: The maximum number of stacked rulesets is reached for the current
  *   thread.
+ *
+ * .. kernel-doc:: include/uapi/linux/landlock.h
+ *     :identifiers: landlock_restrict_self_flags
  */
 SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32,
 		flags)

tools/arch/x86/lib/x86-opcode-map.txt

···
 83: Grp1 Ev,Ib (1A),(es)
 # CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
 #			     CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
 88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
 8f: POP2 Bq,Rq (000),(11B),(ev)
 a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)

tools/sched_ext/scx_flatcg.bpf.c

···
 	       .cgroup_move		= (void *)fcg_cgroup_move,
 	       .init			= (void *)fcg_init,
 	       .exit			= (void *)fcg_exit,
-	       .flags			= SCX_OPS_HAS_CGROUP_WEIGHT | SCX_OPS_ENQ_EXITING,
+	       .flags			= SCX_OPS_ENQ_EXITING,
 	       .name			= "flatcg");

tools/testing/cxl/test/mem.c

···
 	if (rc)
 		return rc;
 
-	rc = devm_cxl_setup_fwctl(cxlmd);
+	rc = devm_cxl_setup_fwctl(&pdev->dev, cxlmd);
 	if (rc)
 		dev_dbg(dev, "No CXL FWCTL setup\n");
 

tools/testing/kunit/configs/all_tests.config

···
 
 CONFIG_AUDIT=y
 
+CONFIG_PRIME_NUMBERS=y
+
 CONFIG_SECURITY=y
 CONFIG_SECURITY_APPARMOR=y
 CONFIG_SECURITY_LANDLOCK=y

tools/testing/selftests/bpf/prog_tests/for_each.c

···
 #include "for_each_array_map_elem.skel.h"
 #include "for_each_map_elem_write_key.skel.h"
 #include "for_each_multi_maps.skel.h"
+#include "for_each_hash_modify.skel.h"
 
 static unsigned int duration;
 
···
 	for_each_multi_maps__destroy(skel);
 }
 
+static void test_hash_modify(void)
+{
+	struct for_each_hash_modify *skel;
+	int max_entries, i, err;
+	__u64 key, val;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1
+	);
+
+	skel = for_each_hash_modify__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "for_each_hash_modify__open_and_load"))
+		return;
+
+	max_entries = bpf_map__max_entries(skel->maps.hashmap);
+	for (i = 0; i < max_entries; i++) {
+		key = i;
+		val = i;
+		err = bpf_map__update_elem(skel->maps.hashmap, &key, sizeof(key),
+					   &val, sizeof(val), BPF_ANY);
+		if (!ASSERT_OK(err, "map_update"))
+			goto out;
+	}
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+	ASSERT_OK(topts.retval, "retval");
+
+out:
+	for_each_hash_modify__destroy(skel);
+}
+
 void test_for_each(void)
 {
 	if (test__start_subtest("hash_map"))
···
 		test_write_map_key();
 	if (test__start_subtest("multi_maps"))
 		test_multi_maps();
+	if (test__start_subtest("hash_modify"))
+		test_hash_modify();
 }

tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c

···
 		goto close_cli;
 
 	err = disconnect(cli);
-	ASSERT_OK(err, "disconnect");
 
 close_cli:
 	close(cli);

tools/testing/selftests/bpf/progs/bpf_misc.h

···
 #define CAN_USE_GOTOL
 #endif
 
-#if _clang_major__ >= 18
+#if __clang_major__ >= 18
 #define CAN_USE_BPF_ST
 #endif
 

tools/testing/selftests/bpf/progs/for_each_hash_modify.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Intel Corporation */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 128);
+	__type(key, __u64);
+	__type(value, __u64);
+} hashmap SEC(".maps");
+
+static int cb(struct bpf_map *map, __u64 *key, __u64 *val, void *arg)
+{
+	bpf_map_delete_elem(map, key);
+	bpf_map_update_elem(map, key, val, 0);
+	return 0;
+}
+
+SEC("tc")
+int test_pkt_access(struct __sk_buff *skb)
+{
+	(void)skb;
+
+	bpf_for_each_map_elem(&hashmap, cb, NULL, 0);
+
+	return 0;
+}

tools/testing/selftests/landlock/audit.h

···
 	return err;
 }
 
-static int __maybe_unused matches_log_domain_allocated(int audit_fd,
+static int __maybe_unused matches_log_domain_allocated(int audit_fd, pid_t pid,
 						       __u64 *domain_id)
 {
-	return audit_match_record(
-		audit_fd, AUDIT_LANDLOCK_DOMAIN,
-		REGEX_LANDLOCK_PREFIX
-		" status=allocated mode=enforcing pid=[0-9]\\+ uid=[0-9]\\+"
-		" exe=\"[^\"]\\+\" comm=\".*_test\"$",
-		domain_id);
+	static const char log_template[] = REGEX_LANDLOCK_PREFIX
+		" status=allocated mode=enforcing pid=%d uid=[0-9]\\+"
+		" exe=\"[^\"]\\+\" comm=\".*_test\"$";
+	char log_match[sizeof(log_template) + 10];
+	int log_match_len;
+
+	log_match_len =
+		snprintf(log_match, sizeof(log_match), log_template, pid);
+	if (log_match_len > sizeof(log_match))
+		return -E2BIG;
+
+	return audit_match_record(audit_fd, AUDIT_LANDLOCK_DOMAIN, log_match,
+				  domain_id);
 }
 
 static int __maybe_unused matches_log_domain_deallocated(

tools/testing/selftests/landlock/audit_test.c

···
 #include <errno.h>
 #include <limits.h>
 #include <linux/landlock.h>
+#include <pthread.h>
 #include <stdlib.h>
 #include <sys/mount.h>
 #include <sys/prctl.h>
···
 {
 	struct audit_filter audit_filter;
 	int audit_fd;
-	__u64(*domain_stack)[16];
 };
 
 FIXTURE_SETUP(audit)
···
 		TH_LOG("Failed to initialize audit: %s", error_msg);
 	}
 	clear_cap(_metadata, CAP_AUDIT_CONTROL);
-
-	self->domain_stack = mmap(NULL, sizeof(*self->domain_stack),
-				  PROT_READ | PROT_WRITE,
-				  MAP_SHARED | MAP_ANONYMOUS, -1, 0);
-	ASSERT_NE(MAP_FAILED, self->domain_stack);
-	memset(self->domain_stack, 0, sizeof(*self->domain_stack));
 }
 
 FIXTURE_TEARDOWN(audit)
 {
-	EXPECT_EQ(0, munmap(self->domain_stack, sizeof(*self->domain_stack)));
-
 	set_cap(_metadata, CAP_AUDIT_CONTROL);
 	EXPECT_EQ(0, audit_cleanup(self->audit_fd, &self->audit_filter));
 	clear_cap(_metadata, CAP_AUDIT_CONTROL);
···
 		.scoped = LANDLOCK_SCOPE_SIGNAL,
 	};
 	int status, ruleset_fd, i;
+	__u64(*domain_stack)[16];
 	__u64 prev_dom = 3;
 	pid_t child;
+
+	domain_stack = mmap(NULL, sizeof(*domain_stack), PROT_READ | PROT_WRITE,
+			    MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(MAP_FAILED, domain_stack);
+	memset(domain_stack, 0, sizeof(*domain_stack));
 
 	ruleset_fd =
 		landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
···
 	child = fork();
 	ASSERT_LE(0, child);
 	if (child == 0) {
-		for (i = 0; i < ARRAY_SIZE(*self->domain_stack); i++) {
+		for (i = 0; i < ARRAY_SIZE(*domain_stack); i++) {
 			__u64 denial_dom = 1;
 			__u64 allocated_dom = 2;
 
···
 				  matches_log_signal(_metadata, self->audit_fd,
 						     getppid(), &denial_dom));
 			EXPECT_EQ(0, matches_log_domain_allocated(
-					     self->audit_fd, &allocated_dom));
+					     self->audit_fd, getpid(),
+					     &allocated_dom));
 			EXPECT_NE(denial_dom, 1);
 			EXPECT_NE(denial_dom, 0);
 			EXPECT_EQ(denial_dom, allocated_dom);
···
 			/* Checks that the new domain is younger than the previous one. */
 			EXPECT_GT(allocated_dom, prev_dom);
 			prev_dom = allocated_dom;
-			(*self->domain_stack)[i] = allocated_dom;
+			(*domain_stack)[i] = allocated_dom;
 		}
 
 		/* Checks that we reached the maximum number of layers. */
···
 	/* Purges log from deallocated domains. */
 	EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
 				&audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
-	for (i = ARRAY_SIZE(*self->domain_stack) - 1; i >= 0; i--) {
+	for (i = ARRAY_SIZE(*domain_stack) - 1; i >= 0; i--) {
 		__u64 deallocated_dom = 2;
 
 		EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
 							    &deallocated_dom));
-		EXPECT_EQ((*self->domain_stack)[i], deallocated_dom)
+		EXPECT_EQ((*domain_stack)[i], deallocated_dom)
 		{
 			TH_LOG("Failed to match domain %llx (#%d)",
-			       (*self->domain_stack)[i], i);
+			       (*domain_stack)[i], i);
 		}
 	}
+	EXPECT_EQ(0, munmap(domain_stack, sizeof(*domain_stack)));
 	EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
 				&audit_tv_default, sizeof(audit_tv_default)));
-
 	EXPECT_EQ(0, close(ruleset_fd));
+}
+
+struct thread_data {
+	pid_t parent_pid;
+	int ruleset_fd, pipe_child, pipe_parent;
+};
+
+static void *thread_audit_test(void *arg)
+{
+	const struct thread_data *data = (struct thread_data *)arg;
+	uintptr_t err = 0;
+	char buffer;
+
+	/* TGID and TID are different for a second thread. */
+	if (getpid() == gettid()) {
+		err = 1;
+		goto out;
+	}
+
+	if (landlock_restrict_self(data->ruleset_fd, 0)) {
+		err = 2;
+		goto out;
+	}
+
+	if (close(data->ruleset_fd)) {
+		err = 3;
+		goto out;
+	}
+
+	/* Creates a denial to get the domain ID. */
+	if (kill(data->parent_pid, 0) != -1) {
+		err = 4;
+		goto out;
+	}
+
+	if (EPERM != errno) {
+		err = 5;
+		goto out;
+	}
+
+	/* Signals the parent to read denial logs. */
+	if (write(data->pipe_child, ".", 1) != 1) {
+		err = 6;
+		goto out;
+	}
+
+	/* Waits for the parent to update audit filters. */
+	if (read(data->pipe_parent, &buffer, 1) != 1) {
+		err = 7;
+		goto out;
+	}
+
+out:
+	close(data->pipe_child);
+	close(data->pipe_parent);
+	return (void *)err;
+}
+
+/* Checks that the PID tied to a domain is not a TID but the TGID. */
+TEST_F(audit, thread)
+{
+	const struct landlock_ruleset_attr ruleset_attr = {
+		.scoped = LANDLOCK_SCOPE_SIGNAL,
+	};
+	__u64 denial_dom = 1;
+	__u64 allocated_dom = 2;
+	__u64 deallocated_dom = 3;
+	pthread_t thread;
+	int pipe_child[2], pipe_parent[2];
+	char buffer;
+	struct thread_data child_data;
+
+	child_data.parent_pid = getppid();
+	ASSERT_EQ(0, pipe2(pipe_child, O_CLOEXEC));
+	child_data.pipe_child = pipe_child[1];
+	ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC));
+	child_data.pipe_parent = pipe_parent[0];
+	child_data.ruleset_fd =
+		landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+	ASSERT_LE(0, child_data.ruleset_fd);
+
+	/* TGID and TID are the same for the initial thread . */
+	EXPECT_EQ(getpid(), gettid());
+	EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+	ASSERT_EQ(0, pthread_create(&thread, NULL, thread_audit_test,
+				    &child_data));
+
+	/* Waits for the child to generate a denial. */
+	ASSERT_EQ(1, read(pipe_child[0], &buffer, 1));
+	EXPECT_EQ(0, close(pipe_child[0]));
+
+	/* Matches the signal log to get the domain ID. */
+	EXPECT_EQ(0, matches_log_signal(_metadata, self->audit_fd,
+					child_data.parent_pid, &denial_dom));
+	EXPECT_NE(denial_dom, 1);
+	EXPECT_NE(denial_dom, 0);
+
+	EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, getpid(),
+						  &allocated_dom));
+	EXPECT_EQ(denial_dom, allocated_dom);
+
+	/* Updates filter rules to match the drop record. */
+	set_cap(_metadata, CAP_AUDIT_CONTROL);
+	EXPECT_EQ(0, audit_filter_drop(self->audit_fd, AUDIT_ADD_RULE));
+	EXPECT_EQ(0, audit_filter_exe(self->audit_fd, &self->audit_filter,
+				      AUDIT_DEL_RULE));
+	clear_cap(_metadata, CAP_AUDIT_CONTROL);
+
+	/* Signals the thread to exit, which will generate a domain deallocation. */
+	ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+	EXPECT_EQ(0, close(pipe_parent[1]));
+	ASSERT_EQ(0, pthread_join(thread, NULL));
+
+	EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+				&audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
+	EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
+						    &deallocated_dom));
+	EXPECT_EQ(denial_dom, deallocated_dom);
+	EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+				&audit_tv_default, sizeof(audit_tv_default)));
 }
 
 FIXTURE(audit_flags)
···
 
 			/* Checks domain information records. */
 			EXPECT_EQ(0, matches_log_domain_allocated(
-					     self->audit_fd, &allocated_dom));
+					     self->audit_fd, getpid(),
+					     &allocated_dom));
 			EXPECT_NE(*self->domain_id, 1);
 			EXPECT_NE(*self->domain_id, 0);
 			EXPECT_EQ(*self->domain_id, allocated_dom);

tools/testing/selftests/landlock/fs_test.c

···
 	EXPECT_EQ(EXDEV, errno);
 	EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
 				    dir_s1d1));
-	EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, NULL));
+	EXPECT_EQ(0,
+		  matches_log_domain_allocated(self->audit_fd, getpid(), NULL));
 	EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
 				    dir_s1d3));
 

tools/testing/selftests/net/mptcp/diag.sh

···
 	local token
 	local msg
 
-	ss_token="$(ss -inmHMN $ns | grep 'token:' |\
-		    head -n 1 |\
-		    sed 's/.*token:\([0-9a-f]*\).*/\1/')"
+	ss_token="$(ss -inmHMN $ns |
+		    mptcp_lib_get_info_value "token" "token")"
 
 	token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\
 		 awk -F':[ \t]+' '/^token/ {print $2}')"

tools/testing/selftests/pcie_bwctrl/Makefile

···
-TEST_PROGS = set_pcie_cooling_state.sh set_pcie_speed.sh
+TEST_PROGS = set_pcie_cooling_state.sh
+TEST_FILES = set_pcie_speed.sh
 include ../lib.mk

tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json

···
             "$TC qdisc del dev $DUMMY handle 1: root",
             "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
         ]
+    },
+    {
+        "id": "a4c3",
+        "name": "Test HFSC with netem/blackhole - queue emptying during peek operation",
+        "category": [
+            "qdisc",
+            "hfsc",
+            "netem",
+            "blackhole"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+            "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr",
+            "$TC class add dev $DUMMY parent 1:0 classid 1:2 drr",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 plug limit 1024",
+            "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 hfsc default 1",
+            "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+            "$TC qdisc add dev $DUMMY parent 3:1 handle 4:0 netem delay 1ms",
+            "$TC qdisc add dev $DUMMY parent 4:1 handle 5:0 blackhole",
+            "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true",
+            "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+            "$TC class del dev $DUMMY parent 3:0 classid 3:1",
+            "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+            "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true"
+        ],
+        "cmdUnderTest": "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "qdisc hfsc 3:.*parent 1:2.*default 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1:0 root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
     }
 ]

tools/testing/selftests/ublk/kublk.c

···
 			value = strtol(optarg, NULL, 10);
 			if (value)
 				ctx.flags |= UBLK_F_NEED_GET_DATA;
+			break;
 		case 0:
 			if (!strcmp(longopts[option_idx].name, "debug_mask"))
 				ublk_dbg_mask = strtol(optarg, NULL, 16);

tools/testing/selftests/ublk/kublk.h

···
 	unsigned int	fg:1;
 	unsigned int	recovery:1;
 
-	/* fault_inject */
-	long long	delay_us;
-
 	int _evtfd;
 	int _shmid;
 

tools/testing/selftests/ublk/test_common.sh

···
 	local minor
 
 	dev=/dev/ublkb"${dev_id}"
-	major=$(stat -c '%Hr' "$dev")
-	minor=$(stat -c '%Lr' "$dev")
+	major="0x"$(stat -c '%t' "$dev")
+	minor="0x"$(stat -c '%T' "$dev")
 
 	echo $(( (major & 0xfff) << 20 | (minor & 0xfffff) ))
 }

tools/testing/selftests/ublk/test_generic_05.sh

···
 
 . "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
 
-TID="generic_04"
+TID="generic_05"
 ERR_CODE=0
 
 ublk_run_recover_test()