diff options
254 files changed, 2920 insertions, 1652 deletions
diff --git a/.gitignore b/.gitignore index 72ef86a5570d..2763fce8766c 100644 --- a/.gitignore +++ b/.gitignore @@ -100,6 +100,10 @@ modules.order /include/ksym/ /arch/*/include/generated/ +# Generated lkdtm tests +/tools/testing/selftests/lkdtm/*.sh +!/tools/testing/selftests/lkdtm/run.sh + # stgit generated dirs patches-* @@ -567,6 +567,11 @@ D: Original author of Amiga FFS filesystem S: Orlando, Florida S: USA +N: Paul Burton +E: paulburton@kernel.org +W: https://pburton.com +D: MIPS maintainer 2018-2020 + N: Lennert Buytenhek E: kernel@wantstofly.org D: Original (2.4) rewrite of the ethernet bridging code diff --git a/Documentation/admin-guide/bootconfig.rst b/Documentation/admin-guide/bootconfig.rst index b342a6796392..cf2edcd09183 100644 --- a/Documentation/admin-guide/bootconfig.rst +++ b/Documentation/admin-guide/bootconfig.rst @@ -62,6 +62,30 @@ Or more shorter, written as following:: In both styles, same key words are automatically merged when parsing it at boot time. So you can append similar trees or key-values. +Same-key Values +--------------- + +It is prohibited that two or more values or arrays share a same-key. +For example,:: + + foo = bar, baz + foo = qux # !ERROR! we can not re-define same key + +If you want to append the value to existing key as an array member, +you can use ``+=`` operator. For example:: + + foo = bar, baz + foo += qux + +In this case, the key ``foo`` has ``bar``, ``baz`` and ``qux``. + +However, a sub-key and a value can not co-exist under a parent key. +For example, following config is NOT allowed.:: + + foo = value1 + foo.bar = value2 # !ERROR! subkey "bar" and value "value1" can NOT co-exist + + Comments -------- @@ -102,9 +126,13 @@ Boot Kernel With a Boot Config ============================== Since the boot configuration file is loaded with initrd, it will be added -to the end of the initrd (initramfs) image file. The Linux kernel decodes -the last part of the initrd image in memory to get the boot configuration -data. +to the end of the initrd (initramfs) image file with size, checksum and +12-byte magic word as below. + +[initrd][bootconfig][size(u32)][checksum(u32)][#BOOTCONFIG\n] + +The Linux kernel decodes the last part of the initrd image in memory to +get the boot configuration data. Because of this "piggyback" method, there is no need to change or update the boot loader and the kernel image itself. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index dbc22d684627..c07815d230bc 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -136,6 +136,10 @@ dynamic table installation which will install SSDT tables to /sys/firmware/acpi/tables/dynamic. + acpi_no_watchdog [HW,ACPI,WDT] + Ignore the ACPI-based watchdog interface (WDAT) and let + a native driver control the watchdog device instead. + acpi_rsdp= [ACPI,EFI,KEXEC] Pass the RSDP address to the kernel, mostly used on machines running EFI runtime service to boot the diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst index 7cd56a1993b1..607758a66a99 100644 --- a/Documentation/dev-tools/kunit/usage.rst +++ b/Documentation/dev-tools/kunit/usage.rst @@ -551,6 +551,7 @@ options to your ``.config``: Once the kernel is built and installed, a simple .. code-block:: bash + modprobe example-test ...will run the tests. diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index 0e0eb2c8da7d..6bc126a14b3d 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -765,7 +765,7 @@ is not sufficient this sometimes needs to be explicit. Example:: #arch/x86/boot/Makefile - subdir- := compressed/ + subdir- := compressed The above assignment instructs kbuild to descend down in the directory compressed/ when "make clean" is executed. @@ -1379,9 +1379,6 @@ See subsequent chapter for the syntax of the Kbuild file. in arch/$(ARCH)/include/(uapi/)/asm, Kbuild will automatically generate a wrapper of the asm-generic one. - The convention is to list one subdir per line and - preferably in alphabetic order. - 8 Kbuild Variables ================== diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index 1e4735cc0553..256106054c8c 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -487,8 +487,9 @@ phy_register_fixup_for_id():: The stubs set one of the two matching criteria, and set the other one to match anything. -When phy_register_fixup() or \*_for_uid()/\*_for_id() is called at module, -unregister fixup and free allocate memory are required. +When phy_register_fixup() or \*_for_uid()/\*_for_id() is called at module load +time, the module needs to unregister the fixup and free allocated memory when +it's unloaded. Call one of following function before unloading module:: diff --git a/Documentation/power/index.rst b/Documentation/power/index.rst index 002e42745263..ced8a8007434 100644 --- a/Documentation/power/index.rst +++ b/Documentation/power/index.rst @@ -13,7 +13,6 @@ Power Management drivers-testing energy-model freezing-of-tasks - interface opp pci pm_qos_interface diff --git a/Documentation/sphinx/parallel-wrapper.sh b/Documentation/sphinx/parallel-wrapper.sh index 7daf5133bdd3..e54c44ce117d 100644 --- a/Documentation/sphinx/parallel-wrapper.sh +++ b/Documentation/sphinx/parallel-wrapper.sh @@ -30,4 +30,4 @@ if [ -n "$parallel" ] ; then parallel="-j$parallel" fi -exec "$sphinx" "$parallel" "$@" +exec "$sphinx" $parallel "$@" diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 97a72a53fa4b..ebd383fba939 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4611,35 +4611,38 @@ unpins the VPA pages and releases all the device pages that are used to track the secure pages by hypervisor. 4.122 KVM_S390_NORMAL_RESET +--------------------------- -Capability: KVM_CAP_S390_VCPU_RESETS -Architectures: s390 -Type: vcpu ioctl -Parameters: none -Returns: 0 +:Capability: KVM_CAP_S390_VCPU_RESETS +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 This ioctl resets VCPU registers and control structures according to the cpu reset definition in the POP (Principles Of Operation). 4.123 KVM_S390_INITIAL_RESET +---------------------------- -Capability: none -Architectures: s390 -Type: vcpu ioctl -Parameters: none -Returns: 0 +:Capability: none +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 This ioctl resets VCPU registers and control structures according to the initial cpu reset definition in the POP. However, the cpu is not put into ESA mode. This reset is a superset of the normal reset. 4.124 KVM_S390_CLEAR_RESET +-------------------------- -Capability: KVM_CAP_S390_VCPU_RESETS -Architectures: s390 -Type: vcpu ioctl -Parameters: none -Returns: 0 +:Capability: KVM_CAP_S390_VCPU_RESETS +:Architectures: s390 +:Type: vcpu ioctl +:Parameters: none +:Returns: 0 This ioctl resets VCPU registers and control structures according to the clear cpu reset definition in the POP. However, the cpu is not put diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst index a8de2fbc1caa..265d9e9a093b 100644 --- a/Documentation/x86/index.rst +++ b/Documentation/x86/index.rst @@ -19,7 +19,6 @@ x86-specific Documentation tlb mtrr pat - intel_mpx intel-iommu intel_txt amd-memory-encryption diff --git a/MAINTAINERS b/MAINTAINERS index fcd79fc38928..6158a143a13e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11115,14 +11115,12 @@ S: Maintained F: drivers/usb/image/microtek.* MIPS -M: Ralf Baechle <ralf@linux-mips.org> -M: Paul Burton <paulburton@kernel.org> +M: Thomas Bogendoerfer <tsbogend@alpha.franken.de> L: linux-mips@vger.kernel.org W: http://www.linux-mips.org/ -T: git git://git.linux-mips.org/pub/scm/ralf/linux.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux.git Q: http://patchwork.linux-mips.org/project/linux-mips/list/ -S: Supported +S: Maintained F: Documentation/devicetree/bindings/mips/ F: Documentation/mips/ F: arch/mips/ @@ -12741,7 +12739,7 @@ M: Tom Joseph <tjoseph@cadence.com> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/cdns,*.txt -F: drivers/pci/controller/pcie-cadence* +F: drivers/pci/controller/cadence/ PCI DRIVER FOR FREESCALE LAYERSCAPE M: Minghuan Lian <minghuan.Lian@nxp.com> @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -68,6 +68,7 @@ unexport GREP_OPTIONS # # If KBUILD_VERBOSE equals 0 then the above command will be hidden. # If KBUILD_VERBOSE equals 1 then the above command is displayed. +# If KBUILD_VERBOSE equals 2 then give the reason why each target is rebuilt. # # To put more focus on warnings, be less verbose as default # Use 'make V=1' to see the full commands @@ -1238,7 +1239,7 @@ ifneq ($(dtstree),) %.dtb: include/config/kernel.release scripts_dtc $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ -PHONY += dtbs dtbs_install dt_binding_check +PHONY += dtbs dtbs_install dtbs_check dtbs dtbs_check: include/config/kernel.release scripts_dtc $(Q)$(MAKE) $(build)=$(dtstree) @@ -1258,6 +1259,7 @@ PHONY += scripts_dtc scripts_dtc: scripts_basic $(Q)$(MAKE) $(build)=scripts/dtc +PHONY += dt_binding_check dt_binding_check: scripts_dtc $(Q)$(MAKE) $(build)=Documentation/devicetree/bindings diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index c3314b286a61..a827b4d60d38 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -392,9 +392,6 @@ static inline void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} -static inline void kvm_arm_vhe_guest_enter(void) {} -static inline void kvm_arm_vhe_guest_exit(void) {} - #define KVM_BP_HARDEN_UNKNOWN -1 #define KVM_BP_HARDEN_WA_NEEDED 0 #define KVM_BP_HARDEN_NOT_REQUIRED 1 diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 25fec4bde43a..a358e97572c1 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -32,7 +32,7 @@ static inline void gic_write_eoir(u32 irq) isb(); } -static inline void gic_write_dir(u32 irq) +static __always_inline void gic_write_dir(u32 irq) { write_sysreg_s(irq, SYS_ICC_DIR_EL1); isb(); diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 806e9dc2a852..a4d1b5f771f6 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -69,7 +69,7 @@ static inline int icache_is_aliasing(void) return test_bit(ICACHEF_ALIASING, &__icache_flags); } -static inline int icache_is_vpipt(void) +static __always_inline int icache_is_vpipt(void) { return test_bit(ICACHEF_VPIPT, &__icache_flags); } diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 665c78e0665a..e6cca3d4acf7 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -145,7 +145,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); -static inline void __flush_icache_all(void) +static __always_inline void __flush_icache_all(void) { if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC)) return; diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 92ef9539874a..2a746b99e937 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -435,13 +435,13 @@ cpuid_feature_extract_signed_field(u64 features, int field) return cpuid_feature_extract_signed_field_width(features, field, 4); } -static inline unsigned int __attribute_const__ +static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width) { return (u64)(features << (64 - width - field)) >> (64 - width); } -static inline unsigned int __attribute_const__ +static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field(u64 features, int field) { return cpuid_feature_extract_unsigned_field_width(features, field, 4); @@ -564,7 +564,7 @@ static inline bool system_supports_mixed_endian(void) return val == 0x1; } -static inline bool system_supports_fpsimd(void) +static __always_inline bool system_supports_fpsimd(void) { return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD); } @@ -575,13 +575,13 @@ static inline bool system_uses_ttbr0_pan(void) !cpus_have_const_cap(ARM64_HAS_PAN); } -static inline bool system_supports_sve(void) +static __always_inline bool system_supports_sve(void) { return IS_ENABLED(CONFIG_ARM64_SVE) && cpus_have_const_cap(ARM64_SVE); } -static inline bool system_supports_cnp(void) +static __always_inline bool system_supports_cnp(void) { return IS_ENABLED(CONFIG_ARM64_CNP) && cpus_have_const_cap(ARM64_HAS_CNP); diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 4e531f57147d..6facd1308e7c 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -34,7 +34,7 @@ static inline void __raw_writew(u16 val, volatile void __iomem *addr) } #define __raw_writel __raw_writel -static inline void __raw_writel(u32 val, volatile void __iomem *addr) +static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr) { asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr)); } @@ -69,7 +69,7 @@ static inline u16 __raw_readw(const volatile void __iomem *addr) } #define __raw_readl __raw_readl -static inline u32 __raw_readl(const volatile void __iomem *addr) +static __always_inline u32 __raw_readl(const volatile void __iomem *addr) { u32 val; asm volatile(ALTERNATIVE("ldr %w0, [%1]", diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 688c63412cc2..f658dda12364 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -36,7 +36,7 @@ void kvm_inject_undef32(struct kvm_vcpu *vcpu); void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr); -static inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) +static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { return !(vcpu->arch.hcr_el2 & HCR_RW); } @@ -127,7 +127,7 @@ static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr) vcpu->arch.vsesr_el2 = vsesr; } -static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) +static __always_inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc; } @@ -153,17 +153,17 @@ static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long *__vcpu_elr_el1(vcpu) = v; } -static inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu) +static __always_inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pstate; } -static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu) +static __always_inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu) { return !!(*vcpu_cpsr(vcpu) & PSR_MODE32_BIT); } -static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) return kvm_condition_valid32(vcpu); @@ -181,13 +181,13 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) * coming from a read of ESR_EL2. Otherwise, it may give the wrong result on * AArch32 with banked registers. */ -static inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu, +static __always_inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu, u8 reg_num) { return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num]; } -static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, +static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, unsigned long val) { if (reg_num != 31) @@ -264,12 +264,12 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu) return mode != PSR_MODE_EL0t; } -static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) +static __always_inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) { return vcpu->arch.fault.esr_el2; } -static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) +static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) { u32 esr = kvm_vcpu_get_hsr(vcpu); @@ -279,12 +279,12 @@ static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) return -1; } -static inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vcpu) +static __always_inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vcpu) { return vcpu->arch.fault.far_el2; } -static inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu) +static __always_inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu) { return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8; } @@ -299,7 +299,7 @@ static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK; } -static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV); } @@ -319,17 +319,17 @@ static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu) return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF); } -static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) +static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) { return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT; } -static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW); } -static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) || kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */ @@ -340,18 +340,18 @@ static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu) return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM); } -static inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu) +static __always_inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu) { return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT); } /* This one is not specific to Data Abort */ -static inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_IL); } -static inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu) +static __always_inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu) { return ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu)); } @@ -361,17 +361,17 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW; } -static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) +static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC; } -static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu) +static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE; } -static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu) { switch (kvm_vcpu_trap_get_fault(vcpu)) { case FSC_SEA: @@ -390,7 +390,7 @@ static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu) } } -static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) +static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) { u32 esr = kvm_vcpu_get_hsr(vcpu); return ESR_ELx_SYS64_ISS_RT(esr); @@ -504,7 +504,7 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, return data; /* Leave LE untouched */ } -static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) +static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) { if (vcpu_mode_is_32bit(vcpu)) kvm_skip_instr32(vcpu, is_wide_instr); @@ -519,7 +519,7 @@ static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) * Skip an instruction which has been emulated at hyp while most guest sysregs * are live. */ -static inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu) +static __always_inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index d87aa609d2b6..57fd46acd058 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -626,38 +626,6 @@ static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u32 clr) {} #endif -static inline void kvm_arm_vhe_guest_enter(void) -{ - local_daif_mask(); - - /* - * Having IRQs masked via PMR when entering the guest means the GIC - * will not signal the CPU of interrupts of lower priority, and the - * only way to get out will be via guest exceptions. - * Naturally, we want to avoid this. - * - * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a - * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. - */ - pmr_sync(); -} - -static inline void kvm_arm_vhe_guest_exit(void) -{ - /* - * local_daif_restore() takes care to properly restore PSTATE.DAIF - * and the GIC PMR if the host is using IRQ priorities. - */ - local_daif_restore(DAIF_PROCCTX_NOIRQ); - - /* - * When we exit from the guest we change a number of CPU configuration - * parameters, such as traps. Make sure these changes take effect - * before running the host or additional guests. - */ - isb(); -} - #define KVM_BP_HARDEN_UNKNOWN -1 #define KVM_BP_HARDEN_WA_NEEDED 0 #define KVM_BP_HARDEN_NOT_REQUIRED 1 diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index a3a6a2ba9a63..fe57f60f06a8 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -47,6 +47,13 @@ #define read_sysreg_el2(r) read_sysreg_elx(r, _EL2, _EL1) #define write_sysreg_el2(v,r) write_sysreg_elx(v, r, _EL2, _EL1) +/* + * Without an __arch_swab32(), we fall back to ___constant_swab32(), but the + * static inline can allow the compiler to out-of-line this. KVM always wants + * the macro version as its always inlined. + */ +#define __kvm_swab32(x) ___constant_swab32(x) + int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu); void __vgic_v3_save_state(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 53d846f1bfe7..785762860c63 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -93,7 +93,7 @@ void kvm_update_va_mask(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); void kvm_compute_layout(void); -static inline unsigned long __kern_hyp_va(unsigned long v) +static __always_inline unsigned long __kern_hyp_va(unsigned long v) { asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n" "ror %0, %0, #1\n" @@ -473,6 +473,7 @@ static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, extern void *__kvm_bp_vect_base; extern int __kvm_harden_el2_vector_slot; +/* This is only called on a VHE system */ static inline void *kvm_get_hyp_vector(void) { struct bp_hardening_data *data = arm64_get_bp_hardening_data(); diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 0958ed6191aa..61fd26752adc 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -83,7 +83,7 @@ static inline bool is_kernel_in_hyp_mode(void) return read_sysreg(CurrentEL) == CurrentEL_EL2; } -static inline bool has_vhe(void) +static __always_inline bool has_vhe(void) { if (cpus_have_const_cap(ARM64_HAS_VIRT_HOST_EXTN)) return true; diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index dfe8dd172512..925086b46136 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -625,7 +625,7 @@ static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt) } /* Switch to the guest for VHE systems running in EL2 */ -int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) +static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; @@ -678,7 +678,42 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) return exit_code; } -NOKPROBE_SYMBOL(kvm_vcpu_run_vhe); +NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe); + +int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) +{ + int ret; + + local_daif_mask(); + + /* + * Having IRQs masked via PMR when entering the guest means the GIC + * will not signal the CPU of interrupts of lower priority, and the + * only way to get out will be via guest exceptions. + * Naturally, we want to avoid this. + * + * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a + * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. + */ + pmr_sync(); + + ret = __kvm_vcpu_run_vhe(vcpu); + + /* + * local_daif_restore() takes care to properly restore PSTATE.DAIF + * and the GIC PMR if the host is using IRQ priorities. + */ + local_daif_restore(DAIF_PROCCTX_NOIRQ); + + /* + * When we exit from the guest we change a number of CPU configuration + * parameters, such as traps. Make sure these changes take effect + * before running the host or additional guests. + */ + isb(); + + return ret; +} /* Switch to the guest for legacy non-VHE systems */ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c index 29ee1feba4eb..4f3a087e36d5 100644 --- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c +++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c @@ -69,14 +69,14 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu) u32 data = vcpu_get_reg(vcpu, rd); if (__is_be(vcpu)) { /* guest pre-swabbed data, undo this for writel() */ - data = swab32(data); + data = __kvm_swab32(data); } writel_relaxed(data, addr); } else { u32 data = readl_relaxed(addr); if (__is_be(vcpu)) { /* guest expects swabbed data */ - data = swab32(data); + data = __kvm_swab32(data); } vcpu_set_reg(vcpu, rd, data); } diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi index 5accda2767be..a3301bab9231 100644 --- a/arch/mips/boot/dts/ingenic/jz4740.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <dt-bindings/clock/jz4740-cgu.h> +#include <dt-bindings/clock/ingenic,tcu.h> / { #address-cells = <1>; @@ -45,14 +46,6 @@ #clock-cells = <1>; }; - watchdog: watchdog@10002000 { - compatible = "ingenic,jz4740-watchdog"; - reg = <0x10002000 0x10>; - - clocks = <&cgu JZ4740_CLK_RTC>; - clock-names = "rtc"; - }; - tcu: timer@10002000 { compatible = "ingenic,jz4740-tcu", "simple-mfd"; reg = <0x10002000 0x1000>; @@ -73,6 +66,14 @@ interrupt-parent = <&intc>; interrupts = <23 22 21>; + + watchdog: watchdog@0 { + compatible = "ingenic,jz4740-watchdog"; + reg = <0x0 0xc>; + + clocks = <&tcu TCU_CLK_WDT>; + clock-names = "wdt"; + }; }; rtc_dev: rtc@10003000 { diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi index f928329b034b..bb89653d16a3 100644 --- a/arch/mips/boot/dts/ingenic/jz4780.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <dt-bindings/clock/jz4780-cgu.h> +#include <dt-bindings/clock/ingenic,tcu.h> #include <dt-bindings/dma/jz4780-dma.h> / { @@ -67,6 +68,14 @@ interrupt-parent = <&intc>; interrupts = <27 26 25>; + + watchdog: watchdog@0 { + compatible = "ingenic,jz4780-watchdog"; + reg = <0x0 0xc>; + + clocks = <&tcu TCU_CLK_WDT>; + clock-names = "wdt"; + }; }; rtc_dev: rtc@10003000 { @@ -348,14 +357,6 @@ status = "disabled"; }; - watchdog: watchdog@10002000 { - compatible = "ingenic,jz4780-watchdog"; - reg = <0x10002000 0x10>; - - clocks = <&cgu JZ4780_CLK_RTCLK>; - clock-names = "rtc"; - }; - nemc: nemc@13410000 { compatible = "ingenic,jz4780-nemc"; reg = <0x13410000 0x10000>; diff --git a/arch/mips/boot/dts/ingenic/x1000.dtsi b/arch/mips/boot/dts/ingenic/x1000.dtsi index 4994c695a1a7..147f7d5c243a 100644 --- a/arch/mips/boot/dts/ingenic/x1000.dtsi +++ b/arch/mips/boot/dts/ingenic/x1000.dtsi @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <dt-bindings/clock/ingenic,tcu.h> #include <dt-bindings/clock/x1000-cgu.h> #include <dt-bindings/dma/x1000-dma.h> @@ -72,7 +73,7 @@ compatible = "ingenic,x1000-watchdog", "ingenic,jz4780-watchdog"; reg = <0x0 0x10>; - clocks = <&cgu X1000_CLK_RTCLK>; + clocks = <&tcu TCU_CLK_WDT>; clock-names = "wdt"; }; }; @@ -158,7 +159,6 @@ i2c0: i2c-controller@10050000 { compatible = "ingenic,x1000-i2c"; reg = <0x10050000 0x1000>; - #address-cells = <1>; #size-cells = <0>; @@ -173,7 +173,6 @@ i2c1: i2c-controller@10051000 { compatible = "ingenic,x1000-i2c"; reg = <0x10051000 0x1000>; - #address-cells = <1>; #size-cells = <0>; @@ -188,7 +187,6 @@ i2c2: i2c-controller@10052000 { compatible = "ingenic,x1000-i2c"; reg = <0x10052000 0x1000>; - #address-cells = <1>; #size-cells = <0>; diff --git a/arch/mips/include/asm/sync.h b/arch/mips/include/asm/sync.h index 7c6a1095f556..aabd097933fe 100644 --- a/arch/mips/include/asm/sync.h +++ b/arch/mips/include/asm/sync.h @@ -155,9 +155,11 @@ * effective barrier as noted by commit 6b07d38aaa52 ("MIPS: Octeon: Use * optimized memory barrier primitives."). Here we specify that the affected * sync instructions should be emitted twice. + * Note that this expression is evaluated by the assembler (not the compiler), + * and that the assembler evaluates '==' as 0 or -1, not 0 or 1. */ #ifdef CONFIG_CPU_CAVIUM_OCTEON -# define __SYNC_rpt(type) (1 + (type == __SYNC_wmb)) +# define __SYNC_rpt(type) (1 - (type == __SYNC_wmb)) #else # define __SYNC_rpt(type) 1 #endif diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 6176b9acba95..d0d832ab3d3b 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -134,7 +134,7 @@ void release_vpe(struct vpe *v) { list_del(&v->list); if (v->load_addr) - release_progmem(v); + release_progmem(v->load_addr); kfree(v); } diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index aa89a41dc5dd..d7fe8408603e 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -33,6 +33,7 @@ endif cflags-vdso := $(ccflags-vdso) \ $(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \ -O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \ + -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \ $(call cc-option, -fno-asynchronous-unwind-tables) \ $(call cc-option, -fno-stack-protector) @@ -51,6 +52,8 @@ endif CFLAGS_REMOVE_vgettimeofday.o = -pg +DISABLE_VDSO := n + # # For the pre-R6 code in arch/mips/vdso/vdso.h for locating # the base address of VDSO, the linker will emit a R_MIPS_PC32 @@ -64,11 +67,24 @@ CFLAGS_REMOVE_vgettimeofday.o = -pg ifndef CONFIG_CPU_MIPSR6 ifeq ($(call ld-ifversion, -lt, 225000000, y),y) $(warning MIPS VDSO requires binutils >= 2.25) - obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y)) - ccflags-vdso += -DDISABLE_MIPS_VDSO + DISABLE_VDSO := y endif endif +# +# GCC (at least up to version 9.2) appears to emit function calls that make use +# of the GOT when targeting microMIPS, which we can't use in the VDSO due to +# the lack of relocations. As such, we disable the VDSO for microMIPS builds. +# +ifdef CONFIG_CPU_MICROMIPS + DISABLE_VDSO := y +endif + +ifeq ($(DISABLE_VDSO),y) + obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y)) + ccflags-vdso += -DDISABLE_MIPS_VDSO +endif + # VDSO linker flags. VDSO_LDFLAGS := \ -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 \ @@ -81,12 +97,18 @@ GCOV_PROFILE := n UBSAN_SANITIZE := n KCOV_INSTRUMENT := n +# Check that we don't have PIC 'jalr t9' calls left +quiet_cmd_vdso_mips_check = VDSOCHK $@ + cmd_vdso_mips_check = if $(OBJDUMP) --disassemble $@ | egrep -h "jalr.*t9" > /dev/null; \ + then (echo >&2 "$@: PIC 'jalr t9' calls are not supported"; \ + rm -f $@; /bin/false); fi + # # Shared build commands. # quiet_cmd_vdsold_and_vdso_check = LD $@ - cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check) + cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check); $(cmd_vdso_mips_check) quiet_cmd_vdsold = VDSO $@ cmd_vdsold = $(CC) $(c_flags) $(VDSO_LDFLAGS) \ diff --git a/arch/riscv/boot/.gitignore b/arch/riscv/boot/.gitignore index 8dab0bb6ae66..8a45a37d2af4 100644 --- a/arch/riscv/boot/.gitignore +++ b/arch/riscv/boot/.gitignore @@ -1,2 +1,4 @@ Image Image.gz +loader +loader.lds diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 435b65532e29..8e18d2c64399 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -72,6 +72,16 @@ #define EXC_LOAD_PAGE_FAULT 13 #define EXC_STORE_PAGE_FAULT 15 +/* PMP configuration */ +#define PMP_R 0x01 +#define PMP_W 0x02 +#define PMP_X 0x04 +#define PMP_A 0x18 +#define PMP_A_TOR 0x08 +#define PMP_A_NA4 0x10 +#define PMP_A_NAPOT 0x18 +#define PMP_L 0x80 + /* symbolic CSR names: */ #define CSR_CYCLE 0xc00 #define CSR_TIME 0xc01 @@ -100,6 +110,8 @@ #define CSR_MCAUSE 0x342 #define CSR_MTVAL 0x343 #define CSR_MIP 0x344 +#define CSR_PMPCFG0 0x3a0 +#define CSR_PMPADDR0 0x3b0 #define CSR_MHARTID 0xf14 #ifdef CONFIG_RISCV_M_MODE diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 271860fc2c3f..85f2073e7fe4 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -58,6 +58,12 @@ _start_kernel: /* Reset all registers except ra, a0, a1 */ call reset_regs + /* Setup a PMP to permit access to all of memory. */ + li a0, -1 + csrw CSR_PMPADDR0, a0 + li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X) + csrw CSR_PMPCFG0, a0 + /* * The hartid in a0 is expected later on, and we have no firmware * to hand it to us. diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index f4cad5163bf2..ffb3d94bf0cc 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -156,6 +156,6 @@ void __init trap_init(void) csr_write(CSR_SCRATCH, 0); /* Set the exception vector address */ csr_write(CSR_TVEC, &handle_exception); - /* Enable all interrupts */ - csr_write(CSR_IE, -1); + /* Enable interrupts */ + csr_write(CSR_IE, IE_SIE | IE_EIE); } diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index f0cc86040587..ec0ca90dd900 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -19,18 +19,20 @@ asmlinkage void __init kasan_early_init(void) for (i = 0; i < PTRS_PER_PTE; ++i) set_pte(kasan_early_shadow_pte + i, mk_pte(virt_to_page(kasan_early_shadow_page), - PAGE_KERNEL)); + PAGE_KERNEL)); for (i = 0; i < PTRS_PER_PMD; ++i) set_pmd(kasan_early_shadow_pmd + i, - pfn_pmd(PFN_DOWN(__pa((uintptr_t)kasan_early_shadow_pte)), - __pgprot(_PAGE_TABLE))); + pfn_pmd(PFN_DOWN + (__pa((uintptr_t) kasan_early_shadow_pte)), + __pgprot(_PAGE_TABLE))); for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END; i += PGDIR_SIZE, ++pgd) set_pgd(pgd, - pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))), - __pgprot(_PAGE_TABLE))); + pfn_pgd(PFN_DOWN + (__pa(((uintptr_t) kasan_early_shadow_pmd))), + __pgprot(_PAGE_TABLE))); /* init for swapper_pg_dir */ pgd = pgd_offset_k(KASAN_SHADOW_START); @@ -38,37 +40,43 @@ asmlinkage void __init kasan_early_init(void) for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END; i += PGDIR_SIZE, ++pgd) set_pgd(pgd, - pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))), - __pgprot(_PAGE_TABLE))); + pfn_pgd(PFN_DOWN + (__pa(((uintptr_t) kasan_early_shadow_pmd))), + __pgprot(_PAGE_TABLE))); flush_tlb_all(); } static void __init populate(void *start, void *end) { - unsigned long i; + unsigned long i, offset; unsigned long vaddr = (unsigned long)start & PAGE_MASK; unsigned long vend = PAGE_ALIGN((unsigned long)end); unsigned long n_pages = (vend - vaddr) / PAGE_SIZE; + unsigned long n_ptes = + ((n_pages + PTRS_PER_PTE) & -PTRS_PER_PTE) / PTRS_PER_PTE; unsigned long n_pmds = - (n_pages % PTRS_PER_PTE) ? n_pages / PTRS_PER_PTE + 1 : - n_pages / PTRS_PER_PTE; + ((n_ptes + PTRS_PER_PMD) & -PTRS_PER_PMD) / PTRS_PER_PMD; + + pte_t *pte = + memblock_alloc(n_ptes * PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); + pmd_t *pmd = + memblock_alloc(n_pmds * PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); pgd_t *pgd = pgd_offset_k(vaddr); - pmd_t *pmd = memblock_alloc(n_pmds * sizeof(pmd_t), PAGE_SIZE); - pte_t *pte = memblock_alloc(n_pages * sizeof(pte_t), PAGE_SIZE); for (i = 0; i < n_pages; i++) { phys_addr_t phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); - - set_pte(pte + i, pfn_pte(PHYS_PFN(phys), PAGE_KERNEL)); + set_pte(&pte[i], pfn_pte(PHYS_PFN(phys), PAGE_KERNEL)); } - for (i = 0; i < n_pmds; ++pgd, i += PTRS_PER_PMD) - set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(((uintptr_t)(pmd + i)))), + for (i = 0, offset = 0; i < n_ptes; i++, offset += PTRS_PER_PTE) + set_pmd(&pmd[i], + pfn_pmd(PFN_DOWN(__pa(&pte[offset])), __pgprot(_PAGE_TABLE))); - for (i = 0; i < n_pages; ++pmd, i += PTRS_PER_PTE) - set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa((uintptr_t)(pte + i))), + for (i = 0, offset = 0; i < n_pmds; i++, offset += PTRS_PER_PMD) + set_pgd(&pgd[i], + pfn_pgd(PFN_DOWN(__pa(&pmd[offset])), __pgprot(_PAGE_TABLE))); flush_tlb_all(); @@ -81,7 +89,8 @@ void __init kasan_init(void) unsigned long i; kasan_populate_early_shadow((void *)KASAN_SHADOW_START, - (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); + (void *)kasan_mem_to_shadow((void *) + VMALLOC_END)); for_each_memblock(memory, reg) { void *start = (void *)__va(reg->base); @@ -90,14 +99,14 @@ void __init kasan_init(void) if (start >= end) break; - populate(kasan_mem_to_shadow(start), - kasan_mem_to_shadow(end)); + populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end)); }; for (i = 0; i < PTRS_PER_PTE; i++) set_pte(&kasan_early_shadow_pte[i], mk_pte(virt_to_page(kasan_early_shadow_page), - __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_ACCESSED))); + __pgprot(_PAGE_PRESENT | _PAGE_READ | + _PAGE_ACCESSED))); memset(kasan_early_shadow_page, 0, PAGE_SIZE); init_task.kasan_depth = 0; diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h index 02c6ef8f7667..07344d82e88e 100644 --- a/arch/x86/include/asm/io_bitmap.h +++ b/arch/x86/include/asm/io_bitmap.h @@ -19,7 +19,14 @@ struct task_struct; void io_bitmap_share(struct task_struct *tsk); void io_bitmap_exit(void); -void tss_update_io_bitmap(void); +void native_tss_update_io_bitmap(void); + +#ifdef CONFIG_PARAVIRT_XXL +#include <asm/paravirt.h> +#else +#define tss_update_io_bitmap native_tss_update_io_bitmap +#endif + #else static inline void io_bitmap_share(struct task_struct *tsk) { } static inline void io_bitmap_exit(void) { } diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 03946eb3e2b9..2a8f2bd2e5cf 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -292,6 +292,14 @@ enum x86emul_mode { #define X86EMUL_SMM_MASK (1 << 6) #define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7) +/* + * fastop functions are declared as taking a never-defined fastop parameter, + * so they can't be called from C directly. + */ +struct fastop; + +typedef void (*fastop_t)(struct fastop *); + struct x86_emulate_ctxt { const struct x86_emulate_ops *ops; @@ -324,7 +332,10 @@ struct x86_emulate_ctxt { struct operand src; struct operand src2; struct operand dst; - int (*execute)(struct x86_emulate_ctxt *ctxt); + union { + int (*execute)(struct x86_emulate_ctxt *ctxt); + fastop_t fop; + }; int (*check_perm)(struct x86_emulate_ctxt *ctxt); /* * The following six fields are cleared together, diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 40a0c0fd95ca..98959e8cd448 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1122,6 +1122,7 @@ struct kvm_x86_ops { int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); + void (*update_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); void (*patch_hypercall)(struct kvm_vcpu *vcpu, @@ -1146,7 +1147,7 @@ struct kvm_x86_ops { void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); - void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); + int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 86e7317eb31f..694d8daf4983 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -295,6 +295,13 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g); } +#ifdef CONFIG_X86_IOPL_IOPERM +static inline void tss_update_io_bitmap(void) +{ + PVOP_VCALL0(cpu.update_io_bitmap); +} +#endif + static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 84812964d3dd..732f62e04ddb 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -140,6 +140,10 @@ struct pv_cpu_ops { void (*load_sp0)(unsigned long sp0); +#ifdef CONFIG_X86_IOPL_IOPERM + void (*update_io_bitmap)(void); +#endif + void (*wbinvd)(void); /* cpuid emulation, mostly so that caps bits can be disabled */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2a85287b3685..8521af3fef27 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -72,7 +72,7 @@ #define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC) #define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA) #define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING) -#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE 0x04000000 +#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE) #define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING) #define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING) diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index a50e4a0de315..9915990fd8cf 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/arch/x86/include/asm/vmxfeatures.h @@ -81,6 +81,7 @@ #define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */ #define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* "" Processor Trace logs GPAs */ #define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */ +#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */ #define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */ #endif /* _ASM_X86_VMXFEATURES_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 503d3f42da16..3f3f780c8c65 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -390,6 +390,7 @@ struct kvm_sync_regs { #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 #define KVM_STATE_NESTED_EVMCS 0x00000004 +#define KVM_STATE_NESTED_MTF_PENDING 0x00000008 #define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_SMM_VMXON 0x00000002 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 52c9bfbbdb2a..4cdb123ff66a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -445,7 +445,7 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c) * cpuid bit to be set. We need to ensure that we * update that bit in this CPU's "cpu_info". */ - get_cpu_cap(c); + set_cpu_cap(c, X86_FEATURE_OSPKE); } #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d817f255aed8..6efe0410fb72 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -425,7 +425,29 @@ static void __init sev_map_percpu_data(void) } } +static bool pv_tlb_flush_supported(void) +{ + return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); +} + +static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask); + #ifdef CONFIG_SMP + +static bool pv_ipi_supported(void) +{ + return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI); +} + +static bool pv_sched_yield_supported(void) +{ + return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)); +} + #define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG) static void __send_ipi_mask(const struct cpumask *mask, int vector) @@ -490,12 +512,12 @@ static void kvm_send_ipi_mask(const struct cpumask *mask, int vector) static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) { unsigned int this_cpu = smp_processor_id(); - struct cpumask new_mask; + struct cpumask *new_mask = this_cpu_cpumask_var_ptr(__pv_cpu_mask); const struct cpumask *local_mask; - cpumask_copy(&new_mask, mask); - cpumask_clear_cpu(this_cpu, &new_mask); - local_mask = &new_mask; + cpumask_copy(new_mask, mask); + cpumask_clear_cpu(this_cpu, new_mask); + local_mask = new_mask; __send_ipi_mask(local_mask, vector); } @@ -575,7 +597,6 @@ static void __init kvm_apf_trap_init(void) update_intr_gate(X86_TRAP_PF, async_page_fault); } -static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask); static void kvm_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info) @@ -583,7 +604,7 @@ static void kvm_flush_tlb_others(const struct cpumask *cpumask, u8 state; int cpu; struct kvm_steal_time *src; - struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask); + struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_cpu_mask); cpumask_copy(flushmask, cpumask); /* @@ -619,11 +640,10 @@ static void __init kvm_guest_init(void) pv_ops.time.steal_clock = kvm_steal_clock; } - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_tlb_flush_supported()) { pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others; pv_ops.mmu.tlb_remove_table = tlb_remove_table; + pr_info("KVM setup pv remote TLB flush\n"); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) @@ -632,9 +652,7 @@ static void __init kvm_guest_init(void) #ifdef CONFIG_SMP smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus; smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; - if (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_sched_yield_supported()) { smp_ops.send_call_func_ipi = kvm_smp_send_call_func_ipi; pr_info("KVM setup pv sched yield\n"); } @@ -700,7 +718,7 @@ static uint32_t __init kvm_detect(void) static void __init kvm_apic_init(void) { #if defined(CONFIG_SMP) - if (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI)) + if (pv_ipi_supported()) kvm_setup_pv_ipi(); #endif } @@ -732,26 +750,31 @@ static __init int activate_jump_labels(void) } arch_initcall(activate_jump_labels); -static __init int kvm_setup_pv_tlb_flush(void) +static __init int kvm_alloc_cpumask(void) { int cpu; + bool alloc = false; if (!kvm_para_available() || nopv) return 0; - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_REALTIME) && - kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + if (pv_tlb_flush_supported()) + alloc = true; + +#if defined(CONFIG_SMP) + if (pv_ipi_supported()) + alloc = true; +#endif + + if (alloc) for_each_possible_cpu(cpu) { - zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), + zalloc_cpumask_var_node(per_cpu_ptr(&__pv_cpu_mask, cpu), GFP_KERNEL, cpu_to_node(cpu)); } - pr_info("KVM setup pv remote TLB flush\n"); - } return 0; } -arch_initcall(kvm_setup_pv_tlb_flush); +arch_initcall(kvm_alloc_cpumask); #ifdef CONFIG_PARAVIRT_SPINLOCKS diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 789f5e4f89de..c131ba4e70ef 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -30,6 +30,7 @@ #include <asm/timer.h> #include <asm/special_insns.h> #include <asm/tlb.h> +#include <asm/io_bitmap.h> /* * nop stub, which must not clobber anything *including the stack* to @@ -341,6 +342,10 @@ struct paravirt_patch_template pv_ops = { .cpu.iret = native_iret, .cpu.swapgs = native_swapgs, +#ifdef CONFIG_X86_IOPL_IOPERM + .cpu.update_io_bitmap = native_tss_update_io_bitmap, +#endif + .cpu.start_context_switch = paravirt_nop, .cpu.end_context_switch = paravirt_nop, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 839b5244e3b7..3053c85e0e42 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -374,7 +374,7 @@ static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) /** * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode */ -void tss_update_io_bitmap(void) +void native_tss_update_io_bitmap(void) { struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); struct thread_struct *t = ¤t->thread; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 991019d5eee1..1bb4927030af 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -59,6 +59,19 @@ config KVM If unsure, say N. +config KVM_WERROR + bool "Compile KVM with -Werror" + # KASAN may cause the build to fail due to larger frames + default y if X86_64 && !KASAN + # We use the dependency on !COMPILE_TEST to not be enabled + # blindly in allmodconfig or allyesconfig configurations + depends on (X86_64 && !KASAN) || !COMPILE_TEST + depends on EXPERT + help + Add -Werror to the build flags for (and only for) i915.ko. + + If in doubt, say "N". + config KVM_INTEL tristate "KVM for Intel (and compatible) processors support" depends on KVM && IA32_FEAT_CTL diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index b19ef421084d..e553f0fdd87d 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 ccflags-y += -Iarch/x86/kvm +ccflags-$(CONFIG_KVM_WERROR) += -Werror KVM := ../../../virt/kvm diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ddbc61984227..dd19fb3539e0 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -191,25 +191,6 @@ #define NR_FASTOP (ilog2(sizeof(ulong)) + 1) #define FASTOP_SIZE 8 -/* - * fastop functions have a special calling convention: - * - * dst: rax (in/out) - * src: rdx (in/out) - * src2: rcx (in) - * flags: rflags (in/out) - * ex: rsi (in:fastop pointer, out:zero if exception) - * - * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for - * different operand sizes can be reached by calculation, rather than a jump - * table (which would be bigger than the code). - * - * fastop functions are declared as taking a never-defined fastop parameter, - * so they can't be called from C directly. - */ - -struct fastop; - struct opcode { u64 flags : 56; u64 intercept : 8; @@ -311,8 +292,19 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) #define ON64(x) #endif -typedef void (*fastop_t)(struct fastop *); - +/* + * fastop functions have a special calling convention: + * + * dst: rax (in/out) + * src: rdx (in/out) + * src2: rcx (in) + * flags: rflags (in/out) + * ex: rsi (in:fastop pointer, out:zero if exception) + * + * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for + * different operand sizes can be reached by calculation, rather than a jump + * table (which would be bigger than the code). + */ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define __FOP_FUNC(name) \ @@ -5683,7 +5675,7 @@ special_insn: if (ctxt->execute) { if (ctxt->d & Fastop) - rc = fastop(ctxt, (fastop_t)ctxt->execute); + rc = fastop(ctxt, ctxt->fop); else rc = ctxt->execute(ctxt); if (rc != X86EMUL_CONTINUE) diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 79afa0bb5f41..c47d2acec529 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -417,7 +417,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, kvm_set_msi_irq(vcpu->kvm, entry, &irq); - if (irq.level && + if (irq.trig_mode && kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, irq.dest_id, irq.dest_mode)) __set_bit(irq.vector, ioapic_handled_vectors); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index afcd30d44cbb..e3099c642fec 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -627,9 +627,11 @@ static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) { u8 val; - if (pv_eoi_get_user(vcpu, &val) < 0) + if (pv_eoi_get_user(vcpu, &val) < 0) { printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n", (unsigned long long)vcpu->arch.pv_eoi.msr_val); + return false; + } return val & 0x1; } @@ -1046,11 +1048,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic->regs + APIC_TMR); } - if (vcpu->arch.apicv_active) - kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); - else { + if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) { kvm_lapic_set_irr(vector, apic); - kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 3c6522b84ff1..ffcd96fc02d0 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -339,7 +339,7 @@ TRACE_EVENT( /* These depend on page entry type, so compute them now. */ __field(bool, r) __field(bool, x) - __field(u8, u) + __field(signed char, u) ), TP_fast_assign( diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index bef0ba35f121..24c0b2ba8fb9 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -57,11 +57,13 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); +#ifdef MODULE static const struct x86_cpu_id svm_cpu_id[] = { X86_FEATURE_MATCH(X86_FEATURE_SVM), {} }; MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); +#endif #define IOPM_ALLOC_ORDER 2 #define MSRPM_ALLOC_ORDER 1 @@ -1005,33 +1007,32 @@ static void svm_cpu_uninit(int cpu) static int svm_cpu_init(int cpu) { struct svm_cpu_data *sd; - int r; sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); if (!sd) return -ENOMEM; sd->cpu = cpu; - r = -ENOMEM; sd->save_area = alloc_page(GFP_KERNEL); if (!sd->save_area) - goto err_1; + goto free_cpu_data; if (svm_sev_enabled()) { - r = -ENOMEM; sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1, sizeof(void *), GFP_KERNEL); if (!sd->sev_vmcbs) - goto err_1; + goto free_save_area; } per_cpu(svm_data, cpu) = sd; return 0; -err_1: +free_save_area: + __free_page(sd->save_area); +free_cpu_data: kfree(sd); - return r; + return -ENOMEM; } @@ -1350,6 +1351,24 @@ static __init void svm_adjust_mmio_mask(void) kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); } +static void svm_hardware_teardown(void) +{ + int cpu; + + if (svm_sev_enabled()) { + bitmap_free(sev_asid_bitmap); + bitmap_free(sev_reclaim_asid_bitmap); + + sev_flush_asids(); + } + + for_each_possible_cpu(cpu) + svm_cpu_uninit(cpu); + + __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); + iopm_base = 0; +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1463,29 +1482,10 @@ static __init int svm_hardware_setup(void) return 0; err: - __free_pages(iopm_pages, IOPM_ALLOC_ORDER); - iopm_base = 0; + svm_hardware_teardown(); return r; } -static __exit void svm_hardware_unsetup(void) -{ - int cpu; - - if (svm_sev_enabled()) { - bitmap_free(sev_asid_bitmap); - bitmap_free(sev_reclaim_asid_bitmap); - - sev_flush_asids(); - } - - for_each_possible_cpu(cpu) - svm_cpu_uninit(cpu); - - __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); - iopm_base = 0; -} - static void init_seg(struct vmcb_seg *seg) { seg->selector = 0; @@ -2196,8 +2196,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) static int avic_init_vcpu(struct vcpu_svm *svm) { int ret; + struct kvm_vcpu *vcpu = &svm->vcpu; - if (!kvm_vcpu_apicv_active(&svm->vcpu)) + if (!avic || !irqchip_in_kernel(vcpu->kvm)) return 0; ret = avic_init_backing_page(&svm->vcpu); @@ -5232,6 +5233,9 @@ static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) struct vmcb *vmcb = svm->vmcb; bool activated = kvm_vcpu_apicv_active(vcpu); + if (!avic) + return; + if (activated) { /** * During AVIC temporary deactivation, guest could update @@ -5255,8 +5259,11 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) +static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) { + if (!vcpu->arch.apicv_active) + return -1; + kvm_lapic_set_irr(vec, vcpu->arch.apic); smp_mb__after_atomic(); @@ -5268,6 +5275,8 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) put_cpu(); } else kvm_vcpu_wake_up(vcpu); + + return 0; } static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) @@ -7378,7 +7387,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, .hardware_setup = svm_hardware_setup, - .hardware_unsetup = svm_hardware_unsetup, + .hardware_unsetup = svm_hardware_teardown, .check_processor_compatibility = svm_check_processor_compat, .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, @@ -7433,6 +7442,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .run = svm_vcpu_run, .handle_exit = handle_exit, .skip_emulated_instruction = skip_emulated_instruction, + .update_emulated_instruction = NULL, .set_interrupt_shadow = svm_set_interrupt_shadow, .get_interrupt_shadow = svm_get_interrupt_shadow, .patch_hypercall = svm_patch_hypercall, diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 283bdb7071af..f486e2606247 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -12,6 +12,7 @@ extern bool __read_mostly enable_ept; extern bool __read_mostly enable_unrestricted_guest; extern bool __read_mostly enable_ept_ad_bits; extern bool __read_mostly enable_pml; +extern bool __read_mostly enable_apicv; extern int __read_mostly pt_mode; #define PT_MODE_SYSTEM 0 diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 3589cd3c0fcc..e920d7834d73 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3161,10 +3161,10 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume. * * Returns: - * NVMX_ENTRY_SUCCESS: Entered VMX non-root mode - * NVMX_ENTRY_VMFAIL: Consistency check VMFail - * NVMX_ENTRY_VMEXIT: Consistency check VMExit - * NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error + * NVMX_VMENTRY_SUCCESS: Entered VMX non-root mode + * NVMX_VMENTRY_VMFAIL: Consistency check VMFail + * NVMX_VMENTRY_VMEXIT: Consistency check VMExit + * NVMX_VMENTRY_KVM_INTERNAL_ERROR: KVM internal error */ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) @@ -3609,8 +3609,15 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) unsigned long exit_qual; bool block_nested_events = vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu); + bool mtf_pending = vmx->nested.mtf_pending; struct kvm_lapic *apic = vcpu->arch.apic; + /* + * Clear the MTF state. If a higher priority VM-exit is delivered first, + * this state is discarded. + */ + vmx->nested.mtf_pending = false; + if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { if (block_nested_events) @@ -3621,8 +3628,28 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } + /* + * Process any exceptions that are not debug traps before MTF. + */ + if (vcpu->arch.exception.pending && + !vmx_pending_dbg_trap(vcpu) && + nested_vmx_check_exception(vcpu, &exit_qual)) { + if (block_nested_events) + return -EBUSY; + nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + return 0; + } + + if (mtf_pending) { + if (block_nested_events) + return -EBUSY; + nested_vmx_update_pending_dbg(vcpu); + nested_vmx_vmexit(vcpu, EXIT_REASON_MONITOR_TRAP_FLAG, 0, 0); + return 0; + } + if (vcpu->arch.exception.pending && - nested_vmx_check_exception(vcpu, &exit_qual)) { + nested_vmx_check_exception(vcpu, &exit_qual)) { if (block_nested_events) return -EBUSY; nested_vmx_inject_exception_vmexit(vcpu, exit_qual); @@ -5285,24 +5312,17 @@ fail: return 1; } - -static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) +/* + * Return true if an IO instruction with the specified port and size should cause + * a VM-exit into L1. + */ +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size) { - unsigned long exit_qualification; + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); gpa_t bitmap, last_bitmap; - unsigned int port; - int size; u8 b; - if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) - return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - - port = exit_qualification >> 16; - size = (exit_qualification & 7) + 1; - last_bitmap = (gpa_t)-1; b = -1; @@ -5329,8 +5349,26 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, return false; } +static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ + unsigned long exit_qualification; + unsigned short port; + int size; + + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING); + + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); + + port = exit_qualification >> 16; + size = (exit_qualification & 7) + 1; + + return nested_vmx_check_io_bitmaps(vcpu, port, size); +} + /* - * Return 1 if we should exit from L2 to L1 to handle an MSR access access, + * Return 1 if we should exit from L2 to L1 to handle an MSR access, * rather than handle it ourselves in L0. I.e., check whether L1 expressed * disinterest in the current event (read or write a specific MSR) by using an * MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps. @@ -5712,6 +5750,9 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (vmx->nested.nested_run_pending) kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING; + + if (vmx->nested.mtf_pending) + kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING; } } @@ -5892,6 +5933,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmx->nested.nested_run_pending = !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); + vmx->nested.mtf_pending = + !!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING); + ret = -EINVAL; if (nested_cpu_has_shadow_vmcs(vmcs12) && vmcs12->vmcs_link_pointer != -1ull) { @@ -5949,8 +5993,7 @@ void nested_vmx_set_vmcs_shadowing_bitmap(void) * bit in the high half is on if the corresponding bit in the control field * may be on. See also vmx_control_verify(). */ -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv) +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps) { /* * Note that as a general rule, the high half of the MSRs (bits in @@ -5977,7 +6020,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS | - (apicv ? PIN_BASED_POSTED_INTR : 0); + (enable_apicv ? PIN_BASED_POSTED_INTR : 0); msrs->pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index fc874d4ead0f..9aeda46f473e 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -17,8 +17,7 @@ enum nvmx_vmentry_status { }; void vmx_leave_nested(struct kvm_vcpu *vcpu); -void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, - bool apicv); +void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps); void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_set_vmcs_shadowing_bitmap(void); @@ -34,6 +33,8 @@ int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata); int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, u32 vmx_instruction_info, bool wr, int len, gva_t *ret); void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu); +bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, + int size); static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { @@ -175,6 +176,11 @@ static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12) return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS; } +static inline int nested_cpu_has_mtf(struct vmcs12 *vmcs12) +{ + return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG); +} + static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12) { return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 3be25ecae145..40b1e6138cd5 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -64,11 +64,13 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); +#ifdef MODULE static const struct x86_cpu_id vmx_cpu_id[] = { X86_FEATURE_MATCH(X86_FEATURE_VMX), {} }; MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id); +#endif bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); @@ -95,7 +97,7 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO); static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); -static bool __read_mostly enable_apicv = 1; +bool __read_mostly enable_apicv = 1; module_param(enable_apicv, bool, S_IRUGO); /* @@ -1175,6 +1177,10 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmx->guest_msrs[i].mask); } + + if (vmx->nested.need_vmcs12_to_shadow_sync) + nested_sync_vmcs12_to_shadow(vcpu); + if (vmx->guest_state_loaded) return; @@ -1599,6 +1605,40 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) return 1; } + +/* + * Recognizes a pending MTF VM-exit and records the nested state for later + * delivery. + */ +static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!is_guest_mode(vcpu)) + return; + + /* + * Per the SDM, MTF takes priority over debug-trap exceptions besides + * T-bit traps. As instruction emulation is completed (i.e. at the + * instruction boundary), any #DB exception pending delivery must be a + * debug-trap. Record the pending MTF state to be delivered in + * vmx_check_nested_events(). + */ + if (nested_cpu_has_mtf(vmcs12) && + (!vcpu->arch.exception.pending || + vcpu->arch.exception.nr == DB_VECTOR)) + vmx->nested.mtf_pending = true; + else + vmx->nested.mtf_pending = false; +} + +static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + vmx_update_emulated_instruction(vcpu); + return skip_emulated_instruction(vcpu); +} + static void vmx_clear_hlt(struct kvm_vcpu *vcpu) { /* @@ -3818,24 +3858,29 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, * 2. If target vcpu isn't running(root mode), kick it to pick up the * interrupt from PIR in next vmentry. */ -static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) +static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vmx *vmx = to_vmx(vcpu); int r; r = vmx_deliver_nested_posted_interrupt(vcpu, vector); if (!r) - return; + return 0; + + if (!vcpu->arch.apicv_active) + return -1; if (pi_test_and_set_pir(vector, &vmx->pi_desc)) - return; + return 0; /* If a previous notification has sent the IPI, nothing to do. */ if (pi_test_and_set_on(&vmx->pi_desc)) - return; + return 0; if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); + + return 0; } /* @@ -6482,8 +6527,11 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_write32(PLE_WINDOW, vmx->ple_window); } - if (vmx->nested.need_vmcs12_to_shadow_sync) - nested_sync_vmcs12_to_shadow(vcpu); + /* + * We did this in prepare_switch_to_guest, because it needs to + * be within srcu_read_lock. + */ + WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync); if (kvm_register_is_dirty(vcpu, VCPU_REGS_RSP)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); @@ -6757,8 +6805,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, - vmx_capability.ept, - kvm_vcpu_apicv_active(vcpu)); + vmx_capability.ept); else memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs)); @@ -6839,8 +6886,7 @@ static int __init vmx_check_processor_compat(void) if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) return -EIO; if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept, - enable_apicv); + nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept); if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", smp_processor_id()); @@ -7101,6 +7147,40 @@ static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) to_vmx(vcpu)->req_immediate_exit = true; } +static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + unsigned short port; + bool intercept; + int size; + + if (info->intercept == x86_intercept_in || + info->intercept == x86_intercept_ins) { + port = info->src_val; + size = info->dst_bytes; + } else { + port = info->dst_val; + size = info->src_bytes; + } + + /* + * If the 'use IO bitmaps' VM-execution control is 0, IO instruction + * VM-exits depend on the 'unconditional IO exiting' VM-execution + * control. + * + * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps. + */ + if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS)) + intercept = nested_cpu_has(vmcs12, + CPU_BASED_UNCOND_IO_EXITING); + else + intercept = nested_vmx_check_io_bitmaps(vcpu, port, size); + + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; +} + static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage) @@ -7108,19 +7188,45 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + switch (info->intercept) { /* * RDPID causes #UD if disabled through secondary execution controls. * Because it is marked as EmulateOnUD, we need to intercept it here. */ - if (info->intercept == x86_intercept_rdtscp && - !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { - ctxt->exception.vector = UD_VECTOR; - ctxt->exception.error_code_valid = false; - return X86EMUL_PROPAGATE_FAULT; - } + case x86_intercept_rdtscp: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { + ctxt->exception.vector = UD_VECTOR; + ctxt->exception.error_code_valid = false; + return X86EMUL_PROPAGATE_FAULT; + } + break; + + case x86_intercept_in: + case x86_intercept_ins: + case x86_intercept_out: + case x86_intercept_outs: + return vmx_check_intercept_io(vcpu, info); + + case x86_intercept_lgdt: + case x86_intercept_lidt: + case x86_intercept_lldt: + case x86_intercept_ltr: + case x86_intercept_sgdt: + case x86_intercept_sidt: + case x86_intercept_sldt: + case x86_intercept_str: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC)) + return X86EMUL_CONTINUE; + + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + break; /* TODO: check more intercepts... */ - return X86EMUL_CONTINUE; + default: + break; + } + + return X86EMUL_UNHANDLEABLE; } #ifdef CONFIG_X86_64 @@ -7702,7 +7808,7 @@ static __init int hardware_setup(void) if (nested) { nested_vmx_setup_ctls_msrs(&vmcs_config.nested, - vmx_capability.ept, enable_apicv); + vmx_capability.ept); r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers); if (r) @@ -7786,7 +7892,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .run = vmx_vcpu_run, .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, + .skip_emulated_instruction = vmx_skip_emulated_instruction, + .update_emulated_instruction = vmx_update_emulated_instruction, .set_interrupt_shadow = vmx_set_interrupt_shadow, .get_interrupt_shadow = vmx_get_interrupt_shadow, .patch_hypercall = vmx_patch_hypercall, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7f42cf3dcd70..e64da06c7009 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -150,6 +150,9 @@ struct nested_vmx { /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + /* Pending MTF VM-exit into L1. */ + bool mtf_pending; + struct loaded_vmcs vmcs02; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fb5d64ebc35d..5de200663f51 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6891,6 +6891,8 @@ restart: kvm_rip_write(vcpu, ctxt->eip); if (r && ctxt->tf) r = kvm_vcpu_do_singlestep(vcpu); + if (kvm_x86_ops->update_emulated_instruction) + kvm_x86_ops->update_emulated_instruction(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } @@ -7188,15 +7190,15 @@ static void kvm_timer_init(void) if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { #ifdef CONFIG_CPU_FREQ - struct cpufreq_policy policy; + struct cpufreq_policy *policy; int cpu; - memset(&policy, 0, sizeof(policy)); cpu = get_cpu(); - cpufreq_get_policy(&policy, cpu); - if (policy.cpuinfo.max_freq) - max_tsc_khz = policy.cpuinfo.max_freq; + policy = cpufreq_cpu_get(cpu); + if (policy && policy->cpuinfo.max_freq) + max_tsc_khz = policy->cpuinfo.max_freq; put_cpu(); + cpufreq_cpu_put(policy); #endif cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); @@ -7306,12 +7308,12 @@ int kvm_arch_init(void *opaque) } if (!ops->cpu_has_kvm_support()) { - printk(KERN_ERR "kvm: no hardware support\n"); + pr_err_ratelimited("kvm: no hardware support\n"); r = -EOPNOTSUPP; goto out; } if (ops->disabled_by_bios()) { - printk(KERN_ERR "kvm: disabled by bios\n"); + pr_err_ratelimited("kvm: disabled by bios\n"); r = -EOPNOTSUPP; goto out; } diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 64229dad7eab..69309cd56fdf 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -363,13 +363,8 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, { const struct ptdump_range ptdump_ranges[] = { #ifdef CONFIG_X86_64 - -#define normalize_addr_shift (64 - (__VIRTUAL_MASK_SHIFT + 1)) -#define normalize_addr(u) ((signed long)((u) << normalize_addr_shift) >> \ - normalize_addr_shift) - {0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2}, - {normalize_addr(PTRS_PER_PGD * PGD_LEVEL_MULT / 2), ~0UL}, + {GUARD_HOLE_END_ADDR, ~0UL}, #else {0, ~0UL}, #endif diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index fa8506e76bbe..d19a2edd63cb 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -180,7 +180,7 @@ void efi_sync_low_kernel_mappings(void) static inline phys_addr_t virt_to_phys_or_null_size(void *va, unsigned long size) { - bool bad_size; + phys_addr_t pa; if (!va) return 0; @@ -188,16 +188,13 @@ virt_to_phys_or_null_size(void *va, unsigned long size) if (virt_addr_valid(va)) return virt_to_phys(va); - /* - * A fully aligned variable on the stack is guaranteed not to - * cross a page bounary. Try to catch strings on the stack by - * checking that 'size' is a power of two. - */ - bad_size = size > PAGE_SIZE || !is_power_of_2(size); + pa = slow_virt_to_phys(va); - WARN_ON(!IS_ALIGNED((unsigned long)va, size) || bad_size); + /* check if the object crosses a page boundary */ + if (WARN_ON((pa ^ (pa + size - 1)) & PAGE_MASK)) + return 0; - return slow_virt_to_phys(va); + return pa; } #define virt_to_phys_or_null(addr) \ @@ -568,85 +565,25 @@ efi_thunk_set_virtual_address_map(unsigned long memory_map_size, static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc) { - efi_status_t status; - u32 phys_tm, phys_tc; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_tm = virt_to_phys_or_null(tm); - phys_tc = virt_to_phys_or_null(tc); - - status = efi_thunk(get_time, phys_tm, phys_tc); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static efi_status_t efi_thunk_set_time(efi_time_t *tm) { - efi_status_t status; - u32 phys_tm; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_tm = virt_to_phys_or_null(tm); - - status = efi_thunk(set_time, phys_tm); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static efi_status_t efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, efi_time_t *tm) { - efi_status_t status; - u32 phys_enabled, phys_pending, phys_tm; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_enabled = virt_to_phys_or_null(enabled); - phys_pending = virt_to_phys_or_null(pending); - phys_tm = virt_to_phys_or_null(tm); - - status = efi_thunk(get_wakeup_time, phys_enabled, - phys_pending, phys_tm); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static efi_status_t efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) { - efi_status_t status; - u32 phys_tm; - unsigned long flags; - - spin_lock(&rtc_lock); - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_tm = virt_to_phys_or_null(tm); - - status = efi_thunk(set_wakeup_time, enabled, phys_tm); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - spin_unlock(&rtc_lock); - - return status; + return EFI_UNSUPPORTED; } static unsigned long efi_name_size(efi_char16_t *name) @@ -658,6 +595,8 @@ static efi_status_t efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, u32 *attr, unsigned long *data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); efi_status_t status; u32 phys_name, phys_vendor, phys_attr; u32 phys_data_size, phys_data; @@ -665,14 +604,19 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_data_size = virt_to_phys_or_null(data_size); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); phys_attr = virt_to_phys_or_null(attr); phys_data = virt_to_phys_or_null_size(data, *data_size); - status = efi_thunk(get_variable, phys_name, phys_vendor, - phys_attr, phys_data_size, phys_data); + if (!phys_name || (data && !phys_data)) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(get_variable, phys_name, phys_vendor, + phys_attr, phys_data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -683,19 +627,25 @@ static efi_status_t efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); u32 phys_name, phys_vendor, phys_data; efi_status_t status; unsigned long flags; spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - /* If data_size is > sizeof(u32) we've got problems */ - status = efi_thunk(set_variable, phys_name, phys_vendor, - attr, data_size, phys_data); + if (!phys_name || !phys_data) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -707,6 +657,8 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, u32 attr, unsigned long data_size, void *data) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); u32 phys_name, phys_vendor, phys_data; efi_status_t status; unsigned long flags; @@ -714,13 +666,17 @@ efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor, if (!spin_trylock_irqsave(&efi_runtime_lock, flags)) return EFI_NOT_READY; + *vnd = *vendor; + phys_name = virt_to_phys_or_null_size(name, efi_name_size(name)); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_data = virt_to_phys_or_null_size(data, data_size); - /* If data_size is > sizeof(u32) we've got problems */ - status = efi_thunk(set_variable, phys_name, phys_vendor, - attr, data_size, phys_data); + if (!phys_name || !phys_data) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); spin_unlock_irqrestore(&efi_runtime_lock, flags); @@ -732,39 +688,36 @@ efi_thunk_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { + u8 buf[24] __aligned(8); + efi_guid_t *vnd = PTR_ALIGN((efi_guid_t *)buf, sizeof(*vnd)); efi_status_t status; u32 phys_name_size, phys_name, phys_vendor; unsigned long flags; spin_lock_irqsave(&efi_runtime_lock, flags); + *vnd = *vendor; + phys_name_size = virt_to_phys_or_null(name_size); - phys_vendor = virt_to_phys_or_null(vendor); + phys_vendor = virt_to_phys_or_null(vnd); phys_name = virt_to_phys_or_null_size(name, *name_size); - status = efi_thunk(get_next_variable, phys_name_size, - phys_name, phys_vendor); + if (!phys_name) + status = EFI_INVALID_PARAMETER; + else + status = efi_thunk(get_next_variable, phys_name_size, + phys_name, phys_vendor); spin_unlock_irqrestore(&efi_runtime_lock, flags); + *vendor = *vnd; return status; } static efi_status_t efi_thunk_get_next_high_mono_count(u32 *count) { - efi_status_t status; - u32 phys_count; - unsigned long flags; - - spin_lock_irqsave(&efi_runtime_lock, flags); - - phys_count = virt_to_phys_or_null(count); - status = efi_thunk(get_next_high_mono_count, phys_count); - - spin_unlock_irqrestore(&efi_runtime_lock, flags); - - return status; + return EFI_UNSUPPORTED; } static void diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 79409120a603..507f4fb88fa7 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -72,6 +72,9 @@ #include <asm/mwait.h> #include <asm/pci_x86.h> #include <asm/cpu.h> +#ifdef CONFIG_X86_IOPL_IOPERM +#include <asm/io_bitmap.h> +#endif #ifdef CONFIG_ACPI #include <linux/acpi.h> @@ -837,6 +840,25 @@ static void xen_load_sp0(unsigned long sp0) this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } +#ifdef CONFIG_X86_IOPL_IOPERM +static void xen_update_io_bitmap(void) +{ + struct physdev_set_iobitmap iobitmap; + struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); + + native_tss_update_io_bitmap(); + + iobitmap.bitmap = (uint8_t *)(&tss->x86_tss) + + tss->x86_tss.io_bitmap_base; + if (tss->x86_tss.io_bitmap_base == IO_BITMAP_OFFSET_INVALID) + iobitmap.nr_ports = 0; + else + iobitmap.nr_ports = IO_BITMAP_BITS; + + HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap); +} +#endif + static void xen_io_delay(void) { } @@ -1047,6 +1069,9 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .write_idt_entry = xen_write_idt_entry, .load_sp0 = xen_load_sp0, +#ifdef CONFIG_X86_IOPL_IOPERM + .update_io_bitmap = xen_update_io_bitmap, +#endif .io_delay = xen_io_delay, /* Xen takes care of %gs when switching to usermode for us */ diff --git a/block/blk-flush.c b/block/blk-flush.c index 3f977c517960..5cc775bdb06a 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -412,7 +412,7 @@ void blk_insert_flush(struct request *rq) */ if ((policy & REQ_FSEQ_DATA) && !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) { - blk_mq_request_bypass_insert(rq, false); + blk_mq_request_bypass_insert(rq, false, false); return; } diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index ca22afd47b3d..856356b1619e 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -361,13 +361,19 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, bool has_sched, struct request *rq) { - /* dispatch flush rq directly */ - if (rq->rq_flags & RQF_FLUSH_SEQ) { - spin_lock(&hctx->lock); - list_add(&rq->queuelist, &hctx->dispatch); - spin_unlock(&hctx->lock); + /* + * dispatch flush and passthrough rq directly + * + * passthrough request has to be added to hctx->dispatch directly. + * For some reason, device may be in one situation which can't + * handle FS request, so STS_RESOURCE is always returned and the + * FS request will be added to hctx->dispatch. However passthrough + * request may be required at that time for fixing the problem. If + * passthrough request is added to scheduler queue, there isn't any + * chance to dispatch it given we prioritize requests in hctx->dispatch. + */ + if ((rq->rq_flags & RQF_FLUSH_SEQ) || blk_rq_is_passthrough(rq)) return true; - } if (has_sched) rq->rq_flags |= RQF_SORTED; @@ -391,8 +397,10 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head, WARN_ON(e && (rq->tag != -1)); - if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) + if (blk_mq_sched_bypass_insert(hctx, !!e, rq)) { + blk_mq_request_bypass_insert(rq, at_head, false); goto run; + } if (e && e->type->ops.insert_requests) { LIST_HEAD(list); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index fbacde454718..586c9d6e904a 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -183,8 +183,8 @@ found_tag: return tag + tag_offset; } -void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags, - struct blk_mq_ctx *ctx, unsigned int tag) +void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, + unsigned int tag) { if (!blk_mq_tag_is_reserved(tags, tag)) { const int real_tag = tag - tags->nr_reserved_tags; diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 15bc74acb57e..2b8321efb682 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -26,8 +26,8 @@ extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int r extern void blk_mq_free_tags(struct blk_mq_tags *tags); extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); -extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags, - struct blk_mq_ctx *ctx, unsigned int tag); +extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, + unsigned int tag); extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); diff --git a/block/blk-mq.c b/block/blk-mq.c index a12b1763508d..d92088dec6c3 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -477,9 +477,9 @@ static void __blk_mq_free_request(struct request *rq) blk_pm_mark_last_busy(rq); rq->mq_hctx = NULL; if (rq->tag != -1) - blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag); + blk_mq_put_tag(hctx->tags, ctx, rq->tag); if (sched_tag != -1) - blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag); + blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag); blk_mq_sched_restart(hctx); blk_queue_exit(q); } @@ -735,7 +735,7 @@ static void blk_mq_requeue_work(struct work_struct *work) * merge. */ if (rq->rq_flags & RQF_DONTPREP) - blk_mq_request_bypass_insert(rq, false); + blk_mq_request_bypass_insert(rq, false, false); else blk_mq_sched_insert_request(rq, true, false, false); } @@ -1286,7 +1286,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, q->mq_ops->commit_rqs(hctx); spin_lock(&hctx->lock); - list_splice_init(list, &hctx->dispatch); + list_splice_tail_init(list, &hctx->dispatch); spin_unlock(&hctx->lock); /* @@ -1677,12 +1677,16 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, * Should only be used carefully, when the caller knows we want to * bypass a potential IO scheduler on the target device. */ -void blk_mq_request_bypass_insert(struct request *rq, bool run_queue) +void blk_mq_request_bypass_insert(struct request *rq, bool at_head, + bool run_queue) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; spin_lock(&hctx->lock); - list_add_tail(&rq->queuelist, &hctx->dispatch); + if (at_head) + list_add(&rq->queuelist, &hctx->dispatch); + else + list_add_tail(&rq->queuelist, &hctx->dispatch); spin_unlock(&hctx->lock); if (run_queue) @@ -1849,7 +1853,7 @@ insert: if (bypass_insert) return BLK_STS_RESOURCE; - blk_mq_request_bypass_insert(rq, run_queue); + blk_mq_request_bypass_insert(rq, false, run_queue); return BLK_STS_OK; } @@ -1876,7 +1880,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true); if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) - blk_mq_request_bypass_insert(rq, true); + blk_mq_request_bypass_insert(rq, false, true); else if (ret != BLK_STS_OK) blk_mq_end_request(rq, ret); @@ -1910,7 +1914,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, if (ret != BLK_STS_OK) { if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { - blk_mq_request_bypass_insert(rq, + blk_mq_request_bypass_insert(rq, false, list_empty(list)); break; } @@ -3398,7 +3402,6 @@ static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb) } static unsigned long blk_mq_poll_nsecs(struct request_queue *q, - struct blk_mq_hw_ctx *hctx, struct request *rq) { unsigned long ret = 0; @@ -3431,7 +3434,6 @@ static unsigned long blk_mq_poll_nsecs(struct request_queue *q, } static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, - struct blk_mq_hw_ctx *hctx, struct request *rq) { struct hrtimer_sleeper hs; @@ -3451,7 +3453,7 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, if (q->poll_nsec > 0) nsecs = q->poll_nsec; else - nsecs = blk_mq_poll_nsecs(q, hctx, rq); + nsecs = blk_mq_poll_nsecs(q, rq); if (!nsecs) return false; @@ -3506,7 +3508,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q, return false; } - return blk_mq_poll_hybrid_sleep(q, hctx, rq); + return blk_mq_poll_hybrid_sleep(q, rq); } /** diff --git a/block/blk-mq.h b/block/blk-mq.h index eaaca8fc1c28..10bfdfb494fa 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -66,7 +66,8 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, */ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head); -void blk_mq_request_bypass_insert(struct request *rq, bool run_queue); +void blk_mq_request_bypass_insert(struct request *rq, bool at_head, + bool run_queue); void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list); @@ -199,7 +200,7 @@ static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx) static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq) { - blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag); + blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag); rq->tag = -1; if (rq->rq_flags & RQF_MQ_INFLIGHT) { diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c index b5516b04ffc0..6e9ec6e3fe47 100644 --- a/drivers/acpi/acpi_watchdog.c +++ b/drivers/acpi/acpi_watchdog.c @@ -55,12 +55,14 @@ static bool acpi_watchdog_uses_rtc(const struct acpi_table_wdat *wdat) } #endif +static bool acpi_no_watchdog; + static const struct acpi_table_wdat *acpi_watchdog_get_wdat(void) { const struct acpi_table_wdat *wdat = NULL; acpi_status status; - if (acpi_disabled) + if (acpi_disabled || acpi_no_watchdog) return NULL; status = acpi_get_table(ACPI_SIG_WDAT, 0, @@ -88,6 +90,14 @@ bool acpi_has_watchdog(void) } EXPORT_SYMBOL_GPL(acpi_has_watchdog); +/* ACPI watchdog can be disabled on boot command line */ +static int __init disable_acpi_watchdog(char *str) +{ + acpi_no_watchdog = true; + return 1; +} +__setup("acpi_no_watchdog", disable_acpi_watchdog); + void __init acpi_watchdog_init(void) { const struct acpi_wdat_entry *entries; @@ -126,12 +136,11 @@ void __init acpi_watchdog_init(void) gas = &entries[i].register_region; res.start = gas->address; + res.end = res.start + ACPI_ACCESS_BYTE_WIDTH(gas->access_width) - 1; if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { res.flags = IORESOURCE_MEM; - res.end = res.start + ALIGN(gas->access_width, 4) - 1; } else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { res.flags = IORESOURCE_IO; - res.end = res.start + gas->access_width - 1; } else { pr_warn("Unsupported address space: %u\n", gas->space_id); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index cd3612e4e2e1..8ef65c085640 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -853,14 +853,17 @@ static void reset_fdc_info(int mode) /* selects the fdc and drive, and enables the fdc's input/dma. */ static void set_fdc(int drive) { + unsigned int new_fdc = fdc; + if (drive >= 0 && drive < N_DRIVE) { - fdc = FDC(drive); + new_fdc = FDC(drive); current_drive = drive; } - if (fdc != 1 && fdc != 0) { + if (new_fdc >= N_FDC) { pr_info("bad fdc value\n"); return; } + fdc = new_fdc; set_dor(fdc, ~0, 8); #if N_FDC > 1 set_dor(1 - fdc, ~8, 0); diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index bc837862b767..62b660821dbc 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -14,9 +14,6 @@ #include <linux/fault-inject.h> struct nullb_cmd { - struct list_head list; - struct llist_node ll_list; - struct __call_single_data csd; struct request *rq; struct bio *bio; unsigned int tag; diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 16510795e377..133060431dbd 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1518,8 +1518,6 @@ static int setup_commands(struct nullb_queue *nq) for (i = 0; i < nq->queue_depth; i++) { cmd = &nq->cmds[i]; - INIT_LIST_HEAD(&cmd->list); - cmd->ll_list.next = NULL; cmd->tag = -1U; } diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 117cfc8cd05a..cda5cf917e9a 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -276,7 +276,7 @@ static const struct block_device_operations pcd_bdops = { .release = pcd_block_release, .ioctl = pcd_block_ioctl, #ifdef CONFIG_COMPAT - .ioctl = blkdev_compat_ptr_ioctl, + .compat_ioctl = blkdev_compat_ptr_ioctl, #endif .check_events = pcd_block_check_events, }; diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index 886b2638c730..c51292c2a131 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -519,7 +519,7 @@ static const struct block_device_operations gdrom_bdops = { .check_events = gdrom_bdops_check_events, .ioctl = gdrom_bdops_ioctl, #ifdef CONFIG_COMPAT - .ioctl = blkdev_compat_ptr_ioctl, + .compat_ioctl = blkdev_compat_ptr_ioctl, #endif }; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index cbe6c94bf158..808874bccf4a 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1076,9 +1076,17 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy) pol = policy->last_policy; } else if (def_gov) { pol = cpufreq_parse_policy(def_gov->name); - } else { - return -ENODATA; + /* + * In case the default governor is neiter "performance" + * nor "powersave", fall back to the initial policy + * value set by the driver. + */ + if (pol == CPUFREQ_POLICY_UNKNOWN) + pol = policy->policy; } + if (pol != CPUFREQ_POLICY_PERFORMANCE && + pol != CPUFREQ_POLICY_POWERSAVE) + return -ENODATA; } return cpufreq_set_policy(policy, gov, pol); diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index cceee8bc3c2f..7dcf2093e531 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -738,7 +738,6 @@ struct devfreq *devfreq_add_device(struct device *dev, { struct devfreq *devfreq; struct devfreq_governor *governor; - static atomic_t devfreq_no = ATOMIC_INIT(-1); int err = 0; if (!dev || !profile || !governor_name) { @@ -800,8 +799,7 @@ struct devfreq *devfreq_add_device(struct device *dev, devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev); atomic_set(&devfreq->suspend_count, 0); - dev_set_name(&devfreq->dev, "devfreq%d", - atomic_inc_return(&devfreq_no)); + dev_set_name(&devfreq->dev, "%s", dev_name(dev)); err = device_register(&devfreq->dev); if (err) { mutex_unlock(&devfreq->lock); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 621220ab3d0e..21ea99f65113 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -552,7 +552,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz, seed = early_memremap(efi.rng_seed, sizeof(*seed)); if (seed != NULL) { - size = seed->size; + size = READ_ONCE(seed->size); early_memunmap(seed, sizeof(*seed)); } else { pr_err("Could not map UEFI random seed!\n"); @@ -562,7 +562,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz, sizeof(*seed) + size); if (seed != NULL) { pr_notice("seeding entropy pool\n"); - add_bootloader_randomness(seed->bits, seed->size); + add_bootloader_randomness(seed->bits, size); early_memunmap(seed, sizeof(*seed) + size); } else { pr_err("Could not map UEFI random seed!\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 94e2fd758e01..42f4febe24c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1389,7 +1389,7 @@ amdgpu_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe, static struct drm_driver kms_driver = { .driver_features = - DRIVER_USE_AGP | DRIVER_ATOMIC | + DRIVER_ATOMIC | DRIVER_GEM | DRIVER_RENDER | DRIVER_MODESET | DRIVER_SYNCOBJ | DRIVER_SYNCOBJ_TIMELINE, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h index d3c27a3c43f6..7546da0cc70c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h @@ -195,6 +195,7 @@ struct amdgpu_gmc { uint32_t srbm_soft_reset; bool prt_warning; uint64_t stolen_size; + uint32_t sdpif_register; /* apertures */ u64 shared_aperture_start; u64 shared_aperture_end; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 90216abf14a4..cc0c273a86f9 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1272,6 +1272,19 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev) } /** + * gmc_v9_0_restore_registers - restores regs + * + * @adev: amdgpu_device pointer + * + * This restores register values, saved at suspend. + */ +static void gmc_v9_0_restore_registers(struct amdgpu_device *adev) +{ + if (adev->asic_type == CHIP_RAVEN) + WREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0, adev->gmc.sdpif_register); +} + +/** * gmc_v9_0_gart_enable - gart enable * * @adev: amdgpu_device pointer @@ -1377,6 +1390,20 @@ static int gmc_v9_0_hw_init(void *handle) } /** + * gmc_v9_0_save_registers - saves regs + * + * @adev: amdgpu_device pointer + * + * This saves potential register values that should be + * restored upon resume + */ +static void gmc_v9_0_save_registers(struct amdgpu_device *adev) +{ + if (adev->asic_type == CHIP_RAVEN) + adev->gmc.sdpif_register = RREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0); +} + +/** * gmc_v9_0_gart_disable - gart disable * * @adev: amdgpu_device pointer @@ -1412,9 +1439,16 @@ static int gmc_v9_0_hw_fini(void *handle) static int gmc_v9_0_suspend(void *handle) { + int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - return gmc_v9_0_hw_fini(adev); + r = gmc_v9_0_hw_fini(adev); + if (r) + return r; + + gmc_v9_0_save_registers(adev); + + return 0; } static int gmc_v9_0_resume(void *handle) @@ -1422,6 +1456,7 @@ static int gmc_v9_0_resume(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v9_0_restore_registers(adev); r = gmc_v9_0_hw_init(adev); if (r) return r; diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h index b6f74bf4af02..27bb8c1ab858 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h @@ -7376,6 +7376,8 @@ #define mmCRTC4_CRTC_DRR_CONTROL 0x0f3e #define mmCRTC4_CRTC_DRR_CONTROL_BASE_IDX 2 +#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0 0x395d +#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0_BASE_IDX 2 // addressBlock: dce_dc_fmt4_dispdec // base address: 0x2000 diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c index b06c057a9002..c9e5ce135fd4 100644 --- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c +++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c @@ -978,8 +978,12 @@ int smu_v11_0_init_max_sustainable_clocks(struct smu_context *smu) struct smu_11_0_max_sustainable_clocks *max_sustainable_clocks; int ret = 0; - max_sustainable_clocks = kzalloc(sizeof(struct smu_11_0_max_sustainable_clocks), + if (!smu->smu_table.max_sustainable_clocks) + max_sustainable_clocks = kzalloc(sizeof(struct smu_11_0_max_sustainable_clocks), GFP_KERNEL); + else + max_sustainable_clocks = smu->smu_table.max_sustainable_clocks; + smu->smu_table.max_sustainable_clocks = (void *)max_sustainable_clocks; max_sustainable_clocks->uclock = smu->smu_table.boot_values.uclk / 100; diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index b8c5f8934dbd..a1f2411aa21b 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -294,7 +294,7 @@ extra-$(CONFIG_DRM_I915_WERROR) += \ $(shell cd $(srctree)/$(src) && find * -name '*.h'))) quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@) - cmd_hdrtest = $(CC) $(c_flags) -S -o /dev/null -x c /dev/null -include $<; touch $@ + cmd_hdrtest = $(CC) $(filter-out $(CFLAGS_GCOV), $(c_flags)) -S -o /dev/null -x c /dev/null -include $<; touch $@ $(obj)/%.hdrtest: $(src)/%.h FORCE $(call if_changed_dep,hdrtest) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index f7e4b39c734f..59b387ade49c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -256,8 +256,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *i915) with_intel_runtime_pm(&i915->runtime_pm, wakeref) { freed = i915_gem_shrink(i915, -1UL, NULL, I915_SHRINK_BOUND | - I915_SHRINK_UNBOUND | - I915_SHRINK_ACTIVE); + I915_SHRINK_UNBOUND); } return freed; @@ -336,7 +335,6 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr) freed_pages = 0; with_intel_runtime_pm(&i915->runtime_pm, wakeref) freed_pages += i915_gem_shrink(i915, -1UL, NULL, - I915_SHRINK_ACTIVE | I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_WRITEBACK); diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 2477a1e5a166..ae139f0877ae 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -151,12 +151,12 @@ static void dmabuf_gem_object_free(struct kref *kref) dmabuf_obj = container_of(pos, struct intel_vgpu_dmabuf_obj, list); if (dmabuf_obj == obj) { + list_del(pos); intel_gvt_hypervisor_put_vfio_device(vgpu); idr_remove(&vgpu->object_idr, dmabuf_obj->dmabuf_id); kfree(dmabuf_obj->info); kfree(dmabuf_obj); - list_del(pos); break; } } diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 85bd9bf4f6ee..487af6ea9972 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -560,9 +560,9 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, intel_vgpu_reset_mmio(vgpu, dmlr); populate_pvinfo_page(vgpu); - intel_vgpu_reset_display(vgpu); if (dmlr) { + intel_vgpu_reset_display(vgpu); intel_vgpu_reset_cfg_space(vgpu); /* only reset the failsafe mode when dmlr reset */ vgpu->failsafe = false; diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 83f01401b8b5..f631f6d21127 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -437,7 +437,7 @@ static const struct intel_device_info snb_m_gt2_info = { .has_rc6 = 1, \ .has_rc6p = 1, \ .has_rps = true, \ - .ppgtt_type = INTEL_PPGTT_FULL, \ + .ppgtt_type = INTEL_PPGTT_ALIASING, \ .ppgtt_size = 31, \ IVB_PIPE_OFFSETS, \ IVB_CURSOR_OFFSETS, \ @@ -494,7 +494,7 @@ static const struct intel_device_info vlv_info = { .has_rps = true, .display.has_gmch = 1, .display.has_hotplug = 1, - .ppgtt_type = INTEL_PPGTT_FULL, + .ppgtt_type = INTEL_PPGTT_ALIASING, .ppgtt_size = 31, .has_snoop = true, .has_coherent_ggtt = false, diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index ec0299490dd4..aa729d04abe2 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -822,11 +822,6 @@ static ssize_t i915_pmu_event_show(struct device *dev, return sprintf(buf, "config=0x%lx\n", eattr->val); } -static struct attribute_group i915_pmu_events_attr_group = { - .name = "events", - /* Patch in attrs at runtime. */ -}; - static ssize_t i915_pmu_get_attr_cpumask(struct device *dev, struct device_attribute *attr, @@ -846,13 +841,6 @@ static const struct attribute_group i915_pmu_cpumask_attr_group = { .attrs = i915_cpumask_attrs, }; -static const struct attribute_group *i915_pmu_attr_groups[] = { - &i915_pmu_format_attr_group, - &i915_pmu_events_attr_group, - &i915_pmu_cpumask_attr_group, - NULL -}; - #define __event(__config, __name, __unit) \ { \ .config = (__config), \ @@ -1026,23 +1014,23 @@ err_alloc: static void free_event_attributes(struct i915_pmu *pmu) { - struct attribute **attr_iter = i915_pmu_events_attr_group.attrs; + struct attribute **attr_iter = pmu->events_attr_group.attrs; for (; *attr_iter; attr_iter++) kfree((*attr_iter)->name); - kfree(i915_pmu_events_attr_group.attrs); + kfree(pmu->events_attr_group.attrs); kfree(pmu->i915_attr); kfree(pmu->pmu_attr); - i915_pmu_events_attr_group.attrs = NULL; + pmu->events_attr_group.attrs = NULL; pmu->i915_attr = NULL; pmu->pmu_attr = NULL; } static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node) { - struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), node); + struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node); GEM_BUG_ON(!pmu->base.event_init); @@ -1055,7 +1043,7 @@ static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node) static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node) { - struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), node); + struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node); unsigned int target; GEM_BUG_ON(!pmu->base.event_init); @@ -1072,8 +1060,6 @@ static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node) return 0; } -static enum cpuhp_state cpuhp_slot = CPUHP_INVALID; - static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu) { enum cpuhp_state slot; @@ -1087,21 +1073,22 @@ static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu) return ret; slot = ret; - ret = cpuhp_state_add_instance(slot, &pmu->node); + ret = cpuhp_state_add_instance(slot, &pmu->cpuhp.node); if (ret) { cpuhp_remove_multi_state(slot); return ret; } - cpuhp_slot = slot; + pmu->cpuhp.slot = slot; return 0; } static void i915_pmu_unregister_cpuhp_state(struct i915_pmu *pmu) { - WARN_ON(cpuhp_slot == CPUHP_INVALID); - WARN_ON(cpuhp_state_remove_instance(cpuhp_slot, &pmu->node)); - cpuhp_remove_multi_state(cpuhp_slot); + WARN_ON(pmu->cpuhp.slot == CPUHP_INVALID); + WARN_ON(cpuhp_state_remove_instance(pmu->cpuhp.slot, &pmu->cpuhp.node)); + cpuhp_remove_multi_state(pmu->cpuhp.slot); + pmu->cpuhp.slot = CPUHP_INVALID; } static bool is_igp(struct drm_i915_private *i915) @@ -1118,6 +1105,13 @@ static bool is_igp(struct drm_i915_private *i915) void i915_pmu_register(struct drm_i915_private *i915) { struct i915_pmu *pmu = &i915->pmu; + const struct attribute_group *attr_groups[] = { + &i915_pmu_format_attr_group, + &pmu->events_attr_group, + &i915_pmu_cpumask_attr_group, + NULL + }; + int ret = -ENOMEM; if (INTEL_GEN(i915) <= 2) { @@ -1128,6 +1122,7 @@ void i915_pmu_register(struct drm_i915_private *i915) spin_lock_init(&pmu->lock); hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); pmu->timer.function = i915_sample; + pmu->cpuhp.slot = CPUHP_INVALID; if (!is_igp(i915)) { pmu->name = kasprintf(GFP_KERNEL, @@ -1143,11 +1138,16 @@ void i915_pmu_register(struct drm_i915_private *i915) if (!pmu->name) goto err; - i915_pmu_events_attr_group.attrs = create_event_attributes(pmu); - if (!i915_pmu_events_attr_group.attrs) + pmu->events_attr_group.name = "events"; + pmu->events_attr_group.attrs = create_event_attributes(pmu); + if (!pmu->events_attr_group.attrs) goto err_name; - pmu->base.attr_groups = i915_pmu_attr_groups; + pmu->base.attr_groups = kmemdup(attr_groups, sizeof(attr_groups), + GFP_KERNEL); + if (!pmu->base.attr_groups) + goto err_attr; + pmu->base.task_ctx_nr = perf_invalid_context; pmu->base.event_init = i915_pmu_event_init; pmu->base.add = i915_pmu_event_add; @@ -1159,7 +1159,7 @@ void i915_pmu_register(struct drm_i915_private *i915) ret = perf_pmu_register(&pmu->base, pmu->name, -1); if (ret) - goto err_attr; + goto err_groups; ret = i915_pmu_register_cpuhp_state(pmu); if (ret) @@ -1169,6 +1169,8 @@ void i915_pmu_register(struct drm_i915_private *i915) err_unreg: perf_pmu_unregister(&pmu->base); +err_groups: + kfree(pmu->base.attr_groups); err_attr: pmu->base.event_init = NULL; free_event_attributes(pmu); @@ -1194,6 +1196,7 @@ void i915_pmu_unregister(struct drm_i915_private *i915) perf_pmu_unregister(&pmu->base); pmu->base.event_init = NULL; + kfree(pmu->base.attr_groups); if (!is_igp(i915)) kfree(pmu->name); free_event_attributes(pmu); diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index 6c1647c5daf2..f1d6cad0d7d5 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -39,9 +39,12 @@ struct i915_pmu_sample { struct i915_pmu { /** - * @node: List node for CPU hotplug handling. + * @cpuhp: Struct used for CPU hotplug handling. */ - struct hlist_node node; + struct { + struct hlist_node node; + enum cpuhp_state slot; + } cpuhp; /** * @base: PMU base. */ @@ -105,6 +108,10 @@ struct i915_pmu { */ ktime_t sleep_last; /** + * @events_attr_group: Device events attribute group. + */ + struct attribute_group events_attr_group; + /** * @i915_attr: Memory block holding device attributes. */ void *i915_attr; diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index fd74e2611185..8696af1ee14d 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -37,6 +37,7 @@ #include <linux/vga_switcheroo.h> #include <linux/mmu_notifier.h> +#include <drm/drm_agpsupport.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_drv.h> #include <drm/drm_fb_helper.h> @@ -325,6 +326,7 @@ static int radeon_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { unsigned long flags = 0; + struct drm_device *dev; int ret; if (!ent) @@ -365,7 +367,44 @@ static int radeon_pci_probe(struct pci_dev *pdev, if (ret) return ret; - return drm_get_pci_dev(pdev, ent, &kms_driver); + dev = drm_dev_alloc(&kms_driver, &pdev->dev); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + ret = pci_enable_device(pdev); + if (ret) + goto err_free; + + dev->pdev = pdev; +#ifdef __alpha__ + dev->hose = pdev->sysdata; +#endif + + pci_set_drvdata(pdev, dev); + + if (pci_find_capability(dev->pdev, PCI_CAP_ID_AGP)) + dev->agp = drm_agp_init(dev); + if (dev->agp) { + dev->agp->agp_mtrr = arch_phys_wc_add( + dev->agp->agp_info.aper_base, + dev->agp->agp_info.aper_size * + 1024 * 1024); + } + + ret = drm_dev_register(dev, ent->driver_data); + if (ret) + goto err_agp; + + return 0; + +err_agp: + if (dev->agp) + arch_phys_wc_del(dev->agp->agp_mtrr); + kfree(dev->agp); + pci_disable_device(pdev); +err_free: + drm_dev_put(dev); + return ret; } static void @@ -575,7 +614,7 @@ radeon_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe, static struct drm_driver kms_driver = { .driver_features = - DRIVER_USE_AGP | DRIVER_GEM | DRIVER_RENDER, + DRIVER_GEM | DRIVER_RENDER, .load = radeon_driver_load_kms, .open = radeon_driver_open_kms, .postclose = radeon_driver_postclose_kms, diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index d24f23a81656..dd2f19b8022b 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -32,6 +32,7 @@ #include <linux/uaccess.h> #include <linux/vga_switcheroo.h> +#include <drm/drm_agpsupport.h> #include <drm/drm_fb_helper.h> #include <drm/drm_file.h> #include <drm/drm_ioctl.h> @@ -77,6 +78,11 @@ void radeon_driver_unload_kms(struct drm_device *dev) radeon_modeset_fini(rdev); radeon_device_fini(rdev); + if (dev->agp) + arch_phys_wc_del(dev->agp->agp_mtrr); + kfree(dev->agp); + dev->agp = NULL; + done_free: kfree(rdev); dev->dev_private = NULL; diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index ae79a7c66737..fa704153cb00 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -730,7 +730,7 @@ static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi) if (data->has_sp) { input2 = input_allocate_device(); if (!input2) { - input_free_device(input2); + ret = -ENOMEM; goto exit; } diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 6ac8becc2372..d732d1d10caf 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -340,7 +340,8 @@ static int apple_input_mapping(struct hid_device *hdev, struct hid_input *hi, unsigned long **bit, int *max) { if (usage->hid == (HID_UP_CUSTOM | 0x0003) || - usage->hid == (HID_UP_MSVENDOR | 0x0003)) { + usage->hid == (HID_UP_MSVENDOR | 0x0003) || + usage->hid == (HID_UP_HPVENDOR2 | 0x0003)) { /* The fn key on Apple USB keyboards */ set_bit(EV_REP, hi->input->evbit); hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_FN); diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index 3f6abd190df4..db6da21ade06 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -174,6 +174,7 @@ static __u8 pid0902_rdesc_fixed[] = { struct bigben_device { struct hid_device *hid; struct hid_report *report; + bool removed; u8 led_state; /* LED1 = 1 .. LED4 = 8 */ u8 right_motor_on; /* right motor off/on 0/1 */ u8 left_motor_force; /* left motor force 0-255 */ @@ -190,6 +191,9 @@ static void bigben_worker(struct work_struct *work) struct bigben_device, worker); struct hid_field *report_field = bigben->report->field[0]; + if (bigben->removed) + return; + if (bigben->work_led) { bigben->work_led = false; report_field->value[0] = 0x01; /* 1 = led message */ @@ -220,10 +224,16 @@ static void bigben_worker(struct work_struct *work) static int hid_bigben_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect) { - struct bigben_device *bigben = data; + struct hid_device *hid = input_get_drvdata(dev); + struct bigben_device *bigben = hid_get_drvdata(hid); u8 right_motor_on; u8 left_motor_force; + if (!bigben) { + hid_err(hid, "no device data\n"); + return 0; + } + if (effect->type != FF_RUMBLE) return 0; @@ -298,8 +308,8 @@ static void bigben_remove(struct hid_device *hid) { struct bigben_device *bigben = hid_get_drvdata(hid); + bigben->removed = true; cancel_work_sync(&bigben->worker); - hid_hw_close(hid); hid_hw_stop(hid); } @@ -319,6 +329,7 @@ static int bigben_probe(struct hid_device *hid, return -ENOMEM; hid_set_drvdata(hid, bigben); bigben->hid = hid; + bigben->removed = false; error = hid_parse(hid); if (error) { @@ -341,10 +352,10 @@ static int bigben_probe(struct hid_device *hid, INIT_WORK(&bigben->worker, bigben_worker); - error = input_ff_create_memless(hidinput->input, bigben, + error = input_ff_create_memless(hidinput->input, NULL, hid_bigben_play_effect); if (error) - return error; + goto error_hw_stop; name_sz = strlen(dev_name(&hid->dev)) + strlen(":red:bigben#") + 1; @@ -354,8 +365,10 @@ static int bigben_probe(struct hid_device *hid, sizeof(struct led_classdev) + name_sz, GFP_KERNEL ); - if (!led) - return -ENOMEM; + if (!led) { + error = -ENOMEM; + goto error_hw_stop; + } name = (void *)(&led[1]); snprintf(name, name_sz, "%s:red:bigben%d", @@ -369,7 +382,7 @@ static int bigben_probe(struct hid_device *hid, bigben->leds[n] = led; error = devm_led_classdev_register(&hid->dev, led); if (error) - return error; + goto error_hw_stop; } /* initial state: LED1 is on, no rumble effect */ @@ -383,6 +396,10 @@ static int bigben_probe(struct hid_device *hid, hid_info(hid, "LED and force feedback support for BigBen gamepad\n"); return 0; + +error_hw_stop: + hid_hw_stop(hid); + return error; } static __u8 *bigben_report_fixup(struct hid_device *hid, __u8 *rdesc, diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 851fe54ea59e..359616e3efbb 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1741,7 +1741,9 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, rsize = ((report->size - 1) >> 3) + 1; - if (rsize > HID_MAX_BUFFER_SIZE) + if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE) + rsize = HID_MAX_BUFFER_SIZE - 1; + else if (rsize > HID_MAX_BUFFER_SIZE) rsize = HID_MAX_BUFFER_SIZE; if (csize < rsize) { diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index c436e12feb23..6c55682c5974 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -41,8 +41,9 @@ static const struct hid_device_id ite_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) }, { HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) }, /* ITE8595 USB kbd ctlr, with Synaptics touchpad connected to it. */ - { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, - USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_SYNAPTICS, + USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 70e1cb928bf0..094f4f1b6555 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -1256,36 +1256,35 @@ static int hidpp20_battery_map_status_voltage(u8 data[3], int *voltage, { int status; - long charge_sts = (long)data[2]; + long flags = (long) data[2]; - *level = POWER_SUPPLY_CAPACITY_LEVEL_UNKNOWN; - switch (data[2] & 0xe0) { - case 0x00: - status = POWER_SUPPLY_STATUS_CHARGING; - break; - case 0x20: - status = POWER_SUPPLY_STATUS_FULL; - *level = POWER_SUPPLY_CAPACITY_LEVEL_FULL; - break; - case 0x40: + if (flags & 0x80) + switch (flags & 0x07) { + case 0: + status = POWER_SUPPLY_STATUS_CHARGING; + break; + case 1: + status = POWER_SUPPLY_STATUS_FULL; + *level = POWER_SUPPLY_CAPACITY_LEVEL_FULL; + break; + case 2: + status = POWER_SUPPLY_STATUS_NOT_CHARGING; + break; + default: + status = POWER_SUPPLY_STATUS_UNKNOWN; + break; + } + else status = POWER_SUPPLY_STATUS_DISCHARGING; - break; - case 0xe0: - status = POWER_SUPPLY_STATUS_NOT_CHARGING; - break; - default: - status = POWER_SUPPLY_STATUS_UNKNOWN; - } *charge_type = POWER_SUPPLY_CHARGE_TYPE_STANDARD; - if (test_bit(3, &charge_sts)) { + if (test_bit(3, &flags)) { *charge_type = POWER_SUPPLY_CHARGE_TYPE_FAST; } - if (test_bit(4, &charge_sts)) { + if (test_bit(4, &flags)) { *charge_type = POWER_SUPPLY_CHARGE_TYPE_TRICKLE; } - - if (test_bit(5, &charge_sts)) { + if (test_bit(5, &flags)) { *level = POWER_SUPPLY_CAPACITY_LEVEL_CRITICAL; } diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c index d31ea82b84c1..a66f08041a1a 100644 --- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -342,6 +342,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { .driver_data = (void *)&sipodev_desc }, { + .ident = "Trekstor SURFBOOK E11B", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SURFBOOK E11B"), + }, + .driver_data = (void *)&sipodev_desc + }, + { .ident = "Direkt-Tek DTLAPY116-2", .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"), diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index a970b809d778..4140dea693e9 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -932,9 +932,9 @@ void hiddev_disconnect(struct hid_device *hid) hiddev->exist = 0; if (hiddev->open) { - mutex_unlock(&hiddev->existancelock); hid_hw_close(hiddev->hid); wake_up_interruptible(&hiddev->wait); + mutex_unlock(&hiddev->existancelock); } else { mutex_unlock(&hiddev->existancelock); kfree(hiddev); diff --git a/drivers/i2c/busses/i2c-altera.c b/drivers/i2c/busses/i2c-altera.c index 5255d3755411..1de23b4f3809 100644 --- a/drivers/i2c/busses/i2c-altera.c +++ b/drivers/i2c/busses/i2c-altera.c @@ -171,7 +171,7 @@ static void altr_i2c_init(struct altr_i2c_dev *idev) /* SCL Low Time */ writel(t_low, idev->base + ALTR_I2C_SCL_LOW); /* SDA Hold Time, 300ns */ - writel(div_u64(300 * clk_mhz, 1000), idev->base + ALTR_I2C_SDA_HOLD); + writel(3 * clk_mhz / 10, idev->base + ALTR_I2C_SDA_HOLD); /* Mask all master interrupt bits */ altr_i2c_int_enable(idev, ALTR_I2C_ALL_IRQ, false); diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c index 16a67a64284a..b426fc956938 100644 --- a/drivers/i2c/busses/i2c-jz4780.c +++ b/drivers/i2c/busses/i2c-jz4780.c @@ -78,25 +78,6 @@ #define X1000_I2C_DC_STOP BIT(9) -static const char * const jz4780_i2c_abrt_src[] = { - "ABRT_7B_ADDR_NOACK", - "ABRT_10ADDR1_NOACK", - "ABRT_10ADDR2_NOACK", - "ABRT_XDATA_NOACK", - "ABRT_GCALL_NOACK", - "ABRT_GCALL_READ", - "ABRT_HS_ACKD", - "SBYTE_ACKDET", - "ABRT_HS_NORSTRT", - "SBYTE_NORSTRT", - "ABRT_10B_RD_NORSTRT", - "ABRT_MASTER_DIS", - "ARB_LOST", - "SLVFLUSH_TXFIFO", - "SLV_ARBLOST", - "SLVRD_INTX", -}; - #define JZ4780_I2C_INTST_IGC BIT(11) #define JZ4780_I2C_INTST_ISTT BIT(10) #define JZ4780_I2C_INTST_ISTP BIT(9) @@ -576,21 +557,8 @@ done: static void jz4780_i2c_txabrt(struct jz4780_i2c *i2c, int src) { - int i; - - dev_err(&i2c->adap.dev, "txabrt: 0x%08x\n", src); - dev_err(&i2c->adap.dev, "device addr=%x\n", - jz4780_i2c_readw(i2c, JZ4780_I2C_TAR)); - dev_err(&i2c->adap.dev, "send cmd count:%d %d\n", - i2c->cmd, i2c->cmd_buf[i2c->cmd]); - dev_err(&i2c->adap.dev, "receive data count:%d %d\n", - i2c->cmd, i2c->data_buf[i2c->cmd]); - - for (i = 0; i < 16; i++) { - if (src & BIT(i)) - dev_dbg(&i2c->adap.dev, "I2C TXABRT[%d]=%s\n", - i, jz4780_i2c_abrt_src[i]); - } + dev_dbg(&i2c->adap.dev, "txabrt: 0x%08x, cmd: %d, send: %d, recv: %d\n", + src, i2c->cmd, i2c->cmd_buf[i2c->cmd], i2c->data_buf[i2c->cmd]); } static inline int jz4780_i2c_xfer_read(struct jz4780_i2c *i2c, diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c index 1bb99b556393..05c26986637b 100644 --- a/drivers/ide/ide-gd.c +++ b/drivers/ide/ide-gd.c @@ -361,7 +361,7 @@ static const struct block_device_operations ide_gd_ops = { .release = ide_gd_release, .ioctl = ide_gd_ioctl, #ifdef CONFIG_COMPAT - .ioctl = ide_gd_compat_ioctl, + .compat_ioctl = ide_gd_compat_ioctl, #endif .getgeo = ide_gd_getgeo, .check_events = ide_gd_check_events, diff --git a/drivers/macintosh/therm_windtunnel.c b/drivers/macintosh/therm_windtunnel.c index 8c744578122a..a0d87ed9da69 100644 --- a/drivers/macintosh/therm_windtunnel.c +++ b/drivers/macintosh/therm_windtunnel.c @@ -300,9 +300,11 @@ static int control_loop(void *dummy) /* i2c probing and setup */ /************************************************************************/ -static int -do_attach( struct i2c_adapter *adapter ) +static void do_attach(struct i2c_adapter *adapter) { + struct i2c_board_info info = { }; + struct device_node *np; + /* scan 0x48-0x4f (DS1775) and 0x2c-2x2f (ADM1030) */ static const unsigned short scan_ds1775[] = { 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, @@ -313,25 +315,24 @@ do_attach( struct i2c_adapter *adapter ) I2C_CLIENT_END }; - if( strncmp(adapter->name, "uni-n", 5) ) - return 0; - - if( !x.running ) { - struct i2c_board_info info; + if (x.running || strncmp(adapter->name, "uni-n", 5)) + return; - memset(&info, 0, sizeof(struct i2c_board_info)); - strlcpy(info.type, "therm_ds1775", I2C_NAME_SIZE); + np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,ds1775"); + if (np) { + of_node_put(np); + } else { + strlcpy(info.type, "MAC,ds1775", I2C_NAME_SIZE); i2c_new_probed_device(adapter, &info, scan_ds1775, NULL); + } - strlcpy(info.type, "therm_adm1030", I2C_NAME_SIZE); + np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,adm1030"); + if (np) { + of_node_put(np); + } else { + strlcpy(info.type, "MAC,adm1030", I2C_NAME_SIZE); i2c_new_probed_device(adapter, &info, scan_adm1030, NULL); - - if( x.thermostat && x.fan ) { - x.running = 1; - x.poll_task = kthread_run(control_loop, NULL, "g4fand"); - } } - return 0; } static int @@ -404,8 +405,8 @@ out: enum chip { ds1775, adm1030 }; static const struct i2c_device_id therm_windtunnel_id[] = { - { "therm_ds1775", ds1775 }, - { "therm_adm1030", adm1030 }, + { "MAC,ds1775", ds1775 }, + { "MAC,adm1030", adm1030 }, { } }; MODULE_DEVICE_TABLE(i2c, therm_windtunnel_id); @@ -414,6 +415,7 @@ static int do_probe(struct i2c_client *cl, const struct i2c_device_id *id) { struct i2c_adapter *adapter = cl->adapter; + int ret = 0; if( !i2c_check_functionality(adapter, I2C_FUNC_SMBUS_WORD_DATA | I2C_FUNC_SMBUS_WRITE_BYTE) ) @@ -421,11 +423,19 @@ do_probe(struct i2c_client *cl, const struct i2c_device_id *id) switch (id->driver_data) { case adm1030: - return attach_fan( cl ); + ret = attach_fan(cl); + break; case ds1775: - return attach_thermostat(cl); + ret = attach_thermostat(cl); + break; } - return 0; + + if (!x.running && x.thermostat && x.fan) { + x.running = 1; + x.poll_task = kthread_run(control_loop, NULL, "g4fand"); + } + + return ret; } static struct i2c_driver g4fan_driver = { diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index d1955543acd1..b0f5280a83cb 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -69,8 +69,7 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port) /* Force link status for IMP port */ reg = core_readl(priv, offset); reg |= (MII_SW_OR | LINK_STS); - if (priv->type == BCM7278_DEVICE_ID) - reg |= GMII_SPEED_UP_2G; + reg &= ~GMII_SPEED_UP_2G; core_writel(priv, reg, offset); /* Enable Broadcast, Multicast, Unicast forwarding to IMP port */ diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index b016cc205f81..ca3a7a7a73c3 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -278,13 +278,13 @@ int mv88e6095_g1_set_egress_port(struct mv88e6xxx_chip *chip, switch (direction) { case MV88E6XXX_EGRESS_DIR_INGRESS: dest_port_chip = &chip->ingress_dest_port; - reg &= MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK; + reg &= ~MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK; reg |= port << __bf_shf(MV88E6185_G1_MONITOR_CTL_INGRESS_DEST_MASK); break; case MV88E6XXX_EGRESS_DIR_EGRESS: dest_port_chip = &chip->egress_dest_port; - reg &= MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK; + reg &= ~MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK; reg |= port << __bf_shf(MV88E6185_G1_MONITOR_CTL_EGRESS_DEST_MASK); break; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index fd6e0e48cd51..f9a8151f092c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11252,7 +11252,7 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp) } } if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event)) - netdev_info(bp->dev, "Receive PF driver unload event!"); + netdev_info(bp->dev, "Receive PF driver unload event!\n"); } #else @@ -11759,7 +11759,7 @@ static int bnxt_pcie_dsn_get(struct bnxt *bp, u8 dsn[]) u32 dw; if (!pos) { - netdev_info(bp->dev, "Unable do read adapter's DSN"); + netdev_info(bp->dev, "Unable do read adapter's DSN\n"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index eec0168330b7..d3c93ccee86a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -641,14 +641,14 @@ static int bnxt_dl_params_register(struct bnxt *bp) rc = devlink_params_register(bp->dl, bnxt_dl_params, ARRAY_SIZE(bnxt_dl_params)); if (rc) { - netdev_warn(bp->dev, "devlink_params_register failed. rc=%d", + netdev_warn(bp->dev, "devlink_params_register failed. rc=%d\n", rc); return rc; } rc = devlink_port_params_register(&bp->dl_port, bnxt_dl_port_params, ARRAY_SIZE(bnxt_dl_port_params)); if (rc) { - netdev_err(bp->dev, "devlink_port_params_register failed"); + netdev_err(bp->dev, "devlink_port_params_register failed\n"); devlink_params_unregister(bp->dl, bnxt_dl_params, ARRAY_SIZE(bnxt_dl_params)); return rc; @@ -679,7 +679,7 @@ int bnxt_dl_register(struct bnxt *bp) else dl = devlink_alloc(&bnxt_vf_dl_ops, sizeof(struct bnxt_dl)); if (!dl) { - netdev_warn(bp->dev, "devlink_alloc failed"); + netdev_warn(bp->dev, "devlink_alloc failed\n"); return -ENOMEM; } @@ -692,7 +692,7 @@ int bnxt_dl_register(struct bnxt *bp) rc = devlink_register(dl, &bp->pdev->dev); if (rc) { - netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc); + netdev_warn(bp->dev, "devlink_register failed. rc=%d\n", rc); goto err_dl_free; } @@ -704,7 +704,7 @@ int bnxt_dl_register(struct bnxt *bp) sizeof(bp->dsn)); rc = devlink_port_register(dl, &bp->dl_port, bp->pf.port_id); if (rc) { - netdev_err(bp->dev, "devlink_port_register failed"); + netdev_err(bp->dev, "devlink_port_register failed\n"); goto err_dl_unreg; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 6171fa8b3677..e8fc1671c581 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -2028,7 +2028,7 @@ int bnxt_flash_package_from_file(struct net_device *dev, const char *filename, } if (fw->size > item_len) { - netdev_err(dev, "PKG insufficient update area in nvram: %lu", + netdev_err(dev, "PKG insufficient update area in nvram: %lu\n", (unsigned long)fw->size); rc = -EFBIG; } else { @@ -3338,7 +3338,7 @@ err: kfree(coredump.data); *dump_len += sizeof(struct bnxt_coredump_record); if (rc == -ENOBUFS) - netdev_err(bp->dev, "Firmware returned large coredump buffer"); + netdev_err(bp->dev, "Firmware returned large coredump buffer\n"); return rc; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 0cc6ec51f45f..9bec256b0934 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -50,7 +50,7 @@ static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev) /* check if dev belongs to the same switch */ if (!netdev_port_same_parent_id(pf_bp->dev, dev)) { - netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch", + netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch\n", dev->ifindex); return BNXT_FID_INVALID; } @@ -70,7 +70,7 @@ static int bnxt_tc_parse_redir(struct bnxt *bp, struct net_device *dev = act->dev; if (!dev) { - netdev_info(bp->dev, "no dev in mirred action"); + netdev_info(bp->dev, "no dev in mirred action\n"); return -EINVAL; } @@ -106,7 +106,7 @@ static int bnxt_tc_parse_tunnel_set(struct bnxt *bp, const struct ip_tunnel_key *tun_key = &tun_info->key; if (ip_tunnel_info_af(tun_info) != AF_INET) { - netdev_info(bp->dev, "only IPv4 tunnel-encap is supported"); + netdev_info(bp->dev, "only IPv4 tunnel-encap is supported\n"); return -EOPNOTSUPP; } @@ -295,7 +295,7 @@ static int bnxt_tc_parse_actions(struct bnxt *bp, int i, rc; if (!flow_action_has_entries(flow_action)) { - netdev_info(bp->dev, "no actions"); + netdev_info(bp->dev, "no actions\n"); return -EINVAL; } @@ -370,7 +370,7 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, /* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */ if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 || (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) == 0) { - netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x", + netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x\n", dissector->used_keys); return -EOPNOTSUPP; } @@ -508,7 +508,7 @@ static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); return rc; } @@ -841,7 +841,7 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp, resp = bnxt_get_hwrm_resp_addr(bp, &req); *decap_filter_handle = resp->decap_filter_id; } else { - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -859,7 +859,7 @@ static int hwrm_cfa_decap_filter_free(struct bnxt *bp, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); return rc; } @@ -906,7 +906,7 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp, resp = bnxt_get_hwrm_resp_addr(bp, &req); *encap_record_handle = resp->encap_record_id; } else { - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -924,7 +924,7 @@ static int hwrm_cfa_encap_record_free(struct bnxt *bp, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s: Error rc=%d\n", __func__, rc); return rc; } @@ -943,7 +943,7 @@ static int bnxt_tc_put_l2_node(struct bnxt *bp, tc_info->l2_ht_params); if (rc) netdev_err(bp->dev, - "Error: %s: rhashtable_remove_fast: %d", + "Error: %s: rhashtable_remove_fast: %d\n", __func__, rc); kfree_rcu(l2_node, rcu); } @@ -972,7 +972,7 @@ bnxt_tc_get_l2_node(struct bnxt *bp, struct rhashtable *l2_table, if (rc) { kfree_rcu(l2_node, rcu); netdev_err(bp->dev, - "Error: %s: rhashtable_insert_fast: %d", + "Error: %s: rhashtable_insert_fast: %d\n", __func__, rc); return NULL; } @@ -1031,7 +1031,7 @@ static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow) if ((flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) && (flow->l4_key.ip_proto != IPPROTO_TCP && flow->l4_key.ip_proto != IPPROTO_UDP)) { - netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports", + netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports\n", flow->l4_key.ip_proto); return false; } @@ -1088,7 +1088,7 @@ static int bnxt_tc_put_tunnel_node(struct bnxt *bp, rc = rhashtable_remove_fast(tunnel_table, &tunnel_node->node, *ht_params); if (rc) { - netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc); + netdev_err(bp->dev, "rhashtable_remove_fast rc=%d\n", rc); rc = -1; } kfree_rcu(tunnel_node, rcu); @@ -1129,7 +1129,7 @@ bnxt_tc_get_tunnel_node(struct bnxt *bp, struct rhashtable *tunnel_table, tunnel_node->refcount++; return tunnel_node; err: - netdev_info(bp->dev, "error rc=%d", rc); + netdev_info(bp->dev, "error rc=%d\n", rc); return NULL; } @@ -1187,7 +1187,7 @@ static void bnxt_tc_put_decap_l2_node(struct bnxt *bp, &decap_l2_node->node, tc_info->decap_l2_ht_params); if (rc) - netdev_err(bp->dev, "rhashtable_remove_fast rc=%d", rc); + netdev_err(bp->dev, "rhashtable_remove_fast rc=%d\n", rc); kfree_rcu(decap_l2_node, rcu); } } @@ -1227,7 +1227,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, rt = ip_route_output_key(dev_net(real_dst_dev), &flow); if (IS_ERR(rt)) { - netdev_info(bp->dev, "no route to %pI4b", &flow.daddr); + netdev_info(bp->dev, "no route to %pI4b\n", &flow.daddr); return -EOPNOTSUPP; } @@ -1241,7 +1241,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, if (vlan->real_dev != real_dst_dev) { netdev_info(bp->dev, - "dst_dev(%s) doesn't use PF-if(%s)", + "dst_dev(%s) doesn't use PF-if(%s)\n", netdev_name(dst_dev), netdev_name(real_dst_dev)); rc = -EOPNOTSUPP; @@ -1253,7 +1253,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, #endif } else if (dst_dev != real_dst_dev) { netdev_info(bp->dev, - "dst_dev(%s) for %pI4b is not PF-if(%s)", + "dst_dev(%s) for %pI4b is not PF-if(%s)\n", netdev_name(dst_dev), &flow.daddr, netdev_name(real_dst_dev)); rc = -EOPNOTSUPP; @@ -1262,7 +1262,7 @@ static int bnxt_tc_resolve_tunnel_hdrs(struct bnxt *bp, nbr = dst_neigh_lookup(&rt->dst, &flow.daddr); if (!nbr) { - netdev_info(bp->dev, "can't lookup neighbor for %pI4b", + netdev_info(bp->dev, "can't lookup neighbor for %pI4b\n", &flow.daddr); rc = -EOPNOTSUPP; goto put_rt; @@ -1472,7 +1472,7 @@ static int __bnxt_tc_del_flow(struct bnxt *bp, rc = rhashtable_remove_fast(&tc_info->flow_table, &flow_node->node, tc_info->flow_ht_params); if (rc) - netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d", + netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d\n", __func__, rc); kfree_rcu(flow_node, rcu); @@ -1587,7 +1587,7 @@ unlock: free_node: kfree_rcu(new_node, rcu); done: - netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d", + netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d\n", __func__, tc_flow_cmd->cookie, rc); return rc; } @@ -1700,7 +1700,7 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows, le64_to_cpu(resp_bytes[i]); } } else { - netdev_info(bp->dev, "error rc=%d", rc); + netdev_info(bp->dev, "error rc=%d\n", rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -1970,7 +1970,7 @@ static int bnxt_tc_indr_block_event(struct notifier_block *nb, bp); if (rc) netdev_info(bp->dev, - "Failed to register indirect blk: dev: %s", + "Failed to register indirect blk: dev: %s\n", netdev->name); break; case NETDEV_UNREGISTER: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c index b010b34cdaf8..6f2faf81c1ae 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -43,7 +43,7 @@ static int hwrm_cfa_vfr_alloc(struct bnxt *bp, u16 vf_idx, netdev_dbg(bp->dev, "tx_cfa_action=0x%x, rx_cfa_code=0x%x", *tx_cfa_action, *rx_cfa_code); } else { - netdev_info(bp->dev, "%s error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc); } mutex_unlock(&bp->hwrm_cmd_lock); @@ -60,7 +60,7 @@ static int hwrm_cfa_vfr_free(struct bnxt *bp, u16 vf_idx) rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - netdev_info(bp->dev, "%s error rc=%d", __func__, rc); + netdev_info(bp->dev, "%s error rc=%d\n", __func__, rc); return rc; } @@ -465,7 +465,7 @@ static int bnxt_vf_reps_create(struct bnxt *bp) return 0; err: - netdev_info(bp->dev, "%s error=%d", __func__, rc); + netdev_info(bp->dev, "%s error=%d\n", __func__, rc); kfree(cfa_code_map); __bnxt_vf_reps_destroy(bp); return rc; @@ -488,7 +488,7 @@ int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode, mutex_lock(&bp->sriov_lock); if (bp->eswitch_mode == mode) { - netdev_info(bp->dev, "already in %s eswitch mode", + netdev_info(bp->dev, "already in %s eswitch mode\n", mode == DEVLINK_ESWITCH_MODE_LEGACY ? "legacy" : "switchdev"); rc = -EINVAL; @@ -508,7 +508,7 @@ int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode, } if (pci_num_vf(bp->pdev) == 0) { - netdev_info(bp->dev, "Enable VFs before setting switchdev mode"); + netdev_info(bp->dev, "Enable VFs before setting switchdev mode\n"); rc = -EPERM; goto done; } diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 6392a2530183..10244941a7a6 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -294,6 +294,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) */ if (priv->ext_phy) { reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); + reg &= ~ID_MODE_DIS; reg |= id_mode_dis; if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv)) reg |= RGMII_MODE_EN_V123; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 6f2cf569a283..79b3d53f2fbf 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -297,6 +297,7 @@ static int set_hw_ioctxt(struct hinic_hwdev *hwdev, unsigned int rq_depth, } hw_ioctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + hw_ioctxt.ppf_idx = HINIC_HWIF_PPF_IDX(hwif); hw_ioctxt.set_cmdq_depth = HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT; hw_ioctxt.cmdq_depth = 0; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h index b069045de416..66fd2340d447 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -151,8 +151,8 @@ struct hinic_cmd_hw_ioctxt { u8 lro_en; u8 rsvd3; + u8 ppf_idx; u8 rsvd4; - u8 rsvd5; u16 rq_depth; u16 rx_buf_sz_idx; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h index 517794509eb2..c7bb9ceca72c 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h @@ -137,6 +137,7 @@ #define HINIC_HWIF_FUNC_IDX(hwif) ((hwif)->attr.func_idx) #define HINIC_HWIF_PCI_INTF(hwif) ((hwif)->attr.pci_intf_idx) #define HINIC_HWIF_PF_IDX(hwif) ((hwif)->attr.pf_idx) +#define HINIC_HWIF_PPF_IDX(hwif) ((hwif)->attr.ppf_idx) #define HINIC_FUNC_TYPE(hwif) ((hwif)->attr.func_type) #define HINIC_IS_PF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PF) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h index f4a339b10b10..79091e131418 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h @@ -94,6 +94,7 @@ struct hinic_rq { struct hinic_wq *wq; + struct cpumask affinity_mask; u32 irq; u16 msix_entry; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 02a14f5e7fe3..13560975c103 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -356,7 +356,8 @@ static void hinic_enable_rss(struct hinic_dev *nic_dev) if (!num_cpus) num_cpus = num_online_cpus(); - nic_dev->num_qps = min_t(u16, nic_dev->max_qps, num_cpus); + nic_dev->num_qps = hinic_hwdev_num_qps(hwdev); + nic_dev->num_qps = min_t(u16, nic_dev->num_qps, num_cpus); nic_dev->rss_limit = nic_dev->num_qps; nic_dev->num_rss = nic_dev->num_qps; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index 56ea6d692f1c..2695ad69fca6 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -475,7 +475,6 @@ static int rx_request_irq(struct hinic_rxq *rxq) struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_rq *rq = rxq->rq; struct hinic_qp *qp; - struct cpumask mask; int err; rx_add_napi(rxq); @@ -492,8 +491,8 @@ static int rx_request_irq(struct hinic_rxq *rxq) } qp = container_of(rq, struct hinic_qp, rq); - cpumask_set_cpu(qp->q_id % num_online_cpus(), &mask); - return irq_set_affinity_hint(rq->irq, &mask); + cpumask_set_cpu(qp->q_id % num_online_cpus(), &rq->affinity_mask); + return irq_set_affinity_hint(rq->irq, &rq->affinity_mask); } static void rx_free_irq(struct hinic_rxq *rxq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 966983674663..21de4764d4c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5147,7 +5147,6 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) static void mlx5e_nic_disable(struct mlx5e_priv *priv) { - struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; #ifdef CONFIG_MLX5_CORE_EN_DCB @@ -5168,7 +5167,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) mlx5e_monitor_counter_cleanup(priv); mlx5e_disable_async_events(priv); - mlx5_lag_remove(mdev, netdev); + mlx5_lag_remove(mdev); } int mlx5e_update_nic_rx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 7b48ccacebe2..6ed307d7f191 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1861,7 +1861,6 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) { - struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_rep_priv *rpriv = priv->ppriv; @@ -1870,7 +1869,7 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) #endif mlx5_notifier_unregister(mdev, &priv->events_nb); cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work); - mlx5_lag_remove(mdev, netdev); + mlx5_lag_remove(mdev); } static MLX5E_DEFINE_STATS_GRP(sw_rep, 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index b91eabc09fbc..8e19f6ab8393 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -464,9 +464,6 @@ static int mlx5_lag_netdev_event(struct notifier_block *this, struct mlx5_lag *ldev; int changed = 0; - if (!net_eq(dev_net(ndev), &init_net)) - return NOTIFY_DONE; - if ((event != NETDEV_CHANGEUPPER) && (event != NETDEV_CHANGELOWERSTATE)) return NOTIFY_DONE; @@ -586,8 +583,7 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) if (!ldev->nb.notifier_call) { ldev->nb.notifier_call = mlx5_lag_netdev_event; - if (register_netdevice_notifier_dev_net(netdev, &ldev->nb, - &ldev->nn)) { + if (register_netdevice_notifier_net(&init_net, &ldev->nb)) { ldev->nb.notifier_call = NULL; mlx5_core_err(dev, "Failed to register LAG netdev notifier\n"); } @@ -600,7 +596,7 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) } /* Must be called with intf_mutex held */ -void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev) +void mlx5_lag_remove(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; int i; @@ -620,8 +616,7 @@ void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev) if (i == MLX5_MAX_PORTS) { if (ldev->nb.notifier_call) - unregister_netdevice_notifier_dev_net(netdev, &ldev->nb, - &ldev->nn); + unregister_netdevice_notifier_net(&init_net, &ldev->nb); mlx5_lag_mp_cleanup(ldev); cancel_delayed_work_sync(&ldev->bond_work); mlx5_lag_dev_free(ldev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h index 316ab09e2664..f1068aac6406 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h @@ -44,7 +44,6 @@ struct mlx5_lag { struct workqueue_struct *wq; struct delayed_work bond_work; struct notifier_block nb; - struct netdev_net_notifier nn; struct lag_mp lag_mp; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index fcce9e0fc82c..da67b28d6e23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -157,7 +157,7 @@ int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam, u8 feature_group, u8 access_reg_group); void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev); -void mlx5_lag_remove(struct mlx5_core_dev *dev, struct net_device *netdev); +void mlx5_lag_remove(struct mlx5_core_dev *dev); int mlx5_irq_table_init(struct mlx5_core_dev *dev); void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index e0d7d2d9a0c8..43fa8c85b5d9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -28,7 +28,7 @@ #define MLXSW_PCI_SW_RESET 0xF0010 #define MLXSW_PCI_SW_RESET_RST_BIT BIT(0) #define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 900000 -#define MLXSW_PCI_SW_RESET_WAIT_MSECS 100 +#define MLXSW_PCI_SW_RESET_WAIT_MSECS 200 #define MLXSW_PCI_FW_READY 0xA1844 #define MLXSW_PCI_FW_READY_MASK 0xFFFF #define MLXSW_PCI_FW_READY_MAGIC 0x5E diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index 1c9e70c8cc30..58579baf3f7a 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -513,14 +513,17 @@ static irqreturn_t ks_irq(int irq, void *pw) { struct net_device *netdev = pw; struct ks_net *ks = netdev_priv(netdev); + unsigned long flags; u16 status; + spin_lock_irqsave(&ks->statelock, flags); /*this should be the first in IRQ handler */ ks_save_cmd_reg(ks); status = ks_rdreg16(ks, KS_ISR); if (unlikely(!status)) { ks_restore_cmd_reg(ks); + spin_unlock_irqrestore(&ks->statelock, flags); return IRQ_NONE; } @@ -546,6 +549,7 @@ static irqreturn_t ks_irq(int irq, void *pw) ks->netdev->stats.rx_over_errors++; /* this should be the last in IRQ handler*/ ks_restore_cmd_reg(ks); + spin_unlock_irqrestore(&ks->statelock, flags); return IRQ_HANDLED; } @@ -615,6 +619,7 @@ static int ks_net_stop(struct net_device *netdev) /* shutdown RX/TX QMU */ ks_disable_qmu(ks); + ks_disable_int(ks); /* set powermode to soft power down to save power */ ks_set_powermode(ks, PMECR_PM_SOFTDOWN); @@ -671,10 +676,9 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) { netdev_tx_t retv = NETDEV_TX_OK; struct ks_net *ks = netdev_priv(netdev); + unsigned long flags; - disable_irq(netdev->irq); - ks_disable_int(ks); - spin_lock(&ks->statelock); + spin_lock_irqsave(&ks->statelock, flags); /* Extra space are required: * 4 byte for alignment, 4 for status/length, 4 for CRC @@ -688,9 +692,7 @@ static netdev_tx_t ks_start_xmit(struct sk_buff *skb, struct net_device *netdev) dev_kfree_skb(skb); } else retv = NETDEV_TX_BUSY; - spin_unlock(&ks->statelock); - ks_enable_int(ks); - enable_irq(netdev->irq); + spin_unlock_irqrestore(&ks->statelock, flags); return retv; } diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 06de59521fc4..fbf4cbcf1a65 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -13,25 +13,6 @@ #include "rmnet_vnd.h" #include "rmnet_private.h" -/* Locking scheme - - * The shared resource which needs to be protected is realdev->rx_handler_data. - * For the writer path, this is using rtnl_lock(). The writer paths are - * rmnet_newlink(), rmnet_dellink() and rmnet_force_unassociate_device(). These - * paths are already called with rtnl_lock() acquired in. There is also an - * ASSERT_RTNL() to ensure that we are calling with rtnl acquired. For - * dereference here, we will need to use rtnl_dereference(). Dev list writing - * needs to happen with rtnl_lock() acquired for netdev_master_upper_dev_link(). - * For the reader path, the real_dev->rx_handler_data is called in the TX / RX - * path. We only need rcu_read_lock() for these scenarios. In these cases, - * the rcu_read_lock() is held in __dev_queue_xmit() and - * netif_receive_skb_internal(), so readers need to use rcu_dereference_rtnl() - * to get the relevant information. For dev list reading, we again acquire - * rcu_read_lock() in rmnet_dellink() for netdev_master_upper_dev_get_rcu(). - * We also use unregister_netdevice_many() to free all rmnet devices in - * rmnet_force_unassociate_device() so we dont lose the rtnl_lock() and free in - * same context. - */ - /* Local Definitions and Declarations */ static const struct nla_policy rmnet_policy[IFLA_RMNET_MAX + 1] = { @@ -51,9 +32,10 @@ rmnet_get_port_rtnl(const struct net_device *real_dev) return rtnl_dereference(real_dev->rx_handler_data); } -static int rmnet_unregister_real_device(struct net_device *real_dev, - struct rmnet_port *port) +static int rmnet_unregister_real_device(struct net_device *real_dev) { + struct rmnet_port *port = rmnet_get_port_rtnl(real_dev); + if (port->nr_rmnet_devs) return -EINVAL; @@ -61,9 +43,6 @@ static int rmnet_unregister_real_device(struct net_device *real_dev, kfree(port); - /* release reference on real_dev */ - dev_put(real_dev); - netdev_dbg(real_dev, "Removed from rmnet\n"); return 0; } @@ -89,9 +68,6 @@ static int rmnet_register_real_device(struct net_device *real_dev) return -EBUSY; } - /* hold on to real dev for MAP data */ - dev_hold(real_dev); - for (entry = 0; entry < RMNET_MAX_LOGICAL_EP; entry++) INIT_HLIST_HEAD(&port->muxed_ep[entry]); @@ -99,28 +75,33 @@ static int rmnet_register_real_device(struct net_device *real_dev) return 0; } -static void rmnet_unregister_bridge(struct net_device *dev, - struct rmnet_port *port) +static void rmnet_unregister_bridge(struct rmnet_port *port) { - struct rmnet_port *bridge_port; - struct net_device *bridge_dev; + struct net_device *bridge_dev, *real_dev, *rmnet_dev; + struct rmnet_port *real_port; if (port->rmnet_mode != RMNET_EPMODE_BRIDGE) return; - /* bridge slave handling */ + rmnet_dev = port->rmnet_dev; if (!port->nr_rmnet_devs) { - bridge_dev = port->bridge_ep; + /* bridge device */ + real_dev = port->bridge_ep; + bridge_dev = port->dev; - bridge_port = rmnet_get_port_rtnl(bridge_dev); - bridge_port->bridge_ep = NULL; - bridge_port->rmnet_mode = RMNET_EPMODE_VND; + real_port = rmnet_get_port_rtnl(real_dev); + real_port->bridge_ep = NULL; + real_port->rmnet_mode = RMNET_EPMODE_VND; } else { + /* real device */ bridge_dev = port->bridge_ep; - bridge_port = rmnet_get_port_rtnl(bridge_dev); - rmnet_unregister_real_device(bridge_dev, bridge_port); + port->bridge_ep = NULL; + port->rmnet_mode = RMNET_EPMODE_VND; } + + netdev_upper_dev_unlink(bridge_dev, rmnet_dev); + rmnet_unregister_real_device(bridge_dev); } static int rmnet_newlink(struct net *src_net, struct net_device *dev, @@ -135,6 +116,11 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, int err = 0; u16 mux_id; + if (!tb[IFLA_LINK]) { + NL_SET_ERR_MSG_MOD(extack, "link not specified"); + return -EINVAL; + } + real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev || !dev) return -ENODEV; @@ -157,7 +143,12 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, if (err) goto err1; + err = netdev_upper_dev_link(real_dev, dev, extack); + if (err < 0) + goto err2; + port->rmnet_mode = mode; + port->rmnet_dev = dev; hlist_add_head_rcu(&ep->hlnode, &port->muxed_ep[mux_id]); @@ -173,8 +164,11 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, return 0; +err2: + unregister_netdevice(dev); + rmnet_vnd_dellink(mux_id, port, ep); err1: - rmnet_unregister_real_device(real_dev, port); + rmnet_unregister_real_device(real_dev); err0: kfree(ep); return err; @@ -183,77 +177,74 @@ err0: static void rmnet_dellink(struct net_device *dev, struct list_head *head) { struct rmnet_priv *priv = netdev_priv(dev); - struct net_device *real_dev; + struct net_device *real_dev, *bridge_dev; + struct rmnet_port *real_port, *bridge_port; struct rmnet_endpoint *ep; - struct rmnet_port *port; - u8 mux_id; + u8 mux_id = priv->mux_id; real_dev = priv->real_dev; - if (!real_dev || !rmnet_is_real_dev_registered(real_dev)) + if (!rmnet_is_real_dev_registered(real_dev)) return; - port = rmnet_get_port_rtnl(real_dev); - - mux_id = rmnet_vnd_get_mux(dev); + real_port = rmnet_get_port_rtnl(real_dev); + bridge_dev = real_port->bridge_ep; + if (bridge_dev) { + bridge_port = rmnet_get_port_rtnl(bridge_dev); + rmnet_unregister_bridge(bridge_port); + } - ep = rmnet_get_endpoint(port, mux_id); + ep = rmnet_get_endpoint(real_port, mux_id); if (ep) { hlist_del_init_rcu(&ep->hlnode); - rmnet_unregister_bridge(dev, port); - rmnet_vnd_dellink(mux_id, port, ep); + rmnet_vnd_dellink(mux_id, real_port, ep); kfree(ep); } - rmnet_unregister_real_device(real_dev, port); + netdev_upper_dev_unlink(real_dev, dev); + rmnet_unregister_real_device(real_dev); unregister_netdevice_queue(dev, head); } -static void rmnet_force_unassociate_device(struct net_device *dev) +static void rmnet_force_unassociate_device(struct net_device *real_dev) { - struct net_device *real_dev = dev; struct hlist_node *tmp_ep; struct rmnet_endpoint *ep; struct rmnet_port *port; unsigned long bkt_ep; LIST_HEAD(list); - if (!rmnet_is_real_dev_registered(real_dev)) - return; - - ASSERT_RTNL(); - - port = rmnet_get_port_rtnl(dev); - - rcu_read_lock(); - rmnet_unregister_bridge(dev, port); - - hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) { - unregister_netdevice_queue(ep->egress_dev, &list); - rmnet_vnd_dellink(ep->mux_id, port, ep); + port = rmnet_get_port_rtnl(real_dev); - hlist_del_init_rcu(&ep->hlnode); - kfree(ep); + if (port->nr_rmnet_devs) { + /* real device */ + rmnet_unregister_bridge(port); + hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) { + unregister_netdevice_queue(ep->egress_dev, &list); + netdev_upper_dev_unlink(real_dev, ep->egress_dev); + rmnet_vnd_dellink(ep->mux_id, port, ep); + hlist_del_init_rcu(&ep->hlnode); + kfree(ep); + } + rmnet_unregister_real_device(real_dev); + unregister_netdevice_many(&list); + } else { + rmnet_unregister_bridge(port); } - - rcu_read_unlock(); - unregister_netdevice_many(&list); - - rmnet_unregister_real_device(real_dev, port); } static int rmnet_config_notify_cb(struct notifier_block *nb, unsigned long event, void *data) { - struct net_device *dev = netdev_notifier_info_to_dev(data); + struct net_device *real_dev = netdev_notifier_info_to_dev(data); - if (!dev) + if (!rmnet_is_real_dev_registered(real_dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UNREGISTER: - netdev_dbg(dev, "Kernel unregister\n"); - rmnet_force_unassociate_device(dev); + netdev_dbg(real_dev, "Kernel unregister\n"); + rmnet_force_unassociate_device(real_dev); break; default: @@ -295,16 +286,18 @@ static int rmnet_changelink(struct net_device *dev, struct nlattr *tb[], if (!dev) return -ENODEV; - real_dev = __dev_get_by_index(dev_net(dev), - nla_get_u32(tb[IFLA_LINK])); - - if (!real_dev || !rmnet_is_real_dev_registered(real_dev)) + real_dev = priv->real_dev; + if (!rmnet_is_real_dev_registered(real_dev)) return -ENODEV; port = rmnet_get_port_rtnl(real_dev); if (data[IFLA_RMNET_MUX_ID]) { mux_id = nla_get_u16(data[IFLA_RMNET_MUX_ID]); + if (rmnet_get_endpoint(port, mux_id)) { + NL_SET_ERR_MSG_MOD(extack, "MUX ID already exists"); + return -EINVAL; + } ep = rmnet_get_endpoint(port, priv->mux_id); if (!ep) return -ENODEV; @@ -379,11 +372,10 @@ struct rtnl_link_ops rmnet_link_ops __read_mostly = { .fill_info = rmnet_fill_info, }; -/* Needs either rcu_read_lock() or rtnl lock */ -struct rmnet_port *rmnet_get_port(struct net_device *real_dev) +struct rmnet_port *rmnet_get_port_rcu(struct net_device *real_dev) { if (rmnet_is_real_dev_registered(real_dev)) - return rcu_dereference_rtnl(real_dev->rx_handler_data); + return rcu_dereference_bh(real_dev->rx_handler_data); else return NULL; } @@ -409,7 +401,7 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, struct rmnet_port *port, *slave_port; int err; - port = rmnet_get_port(real_dev); + port = rmnet_get_port_rtnl(real_dev); /* If there is more than one rmnet dev attached, its probably being * used for muxing. Skip the briding in that case @@ -417,6 +409,9 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, if (port->nr_rmnet_devs > 1) return -EINVAL; + if (port->rmnet_mode != RMNET_EPMODE_VND) + return -EINVAL; + if (rmnet_is_real_dev_registered(slave_dev)) return -EBUSY; @@ -424,9 +419,17 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, if (err) return -EBUSY; - slave_port = rmnet_get_port(slave_dev); + err = netdev_master_upper_dev_link(slave_dev, rmnet_dev, NULL, NULL, + extack); + if (err) { + rmnet_unregister_real_device(slave_dev); + return err; + } + + slave_port = rmnet_get_port_rtnl(slave_dev); slave_port->rmnet_mode = RMNET_EPMODE_BRIDGE; slave_port->bridge_ep = real_dev; + slave_port->rmnet_dev = rmnet_dev; port->rmnet_mode = RMNET_EPMODE_BRIDGE; port->bridge_ep = slave_dev; @@ -438,16 +441,9 @@ int rmnet_add_bridge(struct net_device *rmnet_dev, int rmnet_del_bridge(struct net_device *rmnet_dev, struct net_device *slave_dev) { - struct rmnet_priv *priv = netdev_priv(rmnet_dev); - struct net_device *real_dev = priv->real_dev; - struct rmnet_port *port, *slave_port; + struct rmnet_port *port = rmnet_get_port_rtnl(slave_dev); - port = rmnet_get_port(real_dev); - port->rmnet_mode = RMNET_EPMODE_VND; - port->bridge_ep = NULL; - - slave_port = rmnet_get_port(slave_dev); - rmnet_unregister_real_device(slave_dev, slave_port); + rmnet_unregister_bridge(port); netdev_dbg(slave_dev, "removed from rmnet as slave\n"); return 0; @@ -473,8 +469,8 @@ static int __init rmnet_init(void) static void __exit rmnet_exit(void) { - unregister_netdevice_notifier(&rmnet_dev_notifier); rtnl_link_unregister(&rmnet_link_ops); + unregister_netdevice_notifier(&rmnet_dev_notifier); } module_init(rmnet_init) diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index cd0a6bcbe74a..be515982d628 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -28,6 +28,7 @@ struct rmnet_port { u8 rmnet_mode; struct hlist_head muxed_ep[RMNET_MAX_LOGICAL_EP]; struct net_device *bridge_ep; + struct net_device *rmnet_dev; }; extern struct rtnl_link_ops rmnet_link_ops; @@ -65,7 +66,7 @@ struct rmnet_priv { struct rmnet_priv_stats stats; }; -struct rmnet_port *rmnet_get_port(struct net_device *real_dev); +struct rmnet_port *rmnet_get_port_rcu(struct net_device *real_dev); struct rmnet_endpoint *rmnet_get_endpoint(struct rmnet_port *port, u8 mux_id); int rmnet_add_bridge(struct net_device *rmnet_dev, struct net_device *slave_dev, diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 1b74bc160402..29a7bfa2584d 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -159,6 +159,9 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, static void rmnet_bridge_handler(struct sk_buff *skb, struct net_device *bridge_dev) { + if (skb_mac_header_was_set(skb)) + skb_push(skb, skb->mac_len); + if (bridge_dev) { skb->dev = bridge_dev; dev_queue_xmit(skb); @@ -184,7 +187,7 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) return RX_HANDLER_PASS; dev = skb->dev; - port = rmnet_get_port(dev); + port = rmnet_get_port_rcu(dev); switch (port->rmnet_mode) { case RMNET_EPMODE_VND: @@ -217,7 +220,7 @@ void rmnet_egress_handler(struct sk_buff *skb) skb->dev = priv->real_dev; mux_id = priv->mux_id; - port = rmnet_get_port(skb->dev); + port = rmnet_get_port_rcu(skb->dev); if (!port) goto drop; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 509dfc895a33..26ad40f19c64 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -266,14 +266,6 @@ int rmnet_vnd_dellink(u8 id, struct rmnet_port *port, return 0; } -u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev) -{ - struct rmnet_priv *priv; - - priv = netdev_priv(rmnet_dev); - return priv->mux_id; -} - int rmnet_vnd_do_flow_control(struct net_device *rmnet_dev, int enable) { netdev_dbg(rmnet_dev, "Setting VND TX queue state to %d\n", enable); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h index 54cbaf3c3bc4..14d77c709d4a 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h @@ -16,6 +16,5 @@ int rmnet_vnd_dellink(u8 id, struct rmnet_port *port, struct rmnet_endpoint *ep); void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev); void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev); -u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev); void rmnet_vnd_setup(struct net_device *dev); #endif /* _RMNET_VND_H_ */ diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index af15a737c675..59b4f16896a8 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -560,13 +560,45 @@ efx_ptp_mac_nic_to_ktime_correction(struct efx_nic *efx, u32 nic_major, u32 nic_minor, s32 correction) { + u32 sync_timestamp; ktime_t kt = { 0 }; + s16 delta; if (!(nic_major & 0x80000000)) { WARN_ON_ONCE(nic_major >> 16); - /* Use the top bits from the latest sync event. */ - nic_major &= 0xffff; - nic_major |= (last_sync_timestamp_major(efx) & 0xffff0000); + + /* Medford provides 48 bits of timestamp, so we must get the top + * 16 bits from the timesync event state. + * + * We only have the lower 16 bits of the time now, but we do + * have a full resolution timestamp at some point in past. As + * long as the difference between the (real) now and the sync + * is less than 2^15, then we can reconstruct the difference + * between those two numbers using only the lower 16 bits of + * each. + * + * Put another way + * + * a - b = ((a mod k) - b) mod k + * + * when -k/2 < (a-b) < k/2. In our case k is 2^16. We know + * (a mod k) and b, so can calculate the delta, a - b. + * + */ + sync_timestamp = last_sync_timestamp_major(efx); + + /* Because delta is s16 this does an implicit mask down to + * 16 bits which is what we need, assuming + * MEDFORD_TX_SECS_EVENT_BITS is 16. delta is signed so that + * we can deal with the (unlikely) case of sync timestamps + * arriving from the future. + */ + delta = nic_major - sync_timestamp; + + /* Recover the fully specified time now, by applying the offset + * to the (fully specified) sync time. + */ + nic_major = sync_timestamp + delta; kt = ptp->nic_to_kernel_time(nic_major, nic_minor, correction); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5836b21edd7e..7da18c9afa01 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4405,6 +4405,8 @@ static void stmmac_init_fs(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + rtnl_lock(); + /* Create per netdev entries */ priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir); @@ -4416,14 +4418,13 @@ static void stmmac_init_fs(struct net_device *dev) debugfs_create_file("dma_cap", 0444, priv->dbgfs_dir, dev, &stmmac_dma_cap_fops); - register_netdevice_notifier(&stmmac_notifier); + rtnl_unlock(); } static void stmmac_exit_fs(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); - unregister_netdevice_notifier(&stmmac_notifier); debugfs_remove_recursive(priv->dbgfs_dir); } #endif /* CONFIG_DEBUG_FS */ @@ -4940,14 +4941,14 @@ int stmmac_dvr_remove(struct device *dev) netdev_info(priv->dev, "%s: removing driver", __func__); -#ifdef CONFIG_DEBUG_FS - stmmac_exit_fs(ndev); -#endif stmmac_stop_all_dma(priv); stmmac_mac_set(priv, priv->ioaddr, false); netif_carrier_off(ndev); unregister_netdev(ndev); +#ifdef CONFIG_DEBUG_FS + stmmac_exit_fs(ndev); +#endif phylink_destroy(priv->phylink); if (priv->plat->stmmac_rst) reset_control_assert(priv->plat->stmmac_rst); @@ -5166,6 +5167,7 @@ static int __init stmmac_init(void) /* Create debugfs main directory if it doesn't exist yet */ if (!stmmac_fs_dir) stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL); + register_netdevice_notifier(&stmmac_notifier); #endif return 0; @@ -5174,6 +5176,7 @@ static int __init stmmac_init(void) static void __exit stmmac_exit(void) { #ifdef CONFIG_DEBUG_FS + unregister_netdevice_notifier(&stmmac_notifier); debugfs_remove_recursive(stmmac_fs_dir); #endif } diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h index 276292bca334..53fb8141f1a6 100644 --- a/drivers/net/ethernet/xilinx/ll_temac.h +++ b/drivers/net/ethernet/xilinx/ll_temac.h @@ -375,10 +375,14 @@ struct temac_local { int tx_bd_next; int tx_bd_tail; int rx_bd_ci; + int rx_bd_tail; /* DMA channel control setup */ u32 tx_chnl_ctrl; u32 rx_chnl_ctrl; + u8 coalesce_count_rx; + + struct delayed_work restart_work; }; /* Wrappers for temac_ior()/temac_iow() function pointers above */ diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 6f11f52c9a9e..9461acec6f70 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -51,6 +51,7 @@ #include <linux/ip.h> #include <linux/slab.h> #include <linux/interrupt.h> +#include <linux/workqueue.h> #include <linux/dma-mapping.h> #include <linux/processor.h> #include <linux/platform_data/xilinx-ll-temac.h> @@ -367,6 +368,8 @@ static int temac_dma_bd_init(struct net_device *ndev) skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data, XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); + if (dma_mapping_error(ndev->dev.parent, skb_dma_addr)) + goto out; lp->rx_bd_v[i].phys = cpu_to_be32(skb_dma_addr); lp->rx_bd_v[i].len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE); lp->rx_bd_v[i].app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND); @@ -387,12 +390,13 @@ static int temac_dma_bd_init(struct net_device *ndev) lp->tx_bd_next = 0; lp->tx_bd_tail = 0; lp->rx_bd_ci = 0; + lp->rx_bd_tail = RX_BD_NUM - 1; /* Enable RX DMA transfers */ wmb(); lp->dma_out(lp, RX_CURDESC_PTR, lp->rx_bd_p); lp->dma_out(lp, RX_TAILDESC_PTR, - lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1))); + lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * lp->rx_bd_tail)); /* Prepare for TX DMA transfer */ lp->dma_out(lp, TX_CURDESC_PTR, lp->tx_bd_p); @@ -788,6 +792,9 @@ static void temac_start_xmit_done(struct net_device *ndev) stat = be32_to_cpu(cur_p->app0); } + /* Matches barrier in temac_start_xmit */ + smp_mb(); + netif_wake_queue(ndev); } @@ -830,9 +837,19 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; if (temac_check_tx_bd_space(lp, num_frag + 1)) { - if (!netif_queue_stopped(ndev)) - netif_stop_queue(ndev); - return NETDEV_TX_BUSY; + if (netif_queue_stopped(ndev)) + return NETDEV_TX_BUSY; + + netif_stop_queue(ndev); + + /* Matches barrier in temac_start_xmit_done */ + smp_mb(); + + /* Space might have just been freed - check again */ + if (temac_check_tx_bd_space(lp, num_frag)) + return NETDEV_TX_BUSY; + + netif_wake_queue(ndev); } cur_p->app0 = 0; @@ -850,12 +867,16 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data, skb_headlen(skb), DMA_TO_DEVICE); cur_p->len = cpu_to_be32(skb_headlen(skb)); + if (WARN_ON_ONCE(dma_mapping_error(ndev->dev.parent, skb_dma_addr))) { + dev_kfree_skb_any(skb); + ndev->stats.tx_dropped++; + return NETDEV_TX_OK; + } cur_p->phys = cpu_to_be32(skb_dma_addr); ptr_to_txbd((void *)skb, cur_p); for (ii = 0; ii < num_frag; ii++) { - lp->tx_bd_tail++; - if (lp->tx_bd_tail >= TX_BD_NUM) + if (++lp->tx_bd_tail >= TX_BD_NUM) lp->tx_bd_tail = 0; cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; @@ -863,6 +884,27 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_frag_address(frag), skb_frag_size(frag), DMA_TO_DEVICE); + if (dma_mapping_error(ndev->dev.parent, skb_dma_addr)) { + if (--lp->tx_bd_tail < 0) + lp->tx_bd_tail = TX_BD_NUM - 1; + cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; + while (--ii >= 0) { + --frag; + dma_unmap_single(ndev->dev.parent, + be32_to_cpu(cur_p->phys), + skb_frag_size(frag), + DMA_TO_DEVICE); + if (--lp->tx_bd_tail < 0) + lp->tx_bd_tail = TX_BD_NUM - 1; + cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; + } + dma_unmap_single(ndev->dev.parent, + be32_to_cpu(cur_p->phys), + skb_headlen(skb), DMA_TO_DEVICE); + dev_kfree_skb_any(skb); + ndev->stats.tx_dropped++; + return NETDEV_TX_OK; + } cur_p->phys = cpu_to_be32(skb_dma_addr); cur_p->len = cpu_to_be32(skb_frag_size(frag)); cur_p->app0 = 0; @@ -884,31 +926,56 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } +static int ll_temac_recv_buffers_available(struct temac_local *lp) +{ + int available; + + if (!lp->rx_skb[lp->rx_bd_ci]) + return 0; + available = 1 + lp->rx_bd_tail - lp->rx_bd_ci; + if (available <= 0) + available += RX_BD_NUM; + return available; +} static void ll_temac_recv(struct net_device *ndev) { struct temac_local *lp = netdev_priv(ndev); - struct sk_buff *skb, *new_skb; - unsigned int bdstat; - struct cdmac_bd *cur_p; - dma_addr_t tail_p, skb_dma_addr; - int length; unsigned long flags; + int rx_bd; + bool update_tail = false; spin_lock_irqsave(&lp->rx_lock, flags); - tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci; - cur_p = &lp->rx_bd_v[lp->rx_bd_ci]; - - bdstat = be32_to_cpu(cur_p->app0); - while ((bdstat & STS_CTRL_APP0_CMPLT)) { + /* Process all received buffers, passing them on network + * stack. After this, the buffer descriptors will be in an + * un-allocated stage, where no skb is allocated for it, and + * they are therefore not available for TEMAC/DMA. + */ + do { + struct cdmac_bd *bd = &lp->rx_bd_v[lp->rx_bd_ci]; + struct sk_buff *skb = lp->rx_skb[lp->rx_bd_ci]; + unsigned int bdstat = be32_to_cpu(bd->app0); + int length; + + /* While this should not normally happen, we can end + * here when GFP_ATOMIC allocations fail, and we + * therefore have un-allocated buffers. + */ + if (!skb) + break; - skb = lp->rx_skb[lp->rx_bd_ci]; - length = be32_to_cpu(cur_p->app4) & 0x3FFF; + /* Loop over all completed buffer descriptors */ + if (!(bdstat & STS_CTRL_APP0_CMPLT)) + break; - dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys), + dma_unmap_single(ndev->dev.parent, be32_to_cpu(bd->phys), XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); + /* The buffer is not valid for DMA anymore */ + bd->phys = 0; + bd->len = 0; + length = be32_to_cpu(bd->app4) & 0x3FFF; skb_put(skb, length); skb->protocol = eth_type_trans(skb, ndev); skb_checksum_none_assert(skb); @@ -923,43 +990,102 @@ static void ll_temac_recv(struct net_device *ndev) * (back) for proper IP checksum byte order * (be16). */ - skb->csum = htons(be32_to_cpu(cur_p->app3) & 0xFFFF); + skb->csum = htons(be32_to_cpu(bd->app3) & 0xFFFF); skb->ip_summed = CHECKSUM_COMPLETE; } if (!skb_defer_rx_timestamp(skb)) netif_rx(skb); + /* The skb buffer is now owned by network stack above */ + lp->rx_skb[lp->rx_bd_ci] = NULL; ndev->stats.rx_packets++; ndev->stats.rx_bytes += length; - new_skb = netdev_alloc_skb_ip_align(ndev, - XTE_MAX_JUMBO_FRAME_SIZE); - if (!new_skb) { - spin_unlock_irqrestore(&lp->rx_lock, flags); - return; + rx_bd = lp->rx_bd_ci; + if (++lp->rx_bd_ci >= RX_BD_NUM) + lp->rx_bd_ci = 0; + } while (rx_bd != lp->rx_bd_tail); + + /* DMA operations will halt when the last buffer descriptor is + * processed (ie. the one pointed to by RX_TAILDESC_PTR). + * When that happens, no more interrupt events will be + * generated. No IRQ_COAL or IRQ_DLY, and not even an + * IRQ_ERR. To avoid stalling, we schedule a delayed work + * when there is a potential risk of that happening. The work + * will call this function, and thus re-schedule itself until + * enough buffers are available again. + */ + if (ll_temac_recv_buffers_available(lp) < lp->coalesce_count_rx) + schedule_delayed_work(&lp->restart_work, HZ / 1000); + + /* Allocate new buffers for those buffer descriptors that were + * passed to network stack. Note that GFP_ATOMIC allocations + * can fail (e.g. when a larger burst of GFP_ATOMIC + * allocations occurs), so while we try to allocate all + * buffers in the same interrupt where they were processed, we + * continue with what we could get in case of allocation + * failure. Allocation of remaining buffers will be retried + * in following calls. + */ + while (1) { + struct sk_buff *skb; + struct cdmac_bd *bd; + dma_addr_t skb_dma_addr; + + rx_bd = lp->rx_bd_tail + 1; + if (rx_bd >= RX_BD_NUM) + rx_bd = 0; + bd = &lp->rx_bd_v[rx_bd]; + + if (bd->phys) + break; /* All skb's allocated */ + + skb = netdev_alloc_skb_ip_align(ndev, XTE_MAX_JUMBO_FRAME_SIZE); + if (!skb) { + dev_warn(&ndev->dev, "skb alloc failed\n"); + break; } - cur_p->app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND); - skb_dma_addr = dma_map_single(ndev->dev.parent, new_skb->data, + skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data, XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); - cur_p->phys = cpu_to_be32(skb_dma_addr); - cur_p->len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE); - lp->rx_skb[lp->rx_bd_ci] = new_skb; + if (WARN_ON_ONCE(dma_mapping_error(ndev->dev.parent, + skb_dma_addr))) { + dev_kfree_skb_any(skb); + break; + } - lp->rx_bd_ci++; - if (lp->rx_bd_ci >= RX_BD_NUM) - lp->rx_bd_ci = 0; + bd->phys = cpu_to_be32(skb_dma_addr); + bd->len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE); + bd->app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND); + lp->rx_skb[rx_bd] = skb; - cur_p = &lp->rx_bd_v[lp->rx_bd_ci]; - bdstat = be32_to_cpu(cur_p->app0); + lp->rx_bd_tail = rx_bd; + update_tail = true; + } + + /* Move tail pointer when buffers have been allocated */ + if (update_tail) { + lp->dma_out(lp, RX_TAILDESC_PTR, + lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_tail); } - lp->dma_out(lp, RX_TAILDESC_PTR, tail_p); spin_unlock_irqrestore(&lp->rx_lock, flags); } +/* Function scheduled to ensure a restart in case of DMA halt + * condition caused by running out of buffer descriptors. + */ +static void ll_temac_restart_work_func(struct work_struct *work) +{ + struct temac_local *lp = container_of(work, struct temac_local, + restart_work.work); + struct net_device *ndev = lp->ndev; + + ll_temac_recv(ndev); +} + static irqreturn_t ll_temac_tx_irq(int irq, void *_ndev) { struct net_device *ndev = _ndev; @@ -1052,6 +1178,8 @@ static int temac_stop(struct net_device *ndev) dev_dbg(&ndev->dev, "temac_close()\n"); + cancel_delayed_work_sync(&lp->restart_work); + free_irq(lp->tx_irq, ndev); free_irq(lp->rx_irq, ndev); @@ -1173,6 +1301,7 @@ static int temac_probe(struct platform_device *pdev) lp->dev = &pdev->dev; lp->options = XTE_OPTION_DEFAULTS; spin_lock_init(&lp->rx_lock); + INIT_DELAYED_WORK(&lp->restart_work, ll_temac_restart_work_func); /* Setup mutex for synchronization of indirect register access */ if (pdata) { @@ -1279,6 +1408,7 @@ static int temac_probe(struct platform_device *pdev) */ lp->tx_chnl_ctrl = 0x10220000; lp->rx_chnl_ctrl = 0xff070000; + lp->coalesce_count_rx = 0x07; /* Finished with the DMA node; drop the reference */ of_node_put(dma_np); @@ -1310,11 +1440,14 @@ static int temac_probe(struct platform_device *pdev) (pdata->tx_irq_count << 16); else lp->tx_chnl_ctrl = 0x10220000; - if (pdata->rx_irq_timeout || pdata->rx_irq_count) + if (pdata->rx_irq_timeout || pdata->rx_irq_count) { lp->rx_chnl_ctrl = (pdata->rx_irq_timeout << 24) | (pdata->rx_irq_count << 16); - else + lp->coalesce_count_rx = pdata->rx_irq_count; + } else { lp->rx_chnl_ctrl = 0xff070000; + lp->coalesce_count_rx = 0x07; + } } /* Error handle returned DMA RX and TX interrupts */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index ae3f3084c2ed..1b320bcf150a 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -99,7 +99,7 @@ static struct netvsc_device *alloc_net_device(void) init_waitqueue_head(&net_device->wait_drain); net_device->destroy = false; - net_device->tx_disable = false; + net_device->tx_disable = true; net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 65e12cb07f45..2c0a24c606fc 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1068,6 +1068,7 @@ static int netvsc_attach(struct net_device *ndev, } /* In any case device is now ready */ + nvdev->tx_disable = false; netif_device_attach(ndev); /* Note: enable and attach happen when sub-channels setup */ @@ -2476,6 +2477,8 @@ static int netvsc_probe(struct hv_device *dev, else net->max_mtu = ETH_DATA_LEN; + nvdev->tx_disable = false; + ret = register_netdevice(net); if (ret != 0) { pr_err("Unable to register netdev.\n"); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 28e33ece4ce1..9a8badafea8a 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1306,6 +1306,9 @@ static int marvell_read_status_page_an(struct phy_device *phydev, } } + if (!(status & MII_M1011_PHY_STATUS_RESOLVED)) + return 0; + if (status & MII_M1011_PHY_STATUS_FULLDUPLEX) phydev->duplex = DUPLEX_FULL; else @@ -1365,6 +1368,8 @@ static int marvell_read_status_page(struct phy_device *phydev, int page) linkmode_zero(phydev->lp_advertising); phydev->pause = 0; phydev->asym_pause = 0; + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; if (phydev->autoneg == AUTONEG_ENABLE) err = marvell_read_status_page_an(phydev, fiber, status); diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c index 937ac7da2789..f686f40f6bdc 100644 --- a/drivers/net/phy/mscc.c +++ b/drivers/net/phy/mscc.c @@ -345,11 +345,11 @@ enum macsec_bank { BIT(VSC8531_FORCE_LED_OFF) | \ BIT(VSC8531_FORCE_LED_ON)) -#define MSCC_VSC8584_REVB_INT8051_FW "mscc_vsc8584_revb_int8051_fb48.bin" +#define MSCC_VSC8584_REVB_INT8051_FW "microchip/mscc_vsc8584_revb_int8051_fb48.bin" #define MSCC_VSC8584_REVB_INT8051_FW_START_ADDR 0xe800 #define MSCC_VSC8584_REVB_INT8051_FW_CRC 0xfb48 -#define MSCC_VSC8574_REVB_INT8051_FW "mscc_vsc8574_revb_int8051_29e8.bin" +#define MSCC_VSC8574_REVB_INT8051_FW "microchip/mscc_vsc8574_revb_int8051_29e8.bin" #define MSCC_VSC8574_REVB_INT8051_FW_START_ADDR 0x4000 #define MSCC_VSC8574_REVB_INT8051_FW_CRC 0x29e8 diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index a1caeee12236..dd2e23fb67c0 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -167,7 +167,7 @@ EXPORT_SYMBOL_GPL(genphy_c45_restart_aneg); */ int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart) { - int ret = 0; + int ret; if (!restart) { /* Configure and restart aneg if it wasn't set before */ @@ -180,9 +180,9 @@ int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart) } if (restart) - ret = genphy_c45_restart_aneg(phydev); + return genphy_c45_restart_aneg(phydev); - return ret; + return 0; } EXPORT_SYMBOL_GPL(genphy_c45_check_and_restart_aneg); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 6a5056e0ae77..c8b0c34030d3 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -247,7 +247,7 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) * MDIO bus driver and clock gated at this point. */ if (!netdev) - return !phydev->suspended; + goto out; if (netdev->wol_enabled) return false; @@ -267,7 +267,8 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) if (device_may_wakeup(&netdev->dev)) return false; - return true; +out: + return !phydev->suspended; } static int mdio_bus_phy_suspend(struct device *dev) @@ -1792,7 +1793,7 @@ EXPORT_SYMBOL(genphy_restart_aneg); */ int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart) { - int ret = 0; + int ret; if (!restart) { /* Advertisement hasn't changed, but maybe aneg was never on to @@ -1807,9 +1808,9 @@ int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart) } if (restart) - ret = genphy_restart_aneg(phydev); + return genphy_restart_aneg(phydev); - return ret; + return 0; } EXPORT_SYMBOL(genphy_check_and_restart_aneg); diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 6f4d7ba8b109..babb01888b78 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -863,7 +863,10 @@ err_free_chan: tty->disc_data = NULL; clear_bit(SLF_INUSE, &sl->flags); sl_free_netdev(sl->dev); + /* do not call free_netdev before rtnl_unlock */ + rtnl_unlock(); free_netdev(sl->dev); + return err; err_exit: rtnl_unlock(); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 3b7a3b8a5e06..5754bb6ca0ee 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -337,6 +337,9 @@ static void qmi_wwan_netdev_setup(struct net_device *net) netdev_dbg(net, "mode: raw IP\n"); } else if (!net->header_ops) { /* don't bother if already set */ ether_setup(net); + /* Restoring min/max mtu values set originally by usbnet */ + net->min_mtu = 0; + net->max_mtu = ETH_MAX_MTU; clear_bit(EVENT_NO_IP_ALIGN, &dev->flags); netdev_dbg(net, "mode: Ethernet\n"); } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index ace4dd9e953c..d3f23d6254e4 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1078,9 +1078,9 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx) spin_lock(&nvmeq->cq_poll_lock); found = nvme_process_cq(nvmeq, &start, &end, -1); + nvme_complete_cqes(nvmeq, start, end); spin_unlock(&nvmeq->cq_poll_lock); - nvme_complete_cqes(nvmeq, start, end); return found; } diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c index d20aabc26273..3a10e678c7f4 100644 --- a/drivers/pci/controller/pcie-brcmstb.c +++ b/drivers/pci/controller/pcie-brcmstb.c @@ -670,7 +670,7 @@ static inline int brcm_pcie_get_rc_bar2_size_and_offset(struct brcm_pcie *pcie, * outbound memory @ 3GB). So instead it will start at the 1x * multiple of its size */ - if (!*rc_bar2_size || *rc_bar2_offset % *rc_bar2_size || + if (!*rc_bar2_size || (*rc_bar2_offset & (*rc_bar2_size - 1)) || (*rc_bar2_offset < SZ_4G && *rc_bar2_offset > SZ_2G)) { dev_err(dev, "Invalid rc_bar2_offset/size: size 0x%llx, off 0x%llx\n", *rc_bar2_size, *rc_bar2_offset); diff --git a/drivers/platform/chrome/wilco_ec/properties.c b/drivers/platform/chrome/wilco_ec/properties.c index e69682c95ea2..62f27610dd33 100644 --- a/drivers/platform/chrome/wilco_ec/properties.c +++ b/drivers/platform/chrome/wilco_ec/properties.c @@ -5,7 +5,7 @@ #include <linux/platform_data/wilco-ec.h> #include <linux/string.h> -#include <linux/unaligned/le_memmove.h> +#include <asm/unaligned.h> /* Operation code; what the EC should do with the property */ enum ec_property_op { diff --git a/drivers/s390/scsi/zfcp_fsf.h b/drivers/s390/scsi/zfcp_fsf.h index 2b1e4da1944f..4bfb79f20588 100644 --- a/drivers/s390/scsi/zfcp_fsf.h +++ b/drivers/s390/scsi/zfcp_fsf.h @@ -410,7 +410,7 @@ struct fsf_qtcb_bottom_port { u8 cb_util; u8 a_util; u8 res2; - u16 temperature; + s16 temperature; u16 vcc; u16 tx_bias; u16 tx_power; diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c index 494b9fe9cc94..a711a0d15100 100644 --- a/drivers/s390/scsi/zfcp_sysfs.c +++ b/drivers/s390/scsi/zfcp_sysfs.c @@ -800,7 +800,7 @@ static ZFCP_DEV_ATTR(adapter_diag, b2b_credit, 0400, static ZFCP_DEV_ATTR(adapter_diag_sfp, _name, 0400, \ zfcp_sysfs_adapter_diag_sfp_##_name##_show, NULL) -ZFCP_DEFINE_DIAG_SFP_ATTR(temperature, temperature, 5, "%hu"); +ZFCP_DEFINE_DIAG_SFP_ATTR(temperature, temperature, 6, "%hd"); ZFCP_DEFINE_DIAG_SFP_ATTR(vcc, vcc, 5, "%hu"); ZFCP_DEFINE_DIAG_SFP_ATTR(tx_bias, tx_bias, 5, "%hu"); ZFCP_DEFINE_DIAG_SFP_ATTR(tx_power, tx_power, 5, "%hu"); diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c index 9c5f7c9178c6..2b865c6423e2 100644 --- a/drivers/scsi/libfc/fc_disc.c +++ b/drivers/scsi/libfc/fc_disc.c @@ -628,6 +628,8 @@ redisc: } out: kref_put(&rdata->kref, fc_rport_destroy); + if (!IS_ERR(fp)) + fc_frame_free(fp); } /** diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index e4282bce5834..f45c22b09726 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -161,6 +161,7 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data) { struct scsi_disk *sdkp = scsi_disk(disk); + sector_t capacity = logical_to_sectors(sdkp->device, sdkp->capacity); unsigned int nr, i; unsigned char *buf; size_t offset, buflen = 0; @@ -171,11 +172,15 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, /* Not a zoned device */ return -EOPNOTSUPP; + if (!capacity) + /* Device gone or invalid */ + return -ENODEV; + buf = sd_zbc_alloc_report_buffer(sdkp, nr_zones, &buflen); if (!buf) return -ENOMEM; - while (zone_idx < nr_zones && sector < get_capacity(disk)) { + while (zone_idx < nr_zones && sector < capacity) { ret = sd_zbc_do_report_zones(sdkp, buf, buflen, sectors_to_logical(sdkp->device, sector), true); if (ret) diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 0fbb8fe6e521..e4240e4ae8bb 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -688,7 +688,7 @@ static const struct block_device_operations sr_bdops = .release = sr_block_release, .ioctl = sr_block_ioctl, #ifdef CONFIG_COMPAT - .ioctl = sr_block_compat_ioctl, + .compat_ioctl = sr_block_compat_ioctl, #endif .check_events = sr_block_check_events, .revalidate_disk = sr_block_revalidate_disk, diff --git a/drivers/tee/amdtee/Kconfig b/drivers/tee/amdtee/Kconfig index 4e32b6413b41..191f9715fa9a 100644 --- a/drivers/tee/amdtee/Kconfig +++ b/drivers/tee/amdtee/Kconfig @@ -3,6 +3,6 @@ config AMDTEE tristate "AMD-TEE" default m - depends on CRYPTO_DEV_SP_PSP + depends on CRYPTO_DEV_SP_PSP && CRYPTO_DEV_CCP_DD help This implements AMD's Trusted Execution Environment (TEE) driver. diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index e158159671fa..18e205eeb9af 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1414,10 +1414,6 @@ static int vhost_net_release(struct inode *inode, struct file *f) static struct socket *get_raw_socket(int fd) { - struct { - struct sockaddr_ll sa; - char buf[MAX_ADDR_LEN]; - } uaddr; int r; struct socket *sock = sockfd_lookup(fd, &r); @@ -1430,11 +1426,7 @@ static struct socket *get_raw_socket(int fd) goto err; } - r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, 0); - if (r < 0) - goto err; - - if (uaddr.sa.sll_family != AF_PACKET) { + if (sock->sk->sk_family != AF_PACKET) { r = -EPFNOSUPPORT; goto err; } diff --git a/drivers/watchdog/wdat_wdt.c b/drivers/watchdog/wdat_wdt.c index b069349b52f5..3065dd670a18 100644 --- a/drivers/watchdog/wdat_wdt.c +++ b/drivers/watchdog/wdat_wdt.c @@ -54,6 +54,13 @@ module_param(nowayout, bool, 0); MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); +#define WDAT_DEFAULT_TIMEOUT 30 + +static int timeout = WDAT_DEFAULT_TIMEOUT; +module_param(timeout, int, 0); +MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds (default=" + __MODULE_STRING(WDAT_DEFAULT_TIMEOUT) ")"); + static int wdat_wdt_read(struct wdat_wdt *wdat, const struct wdat_instruction *instr, u32 *value) { @@ -389,7 +396,7 @@ static int wdat_wdt_probe(struct platform_device *pdev) memset(&r, 0, sizeof(r)); r.start = gas->address; - r.end = r.start + gas->access_width - 1; + r.end = r.start + ACPI_ACCESS_BYTE_WIDTH(gas->access_width) - 1; if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { r.flags = IORESOURCE_MEM; } else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { @@ -438,6 +445,22 @@ static int wdat_wdt_probe(struct platform_device *pdev) platform_set_drvdata(pdev, wdat); + /* + * Set initial timeout so that userspace has time to configure the + * watchdog properly after it has opened the device. In some cases + * the BIOS default is too short and causes immediate reboot. + */ + if (timeout * 1000 < wdat->wdd.min_hw_heartbeat_ms || + timeout * 1000 > wdat->wdd.max_hw_heartbeat_ms) { + dev_warn(dev, "Invalid timeout %d given, using %d\n", + timeout, WDAT_DEFAULT_TIMEOUT); + timeout = WDAT_DEFAULT_TIMEOUT; + } + + ret = wdat_wdt_set_timeout(&wdat->wdd, timeout); + if (ret) + return ret; + watchdog_set_nowayout(&wdat->wdd, nowayout); return devm_watchdog_register_device(dev, &wdat->wdd); } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ff1b764b0c0e..0c7c4adb664e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2391,7 +2391,7 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct flex_groups **old_groups, **new_groups; - int size, i; + int size, i, j; if (!sbi->s_log_groups_per_flex) return 0; @@ -2412,8 +2412,8 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) sizeof(struct flex_groups)), GFP_KERNEL); if (!new_groups[i]) { - for (i--; i >= sbi->s_flex_groups_allocated; i--) - kvfree(new_groups[i]); + for (j = sbi->s_flex_groups_allocated; j < i; j++) + kvfree(new_groups[j]); kvfree(new_groups); ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", size); diff --git a/fs/io-wq.c b/fs/io-wq.c index 0a5ab1a8f69a..bf8ed1b0b90a 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -535,42 +535,23 @@ next: } while (1); } -static inline void io_worker_spin_for_work(struct io_wqe *wqe) -{ - int i = 0; - - while (++i < 1000) { - if (io_wqe_run_queue(wqe)) - break; - if (need_resched()) - break; - cpu_relax(); - } -} - static int io_wqe_worker(void *data) { struct io_worker *worker = data; struct io_wqe *wqe = worker->wqe; struct io_wq *wq = wqe->wq; - bool did_work; io_worker_start(wqe, worker); - did_work = false; while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { set_current_state(TASK_INTERRUPTIBLE); loop: - if (did_work) - io_worker_spin_for_work(wqe); spin_lock_irq(&wqe->lock); if (io_wqe_run_queue(wqe)) { __set_current_state(TASK_RUNNING); io_worker_handle_work(worker); - did_work = true; goto loop; } - did_work = false; /* drops the lock on success, retry */ if (__io_worker_idle(wqe, worker)) { __release(&wqe->lock); diff --git a/fs/io-wq.h b/fs/io-wq.h index ccc7d84af57d..33baba4370c5 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -79,16 +79,10 @@ struct io_wq_work { pid_t task_pid; }; -#define INIT_IO_WORK(work, _func) \ - do { \ - (work)->list.next = NULL; \ - (work)->func = _func; \ - (work)->files = NULL; \ - (work)->mm = NULL; \ - (work)->creds = NULL; \ - (work)->fs = NULL; \ - (work)->flags = 0; \ - } while (0) \ +#define INIT_IO_WORK(work, _func) \ + do { \ + *(work) = (struct io_wq_work){ .func = _func }; \ + } while (0) \ typedef void (get_work_fn)(struct io_wq_work *); typedef void (put_work_fn)(struct io_wq_work *); diff --git a/fs/io_uring.c b/fs/io_uring.c index de650df9ac53..6a595c13e108 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -183,17 +183,12 @@ struct fixed_file_table { struct file **files; }; -enum { - FFD_F_ATOMIC, -}; - struct fixed_file_data { struct fixed_file_table *table; struct io_ring_ctx *ctx; struct percpu_ref refs; struct llist_head put_llist; - unsigned long state; struct work_struct ref_work; struct completion done; }; @@ -1483,10 +1478,10 @@ static void io_free_req(struct io_kiocb *req) __attribute__((nonnull)) static void io_put_req_find_next(struct io_kiocb *req, struct io_kiocb **nxtptr) { - io_req_find_next(req, nxtptr); - - if (refcount_dec_and_test(&req->refs)) + if (refcount_dec_and_test(&req->refs)) { + io_req_find_next(req, nxtptr); __io_free_req(req); + } } static void io_put_req(struct io_kiocb *req) @@ -1821,6 +1816,10 @@ static void io_iopoll_req_issued(struct io_kiocb *req) list_add(&req->list, &ctx->poll_list); else list_add_tail(&req->list, &ctx->poll_list); + + if ((ctx->flags & IORING_SETUP_SQPOLL) && + wq_has_sleeper(&ctx->sqo_wait)) + wake_up(&ctx->sqo_wait); } static void io_file_put(struct io_submit_state *state) @@ -2071,7 +2070,7 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, ssize_t ret; ret = import_single_range(rw, buf, sqe_len, *iovec, iter); *iovec = NULL; - return ret; + return ret < 0 ? ret : sqe_len; } if (req->io) { @@ -3002,6 +3001,11 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + if (!io || req->opcode == IORING_OP_SEND) return 0; /* iovec is already imported */ @@ -3154,6 +3158,11 @@ static int io_recvmsg_prep(struct io_kiocb *req, sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + if (!io || req->opcode == IORING_OP_RECV) return 0; /* iovec is already imported */ @@ -4705,11 +4714,21 @@ static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_kiocb *linked_timeout; struct io_kiocb *nxt = NULL; + const struct cred *old_creds = NULL; int ret; again: linked_timeout = io_prep_linked_timeout(req); + if (req->work.creds && req->work.creds != current_cred()) { + if (old_creds) + revert_creds(old_creds); + if (old_creds == req->work.creds) + old_creds = NULL; /* restored original creds */ + else + old_creds = override_creds(req->work.creds); + } + ret = io_issue_sqe(req, sqe, &nxt, true); /* @@ -4735,7 +4754,7 @@ punt: err: /* drop submission reference */ - io_put_req(req); + io_put_req_find_next(req, &nxt); if (linked_timeout) { if (!ret) @@ -4759,6 +4778,8 @@ done_req: goto punt; goto again; } + if (old_creds) + revert_creds(old_creds); } static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe) @@ -4803,7 +4824,6 @@ static inline void io_queue_link_head(struct io_kiocb *req) static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, struct io_submit_state *state, struct io_kiocb **link) { - const struct cred *old_creds = NULL; struct io_ring_ctx *ctx = req->ctx; unsigned int sqe_flags; int ret, id; @@ -4818,14 +4838,12 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, id = READ_ONCE(sqe->personality); if (id) { - const struct cred *personality_creds; - - personality_creds = idr_find(&ctx->personality_idr, id); - if (unlikely(!personality_creds)) { + req->work.creds = idr_find(&ctx->personality_idr, id); + if (unlikely(!req->work.creds)) { ret = -EINVAL; goto err_req; } - old_creds = override_creds(personality_creds); + get_cred(req->work.creds); } /* same numerical values with corresponding REQ_F_*, safe to copy */ @@ -4837,8 +4855,6 @@ static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, err_req: io_cqring_add_event(req, ret); io_double_put_req(req); - if (old_creds) - revert_creds(old_creds); return false; } @@ -4899,8 +4915,6 @@ err_req: } } - if (old_creds) - revert_creds(old_creds); return true; } @@ -5081,9 +5095,8 @@ static int io_sq_thread(void *data) const struct cred *old_cred; mm_segment_t old_fs; DEFINE_WAIT(wait); - unsigned inflight; unsigned long timeout; - int ret; + int ret = 0; complete(&ctx->completions[1]); @@ -5091,39 +5104,19 @@ static int io_sq_thread(void *data) set_fs(USER_DS); old_cred = override_creds(ctx->creds); - ret = timeout = inflight = 0; + timeout = jiffies + ctx->sq_thread_idle; while (!kthread_should_park()) { unsigned int to_submit; - if (inflight) { + if (!list_empty(&ctx->poll_list)) { unsigned nr_events = 0; - if (ctx->flags & IORING_SETUP_IOPOLL) { - /* - * inflight is the count of the maximum possible - * entries we submitted, but it can be smaller - * if we dropped some of them. If we don't have - * poll entries available, then we know that we - * have nothing left to poll for. Reset the - * inflight count to zero in that case. - */ - mutex_lock(&ctx->uring_lock); - if (!list_empty(&ctx->poll_list)) - io_iopoll_getevents(ctx, &nr_events, 0); - else - inflight = 0; - mutex_unlock(&ctx->uring_lock); - } else { - /* - * Normal IO, just pretend everything completed. - * We don't have to poll completions for that. - */ - nr_events = inflight; - } - - inflight -= nr_events; - if (!inflight) + mutex_lock(&ctx->uring_lock); + if (!list_empty(&ctx->poll_list)) + io_iopoll_getevents(ctx, &nr_events, 0); + else timeout = jiffies + ctx->sq_thread_idle; + mutex_unlock(&ctx->uring_lock); } to_submit = io_sqring_entries(ctx); @@ -5152,7 +5145,7 @@ static int io_sq_thread(void *data) * more IO, we should wait for the application to * reap events and wake us up. */ - if (inflight || + if (!list_empty(&ctx->poll_list) || (!time_after(jiffies, timeout) && ret != -EBUSY && !percpu_ref_is_dying(&ctx->refs))) { cond_resched(); @@ -5162,6 +5155,19 @@ static int io_sq_thread(void *data) prepare_to_wait(&ctx->sqo_wait, &wait, TASK_INTERRUPTIBLE); + /* + * While doing polled IO, before going to sleep, we need + * to check if there are new reqs added to poll_list, it + * is because reqs may have been punted to io worker and + * will be added to poll_list later, hence check the + * poll_list again. + */ + if ((ctx->flags & IORING_SETUP_IOPOLL) && + !list_empty_careful(&ctx->poll_list)) { + finish_wait(&ctx->sqo_wait, &wait); + continue; + } + /* Tell userspace we may need a wakeup call */ ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP; /* make sure to read SQ tail after writing flags */ @@ -5189,8 +5195,7 @@ static int io_sq_thread(void *data) mutex_lock(&ctx->uring_lock); ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true); mutex_unlock(&ctx->uring_lock); - if (ret > 0) - inflight += ret; + timeout = jiffies + ctx->sq_thread_idle; } set_fs(old_fs); @@ -5595,7 +5600,6 @@ static void io_ring_file_ref_switch(struct work_struct *work) data = container_of(work, struct fixed_file_data, ref_work); io_ring_file_ref_flush(data); - percpu_ref_get(&data->refs); percpu_ref_switch_to_percpu(&data->refs); } @@ -5771,8 +5775,13 @@ static void io_atomic_switch(struct percpu_ref *ref) { struct fixed_file_data *data; + /* + * Juggle reference to ensure we hit zero, if needed, so we can + * switch back to percpu mode + */ data = container_of(ref, struct fixed_file_data, refs); - clear_bit(FFD_F_ATOMIC, &data->state); + percpu_ref_put(&data->refs); + percpu_ref_get(&data->refs); } static bool io_queue_file_removal(struct fixed_file_data *data, @@ -5795,11 +5804,7 @@ static bool io_queue_file_removal(struct fixed_file_data *data, llist_add(&pfile->llist, &data->put_llist); if (pfile == &pfile_stack) { - if (!test_and_set_bit(FFD_F_ATOMIC, &data->state)) { - percpu_ref_put(&data->refs); - percpu_ref_switch_to_atomic(&data->refs, - io_atomic_switch); - } + percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch); wait_for_completion(&done); flush_work(&data->ref_work); return false; @@ -5873,10 +5878,8 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, up->offset++; } - if (ref_switch && !test_and_set_bit(FFD_F_ATOMIC, &data->state)) { - percpu_ref_put(&data->refs); + if (ref_switch) percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch); - } return done ? done : err; } @@ -6334,6 +6337,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) io_sqe_buffer_unregister(ctx); io_sqe_files_unregister(ctx); io_eventfd_unregister(ctx); + idr_destroy(&ctx->personality_idr); #if defined(CONFIG_UNIX) if (ctx->ring_sock) { @@ -6647,6 +6651,7 @@ out_fput: return submitted ? submitted : ret; } +#ifdef CONFIG_PROC_FS static int io_uring_show_cred(int id, void *p, void *data) { const struct cred *cred = p; @@ -6720,6 +6725,7 @@ static void io_uring_show_fdinfo(struct seq_file *m, struct file *f) percpu_ref_put(&ctx->refs); } } +#endif static const struct file_operations io_uring_fops = { .release = io_uring_release, @@ -6731,7 +6737,9 @@ static const struct file_operations io_uring_fops = { #endif .poll = io_uring_poll, .fasync = io_uring_fasync, +#ifdef CONFIG_PROC_FS .show_fdinfo = io_uring_show_fdinfo, +#endif }; static int io_allocate_scq_urings(struct io_ring_ctx *ctx, diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index d181948c0390..3dccc23cf010 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1150,8 +1150,8 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh, /* For undo access buffer must have data copied */ if (undo && !jh->b_committed_data) goto out; - if (jh->b_transaction != handle->h_transaction && - jh->b_next_transaction != handle->h_transaction) + if (READ_ONCE(jh->b_transaction) != handle->h_transaction && + READ_ONCE(jh->b_next_transaction) != handle->h_transaction) goto out; /* * There are two reasons for the barrier here: @@ -2569,8 +2569,8 @@ bool __jbd2_journal_refile_buffer(struct journal_head *jh) * our jh reference and thus __jbd2_journal_file_buffer() must not * take a new one. */ - jh->b_transaction = jh->b_next_transaction; - jh->b_next_transaction = NULL; + WRITE_ONCE(jh->b_transaction, jh->b_next_transaction); + WRITE_ONCE(jh->b_next_transaction, NULL); if (buffer_freed(bh)) jlist = BJ_Forget; else if (jh->b_modified) diff --git a/fs/zonefs/Kconfig b/fs/zonefs/Kconfig index fb87ad372e29..ef2697b78820 100644 --- a/fs/zonefs/Kconfig +++ b/fs/zonefs/Kconfig @@ -2,6 +2,7 @@ config ZONEFS_FS tristate "zonefs filesystem support" depends on BLOCK depends on BLK_DEV_ZONED + select FS_IOMAP help zonefs is a simple file system which exposes zones of a zoned block device (e.g. host-managed or host-aware SMR disk drives) as files. diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 8bc6ef82d693..69aee3dfb660 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -601,13 +601,13 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ssize_t ret; /* - * For async direct IOs to sequential zone files, ignore IOCB_NOWAIT + * For async direct IOs to sequential zone files, refuse IOCB_NOWAIT * as this can cause write reordering (e.g. the first aio gets EAGAIN * on the inode lock but the second goes through but is now unaligned). */ - if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !is_sync_kiocb(iocb) - && (iocb->ki_flags & IOCB_NOWAIT)) - iocb->ki_flags &= ~IOCB_NOWAIT; + if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !is_sync_kiocb(iocb) && + (iocb->ki_flags & IOCB_NOWAIT)) + return -EOPNOTSUPP; if (iocb->ki_flags & IOCB_NOWAIT) { if (!inode_trylock(inode)) diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index a2583c2bc054..4defed58ea33 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -532,11 +532,12 @@ typedef u64 acpi_integer; strnlen (a, ACPI_NAMESEG_SIZE) == ACPI_NAMESEG_SIZE) /* - * Algorithm to obtain access bit width. + * Algorithm to obtain access bit or byte width. * Can be used with access_width of struct acpi_generic_address and access_size of * struct acpi_resource_generic_register. */ #define ACPI_ACCESS_BIT_WIDTH(size) (1 << ((size) + 2)) +#define ACPI_ACCESS_BYTE_WIDTH(size) (1 << ((size) - 1)) /******************************************************************************* * diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 053ea4b51988..10455b2bbbb4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -524,7 +524,7 @@ struct request_queue { unsigned int sg_reserved_size; int node; #ifdef CONFIG_BLK_DEV_IO_TRACE - struct blk_trace *blk_trace; + struct blk_trace __rcu *blk_trace; struct mutex blk_trace_mutex; #endif /* diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7bb2d8de9f30..3b6ff5902edc 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -51,9 +51,13 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f **/ #define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ do { \ - struct blk_trace *bt = (q)->blk_trace; \ + struct blk_trace *bt; \ + \ + rcu_read_lock(); \ + bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__) @@ -61,10 +65,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f static inline bool blk_trace_note_message_enabled(struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; - if (likely(!bt)) - return false; - return bt->act_mask & BLK_TC_NOTIFY; + struct blk_trace *bt; + bool ret; + + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + ret = bt && (bt->act_mask & BLK_TC_NOTIFY); + rcu_read_unlock(); + return ret; } extern void blk_add_driver_data(struct request_queue *q, struct request *rq, diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 7e18c939663e..d11e183fcb54 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -10,6 +10,9 @@ #include <linux/kernel.h> #include <linux/types.h> +#define BOOTCONFIG_MAGIC "#BOOTCONFIG\n" +#define BOOTCONFIG_MAGIC_LEN 12 + /* XBC tree node */ struct xbc_node { u16 next; diff --git a/include/linux/hid.h b/include/linux/hid.h index cd41f209043f..875f71132b14 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -492,7 +492,7 @@ struct hid_report_enum { }; #define HID_MIN_BUFFER_SIZE 64 /* make sure there is at least a packet size of space */ -#define HID_MAX_BUFFER_SIZE 4096 /* 4kb */ +#define HID_MAX_BUFFER_SIZE 8192 /* 8kb */ #define HID_CONTROL_FIFO_SIZE 256 /* to init devices with >100 reports */ #define HID_OUTPUT_FIFO_SIZE 64 diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 93338fd54af8..33d379602314 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -22,19 +22,23 @@ extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); +#if IS_ENABLED(CONFIG_NF_NAT) +void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); +#else +#define icmpv6_ndo_send icmpv6_send +#endif + #else static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { - } -#endif -#if IS_ENABLED(CONFIG_NF_NAT) -void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); -#else -#define icmpv6_ndo_send icmpv6_send +static inline void icmpv6_ndo_send(struct sk_buff *skb, + u8 type, u8 code, __u32 info) +{ +} #endif extern int icmpv6_init(void); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e89eb67356cb..bcb9b2ac0791 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -889,6 +889,8 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); +int kvm_arch_post_init_vm(struct kvm *kvm); +void kvm_arch_pre_destroy_vm(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* @@ -1342,7 +1344,7 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ struct kvm_vcpu *kvm_get_running_vcpu(void); -struct kvm_vcpu __percpu **kvm_get_running_vcpus(void); +struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS bool kvm_arch_has_irq_bypass(void); diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 908d38dbcb91..5448c8b443db 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -121,6 +121,7 @@ struct ip_set_ext { u32 timeout; u8 packets_op; u8 bytes_op; + bool target; }; struct ip_set; @@ -187,6 +188,14 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Region-locking is used */ + bool region_lock; +}; + +struct ip_set_region { + spinlock_t lock; /* Region lock */ + size_t ext_size; /* Size of the dynamic extensions */ + u32 elements; /* Number of elements vs timeout */ }; /* The core set type structure */ @@ -501,7 +510,7 @@ ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, } #define IP_SET_INIT_KEXT(skb, opt, set) \ - { .bytes = (skb)->len, .packets = 1, \ + { .bytes = (skb)->len, .packets = 1, .target = true,\ .timeout = ip_set_adt_opt_timeout(opt, set) } #define IP_SET_INIT_UEXT(set) \ diff --git a/init/Kconfig b/init/Kconfig index 452bc1835cd4..20a6ac33761c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1226,13 +1226,12 @@ endif config BOOT_CONFIG bool "Boot config support" - depends on BLK_DEV_INITRD - default y + select BLK_DEV_INITRD help Extra boot config allows system admin to pass a config file as complemental extension of kernel cmdline when booting. The boot config file must be attached at the end of initramfs - with checksum and size. + with checksum, size and magic word. See <file:Documentation/admin-guide/bootconfig.rst> for details. If unsure, say Y. diff --git a/init/main.c b/init/main.c index f95b014a5479..ee4947af823f 100644 --- a/init/main.c +++ b/init/main.c @@ -268,7 +268,6 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size, { struct xbc_node *knode, *vnode; char *end = buf + size; - char c = '\"'; const char *val; int ret; @@ -279,25 +278,20 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size, return ret; vnode = xbc_node_get_child(knode); - ret = snprintf(buf, rest(buf, end), "%s%c", xbc_namebuf, - vnode ? '=' : ' '); - if (ret < 0) - return ret; - buf += ret; - if (!vnode) + if (!vnode) { + ret = snprintf(buf, rest(buf, end), "%s ", xbc_namebuf); + if (ret < 0) + return ret; + buf += ret; continue; - - c = '\"'; + } xbc_array_for_each_value(vnode, val) { - ret = snprintf(buf, rest(buf, end), "%c%s", c, val); + ret = snprintf(buf, rest(buf, end), "%s=\"%s\" ", + xbc_namebuf, val); if (ret < 0) return ret; buf += ret; - c = ','; } - if (rest(buf, end) > 2) - strcpy(buf, "\" "); - buf += 2; } return buf - (end - size); @@ -335,7 +329,7 @@ static char * __init xbc_make_cmdline(const char *key) return new_cmdline; } -u32 boot_config_checksum(unsigned char *p, u32 size) +static u32 boot_config_checksum(unsigned char *p, u32 size) { u32 ret = 0; @@ -374,7 +368,11 @@ static void __init setup_boot_config(const char *cmdline) if (!initrd_end) goto not_found; - hdr = (u32 *)(initrd_end - 8); + data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; + if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) + goto not_found; + + hdr = (u32 *)(data - 8); size = hdr[0]; csum = hdr[1]; @@ -418,6 +416,14 @@ not_found: } #else #define setup_boot_config(cmdline) do { } while (0) + +static int __init warn_bootconfig(char *str) +{ + pr_warn("WARNING: 'bootconfig' found on the kernel command line but CONFIG_BOOTCONFIG is not set.\n"); + return 0; +} +early_param("bootconfig", warn_bootconfig); + #endif /* Change NUL term back to "=", to make "param" the whole string. */ diff --git a/kernel/audit.c b/kernel/audit.c index 17b0d523afb3..9ddfe2aa6671 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1101,13 +1101,11 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature audit_log_end(ab); } -static int audit_set_feature(struct sk_buff *skb) +static int audit_set_feature(struct audit_features *uaf) { - struct audit_features *uaf; int i; BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names)); - uaf = nlmsg_data(nlmsg_hdr(skb)); /* if there is ever a version 2 we should handle that here */ @@ -1175,6 +1173,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { u32 seq; void *data; + int data_len; int err; struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; @@ -1188,6 +1187,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) seq = nlh->nlmsg_seq; data = nlmsg_data(nlh); + data_len = nlmsg_len(nlh); switch (msg_type) { case AUDIT_GET: { @@ -1211,7 +1211,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) struct audit_status s; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); if (s.mask & AUDIT_STATUS_ENABLED) { err = audit_set_enabled(s.enabled); if (err < 0) @@ -1315,7 +1315,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return err; break; case AUDIT_SET_FEATURE: - err = audit_set_feature(skb); + if (data_len < sizeof(struct audit_features)) + return -EINVAL; + err = audit_set_feature(data); if (err) return err; break; @@ -1327,6 +1329,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ + char *str = data; + err = 0; if (msg_type == AUDIT_USER_TTY) { err = tty_audit_push(); @@ -1334,26 +1338,24 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) break; } audit_log_user_recv_msg(&ab, msg_type); - if (msg_type != AUDIT_USER_TTY) + if (msg_type != AUDIT_USER_TTY) { + /* ensure NULL termination */ + str[data_len - 1] = '\0'; audit_log_format(ab, " msg='%.*s'", AUDIT_MESSAGE_TEXT_MAX, - (char *)data); - else { - int size; - + str); + } else { audit_log_format(ab, " data="); - size = nlmsg_len(nlh); - if (size > 0 && - ((unsigned char *)data)[size - 1] == '\0') - size--; - audit_log_n_untrustedstring(ab, data, size); + if (data_len > 0 && str[data_len - 1] == '\0') + data_len--; + audit_log_n_untrustedstring(ab, str, data_len); } audit_log_end(ab); } break; case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: - if (nlmsg_len(nlh) < sizeof(struct audit_rule_data)) + if (data_len < sizeof(struct audit_rule_data)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { audit_log_common_recv_msg(audit_context(), &ab, @@ -1365,7 +1367,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) audit_log_end(ab); return -EPERM; } - err = audit_rule_change(msg_type, seq, data, nlmsg_len(nlh)); + err = audit_rule_change(msg_type, seq, data, data_len); break; case AUDIT_LIST_RULES: err = audit_list_rules_send(skb, seq); @@ -1380,7 +1382,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) case AUDIT_MAKE_EQUIV: { void *bufp = data; u32 sizes[2]; - size_t msglen = nlmsg_len(nlh); + size_t msglen = data_len; char *old, *new; err = -EINVAL; @@ -1456,7 +1458,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); /* check if new data is valid */ if ((s.enabled != 0 && s.enabled != 1) || (s.log_passwd != 0 && s.log_passwd != 1)) diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index b0126e9c0743..026e34da4ace 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -456,6 +456,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; + u32 f_val; err = -EINVAL; @@ -464,12 +465,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, goto exit_free; f->type = data->fields[i]; - f->val = data->values[i]; + f_val = data->values[i]; /* Support legacy tests for a valid loginuid */ - if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) { + if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; - f->val = 0; + f_val = 0; entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } @@ -485,7 +486,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_OBJ_UID: - f->uid = make_kuid(current_user_ns(), f->val); + f->uid = make_kuid(current_user_ns(), f_val); if (!uid_valid(f->uid)) goto exit_free; break; @@ -494,11 +495,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: - f->gid = make_kgid(current_user_ns(), f->val); + f->gid = make_kgid(current_user_ns(), f_val); if (!gid_valid(f->gid)) goto exit_free; break; case AUDIT_ARCH: + f->val = f_val; entry->rule.arch_f = f; break; case AUDIT_SUBJ_USER: @@ -511,11 +513,13 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } + entry->rule.buflen += f_val; + f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, (void **)&f->lsm_rule); /* Keep currently invalid fields around in case they @@ -524,68 +528,71 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, pr_warn("audit rule for LSM \'%s\' is invalid\n", str); err = 0; - } - if (err) { - kfree(str); + } else if (err) goto exit_free; - } else - f->lsm_str = str; break; case AUDIT_WATCH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - - err = audit_to_watch(&entry->rule, str, f->val, f->op); + } + err = audit_to_watch(&entry->rule, str, f_val, f->op); if (err) { kfree(str); goto exit_free; } + entry->rule.buflen += f_val; break; case AUDIT_DIR: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } err = audit_make_tree(&entry->rule, str, f->op); kfree(str); if (err) goto exit_free; + entry->rule.buflen += f_val; break; case AUDIT_INODE: + f->val = f_val; err = audit_to_inode(&entry->rule, f); if (err) goto exit_free; break; case AUDIT_FILTERKEY: - if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN) + if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; + } + entry->rule.buflen += f_val; entry->rule.filterkey = str; break; case AUDIT_EXE: - if (entry->rule.exe || f->val > PATH_MAX) + if (entry->rule.exe || f_val > PATH_MAX) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); + str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } - entry->rule.buflen += f->val; - - audit_mark = audit_alloc_mark(&entry->rule, str, f->val); + audit_mark = audit_alloc_mark(&entry->rule, str, f_val); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); goto exit_free; } + entry->rule.buflen += f_val; entry->rule.exe = audit_mark; break; + default: + f->val = f_val; + break; } } diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index ddade80ad276..d82b7b88d616 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1681,7 +1681,7 @@ static unsigned long minimum_image_size(unsigned long saveable) * hibernation for allocations made while saving the image and for device * drivers, in case they need to allocate memory from their hibernation * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough - * estimate) and reserverd_size divided by PAGE_SIZE (which is tunable through + * estimate) and reserved_size divided by PAGE_SIZE (which is tunable through * /sys/power/reserved_size, respectively). To make this happen, we compute the * total number of available page frames and allocate at least * diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3c8a379c357e..c1217bfe5e81 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8337,6 +8337,8 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd, sgs->group_capacity = group->sgc->capacity; + sgs->group_weight = group->group_weight; + sgs->group_type = group_classify(sd->imbalance_pct, group, sgs); /* diff --git a/kernel/signal.c b/kernel/signal.c index 9ad8dea93dbb..5b2396350dd1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -413,27 +413,32 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi { struct sigqueue *q = NULL; struct user_struct *user; + int sigpending; /* * Protect access to @t credentials. This can go away when all * callers hold rcu read lock. + * + * NOTE! A pending signal will hold on to the user refcount, + * and we get/put the refcount only when the sigpending count + * changes from/to zero. */ rcu_read_lock(); - user = get_uid(__task_cred(t)->user); - atomic_inc(&user->sigpending); + user = __task_cred(t)->user; + sigpending = atomic_inc_return(&user->sigpending); + if (sigpending == 1) + get_uid(user); rcu_read_unlock(); - if (override_rlimit || - atomic_read(&user->sigpending) <= - task_rlimit(t, RLIMIT_SIGPENDING)) { + if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); } if (unlikely(q == NULL)) { - atomic_dec(&user->sigpending); - free_uid(user); + if (atomic_dec_and_test(&user->sigpending)) + free_uid(user); } else { INIT_LIST_HEAD(&q->list); q->flags = 0; @@ -447,8 +452,8 @@ static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) return; - atomic_dec(&q->user->sigpending); - free_uid(q->user); + if (atomic_dec_and_test(&q->user->sigpending)) + free_uid(q->user); kmem_cache_free(sigqueue_cachep, q); } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 91e885194dbc..402eef84c859 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -143,8 +143,8 @@ if FTRACE config BOOTTIME_TRACING bool "Boot-time Tracing support" - depends on BOOT_CONFIG && TRACING - default y + depends on TRACING + select BOOT_CONFIG help Enable developer to setup ftrace subsystem via supplemental kernel cmdline at boot time for debugging (tracing) driver diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 0735ae8545d8..4560878f0bac 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -335,6 +335,7 @@ static void put_probe_ref(void) static void blk_trace_cleanup(struct blk_trace *bt) { + synchronize_rcu(); blk_trace_free(bt); put_probe_ref(); } @@ -629,8 +630,10 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name, static int __blk_trace_startstop(struct request_queue *q, int start) { int ret; - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (bt == NULL) return -EINVAL; @@ -740,8 +743,8 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) void blk_trace_shutdown(struct request_queue *q) { mutex_lock(&q->blk_trace_mutex); - - if (q->blk_trace) { + if (rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } @@ -752,8 +755,10 @@ void blk_trace_shutdown(struct request_queue *q) #ifdef CONFIG_BLK_CGROUP static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + /* We don't use the 'bt' value here except as an optimization... */ + bt = rcu_dereference_protected(q->blk_trace, 1); if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return 0; @@ -796,10 +801,14 @@ blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) static void blk_add_trace_rq(struct request *rq, int error, unsigned int nr_bytes, u32 what, u64 cgid) { - struct blk_trace *bt = rq->q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(rq->q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } if (blk_rq_is_passthrough(rq)) what |= BLK_TC_ACT(BLK_TC_PC); @@ -808,6 +817,7 @@ static void blk_add_trace_rq(struct request *rq, int error, __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq), rq->cmd_flags, what, error, 0, NULL, cgid); + rcu_read_unlock(); } static void blk_add_trace_rq_insert(void *ignore, @@ -853,14 +863,19 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq, static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, u32 what, int error) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, what, error, 0, NULL, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); } static void blk_add_trace_bio_bounce(void *ignore, @@ -905,11 +920,14 @@ static void blk_add_trace_getrq(void *ignore, if (bio) blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, NULL, 0); + rcu_read_unlock(); } } @@ -921,27 +939,35 @@ static void blk_add_trace_sleeprq(void *ignore, if (bio) blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, 0, 0, NULL, 0); + rcu_read_unlock(); } } static void blk_add_trace_plug(void *ignore, struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0); + rcu_read_unlock(); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, unsigned int depth, bool explicit) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(depth); u32 what; @@ -953,14 +979,17 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0); } + rcu_read_unlock(); } static void blk_add_trace_split(void *ignore, struct request_queue *q, struct bio *bio, unsigned int pdu) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(pdu); @@ -969,6 +998,7 @@ static void blk_add_trace_split(void *ignore, BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), &rpdu, blk_trace_bio_get_cgid(q, bio)); } + rcu_read_unlock(); } /** @@ -988,11 +1018,15 @@ static void blk_add_trace_bio_remap(void *ignore, struct request_queue *q, struct bio *bio, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(bio_dev(bio)); @@ -1001,6 +1035,7 @@ static void blk_add_trace_bio_remap(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); } /** @@ -1021,11 +1056,15 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); @@ -1034,6 +1073,7 @@ static void blk_add_trace_rq_remap(void *ignore, __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, sizeof(r), &r, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } /** @@ -1051,14 +1091,19 @@ void blk_add_driver_data(struct request_queue *q, struct request *rq, void *data, size_t len) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, 0, len, data, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data); @@ -1597,6 +1642,7 @@ static int blk_trace_remove_queue(struct request_queue *q) return -EINVAL; put_probe_ref(); + synchronize_rcu(); blk_trace_free(bt); return 0; } @@ -1758,6 +1804,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct hd_struct *p = dev_to_part(dev); struct request_queue *q; struct block_device *bdev; + struct blk_trace *bt; ssize_t ret = -ENXIO; bdev = bdget(part_devt(p)); @@ -1770,21 +1817,23 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - ret = sprintf(buf, "%u\n", !!q->blk_trace); + ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; } - if (q->blk_trace == NULL) + if (bt == NULL) ret = sprintf(buf, "disabled\n"); else if (attr == &dev_attr_act_mask) - ret = blk_trace_mask2str(buf, q->blk_trace->act_mask); + ret = blk_trace_mask2str(buf, bt->act_mask); else if (attr == &dev_attr_pid) - ret = sprintf(buf, "%u\n", q->blk_trace->pid); + ret = sprintf(buf, "%u\n", bt->pid); else if (attr == &dev_attr_start_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba); + ret = sprintf(buf, "%llu\n", bt->start_lba); else if (attr == &dev_attr_end_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); + ret = sprintf(buf, "%llu\n", bt->end_lba); out_unlock_bdev: mutex_unlock(&q->blk_trace_mutex); @@ -1801,6 +1850,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct block_device *bdev; struct request_queue *q; struct hd_struct *p; + struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL; @@ -1831,8 +1881,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - if (!!value == !!q->blk_trace) { + if (!!value == !!bt) { ret = 0; goto out_unlock_bdev; } @@ -1844,18 +1896,18 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } ret = 0; - if (q->blk_trace == NULL) + if (bt == NULL) ret = blk_trace_setup_queue(q, bdev); if (ret == 0) { if (attr == &dev_attr_act_mask) - q->blk_trace->act_mask = value; + bt->act_mask = value; else if (attr == &dev_attr_pid) - q->blk_trace->pid = value; + bt->pid = value; else if (attr == &dev_attr_start_lba) - q->blk_trace->start_lba = value; + bt->start_lba = value; else if (attr == &dev_attr_end_lba) - q->blk_trace->end_lba = value; + bt->end_lba = value; } out_unlock_bdev: diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index 4aefe003cb7c..7d56d621ffea 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -111,11 +111,11 @@ static int __init test_gen_synth_cmd(void) /* Create some bogus values just for testing */ vals[0] = 777; /* next_pid_field */ - vals[1] = (u64)"hula hoops"; /* next_comm_field */ + vals[1] = (u64)(long)"hula hoops"; /* next_comm_field */ vals[2] = 1000000; /* ts_ns */ vals[3] = 1000; /* ts_ms */ - vals[4] = smp_processor_id(); /* cpu */ - vals[5] = (u64)"thneed"; /* my_string_field */ + vals[4] = raw_smp_processor_id(); /* cpu */ + vals[5] = (u64)(long)"thneed"; /* my_string_field */ vals[6] = 598; /* my_int_field */ /* Now generate a gen_synth_test event */ @@ -218,11 +218,11 @@ static int __init test_empty_synth_event(void) /* Create some bogus values just for testing */ vals[0] = 777; /* next_pid_field */ - vals[1] = (u64)"tiddlywinks"; /* next_comm_field */ + vals[1] = (u64)(long)"tiddlywinks"; /* next_comm_field */ vals[2] = 1000000; /* ts_ns */ vals[3] = 1000; /* ts_ms */ - vals[4] = smp_processor_id(); /* cpu */ - vals[5] = (u64)"thneed_2.0"; /* my_string_field */ + vals[4] = raw_smp_processor_id(); /* cpu */ + vals[5] = (u64)(long)"thneed_2.0"; /* my_string_field */ vals[6] = 399; /* my_int_field */ /* Now trace an empty_synth_test event */ @@ -290,11 +290,11 @@ static int __init test_create_synth_event(void) /* Create some bogus values just for testing */ vals[0] = 777; /* next_pid_field */ - vals[1] = (u64)"tiddlywinks"; /* next_comm_field */ + vals[1] = (u64)(long)"tiddlywinks"; /* next_comm_field */ vals[2] = 1000000; /* ts_ns */ vals[3] = 1000; /* ts_ms */ - vals[4] = smp_processor_id(); /* cpu */ - vals[5] = (u64)"thneed"; /* my_string_field */ + vals[4] = raw_smp_processor_id(); /* cpu */ + vals[5] = (u64)(long)"thneed"; /* my_string_field */ vals[6] = 398; /* my_int_field */ /* Now generate a create_synth_test event */ @@ -330,7 +330,7 @@ static int __init test_add_next_synth_val(void) goto out; /* next_comm_field */ - ret = synth_event_add_next_val((u64)"slinky", &trace_state); + ret = synth_event_add_next_val((u64)(long)"slinky", &trace_state); if (ret) goto out; @@ -345,12 +345,12 @@ static int __init test_add_next_synth_val(void) goto out; /* cpu */ - ret = synth_event_add_next_val(smp_processor_id(), &trace_state); + ret = synth_event_add_next_val(raw_smp_processor_id(), &trace_state); if (ret) goto out; /* my_string_field */ - ret = synth_event_add_next_val((u64)"thneed_2.01", &trace_state); + ret = synth_event_add_next_val((u64)(long)"thneed_2.01", &trace_state); if (ret) goto out; @@ -388,7 +388,7 @@ static int __init test_add_synth_val(void) if (ret) goto out; - ret = synth_event_add_val("cpu", smp_processor_id(), &trace_state); + ret = synth_event_add_val("cpu", raw_smp_processor_id(), &trace_state); if (ret) goto out; @@ -396,12 +396,12 @@ static int __init test_add_synth_val(void) if (ret) goto out; - ret = synth_event_add_val("next_comm_field", (u64)"silly putty", + ret = synth_event_add_val("next_comm_field", (u64)(long)"silly putty", &trace_state); if (ret) goto out; - ret = synth_event_add_val("my_string_field", (u64)"thneed_9", + ret = synth_event_add_val("my_string_field", (u64)(long)"thneed_9", &trace_state); if (ret) goto out; @@ -423,13 +423,13 @@ static int __init test_trace_synth_event(void) /* Trace some bogus values just for testing */ ret = synth_event_trace(create_synth_test, 7, /* number of values */ - 444, /* next_pid_field */ - (u64)"clackers", /* next_comm_field */ - 1000000, /* ts_ns */ - 1000, /* ts_ms */ - smp_processor_id(), /* cpu */ - (u64)"Thneed", /* my_string_field */ - 999); /* my_int_field */ + (u64)444, /* next_pid_field */ + (u64)(long)"clackers", /* next_comm_field */ + (u64)1000000, /* ts_ns */ + (u64)1000, /* ts_ms */ + (u64)raw_smp_processor_id(), /* cpu */ + (u64)(long)"Thneed", /* my_string_field */ + (u64)999); /* my_int_field */ return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c797a15a1fc7..6b11e4e2150c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1837,6 +1837,7 @@ static __init int init_trace_selftests(void) pr_info("Running postponed tracer tests:\n"); + tracing_selftest_running = true; list_for_each_entry_safe(p, n, &postponed_selftests, list) { /* This loop can take minutes when sanitizers are enabled, so * lets make sure we allow RCU processing. @@ -1859,6 +1860,7 @@ static __init int init_trace_selftests(void) list_del(&p->list); kfree(p); } + tracing_selftest_running = false; out: mutex_unlock(&trace_types_lock); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 483b3fd1094f..5f6834a2bf41 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -821,6 +821,29 @@ static const char *synth_field_fmt(char *type) return fmt; } +static void print_synth_event_num_val(struct trace_seq *s, + char *print_fmt, char *name, + int size, u64 val, char *space) +{ + switch (size) { + case 1: + trace_seq_printf(s, print_fmt, name, (u8)val, space); + break; + + case 2: + trace_seq_printf(s, print_fmt, name, (u16)val, space); + break; + + case 4: + trace_seq_printf(s, print_fmt, name, (u32)val, space); + break; + + default: + trace_seq_printf(s, print_fmt, name, val, space); + break; + } +} + static enum print_line_t print_synth_event(struct trace_iterator *iter, int flags, struct trace_event *event) @@ -859,10 +882,13 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, } else { struct trace_print_flags __flags[] = { __def_gfpflag_names, {-1, NULL} }; + char *space = (i == se->n_fields - 1 ? "" : " "); - trace_seq_printf(s, print_fmt, se->fields[i]->name, - entry->fields[n_u64], - i == se->n_fields - 1 ? "" : " "); + print_synth_event_num_val(s, print_fmt, + se->fields[i]->name, + se->fields[i]->size, + entry->fields[n_u64], + space); if (strcmp(se->fields[i]->type, "gfp_t") == 0) { trace_seq_puts(s, " ("); @@ -1805,6 +1831,8 @@ __synth_event_trace_start(struct trace_event_file *file, int entry_size, fields_size = 0; int ret = 0; + memset(trace_state, '\0', sizeof(*trace_state)); + /* * Normal event tracing doesn't get called at all unless the * ENABLED bit is set (which attaches the probe thus allowing @@ -1885,6 +1913,11 @@ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...) return ret; } + if (n_vals != state.event->n_fields) { + ret = -EINVAL; + goto out; + } + va_start(args, n_vals); for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) { u64 val; @@ -1898,12 +1931,30 @@ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...) strscpy(str_field, str_val, STR_VAR_LEN_MAX); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { - state.entry->fields[n_u64] = val; + struct synth_field *field = state.event->fields[i]; + + switch (field->size) { + case 1: + *(u8 *)&state.entry->fields[n_u64] = (u8)val; + break; + + case 2: + *(u16 *)&state.entry->fields[n_u64] = (u16)val; + break; + + case 4: + *(u32 *)&state.entry->fields[n_u64] = (u32)val; + break; + + default: + state.entry->fields[n_u64] = val; + break; + } n_u64++; } } va_end(args); - +out: __synth_event_trace_end(&state); return ret; @@ -1942,6 +1993,11 @@ int synth_event_trace_array(struct trace_event_file *file, u64 *vals, return ret; } + if (n_vals != state.event->n_fields) { + ret = -EINVAL; + goto out; + } + for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) { if (state.event->fields[i]->is_string) { char *str_val = (char *)(long)vals[i]; @@ -1950,11 +2006,30 @@ int synth_event_trace_array(struct trace_event_file *file, u64 *vals, strscpy(str_field, str_val, STR_VAR_LEN_MAX); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { - state.entry->fields[n_u64] = vals[i]; + struct synth_field *field = state.event->fields[i]; + u64 val = vals[i]; + + switch (field->size) { + case 1: + *(u8 *)&state.entry->fields[n_u64] = (u8)val; + break; + + case 2: + *(u16 *)&state.entry->fields[n_u64] = (u16)val; + break; + + case 4: + *(u32 *)&state.entry->fields[n_u64] = (u32)val; + break; + + default: + state.entry->fields[n_u64] = val; + break; + } n_u64++; } } - +out: __synth_event_trace_end(&state); return ret; @@ -1997,8 +2072,6 @@ int synth_event_trace_start(struct trace_event_file *file, if (!trace_state) return -EINVAL; - memset(trace_state, '\0', sizeof(*trace_state)); - ret = __synth_event_trace_start(file, trace_state); if (ret == -ENOENT) ret = 0; /* just disabled, not really an error */ @@ -2069,8 +2142,25 @@ static int __synth_event_add_val(const char *field_name, u64 val, str_field = (char *)&entry->fields[field->offset]; strscpy(str_field, str_val, STR_VAR_LEN_MAX); - } else - entry->fields[field->offset] = val; + } else { + switch (field->size) { + case 1: + *(u8 *)&trace_state->entry->fields[field->offset] = (u8)val; + break; + + case 2: + *(u16 *)&trace_state->entry->fields[field->offset] = (u16)val; + break; + + case 4: + *(u32 *)&trace_state->entry->fields[field->offset] = (u32)val; + break; + + default: + trace_state->entry->fields[field->offset] = val; + break; + } + } out: return ret; } diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 3ea601a2eba5..ec3ce7fd299f 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -533,7 +533,7 @@ struct xbc_node *find_match_node(struct xbc_node *node, char *k) static int __init __xbc_add_key(char *k) { - struct xbc_node *node; + struct xbc_node *node, *child; if (!xbc_valid_keyword(k)) return xbc_parse_error("Invalid keyword", k); @@ -543,8 +543,12 @@ static int __init __xbc_add_key(char *k) if (!last_parent) /* the first level */ node = find_match_node(xbc_nodes, k); - else - node = find_match_node(xbc_node_get_child(last_parent), k); + else { + child = xbc_node_get_child(last_parent); + if (child && xbc_node_is_value(child)) + return xbc_parse_error("Subkey is mixed with value", k); + node = find_match_node(child, k); + } if (node) last_parent = node; @@ -574,10 +578,10 @@ static int __init __xbc_parse_keys(char *k) return __xbc_add_key(k); } -static int __init xbc_parse_kv(char **k, char *v) +static int __init xbc_parse_kv(char **k, char *v, int op) { struct xbc_node *prev_parent = last_parent; - struct xbc_node *node; + struct xbc_node *child; char *next; int c, ret; @@ -585,12 +589,19 @@ static int __init xbc_parse_kv(char **k, char *v) if (ret) return ret; + child = xbc_node_get_child(last_parent); + if (child) { + if (xbc_node_is_key(child)) + return xbc_parse_error("Value is mixed with subkey", v); + else if (op == '=') + return xbc_parse_error("Value is redefined", v); + } + c = __xbc_parse_value(&v, &next); if (c < 0) return c; - node = xbc_add_sibling(v, XBC_VALUE); - if (!node) + if (!xbc_add_sibling(v, XBC_VALUE)) return -ENOMEM; if (c == ',') { /* Array */ @@ -763,7 +774,7 @@ int __init xbc_init(char *buf) p = buf; do { - q = strpbrk(p, "{}=;\n#"); + q = strpbrk(p, "{}=+;\n#"); if (!q) { p = skip_spaces(p); if (*p != '\0') @@ -774,8 +785,15 @@ int __init xbc_init(char *buf) c = *q; *q++ = '\0'; switch (c) { + case '+': + if (*q++ != '=') { + ret = xbc_parse_error("Wrong '+' operator", + q - 2); + break; + } + /* Fall through */ case '=': - ret = xbc_parse_kv(&p, q); + ret = xbc_parse_kv(&p, q, c); break; case '{': ret = xbc_open_brace(&p, q); diff --git a/lib/crypto/chacha20poly1305.c b/lib/crypto/chacha20poly1305.c index 6d83cafebc69..ad0699ce702f 100644 --- a/lib/crypto/chacha20poly1305.c +++ b/lib/crypto/chacha20poly1305.c @@ -235,6 +235,9 @@ bool chacha20poly1305_crypt_sg_inplace(struct scatterlist *src, __le64 lens[2]; } b __aligned(16); + if (WARN_ON(src_len > INT_MAX)) + return false; + chacha_load_key(b.k, key); b.iv[0] = 0; diff --git a/mm/shmem.c b/mm/shmem.c index c8f7540ef048..aad3ba74b0e9 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3386,8 +3386,6 @@ static const struct constant_table shmem_param_enums_huge[] = { {"always", SHMEM_HUGE_ALWAYS }, {"within_size", SHMEM_HUGE_WITHIN_SIZE }, {"advise", SHMEM_HUGE_ADVISE }, - {"deny", SHMEM_HUGE_DENY }, - {"force", SHMEM_HUGE_FORCE }, {} }; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index dc3d2c1dd9d5..0e3dbc5f3c34 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -34,7 +34,6 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) const struct nf_br_ops *nf_ops; u8 state = BR_STATE_FORWARDING; const unsigned char *dest; - struct ethhdr *eth; u16 vid = 0; rcu_read_lock(); @@ -54,15 +53,14 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) BR_INPUT_SKB_CB(skb)->frag_max_size = 0; skb_reset_mac_header(skb); - eth = eth_hdr(skb); skb_pull(skb, ETH_HLEN); if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, &state)) goto out; if (IS_ENABLED(CONFIG_INET) && - (eth->h_proto == htons(ETH_P_ARP) || - eth->h_proto == htons(ETH_P_RARP)) && + (eth_hdr(skb)->h_proto == htons(ETH_P_ARP) || + eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { br_do_proxy_suppress_arp(skb, br, vid, NULL); } else if (IS_ENABLED(CONFIG_IPV6) && diff --git a/net/core/dev.c b/net/core/dev.c index e10bd680dc03..c6c985fe7b1b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3076,6 +3076,8 @@ static u16 skb_tx_hash(const struct net_device *dev, if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); + if (hash >= qoffset) + hash -= qoffset; while (unlikely(hash >= qcount)) hash -= qcount; return hash + qoffset; diff --git a/net/core/devlink.c b/net/core/devlink.c index 549ee56b7a21..5e220809844c 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2103,11 +2103,11 @@ err_action_values_put: static struct devlink_dpipe_table * devlink_dpipe_table_find(struct list_head *dpipe_tables, - const char *table_name) + const char *table_name, struct devlink *devlink) { struct devlink_dpipe_table *table; - - list_for_each_entry_rcu(table, dpipe_tables, list) { + list_for_each_entry_rcu(table, dpipe_tables, list, + lockdep_is_held(&devlink->lock)) { if (!strcmp(table->name, table_name)) return table; } @@ -2226,7 +2226,7 @@ static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) return -EINVAL; @@ -2382,7 +2382,7 @@ static int devlink_dpipe_table_counters_set(struct devlink *devlink, struct devlink_dpipe_table *table; table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) return -EINVAL; @@ -6854,7 +6854,7 @@ bool devlink_dpipe_table_counter_enabled(struct devlink *devlink, rcu_read_lock(); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); enabled = false; if (table) enabled = table->counters_enabled; @@ -6878,26 +6878,34 @@ int devlink_dpipe_table_register(struct devlink *devlink, void *priv, bool counter_control_extern) { struct devlink_dpipe_table *table; - - if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name)) - return -EEXIST; + int err = 0; if (WARN_ON(!table_ops->size_get)) return -EINVAL; + mutex_lock(&devlink->lock); + + if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name, + devlink)) { + err = -EEXIST; + goto unlock; + } + table = kzalloc(sizeof(*table), GFP_KERNEL); - if (!table) - return -ENOMEM; + if (!table) { + err = -ENOMEM; + goto unlock; + } table->name = table_name; table->table_ops = table_ops; table->priv = priv; table->counter_control_extern = counter_control_extern; - mutex_lock(&devlink->lock); list_add_tail_rcu(&table->list, &devlink->dpipe_table_list); +unlock: mutex_unlock(&devlink->lock); - return 0; + return err; } EXPORT_SYMBOL_GPL(devlink_dpipe_table_register); @@ -6914,7 +6922,7 @@ void devlink_dpipe_table_unregister(struct devlink *devlink, mutex_lock(&devlink->lock); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) goto unlock; list_del_rcu(&table->list); @@ -7071,7 +7079,7 @@ int devlink_dpipe_table_resource_set(struct devlink *devlink, mutex_lock(&devlink->lock); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, - table_name); + table_name, devlink); if (!table) { err = -EINVAL; goto out; diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index 8977fe1f3946..ef9197541cb3 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -305,7 +305,8 @@ nla_put_failure: static const struct nla_policy bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = { [ETHTOOL_A_BITSET_UNSPEC] = { .type = NLA_REJECT }, [ETHTOOL_A_BITSET_NOMASK] = { .type = NLA_FLAG }, - [ETHTOOL_A_BITSET_SIZE] = { .type = NLA_U32 }, + [ETHTOOL_A_BITSET_SIZE] = NLA_POLICY_MAX(NLA_U32, + ETHNL_MAX_BITSET_SIZE), [ETHTOOL_A_BITSET_BITS] = { .type = NLA_NESTED }, [ETHTOOL_A_BITSET_VALUE] = { .type = NLA_BINARY }, [ETHTOOL_A_BITSET_MASK] = { .type = NLA_BINARY }, diff --git a/net/ethtool/bitset.h b/net/ethtool/bitset.h index b8247e34109d..b849f9d19676 100644 --- a/net/ethtool/bitset.h +++ b/net/ethtool/bitset.h @@ -3,6 +3,8 @@ #ifndef _NET_ETHTOOL_BITSET_H #define _NET_ETHTOOL_BITSET_H +#define ETHNL_MAX_BITSET_SIZE S16_MAX + typedef const char (*const ethnl_string_array_t)[ETH_GSTRING_LEN]; int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 376882215919..0bd10a1f477f 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1724,6 +1724,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; + int res; if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; @@ -1735,7 +1736,11 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) memset(opt, 0, sizeof(struct ip_options)); opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); - if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL); + rcu_read_unlock(); + + if (res) return; if (gateway) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 316ebdf8151d..6b6b57000dad 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6124,7 +6124,11 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) { struct request_sock *req; - tcp_try_undo_loss(sk, false); + /* If we are still handling the SYNACK RTO, see if timestamp ECR allows + * undo. If peer SACKs triggered fast recovery, we can't undo here. + */ + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss) + tcp_try_undo_loss(sk, false); /* Reset rtx states to prevent spurious retransmits_timed_out() */ tcp_sk(sk)->retrans_stamp = 0; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 79fc012dd2ca..debdaeba5d8c 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -183,9 +183,15 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = -EBUSY; break; } - } else if (sk->sk_protocol != IPPROTO_TCP) + } else if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_prot != &tcpv6_prot) { + retv = -EBUSY; + break; + } break; - + } else { + break; + } if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; break; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e041af2f021a..88d7a692a965 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2959,7 +2959,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, (auth_transaction == 2 && ifmgd->auth_data->expected_transaction == 2)) { if (!ieee80211_mark_sta_auth(sdata, bssid)) - goto out_err; + return; /* ignore frame -- wait for timeout */ } else if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE && auth_transaction == 2) { sdata_info(sdata, "SAE peer confirmed\n"); @@ -2967,10 +2967,6 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, } cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); - return; - out_err: - mutex_unlock(&sdata->local->sta_mtx); - /* ignore frame -- wait for timeout */ } #define case_WLAN(type) \ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0e05ff037672..0ba98ad9bc85 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4114,7 +4114,7 @@ void __ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata) lockdep_assert_held(&local->sta_mtx); - list_for_each_entry_rcu(sta, &local->sta_list, list) { + list_for_each_entry(sta, &local->sta_list, list) { if (sdata != sta->sdata && (!sta->sdata->bss || sta->sdata->bss != sdata->bss)) continue; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e9aa6807b5be..3c19a8efdcea 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -543,6 +543,11 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, } } +static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) +{ + return 0; +} + static int __mptcp_init_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -551,6 +556,7 @@ static int __mptcp_init_sock(struct sock *sk) __set_bit(MPTCP_SEND_SPACE, &msk->flags); msk->first = NULL; + inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; return 0; } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 69c107f9ba8d..8dd17589217d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -723,6 +723,20 @@ ip_set_rcu_get(struct net *net, ip_set_id_t index) return set; } +static inline void +ip_set_lock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_lock_bh(&set->lock); +} + +static inline void +ip_set_unlock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_unlock_bh(&set->lock); +} + int ip_set_test(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt) @@ -744,9 +758,9 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, if (ret == -EAGAIN) { /* Type requests element to be completed */ pr_debug("element must be completed, ADD is triggered\n"); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); ret = 1; } else { /* --return-nomatch: invert matched element */ @@ -775,9 +789,9 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -797,9 +811,9 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -1264,9 +1278,9 @@ ip_set_flush_set(struct ip_set *set) { pr_debug("set: %s\n", set->name); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->flush(set); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); } static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb, @@ -1713,9 +1727,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, bool eexist = flags & IPSET_FLAG_EXIST, retried = false; do { - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); retried = true; } while (ret == -EAGAIN && set->variant->resize && diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 7480ce55b5c8..e52d7b7597a0 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -7,13 +7,21 @@ #include <linux/rcupdate.h> #include <linux/jhash.h> #include <linux/types.h> +#include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/ipset/ip_set.h> -#define __ipset_dereference_protected(p, c) rcu_dereference_protected(p, c) -#define ipset_dereference_protected(p, set) \ - __ipset_dereference_protected(p, lockdep_is_held(&(set)->lock)) - -#define rcu_dereference_bh_nfnl(p) rcu_dereference_bh_check(p, 1) +#define __ipset_dereference(p) \ + rcu_dereference_protected(p, 1) +#define ipset_dereference_nfnl(p) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) +#define ipset_dereference_set(p, set) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ + lockdep_is_held(&(set)->lock)) +#define ipset_dereference_bh_nfnl(p) \ + rcu_dereference_bh_check(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) /* Hashing which uses arrays to resolve clashing. The hash table is resized * (doubled) when searching becomes too long. @@ -72,11 +80,35 @@ struct hbucket { __aligned(__alignof__(u64)); }; +/* Region size for locking == 2^HTABLE_REGION_BITS */ +#define HTABLE_REGION_BITS 10 +#define ahash_numof_locks(htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 1 \ + : jhash_size((htable_bits) - HTABLE_REGION_BITS)) +#define ahash_sizeof_regions(htable_bits) \ + (ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region)) +#define ahash_region(n, htable_bits) \ + ((n) % ahash_numof_locks(htable_bits)) +#define ahash_bucket_start(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 0 \ + : (h) * jhash_size(HTABLE_REGION_BITS)) +#define ahash_bucket_end(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? jhash_size(htable_bits) \ + : ((h) + 1) * jhash_size(HTABLE_REGION_BITS)) + +struct htable_gc { + struct delayed_work dwork; + struct ip_set *set; /* Set the gc belongs to */ + u32 region; /* Last gc run position */ +}; + /* The hash table: the table size stored here in order to make resizing easy */ struct htable { atomic_t ref; /* References for resizing */ - atomic_t uref; /* References for dumping */ + atomic_t uref; /* References for dumping and gc */ u8 htable_bits; /* size of hash table == 2^htable_bits */ + u32 maxelem; /* Maxelem per region */ + struct ip_set_region *hregion; /* Region locks and ext sizes */ struct hbucket __rcu *bucket[0]; /* hashtable buckets */ }; @@ -162,6 +194,10 @@ htable_bits(u32 hashsize) #define NLEN 0 #endif /* IP_SET_HASH_WITH_NETS */ +#define SET_ELEM_EXPIRED(set, d) \ + (SET_WITH_TIMEOUT(set) && \ + ip_set_timeout_expired(ext_timeout(d, set))) + #endif /* _IP_SET_HASH_GEN_H */ #ifndef MTYPE @@ -205,10 +241,12 @@ htable_bits(u32 hashsize) #undef mtype_test_cidrs #undef mtype_test #undef mtype_uref -#undef mtype_expire #undef mtype_resize +#undef mtype_ext_size +#undef mtype_resize_ad #undef mtype_head #undef mtype_list +#undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init #undef mtype_variant @@ -247,10 +285,12 @@ htable_bits(u32 hashsize) #define mtype_test_cidrs IPSET_TOKEN(MTYPE, _test_cidrs) #define mtype_test IPSET_TOKEN(MTYPE, _test) #define mtype_uref IPSET_TOKEN(MTYPE, _uref) -#define mtype_expire IPSET_TOKEN(MTYPE, _expire) #define mtype_resize IPSET_TOKEN(MTYPE, _resize) +#define mtype_ext_size IPSET_TOKEN(MTYPE, _ext_size) +#define mtype_resize_ad IPSET_TOKEN(MTYPE, _resize_ad) #define mtype_head IPSET_TOKEN(MTYPE, _head) #define mtype_list IPSET_TOKEN(MTYPE, _list) +#define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) @@ -275,8 +315,7 @@ htable_bits(u32 hashsize) /* The generic hash structure */ struct htype { struct htable __rcu *table; /* the hash table */ - struct timer_list gc; /* garbage collection when timeout enabled */ - struct ip_set *set; /* attached to this ip_set */ + struct htable_gc gc; /* gc workqueue */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ #ifdef IP_SET_HASH_WITH_MARKMASK @@ -288,21 +327,33 @@ struct htype { #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif + struct list_head ad; /* Resize add|del backlist */ struct mtype_elem next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_NETS struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */ #endif }; +/* ADD|DEL entries saved during resize */ +struct mtype_resize_ad { + struct list_head list; + enum ipset_adt ad; /* ADD|DEL element */ + struct mtype_elem d; /* Element value */ + struct ip_set_ext ext; /* Extensions for ADD */ + struct ip_set_ext mext; /* Target extensions for ADD */ + u32 flags; /* Flags for ADD */ +}; + #ifdef IP_SET_HASH_WITH_NETS /* Network cidr size book keeping when the hash stores different * sized networks. cidr == real cidr + 1 to support /0. */ static void -mtype_add_cidr(struct htype *h, u8 cidr, u8 n) +mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { int i, j; + spin_lock_bh(&set->lock); /* Add in increasing prefix order, so larger cidr first */ for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) { if (j != -1) { @@ -311,7 +362,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) j = i; } else if (h->nets[i].cidr[n] == cidr) { h->nets[CIDR_POS(cidr)].nets[n]++; - return; + goto unlock; } } if (j != -1) { @@ -320,24 +371,29 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) } h->nets[i].cidr[n] = cidr; h->nets[CIDR_POS(cidr)].nets[n] = 1; +unlock: + spin_unlock_bh(&set->lock); } static void -mtype_del_cidr(struct htype *h, u8 cidr, u8 n) +mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { u8 i, j, net_end = NLEN - 1; + spin_lock_bh(&set->lock); for (i = 0; i < NLEN; i++) { if (h->nets[i].cidr[n] != cidr) continue; h->nets[CIDR_POS(cidr)].nets[n]--; if (h->nets[CIDR_POS(cidr)].nets[n] > 0) - return; + goto unlock; for (j = i; j < net_end && h->nets[j].cidr[n]; j++) h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; h->nets[j].cidr[n] = 0; - return; + goto unlock; } +unlock: + spin_unlock_bh(&set->lock); } #endif @@ -345,7 +401,7 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 n) static size_t mtype_ahash_memsize(const struct htype *h, const struct htable *t) { - return sizeof(*h) + sizeof(*t); + return sizeof(*h) + sizeof(*t) + ahash_sizeof_regions(t->htable_bits); } /* Get the ith element from the array block n */ @@ -369,24 +425,29 @@ mtype_flush(struct ip_set *set) struct htype *h = set->data; struct htable *t; struct hbucket *n; - u32 i; - - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); - if (!n) - continue; - if (set->extensions & IPSET_EXT_DESTROY) - mtype_ext_cleanup(set, n); - /* FIXME: use slab cache */ - rcu_assign_pointer(hbucket(t, i), NULL); - kfree_rcu(n, rcu); + u32 r, i; + + t = ipset_dereference_nfnl(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); + if (!n) + continue; + if (set->extensions & IPSET_EXT_DESTROY) + mtype_ext_cleanup(set, n); + /* FIXME: use slab cache */ + rcu_assign_pointer(hbucket(t, i), NULL); + kfree_rcu(n, rcu); + } + t->hregion[r].ext_size = 0; + t->hregion[r].elements = 0; + spin_unlock_bh(&t->hregion[r].lock); } #ifdef IP_SET_HASH_WITH_NETS memset(h->nets, 0, sizeof(h->nets)); #endif - set->elements = 0; - set->ext_size = 0; } /* Destroy the hashtable part of the set */ @@ -397,7 +458,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -406,6 +467,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) kfree(n); } + ip_set_free(t->hregion); ip_set_free(t); } @@ -414,28 +476,21 @@ static void mtype_destroy(struct ip_set *set) { struct htype *h = set->data; + struct list_head *l, *lt; if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&h->gc); + cancel_delayed_work_sync(&h->gc.dwork); - mtype_ahash_destroy(set, - __ipset_dereference_protected(h->table, 1), true); + mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + list_for_each_safe(l, lt, &h->ad) { + list_del(l); + kfree(l); + } kfree(h); set->data = NULL; } -static void -mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) -{ - struct htype *h = set->data; - - timer_setup(&h->gc, gc, 0); - mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); - pr_debug("gc initialized, run in every %u\n", - IPSET_GC_PERIOD(set->timeout)); -} - static bool mtype_same_set(const struct ip_set *a, const struct ip_set *b) { @@ -454,11 +509,9 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } -/* Delete expired elements from the hashtable */ static void -mtype_expire(struct ip_set *set, struct htype *h) +mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) { - struct htable *t; struct hbucket *n, *tmp; struct mtype_elem *data; u32 i, j, d; @@ -466,10 +519,12 @@ mtype_expire(struct ip_set *set, struct htype *h) #ifdef IP_SET_HASH_WITH_NETS u8 k; #endif + u8 htable_bits = t->htable_bits; - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, htable_bits); + i < ahash_bucket_end(r, htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; for (j = 0, d = 0; j < n->pos; j++) { @@ -485,58 +540,100 @@ mtype_expire(struct ip_set *set, struct htype *h) smp_mb__after_atomic(); #ifdef IP_SET_HASH_WITH_NETS for (k = 0; k < IPSET_NET_COUNT; k++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, k)), k); #endif + t->hregion[r].elements--; ip_set_ext_destroy(set, data); - set->elements--; d++; } if (d >= AHASH_INIT_SIZE) { if (d >= n->size) { + t->hregion[r].ext_size -= + ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, i), NULL); kfree_rcu(n, rcu); continue; } tmp = kzalloc(sizeof(*tmp) + - (n->size - AHASH_INIT_SIZE) * dsize, - GFP_ATOMIC); + (n->size - AHASH_INIT_SIZE) * dsize, + GFP_ATOMIC); if (!tmp) - /* Still try to delete expired elements */ + /* Still try to delete expired elements. */ continue; tmp->size = n->size - AHASH_INIT_SIZE; for (j = 0, d = 0; j < n->pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); - memcpy(tmp->value + d * dsize, data, dsize); + memcpy(tmp->value + d * dsize, + data, dsize); set_bit(d, tmp->used); d++; } tmp->pos = d; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, i), tmp); kfree_rcu(n, rcu); } } + spin_unlock_bh(&t->hregion[r].lock); } static void -mtype_gc(struct timer_list *t) +mtype_gc(struct work_struct *work) { - struct htype *h = from_timer(h, t, gc); - struct ip_set *set = h->set; + struct htable_gc *gc; + struct ip_set *set; + struct htype *h; + struct htable *t; + u32 r, numof_locks; + unsigned int next_run; + + gc = container_of(work, struct htable_gc, dwork.work); + set = gc->set; + h = set->data; - pr_debug("called\n"); spin_lock_bh(&set->lock); - mtype_expire(set, h); + t = ipset_dereference_set(h->table, set); + atomic_inc(&t->uref); + numof_locks = ahash_numof_locks(t->htable_bits); + r = gc->region++; + if (r >= numof_locks) { + r = gc->region = 0; + } + next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks; + if (next_run < HZ/10) + next_run = HZ/10; spin_unlock_bh(&set->lock); - h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; - add_timer(&h->gc); + mtype_gc_do(set, h, t, r); + + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by expire: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + + queue_delayed_work(system_power_efficient_wq, &gc->dwork, next_run); + +} + +static void +mtype_gc_init(struct htable_gc *gc) +{ + INIT_DEFERRABLE_WORK(&gc->dwork, mtype_gc); + queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static int +mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); +static int +mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); + /* Resize a hash: create a new hash table with doubling the hashsize * and inserting the elements to it. Repeat until we succeed or * fail due to memory pressures. @@ -547,7 +644,7 @@ mtype_resize(struct ip_set *set, bool retried) struct htype *h = set->data; struct htable *t, *orig; u8 htable_bits; - size_t extsize, dsize = set->dsize; + size_t dsize = set->dsize; #ifdef IP_SET_HASH_WITH_NETS u8 flags; struct mtype_elem *tmp; @@ -555,7 +652,9 @@ mtype_resize(struct ip_set *set, bool retried) struct mtype_elem *data; struct mtype_elem *d; struct hbucket *n, *m; - u32 i, j, key; + struct list_head *l, *lt; + struct mtype_resize_ad *x; + u32 i, j, r, nr, key; int ret; #ifdef IP_SET_HASH_WITH_NETS @@ -563,10 +662,8 @@ mtype_resize(struct ip_set *set, bool retried) if (!tmp) return -ENOMEM; #endif - rcu_read_lock_bh(); - orig = rcu_dereference_bh_nfnl(h->table); + orig = ipset_dereference_bh_nfnl(h->table); htable_bits = orig->htable_bits; - rcu_read_unlock_bh(); retry: ret = 0; @@ -583,88 +680,124 @@ retry: ret = -ENOMEM; goto out; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits)); + if (!t->hregion) { + kfree(t); + ret = -ENOMEM; + goto out; + } t->htable_bits = htable_bits; + t->maxelem = h->maxelem / ahash_numof_locks(htable_bits); + for (i = 0; i < ahash_numof_locks(htable_bits); i++) + spin_lock_init(&t->hregion[i].lock); - spin_lock_bh(&set->lock); - orig = __ipset_dereference_protected(h->table, 1); - /* There can't be another parallel resizing, but dumping is possible */ + /* There can't be another parallel resizing, + * but dumping, gc, kernel side add/del are possible + */ + orig = ipset_dereference_bh_nfnl(h->table); atomic_set(&orig->ref, 1); atomic_inc(&orig->uref); - extsize = 0; pr_debug("attempt to resize set %s from %u to %u, t %p\n", set->name, orig->htable_bits, htable_bits, orig); - for (i = 0; i < jhash_size(orig->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(orig, i), 1); - if (!n) - continue; - for (j = 0; j < n->pos; j++) { - if (!test_bit(j, n->used)) + for (r = 0; r < ahash_numof_locks(orig->htable_bits); r++) { + /* Expire may replace a hbucket with another one */ + rcu_read_lock_bh(); + for (i = ahash_bucket_start(r, orig->htable_bits); + i < ahash_bucket_end(r, orig->htable_bits); i++) { + n = __ipset_dereference(hbucket(orig, i)); + if (!n) continue; - data = ahash_data(n, j, dsize); + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, dsize); + if (SET_ELEM_EXPIRED(set, data)) + continue; #ifdef IP_SET_HASH_WITH_NETS - /* We have readers running parallel with us, - * so the live data cannot be modified. - */ - flags = 0; - memcpy(tmp, data, dsize); - data = tmp; - mtype_data_reset_flags(data, &flags); + /* We have readers running parallel with us, + * so the live data cannot be modified. + */ + flags = 0; + memcpy(tmp, data, dsize); + data = tmp; + mtype_data_reset_flags(data, &flags); #endif - key = HKEY(data, h->initval, htable_bits); - m = __ipset_dereference_protected(hbucket(t, key), 1); - if (!m) { - m = kzalloc(sizeof(*m) + + key = HKEY(data, h->initval, htable_bits); + m = __ipset_dereference(hbucket(t, key)); + nr = ahash_region(key, htable_bits); + if (!m) { + m = kzalloc(sizeof(*m) + AHASH_INIT_SIZE * dsize, GFP_ATOMIC); - if (!m) { - ret = -ENOMEM; - goto cleanup; - } - m->size = AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - RCU_INIT_POINTER(hbucket(t, key), m); - } else if (m->pos >= m->size) { - struct hbucket *ht; - - if (m->size >= AHASH_MAX(h)) { - ret = -EAGAIN; - } else { - ht = kzalloc(sizeof(*ht) + + if (!m) { + ret = -ENOMEM; + goto cleanup; + } + m->size = AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + RCU_INIT_POINTER(hbucket(t, key), m); + } else if (m->pos >= m->size) { + struct hbucket *ht; + + if (m->size >= AHASH_MAX(h)) { + ret = -EAGAIN; + } else { + ht = kzalloc(sizeof(*ht) + (m->size + AHASH_INIT_SIZE) * dsize, GFP_ATOMIC); - if (!ht) - ret = -ENOMEM; + if (!ht) + ret = -ENOMEM; + } + if (ret < 0) + goto cleanup; + memcpy(ht, m, sizeof(struct hbucket) + + m->size * dsize); + ht->size = m->size + AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + kfree(m); + m = ht; + RCU_INIT_POINTER(hbucket(t, key), ht); } - if (ret < 0) - goto cleanup; - memcpy(ht, m, sizeof(struct hbucket) + - m->size * dsize); - ht->size = m->size + AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - kfree(m); - m = ht; - RCU_INIT_POINTER(hbucket(t, key), ht); - } - d = ahash_data(m, m->pos, dsize); - memcpy(d, data, dsize); - set_bit(m->pos++, m->used); + d = ahash_data(m, m->pos, dsize); + memcpy(d, data, dsize); + set_bit(m->pos++, m->used); + t->hregion[nr].elements++; #ifdef IP_SET_HASH_WITH_NETS - mtype_data_reset_flags(d, &flags); + mtype_data_reset_flags(d, &flags); #endif + } } + rcu_read_unlock_bh(); } - rcu_assign_pointer(h->table, t); - set->ext_size = extsize; - spin_unlock_bh(&set->lock); + /* There can't be any other writer. */ + rcu_assign_pointer(h->table, t); /* Give time to other readers of the set */ synchronize_rcu(); pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, orig->htable_bits, orig, t->htable_bits, t); - /* If there's nobody else dumping the table, destroy it */ + /* Add/delete elements processed by the SET target during resize. + * Kernel-side add cannot trigger a resize and userspace actions + * are serialized by the mutex. + */ + list_for_each_safe(l, lt, &h->ad) { + x = list_entry(l, struct mtype_resize_ad, list); + if (x->ad == IPSET_ADD) { + mtype_add(set, &x->d, &x->ext, &x->mext, x->flags); + } else { + mtype_del(set, &x->d, NULL, NULL, 0); + } + list_del(l); + kfree(l); + } + /* If there's nobody else using the table, destroy it */ if (atomic_dec_and_test(&orig->uref)) { pr_debug("Table destroy by resize %p\n", orig); mtype_ahash_destroy(set, orig, false); @@ -677,15 +810,44 @@ out: return ret; cleanup: + rcu_read_unlock_bh(); atomic_set(&orig->ref, 0); atomic_dec(&orig->uref); - spin_unlock_bh(&set->lock); mtype_ahash_destroy(set, t, false); if (ret == -EAGAIN) goto retry; goto out; } +/* Get the current number of elements and ext_size in the set */ +static void +mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) +{ + struct htype *h = set->data; + const struct htable *t; + u32 i, j, r; + struct hbucket *n; + struct mtype_elem *data; + + t = rcu_dereference_bh(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = rcu_dereference_bh(hbucket(t, i)); + if (!n) + continue; + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, set->dsize); + if (!SET_ELEM_EXPIRED(set, data)) + (*elements)++; + } + } + *ext_size += t->hregion[r].ext_size; + } +} + /* Add an element to a hash and update the internal counters when succeeded, * otherwise report the proper error code. */ @@ -698,32 +860,49 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n, *old = ERR_PTR(-ENOENT); - int i, j = -1; + int i, j = -1, ret; bool flag_exist = flags & IPSET_FLAG_EXIST; bool deleted = false, forceadd = false, reuse = false; - u32 key, multi = 0; + u32 r, key, multi = 0, elements, maxelem; - if (set->elements >= h->maxelem) { - if (SET_WITH_TIMEOUT(set)) - /* FIXME: when set is full, we slow down here */ - mtype_expire(set, h); - if (set->elements >= h->maxelem && SET_WITH_FORCEADD(set)) + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(value, h->initval, t->htable_bits); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + elements = t->hregion[r].elements; + maxelem = t->maxelem; + if (elements >= maxelem) { + u32 e; + if (SET_WITH_TIMEOUT(set)) { + rcu_read_unlock_bh(); + mtype_gc_do(set, h, t, r); + rcu_read_lock_bh(); + } + maxelem = h->maxelem; + elements = 0; + for (e = 0; e < ahash_numof_locks(t->htable_bits); e++) + elements += t->hregion[e].elements; + if (elements >= maxelem && SET_WITH_FORCEADD(set)) forceadd = true; } + rcu_read_unlock_bh(); - t = ipset_dereference_protected(h->table, set); - key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) { - if (forceadd || set->elements >= h->maxelem) + if (forceadd || elements >= maxelem) goto set_full; old = NULL; n = kzalloc(sizeof(*n) + AHASH_INIT_SIZE * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } n->size = AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); goto copy_elem; } for (i = 0; i < n->pos; i++) { @@ -737,38 +916,37 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, } data = ahash_data(n, i, set->dsize); if (mtype_data_equal(data, d, &multi)) { - if (flag_exist || - (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)))) { + if (flag_exist || SET_ELEM_EXPIRED(set, data)) { /* Just the extensions could be overwritten */ j = i; goto overwrite_extensions; } - return -IPSET_ERR_EXIST; + ret = -IPSET_ERR_EXIST; + goto unlock; } /* Reuse first timed out entry */ - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)) && - j == -1) { + if (SET_ELEM_EXPIRED(set, data) && j == -1) { j = i; reuse = true; } } if (reuse || forceadd) { + if (j == -1) + j = 0; data = ahash_data(n, j, set->dsize); if (!deleted) { #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, i)), i); #endif ip_set_ext_destroy(set, data); - set->elements--; + t->hregion[r].elements--; } goto copy_data; } - if (set->elements >= h->maxelem) + if (elements >= maxelem) goto set_full; /* Create a new slot */ if (n->pos >= n->size) { @@ -776,28 +954,32 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); - return -EAGAIN; + ret = -EAGAIN; + goto resize; } old = n; n = kzalloc(sizeof(*n) + (old->size + AHASH_INIT_SIZE) * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } memcpy(n, old, sizeof(struct hbucket) + old->size * set->dsize); n->size = old->size + AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); } copy_elem: j = n->pos++; data = ahash_data(n, j, set->dsize); copy_data: - set->elements++; + t->hregion[r].elements++; #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_add_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); + mtype_add_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); #endif memcpy(data, d, sizeof(struct mtype_elem)); overwrite_extensions: @@ -820,13 +1002,41 @@ overwrite_extensions: if (old) kfree_rcu(old, rcu); } + ret = 0; +resize: + spin_unlock_bh(&t->hregion[r].lock); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side add, save values */ + struct mtype_resize_ad *x; + + x = kzalloc(sizeof(struct mtype_resize_ad), GFP_ATOMIC); + if (!x) + /* Don't bother */ + goto out; + x->ad = IPSET_ADD; + memcpy(&x->d, value, sizeof(struct mtype_elem)); + memcpy(&x->ext, ext, sizeof(struct ip_set_ext)); + memcpy(&x->mext, mext, sizeof(struct ip_set_ext)); + x->flags = flags; + spin_lock_bh(&set->lock); + list_add_tail(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + goto out; - return 0; set_full: if (net_ratelimit()) pr_warn("Set %s is full, maxelem %u reached\n", - set->name, h->maxelem); - return -IPSET_ERR_HASH_FULL; + set->name, maxelem); + ret = -IPSET_ERR_HASH_FULL; +unlock: + spin_unlock_bh(&t->hregion[r].lock); +out: + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by add: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + return ret; } /* Delete an element from the hash and free up space if possible. @@ -840,13 +1050,23 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n; - int i, j, k, ret = -IPSET_ERR_EXIST; + struct mtype_resize_ad *x = NULL; + int i, j, k, r, ret = -IPSET_ERR_EXIST; u32 key, multi = 0; size_t dsize = set->dsize; - t = ipset_dereference_protected(h->table, set); + /* Userspace add and resize is excluded by the mutex. + * Kernespace add does not trigger resize. + */ + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + rcu_read_unlock_bh(); + + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) goto out; for (i = 0, k = 0; i < n->pos; i++) { @@ -857,8 +1077,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, data = ahash_data(n, i, dsize); if (!mtype_data_equal(data, d, &multi)) continue; - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set))) + if (SET_ELEM_EXPIRED(set, data)) goto out; ret = 0; @@ -866,20 +1085,33 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, smp_mb__after_atomic(); if (i + 1 == n->pos) n->pos--; - set->elements--; + t->hregion[r].elements--; #ifdef IP_SET_HASH_WITH_NETS for (j = 0; j < IPSET_NET_COUNT; j++) - mtype_del_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, j)), - j); + mtype_del_cidr(set, h, + NCIDR_PUT(DCIDR_GET(d->cidr, j)), j); #endif ip_set_ext_destroy(set, data); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side del, + * save values + */ + x = kzalloc(sizeof(struct mtype_resize_ad), + GFP_ATOMIC); + if (x) { + x->ad = IPSET_DEL; + memcpy(&x->d, value, + sizeof(struct mtype_elem)); + x->flags = flags; + } + } for (; i < n->pos; i++) { if (!test_bit(i, n->used)) k++; } if (n->pos == 0 && k == 0) { - set->ext_size -= ext_size(n->size, dsize); + t->hregion[r].ext_size -= ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, key), NULL); kfree_rcu(n, rcu); } else if (k >= AHASH_INIT_SIZE) { @@ -898,7 +1130,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, k++; } tmp->pos = k; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, key), tmp); kfree_rcu(n, rcu); } @@ -906,6 +1139,16 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, } out: + spin_unlock_bh(&t->hregion[r].lock); + if (x) { + spin_lock_bh(&set->lock); + list_add(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by del: %p\n", t); + mtype_ahash_destroy(set, t, false); + } return ret; } @@ -991,6 +1234,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, int i, ret = 0; u32 key, multi = 0; + rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); #ifdef IP_SET_HASH_WITH_NETS /* If we test an IP address and not a network address, @@ -1022,6 +1266,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, goto out; } out: + rcu_read_unlock_bh(); return ret; } @@ -1033,23 +1278,14 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) const struct htable *t; struct nlattr *nested; size_t memsize; + u32 elements = 0; + size_t ext_size = 0; u8 htable_bits; - /* If any members have expired, set->elements will be wrong - * mytype_expire function will update it with the right count. - * we do not hold set->lock here, so grab it first. - * set->elements can still be incorrect in the case of a huge set, - * because elements might time out during the listing. - */ - if (SET_WITH_TIMEOUT(set)) { - spin_lock_bh(&set->lock); - mtype_expire(set, h); - spin_unlock_bh(&set->lock); - } - rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); - memsize = mtype_ahash_memsize(h, t) + set->ext_size; + t = rcu_dereference_bh(h->table); + mtype_ext_size(set, &elements, &ext_size); + memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size; htable_bits = t->htable_bits; rcu_read_unlock_bh(); @@ -1071,7 +1307,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) #endif if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || - nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements))) + nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; @@ -1091,15 +1327,15 @@ mtype_uref(struct ip_set *set, struct netlink_callback *cb, bool start) if (start) { rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); + t = ipset_dereference_bh_nfnl(h->table); atomic_inc(&t->uref); cb->args[IPSET_CB_PRIVATE] = (unsigned long)t; rcu_read_unlock_bh(); } else if (cb->args[IPSET_CB_PRIVATE]) { t = (struct htable *)cb->args[IPSET_CB_PRIVATE]; if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { - /* Resizing didn't destroy the hash table */ - pr_debug("Table destroy by dump: %p\n", t); + pr_debug("Table destroy after resize " + " by dump: %p\n", t); mtype_ahash_destroy(set, t, false); } cb->args[IPSET_CB_PRIVATE] = 0; @@ -1141,8 +1377,7 @@ mtype_list(const struct ip_set *set, if (!test_bit(i, n->used)) continue; e = ahash_data(n, i, set->dsize); - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(e, set))) + if (SET_ELEM_EXPIRED(set, e)) continue; pr_debug("list hash %lu hbucket %p i %u, data %p\n", cb->args[IPSET_CB_ARG0], n, i, e); @@ -1208,6 +1443,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .region_lock = true, }; #ifdef IP_SET_EMIT_CREATE @@ -1226,6 +1462,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, size_t hsize; struct htype *h; struct htable *t; + u32 i; pr_debug("Create set %s with family %s\n", set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6"); @@ -1294,6 +1531,15 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, kfree(h); return -ENOMEM; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); + if (!t->hregion) { + kfree(t); + kfree(h); + return -ENOMEM; + } + h->gc.set = set; + for (i = 0; i < ahash_numof_locks(hbits); i++) + spin_lock_init(&t->hregion[i].lock); h->maxelem = maxelem; #ifdef IP_SET_HASH_WITH_NETMASK h->netmask = netmask; @@ -1304,9 +1550,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, get_random_bytes(&h->initval, sizeof(h->initval)); t->htable_bits = hbits; + t->maxelem = h->maxelem / ahash_numof_locks(hbits); RCU_INIT_POINTER(h->table, t); - h->set = set; + INIT_LIST_HEAD(&h->ad); set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { @@ -1329,12 +1576,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) #endif - IPSET_TOKEN(HTYPE, 4_gc_init)(set, - IPSET_TOKEN(HTYPE, 4_gc)); + IPSET_TOKEN(HTYPE, 4_gc_init)(&h->gc); #ifndef IP_SET_PROTO_UNDEF else - IPSET_TOKEN(HTYPE, 6_gc_init)(set, - IPSET_TOKEN(HTYPE, 6_gc)); + IPSET_TOKEN(HTYPE, 6_gc_init)(&h->gc); #endif } pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index feac8553f6d9..4fc0c924ed5d 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1766,11 +1766,13 @@ static bool pipapo_match_field(struct nft_pipapo_field *f, static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { - const u8 *data = (const u8 *)elem->key.val.data; struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; + struct nft_pipapo_elem *e = elem->priv; int rules_f0, first_rule = 0; - struct nft_pipapo_elem *e; + const u8 *data; + + data = (const u8 *)nft_set_ext_key(&e->ext); e = pipapo_get(net, set, data, 0); if (IS_ERR(e)) diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 7a2c4b8408c4..8c835ad63729 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -402,15 +402,6 @@ static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) remove_proc_entry(hinfo->name, parent); } -static void htable_destroy(struct xt_hashlimit_htable *hinfo) -{ - cancel_delayed_work_sync(&hinfo->gc_work); - htable_remove_proc_entry(hinfo); - htable_selective_cleanup(hinfo, true); - kfree(hinfo->name); - vfree(hinfo); -} - static struct xt_hashlimit_htable *htable_find_get(struct net *net, const char *name, u_int8_t family) @@ -432,8 +423,13 @@ static void htable_put(struct xt_hashlimit_htable *hinfo) { if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) { hlist_del(&hinfo->node); + htable_remove_proc_entry(hinfo); mutex_unlock(&hashlimit_mutex); - htable_destroy(hinfo); + + cancel_delayed_work_sync(&hinfo->gc_work); + htable_selective_cleanup(hinfo, true); + kfree(hinfo->name); + vfree(hinfo); } } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 0522b2b1fd95..9f357aa22b94 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -497,8 +497,9 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, family->policy, validate, extack); - if (err && parallel) { - kfree(attrbuf); + if (err) { + if (parallel) + kfree(attrbuf); return ERR_PTR(err); } return attrbuf; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 90a31b15585f..8c466a712cda 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -186,6 +186,7 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + cookie_len /* TCA_ACT_COOKIE */ + nla_total_size(0) /* TCA_ACT_STATS nested */ + + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ /* TCA_STATS_BASIC */ + nla_total_size_64bit(sizeof(struct gnet_stats_basic)) /* TCA_STATS_PKT64 */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 90988a511cd5..6fd44bdb0fc3 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -512,15 +512,18 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) static int smc_connect_abort(struct smc_sock *smc, int reason_code, int local_contact) { + bool is_smcd = smc->conn.lgr->is_smcd; + if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(smc->conn.lgr); - if (smc->conn.lgr->is_smcd) + smc_lgr_cleanup_early(&smc->conn); + else + smc_conn_free(&smc->conn); + if (is_smcd) /* there is only one lgr role for SMC-D; use server lock */ mutex_unlock(&smc_server_lgr_pending); else mutex_unlock(&smc_client_lgr_pending); - smc_conn_free(&smc->conn); smc->connect_nonblock = 0; return reason_code; } @@ -1091,7 +1094,6 @@ static void smc_listen_out_err(struct smc_sock *new_smc) if (newsmcsk->sk_state == SMC_INIT) sock_put(&new_smc->sk); /* passive closing */ newsmcsk->sk_state = SMC_CLOSED; - smc_conn_free(&new_smc->conn); smc_listen_out(new_smc); } @@ -1102,12 +1104,13 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, { /* RDMA setup failed, switch back to TCP */ if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); if (reason_code < 0) { /* error, no fallback possible */ smc_listen_out_err(new_smc); return; } - smc_conn_free(&new_smc->conn); smc_switch_to_fallback(new_smc); new_smc->fallback_rsn = reason_code; if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { @@ -1170,16 +1173,18 @@ static int smc_listen_ism_init(struct smc_sock *new_smc, new_smc->conn.lgr->vlan_id, new_smc->conn.lgr->smcd)) { if (ini->cln_first_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); - smc_conn_free(&new_smc->conn); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); return SMC_CLC_DECL_SMCDNOTALK; } /* Create send and receive buffers */ if (smc_buf_create(new_smc, true)) { if (ini->cln_first_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); - smc_conn_free(&new_smc->conn); + smc_lgr_cleanup_early(&new_smc->conn); + else + smc_conn_free(&new_smc->conn); return SMC_CLC_DECL_MEM; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2249de5379ee..5b085efa3bce 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -162,6 +162,18 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) conn->lgr = NULL; } +void smc_lgr_cleanup_early(struct smc_connection *conn) +{ + struct smc_link_group *lgr = conn->lgr; + + if (!lgr) + return; + + smc_conn_free(conn); + smc_lgr_forget(lgr); + smc_lgr_schedule_free_work_fast(lgr); +} + /* Send delete link, either as client to request the initiation * of the DELETE LINK sequence from server; or as server to * initiate the delete processing. See smc_llc_rx_delete_link(). diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index c472e12951d1..234ae25f0025 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -296,6 +296,7 @@ struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; void smc_lgr_forget(struct smc_link_group *lgr); +void smc_lgr_cleanup_early(struct smc_connection *conn); void smc_lgr_terminate(struct smc_link_group *lgr, bool soft); void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport); void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, @@ -316,7 +317,6 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini); void smc_conn_free(struct smc_connection *conn); int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini); -void smcd_conn_free(struct smc_connection *conn); void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr); int smc_core_init(void); void smc_core_exit(void); diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 548632621f4b..d6ba186f67e2 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -573,6 +573,8 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) struct smc_ib_device *smcibdev; smcibdev = ib_get_client_data(ibdev, &smc_ib_client); + if (!smcibdev || smcibdev->ibdev != ibdev) + return; ib_set_client_data(ibdev, &smc_ib_client, NULL); spin_lock(&smc_ib_devices.lock); list_del_init(&smcibdev->list); /* remove from smc_ib_devices */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 62c12cb5763e..68debcb28fa4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -682,6 +682,7 @@ static int unix_set_peek_off(struct sock *sk, int val) return 0; } +#ifdef CONFIG_PROC_FS static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) { struct sock *sk = sock->sk; @@ -692,6 +693,9 @@ static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) seq_printf(m, "scm_fds: %u\n", READ_ONCE(u->scm_stat.nr_fds)); } } +#else +#define unix_show_fdinfo NULL +#endif static const struct proto_ops unix_stream_ops = { .family = PF_UNIX, diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9c5b2a91baad..a5f28708e0e7 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -451,6 +451,12 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) if (vsk->transport == new_transport) return 0; + /* transport->release() must be called with sock lock acquired. + * This path can only be taken during vsock_stream_connect(), + * where we have already held the sock lock. + * In the other cases, this function is called on a new socket + * which is not assigned to any transport. + */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); } @@ -753,20 +759,18 @@ static void __vsock_release(struct sock *sk, int level) vsk = vsock_sk(sk); pending = NULL; /* Compiler warning. */ - /* The release call is supposed to use lock_sock_nested() - * rather than lock_sock(), if a sock lock should be acquired. - */ - if (vsk->transport) - vsk->transport->release(vsk); - else if (sk->sk_type == SOCK_STREAM) - vsock_remove_sock(vsk); - /* When "level" is SINGLE_DEPTH_NESTING, use the nested * version to avoid the warning "possible recursive locking * detected". When "level" is 0, lock_sock_nested(sk, level) * is the same as lock_sock(sk). */ lock_sock_nested(sk, level); + + if (vsk->transport) + vsk->transport->release(vsk); + else if (sk->sk_type == SOCK_STREAM) + vsock_remove_sock(vsk); + sock_orphan(sk); sk->sk_shutdown = SHUTDOWN_MASK; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 3492c021925f..630b851f8150 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -526,12 +526,9 @@ static bool hvs_close_lock_held(struct vsock_sock *vsk) static void hvs_release(struct vsock_sock *vsk) { - struct sock *sk = sk_vsock(vsk); bool remove_sock; - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); remove_sock = hvs_close_lock_held(vsk); - release_sock(sk); if (remove_sock) vsock_remove_sock(vsk); } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index d9f0c9c5425a..f3c4bab2f737 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -829,7 +829,6 @@ void virtio_transport_release(struct vsock_sock *vsk) struct sock *sk = &vsk->sk; bool remove_sock = true; - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (sk->sk_type == SOCK_STREAM) remove_sock = virtio_transport_close(vsk); @@ -837,7 +836,6 @@ void virtio_transport_release(struct vsock_sock *vsk) list_del(&pkt->list); virtio_transport_free_pkt(pkt); } - release_sock(sk); if (remove_sock) vsock_remove_sock(vsk); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index cedf17d4933f..5b19e9fac4aa 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -20,6 +20,7 @@ #include <linux/netlink.h> #include <linux/nospec.h> #include <linux/etherdevice.h> +#include <linux/if_vlan.h> #include <net/net_namespace.h> #include <net/genetlink.h> #include <net/cfg80211.h> @@ -4800,8 +4801,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_he_obss_pd( info->attrs[NL80211_ATTR_HE_OBSS_PD], ¶ms.he_obss_pd); - if (err) - return err; + goto out; } nl80211_calculate_ap_params(¶ms); @@ -4823,6 +4823,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) } wdev_unlock(wdev); +out: kfree(params.acl); return err; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index fff9a74891fc..1a8218f1bbe0 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2276,7 +2276,7 @@ static void handle_channel_custom(struct wiphy *wiphy, break; } - if (IS_ERR(reg_rule)) { + if (IS_ERR_OR_NULL(reg_rule)) { pr_debug("Disabling freq %d MHz as custom regd has no rule that fits it\n", chan->center_freq); if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) { diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index bae62549e3d2..752ff0a225a9 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -300,15 +300,15 @@ DT_BINDING_DIR := Documentation/devicetree/bindings DT_TMP_SCHEMA := $(objtree)/$(DT_BINDING_DIR)/processed-schema.yaml quiet_cmd_dtb_check = CHECK $@ - cmd_dtb_check = $(DT_CHECKER) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ ; + cmd_dtb_check = $(DT_CHECKER) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ -define rule_dtc_dt_yaml +define rule_dtc $(call cmd_and_fixdep,dtc,yaml) $(call cmd,dtb_check) endef $(obj)/%.dt.yaml: $(src)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE - $(call if_changed_rule,dtc_dt_yaml) + $(call if_changed_rule,dtc) dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index ebe1685e92dd..d5e517d1c3dd 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -512,6 +512,8 @@ #define MSR_K7_HWCR 0xc0010015 #define MSR_K7_HWCR_SMMLOCK_BIT 0 #define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) +#define MSR_K7_HWCR_IRPERF_EN_BIT 30 +#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 503d3f42da16..3f3f780c8c65 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -390,6 +390,7 @@ struct kvm_sync_regs { #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 #define KVM_STATE_NESTED_EVMCS 0x00000004 +#define KVM_STATE_NESTED_MTF_PENDING 0x00000008 #define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_SMM_VMXON 0x00000002 diff --git a/tools/bootconfig/include/linux/printk.h b/tools/bootconfig/include/linux/printk.h index e978a63d3222..036e667596eb 100644 --- a/tools/bootconfig/include/linux/printk.h +++ b/tools/bootconfig/include/linux/printk.h @@ -4,10 +4,7 @@ #include <stdio.h> -/* controllable printf */ -extern int pr_output; -#define printk(fmt, ...) \ - (pr_output ? printf(fmt, ##__VA_ARGS__) : 0) +#define printk(fmt, ...) printf(fmt, ##__VA_ARGS__) #define pr_err printk #define pr_warn printk diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index e18eeb070562..a9b97814d1a9 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -14,8 +14,6 @@ #include <linux/kernel.h> #include <linux/bootconfig.h> -int pr_output = 1; - static int xbc_show_array(struct xbc_node *node) { const char *val; @@ -131,15 +129,26 @@ int load_xbc_from_initrd(int fd, char **buf) struct stat stat; int ret; u32 size = 0, csum = 0, rcsum; + char magic[BOOTCONFIG_MAGIC_LEN]; ret = fstat(fd, &stat); if (ret < 0) return -errno; - if (stat.st_size < 8) + if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN) + return 0; + + if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) { + pr_err("Failed to lseek: %d\n", -errno); + return -errno; + } + if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0) + return -errno; + /* Check the bootconfig magic bytes */ + if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0) return 0; - if (lseek(fd, -8, SEEK_END) < 0) { + if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) { pr_err("Failed to lseek: %d\n", -errno); return -errno; } @@ -150,11 +159,14 @@ int load_xbc_from_initrd(int fd, char **buf) if (read(fd, &csum, sizeof(u32)) < 0) return -errno; - /* Wrong size, maybe no boot config here */ - if (stat.st_size < size + 8) - return 0; + /* Wrong size error */ + if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) { + pr_err("bootconfig size is too big\n"); + return -E2BIG; + } - if (lseek(fd, stat.st_size - 8 - size, SEEK_SET) < 0) { + if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN), + SEEK_SET) < 0) { pr_err("Failed to lseek: %d\n", -errno); return -errno; } @@ -163,17 +175,17 @@ int load_xbc_from_initrd(int fd, char **buf) if (ret < 0) return ret; - /* Wrong Checksum, maybe no boot config here */ + /* Wrong Checksum */ rcsum = checksum((unsigned char *)*buf, size); if (csum != rcsum) { pr_err("checksum error: %d != %d\n", csum, rcsum); - return 0; + return -EINVAL; } ret = xbc_init(*buf); - /* Wrong data, maybe no boot config here */ + /* Wrong data */ if (ret < 0) - return 0; + return ret; return size; } @@ -213,20 +225,15 @@ int delete_xbc(const char *path) return -errno; } - /* - * Suppress error messages in xbc_init() because it can be just a - * data which concidentally matches the size and checksum footer. - */ - pr_output = 0; size = load_xbc_from_initrd(fd, &buf); - pr_output = 1; if (size < 0) { ret = size; pr_err("Failed to load a boot config from initrd: %d\n", ret); } else if (size > 0) { ret = fstat(fd, &stat); if (!ret) - ret = ftruncate(fd, stat.st_size - size - 8); + ret = ftruncate(fd, stat.st_size + - size - 8 - BOOTCONFIG_MAGIC_LEN); if (ret) ret = -errno; } /* Ignore if there is no boot config in initrd */ @@ -295,6 +302,12 @@ int apply_xbc(const char *path, const char *xbc_path) pr_err("Failed to apply a boot config: %d\n", ret); return ret; } + /* Write a magic word of the bootconfig */ + ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); + if (ret < 0) { + pr_err("Failed to apply a boot config magic: %d\n", ret); + return ret; + } close(fd); free(data); diff --git a/tools/bootconfig/samples/bad-mixed-kv1.bconf b/tools/bootconfig/samples/bad-mixed-kv1.bconf new file mode 100644 index 000000000000..1761547dd05c --- /dev/null +++ b/tools/bootconfig/samples/bad-mixed-kv1.bconf @@ -0,0 +1,3 @@ +# value -> subkey pattern +key = value +key.subkey = another-value diff --git a/tools/bootconfig/samples/bad-mixed-kv2.bconf b/tools/bootconfig/samples/bad-mixed-kv2.bconf new file mode 100644 index 000000000000..6b32e0c3878c --- /dev/null +++ b/tools/bootconfig/samples/bad-mixed-kv2.bconf @@ -0,0 +1,3 @@ +# subkey -> value pattern +key.subkey = value +key = another-value diff --git a/tools/bootconfig/samples/bad-samekey.bconf b/tools/bootconfig/samples/bad-samekey.bconf new file mode 100644 index 000000000000..e8d983a4563c --- /dev/null +++ b/tools/bootconfig/samples/bad-samekey.bconf @@ -0,0 +1,6 @@ +# Same key value is not allowed +key { + foo = value + bar = value2 +} +key.foo = value diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index 1de06de328e2..1411f4c3454f 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -9,7 +9,7 @@ TEMPCONF=`mktemp temp-XXXX.bconf` NG=0 cleanup() { - rm -f $INITRD $TEMPCONF + rm -f $INITRD $TEMPCONF $OUTFILE exit $NG } @@ -49,7 +49,7 @@ xpass $BOOTCONF -a $TEMPCONF $INITRD new_size=$(stat -c %s $INITRD) echo "File size check" -xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9) +xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12) echo "Apply command repeat test" xpass $BOOTCONF -a $TEMPCONF $INITRD @@ -71,7 +71,6 @@ printf " \0\0\0 \0\0\0" >> $INITRD $BOOTCONF -a $TEMPCONF $INITRD > $OUTFILE 2>&1 xfail grep -i "failed" $OUTFILE xfail grep -i "error" $OUTFILE -rm $OUTFILE echo "Max node number check" @@ -96,6 +95,19 @@ truncate -s 32764 $TEMPCONF echo "\"" >> $TEMPCONF # add 2 bytes + terminal ('\"\n\0') xpass $BOOTCONF -a $TEMPCONF $INITRD +echo "Adding same-key values" +cat > $TEMPCONF << EOF +key = bar, baz +key += qux +EOF +echo > $INITRD + +xpass $BOOTCONF -a $TEMPCONF $INITRD +$BOOTCONF $INITRD > $OUTFILE +xpass grep -q "bar" $OUTFILE +xpass grep -q "baz" $OUTFILE +xpass grep -q "qux" $OUTFILE + echo "=== expected failure cases ===" for i in samples/bad-* ; do xfail $BOOTCONF -a $i $INITRD diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index c4dd23c4b478..8ead55593984 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -239,7 +239,6 @@ buildid.*:: set buildid.dir to /dev/null. The default is $HOME/.debug annotate.*:: - These options work only for TUI. These are in control of addresses, jump function, source code in lines of assembly code from a specific program. @@ -269,6 +268,8 @@ annotate.*:: │ mov (%rdi),%rdx │ return n; + This option works with tui, stdio2 browsers. + annotate.use_offset:: Basing on a first address of a loaded function, offset can be used. Instead of using original addresses of assembly code, @@ -287,6 +288,8 @@ annotate.*:: 368:│ mov 0x8(%r14),%rdi + This option works with tui, stdio2 browsers. + annotate.jump_arrows:: There can be jump instruction among assembly code. Depending on a boolean value of jump_arrows, @@ -306,6 +309,8 @@ annotate.*:: │1330: mov %r15,%r10 │1333: cmp %r15,%r14 + This option works with tui browser. + annotate.show_linenr:: When showing source code if this option is 'true', line numbers are printed as below. @@ -325,6 +330,8 @@ annotate.*:: │ array++; │ } + This option works with tui, stdio2 browsers. + annotate.show_nr_jumps:: Let's see a part of assembly code. @@ -335,6 +342,8 @@ annotate.*:: │1 1382: movb $0x1,-0x270(%rbp) + This option works with tui, stdio2 browsers. + annotate.show_total_period:: To compare two records on an instruction base, with this option provided, display total number of samples that belong to a line @@ -348,11 +357,30 @@ annotate.*:: 99.93 │ mov %eax,%eax + This option works with tui, stdio2, stdio browsers. + + annotate.show_nr_samples:: + By default perf annotate shows percentage of samples. This option + can be used to print absolute number of samples. Ex, when set as + false: + + Percent│ + 74.03 │ mov %fs:0x28,%rax + + When set as true: + + Samples│ + 6 │ mov %fs:0x28,%rax + + This option works with tui, stdio2, stdio browsers. + annotate.offset_level:: Default is '1', meaning just jump targets will have offsets show right beside the instruction. When set to '2' 'call' instructions will also have its offsets shown, 3 or higher will show offsets for all instructions. + This option works with tui, stdio2 browsers. + hist.*:: hist.percentage:: This option control the way to calculate overhead of filtered entries - @@ -490,6 +518,12 @@ top.*:: column by default. The default is 'true'. + top.call-graph:: + This is identical to 'call-graph.record-mode', except it is + applicable only for 'top' subcommand. This option ONLY setup + the unwind method. To enable 'perf top' to actually use it, + the command line option -g must be specified. + man.*:: man.viewer:: This option can assign a tool to view manual pages when 'help' @@ -517,6 +551,16 @@ record.*:: But if this option is 'no-cache', it will not update the build-id cache. 'skip' skips post-processing and does not update the cache. + record.call-graph:: + This is identical to 'call-graph.record-mode', except it is + applicable only for 'record' subcommand. This option ONLY setup + the unwind method. To enable 'perf record' to actually use it, + the command line option -g must be specified. + + record.aio:: + Use 'n' control blocks in asynchronous (Posix AIO) trace writing + mode ('n' default: 1, max: 4). + diff.*:: diff.order:: This option sets the number of columns to sort the result. @@ -566,6 +610,11 @@ trace.*:: "libbeauty", the default, to use the same argument beautifiers used in the strace-like sys_enter+sys_exit lines. +ftrace.*:: + ftrace.tracer:: + Can be used to select the default tracer. Possible values are + 'function' and 'function_graph'. + llvm.*:: llvm.clang-path:: Path to clang. If omit, search it from $PATH. @@ -610,6 +659,29 @@ scripts.*:: The script gets the same options passed as a full perf script, in particular -i perfdata file, --cpu, --tid +convert.*:: + + convert.queue-size:: + Limit the size of ordered_events queue, so we could control + allocation size of perf data files without proper finished + round events. + +intel-pt.*:: + + intel-pt.cache-divisor:: + + intel-pt.mispred-all:: + If set, Intel PT decoder will set the mispred flag on all + branches. + +auxtrace.*:: + + auxtrace.dumpdir:: + s390 only. The directory to save the auxiliary trace buffer + can be changed using this option. Ex, auxtrace.dumpdir=/tmp. + If the directory does not exist or has the wrong file type, + the current directory is used. + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 2898cfdf8fe1..941f814820b8 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -858,21 +858,6 @@ static void cs_etm_recording_free(struct auxtrace_record *itr) free(ptr); } -static int cs_etm_read_finish(struct auxtrace_record *itr, int idx) -{ - struct cs_etm_recording *ptr = - container_of(itr, struct cs_etm_recording, itr); - struct evsel *evsel; - - evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->core.attr.type == ptr->cs_etm_pmu->type) - return perf_evlist__enable_event_idx(ptr->evlist, - evsel, idx); - } - - return -EINVAL; -} - struct auxtrace_record *cs_etm_record_init(int *err) { struct perf_pmu *cs_etm_pmu; @@ -892,6 +877,7 @@ struct auxtrace_record *cs_etm_record_init(int *err) } ptr->cs_etm_pmu = cs_etm_pmu; + ptr->itr.pmu = cs_etm_pmu; ptr->itr.parse_snapshot_options = cs_etm_parse_snapshot_options; ptr->itr.recording_options = cs_etm_recording_options; ptr->itr.info_priv_size = cs_etm_info_priv_size; @@ -901,7 +887,7 @@ struct auxtrace_record *cs_etm_record_init(int *err) ptr->itr.snapshot_finish = cs_etm_snapshot_finish; ptr->itr.reference = cs_etm_reference; ptr->itr.free = cs_etm_recording_free; - ptr->itr.read_finish = cs_etm_read_finish; + ptr->itr.read_finish = auxtrace_record__read_finish; *err = 0; return &ptr->itr; diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index eba6541ec0f1..8d6821d9c3f6 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -158,20 +158,6 @@ static void arm_spe_recording_free(struct auxtrace_record *itr) free(sper); } -static int arm_spe_read_finish(struct auxtrace_record *itr, int idx) -{ - struct arm_spe_recording *sper = - container_of(itr, struct arm_spe_recording, itr); - struct evsel *evsel; - - evlist__for_each_entry(sper->evlist, evsel) { - if (evsel->core.attr.type == sper->arm_spe_pmu->type) - return perf_evlist__enable_event_idx(sper->evlist, - evsel, idx); - } - return -EINVAL; -} - struct auxtrace_record *arm_spe_recording_init(int *err, struct perf_pmu *arm_spe_pmu) { @@ -189,12 +175,13 @@ struct auxtrace_record *arm_spe_recording_init(int *err, } sper->arm_spe_pmu = arm_spe_pmu; + sper->itr.pmu = arm_spe_pmu; sper->itr.recording_options = arm_spe_recording_options; sper->itr.info_priv_size = arm_spe_info_priv_size; sper->itr.info_fill = arm_spe_info_fill; sper->itr.free = arm_spe_recording_free; sper->itr.reference = arm_spe_reference; - sper->itr.read_finish = arm_spe_read_finish; + sper->itr.read_finish = auxtrace_record__read_finish; sper->itr.alignment = 0; *err = 0; diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 43f736ed47f2..35b61bfc1b1a 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -517,3 +517,5 @@ 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open 435 nospu clone3 ppc_clone3 +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 27d9e214d068..26cee1052179 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -413,20 +413,6 @@ out_err: return err; } -static int intel_bts_read_finish(struct auxtrace_record *itr, int idx) -{ - struct intel_bts_recording *btsr = - container_of(itr, struct intel_bts_recording, itr); - struct evsel *evsel; - - evlist__for_each_entry(btsr->evlist, evsel) { - if (evsel->core.attr.type == btsr->intel_bts_pmu->type) - return perf_evlist__enable_event_idx(btsr->evlist, - evsel, idx); - } - return -EINVAL; -} - struct auxtrace_record *intel_bts_recording_init(int *err) { struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); @@ -447,6 +433,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err) } btsr->intel_bts_pmu = intel_bts_pmu; + btsr->itr.pmu = intel_bts_pmu; btsr->itr.recording_options = intel_bts_recording_options; btsr->itr.info_priv_size = intel_bts_info_priv_size; btsr->itr.info_fill = intel_bts_info_fill; @@ -456,7 +443,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err) btsr->itr.find_snapshot = intel_bts_find_snapshot; btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options; btsr->itr.reference = intel_bts_reference; - btsr->itr.read_finish = intel_bts_read_finish; + btsr->itr.read_finish = auxtrace_record__read_finish; btsr->itr.alignment = sizeof(struct branch); return &btsr->itr; } diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 20df442fdf36..7eea4fd7ce58 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -1166,20 +1166,6 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused) return rdtsc(); } -static int intel_pt_read_finish(struct auxtrace_record *itr, int idx) -{ - struct intel_pt_recording *ptr = - container_of(itr, struct intel_pt_recording, itr); - struct evsel *evsel; - - evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->core.attr.type == ptr->intel_pt_pmu->type) - return perf_evlist__enable_event_idx(ptr->evlist, evsel, - idx); - } - return -EINVAL; -} - struct auxtrace_record *intel_pt_recording_init(int *err) { struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); @@ -1200,6 +1186,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err) } ptr->intel_pt_pmu = intel_pt_pmu; + ptr->itr.pmu = intel_pt_pmu; ptr->itr.recording_options = intel_pt_recording_options; ptr->itr.info_priv_size = intel_pt_info_priv_size; ptr->itr.info_fill = intel_pt_info_fill; @@ -1209,7 +1196,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err) ptr->itr.find_snapshot = intel_pt_find_snapshot; ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options; ptr->itr.reference = intel_pt_reference; - ptr->itr.read_finish = intel_pt_read_finish; + ptr->itr.read_finish = auxtrace_record__read_finish; /* * Decoding starts at a PSB packet. Minimum PSB period is 2K so 4K * should give at least 1 PSB per sample. diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index ff61795a4d13..6c0a0412502e 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -566,6 +566,8 @@ int cmd_annotate(int argc, const char **argv) if (ret < 0) return ret; + annotation_config__init(&annotate.opts); + argc = parse_options(argc, argv, options, annotate_usage, 0); if (argc) { /* @@ -605,8 +607,6 @@ int cmd_annotate(int argc, const char **argv) if (ret < 0) goto out_delete; - annotation_config__init(); - symbol_conf.try_vmlinux_path = true; ret = symbol__init(&annotate.session->header.env); diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 26bc5923e6b5..70548df2abb9 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -449,7 +449,8 @@ static int perf_del_probe_events(struct strfilter *filter) ret = probe_file__del_strlist(kfd, klist); if (ret < 0) goto error; - } + } else if (ret == -ENOMEM) + goto error; ret2 = probe_file__get_events(ufd, filter, ulist); if (ret2 == 0) { @@ -459,7 +460,8 @@ static int perf_del_probe_events(struct strfilter *filter) ret2 = probe_file__del_strlist(ufd, ulist); if (ret2 < 0) goto error; - } + } else if (ret2 == -ENOMEM) + goto error; if (ret == -ENOENT && ret2 == -ENOENT) pr_warning("\"%s\" does not hit any event.\n", str); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 9483b3f0cae3..72a12b69f120 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1507,7 +1507,7 @@ repeat: symbol_conf.priv_size += sizeof(u32); symbol_conf.sort_by_name = true; } - annotation_config__init(); + annotation_config__init(&report.annotation_opts); } if (symbol__init(&session->header.env) < 0) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 8affcab75604..f6dd1a63f159 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -143,7 +143,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) return err; } - err = symbol__annotate(&he->ms, evsel, 0, &top->annotation_opts, NULL); + err = symbol__annotate(&he->ms, evsel, &top->annotation_opts, NULL); if (err == 0) { top->sym_filter_entry = he; } else { @@ -1683,7 +1683,7 @@ int cmd_top(int argc, const char **argv) if (status < 0) goto out_delete_evlist; - annotation_config__init(); + annotation_config__init(&top.annotation_opts); symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); status = symbol__init(NULL); diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h index 607189a315b2..6e61c4bdf548 100644 --- a/tools/perf/include/bpf/pid_filter.h +++ b/tools/perf/include/bpf/pid_filter.h @@ -3,7 +3,7 @@ #ifndef _PERF_BPF_PID_FILTER_ #define _PERF_BPF_PID_FILTER_ -#include <bpf/bpf.h> +#include <bpf.h> #define pid_filter(name) pid_map(name, bool) diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h index 7ca6fa5463ee..316af5b2ff35 100644 --- a/tools/perf/include/bpf/stdio.h +++ b/tools/perf/include/bpf/stdio.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -#include <bpf/bpf.h> +#include <bpf.h> struct bpf_map SEC("maps") __bpf_stdout__ = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h index d1a35b6c649d..ca7877f9a976 100644 --- a/tools/perf/include/bpf/unistd.h +++ b/tools/perf/include/bpf/unistd.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 -#include <bpf/bpf.h> +#include <bpf.h> static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid; diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh index 7cb99b433888..c2cc42daf924 100644 --- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh @@ -14,7 +14,7 @@ add_probe_vfs_getname() { if [ $had_vfs_getname -eq 1 ] ; then line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/') perf probe -q "vfs_getname=getname_flags:${line} pathname=result->name:string" || \ - perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string" + perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" fi } diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index badbddbb30f8..9023267e5643 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -754,10 +754,9 @@ static int annotate_browser__run(struct annotate_browser *browser, "? Search string backwards\n"); continue; case 'r': - { - script_browse(NULL, NULL); - continue; - } + script_browse(NULL, NULL); + annotate_browser__show(&browser->b, title, help); + continue; case 'k': notes->options->show_linenr = !notes->options->show_linenr; break; @@ -834,13 +833,13 @@ show_sup_ins: map_symbol__annotation_dump(ms, evsel, browser->opts); continue; case 't': - if (notes->options->show_total_period) { - notes->options->show_total_period = false; - notes->options->show_nr_samples = true; - } else if (notes->options->show_nr_samples) - notes->options->show_nr_samples = false; + if (symbol_conf.show_total_period) { + symbol_conf.show_total_period = false; + symbol_conf.show_nr_samples = true; + } else if (symbol_conf.show_nr_samples) + symbol_conf.show_nr_samples = false; else - notes->options->show_total_period = true; + symbol_conf.show_total_period = true; annotation__update_column_widths(notes); continue; case 'c': diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 22cc240f7371..35f9641bf670 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -174,7 +174,7 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel, if (ms->map->dso->annotate_warned) return -1; - err = symbol__annotate(ms, evsel, 0, &annotation__default_options, NULL); + err = symbol__annotate(ms, evsel, &annotation__default_options, NULL); if (err) { char msg[BUFSIZ]; symbol__strerror_disassemble(ms, err, msg, sizeof(msg)); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index ca73fb74ad03..0ea95be84b3b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1143,93 +1143,70 @@ out: } struct annotate_args { - size_t privsize; - struct arch *arch; - struct map_symbol ms; - struct evsel *evsel; + struct arch *arch; + struct map_symbol ms; + struct evsel *evsel; struct annotation_options *options; - s64 offset; - char *line; - int line_nr; + s64 offset; + char *line; + int line_nr; }; -static void annotation_line__delete(struct annotation_line *al) +static void annotation_line__init(struct annotation_line *al, + struct annotate_args *args, + int nr) { - void *ptr = (void *) al - al->privsize; + al->offset = args->offset; + al->line = strdup(args->line); + al->line_nr = args->line_nr; + al->data_nr = nr; +} +static void annotation_line__exit(struct annotation_line *al) +{ free_srcline(al->path); zfree(&al->line); - free(ptr); } -/* - * Allocating the annotation line data with following - * structure: - * - * -------------------------------------- - * private space | struct annotation_line - * -------------------------------------- - * - * Size of the private space is stored in 'struct annotation_line'. - * - */ -static struct annotation_line * -annotation_line__new(struct annotate_args *args, size_t privsize) +static size_t disasm_line_size(int nr) { struct annotation_line *al; - struct evsel *evsel = args->evsel; - size_t size = privsize + sizeof(*al); - int nr = 1; - - if (perf_evsel__is_group_event(evsel)) - nr = evsel->core.nr_members; - size += sizeof(al->data[0]) * nr; - - al = zalloc(size); - if (al) { - al = (void *) al + privsize; - al->privsize = privsize; - al->offset = args->offset; - al->line = strdup(args->line); - al->line_nr = args->line_nr; - al->data_nr = nr; - } - - return al; + return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr)); } /* * Allocating the disasm annotation line data with * following structure: * - * ------------------------------------------------------------ - * privsize space | struct disasm_line | struct annotation_line - * ------------------------------------------------------------ + * ------------------------------------------- + * struct disasm_line | struct annotation_line + * ------------------------------------------- * * We have 'struct annotation_line' member as last member * of 'struct disasm_line' to have an easy access. - * */ static struct disasm_line *disasm_line__new(struct annotate_args *args) { struct disasm_line *dl = NULL; - struct annotation_line *al; - size_t privsize = args->privsize + offsetof(struct disasm_line, al); + int nr = 1; - al = annotation_line__new(args, privsize); - if (al != NULL) { - dl = disasm_line(al); + if (perf_evsel__is_group_event(args->evsel)) + nr = args->evsel->core.nr_members; - if (dl->al.line == NULL) - goto out_delete; + dl = zalloc(disasm_line_size(nr)); + if (!dl) + return NULL; - if (args->offset != -1) { - if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0) - goto out_free_line; + annotation_line__init(&dl->al, args, nr); + if (dl->al.line == NULL) + goto out_delete; - disasm_line__init_ins(dl, args->arch, &args->ms); - } + if (args->offset != -1) { + if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0) + goto out_free_line; + + disasm_line__init_ins(dl, args->arch, &args->ms); } return dl; @@ -1248,7 +1225,8 @@ void disasm_line__free(struct disasm_line *dl) else ins__delete(&dl->ops); zfree(&dl->ins.name); - annotation_line__delete(&dl->al); + annotation_line__exit(&dl->al); + free(dl); } int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name) @@ -2149,13 +2127,12 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel) annotation__calc_percent(notes, evsel, symbol__size(sym)); } -int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, size_t privsize, +int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *options, struct arch **parch) { struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); struct annotate_args args = { - .privsize = privsize, .evsel = evsel, .options = options, }; @@ -2644,6 +2621,8 @@ void annotation__set_offsets(struct annotation *notes, s64 size) struct annotation_line *al; notes->max_line_len = 0; + notes->nr_entries = 0; + notes->nr_asm_entries = 0; list_for_each_entry(al, ¬es->src->source, node) { size_t line_len = strlen(al->line); @@ -2790,7 +2769,7 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; - if (symbol__annotate(ms, evsel, 0, opts, NULL) < 0) + if (symbol__annotate(ms, evsel, opts, NULL) < 0) return -1; symbol__calc_percent(sym, evsel); @@ -2915,9 +2894,9 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati percent = annotation_data__percent(&al->data[i], percent_type); obj__set_percent_color(obj, percent, current_entry); - if (notes->options->show_total_period) { + if (symbol_conf.show_total_period) { obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period); - } else if (notes->options->show_nr_samples) { + } else if (symbol_conf.show_nr_samples) { obj__printf(obj, "%6" PRIu64 " ", al->data[i].he.nr_samples); } else { @@ -2931,8 +2910,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati obj__printf(obj, "%-*s", pcnt_width, " "); else { obj__printf(obj, "%-*s", pcnt_width, - notes->options->show_total_period ? "Period" : - notes->options->show_nr_samples ? "Samples" : "Percent"); + symbol_conf.show_total_period ? "Period" : + symbol_conf.show_nr_samples ? "Samples" : "Percent"); } } @@ -3070,7 +3049,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, if (perf_evsel__is_group_event(evsel)) nr_pcnt = evsel->core.nr_members; - err = symbol__annotate(ms, evsel, 0, options, parch); + err = symbol__annotate(ms, evsel, options, parch); if (err) goto out_free_offsets; @@ -3094,69 +3073,46 @@ out_free_offsets: return err; } -#define ANNOTATION__CFG(n) \ - { .name = #n, .value = &annotation__default_options.n, } - -/* - * Keep the entries sorted, they are bsearch'ed - */ -static struct annotation_config { - const char *name; - void *value; -} annotation__configs[] = { - ANNOTATION__CFG(hide_src_code), - ANNOTATION__CFG(jump_arrows), - ANNOTATION__CFG(offset_level), - ANNOTATION__CFG(show_linenr), - ANNOTATION__CFG(show_nr_jumps), - ANNOTATION__CFG(show_nr_samples), - ANNOTATION__CFG(show_total_period), - ANNOTATION__CFG(use_offset), -}; - -#undef ANNOTATION__CFG - -static int annotation_config__cmp(const void *name, const void *cfgp) -{ - const struct annotation_config *cfg = cfgp; - - return strcmp(name, cfg->name); -} - -static int annotation__config(const char *var, const char *value, - void *data __maybe_unused) +static int annotation__config(const char *var, const char *value, void *data) { - struct annotation_config *cfg; - const char *name; + struct annotation_options *opt = data; if (!strstarts(var, "annotate.")) return 0; - name = var + 9; - cfg = bsearch(name, annotation__configs, ARRAY_SIZE(annotation__configs), - sizeof(struct annotation_config), annotation_config__cmp); - - if (cfg == NULL) - pr_debug("%s variable unknown, ignoring...", var); - else if (strcmp(var, "annotate.offset_level") == 0) { - perf_config_int(cfg->value, name, value); - - if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL) - *(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL; - else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL) - *(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL; + if (!strcmp(var, "annotate.offset_level")) { + perf_config_u8(&opt->offset_level, "offset_level", value); + + if (opt->offset_level > ANNOTATION__MAX_OFFSET_LEVEL) + opt->offset_level = ANNOTATION__MAX_OFFSET_LEVEL; + else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL) + opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL; + } else if (!strcmp(var, "annotate.hide_src_code")) { + opt->hide_src_code = perf_config_bool("hide_src_code", value); + } else if (!strcmp(var, "annotate.jump_arrows")) { + opt->jump_arrows = perf_config_bool("jump_arrows", value); + } else if (!strcmp(var, "annotate.show_linenr")) { + opt->show_linenr = perf_config_bool("show_linenr", value); + } else if (!strcmp(var, "annotate.show_nr_jumps")) { + opt->show_nr_jumps = perf_config_bool("show_nr_jumps", value); + } else if (!strcmp(var, "annotate.show_nr_samples")) { + symbol_conf.show_nr_samples = perf_config_bool("show_nr_samples", + value); + } else if (!strcmp(var, "annotate.show_total_period")) { + symbol_conf.show_total_period = perf_config_bool("show_total_period", + value); + } else if (!strcmp(var, "annotate.use_offset")) { + opt->use_offset = perf_config_bool("use_offset", value); } else { - *(bool *)cfg->value = perf_config_bool(name, value); + pr_debug("%s variable unknown, ignoring...", var); } + return 0; } -void annotation_config__init(void) +void annotation_config__init(struct annotation_options *opt) { - perf_config(annotation__config, NULL); - - annotation__default_options.show_total_period = symbol_conf.show_total_period; - annotation__default_options.show_nr_samples = symbol_conf.show_nr_samples; + perf_config(annotation__config, opt); } static unsigned int parse_percent_type(char *str1, char *str2) diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 455403e8fede..001258601a37 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -83,8 +83,6 @@ struct annotation_options { full_path, show_linenr, show_nr_jumps, - show_nr_samples, - show_total_period, show_minmax_cycle, show_asm_raw, annotate_src; @@ -141,7 +139,6 @@ struct annotation_line { u64 cycles; u64 cycles_max; u64 cycles_min; - size_t privsize; char *path; u32 idx; int idx_asm; @@ -309,7 +306,7 @@ static inline int annotation__cycles_width(struct annotation *notes) static inline int annotation__pcnt_width(struct annotation *notes) { - return (notes->options->show_total_period ? 12 : 7) * notes->nr_events; + return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events; } static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes) @@ -352,7 +349,7 @@ struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists); void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__annotate(struct map_symbol *ms, - struct evsel *evsel, size_t privsize, + struct evsel *evsel, struct annotation_options *options, struct arch **parch); int symbol__annotate2(struct map_symbol *ms, @@ -413,7 +410,7 @@ static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused, } #endif -void annotation_config__init(void); +void annotation_config__init(struct annotation_options *opt); int annotate_parse_percent_type(const struct option *opt, const char *_str, int unset); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index eb087e7df6f4..3571ce72ca28 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -629,8 +629,10 @@ int auxtrace_record__options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts) { - if (itr) + if (itr) { + itr->evlist = evlist; return itr->recording_options(itr, evlist, opts); + } return 0; } @@ -664,6 +666,24 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, return -EINVAL; } +int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx) +{ + struct evsel *evsel; + + if (!itr->evlist || !itr->pmu) + return -EINVAL; + + evlist__for_each_entry(itr->evlist, evsel) { + if (evsel->core.attr.type == itr->pmu->type) { + if (evsel->disabled) + return 0; + return perf_evlist__enable_event_idx(itr->evlist, evsel, + idx); + } + } + return -EINVAL; +} + /* * Event record size is 16-bit which results in a maximum size of about 64KiB. * Allow about 4KiB for the rest of the sample record, to give a maximum diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 749d72cd9c7b..e58ef160b599 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -29,6 +29,7 @@ struct record_opts; struct perf_record_auxtrace_error; struct perf_record_auxtrace_info; struct events_stats; +struct perf_pmu; enum auxtrace_error_type { PERF_AUXTRACE_ERROR_ITRACE = 1, @@ -322,6 +323,8 @@ struct auxtrace_mmap_params { * @read_finish: called after reading from an auxtrace mmap * @alignment: alignment (if any) for AUX area data * @default_aux_sample_size: default sample size for --aux sample option + * @pmu: associated pmu + * @evlist: selected events list */ struct auxtrace_record { int (*recording_options)(struct auxtrace_record *itr, @@ -346,6 +349,8 @@ struct auxtrace_record { int (*read_finish)(struct auxtrace_record *itr, int idx); unsigned int alignment; unsigned int default_aux_sample_size; + struct perf_pmu *pmu; + struct evlist *evlist; }; /** @@ -537,6 +542,7 @@ int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx, struct auxtrace_mmap *mm, unsigned char *data, u64 *head, u64 *old); u64 auxtrace_record__reference(struct auxtrace_record *itr); +int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx); int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event, off_t file_offset); diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 0bc9c4d7fdc5..ef38eba56ed0 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -374,6 +374,18 @@ int perf_config_int(int *dest, const char *name, const char *value) return 0; } +int perf_config_u8(u8 *dest, const char *name, const char *value) +{ + long ret = 0; + + if (!perf_parse_long(value, &ret)) { + bad_config(name); + return -1; + } + *dest = ret; + return 0; +} + static int perf_config_bool_or_int(const char *name, const char *value, int *is_bool) { int ret; diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index bd0a5897c76a..c10b66dde2f3 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -29,6 +29,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *); int perf_default_config(const char *, const char *, void *); int perf_config(config_fn_t fn, void *); int perf_config_int(int *dest, const char *, const char *); +int perf_config_u8(u8 *dest, const char *name, const char *value); int perf_config_u64(u64 *dest, const char *, const char *); int perf_config_bool(const char *, const char *); int config_error_nonbool(const char *); diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 5003ba403345..0f5fda11675f 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -301,10 +301,15 @@ int probe_file__get_events(int fd, struct strfilter *filter, p = strchr(ent->s, ':'); if ((p && strfilter__compare(filter, p + 1)) || strfilter__compare(filter, ent->s)) { - strlist__add(plist, ent->s); + ret = strlist__add(plist, ent->s); + if (ret == -ENOMEM) { + pr_err("strlist__add failed with -ENOMEM\n"); + goto out; + } ret = 0; } } +out: strlist__delete(namelist); return ret; @@ -511,7 +516,11 @@ static int probe_cache__load(struct probe_cache *pcache) ret = -EINVAL; goto out; } - strlist__add(entry->tevlist, buf); + ret = strlist__add(entry->tevlist, buf); + if (ret == -ENOMEM) { + pr_err("strlist__add failed with -ENOMEM\n"); + goto out; + } } } out: @@ -672,7 +681,12 @@ int probe_cache__add_entry(struct probe_cache *pcache, command = synthesize_probe_trace_command(&tevs[i]); if (!command) goto out_err; - strlist__add(entry->tevlist, command); + ret = strlist__add(entry->tevlist, command); + if (ret == -ENOMEM) { + pr_err("strlist__add failed with -ENOMEM\n"); + goto out_err; + } + free(command); } list_add_tail(&entry->node, &pcache->entries); @@ -853,9 +867,15 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname) break; } - strlist__add(entry->tevlist, buf); + ret = strlist__add(entry->tevlist, buf); + free(buf); entry = NULL; + + if (ret == -ENOMEM) { + pr_err("strlist__add failed with -ENOMEM\n"); + break; + } } if (entry) { list_del_init(&entry->node); diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index e59eb9e7f923..180ad1e1b04f 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -24,6 +24,8 @@ KunitResult = namedtuple('KunitResult', ['status','result']) KunitRequest = namedtuple('KunitRequest', ['raw_output','timeout', 'jobs', 'build_dir', 'defconfig']) +KernelDirectoryPath = sys.argv[0].split('tools/testing/kunit/')[0] + class KunitStatus(Enum): SUCCESS = auto() CONFIG_FAILURE = auto() @@ -35,6 +37,13 @@ def create_default_kunitconfig(): shutil.copyfile('arch/um/configs/kunit_defconfig', kunit_kernel.kunitconfig_path) +def get_kernel_root_path(): + parts = sys.argv[0] if not __file__ else __file__ + parts = os.path.realpath(parts).split('tools/testing/kunit') + if len(parts) != 2: + sys.exit(1) + return parts[0] + def run_tests(linux: kunit_kernel.LinuxSourceTree, request: KunitRequest) -> KunitResult: config_start = time.time() @@ -114,6 +123,9 @@ def main(argv, linux=None): cli_args = parser.parse_args(argv) if cli_args.subcommand == 'run': + if get_kernel_root_path(): + os.chdir(get_kernel_root_path()) + if cli_args.build_dir: if not os.path.exists(cli_args.build_dir): os.mkdir(cli_args.build_dir) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index cc5d844ecca1..d99ae75ef72f 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -93,6 +93,20 @@ class LinuxSourceTree(object): return False return True + def validate_config(self, build_dir): + kconfig_path = get_kconfig_path(build_dir) + validated_kconfig = kunit_config.Kconfig() + validated_kconfig.read_from_file(kconfig_path) + if not self._kconfig.is_subset_of(validated_kconfig): + invalid = self._kconfig.entries() - validated_kconfig.entries() + message = 'Provided Kconfig is not contained in validated .config. Following fields found in kunitconfig, ' \ + 'but not in .config: %s' % ( + ', '.join([str(e) for e in invalid]) + ) + logging.error(message) + return False + return True + def build_config(self, build_dir): kconfig_path = get_kconfig_path(build_dir) if build_dir and not os.path.exists(build_dir): @@ -103,12 +117,7 @@ class LinuxSourceTree(object): except ConfigError as e: logging.error(e) return False - validated_kconfig = kunit_config.Kconfig() - validated_kconfig.read_from_file(kconfig_path) - if not self._kconfig.is_subset_of(validated_kconfig): - logging.error('Provided Kconfig is not contained in validated .config!') - return False - return True + return self.validate_config(build_dir) def build_reconfig(self, build_dir): """Creates a new .config if it is not a subset of the .kunitconfig.""" @@ -133,12 +142,7 @@ class LinuxSourceTree(object): except (ConfigError, BuildError) as e: logging.error(e) return False - used_kconfig = kunit_config.Kconfig() - used_kconfig.read_from_file(get_kconfig_path(build_dir)) - if not self._kconfig.is_subset_of(used_kconfig): - logging.error('Provided Kconfig is not contained in final config!') - return False - return True + return self.validate_config(build_dir) def run_kernel(self, args=[], timeout=None, build_dir=''): args.extend(['mem=256M']) diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index cd1f5b3a7774..d6e106fbce11 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -2,7 +2,7 @@ all: TEST_PROGS := ftracetest -TEST_FILES := test.d +TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* include ../lib.mk diff --git a/tools/testing/selftests/livepatch/Makefile b/tools/testing/selftests/livepatch/Makefile index 3876d8d62494..1acc9e1fa3fb 100644 --- a/tools/testing/selftests/livepatch/Makefile +++ b/tools/testing/selftests/livepatch/Makefile @@ -8,4 +8,6 @@ TEST_PROGS := \ test-state.sh \ test-ftrace.sh +TEST_FILES := settings + include ../lib.mk diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 93de52016dde..ba450e62dc5b 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -8,6 +8,8 @@ TEST_PROGS := mptcp_connect.sh TEST_GEN_FILES = mptcp_connect +TEST_FILES := settings + EXTRA_CLEAN := *.pcap include ../../lib.mk diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh index aca21dde102a..5a4938d6dcf2 100755 --- a/tools/testing/selftests/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -13,11 +13,12 @@ KSELFTEST_SKIP=4 # Available test groups: +# - reported_issues: check for issues that were reported in the past # - correctness: check that packets match given entries, and only those # - concurrency: attempt races between insertion, deletion and lookup # - timeout: check that packets match entries until they expire # - performance: estimate matching rate, compare with rbtree and hash baselines -TESTS="correctness concurrency timeout" +TESTS="reported_issues correctness concurrency timeout" [ "${quicktest}" != "1" ] && TESTS="${TESTS} performance" # Set types, defined by TYPE_ variables below @@ -25,6 +26,9 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port net_port_mac_proto_net" +# Reported bugs, also described by TYPE_ variables below +BUGS="flush_remove_add" + # List of possible paths to pktgen script from kernel tree for performance tests PKTGEN_SCRIPT_PATHS=" ../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh @@ -327,6 +331,12 @@ flood_spec ip daddr . tcp dport . meta l4proto . ip saddr perf_duration 0 " +# Definition of tests for bugs reported in the past: +# display display text for test report +TYPE_flush_remove_add=" +display Add two elements, flush, re-add +" + # Set template for all tests, types and rules are filled in depending on test set_template=' flush ruleset @@ -440,6 +450,8 @@ setup_set() { # Check that at least one of the needed tools is available check_tools() { + [ -z "${tools}" ] && return 0 + __tools= for tool in ${tools}; do if [ "${tool}" = "nc" ] && [ "${proto}" = "udp6" ] && \ @@ -1025,7 +1037,7 @@ format_noconcat() { add() { if ! nft add element inet filter test "${1}"; then err "Failed to add ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1045,7 +1057,7 @@ add_perf() { add_perf_norange() { if ! nft add element netdev perf norange "${1}"; then err "Failed to add ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1054,7 +1066,7 @@ add_perf_norange() { add_perf_noconcat() { if ! nft add element netdev perf noconcat "${1}"; then err "Failed to add ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1063,7 +1075,7 @@ add_perf_noconcat() { del() { if ! nft delete element inet filter test "${1}"; then err "Failed to delete ${1} given ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1134,7 +1146,7 @@ send_match() { err " $(for f in ${src}; do eval format_\$f "${2}"; printf ' '; done)" err "should have matched ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi nft reset counter inet filter test >/dev/null @@ -1160,7 +1172,7 @@ send_nomatch() { err " $(for f in ${src}; do eval format_\$f "${2}"; printf ' '; done)" err "should not have matched ruleset:" - err "$(nft list ruleset -a)" + err "$(nft -a list ruleset)" return 1 fi } @@ -1430,6 +1442,23 @@ test_performance() { kill "${perf_pid}" } +test_bug_flush_remove_add() { + set_cmd='{ set s { type ipv4_addr . inet_service; flags interval; }; }' + elem1='{ 10.0.0.1 . 22-25, 10.0.0.1 . 10-20 }' + elem2='{ 10.0.0.1 . 10-20, 10.0.0.1 . 22-25 }' + for i in `seq 1 100`; do + nft add table t ${set_cmd} || return ${KSELFTEST_SKIP} + nft add element t s ${elem1} 2>/dev/null || return 1 + nft flush set t s 2>/dev/null || return 1 + nft add element t s ${elem2} 2>/dev/null || return 1 + done + nft flush ruleset +} + +test_reported_issues() { + eval test_bug_"${subtest}" +} + # Run everything in a separate network namespace [ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; } tmp="$(mktemp)" @@ -1438,9 +1467,15 @@ trap cleanup EXIT # Entry point for test runs passed=0 for name in ${TESTS}; do - printf "TEST: %s\n" "${name}" - for type in ${TYPES}; do - eval desc=\$TYPE_"${type}" + printf "TEST: %s\n" "$(echo ${name} | tr '_' ' ')" + if [ "${name}" = "reported_issues" ]; then + SUBTESTS="${BUGS}" + else + SUBTESTS="${TYPES}" + fi + + for subtest in ${SUBTESTS}; do + eval desc=\$TYPE_"${subtest}" IFS=' ' for __line in ${desc}; do diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index d6469535630a..2af9d39a9716 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -4,7 +4,7 @@ ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) CLANG_FLAGS += -no-integrated-as endif -CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L./ -Wl,-rpath=./ \ +CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \ $(CLANG_FLAGS) LDLIBS += -lpthread @@ -19,6 +19,8 @@ TEST_GEN_PROGS_EXTENDED = librseq.so TEST_PROGS = run_param_test.sh +TEST_FILES := settings + include ../lib.mk $(OUTPUT)/librseq.so: rseq.c rseq.h rseq-*.h diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile index 2d93d65723c9..55198ecc04db 100644 --- a/tools/testing/selftests/rtc/Makefile +++ b/tools/testing/selftests/rtc/Makefile @@ -6,4 +6,6 @@ TEST_GEN_PROGS = rtctest TEST_GEN_PROGS_EXTENDED = setdate +TEST_FILES := settings + include ../lib.mk diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index d65a0faa46d8..eda7b624eab8 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -742,9 +742,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) guest_enter_irqoff(); if (has_vhe()) { - kvm_arm_vhe_guest_enter(); ret = kvm_vcpu_run_vhe(vcpu); - kvm_arm_vhe_guest_exit(); } else { ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu); } diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h index 204d210d01c2..cc94ccc68821 100644 --- a/virt/kvm/arm/trace.h +++ b/virt/kvm/arm/trace.h @@ -4,6 +4,7 @@ #include <kvm/arm_arch_timer.h> #include <linux/tracepoint.h> +#include <asm/kvm_arm.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm |