diff options
440 files changed, 4280 insertions, 2482 deletions
diff --git a/Documentation/arch/arm64/cpu-feature-registers.rst b/Documentation/arch/arm64/cpu-feature-registers.rst index 4e4625f2455f..de6d8a4790e2 100644 --- a/Documentation/arch/arm64/cpu-feature-registers.rst +++ b/Documentation/arch/arm64/cpu-feature-registers.rst @@ -175,6 +175,8 @@ infrastructure: +------------------------------+---------+---------+ | Name | bits | visible | +------------------------------+---------+---------+ + | SME | [27-24] | y | + +------------------------------+---------+---------+ | MTE | [11-8] | y | +------------------------------+---------+---------+ | SSBS | [7-4] | y | @@ -288,8 +290,18 @@ infrastructure: +------------------------------+---------+---------+ | Name | bits | visible | +------------------------------+---------+---------+ + | CSSC | [55-52] | y | + +------------------------------+---------+---------+ + | RPRFM | [51-48] | y | + +------------------------------+---------+---------+ + | BC | [23-20] | y | + +------------------------------+---------+---------+ | MOPS | [19-16] | y | +------------------------------+---------+---------+ + | APA3 | [15-12] | y | + +------------------------------+---------+---------+ + | GPA3 | [11-8] | y | + +------------------------------+---------+---------+ | RPRES | [7-4] | y | +------------------------------+---------+---------+ | WFXT | [3-0] | y | diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index 8c8addb4194c..76ff9d7398fd 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -305,6 +305,9 @@ HWCAP2_SMEF16F16 HWCAP2_MOPS Functionality implied by ID_AA64ISAR2_EL1.MOPS == 0b0001. +HWCAP2_HBC + Functionality implied by ID_AA64ISAR2_EL1.BC == 0b0001. + 4. Unused AT_HWCAP bits ----------------------- diff --git a/Documentation/arch/loongarch/introduction.rst b/Documentation/arch/loongarch/introduction.rst index 49135d451ced..8c568cfc2107 100644 --- a/Documentation/arch/loongarch/introduction.rst +++ b/Documentation/arch/loongarch/introduction.rst @@ -381,9 +381,9 @@ Documentation of LoongArch ISA: Documentation of LoongArch ELF psABI: - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.00-CN.pdf (in Chinese) + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.01-CN.pdf (in Chinese) - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.00-EN.pdf (in English) + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.01-EN.pdf (in English) Linux kernel repository of Loongson and LoongArch: diff --git a/Documentation/networking/ax25.rst b/Documentation/networking/ax25.rst index f060cfb1445a..605e72c6c877 100644 --- a/Documentation/networking/ax25.rst +++ b/Documentation/networking/ax25.rst @@ -7,9 +7,9 @@ AX.25 To use the amateur radio protocols within Linux you will need to get a suitable copy of the AX.25 Utilities. More detailed information about AX.25, NET/ROM and ROSE, associated programs and utilities can be -found on http://www.linux-ax25.org. +found on https://linux-ax25.in-berlin.de. -There is an active mailing list for discussing Linux amateur radio matters +There is a mailing list for discussing Linux amateur radio matters called linux-hams@vger.kernel.org. To subscribe to it, send a message to majordomo@vger.kernel.org with the words "subscribe linux-hams" in the body of the message, the subject field is ignored. You don't need to be diff --git a/Documentation/sound/designs/midi-2.0.rst b/Documentation/sound/designs/midi-2.0.rst index 45987f256b97..086487ca7ab1 100644 --- a/Documentation/sound/designs/midi-2.0.rst +++ b/Documentation/sound/designs/midi-2.0.rst @@ -74,8 +74,8 @@ topology based on those information. When the device is older and doesn't respond to the new UMP inquiries, the driver falls back and builds the topology based on Group Terminal Block (GTB) information from the USB descriptor. Some device might be screwed up by the -unexpected UMP command; in such a case, pass `midi2_probe=0` option to -snd-usb-audio driver for skipping the UMP v1.1 inquiries. +unexpected UMP command; in such a case, pass `midi2_ump_probe=0` +option to snd-usb-audio driver for skipping the UMP v1.1 inquiries. When the MIDI 2.0 device is probed, the kernel creates a rawmidi device for each UMP Endpoint of the device. Its device name is diff --git a/Documentation/translations/zh_CN/arch/loongarch/introduction.rst b/Documentation/translations/zh_CN/arch/loongarch/introduction.rst index cba04befc950..59d6bf33050c 100644 --- a/Documentation/translations/zh_CN/arch/loongarch/introduction.rst +++ b/Documentation/translations/zh_CN/arch/loongarch/introduction.rst @@ -344,9 +344,9 @@ LoongArch指令集架构的文档： LoongArch的ELF psABI文档： - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.00-CN.pdf （中文版） + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.01-CN.pdf （中文版） - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.00-EN.pdf （英文版） + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-ELF-ABI-v2.01-EN.pdf （英文版） Loongson与LoongArch的Linux内核源码仓库： diff --git a/MAINTAINERS b/MAINTAINERS index bf0f54c24f81..b19995690904 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1662,7 +1662,7 @@ F: arch/arm*/include/asm/perf_event.h F: arch/arm*/kernel/hw_breakpoint.c F: arch/arm*/kernel/perf_* F: drivers/perf/ -F: include/linux/perf/arm_pmu.h +F: include/linux/perf/arm_pmu*.h ARM PORT M: Russell King <linux@armlinux.org.uk> @@ -3344,7 +3344,7 @@ AX.25 NETWORK LAYER M: Ralf Baechle <ralf@linux-mips.org> L: linux-hams@vger.kernel.org S: Maintained -W: http://www.linux-ax25.org/ +W: https://linux-ax25.in-berlin.de F: include/net/ax25.h F: include/uapi/linux/ax25.h F: net/ax25/ @@ -6645,7 +6645,6 @@ F: Documentation/devicetree/bindings/display/panel/novatek,nt36672a.yaml F: drivers/gpu/drm/panel/panel-novatek-nt36672a.c DRM DRIVER FOR NVIDIA GEFORCE/QUADRO GPUS -M: Ben Skeggs <bskeggs@redhat.com> M: Karol Herbst <kherbst@redhat.com> M: Lyude Paul <lyude@redhat.com> L: dri-devel@lists.freedesktop.org @@ -8874,7 +8873,7 @@ F: drivers/gpio/gpio-mockup.c F: tools/testing/selftests/gpio/ GPIO REGMAP -R: Michael Walle <michael@walle.cc> +M: Michael Walle <michael@walle.cc> S: Maintained F: drivers/gpio/gpio-regmap.c F: include/linux/gpio/regmap.h @@ -13616,6 +13615,7 @@ F: drivers/net/ethernet/mellanox/mlxfw/ MELLANOX HARDWARE PLATFORM SUPPORT M: Hans de Goede <hdegoede@redhat.com> +M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com> M: Mark Gross <markgross@kernel.org> M: Vadim Pasternak <vadimp@nvidia.com> L: platform-driver-x86@vger.kernel.org @@ -14210,6 +14210,7 @@ F: drivers/platform/surface/surface_gpe.c MICROSOFT SURFACE HARDWARE PLATFORM SUPPORT M: Hans de Goede <hdegoede@redhat.com> +M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com> M: Mark Gross <markgross@kernel.org> M: Maximilian Luz <luzmaximilian@gmail.com> L: platform-driver-x86@vger.kernel.org @@ -14756,7 +14757,7 @@ NETROM NETWORK LAYER M: Ralf Baechle <ralf@linux-mips.org> L: linux-hams@vger.kernel.org S: Maintained -W: http://www.linux-ax25.org/ +W: https://linux-ax25.in-berlin.de F: include/net/netrom.h F: include/uapi/linux/netrom.h F: net/netrom/ @@ -18607,7 +18608,7 @@ ROSE NETWORK LAYER M: Ralf Baechle <ralf@linux-mips.org> L: linux-hams@vger.kernel.org S: Maintained -W: http://www.linux-ax25.org/ +W: https://linux-ax25.in-berlin.de F: include/net/rose.h F: include/uapi/linux/rose.h F: net/rose/ @@ -23423,9 +23424,11 @@ F: drivers/platform/x86/x86-android-tablets/ X86 PLATFORM DRIVERS M: Hans de Goede <hdegoede@redhat.com> +M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com> M: Mark Gross <markgross@kernel.org> L: platform-driver-x86@vger.kernel.org S: Maintained +Q: https://patchwork.kernel.org/project/platform-driver-x86/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86.git F: drivers/platform/olpc/ F: drivers/platform/x86/ @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 7d59765aef22..c392e18f1e43 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -207,7 +207,7 @@ static void xen_power_off(void) static irqreturn_t xen_arm_callback(int irq, void *arg) { - xen_hvm_evtchn_do_upcall(); + xen_evtchn_do_upcall(); return IRQ_HANDLED; } diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 96e50227f940..5bba39376055 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -663,7 +663,7 @@ static inline bool supports_clearbhb(int scope) isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); return cpuid_feature_extract_unsigned_field(isar2, - ID_AA64ISAR2_EL1_BC_SHIFT); + ID_AA64ISAR2_EL1_CLRBHB_SHIFT); } const struct cpumask *system_32bit_el0_cpumask(void); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index b66ef77cf49e..13c948a0502d 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -54,6 +54,11 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu); int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2); int kvm_inject_nested_irq(struct kvm_vcpu *vcpu); +static inline bool vcpu_has_feature(const struct kvm_vcpu *vcpu, int feature) +{ + return test_bit(feature, vcpu->kvm->arch.vcpu_features); +} + #if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__) static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { @@ -62,7 +67,7 @@ static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) #else static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) { - return test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features); + return vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); } #endif @@ -565,12 +570,6 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) vcpu_set_flag((v), e); \ } while (0) - -static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature) -{ - return test_bit(feature, vcpu->arch.features); -} - static __always_inline void kvm_write_cptr_el2(u64 val) { if (has_vhe() || has_hvhe()) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 4b5a57a60b6a..6a0b6f3b6f41 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -78,7 +78,7 @@ extern unsigned int __ro_after_init kvm_sve_max_vl; int __init kvm_arm_init_sve(void); u32 __attribute_const__ kvm_target_cpu(void); -int kvm_reset_vcpu(struct kvm_vcpu *vcpu); +void kvm_reset_vcpu(struct kvm_vcpu *vcpu); void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu); struct kvm_hyp_memcache { @@ -158,6 +158,16 @@ struct kvm_s2_mmu { phys_addr_t pgd_phys; struct kvm_pgtable *pgt; + /* + * VTCR value used on the host. For a non-NV guest (or a NV + * guest that runs in a context where its own S2 doesn't + * apply), its T0SZ value reflects that of the IPA size. + * + * For a shadow S2 MMU, T0SZ reflects the PARange exposed to + * the guest. + */ + u64 vtcr; + /* The last vcpu id that ran on each physical CPU */ int __percpu *last_vcpu_ran; @@ -230,9 +240,6 @@ static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr) struct kvm_arch { struct kvm_s2_mmu mmu; - /* VTCR_EL2 value for this VM */ - u64 vtcr; - /* Interrupt controller */ struct vgic_dist vgic; @@ -264,10 +271,8 @@ struct kvm_arch { #define KVM_ARCH_FLAG_VM_COUNTER_OFFSET 5 /* Timer PPIs made immutable */ #define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE 6 - /* SMCCC filter initialized for the VM */ -#define KVM_ARCH_FLAG_SMCCC_FILTER_CONFIGURED 7 /* Initial ID reg values loaded */ -#define KVM_ARCH_FLAG_ID_REGS_INITIALIZED 8 +#define KVM_ARCH_FLAG_ID_REGS_INITIALIZED 7 unsigned long flags; /* VM-wide vCPU feature set */ @@ -602,9 +607,6 @@ struct kvm_vcpu_arch { /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; - /* feature flags */ - DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES); - /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; @@ -1053,7 +1055,7 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, extern unsigned int __ro_after_init kvm_arm_vmid_bits; int __init kvm_arm_vmid_alloc_init(void); void __init kvm_arm_vmid_alloc_free(void); -void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid); +bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid); void kvm_arm_vmid_clear_active(void); static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) @@ -1137,8 +1139,8 @@ static inline bool kvm_set_pmuserenr(u64 val) } #endif -void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu); -void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu); +void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu); +void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu); int __init kvm_set_ipa_limit(void); diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index b7238c72a04c..145ce73fc16c 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -93,6 +93,8 @@ void __timer_disable_traps(struct kvm_vcpu *vcpu); void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt); void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt); #else +void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu); +void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu); void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt); void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt); void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt); @@ -111,14 +113,9 @@ void __fpsimd_save_state(struct user_fpsimd_state *fp_regs); void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs); void __sve_restore_state(void *sve_pffr, u32 *fpsr); -#ifndef __KVM_NVHE_HYPERVISOR__ -void activate_traps_vhe_load(struct kvm_vcpu *vcpu); -void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu); -#endif - u64 __guest_enter(struct kvm_vcpu *vcpu); -bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt); +bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id); #ifdef __KVM_NVHE_HYPERVISOR__ void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr, diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 96a80e8f6226..d86c8661200a 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -150,9 +150,9 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v) */ #define KVM_PHYS_SHIFT (40) -#define kvm_phys_shift(kvm) VTCR_EL2_IPA(kvm->arch.vtcr) -#define kvm_phys_size(kvm) (_AC(1, ULL) << kvm_phys_shift(kvm)) -#define kvm_phys_mask(kvm) (kvm_phys_size(kvm) - _AC(1, ULL)) +#define kvm_phys_shift(mmu) VTCR_EL2_IPA((mmu)->vtcr) +#define kvm_phys_size(mmu) (_AC(1, ULL) << kvm_phys_shift(mmu)) +#define kvm_phys_mask(mmu) (kvm_phys_size(mmu) - _AC(1, ULL)) #include <asm/kvm_pgtable.h> #include <asm/stage2_pgtable.h> @@ -224,16 +224,41 @@ static inline void __clean_dcache_guest_page(void *va, size_t size) kvm_flush_dcache_to_poc(va, size); } +static inline size_t __invalidate_icache_max_range(void) +{ + u8 iminline; + u64 ctr; + + asm volatile(ALTERNATIVE_CB("movz %0, #0\n" + "movk %0, #0, lsl #16\n" + "movk %0, #0, lsl #32\n" + "movk %0, #0, lsl #48\n", + ARM64_ALWAYS_SYSTEM, + kvm_compute_final_ctr_el0) + : "=r" (ctr)); + + iminline = SYS_FIELD_GET(CTR_EL0, IminLine, ctr) + 2; + return MAX_DVM_OPS << iminline; +} + static inline void __invalidate_icache_guest_page(void *va, size_t size) { - if (icache_is_aliasing()) { - /* any kind of VIPT cache */ + /* + * VPIPT I-cache maintenance must be done from EL2. See comment in the + * nVHE flavor of __kvm_tlb_flush_vmid_ipa(). + */ + if (icache_is_vpipt() && read_sysreg(CurrentEL) != CurrentEL_EL2) + return; + + /* + * Blow the whole I-cache if it is aliasing (i.e. VIPT) or the + * invalidation range exceeds our arbitrary limit on invadations by + * cache line. + */ + if (icache_is_aliasing() || size > __invalidate_icache_max_range()) icache_inval_all_pou(); - } else if (read_sysreg(CurrentEL) != CurrentEL_EL1 || - !icache_is_vpipt()) { - /* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */ + else icache_inval_pou((unsigned long)va, (unsigned long)va + size); - } } void kvm_set_way_flush(struct kvm_vcpu *vcpu); @@ -299,7 +324,7 @@ static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu) static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu, struct kvm_arch *arch) { - write_sysreg(arch->vtcr, vtcr_el2); + write_sysreg(mmu->vtcr, vtcr_el2); write_sysreg(kvm_get_vttbr(mmu), vttbr_el2); /* diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index fa23cc9c2adc..6cec8e9c6c91 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -2,13 +2,14 @@ #ifndef __ARM64_KVM_NESTED_H #define __ARM64_KVM_NESTED_H +#include <asm/kvm_emulate.h> #include <linux/kvm_host.h> static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu) { return (!__is_defined(__KVM_NVHE_HYPERVISOR__) && cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) && - test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features)); + vcpu_has_feature(vcpu, KVM_ARM_VCPU_HAS_EL2)); } extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h index c8dca8ae359c..23d27623e478 100644 --- a/arch/arm64/include/asm/stage2_pgtable.h +++ b/arch/arm64/include/asm/stage2_pgtable.h @@ -21,13 +21,13 @@ * (IPA_SHIFT - 4). */ #define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4) -#define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr) +#define kvm_stage2_levels(mmu) VTCR_EL2_LVLS((mmu)->vtcr) /* * kvm_mmmu_cache_min_pages() is the number of pages required to install * a stage-2 translation. We pre-allocate the entry level page table at * the VM creation. */ -#define kvm_mmu_cache_min_pages(kvm) (kvm_stage2_levels(kvm) - 1) +#define kvm_mmu_cache_min_pages(mmu) (kvm_stage2_levels(mmu) - 1) #endif /* __ARM64_S2_PGTABLE_H_ */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 38296579a4fd..5e65f51c10d2 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -270,6 +270,8 @@ /* ETM */ #define SYS_TRCOSLAR sys_reg(2, 1, 1, 0, 4) +#define SYS_BRBCR_EL2 sys_reg(2, 4, 9, 0, 0) + #define SYS_MIDR_EL1 sys_reg(3, 0, 0, 0, 0) #define SYS_MPIDR_EL1 sys_reg(3, 0, 0, 0, 5) #define SYS_REVIDR_EL1 sys_reg(3, 0, 0, 0, 6) @@ -484,6 +486,7 @@ #define SYS_SCTLR_EL2 sys_reg(3, 4, 1, 0, 0) #define SYS_ACTLR_EL2 sys_reg(3, 4, 1, 0, 1) +#define SYS_SCTLR2_EL2 sys_reg(3, 4, 1, 0, 3) #define SYS_HCR_EL2 sys_reg(3, 4, 1, 1, 0) #define SYS_MDCR_EL2 sys_reg(3, 4, 1, 1, 1) #define SYS_CPTR_EL2 sys_reg(3, 4, 1, 1, 2) @@ -497,10 +500,15 @@ #define SYS_VTCR_EL2 sys_reg(3, 4, 2, 1, 2) #define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1) +#define SYS_VNCR_EL2 sys_reg(3, 4, 2, 2, 0) #define SYS_HAFGRTR_EL2 sys_reg(3, 4, 3, 1, 6) #define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0) #define SYS_ELR_EL2 sys_reg(3, 4, 4, 0, 1) #define SYS_SP_EL1 sys_reg(3, 4, 4, 1, 0) +#define SYS_SPSR_irq sys_reg(3, 4, 4, 3, 0) +#define SYS_SPSR_abt sys_reg(3, 4, 4, 3, 1) +#define SYS_SPSR_und sys_reg(3, 4, 4, 3, 2) +#define SYS_SPSR_fiq sys_reg(3, 4, 4, 3, 3) #define SYS_IFSR32_EL2 sys_reg(3, 4, 5, 0, 1) #define SYS_AFSR0_EL2 sys_reg(3, 4, 5, 1, 0) #define SYS_AFSR1_EL2 sys_reg(3, 4, 5, 1, 1) @@ -514,6 +522,18 @@ #define SYS_MAIR_EL2 sys_reg(3, 4, 10, 2, 0) #define SYS_AMAIR_EL2 sys_reg(3, 4, 10, 3, 0) +#define SYS_MPAMHCR_EL2 sys_reg(3, 4, 10, 4, 0) +#define SYS_MPAMVPMV_EL2 sys_reg(3, 4, 10, 4, 1) +#define SYS_MPAM2_EL2 sys_reg(3, 4, 10, 5, 0) +#define __SYS__MPAMVPMx_EL2(x) sys_reg(3, 4, 10, 6, x) +#define SYS_MPAMVPM0_EL2 __SYS__MPAMVPMx_EL2(0) +#define SYS_MPAMVPM1_EL2 __SYS__MPAMVPMx_EL2(1) +#define SYS_MPAMVPM2_EL2 __SYS__MPAMVPMx_EL2(2) +#define SYS_MPAMVPM3_EL2 __SYS__MPAMVPMx_EL2(3) +#define SYS_MPAMVPM4_EL2 __SYS__MPAMVPMx_EL2(4) +#define SYS_MPAMVPM5_EL2 __SYS__MPAMVPMx_EL2(5) +#define SYS_MPAMVPM6_EL2 __SYS__MPAMVPMx_EL2(6) +#define SYS_MPAMVPM7_EL2 __SYS__MPAMVPMx_EL2(7) #define SYS_VBAR_EL2 sys_reg(3, 4, 12, 0, 0) #define SYS_RVBAR_EL2 sys_reg(3, 4, 12, 0, 1) @@ -562,24 +582,49 @@ #define SYS_CONTEXTIDR_EL2 sys_reg(3, 4, 13, 0, 1) #define SYS_TPIDR_EL2 sys_reg(3, 4, 13, 0, 2) +#define SYS_SCXTNUM_EL2 sys_reg(3, 4, 13, 0, 7) + +#define __AMEV_op2(m) (m & 0x7) +#define __AMEV_CRm(n, m) (n | ((m & 0x8) >> 3)) +#define __SYS__AMEVCNTVOFF0n_EL2(m) sys_reg(3, 4, 13, __AMEV_CRm(0x8, m), __AMEV_op2(m)) +#define SYS_AMEVCNTVOFF0n_EL2(m) __SYS__AMEVCNTVOFF0n_EL2(m) +#define __SYS__AMEVCNTVOFF1n_EL2(m) sys_reg(3, 4, 13, __AMEV_CRm(0xA, m), __AMEV_op2(m)) +#define SYS_AMEVCNTVOFF1n_EL2(m) __SYS__AMEVCNTVOFF1n_EL2(m) #define SYS_CNTVOFF_EL2 sys_reg(3, 4, 14, 0, 3) #define SYS_CNTHCTL_EL2 sys_reg(3, 4, 14, 1, 0) +#define SYS_CNTHP_TVAL_EL2 sys_reg(3, 4, 14, 2, 0) +#define SYS_CNTHP_CTL_EL2 sys_reg(3, 4, 14, 2, 1) +#define SYS_CNTHP_CVAL_EL2 sys_reg(3, 4, 14, 2, 2) +#define SYS_CNTHV_TVAL_EL2 sys_reg(3, 4, 14, 3, 0) +#define SYS_CNTHV_CTL_EL2 sys_reg(3, 4, 14, 3, 1) +#define SYS_CNTHV_CVAL_EL2 sys_reg(3, 4, 14, 3, 2) /* VHE encodings for architectural EL0/1 system registers */ +#define SYS_BRBCR_EL12 sys_reg(2, 5, 9, 0, 0) #define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0) +#define SYS_CPACR_EL12 sys_reg(3, 5, 1, 0, 2) +#define SYS_SCTLR2_EL12 sys_reg(3, 5, 1, 0, 3) +#define SYS_ZCR_EL12 sys_reg(3, 5, 1, 2, 0) +#define SYS_TRFCR_EL12 sys_reg(3, 5, 1, 2, 1) +#define SYS_SMCR_EL12 sys_reg(3, 5, 1, 2, 6) #define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0) #define SYS_TTBR1_EL12 sys_reg(3, 5, 2, 0, 1) #define SYS_TCR_EL12 sys_reg(3, 5, 2, 0, 2) +#define SYS_TCR2_EL12 sys_reg(3, 5, 2, 0, 3) #define SYS_SPSR_EL12 sys_reg(3, 5, 4, 0, 0) #define SYS_ELR_EL12 sys_reg(3, 5, 4, 0, 1) #define SYS_AFSR0_EL12 sys_reg(3, 5, 5, 1, 0) #define SYS_AFSR1_EL12 sys_reg(3, 5, 5, 1, 1) #define SYS_ESR_EL12 sys_reg(3, 5, 5, 2, 0) #define SYS_TFSR_EL12 sys_reg(3, 5, 5, 6, 0) +#define SYS_FAR_EL12 sys_reg(3, 5, 6, 0, 0) +#define SYS_PMSCR_EL12 sys_reg(3, 5, 9, 9, 0) #define SYS_MAIR_EL12 sys_reg(3, 5, 10, 2, 0) #define SYS_AMAIR_EL12 sys_reg(3, 5, 10, 3, 0) #define SYS_VBAR_EL12 sys_reg(3, 5, 12, 0, 0) +#define SYS_CONTEXTIDR_EL12 sys_reg(3, 5, 13, 0, 1) +#define SYS_SCXTNUM_EL12 sys_reg(3, 5, 13, 0, 7) #define SYS_CNTKCTL_EL12 sys_reg(3, 5, 14, 1, 0) #define SYS_CNTP_TVAL_EL02 sys_reg(3, 5, 14, 2, 0) #define SYS_CNTP_CTL_EL02 sys_reg(3, 5, 14, 2, 1) diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index b149cf9f91bc..3431d37e5054 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -333,7 +333,7 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) * This is meant to avoid soft lock-ups on large TLB flushing ranges and not * necessarily a performance improvement. */ -#define MAX_TLBI_OPS PTRS_PER_PTE +#define MAX_DVM_OPS PTRS_PER_PTE /* * __flush_tlb_range_op - Perform TLBI operation upon a range @@ -413,12 +413,12 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, /* * When not uses TLB range ops, we can handle up to - * (MAX_TLBI_OPS - 1) pages; + * (MAX_DVM_OPS - 1) pages; * When uses TLB range ops, we can handle up to * (MAX_TLBI_RANGE_PAGES - 1) pages. */ if ((!system_supports_tlb_range() && - (end - start) >= (MAX_TLBI_OPS * stride)) || + (end - start) >= (MAX_DVM_OPS * stride)) || pages >= MAX_TLBI_RANGE_PAGES) { flush_tlb_mm(vma->vm_mm); return; @@ -451,7 +451,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end { unsigned long addr; - if ((end - start) > (MAX_TLBI_OPS * PAGE_SIZE)) { + if ((end - start) > (MAX_DVM_OPS * PAGE_SIZE)) { flush_tlb_all(); return; } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index b018ae12ff5f..444a73c2e638 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -222,7 +222,8 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CLRBHB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_MOPS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0), diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 1f828f3b854c..6615a08382f1 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -943,7 +943,7 @@ void kvm_timer_sync_user(struct kvm_vcpu *vcpu) unmask_vtimer_irq_user(vcpu); } -int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) +void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; @@ -987,8 +987,6 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) soft_timer_cancel(&map.emul_vtimer->hrtimer); if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer); - - return 0; } static void timer_context_init(struct kvm_vcpu *vcpu, int timerid) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e3d667feecaf..e16c5ebd2991 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -368,7 +368,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* Force users to call KVM_ARM_VCPU_INIT */ vcpu_clear_flag(vcpu, VCPU_INITIALIZED); - bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO; @@ -449,7 +448,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_vgic_load(vcpu); kvm_timer_vcpu_load(vcpu); if (has_vhe()) - kvm_vcpu_load_sysregs_vhe(vcpu); + kvm_vcpu_load_vhe(vcpu); kvm_arch_vcpu_load_fp(vcpu); kvm_vcpu_pmu_restore_guest(vcpu); if (kvm_arm_is_pvtime_enabled(&vcpu->arch)) @@ -473,7 +472,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) kvm_arch_vcpu_put_debug_state_flags(vcpu); kvm_arch_vcpu_put_fp(vcpu); if (has_vhe()) - kvm_vcpu_put_sysregs_vhe(vcpu); + kvm_vcpu_put_vhe(vcpu); kvm_timer_vcpu_put(vcpu); kvm_vgic_put(vcpu); kvm_vcpu_pmu_restore_host(vcpu); @@ -1004,7 +1003,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * making a thread's VMID inactive. So we need to call * kvm_arm_vmid_update() in non-premptible context. */ - kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid); + if (kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid) && + has_vhe()) + __load_stage2(vcpu->arch.hw_mmu, + vcpu->arch.hw_mmu->arch); kvm_pmu_flush_hwstate(vcpu); @@ -1237,6 +1239,30 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, return -EINVAL; } +static unsigned long system_supported_vcpu_features(void) +{ + unsigned long features = KVM_VCPU_VALID_FEATURES; + + if (!cpus_have_final_cap(ARM64_HAS_32BIT_EL1)) + clear_bit(KVM_ARM_VCPU_EL1_32BIT, &features); + + if (!kvm_arm_support_pmu_v3()) + clear_bit(KVM_ARM_VCPU_PMU_V3, &features); + + if (!system_supports_sve()) + clear_bit(KVM_ARM_VCPU_SVE, &features); + + if (!system_has_full_ptr_auth()) { + clear_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, &features); + clear_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features); + } + + if (!cpus_have_final_cap(ARM64_HAS_NESTED_VIRT)) + clear_bit(KVM_ARM_VCPU_HAS_EL2, &features); + + return features; +} + static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { @@ -1251,12 +1277,25 @@ static int kvm_vcpu_init_check_features(struct kvm_vcpu *vcpu, return -ENOENT; } - if (!test_bit(KVM_ARM_VCPU_EL1_32BIT, &features)) - return 0; + if (features & ~system_supported_vcpu_features()) + return -EINVAL; - if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) + /* + * For now make sure that both address/generic pointer authentication + * features are requested by the userspace together. + */ + if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, &features) != + test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features)) + return -EINVAL; + + /* Disallow NV+SVE for the time being */ + if (test_bit(KVM_ARM_VCPU_HAS_EL2, &features) && + test_bit(KVM_ARM_VCPU_SVE, &features)) return -EINVAL; + if (!test_bit(KVM_ARM_VCPU_EL1_32BIT, &features)) + return 0; + /* MTE is incompatible with AArch32 */ if (kvm_has_mte(vcpu->kvm)) return -EINVAL; @@ -1273,7 +1312,8 @@ static bool kvm_vcpu_init_changed(struct kvm_vcpu *vcpu, { unsigned long features = init->features[0]; - return !bitmap_equal(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES); + return !bitmap_equal(vcpu->kvm->arch.vcpu_features, &features, + KVM_VCPU_MAX_FEATURES); } static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu, @@ -1286,21 +1326,17 @@ static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu, mutex_lock(&kvm->arch.config_lock); if (test_bit(KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED, &kvm->arch.flags) && - !bitmap_equal(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES)) + kvm_vcpu_init_changed(vcpu, init)) goto out_unlock; - bitmap_copy(vcpu->arch.features, &features, KVM_VCPU_MAX_FEATURES); + bitmap_copy(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES); /* Now we know what it is, we can reset it. */ - ret = kvm_reset_vcpu(vcpu); - if (ret) { - bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); - goto out_unlock; - } + kvm_reset_vcpu(vcpu); - bitmap_copy(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES); set_bit(KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED, &kvm->arch.flags); vcpu_set_flag(vcpu, VCPU_INITIALIZED); + ret = 0; out_unlock: mutex_unlock(&kvm->arch.config_lock); return ret; @@ -1325,7 +1361,8 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, if (kvm_vcpu_init_changed(vcpu, init)) return -EINVAL; - return kvm_reset_vcpu(vcpu); + kvm_reset_vcpu(vcpu); + return 0; } static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 9ced1bf0c2b7..91cc851a6c75 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -648,15 +648,80 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = { SR_TRAP(SYS_APGAKEYLO_EL1, CGT_HCR_APK), SR_TRAP(SYS_APGAKEYHI_EL1, CGT_HCR_APK), /* All _EL2 registers */ - SR_RANGE_TRAP(sys_reg(3, 4, 0, 0, 0), - sys_reg(3, 4, 3, 15, 7), CGT_HCR_NV), + SR_TRAP(SYS_BRBCR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_VPIDR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_VMPIDR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_SCTLR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_ACTLR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_SCTLR2_EL2, CGT_HCR_NV), + SR_RANGE_TRAP(SYS_HCR_EL2, + SYS_HCRX_EL2, CGT_HCR_NV), + SR_TRAP(SYS_SMPRIMAP_EL2, CGT_HCR_NV), + SR_TRAP(SYS_SMCR_EL2, CGT_HCR_NV), + SR_RANGE_TRAP(SYS_TTBR0_EL2, + SYS_TCR2_EL2, CGT_HCR_NV), + SR_TRAP(SYS_VTTBR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_VTCR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_VNCR_EL2, CGT_HCR_NV), + SR_RANGE_TRAP(SYS_HDFGRTR_EL2, + SYS_HAFGRTR_EL2, CGT_HCR_NV), /* Skip the SP_EL1 encoding... */ SR_TRAP(SYS_SPSR_EL2, CGT_HCR_NV), SR_TRAP(SYS_ELR_EL2, CGT_HCR_NV), - SR_RANGE_TRAP(sys_reg(3, 4, 4, 1, 1), - sys_reg(3, 4, 10, 15, 7), CGT_HCR_NV), - SR_RANGE_TRAP(sys_reg(3, 4, 12, 0, 0), - sys_reg(3, 4, 14, 15, 7), CGT_HCR_NV), + /* Skip SPSR_irq, SPSR_abt, SPSR_und, SPSR_fiq */ + SR_TRAP(SYS_AFSR0_EL2, CGT_HCR_NV), + SR_TRAP(SYS_AFSR1_EL2, CGT_HCR_NV), + SR_TRAP(SYS_ESR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_VSESR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_TFSR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_FAR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_HPFAR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_PMSCR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_MAIR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_AMAIR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_MPAMHCR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_MPAMVPMV_EL2, CGT_HCR_NV), + SR_TRAP(SYS_MPAM2_EL2, CGT_HCR_NV), + SR_RANGE_TRAP(SYS_MPAMVPM0_EL2, + SYS_MPAMVPM7_EL2, CGT_HCR_NV), + /* + * Note that the spec. describes a group of MEC registers + * whose access should not trap, therefore skip the following: + * MECID_A0_EL2, MECID_A1_EL2, MECID_P0_EL2, + * MECID_P1_EL2, MECIDR_EL2, VMECID_A_EL2, + * VMECID_P_EL2. + */ + SR_RANGE_TRAP(SYS_VBAR_EL2, + SYS_RMR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_VDISR_EL2, CGT_HCR_NV), + /* ICH_AP0R<m>_EL2 */ + SR_RANGE_TRAP(SYS_ICH_AP0R0_EL2, + SYS_ICH_AP0R3_EL2, CGT_HCR_NV), + /* ICH_AP1R<m>_EL2 */ + SR_RANGE_TRAP(SYS_ICH_AP1R0_EL2, + SYS_ICH_AP1R3_EL2, CGT_HCR_NV), + SR_TRAP(SYS_ICC_SRE_EL2, CGT_HCR_NV), + SR_RANGE_TRAP(SYS_ICH_HCR_EL2, + SYS_ICH_EISR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_ICH_ELRSR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_ICH_VMCR_EL2, CGT_HCR_NV), + /* ICH_LR<m>_EL2 */ + SR_RANGE_TRAP(SYS_ICH_LR0_EL2, + SYS_ICH_LR15_EL2, CGT_HCR_NV), + SR_TRAP(SYS_CONTEXTIDR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_TPIDR_EL2, CGT_HCR_NV), + SR_TRAP(SYS_SCXTNUM_EL2, CGT_HCR_NV), + /* AMEVCNTVOFF0<n>_EL2, AMEVCNTVOFF1<n>_EL2 */ + SR_RANGE_TRAP(SYS_AMEVCNTVOFF0n_EL2(0), + SYS_AMEVCNTVOFF1n_EL2(15), CGT_HCR_NV), + /* CNT*_EL2 */ + SR_TRAP(SYS_CNTVOFF_EL2, CGT_HCR_NV), + SR_TRAP(SYS_CNTPOFF_EL2, CGT_HCR_NV), + SR_TRAP(SYS_CNTHCTL_EL2, CGT_HCR_NV), + SR_RANGE_TRAP(SYS_CNTHP_TVAL_EL2, + SYS_CNTHP_CVAL_EL2, CGT_HCR_NV), + SR_RANGE_TRAP(SYS_CNTHV_TVAL_EL2, + SYS_CNTHV_CVAL_EL2, CGT_HCR_NV), /* All _EL02, _EL12 registers */ SR_RANGE_TRAP(sys_reg(3, 5, 0, 0, 0), sys_reg(3, 5, 10, 15, 7), CGT_HCR_NV), diff --git a/arch/arm64/kvm/hyp/include/nvhe/ffa.h b/arch/arm64/kvm/hyp/include/nvhe/ffa.h index 1becb10ecd80..d9fd5e6c7d3c 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/ffa.h +++ b/arch/arm64/kvm/hyp/include/nvhe/ffa.h @@ -12,6 +12,6 @@ #define FFA_MAX_FUNC_NUM 0x7F int hyp_ffa_init(void *pages); -bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt); +bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id); #endif /* __KVM_HYP_FFA_H */ diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c index ab4f5d160c58..6e4dba9eadef 100644 --- a/arch/arm64/kvm/hyp/nvhe/ffa.c +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -634,9 +634,8 @@ out_handled: return true; } -bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt) +bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id) { - DECLARE_REG(u64, func_id, host_ctxt, 0); struct arm_smccc_res res; /* diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index 90fade1b032e..1cc06e6797bd 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -57,6 +57,7 @@ __do_hyp_init: cmp x0, #HVC_STUB_HCALL_NR b.lo __kvm_handle_stub_hvc + bic x0, x0, #ARM_SMCCC_CALL_HINTS mov x3, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) cmp x0, x3 b.eq 1f diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 857d9bc04fd4..2385fd03ed87 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -368,6 +368,7 @@ static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) if (static_branch_unlikely(&kvm_protected_mode_initialized)) hcall_min = __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize; + id &= ~ARM_SMCCC_CALL_HINTS; id -= KVM_HOST_SMCCC_ID(0); if (unlikely(id < hcall_min || id >= ARRAY_SIZE(host_hcall))) @@ -392,11 +393,14 @@ static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt) static void handle_host_smc(struct kvm_cpu_context *host_ctxt) { + DECLARE_REG(u64, func_id, host_ctxt, 0); bool handled; - handled = kvm_host_psci_handler(host_ctxt); + func_id &= ~ARM_SMCCC_CALL_HINTS; + + handled = kvm_host_psci_handler(host_ctxt, func_id); if (!handled) - handled = kvm_host_ffa_handler(host_ctxt); + handled = kvm_host_ffa_handler(host_ctxt, func_id); if (!handled) default_host_smc_handler(host_ctxt); diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 9d703441278b..8d0a5834e883 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -129,8 +129,8 @@ static void prepare_host_vtcr(void) parange = kvm_get_parange(id_aa64mmfr0_el1_sys_val); phys_shift = id_aa64mmfr0_parange_to_phys_shift(parange); - host_mmu.arch.vtcr = kvm_get_vtcr(id_aa64mmfr0_el1_sys_val, - id_aa64mmfr1_el1_sys_val, phys_shift); + host_mmu.arch.mmu.vtcr = kvm_get_vtcr(id_aa64mmfr0_el1_sys_val, + id_aa64mmfr1_el1_sys_val, phys_shift); } static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot); @@ -235,7 +235,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd) unsigned long nr_pages; int ret; - nr_pages = kvm_pgtable_stage2_pgd_size(vm->kvm.arch.vtcr) >> PAGE_SHIFT; + nr_pages = kvm_pgtable_stage2_pgd_size(mmu->vtcr) >> PAGE_SHIFT; ret = hyp_pool_init(&vm->pool, hyp_virt_to_pfn(pgd), nr_pages, 0); if (ret) return ret; @@ -295,7 +295,7 @@ int __pkvm_prot_finalize(void) return -EPERM; params->vttbr = kvm_get_vttbr(mmu); - params->vtcr = host_mmu.arch.vtcr; + params->vtcr = mmu->vtcr; params->hcr_el2 |= HCR_VM; /* diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 8033ef353a5d..9d23a51d7f75 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -303,7 +303,7 @@ static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm, { hyp_vm->host_kvm = host_kvm; hyp_vm->kvm.created_vcpus = nr_vcpus; - hyp_vm->kvm.arch.vtcr = host_mmu.arch.vtcr; + hyp_vm->kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr; } static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, @@ -483,7 +483,7 @@ int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva, } vm_size = pkvm_get_hyp_vm_size(nr_vcpus); - pgd_size = kvm_pgtable_stage2_pgd_size(host_mmu.arch.vtcr); + pgd_size = kvm_pgtable_stage2_pgd_size(host_mmu.arch.mmu.vtcr); ret = -ENOMEM; diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c index 24543d2a3490..d57bcb6ab94d 100644 --- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c +++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c @@ -273,9 +273,8 @@ static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_ } } -bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt) +bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id) { - DECLARE_REG(u64, func_id, host_ctxt, 0); unsigned long ret; switch (kvm_host_psci_config.version) { diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index f155b8c9e98c..66b30ef88434 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -1314,7 +1314,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED); - if (!ret) + if (!ret || ret == -EAGAIN) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level); return ret; } @@ -1511,7 +1511,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, kvm_pgtable_force_pte_cb_t force_pte_cb) { size_t pgd_sz; - u64 vtcr = mmu->arch->vtcr; + u64 vtcr = mmu->vtcr; u32 ia_bits = VTCR_EL2_IPA(vtcr); u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 6537f58b1a8c..b0cafd7c5f8f 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -93,12 +93,12 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) NOKPROBE_SYMBOL(__deactivate_traps); /* - * Disable IRQs in {activate,deactivate}_traps_vhe_{load,put}() to + * Disable IRQs in __vcpu_{load,put}_{activate,deactivate}_traps() to * prevent a race condition between context switching of PMUSERENR_EL0 * in __{activate,deactivate}_traps_common() and IPIs that attempts to * update PMUSERENR_EL0. See also kvm_set_pmuserenr(). */ -void activate_traps_vhe_load(struct kvm_vcpu *vcpu) +static void __vcpu_load_activate_traps(struct kvm_vcpu *vcpu) { unsigned long flags; @@ -107,7 +107,7 @@ void activate_traps_vhe_load(struct kvm_vcpu *vcpu) local_irq_restore(flags); } -void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu) +static void __vcpu_put_deactivate_traps(struct kvm_vcpu *vcpu) { unsigned long flags; @@ -116,6 +116,19 @@ void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu) local_irq_restore(flags); } +void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu) +{ + __vcpu_load_switch_sysregs(vcpu); + __vcpu_load_activate_traps(vcpu); + __load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch); +} + +void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu) +{ + __vcpu_put_deactivate_traps(vcpu); + __vcpu_put_switch_sysregs(vcpu); +} + static const exit_handler_fn hyp_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = NULL, [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, @@ -170,17 +183,11 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) sysreg_save_host_state_vhe(host_ctxt); /* - * ARM erratum 1165522 requires us to configure both stage 1 and - * stage 2 translation for the guest context before we clear - * HCR_EL2.TGE. - * - * We have already configured the guest's stage 1 translation in - * kvm_vcpu_load_sysregs_vhe above. We must now call - * __load_stage2 before __activate_traps, because - * __load_stage2 configures stage 2 translation, and - * __activate_traps clear HCR_EL2.TGE (among other things). + * Note that ARM erratum 1165522 requires us to configure both stage 1 + * and stage 2 translation for the guest context before we clear + * HCR_EL2.TGE. The stage 1 and stage 2 guest context has already been + * loaded on the CPU in kvm_vcpu_load_vhe(). */ - __load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch); __activate_traps(vcpu); __kvm_adjust_pc(vcpu); diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c index b35a178e7e0d..8e1e0d5033b6 100644 --- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c @@ -52,7 +52,7 @@ void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); /** - * kvm_vcpu_load_sysregs_vhe - Load guest system registers to the physical CPU + * __vcpu_load_switch_sysregs - Load guest system registers to the physical CPU * * @vcpu: The VCPU pointer * @@ -62,7 +62,7 @@ NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); * and loading system register state early avoids having to load them on * every entry to the VM. */ -void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu) +void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; @@ -92,12 +92,10 @@ void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu) __sysreg_restore_el1_state(guest_ctxt); vcpu_set_flag(vcpu, SYSREGS_ON_CPU); - - activate_traps_vhe_load(vcpu); } /** - * kvm_vcpu_put_sysregs_vhe - Restore host system registers to the physical CPU + * __vcpu_put_switch_syregs - Restore host system registers to the physical CPU * * @vcpu: The VCPU pointer * @@ -107,13 +105,12 @@ void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu) * and deferring saving system register state until we're no longer running the * VCPU avoids having to save them on every exit from the VM. */ -void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu) +void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt; - deactivate_traps_vhe_put(vcpu); __sysreg_save_el1_state(guest_ctxt); __sysreg_save_user_state(guest_ctxt); diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c index 46bd43f61d76..b636b4111dbf 100644 --- a/arch/arm64/kvm/hyp/vhe/tlb.c +++ b/arch/arm64/kvm/hyp/vhe/tlb.c @@ -11,18 +11,25 @@ #include <asm/tlbflush.h> struct tlb_inv_context { - unsigned long flags; - u64 tcr; - u64 sctlr; + struct kvm_s2_mmu *mmu; + unsigned long flags; + u64 tcr; + u64 sctlr; }; static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu, struct tlb_inv_context *cxt) { + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); u64 val; local_irq_save(cxt->flags); + if (vcpu && mmu != vcpu->arch.hw_mmu) + cxt->mmu = vcpu->arch.hw_mmu; + else + cxt->mmu = NULL; + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { /* * For CPUs that are affected by ARM errata 1165522 or 1530923, @@ -66,10 +73,13 @@ static void __tlb_switch_to_host(struct tlb_inv_context *cxt) * We're done with the TLB operation, let's restore the host's * view of HCR_EL2. */ - write_sysreg(0, vttbr_el2); write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); isb(); + /* ... and the stage-2 MMU context that we switched away from */ + if (cxt->mmu) + __load_stage2(cxt->mmu, cxt->mmu->arch); + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { /* Restore the registers to what they were */ write_sysreg_el1(cxt->tcr, SYS_TCR); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 7fb4df0456de..5763d979d8ca 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -133,12 +133,10 @@ static bool kvm_smccc_test_fw_bmap(struct kvm_vcpu *vcpu, u32 func_id) ARM_SMCCC_SMC_64, \ 0, ARM_SMCCC_FUNC_MASK) -static void init_smccc_filter(struct kvm *kvm) +static int kvm_smccc_filter_insert_reserved(struct kvm *kvm) { int r; - mt_init(&kvm->arch.smccc_filter); - /* * Prevent userspace from handling any SMCCC calls in the architecture * range, avoiding the risk of misrepresenting Spectre mitigation status @@ -148,14 +146,25 @@ static void init_smccc_filter(struct kvm *kvm) SMC32_ARCH_RANGE_BEGIN, SMC32_ARCH_RANGE_END, xa_mk_value(KVM_SMCCC_FILTER_HANDLE), GFP_KERNEL_ACCOUNT); - WARN_ON_ONCE(r); + if (r) + goto out_destroy; r = mtree_insert_range(&kvm->arch.smccc_filter, SMC64_ARCH_RANGE_BEGIN, SMC64_ARCH_RANGE_END, xa_mk_value(KVM_SMCCC_FILTER_HANDLE), GFP_KERNEL_ACCOUNT); - WARN_ON_ONCE(r); + if (r) + goto out_destroy; + return 0; +out_destroy: + mtree_destroy(&kvm->arch.smccc_filter); + return r; +} + +static bool kvm_smccc_filter_configured(struct kvm *kvm) +{ + return !mtree_empty(&kvm->arch.smccc_filter); } static int kvm_smccc_set_filter(struct kvm *kvm, struct kvm_smccc_filter __user *uaddr) @@ -184,13 +193,14 @@ static int kvm_smccc_set_filter(struct kvm *kvm, struct kvm_smccc_filter __user goto out_unlock; } + if (!kvm_smccc_filter_configured(kvm)) { + r = kvm_smccc_filter_insert_reserved(kvm); + if (WARN_ON_ONCE(r)) + goto out_unlock; + } + r = mtree_insert_range(&kvm->arch.smccc_filter, start, end, xa_mk_value(filter.action), GFP_KERNEL_ACCOUNT); - if (r) - goto out_unlock; - - set_bit(KVM_ARCH_FLAG_SMCCC_FILTER_CONFIGURED, &kvm->arch.flags); - out_unlock: mutex_unlock(&kvm->arch.config_lock); return r; @@ -201,7 +211,7 @@ static u8 kvm_smccc_filter_get_action(struct kvm *kvm, u32 func_id) unsigned long idx = func_id; void *val; - if (!test_bit(KVM_ARCH_FLAG_SMCCC_FILTER_CONFIGURED, &kvm->arch.flags)) + if (!kvm_smccc_filter_configured(kvm)) return KVM_SMCCC_FILTER_HANDLE; /* @@ -387,7 +397,7 @@ void kvm_arm_init_hypercalls(struct kvm *kvm) smccc_feat->std_hyp_bmap = KVM_ARM_SMCCC_STD_HYP_FEATURES; smccc_feat->vendor_hyp_bmap = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; - init_smccc_filter(kvm); + mt_init(&kvm->arch.smccc_filter); } void kvm_arm_teardown_hypercalls(struct kvm *kvm) @@ -554,7 +564,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { bool wants_02; - wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features); + wants_02 = vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2); switch (val) { case KVM_ARM_PSCI_0_1: diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c index 3dd38a151d2a..200c8019a82a 100644 --- a/arch/arm64/kvm/mmio.c +++ b/arch/arm64/kvm/mmio.c @@ -135,6 +135,9 @@ int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) * volunteered to do so, and bail out otherwise. */ if (!kvm_vcpu_dabt_isvalid(vcpu)) { + trace_kvm_mmio_nisv(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu), + kvm_vcpu_get_hfar(vcpu), fault_ipa); + if (test_bit(KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER, &vcpu->kvm->arch.flags)) { run->exit_reason = KVM_EXIT_ARM_NISV; @@ -143,7 +146,6 @@ int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) return 0; } - kvm_pr_unimpl("Data abort outside memslots with no valid syndrome info\n"); return -ENOSYS; } diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 587a104f66c3..4e41ceed5468 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -652,6 +652,9 @@ int hyp_alloc_private_va_range(size_t size, unsigned long *haddr) mutex_unlock(&kvm_hyp_pgd_mutex); + if (!ret) + *haddr = base; + return ret; } @@ -889,7 +892,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); - kvm->arch.vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift); + mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift); if (mmu->pgt != NULL) { kvm_err("kvm_arch already initialized?\n"); @@ -1064,7 +1067,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, phys_addr_t addr; int ret = 0; struct kvm_mmu_memory_cache cache = { .gfp_zero = __GFP_ZERO }; - struct kvm_pgtable *pgt = kvm->arch.mmu.pgt; + struct kvm_s2_mmu *mmu = &kvm->arch.mmu; + struct kvm_pgtable *pgt = mmu->pgt; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_R | (writable ? KVM_PGTABLE_PROT_W : 0); @@ -1077,7 +1081,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, for (addr = guest_ipa; addr < guest_ipa + size; addr += PAGE_SIZE) { ret = kvm_mmu_topup_memory_cache(&cache, - kvm_mmu_cache_min_pages(kvm)); + kvm_mmu_cache_min_pages(mmu)); if (ret) break; @@ -1295,28 +1299,8 @@ transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot, if (sz < PMD_SIZE) return PAGE_SIZE; - /* - * The address we faulted on is backed by a transparent huge - * page. However, because we map the compound huge page and - * not the individual tail page, we need to transfer the - * refcount to the head page. We have to be careful that the - * THP doesn't start to split while we are adjusting the - * refcounts. - * - * We are sure this doesn't happen, because mmu_invalidate_retry - * was successful and we are holding the mmu_lock, so if this - * THP is trying to split, it will be blocked in the mmu - * notifier before touching any of the pages, specifically - * before being able to call __split_huge_page_refcount(). - * - * We can therefore safely transfer the refcount from PG_tail - * to PG_head and switch the pfn from a tail page to the head - * page accordingly. - */ *ipap &= PMD_MASK; - kvm_release_pfn_clean(pfn); pfn &= ~(PTRS_PER_PMD - 1); - get_page(pfn_to_page(pfn)); *pfnp = pfn; return PMD_SIZE; @@ -1428,7 +1412,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (fault_status != ESR_ELx_FSC_PERM || (logging_active && write_fault)) { ret = kvm_mmu_topup_memory_cache(memcache, - kvm_mmu_cache_min_pages(kvm)); + kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu)); if (ret) return ret; } @@ -1744,7 +1728,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) } /* Userspace should not be able to register out-of-bounds IPAs */ - VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm)); + VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->arch.hw_mmu)); if (fault_status == ESR_ELx_FSC_ACCESS) { handle_access_fault(vcpu, fault_ipa); @@ -2018,7 +2002,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * Prevent userspace from creating a memory region outside of the IPA * space addressable by the KVM guest IPA space. */ - if ((new->base_gfn + new->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT)) + if ((new->base_gfn + new->npages) > (kvm_phys_size(&kvm->arch.mmu) >> PAGE_SHIFT)) return -EFAULT; hva = new->userspace_addr; diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c index 6ff3ec18c925..8350fb8fee0b 100644 --- a/arch/arm64/kvm/pkvm.c +++ b/arch/arm64/kvm/pkvm.c @@ -123,7 +123,7 @@ static int __pkvm_create_hyp_vm(struct kvm *host_kvm) if (host_kvm->created_vcpus < 1) return -EINVAL; - pgd_sz = kvm_pgtable_stage2_pgd_size(host_kvm->arch.vtcr); + pgd_sz = kvm_pgtable_stage2_pgd_size(host_kvm->arch.mmu.vtcr); /* * The PGD pages will be reclaimed using a hyp_memcache which implies diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 3afb281ed8d2..845993bab9d2 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -60,6 +60,23 @@ static u32 kvm_pmu_event_mask(struct kvm *kvm) return __kvm_pmu_event_mask(pmuver); } +u64 kvm_pmu_evtyper_mask(struct kvm *kvm) +{ + u64 mask = ARMV8_PMU_EXCLUDE_EL1 | ARMV8_PMU_EXCLUDE_EL0 | + kvm_pmu_event_mask(kvm); + u64 pfr0 = IDREG(kvm, SYS_ID_AA64PFR0_EL1); + + if (SYS_FIELD_GET(ID_AA64PFR0_EL1, EL2, pfr0)) + mask |= ARMV8_PMU_INCLUDE_EL2; + + if (SYS_FIELD_GET(ID_AA64PFR0_EL1, EL3, pfr0)) + mask |= ARMV8_PMU_EXCLUDE_NS_EL0 | + ARMV8_PMU_EXCLUDE_NS_EL1 | + ARMV8_PMU_EXCLUDE_EL3; + + return mask; +} + /** * kvm_pmc_is_64bit - determine if counter is 64bit * @pmc: counter context @@ -584,6 +601,7 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) struct perf_event *event; struct perf_event_attr attr; u64 eventsel, reg, data; + bool p, u, nsk, nsu; reg = counter_index_to_evtreg(pmc->idx); data = __vcpu_sys_reg(vcpu, reg); @@ -610,13 +628,18 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) !test_bit(eventsel, vcpu->kvm->arch.pmu_filter)) return; + p = data & ARMV8_PMU_EXCLUDE_EL1; + u = data & ARMV8_PMU_EXCLUDE_EL0; + nsk = data & ARMV8_PMU_EXCLUDE_NS_EL1; + nsu = data & ARMV8_PMU_EXCLUDE_NS_EL0; + memset(&attr, 0, sizeof(struct perf_event_attr)); attr.type = arm_pmu->pmu.type; attr.size = sizeof(attr); attr.pinned = 1; attr.disabled = !kvm_pmu_counter_is_enabled(pmc); - attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0; - attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0; + attr.exclude_user = (u != nsu); + attr.exclude_kernel = (p != nsk); attr.exclude_hv = 1; /* Don't count EL2 events */ attr.exclude_host = 1; /* Don't count host events */ attr.config = eventsel; @@ -657,18 +680,13 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, u64 select_idx) { struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx); - u64 reg, mask; + u64 reg; if (!kvm_vcpu_has_pmu(vcpu)) return; - mask = ARMV8_PMU_EVTYPE_MASK; - mask &= ~ARMV8_PMU_EVTYPE_EVENT; - mask |= kvm_pmu_event_mask(vcpu->kvm); - reg = counter_index_to_evtreg(pmc->idx); - - __vcpu_sys_reg(vcpu, reg) = data & mask; + __vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm); kvm_pmu_create_perf_event(pmc); } diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 7a65a35ee4ac..5bb4de162cab 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -73,11 +73,8 @@ int __init kvm_arm_init_sve(void) return 0; } -static int kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu) +static void kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu) { - if (!system_supports_sve()) - return -EINVAL; - vcpu->arch.sve_max_vl = kvm_sve_max_vl; /* @@ -86,8 +83,6 @@ static int kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu) * kvm_arm_vcpu_finalize(), which freezes the configuration. */ vcpu_set_flag(vcpu, GUEST_HAS_SVE); - - return 0; } /* @@ -170,20 +165,9 @@ static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu) memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu)); } -static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) +static void kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) { - /* - * For now make sure that both address/generic pointer authentication - * features are requested by the userspace together and the system - * supports these capabilities. - */ - if (!test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) || - !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features) || - !system_has_full_ptr_auth()) - return -EINVAL; - vcpu_set_flag(vcpu, GUEST_HAS_PTRAUTH); - return 0; } /** @@ -204,10 +188,9 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) * disable preemption around the vcpu reset as we would otherwise race with * preempt notifiers which also call put/load. */ -int kvm_reset_vcpu(struct kvm_vcpu *vcpu) +void kvm_reset_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_reset_state reset_state; - int ret; bool loaded; u32 pstate; @@ -224,29 +207,16 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) if (loaded) kvm_arch_vcpu_put(vcpu); - /* Disallow NV+SVE for the time being */ - if (vcpu_has_nv(vcpu) && vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) { - ret = -EINVAL; - goto out; - } - if (!kvm_arm_vcpu_sve_finalized(vcpu)) { - if (test_bit(KVM_ARM_VCPU_SVE, vcpu->arch.features)) { - ret = kvm_vcpu_enable_sve(vcpu); - if (ret) - goto out; - } + if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) + kvm_vcpu_enable_sve(vcpu); } else { kvm_vcpu_reset_sve(vcpu); } - if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) || - test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) { - if (kvm_vcpu_enable_ptrauth(vcpu)) { - ret = -EINVAL; - goto out; - } - } + if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) || + vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC)) + kvm_vcpu_enable_ptrauth(vcpu); if (vcpu_el1_is_32bit(vcpu)) pstate = VCPU_RESET_PSTATE_SVC; @@ -255,11 +225,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) else pstate = VCPU_RESET_PSTATE_EL1; - if (kvm_vcpu_has_pmu(vcpu) && !kvm_arm_support_pmu_v3()) { - ret = -EINVAL; - goto out; - } - /* Reset core registers */ memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu))); memset(&vcpu->arch.ctxt.fp_regs, 0, sizeof(vcpu->arch.ctxt.fp_regs)); @@ -294,12 +259,11 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) } /* Reset timer */ - ret = kvm_timer_vcpu_reset(vcpu); -out: + kvm_timer_vcpu_reset(vcpu); + if (loaded) kvm_arch_vcpu_load(vcpu, smp_processor_id()); preempt_enable(); - return ret; } u32 get_kvm_ipa_limit(void) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e92ec810d449..1a165186701b 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -746,8 +746,12 @@ static u64 reset_pmevcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { + /* This thing will UNDEF, who cares about the reset value? */ + if (!kvm_vcpu_has_pmu(vcpu)) + return 0; + reset_unknown(vcpu, r); - __vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_EVTYPE_MASK; + __vcpu_sys_reg(vcpu, r->reg) &= kvm_pmu_evtyper_mask(vcpu->kvm); return __vcpu_sys_reg(vcpu, r->reg); } @@ -988,7 +992,7 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p, kvm_pmu_set_counter_event_type(vcpu, p->regval, idx); kvm_vcpu_pmu_restore_guest(vcpu); } else { - p->regval = __vcpu_sys_reg(vcpu, reg) & ARMV8_PMU_EVTYPE_MASK; + p->regval = __vcpu_sys_reg(vcpu, reg); } return true; @@ -1228,7 +1232,7 @@ static s64 kvm_arm64_ftr_safe_value(u32 id, const struct arm64_ftr_bits *ftrp, return arm64_ftr_safe_value(&kvm_ftr, new, cur); } -/** +/* * arm64_check_features() - Check if a feature register value constitutes * a subset of features indicated by the idreg's KVM sanitised limit. * @@ -1791,8 +1795,8 @@ static unsigned int el2_visibility(const struct kvm_vcpu *vcpu, * HCR_EL2.E2H==1, and only in the sysreg table for convenience of * handling traps. Given that, they are always hidden from userspace. */ -static unsigned int elx2_visibility(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) +static unsigned int hidden_user_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) { return REG_HIDDEN_USER; } @@ -1803,7 +1807,7 @@ static unsigned int elx2_visibility(const struct kvm_vcpu *vcpu, .reset = rst, \ .reg = name##_EL1, \ .val = v, \ - .visibility = elx2_visibility, \ + .visibility = hidden_user_visibility, \ } /* @@ -1961,7 +1965,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { // DBGDTR[TR]X_EL0 share the same encoding { SYS_DESC(SYS_DBGDTRTX_EL0), trap_raz_wi }, - { SYS_DESC(SYS_DBGVCR32_EL2), NULL, reset_val, DBGVCR32_EL2, 0 }, + { SYS_DESC(SYS_DBGVCR32_EL2), trap_undef, reset_val, DBGVCR32_EL2, 0 }, { SYS_DESC(SYS_MPIDR_EL1), NULL, reset_mpidr, MPIDR_EL1 }, @@ -2380,18 +2384,28 @@ static const struct sys_reg_desc sys_reg_descs[] = { EL2_REG(VTTBR_EL2, access_rw, reset_val, 0), EL2_REG(VTCR_EL2, access_rw, reset_val, 0), - { SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 }, + { SYS_DESC(SYS_DACR32_EL2), trap_undef, reset_unknown, DACR32_EL2 }, EL2_REG(HDFGRTR_EL2, access_rw, reset_val, 0), EL2_REG(HDFGWTR_EL2, access_rw, reset_val, 0), EL2_REG(SPSR_EL2, access_rw, reset_val, 0), EL2_REG(ELR_EL2, access_rw, reset_val, 0), { SYS_DESC(SYS_SP_EL1), access_sp_el1}, - { SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 }, + /* AArch32 SPSR_* are RES0 if trapped from a NV guest */ + { SYS_DESC(SYS_SPSR_irq), .access = trap_raz_wi, + .visibility = hidden_user_visibility }, + { SYS_DESC(SYS_SPSR_abt), .access = trap_raz_wi, + .visibility = hidden_user_visibility }, + { SYS_DESC(SYS_SPSR_und), .access = trap_raz_wi, + .visibility = hidden_user_visibility }, + { SYS_DESC(SYS_SPSR_fiq), .access = trap_raz_wi, + .visibility = hidden_user_visibility }, + + { SYS_DESC(SYS_IFSR32_EL2), trap_undef, reset_unknown, IFSR32_EL2 }, EL2_REG(AFSR0_EL2, access_rw, reset_val, 0), EL2_REG(AFSR1_EL2, access_rw, reset_val, 0), EL2_REG(ESR_EL2, access_rw, reset_val, 0), - { SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x700 }, + { SYS_DESC(SYS_FPEXC32_EL2), trap_undef, reset_val, FPEXC32_EL2, 0x700 }, EL2_REG(FAR_EL2, access_rw, reset_val, 0), EL2_REG(HPFAR_EL2, access_rw, reset_val, 0), diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h index 8ad53104934d..c18c1a95831e 100644 --- a/arch/arm64/kvm/trace_arm.h +++ b/arch/arm64/kvm/trace_arm.h @@ -136,6 +136,31 @@ TRACE_EVENT(kvm_mmio_emulate, __entry->vcpu_pc, __entry->instr, __entry->cpsr) ); +TRACE_EVENT(kvm_mmio_nisv, + TP_PROTO(unsigned long vcpu_pc, unsigned long esr, + unsigned long far, unsigned long ipa), + TP_ARGS(vcpu_pc, esr, far, ipa), + + TP_STRUCT__entry( + __field( unsigned long, vcpu_pc ) + __field( unsigned long, esr ) + __field( unsigned long, far ) + __field( unsigned long, ipa ) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->esr = esr; + __entry->far = far; + __entry->ipa = ipa; + ), + + TP_printk("ipa %#016lx, esr %#016lx, far %#016lx, pc %#016lx", + __entry->ipa, __entry->esr, + __entry->far, __entry->vcpu_pc) +); + + TRACE_EVENT(kvm_set_way_flush, TP_PROTO(unsigned long vcpu_pc, bool cache), TP_ARGS(vcpu_pc, cache), diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index c11962f901e0..f48b8dab8b3d 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -27,7 +27,8 @@ int vgic_check_iorange(struct kvm *kvm, phys_addr_t ioaddr, if (addr + size < addr) return -EINVAL; - if (addr & ~kvm_phys_mask(kvm) || addr + size > kvm_phys_size(kvm)) + if (addr & ~kvm_phys_mask(&kvm->arch.mmu) || + (addr + size) > kvm_phys_size(&kvm->arch.mmu)) return -E2BIG; return 0; diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index 7fe8ba1a2851..806223b7022a 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -135,10 +135,11 @@ void kvm_arm_vmid_clear_active(void) atomic64_set(this_cpu_ptr(&active_vmids), VMID_ACTIVE_INVALID); } -void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid) +bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid) { unsigned long flags; u64 vmid, old_active_vmid; + bool updated = false; vmid = atomic64_read(&kvm_vmid->id); @@ -156,17 +157,21 @@ void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid) if (old_active_vmid != 0 && vmid_gen_match(vmid) && 0 != atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_vmids), old_active_vmid, vmid)) - return; + return false; raw_spin_lock_irqsave(&cpu_vmid_lock, flags); /* Check that our VMID belongs to the current generation. */ vmid = atomic64_read(&kvm_vmid->id); - if (!vmid_gen_match(vmid)) + if (!vmid_gen_match(vmid)) { vmid = new_vmid(kvm_vmid); + updated = true; + } atomic64_set(this_cpu_ptr(&active_vmids), vmid); raw_spin_unlock_irqrestore(&cpu_vmid_lock, flags); + + return updated; } /* diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 2517ef7c21cf..76ce150e7347 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -1347,7 +1347,11 @@ UnsignedEnum 51:48 RPRFM 0b0000 NI 0b0001 IMP EndEnum -Res0 47:28 +Res0 47:32 +UnsignedEnum 31:28 CLRBHB + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 27:24 PAC_frac 0b0000 NI 0b0001 IMP diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 15f6cfddcc08..41e8fe55cd98 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -907,3 +907,7 @@ EXPORT_SYMBOL(acpi_unregister_ioapic); * TBD when IA64 starts to support suspend... */ int acpi_suspend_lowlevel(void) { return 0; } + +void acpi_proc_quirk_mwait_check(void) +{ +} diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h index 5c9c03bdf915..b24437e28c6e 100644 --- a/arch/loongarch/include/asm/addrspace.h +++ b/arch/loongarch/include/asm/addrspace.h @@ -19,7 +19,7 @@ */ #ifndef __ASSEMBLY__ #ifndef PHYS_OFFSET -#define PHYS_OFFSET _AC(0, UL) +#define PHYS_OFFSET _UL(0) #endif extern unsigned long vm_map_base; #endif /* __ASSEMBLY__ */ @@ -43,7 +43,7 @@ extern unsigned long vm_map_base; * Memory above this physical address will be considered highmem. */ #ifndef HIGHMEM_START -#define HIGHMEM_START (_AC(1, UL) << _AC(DMW_PABITS, UL)) +#define HIGHMEM_START (_UL(1) << _UL(DMW_PABITS)) #endif #define TO_PHYS(x) ( ((x) & TO_PHYS_MASK)) @@ -65,16 +65,16 @@ extern unsigned long vm_map_base; #define _ATYPE_ #define _ATYPE32_ #define _ATYPE64_ -#define _CONST64_(x) x #else #define _ATYPE_ __PTRDIFF_TYPE__ #define _ATYPE32_ int #define _ATYPE64_ __s64 +#endif + #ifdef CONFIG_64BIT -#define _CONST64_(x) x ## UL +#define _CONST64_(x) _UL(x) #else -#define _CONST64_(x) x ## ULL -#endif +#define _CONST64_(x) _ULL(x) #endif /* diff --git a/arch/loongarch/include/asm/exception.h b/arch/loongarch/include/asm/exception.h new file mode 100644 index 000000000000..af74a3fdcad1 --- /dev/null +++ b/arch/loongarch/include/asm/exception.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_EXCEPTION_H +#define __ASM_EXCEPTION_H + +#include <asm/ptrace.h> +#include <linux/kprobes.h> + +void show_registers(struct pt_regs *regs); + +asmlinkage void cache_parity_error(void); +asmlinkage void noinstr do_ade(struct pt_regs *regs); +asmlinkage void noinstr do_ale(struct pt_regs *regs); +asmlinkage void noinstr do_bce(struct pt_regs *regs); +asmlinkage void noinstr do_bp(struct pt_regs *regs); +asmlinkage void noinstr do_ri(struct pt_regs *regs); +asmlinkage void noinstr do_fpu(struct pt_regs *regs); +asmlinkage void noinstr do_fpe(struct pt_regs *regs, unsigned long fcsr); +asmlinkage void noinstr do_lsx(struct pt_regs *regs); +asmlinkage void noinstr do_lasx(struct pt_regs *regs); +asmlinkage void noinstr do_lbt(struct pt_regs *regs); +asmlinkage void noinstr do_watch(struct pt_regs *regs); +asmlinkage void noinstr do_syscall(struct pt_regs *regs); +asmlinkage void noinstr do_reserved(struct pt_regs *regs); +asmlinkage void noinstr do_vint(struct pt_regs *regs, unsigned long sp); +asmlinkage void __kprobes do_page_fault(struct pt_regs *regs, + unsigned long write, unsigned long address); + +asmlinkage void handle_ade(void); +asmlinkage void handle_ale(void); +asmlinkage void handle_bce(void); +asmlinkage void handle_sys(void); +asmlinkage void handle_bp(void); +asmlinkage void handle_ri(void); +asmlinkage void handle_fpu(void); +asmlinkage void handle_fpe(void); +asmlinkage void handle_lsx(void); +asmlinkage void handle_lasx(void); +asmlinkage void handle_lbt(void); +asmlinkage void handle_watch(void); +asmlinkage void handle_reserved(void); +asmlinkage void handle_vint(void); +asmlinkage void noinstr handle_loongarch_irq(struct pt_regs *regs); + +#endif /* __ASM_EXCEPTION_H */ diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h index deeff8158f45..cd6084f4e153 100644 --- a/arch/loongarch/include/asm/kasan.h +++ b/arch/loongarch/include/asm/kasan.h @@ -10,8 +10,6 @@ #include <asm/io.h> #include <asm/pgtable.h> -#define __HAVE_ARCH_SHADOW_MAP - #define KASAN_SHADOW_SCALE_SHIFT 3 #define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) @@ -62,61 +60,22 @@ extern bool kasan_early_stage; extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; +#define kasan_mem_to_shadow kasan_mem_to_shadow +void *kasan_mem_to_shadow(const void *addr); + +#define kasan_shadow_to_mem kasan_shadow_to_mem +const void *kasan_shadow_to_mem(const void *shadow_addr); + #define kasan_arch_is_ready kasan_arch_is_ready static __always_inline bool kasan_arch_is_ready(void) { return !kasan_early_stage; } -static inline void *kasan_mem_to_shadow(const void *addr) -{ - if (!kasan_arch_is_ready()) { - return (void *)(kasan_early_shadow_page); - } else { - unsigned long maddr = (unsigned long)addr; - unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff; - unsigned long offset = 0; - - maddr &= XRANGE_SHADOW_MASK; - switch (xrange) { - case XKPRANGE_CC_SEG: - offset = XKPRANGE_CC_SHADOW_OFFSET; - break; - case XKPRANGE_UC_SEG: - offset = XKPRANGE_UC_SHADOW_OFFSET; - break; - case XKVRANGE_VC_SEG: - offset = XKVRANGE_VC_SHADOW_OFFSET; - break; - default: - WARN_ON(1); - return NULL; - } - - return (void *)((maddr >> KASAN_SHADOW_SCALE_SHIFT) + offset); - } -} - -static inline const void *kasan_shadow_to_mem(const void *shadow_addr) +#define addr_has_metadata addr_has_metadata +static __always_inline bool addr_has_metadata(const void *addr) { - unsigned long addr = (unsigned long)shadow_addr; - - if (unlikely(addr > KASAN_SHADOW_END) || - unlikely(addr < KASAN_SHADOW_START)) { - WARN_ON(1); - return NULL; - } - - if (addr >= XKVRANGE_VC_SHADOW_OFFSET) - return (void *)(((addr - XKVRANGE_VC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKVRANGE_VC_START); - else if (addr >= XKPRANGE_UC_SHADOW_OFFSET) - return (void *)(((addr - XKPRANGE_UC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_UC_START); - else if (addr >= XKPRANGE_CC_SHADOW_OFFSET) - return (void *)(((addr - XKPRANGE_CC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_CC_START); - else { - WARN_ON(1); - return NULL; - } + return (kasan_mem_to_shadow((void *)addr) != NULL); } void kasan_init(void); diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index 66ecb480c894..f81e5f01d619 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -70,6 +70,7 @@ struct secondary_data { extern struct secondary_data cpuboot_data; extern asmlinkage void smpboot_entry(void); +extern asmlinkage void start_secondary(void); extern void calculate_cpu_foreign_map(void); diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index c56ea0b75448..4fcc168f0732 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -19,6 +19,10 @@ obj-$(CONFIG_CPU_HAS_LBT) += lbt.o obj-$(CONFIG_ARCH_STRICT_ALIGN) += unaligned.o +CFLAGS_module.o += $(call cc-option,-Wno-override-init,) +CFLAGS_syscall.o += $(call cc-option,-Wno-override-init,) +CFLAGS_perf_event.o += $(call cc-option,-Wno-override-init,) + ifdef CONFIG_FUNCTION_TRACER ifndef CONFIG_DYNAMIC_FTRACE obj-y += mcount.o ftrace.o diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 9450e09073eb..8e00a754e548 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -281,7 +281,6 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) pr_info("SRAT: PXM %u -> CPU 0x%02x -> Node %u\n", pxm, pa->apic_id, node); } -void __init acpi_numa_arch_fixup(void) {} #endif void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) diff --git a/arch/loongarch/kernel/mem.c b/arch/loongarch/kernel/mem.c index 4a4107a6a965..aed901c57fb4 100644 --- a/arch/loongarch/kernel/mem.c +++ b/arch/loongarch/kernel/mem.c @@ -50,7 +50,6 @@ void __init memblock_init(void) } memblock_set_current_limit(PFN_PHYS(max_low_pfn)); - memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); /* Reserve the first 2MB */ memblock_reserve(PHYS_OFFSET, 0x200000); @@ -58,4 +57,7 @@ void __init memblock_init(void) /* Reserve the kernel text/data/bss */ memblock_reserve(__pa_symbol(&_text), __pa_symbol(&_end) - __pa_symbol(&_text)); + + memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); + memblock_set_node(0, PHYS_ADDR_MAX, &memblock.reserved, 0); } diff --git a/arch/loongarch/kernel/module-sections.c b/arch/loongarch/kernel/module-sections.c index d4dbcda1c4b0..e2f30ff9afde 100644 --- a/arch/loongarch/kernel/module-sections.c +++ b/arch/loongarch/kernel/module-sections.c @@ -6,6 +6,7 @@ #include <linux/elf.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/moduleloader.h> #include <linux/ftrace.h> Elf_Addr module_emit_got_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr val) diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 3cb082e0c992..767d94cce0de 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -37,6 +37,7 @@ #include <asm/bootinfo.h> #include <asm/cpu.h> #include <asm/elf.h> +#include <asm/exec.h> #include <asm/fpu.h> #include <asm/lbt.h> #include <asm/io.h> diff --git a/arch/loongarch/kernel/relocate_kernel.S b/arch/loongarch/kernel/relocate_kernel.S index d13252553a7c..f49f6b053763 100644 --- a/arch/loongarch/kernel/relocate_kernel.S +++ b/arch/loongarch/kernel/relocate_kernel.S @@ -72,7 +72,6 @@ copy_word: LONG_ADDI s5, s5, -1 beqz s5, process_entry b copy_word - b process_entry done: ibar 0 diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c index 504fdfe85203..4a3686d13349 100644 --- a/arch/loongarch/kernel/signal.c +++ b/arch/loongarch/kernel/signal.c @@ -13,6 +13,7 @@ #include <linux/audit.h> #include <linux/cache.h> #include <linux/context_tracking.h> +#include <linux/entry-common.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/mm.h> @@ -891,8 +892,8 @@ static unsigned long setup_extcontext(struct extctx_layout *extctx, unsigned lon return new_sp; } -void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, - struct extctx_layout *extctx) +static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, + struct extctx_layout *extctx) { unsigned long sp; @@ -922,7 +923,7 @@ void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, * Atomically swap in the new signal mask, and wait for a signal. */ -asmlinkage long sys_rt_sigreturn(void) +SYSCALL_DEFINE0(rt_sigreturn) { int sig; sigset_t set; diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 6667b0a90f81..ef35c871244f 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -13,6 +13,7 @@ #include <linux/cpumask.h> #include <linux/init.h> #include <linux/interrupt.h> +#include <linux/profile.h> #include <linux/seq_file.h> #include <linux/smp.h> #include <linux/threads.h> @@ -556,10 +557,12 @@ void smp_send_stop(void) smp_call_function(stop_this_cpu, NULL, 0); } +#ifdef CONFIG_PROFILING int setup_profiling_timer(unsigned int multiplier) { return 0; } +#endif static void flush_tlb_all_ipi(void *info) { diff --git a/arch/loongarch/kernel/syscall.c b/arch/loongarch/kernel/syscall.c index 3fc4211db989..b4c5acd7aa3b 100644 --- a/arch/loongarch/kernel/syscall.c +++ b/arch/loongarch/kernel/syscall.c @@ -13,6 +13,7 @@ #include <linux/unistd.h> #include <asm/asm.h> +#include <asm/exception.h> #include <asm/signal.h> #include <asm/switch_to.h> #include <asm-generic/syscalls.h> diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index c189e03cd5da..3064af94db9c 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -29,7 +29,7 @@ static void constant_event_handler(struct clock_event_device *dev) { } -irqreturn_t constant_timer_interrupt(int irq, void *data) +static irqreturn_t constant_timer_interrupt(int irq, void *data) { int cpu = smp_processor_id(); struct clock_event_device *cd; diff --git a/arch/loongarch/kernel/topology.c b/arch/loongarch/kernel/topology.c index caa7cd859078..3fd166006698 100644 --- a/arch/loongarch/kernel/topology.c +++ b/arch/loongarch/kernel/topology.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/acpi.h> #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/init.h> @@ -7,6 +8,8 @@ #include <linux/percpu.h> #include <asm/bootinfo.h> +#include <acpi/processor.h> + static DEFINE_PER_CPU(struct cpu, cpu_devices); #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 65214774ef7c..aebfc3733a76 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -25,7 +25,6 @@ #include <linux/ptrace.h> #include <linux/kgdb.h> #include <linux/kdebug.h> -#include <linux/kprobes.h> #include <linux/notifier.h> #include <linux/irq.h> #include <linux/perf_event.h> @@ -35,6 +34,7 @@ #include <asm/branch.h> #include <asm/break.h> #include <asm/cpu.h> +#include <asm/exception.h> #include <asm/fpu.h> #include <asm/lbt.h> #include <asm/inst.h> @@ -53,21 +53,6 @@ #include "access-helper.h" -extern asmlinkage void handle_ade(void); -extern asmlinkage void handle_ale(void); -extern asmlinkage void handle_bce(void); -extern asmlinkage void handle_sys(void); -extern asmlinkage void handle_bp(void); -extern asmlinkage void handle_ri(void); -extern asmlinkage void handle_fpu(void); -extern asmlinkage void handle_fpe(void); -extern asmlinkage void handle_lbt(void); -extern asmlinkage void handle_lsx(void); -extern asmlinkage void handle_lasx(void); -extern asmlinkage void handle_reserved(void); -extern asmlinkage void handle_watch(void); -extern asmlinkage void handle_vint(void); - static void show_backtrace(struct task_struct *task, const struct pt_regs *regs, const char *loglvl, bool user) { @@ -439,8 +424,8 @@ static inline void setup_vint_size(unsigned int size) * happen together with Overflow or Underflow, and `ptrace' can set * any bits. */ -void force_fcsr_sig(unsigned long fcsr, void __user *fault_addr, - struct task_struct *tsk) +static void force_fcsr_sig(unsigned long fcsr, + void __user *fault_addr, struct task_struct *tsk) { int si_code = FPE_FLTUNK; @@ -458,7 +443,7 @@ void force_fcsr_sig(unsigned long fcsr, void __user *fault_addr, force_sig_fault(SIGFPE, si_code, fault_addr); } -int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcsr) +static int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcsr) { int si_code; @@ -824,7 +809,7 @@ out: asmlinkage void noinstr do_ri(struct pt_regs *regs) { int status = SIGILL; - unsigned int opcode = 0; + unsigned int __maybe_unused opcode; unsigned int __user *era = (unsigned int __user *)exception_era(regs); irqentry_state_t state = irqentry_enter(regs); diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index b1686afcf876..bb2ec86f37a8 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -53,33 +53,6 @@ SECTIONS . = ALIGN(PECOFF_SEGMENT_ALIGN); _etext = .; - /* - * struct alt_inst entries. From the header (alternative.h): - * "Alternative instructions for different CPU types or capabilities" - * Think locking instructions on spinlocks. - */ - . = ALIGN(4); - .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) { - __alt_instructions = .; - *(.altinstructions) - __alt_instructions_end = .; - } - -#ifdef CONFIG_RELOCATABLE - . = ALIGN(8); - .la_abs : AT(ADDR(.la_abs) - LOAD_OFFSET) { - __la_abs_begin = .; - *(.la_abs) - __la_abs_end = .; - } -#endif - - .got : ALIGN(16) { *(.got) } - .plt : ALIGN(16) { *(.plt) } - .got.plt : ALIGN(16) { *(.got.plt) } - - .data.rel : { *(.data.rel*) } - . = ALIGN(PECOFF_SEGMENT_ALIGN); __init_begin = .; __inittext_begin = .; @@ -94,6 +67,18 @@ SECTIONS __initdata_begin = .; + /* + * struct alt_inst entries. From the header (alternative.h): + * "Alternative instructions for different CPU types or capabilities" + * Think locking instructions on spinlocks. + */ + . = ALIGN(4); + .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) { + __alt_instructions = .; + *(.altinstructions) + __alt_instructions_end = .; + } + INIT_DATA_SECTION(16) .exit.data : { EXIT_DATA @@ -113,6 +98,11 @@ SECTIONS _sdata = .; RO_DATA(4096) + + .got : ALIGN(16) { *(.got) } + .plt : ALIGN(16) { *(.plt) } + .got.plt : ALIGN(16) { *(.got.plt) } + RW_DATA(1 << CONFIG_L1_CACHE_SHIFT, PAGE_SIZE, THREAD_SIZE) .rela.dyn : ALIGN(8) { @@ -121,6 +111,17 @@ SECTIONS __rela_dyn_end = .; } + .data.rel : { *(.data.rel*) } + +#ifdef CONFIG_RELOCATABLE + . = ALIGN(8); + .la_abs : AT(ADDR(.la_abs) - LOAD_OFFSET) { + __la_abs_begin = .; + *(.la_abs) + __la_abs_end = .; + } +#endif + .sdata : { *(.sdata) } diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c index e6376e3dce86..1fc2f6813ea0 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -20,12 +20,12 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/kdebug.h> -#include <linux/kprobes.h> #include <linux/perf_event.h> #include <linux/uaccess.h> #include <linux/kfence.h> #include <asm/branch.h> +#include <asm/exception.h> #include <asm/mmu_context.h> #include <asm/ptrace.h> diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c index ba138117b124..1e76fcb83093 100644 --- a/arch/loongarch/mm/hugetlbpage.c +++ b/arch/loongarch/mm/hugetlbpage.c @@ -50,18 +50,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return (pte_t *) pmd; } -/* - * This function checks for proper alignment of input addr and len parameters. - */ -int is_aligned_hugepage_range(unsigned long addr, unsigned long len) -{ - if (len & ~HPAGE_MASK) - return -EINVAL; - if (addr & ~HPAGE_MASK) - return -EINVAL; - return 0; -} - int pmd_huge(pmd_t pmd) { return (pmd_val(pmd) & _PAGE_HUGE) != 0; diff --git a/arch/loongarch/mm/ioremap.c b/arch/loongarch/mm/ioremap.c index 73b0980ab6f5..70ca73019811 100644 --- a/arch/loongarch/mm/ioremap.c +++ b/arch/loongarch/mm/ioremap.c @@ -4,6 +4,7 @@ */ #include <asm/io.h> +#include <asm-generic/early_ioremap.h> void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size) { diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c index da68bc1a4643..cc3e81fe0186 100644 --- a/arch/loongarch/mm/kasan_init.c +++ b/arch/loongarch/mm/kasan_init.c @@ -35,6 +35,57 @@ static pgd_t kasan_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); bool kasan_early_stage = true; +void *kasan_mem_to_shadow(const void *addr) +{ + if (!kasan_arch_is_ready()) { + return (void *)(kasan_early_shadow_page); + } else { + unsigned long maddr = (unsigned long)addr; + unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff; + unsigned long offset = 0; + + maddr &= XRANGE_SHADOW_MASK; + switch (xrange) { + case XKPRANGE_CC_SEG: + offset = XKPRANGE_CC_SHADOW_OFFSET; + break; + case XKPRANGE_UC_SEG: + offset = XKPRANGE_UC_SHADOW_OFFSET; + break; + case XKVRANGE_VC_SEG: + offset = XKVRANGE_VC_SHADOW_OFFSET; + break; + default: + WARN_ON(1); + return NULL; + } + + return (void *)((maddr >> KASAN_SHADOW_SCALE_SHIFT) + offset); + } +} + +const void *kasan_shadow_to_mem(const void *shadow_addr) +{ + unsigned long addr = (unsigned long)shadow_addr; + + if (unlikely(addr > KASAN_SHADOW_END) || + unlikely(addr < KASAN_SHADOW_START)) { + WARN_ON(1); + return NULL; + } + + if (addr >= XKVRANGE_VC_SHADOW_OFFSET) + return (void *)(((addr - XKVRANGE_VC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKVRANGE_VC_START); + else if (addr >= XKPRANGE_UC_SHADOW_OFFSET) + return (void *)(((addr - XKPRANGE_UC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_UC_START); + else if (addr >= XKPRANGE_CC_SHADOW_OFFSET) + return (void *)(((addr - XKPRANGE_CC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_CC_START); + else { + WARN_ON(1); + return NULL; + } +} + /* * Alloc memory for shadow memory page table. */ diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c index eb8572e201ea..2c0a411f23aa 100644 --- a/arch/loongarch/mm/tlb.c +++ b/arch/loongarch/mm/tlb.c @@ -261,7 +261,7 @@ unsigned long pcpu_handlers[NR_CPUS]; #endif extern long exception_handlers[VECSIZE * 128 / sizeof(long)]; -void setup_tlb_handler(int cpu) +static void setup_tlb_handler(int cpu) { setup_ptwalker(); local_flush_tlb_all(); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 54b9387c3691..3aaadfd2c8eb 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -255,7 +255,7 @@ config PPC select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE select HAVE_KRETPROBES - select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT + select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT && (!ARCH_USING_PATCHABLE_FUNCTION_ENTRY || (!CC_IS_GCC || GCC_VERSION >= 110100)) select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index b8513dc3e53a..a1318ce18d0e 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -230,13 +230,15 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs) struct arch_hw_breakpoint *info; int i; + preempt_disable(); + for (i = 0; i < nr_wp_slots(); i++) { struct perf_event *bp = __this_cpu_read(bp_per_reg[i]); if (unlikely(bp && counter_arch_bp(bp)->perf_single_step)) goto reset; } - return; + goto out; reset: regs_set_return_msr(regs, regs->msr & ~MSR_SE); @@ -245,6 +247,9 @@ reset: __set_breakpoint(i, info); info->perf_single_step = false; } + +out: + preempt_enable(); } static bool is_larx_stcx_instr(int type) @@ -363,6 +368,11 @@ static void handle_p10dd1_spurious_exception(struct perf_event **bp, } } +/* + * Handle a DABR or DAWR exception. + * + * Called in atomic context. + */ int hw_breakpoint_handler(struct die_args *args) { bool err = false; @@ -490,6 +500,8 @@ NOKPROBE_SYMBOL(hw_breakpoint_handler); /* * Handle single-step exceptions following a DABR hit. + * + * Called in atomic context. */ static int single_step_dabr_instruction(struct die_args *args) { @@ -541,6 +553,8 @@ NOKPROBE_SYMBOL(single_step_dabr_instruction); /* * Handle debug exception notifications. + * + * Called in atomic context. */ int hw_breakpoint_exceptions_notify( struct notifier_block *unused, unsigned long val, void *data) diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c index a74623025f3a..9e51801c4915 100644 --- a/arch/powerpc/kernel/hw_breakpoint_constraints.c +++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c @@ -131,8 +131,13 @@ void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr, int *type, int *size, unsigned long *ea) { struct instruction_op op; + int err; - if (__get_user_instr(*instr, (void __user *)regs->nip)) + pagefault_disable(); + err = __get_user_instr(*instr, (void __user *)regs->nip); + pagefault_enable(); + + if (err) return; analyse_instr(&op, regs, *instr); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index eeff136b83d9..64ff37721fd0 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1512,23 +1512,11 @@ static void do_program_check(struct pt_regs *regs) return; } - if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) && user_mode(regs)) { - ppc_inst_t insn; - - if (get_user_instr(insn, (void __user *)regs->nip)) { - _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip); - return; - } - - if (ppc_inst_primary_opcode(insn) == 31 && - get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) { - _exception(SIGILL, regs, ILL_ILLOPN, regs->nip); - return; - } + /* User mode considers other cases after enabling IRQs */ + if (!user_mode(regs)) { + _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); + return; } - - _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); - return; } #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (reason & REASON_TM) { @@ -1561,16 +1549,44 @@ static void do_program_check(struct pt_regs *regs) /* * If we took the program check in the kernel skip down to sending a - * SIGILL. The subsequent cases all relate to emulating instructions - * which we should only do for userspace. We also do not want to enable - * interrupts for kernel faults because that might lead to further - * faults, and loose the context of the original exception. + * SIGILL. The subsequent cases all relate to user space, such as + * emulating instructions which we should only do for user space. We + * also do not want to enable interrupts for kernel faults because that + * might lead to further faults, and loose the context of the original + * exception. */ if (!user_mode(regs)) goto sigill; interrupt_cond_local_irq_enable(regs); + /* + * (reason & REASON_TRAP) is mostly handled before enabling IRQs, + * except get_user_instr() can sleep so we cannot reliably inspect the + * current instruction in that context. Now that we know we are + * handling a user space trap and can sleep, we can check if the trap + * was a hashchk failure. + */ + if (reason & REASON_TRAP) { + if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) { + ppc_inst_t insn; + + if (get_user_instr(insn, (void __user *)regs->nip)) { + _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip); + return; + } + + if (ppc_inst_primary_opcode(insn) == 31 && + get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) { + _exception(SIGILL, regs, ILL_ILLOPN, regs->nip); + return; + } + } + + _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip); + return; + } + /* (reason & REASON_ILLEGAL) would be the obvious thing here, * but there seems to be a hardware bug on the 405GP (RevD) * that means ESR is sometimes set incorrectly - either to diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 317175791d23..3449be7c0d51 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1418,7 +1418,7 @@ static int h_24x7_event_init(struct perf_event *event) } domain = event_get_domain(event); - if (domain >= HV_PERF_DOMAIN_MAX) { + if (domain == 0 || domain >= HV_PERF_DOMAIN_MAX) { pr_devel("invalid domain %d\n", domain); return -EINVAL; } diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig index d9f1a2a83158..1824536cf6f2 100644 --- a/arch/powerpc/platforms/82xx/Kconfig +++ b/arch/powerpc/platforms/82xx/Kconfig @@ -2,6 +2,7 @@ menuconfig PPC_82xx bool "82xx-based boards (PQ II)" depends on PPC_BOOK3S_32 + select FSL_SOC if PPC_82xx @@ -9,7 +10,6 @@ config EP8248E bool "Embedded Planet EP8248E (a.k.a. CWH-PPC-8248N-VE)" select CPM2 select PPC_INDIRECT_PCI if PCI - select FSL_SOC select PHYLIB if NETDEVICES select MDIO_BITBANG if PHYLIB help @@ -22,7 +22,6 @@ config MGCOGE bool "Keymile MGCOGE" select CPM2 select PPC_INDIRECT_PCI if PCI - select FSL_SOC help This enables support for the Keymile MGCOGE board. diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c index 1b7e9fa265cb..b7e0e03c69b1 100644 --- a/arch/riscv/kvm/vcpu_onereg.c +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -460,8 +460,11 @@ static int riscv_vcpu_get_isa_ext_single(struct kvm_vcpu *vcpu, reg_num >= ARRAY_SIZE(kvm_isa_ext_arr)) return -ENOENT; - *reg_val = 0; host_isa_ext = kvm_isa_ext_arr[reg_num]; + if (!__riscv_isa_extension_available(NULL, host_isa_ext)) + return -ENOENT; + + *reg_val = 0; if (__riscv_isa_extension_available(vcpu->arch.isa, host_isa_ext)) *reg_val = 1; /* Mark the given extension as available */ @@ -842,7 +845,7 @@ static int copy_isa_ext_reg_indices(const struct kvm_vcpu *vcpu, u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_ISA_EXT | i; isa_ext = kvm_isa_ext_arr[i]; - if (!__riscv_isa_extension_available(vcpu->arch.isa, isa_ext)) + if (!__riscv_isa_extension_available(NULL, isa_ext)) continue; if (uindices) { diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index af2fbe48e16c..438cd92e6080 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -40,23 +40,25 @@ CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set CONFIG_PROFILING=y +CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y +CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y CONFIG_MARCH_ZEC12=y CONFIG_TUNE_ZEC12=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y -CONFIG_KEXEC_SIG=y +CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m CONFIG_VFIO_AP=m -CONFIG_CRASH_DUMP=y CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y +CONFIG_S390_HYPFS_FS=y CONFIG_KVM=m CONFIG_S390_UNWIND_SELFTEST=m CONFIG_S390_KPROBES_SANITY_TEST=m @@ -434,6 +436,7 @@ CONFIG_SCSI_DH_EMC=m CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y +# CONFIG_MD_BITMAP_FILE is not set CONFIG_MD_LINEAR=m CONFIG_MD_MULTIPATH=m CONFIG_MD_FAULTY=m @@ -577,6 +580,7 @@ CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m # CONFIG_DRM_DEBUG_MODESET_LOCK is not set CONFIG_FB=y +# CONFIG_FB_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID_SUPPORT is not set @@ -647,6 +651,7 @@ CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS_INODE64=y +CONFIG_TMPFS_QUOTA=y CONFIG_HUGETLBFS=y CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m @@ -703,6 +708,7 @@ CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_INIT_STACK_NONE=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m @@ -825,9 +831,9 @@ CONFIG_LOCK_STAT=y CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_LOCKING_API_SELFTESTS=y CONFIG_DEBUG_IRQFLAGS=y +CONFIG_DEBUG_LIST=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y -CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_REF_SCALE_TEST=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 3f263b767a4c..1b8150e50f6a 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -38,23 +38,25 @@ CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set CONFIG_PROFILING=y +CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y +CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y CONFIG_MARCH_ZEC12=y CONFIG_TUNE_ZEC12=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y -CONFIG_KEXEC_SIG=y +CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m CONFIG_VFIO_AP=m -CONFIG_CRASH_DUMP=y CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y +CONFIG_S390_HYPFS_FS=y CONFIG_KVM=m CONFIG_S390_UNWIND_SELFTEST=m CONFIG_S390_KPROBES_SANITY_TEST=m @@ -424,6 +426,7 @@ CONFIG_SCSI_DH_EMC=m CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y +# CONFIG_MD_BITMAP_FILE is not set CONFIG_MD_LINEAR=m CONFIG_MD_MULTIPATH=m CONFIG_MD_FAULTY=m @@ -566,6 +569,7 @@ CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m CONFIG_FB=y +# CONFIG_FB_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID_SUPPORT is not set @@ -632,6 +636,7 @@ CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS_INODE64=y +CONFIG_TMPFS_QUOTA=y CONFIG_HUGETLBFS=y CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m @@ -687,6 +692,7 @@ CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_INIT_STACK_NONE=y +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set @@ -781,7 +787,6 @@ CONFIG_PTDUMP_DEBUGFS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_PANIC_ON_OOPS=y CONFIG_TEST_LOCKUP=m -CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index e62fb2015102..b831083b4edd 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -8,6 +8,7 @@ CONFIG_BPF_SYSCALL=y # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_CRASH_DUMP=y CONFIG_MARCH_ZEC12=y CONFIG_TUNE_ZEC12=y # CONFIG_COMPAT is not set @@ -15,9 +16,8 @@ CONFIG_NR_CPUS=2 CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set -CONFIG_CRASH_DUMP=y # CONFIG_PFAULT is not set -# CONFIG_S390_HYPFS_FS is not set +# CONFIG_S390_HYPFS is not set # CONFIG_VIRTUALIZATION is not set # CONFIG_S390_GUEST is not set # CONFIG_SECCOMP is not set diff --git a/arch/s390/kernel/cert_store.c b/arch/s390/kernel/cert_store.c index 3986a044eb36..554447768bdd 100644 --- a/arch/s390/kernel/cert_store.c +++ b/arch/s390/kernel/cert_store.c @@ -432,15 +432,16 @@ static char *get_key_description(struct vcssb *vcssb, const struct vce *vce) char *desc; cs_token = vcssb->cs_token; - /* Description string contains "%64s:%04u:%08u\0". */ + /* Description string contains "%64s:%05u:%010u\0". */ name_len = sizeof(vce->vce_hdr.vc_name); - len = name_len + 1 + 4 + 1 + 8 + 1; + len = name_len + 1 + 5 + 1 + 10 + 1; desc = kmalloc(len, GFP_KERNEL); if (!desc) return NULL; memcpy(desc, vce->vce_hdr.vc_name, name_len); - sprintf(desc + name_len, ":%04u:%08u", vce->vce_hdr.vc_index, cs_token); + snprintf(desc + name_len, len - name_len, ":%05u:%010u", + vce->vce_hdr.vc_index, cs_token); return desc; } diff --git a/arch/sh/mm/ioremap.c b/arch/sh/mm/ioremap.c index c33b3daa4ad1..33d20f34560f 100644 --- a/arch/sh/mm/ioremap.c +++ b/arch/sh/mm/ioremap.c @@ -72,8 +72,8 @@ __ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot) #define __ioremap_29bit(offset, size, prot) NULL #endif /* CONFIG_29BIT */ -void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, - unsigned long prot) +void __iomem __ref *ioremap_prot(phys_addr_t phys_addr, size_t size, + unsigned long prot) { void __iomem *mapped; pgprot_t pgprot = __pgprot(prot); diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 6c2826417b33..93c60c0c9d4a 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -294,7 +294,7 @@ static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs) inc_irq_stat(irq_hv_callback_count); - xen_hvm_evtchn_do_upcall(); + xen_evtchn_do_upcall(); set_irq_regs(old_regs); } diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1a4def36d5bb..17715cb8731d 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1419,7 +1419,6 @@ struct kvm_arch { * the thread holds the MMU lock in write mode. */ spinlock_t tdp_mmu_pages_lock; - struct workqueue_struct *tdp_mmu_zap_wq; #endif /* CONFIG_X86_64 */ /* @@ -1835,7 +1834,7 @@ void kvm_mmu_vendor_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); -int kvm_mmu_init_vm(struct kvm *kvm); +void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 5ff49fd67732..571fe4d2d232 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -105,6 +105,13 @@ CFI_POST_PADDING \ SYM_FUNC_END(__cfi_##name) +/* UML needs to be able to override memcpy() and friends for KASAN. */ +#ifdef CONFIG_UML +# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS_WEAK +#else +# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS +#endif + /* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */ #define SYM_TYPED_FUNC_START(name) \ SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 416901d406f8..8dac45a2c7fc 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -186,8 +186,7 @@ do { \ #else #define deactivate_mm(tsk, mm) \ do { \ - if (!tsk->vfork_done) \ - shstk_free(tsk); \ + shstk_free(tsk); \ load_gs_index(0); \ loadsegment(fs, 0); \ } while (0) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 4acbcddddc29..772d03487520 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -9,13 +9,6 @@ struct paravirt_patch_site { u8 type; /* type of this instruction */ u8 len; /* length of original instruction */ }; - -/* Lazy mode for batching updates / context switch */ -enum paravirt_lazy_mode { - PARAVIRT_LAZY_NONE, - PARAVIRT_LAZY_MMU, - PARAVIRT_LAZY_CPU, -}; #endif #ifdef CONFIG_PARAVIRT @@ -549,14 +542,6 @@ int paravirt_disable_iospace(void); __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) -enum paravirt_lazy_mode paravirt_get_lazy_mode(void); -void paravirt_start_context_switch(struct task_struct *prev); -void paravirt_end_context_switch(struct task_struct *next); - -void paravirt_enter_lazy_mmu(void); -void paravirt_leave_lazy_mmu(void); -void paravirt_flush_lazy_mmu(void); - void _paravirt_nop(void); void paravirt_BUG(void); unsigned long paravirt_ret0(void); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 0086920cda06..a3669a7774ed 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -683,13 +683,11 @@ extern u16 get_llc_id(unsigned int cpu); #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); -extern bool cpu_has_ibpb_brtype_microcode(void); extern void amd_clear_divider(void); extern void amd_check_microcode(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } -static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; } static inline void amd_clear_divider(void) { } static inline void amd_check_microcode(void) { } #endif diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 5fc35f889cd1..7048dfacc04b 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -36,6 +36,7 @@ extern struct shared_info *HYPERVISOR_shared_info; extern struct start_info *xen_start_info; +#include <asm/bug.h> #include <asm/processor.h> #define XEN_SIGNATURE "XenVMMXenVMM" @@ -63,4 +64,40 @@ void __init xen_pvh_init(struct boot_params *boot_params); void __init mem_map_via_hcall(struct boot_params *boot_params_p); #endif +/* Lazy mode for batching updates / context switch */ +enum xen_lazy_mode { + XEN_LAZY_NONE, + XEN_LAZY_MMU, + XEN_LAZY_CPU, +}; + +DECLARE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode); +DECLARE_PER_CPU(unsigned int, xen_lazy_nesting); + +static inline void enter_lazy(enum xen_lazy_mode mode) +{ + enum xen_lazy_mode old_mode = this_cpu_read(xen_lazy_mode); + + if (mode == old_mode) { + this_cpu_inc(xen_lazy_nesting); + return; + } + + BUG_ON(old_mode != XEN_LAZY_NONE); + + this_cpu_write(xen_lazy_mode, mode); +} + +static inline void leave_lazy(enum xen_lazy_mode mode) +{ + BUG_ON(this_cpu_read(xen_lazy_mode) != mode); + + if (this_cpu_read(xen_lazy_nesting) == 0) + this_cpu_write(xen_lazy_mode, XEN_LAZY_NONE); + else + this_cpu_dec(xen_lazy_nesting); +} + +enum xen_lazy_mode xen_get_lazy_mode(void); + #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index a5ead6a6d233..517ee01503be 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -720,13 +720,8 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { s32 *s; - /* - * Do not patch out the default return thunks if those needed are the - * ones generated by the compiler. - */ - if (cpu_feature_enabled(X86_FEATURE_RETHUNK) && - (x86_return_thunk == __x86_return_thunk)) - return; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + static_call_force_reinit(); for (s = start; s < end; s++) { void *dest = NULL, *addr = (void *)s + *s; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index c06bfc086565..faa9f2299848 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -272,7 +272,6 @@ void __init callthunks_patch_builtin_calls(void) pr_info("Setting up call depth tracking\n"); mutex_lock(&text_mutex); callthunks_setup(&cs, &builtin_coretext); - static_call_force_reinit(); thunks_initialized = true; mutex_unlock(&text_mutex); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index dd8379d84445..03ef962a6992 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -766,6 +766,15 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_TOPOEXT)) smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; + + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) { + if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB)) + setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); + else if (c->x86 >= 0x19 && !wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) { + setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); + setup_force_cpu_cap(X86_FEATURE_SBPB); + } + } } static void init_amd_k8(struct cpuinfo_x86 *c) @@ -1301,25 +1310,6 @@ void amd_check_microcode(void) on_each_cpu(zenbleed_check_cpu, NULL, 1); } -bool cpu_has_ibpb_brtype_microcode(void) -{ - switch (boot_cpu_data.x86) { - /* Zen1/2 IBPB flushes branch type predictions too. */ - case 0x17: - return boot_cpu_has(X86_FEATURE_AMD_IBPB); - case 0x19: - /* Poke the MSR bit on Zen3/4 to check its presence. */ - if (!wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) { - setup_force_cpu_cap(X86_FEATURE_SBPB); - return true; - } else { - return false; - } - default: - return false; - } -} - /* * Issue a DIV 0/1 insn to clear any division data from previous DIV * operations. diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index f081d26616ac..10499bcd4e39 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2404,27 +2404,16 @@ early_param("spec_rstack_overflow", srso_parse_cmdline); static void __init srso_select_mitigation(void) { - bool has_microcode; + bool has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE); if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) goto pred_cmd; - /* - * The first check is for the kernel running as a guest in order - * for guests to verify whether IBPB is a viable mitigation. - */ - has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) || cpu_has_ibpb_brtype_microcode(); if (!has_microcode) { pr_warn("IBPB-extending microcode not applied!\n"); pr_warn(SRSO_NOTICE); } else { /* - * Enable the synthetic (even if in a real CPUID leaf) - * flags for guests. - */ - setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); - - /* * Zen1/2 with SMT off aren't vulnerable after the right * IBPB microcode has been applied. */ @@ -2444,7 +2433,7 @@ static void __init srso_select_mitigation(void) switch (srso_cmd) { case SRSO_CMD_OFF: - return; + goto pred_cmd; case SRSO_CMD_MICROCODE: if (has_microcode) { @@ -2717,7 +2706,7 @@ static ssize_t srso_show_state(char *buf) return sysfs_emit(buf, "%s%s\n", srso_strings[srso_mitigation], - (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode")); + boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) ? "" : ", no microcode"); } static ssize_t gds_show_state(char *buf) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 975f98d5eee5..97f1436c1a20 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -143,66 +143,7 @@ int paravirt_disable_iospace(void) return request_resource(&ioport_resource, &reserve_ioports); } -static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE; - -static inline void enter_lazy(enum paravirt_lazy_mode mode) -{ - BUG_ON(this_cpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE); - - this_cpu_write(paravirt_lazy_mode, mode); -} - -static void leave_lazy(enum paravirt_lazy_mode mode) -{ - BUG_ON(this_cpu_read(paravirt_lazy_mode) != mode); - - this_cpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE); -} - -void paravirt_enter_lazy_mmu(void) -{ - enter_lazy(PARAVIRT_LAZY_MMU); -} - -void paravirt_leave_lazy_mmu(void) -{ - leave_lazy(PARAVIRT_LAZY_MMU); -} - -void paravirt_flush_lazy_mmu(void) -{ - preempt_disable(); - - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { - arch_leave_lazy_mmu_mode(); - arch_enter_lazy_mmu_mode(); - } - - preempt_enable(); -} - #ifdef CONFIG_PARAVIRT_XXL -void paravirt_start_context_switch(struct task_struct *prev) -{ - BUG_ON(preemptible()); - - if (this_cpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) { - arch_leave_lazy_mmu_mode(); - set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES); - } - enter_lazy(PARAVIRT_LAZY_CPU); -} - -void paravirt_end_context_switch(struct task_struct *next) -{ - BUG_ON(preemptible()); - - leave_lazy(PARAVIRT_LAZY_CPU); - - if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES)) - arch_enter_lazy_mmu_mode(); -} - static noinstr void pv_native_write_cr2(unsigned long val) { native_write_cr2(val); @@ -229,14 +170,6 @@ static noinstr void pv_native_safe_halt(void) } #endif -enum paravirt_lazy_mode paravirt_get_lazy_mode(void) -{ - if (in_interrupt()) - return PARAVIRT_LAZY_NONE; - - return this_cpu_read(paravirt_lazy_mode); -} - struct pv_info pv_info = { .name = "bare hardware", #ifdef CONFIG_PARAVIRT_XXL diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 9f0909142a0a..b6f4e8399fca 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -257,13 +257,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP))) io_bitmap_share(p); - /* - * If copy_thread() if failing, don't leak the shadow stack possibly - * allocated in shstk_alloc_thread_stack() above. - */ - if (ret) - shstk_free(p); - return ret; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b9145a63da77..b098b1fa2470 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -358,15 +358,11 @@ static void __init add_early_ima_buffer(u64 phys_addr) #if defined(CONFIG_HAVE_IMA_KEXEC) && !defined(CONFIG_OF_FLATTREE) int __init ima_free_kexec_buffer(void) { - int rc; - if (!ima_kexec_buffer_size) return -ENOENT; - rc = memblock_phys_free(ima_kexec_buffer_phys, - ima_kexec_buffer_size); - if (rc) - return rc; + memblock_free_late(ima_kexec_buffer_phys, + ima_kexec_buffer_size); ima_kexec_buffer_phys = 0; ima_kexec_buffer_size = 0; diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c index fd689921a1db..59e15dd8d0f8 100644 --- a/arch/x86/kernel/shstk.c +++ b/arch/x86/kernel/shstk.c @@ -205,10 +205,21 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long cl return 0; /* - * For CLONE_VM, except vfork, the child needs a separate shadow + * For CLONE_VFORK the child will share the parents shadow stack. + * Make sure to clear the internal tracking of the thread shadow + * stack so the freeing logic run for child knows to leave it alone. + */ + if (clone_flags & CLONE_VFORK) { + shstk->base = 0; + shstk->size = 0; + return 0; + } + + /* + * For !CLONE_VM the child will use a copy of the parents shadow * stack. */ - if ((clone_flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM) + if (!(clone_flags & CLONE_VM)) return 0; size = adjust_shstk_size(stack_size); @@ -408,7 +419,25 @@ void shstk_free(struct task_struct *tsk) if (!tsk->mm || tsk->mm != current->mm) return; + /* + * If shstk->base is NULL, then this task is not managing its + * own shadow stack (CLONE_VFORK). So skip freeing it. + */ + if (!shstk->base) + return; + + /* + * shstk->base is NULL for CLONE_VFORK child tasks, and so is + * normal. But size = 0 on a shstk->base is not normal and + * indicated an attempt to free the thread shadow stack twice. + * Warn about it. + */ + if (WARN_ON(!shstk->size)) + return; + unmap_shadow_stack(shstk->base, shstk->size); + + shstk->size = 0; } static int wrss_control(bool enable) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index e1d011c67cc6..f7901cb4d2fa 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6167,20 +6167,15 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); } -int kvm_mmu_init_vm(struct kvm *kvm) +void kvm_mmu_init_vm(struct kvm *kvm) { - int r; - INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); - if (tdp_mmu_enabled) { - r = kvm_mmu_init_tdp_mmu(kvm); - if (r < 0) - return r; - } + if (tdp_mmu_enabled) + kvm_mmu_init_tdp_mmu(kvm); kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache; kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO; @@ -6189,8 +6184,6 @@ int kvm_mmu_init_vm(struct kvm *kvm) kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache; kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO; - - return 0; } static void mmu_free_vm_memory_caches(struct kvm *kvm) @@ -6246,7 +6239,6 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { bool flush; - int i; if (WARN_ON_ONCE(gfn_end <= gfn_start)) return; @@ -6257,11 +6249,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); - if (tdp_mmu_enabled) { - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start, - gfn_end, true, flush); - } + if (tdp_mmu_enabled) + flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush); if (flush) kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index b102014e2c60..decc1f153669 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -58,7 +58,12 @@ struct kvm_mmu_page { bool tdp_mmu_page; bool unsync; - u8 mmu_valid_gen; + union { + u8 mmu_valid_gen; + + /* Only accessed under slots_lock. */ + bool tdp_mmu_scheduled_root_to_zap; + }; /* * The shadow page can't be replaced by an equivalent huge page @@ -100,13 +105,7 @@ struct kvm_mmu_page { struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ tdp_ptep_t ptep; }; - union { - DECLARE_BITMAP(unsync_child_bitmap, 512); - struct { - struct work_struct tdp_mmu_async_work; - void *tdp_mmu_async_data; - }; - }; + DECLARE_BITMAP(unsync_child_bitmap, 512); /* * Tracks shadow pages that, if zapped, would allow KVM to create an NX diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 6c63f2d1675f..6cd4dd631a2f 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -12,18 +12,10 @@ #include <trace/events/kvm.h> /* Initializes the TDP MMU for the VM, if enabled. */ -int kvm_mmu_init_tdp_mmu(struct kvm *kvm) +void kvm_mmu_init_tdp_mmu(struct kvm *kvm) { - struct workqueue_struct *wq; - - wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0); - if (!wq) - return -ENOMEM; - INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); - kvm->arch.tdp_mmu_zap_wq = wq; - return 1; } /* Arbitrarily returns true so that this may be used in if statements. */ @@ -46,20 +38,15 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) * ultimately frees all roots. */ kvm_tdp_mmu_invalidate_all_roots(kvm); - - /* - * Destroying a workqueue also first flushes the workqueue, i.e. no - * need to invoke kvm_tdp_mmu_zap_invalidated_roots(). - */ - destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); + kvm_tdp_mmu_zap_invalidated_roots(kvm); WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* * Ensure that all the outstanding RCU callbacks to free shadow pages - * can run before the VM is torn down. Work items on tdp_mmu_zap_wq - * can call kvm_tdp_mmu_put_root and create new callbacks. + * can run before the VM is torn down. Putting the last reference to + * zapped roots will create new callbacks. */ rcu_barrier(); } @@ -86,46 +73,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) tdp_mmu_free_sp(sp); } -static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared); - -static void tdp_mmu_zap_root_work(struct work_struct *work) -{ - struct kvm_mmu_page *root = container_of(work, struct kvm_mmu_page, - tdp_mmu_async_work); - struct kvm *kvm = root->tdp_mmu_async_data; - - read_lock(&kvm->mmu_lock); - - /* - * A TLB flush is not necessary as KVM performs a local TLB flush when - * allocating a new root (see kvm_mmu_load()), and when migrating vCPU - * to a different pCPU. Note, the local TLB flush on reuse also - * invalidates any paging-structure-cache entries, i.e. TLB entries for - * intermediate paging structures, that may be zapped, as such entries - * are associated with the ASID on both VMX and SVM. - */ - tdp_mmu_zap_root(kvm, root, true); - - /* - * Drop the refcount using kvm_tdp_mmu_put_root() to test its logic for - * avoiding an infinite loop. By design, the root is reachable while - * it's being asynchronously zapped, thus a different task can put its - * last reference, i.e. flowing through kvm_tdp_mmu_put_root() for an - * asynchronously zapped root is unavoidable. - */ - kvm_tdp_mmu_put_root(kvm, root, true); - - read_unlock(&kvm->mmu_lock); -} - -static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root) -{ - root->tdp_mmu_async_data = kvm; - INIT_WORK(&root->tdp_mmu_async_work, tdp_mmu_zap_root_work); - queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work); -} - void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared) { @@ -211,8 +158,12 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true) -#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, false, false) +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false); \ + _root; \ + _root = tdp_mmu_next_root(_kvm, _root, _shared, false)) \ + if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) { \ + } else /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -292,7 +243,7 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) * by a memslot update or by the destruction of the VM. Initialize the * refcount to two; one reference for the vCPU, and one reference for * the TDP MMU itself, which is held until the root is invalidated and - * is ultimately put by tdp_mmu_zap_root_work(). + * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots(). */ refcount_set(&root->tdp_mmu_root_count, 2); @@ -877,13 +828,12 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or * more SPTEs were zapped since the MMU lock was last acquired. */ -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, - bool can_yield, bool flush) +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush) { struct kvm_mmu_page *root; - for_each_tdp_mmu_root_yield_safe(kvm, root, as_id) - flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush); + for_each_tdp_mmu_root_yield_safe(kvm, root, false) + flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; } @@ -891,7 +841,6 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end, void kvm_tdp_mmu_zap_all(struct kvm *kvm) { struct kvm_mmu_page *root; - int i; /* * Zap all roots, including invalid roots, as all SPTEs must be dropped @@ -905,10 +854,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * is being destroyed or the userspace VMM has exited. In both cases, * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request. */ - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - for_each_tdp_mmu_root_yield_safe(kvm, root, i) - tdp_mmu_zap_root(kvm, root, false); - } + for_each_tdp_mmu_root_yield_safe(kvm, root, false) + tdp_mmu_zap_root(kvm, root, false); } /* @@ -917,18 +864,47 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) */ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) { - flush_workqueue(kvm->arch.tdp_mmu_zap_wq); + struct kvm_mmu_page *root; + + read_lock(&kvm->mmu_lock); + + for_each_tdp_mmu_root_yield_safe(kvm, root, true) { + if (!root->tdp_mmu_scheduled_root_to_zap) + continue; + + root->tdp_mmu_scheduled_root_to_zap = false; + KVM_BUG_ON(!root->role.invalid, kvm); + + /* + * A TLB flush is not necessary as KVM performs a local TLB + * flush when allocating a new root (see kvm_mmu_load()), and + * when migrating a vCPU to a different pCPU. Note, the local + * TLB flush on reuse also invalidates paging-structure-cache + * entries, i.e. TLB entries for intermediate paging structures, + * that may be zapped, as such entries are associated with the + * ASID on both VMX and SVM. + */ + tdp_mmu_zap_root(kvm, root, true); + + /* + * The referenced needs to be put *after* zapping the root, as + * the root must be reachable by mmu_notifiers while it's being + * zapped + */ + kvm_tdp_mmu_put_root(kvm, root, true); + } + + read_unlock(&kvm->mmu_lock); } /* * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that * is about to be zapped, e.g. in response to a memslots update. The actual - * zapping is performed asynchronously. Using a separate workqueue makes it - * easy to ensure that the destruction is performed before the "fast zap" - * completes, without keeping a separate list of invalidated roots; the list is - * effectively the list of work items in the workqueue. + * zapping is done separately so that it happens with mmu_lock with read, + * whereas invalidating roots must be done with mmu_lock held for write (unless + * the VM is being destroyed). * - * Note, the asynchronous worker is gifted the TDP MMU's reference. + * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference. * See kvm_tdp_mmu_get_vcpu_root_hpa(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) @@ -953,19 +929,20 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) /* * As above, mmu_lock isn't held when destroying the VM! There can't * be other references to @kvm, i.e. nothing else can invalidate roots - * or be consuming roots, but walking the list of roots does need to be - * guarded against roots being deleted by the asynchronous zap worker. + * or get/put references to roots. */ - rcu_read_lock(); - - list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) { + list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { + /* + * Note, invalid roots can outlive a memslot update! Invalid + * roots must be *zapped* before the memslot update completes, + * but a different task can acquire a reference and keep the + * root alive after its been zapped. + */ if (!root->role.invalid) { + root->tdp_mmu_scheduled_root_to_zap = true; root->role.invalid = true; - tdp_mmu_schedule_zap_root(kvm, root); } } - - rcu_read_unlock(); } /* @@ -1146,8 +1123,13 @@ retry: bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush) { - return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start, - range->end, range->may_block, flush); + struct kvm_mmu_page *root; + + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false) + flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, + range->may_block, flush); + + return flush; } typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter, diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 0a63b1afabd3..733a3aef3a96 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -7,7 +7,7 @@ #include "spte.h" -int kvm_mmu_init_tdp_mmu(struct kvm *kvm); +void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); @@ -20,8 +20,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared); -bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, - gfn_t end, bool can_yield, bool flush); +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); void kvm_tdp_mmu_zap_all(struct kvm *kvm); void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index b9a0a939d59f..4900c078045a 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2962,6 +2962,32 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) count, in); } +static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { + bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + + set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); + } +} + +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_cpuid_entry2 *best; + + /* For sev guests, the memory encryption bit is not reserved in CR3. */ + best = kvm_find_cpuid_entry(vcpu, 0x8000001F); + if (best) + vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); + + if (sev_es_guest(svm->vcpu.kvm)) + sev_es_vcpu_after_set_cpuid(svm); +} + static void sev_es_init_vmcb(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb01.ptr; @@ -3024,14 +3050,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); - - if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && - (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) { - set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1); - if (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP)) - svm_clr_intercept(svm, INTERCEPT_RDTSCP); - } } void sev_init_vmcb(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index f283eb47f6ac..9507df93f410 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -683,6 +683,21 @@ static int svm_hardware_enable(void) amd_pmu_enable_virt(); + /* + * If TSC_AUX virtualization is supported, TSC_AUX becomes a swap type + * "B" field (see sev_es_prepare_switch_to_guest()) for SEV-ES guests. + * Since Linux does not change the value of TSC_AUX once set, prime the + * TSC_AUX field now to avoid a RDMSR on every vCPU run. + */ + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { + struct sev_es_save_area *hostsa; + u32 msr_hi; + + hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); + + rdmsr(MSR_TSC_AUX, hostsa->tsc_aux, msr_hi); + } + return 0; } @@ -1532,7 +1547,14 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) if (tsc_scaling) __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); - if (likely(tsc_aux_uret_slot >= 0)) + /* + * TSC_AUX is always virtualized for SEV-ES guests when the feature is + * available. The user return MSR support is not required in this case + * because TSC_AUX is restored on #VMEXIT from the host save area + * (which has been initialized in svm_hardware_enable()). + */ + if (likely(tsc_aux_uret_slot >= 0) && + (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm))) kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); svm->guest_state_loaded = true; @@ -3087,6 +3109,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_TSC_AUX: /* + * TSC_AUX is always virtualized for SEV-ES guests when the + * feature is available. The user return MSR support is not + * required in this case because TSC_AUX is restored on #VMEXIT + * from the host save area (which has been initialized in + * svm_hardware_enable()). + */ + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm)) + break; + + /* * TSC_AUX is usually changed only during boot and never read * directly. Intercept TSC_AUX instead of exposing it to the * guest via direct_access_msrs, and switch it via user return. @@ -4284,7 +4316,6 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index) static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct kvm_cpuid_entry2 *best; /* * SVM doesn't provide a way to disable just XSAVES in the guest, KVM @@ -4328,12 +4359,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0, !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); - /* For sev guests, the memory encryption bit is not reserved in CR3. */ - if (sev_guest(vcpu->kvm)) { - best = kvm_find_cpuid_entry(vcpu, 0x8000001F); - if (best) - vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); - } + if (sev_guest(vcpu->kvm)) + sev_vcpu_after_set_cpuid(svm); init_vmcb_after_set_cpuid(vcpu); } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f41253958357..be67ab7fdd10 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -684,6 +684,7 @@ void __init sev_hardware_setup(void); void sev_hardware_unsetup(void); int sev_cpu_init(struct svm_cpu_data *sd); void sev_init_vmcb(struct vcpu_svm *svm); +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm); void sev_free_vcpu(struct kvm_vcpu *vcpu); int sev_handle_vmgexit(struct kvm_vcpu *vcpu); int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6c9c81e82e65..9f18b06bbda6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12308,9 +12308,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (ret) goto out; - ret = kvm_mmu_init_vm(kvm); - if (ret) - goto out_page_track; + kvm_mmu_init_vm(kvm); ret = static_call(kvm_x86_vm_init)(kvm); if (ret) @@ -12355,7 +12353,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) out_uninit_mmu: kvm_mmu_uninit_vm(kvm); -out_page_track: kvm_page_track_cleanup(kvm); out: return ret; diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 8f95fb267caa..76697df8dfd5 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -40,7 +40,7 @@ SYM_TYPED_FUNC_START(__memcpy) SYM_FUNC_END(__memcpy) EXPORT_SYMBOL(__memcpy) -SYM_FUNC_ALIAS(memcpy, __memcpy) +SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) SYM_FUNC_START_LOCAL(memcpy_orig) diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 0559b206fb11..ccdf3a597045 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -212,5 +212,5 @@ SYM_FUNC_START(__memmove) SYM_FUNC_END(__memmove) EXPORT_SYMBOL(__memmove) -SYM_FUNC_ALIAS(memmove, __memmove) +SYM_FUNC_ALIAS_MEMFUNC(memmove, __memmove) EXPORT_SYMBOL(memmove) diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 7c59a704c458..3d818b849ec6 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -40,7 +40,7 @@ SYM_FUNC_START(__memset) SYM_FUNC_END(__memset) EXPORT_SYMBOL(__memset) -SYM_FUNC_ALIAS(memset, __memset) +SYM_FUNC_ALIAS_MEMFUNC(memset, __memset) EXPORT_SYMBOL(memset) SYM_FUNC_START_LOCAL(memset_orig) diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c index 863d0d6b3edc..7250d0e0e1a9 100644 --- a/arch/x86/xen/efi.c +++ b/arch/x86/xen/efi.c @@ -138,7 +138,7 @@ void __init xen_efi_init(struct boot_params *boot_params) if (efi_systab_xen == NULL) return; - strncpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen", + strscpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen", sizeof(boot_params->efi_info.efi_loader_signature)); boot_params->efi_info.efi_systab = (__u32)__pa(efi_systab_xen); boot_params->efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index b8db2148c07d..0337392a3121 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -32,7 +32,7 @@ EXPORT_SYMBOL_GPL(hypercall_page); * &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info * but during boot it is switched to point to xen_vcpu_info. - * The pointer is used in __xen_evtchn_do_upcall to acknowledge pending events. + * The pointer is used in xen_evtchn_do_upcall to acknowledge pending events. */ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 9a192f51f1b0..3f8c34707c50 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -136,7 +136,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_xen_hvm_callback) inc_irq_stat(irq_hv_callback_count); - xen_hvm_evtchn_do_upcall(); + xen_evtchn_do_upcall(); set_irq_regs(old_regs); } diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 49352fad7d1d..bbbfdd495ebd 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -101,6 +101,17 @@ struct tls_descs { struct desc_struct desc[3]; }; +DEFINE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode) = XEN_LAZY_NONE; +DEFINE_PER_CPU(unsigned int, xen_lazy_nesting); + +enum xen_lazy_mode xen_get_lazy_mode(void) +{ + if (in_interrupt()) + return XEN_LAZY_NONE; + + return this_cpu_read(xen_lazy_mode); +} + /* * Updating the 3 TLS descriptors in the GDT on every task switch is * surprisingly expensive so we avoid updating them if they haven't @@ -362,10 +373,25 @@ static noinstr unsigned long xen_get_debugreg(int reg) return HYPERVISOR_get_debugreg(reg); } +static void xen_start_context_switch(struct task_struct *prev) +{ + BUG_ON(preemptible()); + + if (this_cpu_read(xen_lazy_mode) == XEN_LAZY_MMU) { + arch_leave_lazy_mmu_mode(); + set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES); + } + enter_lazy(XEN_LAZY_CPU); +} + static void xen_end_context_switch(struct task_struct *next) { + BUG_ON(preemptible()); + xen_mc_flush(); - paravirt_end_context_switch(next); + leave_lazy(XEN_LAZY_CPU); + if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES)) + arch_enter_lazy_mmu_mode(); } static unsigned long xen_store_tr(void) @@ -472,7 +498,7 @@ static void xen_set_ldt(const void *addr, unsigned entries) MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); - xen_mc_issue(PARAVIRT_LAZY_CPU); + xen_mc_issue(XEN_LAZY_CPU); } static void xen_load_gdt(const struct desc_ptr *dtr) @@ -568,7 +594,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu) * exception between the new %fs descriptor being loaded and * %fs being effectively cleared at __switch_to(). */ - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) + if (xen_get_lazy_mode() == XEN_LAZY_CPU) loadsegment(fs, 0); xen_mc_batch(); @@ -577,7 +603,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu) load_TLS_descriptor(t, cpu, 1); load_TLS_descriptor(t, cpu, 2); - xen_mc_issue(PARAVIRT_LAZY_CPU); + xen_mc_issue(XEN_LAZY_CPU); } static void xen_load_gs_index(unsigned int idx) @@ -909,7 +935,7 @@ static void xen_load_sp0(unsigned long sp0) mcs = xen_mc_entry(0); MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0); - xen_mc_issue(PARAVIRT_LAZY_CPU); + xen_mc_issue(XEN_LAZY_CPU); this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } @@ -973,7 +999,7 @@ static void xen_write_cr0(unsigned long cr0) MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0); - xen_mc_issue(PARAVIRT_LAZY_CPU); + xen_mc_issue(XEN_LAZY_CPU); } static void xen_write_cr4(unsigned long cr4) @@ -1156,7 +1182,7 @@ static const typeof(pv_ops) xen_cpu_ops __initconst = { #endif .io_delay = xen_io_delay, - .start_context_switch = paravirt_start_context_switch, + .start_context_switch = xen_start_context_switch, .end_context_switch = xen_end_context_switch, }, }; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 1652c39e3dfb..b6830554ff69 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -236,7 +236,7 @@ static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val) u.val = pmd_val_ma(val); xen_extend_mmu_update(&u); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); preempt_enable(); } @@ -270,7 +270,7 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval) { struct mmu_update u; - if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU) + if (xen_get_lazy_mode() != XEN_LAZY_MMU) return false; xen_mc_batch(); @@ -279,7 +279,7 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval) u.val = pte_val_ma(pteval); xen_extend_mmu_update(&u); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); return true; } @@ -325,7 +325,7 @@ void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, u.val = pte_val_ma(pte); xen_extend_mmu_update(&u); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); } /* Assume pteval_t is equivalent to all the other *val_t types. */ @@ -419,7 +419,7 @@ static void xen_set_pud_hyper(pud_t *ptr, pud_t val) u.val = pud_val_ma(val); xen_extend_mmu_update(&u); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); preempt_enable(); } @@ -499,7 +499,7 @@ static void __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val) __xen_set_p4d_hyper(ptr, val); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); preempt_enable(); } @@ -531,7 +531,7 @@ static void xen_set_p4d(p4d_t *ptr, p4d_t val) if (user_ptr) __xen_set_p4d_hyper((p4d_t *)user_ptr, val); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); } #if CONFIG_PGTABLE_LEVELS >= 5 @@ -1245,7 +1245,7 @@ static noinline void xen_flush_tlb(void) op->cmd = MMUEXT_TLB_FLUSH_LOCAL; MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); preempt_enable(); } @@ -1265,7 +1265,7 @@ static void xen_flush_tlb_one_user(unsigned long addr) op->arg1.linear_addr = addr & PAGE_MASK; MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); preempt_enable(); } @@ -1302,7 +1302,7 @@ static void xen_flush_tlb_multi(const struct cpumask *cpus, MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); } static unsigned long xen_read_cr3(void) @@ -1361,7 +1361,7 @@ static void xen_write_cr3(unsigned long cr3) else __xen_write_cr3(false, 0); - xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */ + xen_mc_issue(XEN_LAZY_CPU); /* interrupts restored */ } /* @@ -1396,7 +1396,7 @@ static void __init xen_write_cr3_init(unsigned long cr3) __xen_write_cr3(true, cr3); - xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */ + xen_mc_issue(XEN_LAZY_CPU); /* interrupts restored */ } static int xen_pgd_alloc(struct mm_struct *mm) @@ -1557,7 +1557,7 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned) __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); } } @@ -1587,7 +1587,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level) __set_pfn_prot(pfn, PAGE_KERNEL); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); ClearPagePinned(page); } @@ -1804,7 +1804,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) */ xen_mc_batch(); __xen_write_cr3(true, __pa(init_top_pgt)); - xen_mc_issue(PARAVIRT_LAZY_CPU); + xen_mc_issue(XEN_LAZY_CPU); /* We can't that easily rip out L3 and L2, as the Xen pagetables are * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ... for @@ -2083,6 +2083,23 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #endif } +static void xen_enter_lazy_mmu(void) +{ + enter_lazy(XEN_LAZY_MMU); +} + +static void xen_flush_lazy_mmu(void) +{ + preempt_disable(); + + if (xen_get_lazy_mode() == XEN_LAZY_MMU) { + arch_leave_lazy_mmu_mode(); + arch_enter_lazy_mmu_mode(); + } + + preempt_enable(); +} + static void __init xen_post_allocator_init(void) { pv_ops.mmu.set_pte = xen_set_pte; @@ -2107,7 +2124,7 @@ static void xen_leave_lazy_mmu(void) { preempt_disable(); xen_mc_flush(); - paravirt_leave_lazy_mmu(); + leave_lazy(XEN_LAZY_MMU); preempt_enable(); } @@ -2166,9 +2183,9 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = { .exit_mmap = xen_exit_mmap, .lazy_mode = { - .enter = paravirt_enter_lazy_mmu, + .enter = xen_enter_lazy_mmu, .leave = xen_leave_lazy_mmu, - .flush = paravirt_flush_lazy_mmu, + .flush = xen_flush_lazy_mmu, }, .set_fixmap = xen_set_fixmap, @@ -2385,7 +2402,7 @@ static noinline void xen_flush_tlb_all(void) op->cmd = MMUEXT_TLB_FLUSH_ALL; MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF); - xen_mc_issue(PARAVIRT_LAZY_MMU); + xen_mc_issue(XEN_LAZY_MMU); preempt_enable(); } diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h index 1c51b2c87f30..c3867b585e0d 100644 --- a/arch/x86/xen/multicalls.h +++ b/arch/x86/xen/multicalls.h @@ -26,7 +26,7 @@ static inline void xen_mc_batch(void) /* need to disable interrupts until this entry is complete */ local_irq_save(flags); - trace_xen_mc_batch(paravirt_get_lazy_mode()); + trace_xen_mc_batch(xen_get_lazy_mode()); __this_cpu_write(xen_mc_irq_flags, flags); } @@ -44,7 +44,7 @@ static inline void xen_mc_issue(unsigned mode) { trace_xen_mc_issue(mode); - if ((paravirt_get_lazy_mode() & mode) == 0) + if ((xen_get_lazy_mode() & mode) == 0) xen_mc_flush(); /* restore flags saved in xen_mc_batch */ diff --git a/crypto/sm2.c b/crypto/sm2.c index 285b3cb7c0bc..5ab120d74c59 100644 --- a/crypto/sm2.c +++ b/crypto/sm2.c @@ -278,10 +278,14 @@ int sm2_compute_z_digest(struct shash_desc *desc, if (!ec) return -ENOMEM; - err = __sm2_set_pub_key(ec, key, keylen); + err = sm2_ec_ctx_init(ec); if (err) goto out_free_ec; + err = __sm2_set_pub_key(ec, key, keylen); + if (err) + goto out_deinit_ec; + bits_len = SM2_DEFAULT_USERID_LEN * 8; entl[0] = bits_len >> 8; entl[1] = bits_len & 0xff; diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c index 34626d66fa10..00c5dbbe6847 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx.c +++ b/drivers/accel/ivpu/ivpu_hw_40xx.c @@ -1046,7 +1046,8 @@ static irqreturn_t ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq) if (status == 0) return IRQ_NONE; - REGB_WR32(VPU_40XX_BUTTRESS_INTERRUPT_STAT, status); + /* Disable global interrupt before handling local buttress interrupts */ + REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x1); if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE, status)) ivpu_dbg(vdev, IRQ, "FREQ_CHANGE"); @@ -1092,6 +1093,12 @@ static irqreturn_t ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq) schedule_recovery = true; } + /* This must be done after interrupts are cleared at the source. */ + REGB_WR32(VPU_40XX_BUTTRESS_INTERRUPT_STAT, status); + + /* Re-enable global interrupt */ + REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x0); + if (schedule_recovery) ivpu_pm_schedule_recovery(vdev); diff --git a/drivers/acpi/processor_pdc.c b/drivers/acpi/processor_pdc.c index 1a8591e9a9bf..994091bd52de 100644 --- a/drivers/acpi/processor_pdc.c +++ b/drivers/acpi/processor_pdc.c @@ -19,6 +19,7 @@ static void acpi_set_pdc_bits(u32 *buf) { buf[0] = ACPI_PDC_REVISION_ID; buf[1] = 1; + buf[2] = 0; /* Twiddle arch-specific bits needed for _PDC */ arch_acpi_set_proc_cap_bits(&buf[2]); diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index d1c559879dcc..40d055560e52 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -14,7 +14,7 @@ struct cxl_cxims_data { int nr_maps; - u64 xormaps[]; + u64 xormaps[] __counted_by(nr_maps); }; /* @@ -112,9 +112,9 @@ static int cxl_parse_cxims(union acpi_subtable_headers *header, void *arg, GFP_KERNEL); if (!cximsd) return -ENOMEM; + cximsd->nr_maps = nr_maps; memcpy(cximsd->xormaps, cxims->xormap_list, nr_maps * sizeof(*cximsd->xormaps)); - cximsd->nr_maps = nr_maps; cxlrd->platform_data = cximsd; return 0; diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index ca60bb8114f2..4df4f614f490 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -715,24 +715,25 @@ static void cxl_walk_cel(struct cxl_memdev_state *mds, size_t size, u8 *cel) for (i = 0; i < cel_entries; i++) { u16 opcode = le16_to_cpu(cel_entry[i].opcode); struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); + int enabled = 0; - if (!cmd && (!cxl_is_poison_command(opcode) || - !cxl_is_security_command(opcode))) { - dev_dbg(dev, - "Opcode 0x%04x unsupported by driver\n", opcode); - continue; - } - - if (cmd) + if (cmd) { set_bit(cmd->info.id, mds->enabled_cmds); + enabled++; + } - if (cxl_is_poison_command(opcode)) + if (cxl_is_poison_command(opcode)) { cxl_set_poison_cmd_enabled(&mds->poison, opcode); + enabled++; + } - if (cxl_is_security_command(opcode)) + if (cxl_is_security_command(opcode)) { cxl_set_security_cmd_enabled(&mds->security, opcode); + enabled++; + } - dev_dbg(dev, "Opcode 0x%04x enabled\n", opcode); + dev_dbg(dev, "Opcode 0x%04x %s\n", opcode, + enabled ? "enabled" : "unsupported by driver"); } } diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 724be8448eb4..7ca01a834e18 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2020 Intel Corporation. All rights reserved. */ +#include <linux/platform_device.h> #include <linux/memregion.h> #include <linux/workqueue.h> #include <linux/debugfs.h> @@ -706,16 +707,20 @@ static int cxl_setup_comp_regs(struct device *dev, struct cxl_register_map *map, return cxl_setup_regs(map); } -static inline int cxl_port_setup_regs(struct cxl_port *port, - resource_size_t component_reg_phys) +static int cxl_port_setup_regs(struct cxl_port *port, + resource_size_t component_reg_phys) { + if (dev_is_platform(port->uport_dev)) + return 0; return cxl_setup_comp_regs(&port->dev, &port->comp_map, component_reg_phys); } -static inline int cxl_dport_setup_regs(struct cxl_dport *dport, - resource_size_t component_reg_phys) +static int cxl_dport_setup_regs(struct cxl_dport *dport, + resource_size_t component_reg_phys) { + if (dev_is_platform(dport->dport_dev)) + return 0; return cxl_setup_comp_regs(dport->dport_dev, &dport->comp_map, component_reg_phys); } diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index e115ba382e04..6d63b8798c29 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -717,13 +717,35 @@ static int match_free_decoder(struct device *dev, void *data) return 0; } +static int match_auto_decoder(struct device *dev, void *data) +{ + struct cxl_region_params *p = data; + struct cxl_decoder *cxld; + struct range *r; + + if (!is_switch_decoder(dev)) + return 0; + + cxld = to_cxl_decoder(dev); + r = &cxld->hpa_range; + + if (p->res && p->res->start == r->start && p->res->end == r->end) + return 1; + + return 0; +} + static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port, struct cxl_region *cxlr) { struct device *dev; int id = 0; - dev = device_find_child(&port->dev, &id, match_free_decoder); + if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) + dev = device_find_child(&port->dev, &cxlr->params, + match_auto_decoder); + else + dev = device_find_child(&port->dev, &id, match_free_decoder); if (!dev) return NULL; /* @@ -1154,16 +1176,15 @@ static int cxl_port_setup_targets(struct cxl_port *port, } /* - * If @parent_port is masking address bits, pick the next unused address - * bit to route @port's targets. + * Interleave granularity is a multiple of @parent_port granularity. + * Multiplier is the parent port interleave ways. */ - if (parent_iw > 1 && cxl_rr->nr_targets > 1) { - u32 address_bit = max(peig + peiw, eiw + peig); - - eig = address_bit - eiw + 1; - } else { - eiw = peiw; - eig = peig; + rc = granularity_to_eig(parent_ig * parent_iw, &eig); + if (rc) { + dev_dbg(&cxlr->dev, + "%s: invalid granularity calculation (%d * %d)\n", + dev_name(&parent_port->dev), parent_ig, parent_iw); + return rc; } rc = eig_to_granularity(eig, &ig); diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 1cb1494c28fe..44a21ab7add5 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -529,7 +529,6 @@ static int cxl_pci_setup_regs(struct pci_dev *pdev, enum cxl_regloc_type type, static int cxl_pci_ras_unmask(struct pci_dev *pdev) { - struct pci_host_bridge *host_bridge = pci_find_host_bridge(pdev->bus); struct cxl_dev_state *cxlds = pci_get_drvdata(pdev); void __iomem *addr; u32 orig_val, val, mask; @@ -541,9 +540,9 @@ static int cxl_pci_ras_unmask(struct pci_dev *pdev) return 0; } - /* BIOS has CXL error control */ - if (!host_bridge->native_cxl_error) - return -ENXIO; + /* BIOS has PCIe AER error control */ + if (!pcie_aer_is_native(pdev)) + return 0; rc = pcie_capability_read_word(pdev, PCI_EXP_DEVCTL, &cap); if (rc) diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index 49b70c70dc69..79d4254d1f9b 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -1863,15 +1863,15 @@ static int cs_dsp_adsp2_setup_algs(struct cs_dsp *dsp) return PTR_ERR(adsp2_alg); for (i = 0; i < n_algs; i++) { - cs_dsp_info(dsp, - "%d: ID %x v%d.%d.%d XM@%x YM@%x ZM@%x\n", - i, be32_to_cpu(adsp2_alg[i].alg.id), - (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff0000) >> 16, - (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff00) >> 8, - be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff, - be32_to_cpu(adsp2_alg[i].xm), - be32_to_cpu(adsp2_alg[i].ym), - be32_to_cpu(adsp2_alg[i].zm)); + cs_dsp_dbg(dsp, + "%d: ID %x v%d.%d.%d XM@%x YM@%x ZM@%x\n", + i, be32_to_cpu(adsp2_alg[i].alg.id), + (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff0000) >> 16, + (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff00) >> 8, + be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff, + be32_to_cpu(adsp2_alg[i].xm), + be32_to_cpu(adsp2_alg[i].ym), + be32_to_cpu(adsp2_alg[i].zm)); alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_XM, adsp2_alg[i].alg.id, @@ -1996,14 +1996,14 @@ static int cs_dsp_halo_setup_algs(struct cs_dsp *dsp) return PTR_ERR(halo_alg); for (i = 0; i < n_algs; i++) { - cs_dsp_info(dsp, - "%d: ID %x v%d.%d.%d XM@%x YM@%x\n", - i, be32_to_cpu(halo_alg[i].alg.id), - (be32_to_cpu(halo_alg[i].alg.ver) & 0xff0000) >> 16, - (be32_to_cpu(halo_alg[i].alg.ver) & 0xff00) >> 8, - be32_to_cpu(halo_alg[i].alg.ver) & 0xff, - be32_to_cpu(halo_alg[i].xm_base), - be32_to_cpu(halo_alg[i].ym_base)); + cs_dsp_dbg(dsp, + "%d: ID %x v%d.%d.%d XM@%x YM@%x\n", + i, be32_to_cpu(halo_alg[i].alg.id), + (be32_to_cpu(halo_alg[i].alg.ver) & 0xff0000) >> 16, + (be32_to_cpu(halo_alg[i].alg.ver) & 0xff00) >> 8, + be32_to_cpu(halo_alg[i].alg.ver) & 0xff, + be32_to_cpu(halo_alg[i].xm_base), + be32_to_cpu(halo_alg[i].ym_base)); ret = cs_dsp_halo_create_regions(dsp, halo_alg[i].alg.id, halo_alg[i].alg.ver, diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 1599f1176842..ce20a60676f0 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -623,6 +623,34 @@ static __init int match_config_table(const efi_guid_t *guid, return 0; } +/** + * reserve_unaccepted - Map and reserve unaccepted configuration table + * @unaccepted: Pointer to unaccepted memory table + * + * memblock_add() makes sure that the table is mapped in direct mapping. During + * normal boot it happens automatically because the table is allocated from + * usable memory. But during crashkernel boot only memory specifically reserved + * for crash scenario is mapped. memblock_add() forces the table to be mapped + * in crashkernel case. + * + * Align the range to the nearest page borders. Ranges smaller than page size + * are not going to be mapped. + * + * memblock_reserve() makes sure that future allocations will not touch the + * table. + */ + +static __init void reserve_unaccepted(struct efi_unaccepted_memory *unaccepted) +{ + phys_addr_t start, size; + + start = PAGE_ALIGN_DOWN(efi.unaccepted); + size = PAGE_ALIGN(sizeof(*unaccepted) + unaccepted->size); + + memblock_add(start, size); + memblock_reserve(start, size); +} + int __init efi_config_parse_tables(const efi_config_table_t *config_tables, int count, const efi_config_table_type_t *arch_tables) @@ -751,11 +779,9 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, unaccepted = early_memremap(efi.unaccepted, sizeof(*unaccepted)); if (unaccepted) { - unsigned long size; if (unaccepted->version == 1) { - size = sizeof(*unaccepted) + unaccepted->size; - memblock_reserve(efi.unaccepted, size); + reserve_unaccepted(unaccepted); } else { efi.unaccepted = EFI_INVALID_TABLE_ADDR; } diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 271db3639a78..44bf1709a648 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -19,6 +19,7 @@ #include <linux/irq.h> #include <linux/irq_sim.h> #include <linux/list.h> +#include <linux/minmax.h> #include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/mutex.h> @@ -685,52 +686,32 @@ gpio_sim_device_config_live_show(struct config_item *item, char *page) return sprintf(page, "%c\n", live ? '1' : '0'); } -static char **gpio_sim_make_line_names(struct gpio_sim_bank *bank, - unsigned int *line_names_size) +static unsigned int gpio_sim_get_line_names_size(struct gpio_sim_bank *bank) { - unsigned int max_offset = 0; - bool has_line_names = false; struct gpio_sim_line *line; - char **line_names; + unsigned int size = 0; list_for_each_entry(line, &bank->line_list, siblings) { - if (line->offset >= bank->num_lines) + if (!line->name || (line->offset >= bank->num_lines)) continue; - if (line->name) { - if (line->offset > max_offset) - max_offset = line->offset; - - /* - * max_offset can stay at 0 so it's not an indicator - * of whether line names were configured at all. - */ - has_line_names = true; - } + size = max(size, line->offset + 1); } - if (!has_line_names) - /* - * This is not an error - NULL means, there are no line - * names configured. - */ - return NULL; - - *line_names_size = max_offset + 1; + return size; +} - line_names = kcalloc(*line_names_size, sizeof(*line_names), GFP_KERNEL); - if (!line_names) - return ERR_PTR(-ENOMEM); +static void +gpio_sim_set_line_names(struct gpio_sim_bank *bank, char **line_names) +{ + struct gpio_sim_line *line; list_for_each_entry(line, &bank->line_list, siblings) { - if (line->offset >= bank->num_lines) + if (!line->name || (line->offset >= bank->num_lines)) continue; - if (line->name && (line->offset <= max_offset)) - line_names[line->offset] = line->name; + line_names[line->offset] = line->name; } - - return line_names; } static void gpio_sim_remove_hogs(struct gpio_sim_device *dev) @@ -834,7 +815,7 @@ gpio_sim_make_bank_swnode(struct gpio_sim_bank *bank, struct fwnode_handle *parent) { struct property_entry properties[GPIO_SIM_PROP_MAX]; - unsigned int prop_idx = 0, line_names_size = 0; + unsigned int prop_idx = 0, line_names_size; char **line_names __free(kfree) = NULL; memset(properties, 0, sizeof(properties)); @@ -845,14 +826,19 @@ gpio_sim_make_bank_swnode(struct gpio_sim_bank *bank, properties[prop_idx++] = PROPERTY_ENTRY_STRING("gpio-sim,label", bank->label); - line_names = gpio_sim_make_line_names(bank, &line_names_size); - if (IS_ERR(line_names)) - return ERR_CAST(line_names); + line_names_size = gpio_sim_get_line_names_size(bank); + if (line_names_size) { + line_names = kcalloc(line_names_size, sizeof(*line_names), + GFP_KERNEL); + if (!line_names) + return ERR_PTR(-ENOMEM); + + gpio_sim_set_line_names(bank, line_names); - if (line_names) properties[prop_idx++] = PROPERTY_ENTRY_STRING_ARRAY_LEN( "gpio-line-names", line_names, line_names_size); + } return fwnode_create_software_node(properties, parent); } diff --git a/drivers/gpio/gpio-tb10x.c b/drivers/gpio/gpio-tb10x.c index 78f8790168ae..f96d260a4a19 100644 --- a/drivers/gpio/gpio-tb10x.c +++ b/drivers/gpio/gpio-tb10x.c @@ -195,7 +195,7 @@ static int tb10x_gpio_probe(struct platform_device *pdev) handle_edge_irq, IRQ_NOREQUEST, IRQ_NOPROBE, IRQ_GC_INIT_MASK_CACHE); if (ret) - return ret; + goto err_remove_domain; gc = tb10x_gpio->domain->gc->gc[0]; gc->reg_base = tb10x_gpio->base; @@ -209,6 +209,10 @@ static int tb10x_gpio_probe(struct platform_device *pdev) } return 0; + +err_remove_domain: + irq_domain_remove(tb10x_gpio->domain); + return ret; } static int tb10x_gpio_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index ab9ef1c20349..3caa020391c7 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -136,7 +136,7 @@ config DRM_FBDEV_EMULATION bool "Enable legacy fbdev support for your modesetting driver" depends on DRM select FRAMEBUFFER_CONSOLE_DETECT_PRIMARY if FRAMEBUFFER_CONSOLE - default y + default FB help Choose this option if you have a need for the legacy fbdev support. Note that this support also provides the linux console diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 73ee14f7a9a4..dce9e7d5e4ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -1776,7 +1776,7 @@ static ssize_t amdgpu_atombios_get_vbios_version(struct device *dev, struct amdgpu_device *adev = drm_to_adev(ddev); struct atom_context *ctx = adev->mode_info.atom_context; - return sysfs_emit(buf, "%s\n", ctx->vbios_ver_str); + return sysfs_emit(buf, "%s\n", ctx->vbios_pn); } static DEVICE_ATTR(vbios_version, 0444, amdgpu_atombios_get_vbios_version, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 937c54fc7174..163445baa4fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -801,6 +801,7 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev, enable ? "enable":"disable", get_ras_block_str(head), amdgpu_ras_is_poison_mode_supported(adev), ret); + kfree(info); return ret; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 8a6cb41444a4..0d3d538b64eb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -216,7 +216,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, if (q->wptr_bo) { wptr_addr_off = (uint64_t)q->properties.write_ptr & (PAGE_SIZE - 1); - queue_input.wptr_mc_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off; + queue_input.wptr_mc_addr = amdgpu_bo_gpu_offset(q->wptr_bo) + wptr_addr_off; } queue_input.is_kfd_process = 1; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index c6fd34bab358..868946dd7ef1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -6098,8 +6098,6 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (recalculate_timing) drm_mode_set_crtcinfo(&saved_mode, 0); - else if (!old_stream) - drm_mode_set_crtcinfo(&mode, 0); /* * If scaling is enabled and refresh rate didn't change @@ -6661,6 +6659,8 @@ enum drm_mode_status amdgpu_dm_connector_mode_valid(struct drm_connector *connec goto fail; } + drm_mode_set_crtcinfo(mode, 0); + stream = create_validate_stream_for_sink(aconnector, mode, to_dm_connector_state(connector->state), NULL); diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 478281f2a5ba..2a6157555fd1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1178,12 +1178,15 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx) dto_params.otg_inst = tg->inst; dto_params.timing = &pipe_ctx->stream->timing; dp_hpo_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst; - dccg->funcs->set_dtbclk_dto(dccg, &dto_params); - dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst); - dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst); - } else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST && dccg->funcs->disable_symclk_se) + if (dccg) { + dccg->funcs->set_dtbclk_dto(dccg, &dto_params); + dccg->funcs->disable_symclk32_se(dccg, dp_hpo_inst); + dccg->funcs->set_dpstreamclk(dccg, REFCLK, tg->inst, dp_hpo_inst); + } + } else if (dccg && dccg->funcs->disable_symclk_se) { dccg->funcs->disable_symclk_se(dccg, stream_enc->stream_enc_inst, link_enc->transmitter - TRANSMITTER_UNIPHY_A); + } if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) { /* TODO: This looks like a bug to me as we are disabling HPO IO when @@ -2658,11 +2661,11 @@ void dce110_prepare_bandwidth( struct clk_mgr *dccg = dc->clk_mgr; dce110_set_safe_displaymarks(&context->res_ctx, dc->res_pool); - - dccg->funcs->update_clocks( - dccg, - context, - false); + if (dccg) + dccg->funcs->update_clocks( + dccg, + context, + false); } void dce110_optimize_bandwidth( @@ -2673,10 +2676,11 @@ void dce110_optimize_bandwidth( dce110_set_displaymarks(dc, context); - dccg->funcs->update_clocks( - dccg, - context, - true); + if (dccg) + dccg->funcs->update_clocks( + dccg, + context, + true); } static void dce110_program_front_end_for_pipe( diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index e72f15ac0048..aeadc587433f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2692,8 +2692,6 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx) struct dce_hwseq *hws = dc->hwseq; unsigned int k1_div = PIXEL_RATE_DIV_NA; unsigned int k2_div = PIXEL_RATE_DIV_NA; - struct link_encoder *link_enc = link_enc_cfg_get_link_enc(pipe_ctx->stream->link); - struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; if (dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) { if (dc->hwseq->funcs.setup_hpo_hw_control) @@ -2713,10 +2711,8 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx) dto_params.timing = &pipe_ctx->stream->timing; dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr); dccg->funcs->set_dtbclk_dto(dccg, &dto_params); - } else if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST && dccg->funcs->enable_symclk_se) - dccg->funcs->enable_symclk_se(dccg, - stream_enc->stream_enc_inst, link_enc->transmitter - TRANSMITTER_UNIPHY_A); - + } else { + } if (hws->funcs.calculate_dccg_k1_k2_values && dc->res_pool->dccg->funcs->set_pixel_rate_div) { hws->funcs.calculate_dccg_k1_k2_values(pipe_ctx, &k1_div, &k2_div); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c index 3082da04a63d..1d052f08aff5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c @@ -75,7 +75,7 @@ void mpc32_power_on_blnd_lut( if (power_on) { REG_UPDATE(MPCC_MCM_MEM_PWR_CTRL[mpcc_id], MPCC_MCM_1DLUT_MEM_PWR_FORCE, 0); REG_WAIT(MPCC_MCM_MEM_PWR_CTRL[mpcc_id], MPCC_MCM_1DLUT_MEM_PWR_STATE, 0, 1, 5); - } else { + } else if (!mpc->ctx->dc->debug.disable_mem_low_power) { ASSERT(false); /* TODO: change to mpc * dpp_base->ctx->dc->optimized_required = true; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index ee15486fed0d..e85d70a62123 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -558,7 +558,6 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id, DRIVER_CAPS(i915)->has_logical_contexts = true; ewma__engine_latency_init(&engine->latency); - seqcount_init(&engine->stats.execlists.lock); ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 8a641bcf777c..3292524469d5 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3550,6 +3550,8 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) logical_ring_default_vfuncs(engine); logical_ring_default_irqs(engine); + seqcount_init(&engine->stats.execlists.lock); + if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) rcs_submission_override(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 957d0aeb0c02..c378cc7c953c 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1094,6 +1094,9 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine) I915_BO_ALLOC_PM_VOLATILE); if (IS_ERR(obj)) { obj = i915_gem_object_create_shmem(engine->i915, context_size); + if (IS_ERR(obj)) + return ERR_CAST(obj); + /* * Wa_22016122933: For Media version 13.0, all Media GT shared * memory needs to be mapped as WC on CPU side and UC (PAT @@ -1102,8 +1105,6 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine) if (intel_gt_needs_wa_22016122933(engine->gt)) i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE); } - if (IS_ERR(obj)) - return ERR_CAST(obj); vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL); if (IS_ERR(vma)) { diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c index 9913971fa5d2..25ea76558690 100644 --- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c +++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c @@ -334,6 +334,8 @@ static void meson_encoder_hdmi_hpd_notify(struct drm_bridge *bridge, return; cec_notifier_set_phys_addr_from_edid(encoder_hdmi->cec_notifier, edid); + + kfree(edid); } else cec_notifier_phys_addr_invalidate(encoder_hdmi->cec_notifier); } diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 1fe17ff95f5e..e73a233c6572 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -189,21 +189,12 @@ u_free(void *addr) static inline void * u_memcpya(uint64_t user, unsigned int nmemb, unsigned int size) { - void *mem; - void __user *userptr = (void __force __user *)(uintptr_t)user; + void __user *userptr = u64_to_user_ptr(user); + size_t bytes; - size *= nmemb; - - mem = kvmalloc(size, GFP_KERNEL); - if (!mem) - return ERR_PTR(-ENOMEM); - - if (copy_from_user(mem, userptr, size)) { - u_free(mem); - return ERR_PTR(-EFAULT); - } - - return mem; + if (unlikely(check_mul_overflow(nmemb, size, &bytes))) + return ERR_PTR(-EOVERFLOW); + return vmemdup_user(userptr, bytes); } #include <nvif/object.h> diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c index 19024ce21fbb..5dda94e1318c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_exec.c +++ b/drivers/gpu/drm/nouveau/nouveau_exec.c @@ -213,7 +213,7 @@ nouveau_exec_job_timeout(struct nouveau_job *job) nouveau_sched_entity_fini(job->entity); - return DRM_GPU_SCHED_STAT_ENODEV; + return DRM_GPU_SCHED_STAT_NOMINAL; } static struct nouveau_job_ops nouveau_exec_job_ops = { diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 61d9e70da9fd..ca762ea55413 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -207,7 +207,7 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha int nouveau_fence_emit(struct nouveau_fence *fence) { - struct nouveau_channel *chan = fence->channel; + struct nouveau_channel *chan = unrcu_pointer(fence->channel); struct nouveau_fence_chan *fctx = chan->fence; struct nouveau_fence_priv *priv = (void*)chan->drm->fence; int ret; diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c index 88217185e0f3..3b7ea5221226 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.c +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c @@ -375,14 +375,20 @@ nouveau_sched_run_job(struct drm_sched_job *sched_job) static enum drm_gpu_sched_stat nouveau_sched_timedout_job(struct drm_sched_job *sched_job) { + struct drm_gpu_scheduler *sched = sched_job->sched; struct nouveau_job *job = to_nouveau_job(sched_job); + enum drm_gpu_sched_stat stat = DRM_GPU_SCHED_STAT_NOMINAL; - NV_PRINTK(warn, job->cli, "Job timed out.\n"); + drm_sched_stop(sched, sched_job); if (job->ops->timeout) - return job->ops->timeout(job); + stat = job->ops->timeout(job); + else + NV_PRINTK(warn, job->cli, "Generic job timeout.\n"); + + drm_sched_start(sched, true); - return DRM_GPU_SCHED_STAT_ENODEV; + return stat; } static void diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c index 186b28dc7038..05d5e7af6d25 100644 --- a/drivers/gpu/drm/tests/drm_mm_test.c +++ b/drivers/gpu/drm/tests/drm_mm_test.c @@ -939,7 +939,7 @@ static void drm_test_mm_insert_range(struct kunit *test) KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, 0, max - 1)); KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, 0, max / 2)); KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, - max / 2, max / 2)); + max / 2, max)); KUNIT_ASSERT_FALSE(test, __drm_test_mm_insert_range(test, count, size, max / 4 + 1, 3 * max / 4 - 1)); diff --git a/drivers/gpu/drm/virtio/virtgpu_submit.c b/drivers/gpu/drm/virtio/virtgpu_submit.c index 3c00135ead45..5c514946bbad 100644 --- a/drivers/gpu/drm/virtio/virtgpu_submit.c +++ b/drivers/gpu/drm/virtio/virtgpu_submit.c @@ -361,7 +361,6 @@ static void virtio_gpu_complete_submit(struct virtio_gpu_submit *submit) submit->buf = NULL; submit->buflist = NULL; submit->sync_file = NULL; - submit->out_fence = NULL; submit->out_fence_fd = -1; } diff --git a/drivers/hwmon/nct6775-core.c b/drivers/hwmon/nct6775-core.c index 02a71244fc3b..b5b81bd83bb1 100644 --- a/drivers/hwmon/nct6775-core.c +++ b/drivers/hwmon/nct6775-core.c @@ -1910,6 +1910,10 @@ static umode_t nct6775_in_is_visible(struct kobject *kobj, struct device *dev = kobj_to_dev(kobj); struct nct6775_data *data = dev_get_drvdata(dev); int in = index / 5; /* voltage index */ + int nr = index % 5; /* attribute index */ + + if (nr == 1 && data->ALARM_BITS[in] == -1) + return 0; if (!(data->have_in & BIT(in))) return 0; diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index cdd8c67d9129..affcfb243f0f 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -441,8 +441,25 @@ err_release_lock: void __i2c_dw_disable(struct dw_i2c_dev *dev) { + unsigned int raw_intr_stats; + unsigned int enable; int timeout = 100; + bool abort_needed; unsigned int status; + int ret; + + regmap_read(dev->map, DW_IC_RAW_INTR_STAT, &raw_intr_stats); + regmap_read(dev->map, DW_IC_ENABLE, &enable); + + abort_needed = raw_intr_stats & DW_IC_INTR_MST_ON_HOLD; + if (abort_needed) { + regmap_write(dev->map, DW_IC_ENABLE, enable | DW_IC_ENABLE_ABORT); + ret = regmap_read_poll_timeout(dev->map, DW_IC_ENABLE, enable, + !(enable & DW_IC_ENABLE_ABORT), 10, + 100); + if (ret) + dev_err(dev->dev, "timeout while trying to abort current transfer\n"); + } do { __i2c_dw_disable_nowait(dev); diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index cf4f684f5356..a7f6f3eafad7 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -98,6 +98,7 @@ #define DW_IC_INTR_START_DET BIT(10) #define DW_IC_INTR_GEN_CALL BIT(11) #define DW_IC_INTR_RESTART_DET BIT(12) +#define DW_IC_INTR_MST_ON_HOLD BIT(13) #define DW_IC_INTR_DEFAULT_MASK (DW_IC_INTR_RX_FULL | \ DW_IC_INTR_TX_ABRT | \ @@ -108,6 +109,8 @@ DW_IC_INTR_RX_UNDER | \ DW_IC_INTR_RD_REQ) +#define DW_IC_ENABLE_ABORT BIT(1) + #define DW_IC_STATUS_ACTIVITY BIT(0) #define DW_IC_STATUS_TFE BIT(2) #define DW_IC_STATUS_RFNE BIT(3) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 73ae06432133..1d855258a45d 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1754,6 +1754,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) "SMBus I801 adapter at %04lx", priv->smba); err = i2c_add_adapter(&priv->adapter); if (err) { + platform_device_unregister(priv->tco_pdev); i801_acpi_remove(priv); return err; } diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index b3bb97762c85..71391b590ada 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -710,7 +710,7 @@ static irqreturn_t xiic_process(int irq, void *dev_id) * reset the IP instead of just flush fifos */ ret = xiic_reinit(i2c); - if (!ret) + if (ret < 0) dev_dbg(i2c->adap.dev.parent, "reinit failed\n"); if (i2c->rx_msg) { diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c index a3a122fae71e..22f2280eab7f 100644 --- a/drivers/i2c/muxes/i2c-demux-pinctrl.c +++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c @@ -243,6 +243,10 @@ static int i2c_demux_pinctrl_probe(struct platform_device *pdev) props[i].name = devm_kstrdup(&pdev->dev, "status", GFP_KERNEL); props[i].value = devm_kstrdup(&pdev->dev, "ok", GFP_KERNEL); + if (!props[i].name || !props[i].value) { + err = -ENOMEM; + goto err_rollback; + } props[i].length = 3; of_changeset_init(&priv->chan[i].chgset); diff --git a/drivers/i2c/muxes/i2c-mux-gpio.c b/drivers/i2c/muxes/i2c-mux-gpio.c index 5d5cbe0130cd..5ca03bd34c8d 100644 --- a/drivers/i2c/muxes/i2c-mux-gpio.c +++ b/drivers/i2c/muxes/i2c-mux-gpio.c @@ -105,8 +105,10 @@ static int i2c_mux_gpio_probe_fw(struct gpiomux *mux, } else if (is_acpi_node(child)) { rc = acpi_get_local_address(ACPI_HANDLE_FWNODE(child), values + i); - if (rc) + if (rc) { + fwnode_handle_put(child); return dev_err_probe(dev, rc, "Cannot get address\n"); + } } i++; diff --git a/drivers/media/common/videobuf2/frame_vector.c b/drivers/media/common/videobuf2/frame_vector.c index 0f430ddc1f67..fd87747be9b1 100644 --- a/drivers/media/common/videobuf2/frame_vector.c +++ b/drivers/media/common/videobuf2/frame_vector.c @@ -31,6 +31,10 @@ * different type underlying the specified range of virtual addresses. * When the function isn't able to map a single page, it returns error. * + * Note that get_vaddr_frames() cannot follow VM_IO mappings. It used + * to be able to do that, but that could (racily) return non-refcounted + * pfns. + * * This function takes care of grabbing mmap_lock as necessary. */ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, bool write, @@ -59,8 +63,6 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, bool write, if (likely(ret > 0)) return ret; - /* This used to (racily) return non-refcounted pfns. Let people know */ - WARN_ONCE(1, "get_vaddr_frames() cannot follow VM_IO mapping"); vec->nr_frames = 0; return ret ? ret : -EFAULT; } diff --git a/drivers/media/i2c/imx219.c b/drivers/media/i2c/imx219.c index a1136fdfbed2..ec53abe2e84e 100644 --- a/drivers/media/i2c/imx219.c +++ b/drivers/media/i2c/imx219.c @@ -691,12 +691,12 @@ static int imx219_init_cfg(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *format; struct v4l2_rect *crop; - /* Initialize try_fmt */ + /* Initialize the format. */ format = v4l2_subdev_get_pad_format(sd, state, 0); imx219_update_pad_format(imx219, &supported_modes[0], format, MEDIA_BUS_FMT_SRGGB10_1X10); - /* Initialize crop rectangle. */ + /* Initialize the crop rectangle. */ crop = v4l2_subdev_get_pad_crop(sd, state, 0); crop->top = IMX219_PIXEL_ARRAY_TOP; crop->left = IMX219_PIXEL_ARRAY_LEFT; @@ -750,6 +750,7 @@ static int imx219_set_pad_format(struct v4l2_subdev *sd, const struct imx219_mode *mode; int exposure_max, exposure_def, hblank; struct v4l2_mbus_framefmt *format; + struct v4l2_rect *crop; mode = v4l2_find_nearest_size(supported_modes, ARRAY_SIZE(supported_modes), @@ -757,10 +758,12 @@ static int imx219_set_pad_format(struct v4l2_subdev *sd, fmt->format.width, fmt->format.height); imx219_update_pad_format(imx219, mode, &fmt->format, fmt->format.code); + format = v4l2_subdev_get_pad_format(sd, sd_state, 0); + crop = v4l2_subdev_get_pad_crop(sd, sd_state, 0); - if (imx219->mode == mode && format->code == fmt->format.code) - return 0; + *format = fmt->format; + *crop = mode->crop; if (fmt->which == V4L2_SUBDEV_FORMAT_ACTIVE) { imx219->mode = mode; @@ -788,8 +791,6 @@ static int imx219_set_pad_format(struct v4l2_subdev *sd, hblank); } - *format = fmt->format; - return 0; } diff --git a/drivers/media/i2c/max9286.c b/drivers/media/i2c/max9286.c index 20e7c7cf5eeb..be84ff1e2b17 100644 --- a/drivers/media/i2c/max9286.c +++ b/drivers/media/i2c/max9286.c @@ -1110,7 +1110,6 @@ err_async: static void max9286_v4l2_unregister(struct max9286_priv *priv) { - fwnode_handle_put(priv->sd.fwnode); v4l2_ctrl_handler_free(&priv->ctrls); v4l2_async_unregister_subdev(&priv->sd); max9286_v4l2_notifier_unregister(priv); diff --git a/drivers/media/i2c/rdacm21.c b/drivers/media/i2c/rdacm21.c index a36a709243fd..3e22df36354f 100644 --- a/drivers/media/i2c/rdacm21.c +++ b/drivers/media/i2c/rdacm21.c @@ -608,7 +608,6 @@ static void rdacm21_remove(struct i2c_client *client) v4l2_async_unregister_subdev(&dev->sd); v4l2_ctrl_handler_free(&dev->ctrls); i2c_unregister_device(dev->isp); - fwnode_handle_put(dev->sd.fwnode); } static const struct of_device_id rdacm21_of_ids[] = { diff --git a/drivers/media/pci/bt8xx/bttv-risc.c b/drivers/media/pci/bt8xx/bttv-risc.c index 436baf6c8b08..241a696e374a 100644 --- a/drivers/media/pci/bt8xx/bttv-risc.c +++ b/drivers/media/pci/bt8xx/bttv-risc.c @@ -68,9 +68,7 @@ bttv_risc_packed(struct bttv *btv, struct btcx_riscmem *risc, sg = sglist; for (line = 0; line < store_lines; line++) { if ((line >= (store_lines - VCR_HACK_LINES)) && - (btv->opt_vcr_hack || - (V4L2_FIELD_HAS_BOTH(btv->field) || - btv->field == V4L2_FIELD_ALTERNATE))) + btv->opt_vcr_hack) continue; while (offset && offset >= sg_dma_len(sg)) { offset -= sg_dma_len(sg); diff --git a/drivers/media/pci/intel/ivsc/Kconfig b/drivers/media/pci/intel/ivsc/Kconfig index 1ef1c4e3750d..212753450576 100644 --- a/drivers/media/pci/intel/ivsc/Kconfig +++ b/drivers/media/pci/intel/ivsc/Kconfig @@ -3,7 +3,10 @@ config INTEL_VSC tristate "Intel Visual Sensing Controller" - depends on INTEL_MEI && ACPI + depends on INTEL_MEI && ACPI && VIDEO_DEV + select MEDIA_CONTROLLER + select VIDEO_V4L2_SUBDEV_API + select V4L2_ASYNC help This adds support for Intel Visual Sensing Controller (IVSC). diff --git a/drivers/media/platform/marvell/Kconfig b/drivers/media/platform/marvell/Kconfig index ec1a16734a28..d6499ffe30e8 100644 --- a/drivers/media/platform/marvell/Kconfig +++ b/drivers/media/platform/marvell/Kconfig @@ -7,7 +7,7 @@ config VIDEO_CAFE_CCIC depends on V4L_PLATFORM_DRIVERS depends on PCI && I2C && VIDEO_DEV depends on COMMON_CLK - select VIDEO_OV7670 + select VIDEO_OV7670 if MEDIA_SUBDRV_AUTOSELECT && VIDEO_CAMERA_SENSOR select VIDEOBUF2_VMALLOC select VIDEOBUF2_DMA_CONTIG select VIDEOBUF2_DMA_SG @@ -22,7 +22,7 @@ config VIDEO_MMP_CAMERA depends on I2C && VIDEO_DEV depends on ARCH_MMP || COMPILE_TEST depends on COMMON_CLK - select VIDEO_OV7670 + select VIDEO_OV7670 if MEDIA_SUBDRV_AUTOSELECT && VIDEO_CAMERA_SENSOR select I2C_GPIO select VIDEOBUF2_VMALLOC select VIDEOBUF2_DMA_CONTIG diff --git a/drivers/media/platform/nxp/imx-mipi-csis.c b/drivers/media/platform/nxp/imx-mipi-csis.c index 16f19a640130..5f93712bf485 100644 --- a/drivers/media/platform/nxp/imx-mipi-csis.c +++ b/drivers/media/platform/nxp/imx-mipi-csis.c @@ -1490,7 +1490,6 @@ err_cleanup: v4l2_async_unregister_subdev(&csis->sd); err_disable_clock: mipi_csis_clk_disable(csis); - fwnode_handle_put(csis->sd.fwnode); return ret; } @@ -1510,7 +1509,6 @@ static void mipi_csis_remove(struct platform_device *pdev) mipi_csis_clk_disable(csis); v4l2_subdev_cleanup(&csis->sd); media_entity_cleanup(&csis->sd.entity); - fwnode_handle_put(csis->sd.fwnode); pm_runtime_set_suspended(&pdev->dev); } diff --git a/drivers/media/platform/via/Kconfig b/drivers/media/platform/via/Kconfig index 8926eb0803b2..6e603c038248 100644 --- a/drivers/media/platform/via/Kconfig +++ b/drivers/media/platform/via/Kconfig @@ -7,7 +7,7 @@ config VIDEO_VIA_CAMERA depends on V4L_PLATFORM_DRIVERS depends on FB_VIA && VIDEO_DEV select VIDEOBUF2_DMA_SG - select VIDEO_OV7670 + select VIDEO_OV7670 if VIDEO_CAMERA_SENSOR help Driver support for the integrated camera controller in VIA Chrome9 chipsets. Currently only tested on OLPC xo-1.5 systems diff --git a/drivers/media/usb/em28xx/Kconfig b/drivers/media/usb/em28xx/Kconfig index b3c472b8c5a9..cb61fd6cc6c6 100644 --- a/drivers/media/usb/em28xx/Kconfig +++ b/drivers/media/usb/em28xx/Kconfig @@ -12,8 +12,8 @@ config VIDEO_EM28XX_V4L2 select VIDEO_SAA711X if MEDIA_SUBDRV_AUTOSELECT select VIDEO_TVP5150 if MEDIA_SUBDRV_AUTOSELECT select VIDEO_MSP3400 if MEDIA_SUBDRV_AUTOSELECT - select VIDEO_MT9V011 if MEDIA_SUBDRV_AUTOSELECT && MEDIA_CAMERA_SUPPORT - select VIDEO_OV2640 if MEDIA_SUBDRV_AUTOSELECT && MEDIA_CAMERA_SUPPORT + select VIDEO_MT9V011 if MEDIA_SUBDRV_AUTOSELECT && VIDEO_CAMERA_SENSOR + select VIDEO_OV2640 if MEDIA_SUBDRV_AUTOSELECT && VIDEO_CAMERA_SENSOR help This is a video4linux driver for Empia 28xx based TV cards. diff --git a/drivers/media/usb/go7007/Kconfig b/drivers/media/usb/go7007/Kconfig index 4ff79940ad8d..b2a15d9fb1f3 100644 --- a/drivers/media/usb/go7007/Kconfig +++ b/drivers/media/usb/go7007/Kconfig @@ -12,8 +12,8 @@ config VIDEO_GO7007 select VIDEO_TW2804 if MEDIA_SUBDRV_AUTOSELECT select VIDEO_TW9903 if MEDIA_SUBDRV_AUTOSELECT select VIDEO_TW9906 if MEDIA_SUBDRV_AUTOSELECT - select VIDEO_OV7640 if MEDIA_SUBDRV_AUTOSELECT && MEDIA_CAMERA_SUPPORT select VIDEO_UDA1342 if MEDIA_SUBDRV_AUTOSELECT + select VIDEO_OV7640 if MEDIA_SUBDRV_AUTOSELECT && VIDEO_CAMERA_SENSOR help This is a video4linux driver for the WIS GO7007 MPEG encoder chip. diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c index 5e9d3da862dd..e59a463c2761 100644 --- a/drivers/media/usb/uvc/uvc_ctrl.c +++ b/drivers/media/usb/uvc/uvc_ctrl.c @@ -1402,6 +1402,9 @@ int uvc_query_v4l2_menu(struct uvc_video_chain *chain, query_menu->id = id; query_menu->index = index; + if (index >= BITS_PER_TYPE(mapping->menu_mask)) + return -EINVAL; + ret = mutex_lock_interruptible(&chain->ctrl_mutex); if (ret < 0) return -ERESTARTSYS; diff --git a/drivers/mfd/cs42l43.c b/drivers/mfd/cs42l43.c index 37b23e9bae82..7b6d07cbe6fc 100644 --- a/drivers/mfd/cs42l43.c +++ b/drivers/mfd/cs42l43.c @@ -1178,8 +1178,8 @@ err: } EXPORT_NS_GPL_DEV_PM_OPS(cs42l43_pm_ops, MFD_CS42L43) = { - SET_SYSTEM_SLEEP_PM_OPS(cs42l43_suspend, cs42l43_resume) - SET_RUNTIME_PM_OPS(cs42l43_runtime_suspend, cs42l43_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(cs42l43_suspend, cs42l43_resume) + RUNTIME_PM_OPS(cs42l43_runtime_suspend, cs42l43_runtime_resume, NULL) }; MODULE_DESCRIPTION("CS42L43 Core Driver"); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index ad32ca81f7ef..f955bde10cf9 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1833,6 +1833,9 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, return work_done; error: + if (xdp_flags & ENA_XDP_REDIRECT) + xdp_do_flush(); + adapter = netdev_priv(rx_ring->netdev); if (rc == -ENOSPC) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 5cc0dbe12132..7551aa8068f8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2614,6 +2614,7 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget) struct rx_cmp_ext *rxcmp1; u32 cp_cons, tmp_raw_cons; u32 raw_cons = cpr->cp_raw_cons; + bool flush_xdp = false; u32 rx_pkts = 0; u8 event = 0; @@ -2648,6 +2649,8 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget) rx_pkts++; else if (rc == -EBUSY) /* partial completion */ break; + if (event & BNXT_REDIRECT_EVENT) + flush_xdp = true; } else if (unlikely(TX_CMP_TYPE(txcmp) == CMPL_BASE_TYPE_HWRM_DONE)) { bnxt_hwrm_handler(bp, txcmp); @@ -2667,6 +2670,8 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget) if (event & BNXT_AGG_EVENT) bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); + if (flush_xdp) + xdp_do_flush(); if (!bnxt_has_work(bp, cpr) && rx_pkts < budget) { napi_complete_done(napi, rx_pkts); diff --git a/drivers/net/ethernet/engleder/tsnep_ethtool.c b/drivers/net/ethernet/engleder/tsnep_ethtool.c index 716815dad7d2..65ec1abc9442 100644 --- a/drivers/net/ethernet/engleder/tsnep_ethtool.c +++ b/drivers/net/ethernet/engleder/tsnep_ethtool.c @@ -300,10 +300,8 @@ static void tsnep_ethtool_get_channels(struct net_device *netdev, { struct tsnep_adapter *adapter = netdev_priv(netdev); - ch->max_rx = adapter->num_rx_queues; - ch->max_tx = adapter->num_tx_queues; - ch->rx_count = adapter->num_rx_queues; - ch->tx_count = adapter->num_tx_queues; + ch->max_combined = adapter->num_queues; + ch->combined_count = adapter->num_queues; } static int tsnep_ethtool_get_ts_info(struct net_device *netdev, diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index f61bd89734c5..8b992dc9bb52 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -87,8 +87,11 @@ static irqreturn_t tsnep_irq(int irq, void *arg) /* handle TX/RX queue 0 interrupt */ if ((active & adapter->queue[0].irq_mask) != 0) { - tsnep_disable_irq(adapter, adapter->queue[0].irq_mask); - napi_schedule(&adapter->queue[0].napi); + if (napi_schedule_prep(&adapter->queue[0].napi)) { + tsnep_disable_irq(adapter, adapter->queue[0].irq_mask); + /* schedule after masking to avoid races */ + __napi_schedule(&adapter->queue[0].napi); + } } return IRQ_HANDLED; @@ -99,8 +102,11 @@ static irqreturn_t tsnep_irq_txrx(int irq, void *arg) struct tsnep_queue *queue = arg; /* handle TX/RX queue interrupt */ - tsnep_disable_irq(queue->adapter, queue->irq_mask); - napi_schedule(&queue->napi); + if (napi_schedule_prep(&queue->napi)) { + tsnep_disable_irq(queue->adapter, queue->irq_mask); + /* schedule after masking to avoid races */ + __napi_schedule(&queue->napi); + } return IRQ_HANDLED; } @@ -1728,6 +1734,10 @@ static int tsnep_poll(struct napi_struct *napi, int budget) if (queue->tx) complete = tsnep_tx_poll(queue->tx, budget); + /* handle case where we are called by netpoll with a budget of 0 */ + if (unlikely(budget <= 0)) + return budget; + if (queue->rx) { done = queue->rx->xsk_pool ? tsnep_rx_poll_zc(queue->rx, napi, budget) : diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index b4895c7b3efd..cf50368441b7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3353,6 +3353,15 @@ static void hns3_set_default_feature(struct net_device *netdev) NETIF_F_HW_TC); netdev->hw_enc_features |= netdev->vlan_features | NETIF_F_TSO_MANGLEID; + + /* The device_version V3 hardware can't offload the checksum for IP in + * GRE packets, but can do it for NvGRE. So default to disable the + * checksum and GSO offload for GRE. + */ + if (ae_dev->dev_version > HNAE3_DEVICE_VERSION_V2) { + netdev->features &= ~NETIF_F_GSO_GRE; + netdev->features &= ~NETIF_F_GSO_GRE_CSUM; + } } static int hns3_alloc_buffer(struct hns3_enet_ring *ring, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 8ca368424436..c42574e29747 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3564,9 +3564,14 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) static void hclge_clear_event_cause(struct hclge_dev *hdev, u32 event_type, u32 regclr) { +#define HCLGE_IMP_RESET_DELAY 5 + switch (event_type) { case HCLGE_VECTOR0_EVENT_PTP: case HCLGE_VECTOR0_EVENT_RST: + if (regclr == BIT(HCLGE_VECTOR0_IMPRESET_INT_B)) + mdelay(HCLGE_IMP_RESET_DELAY); + hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, regclr); break; case HCLGE_VECTOR0_EVENT_MBX: @@ -7348,6 +7353,12 @@ static int hclge_del_cls_flower(struct hnae3_handle *handle, ret = hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, rule->location, NULL, false); if (ret) { + /* if tcam config fail, set rule state to TO_DEL, + * so the rule will be deleted when periodic + * task being scheduled. + */ + hclge_update_fd_list(hdev, HCLGE_FD_TO_DEL, rule->location, NULL); + set_bit(HCLGE_STATE_FD_TBL_CHANGED, &hdev->state); spin_unlock_bh(&hdev->fd_rule_lock); return ret; } @@ -8824,7 +8835,7 @@ static void hclge_update_overflow_flags(struct hclge_vport *vport, if (mac_type == HCLGE_MAC_ADDR_UC) { if (is_all_added) vport->overflow_promisc_flags &= ~HNAE3_OVERFLOW_UPE; - else + else if (hclge_is_umv_space_full(vport, true)) vport->overflow_promisc_flags |= HNAE3_OVERFLOW_UPE; } else { if (is_all_added) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 7a2f9233d695..a4d68fb216fb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1855,7 +1855,8 @@ static void hclgevf_periodic_service_task(struct hclgevf_dev *hdev) unsigned long delta = round_jiffies_relative(HZ); struct hnae3_handle *handle = &hdev->nic; - if (test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) + if (test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state) || + test_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state)) return; if (time_is_after_jiffies(hdev->last_serv_processed + HZ)) { diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c index 9406237c461e..f81a43d2cdfc 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c @@ -456,9 +456,6 @@ int hinic_set_vlan_fliter(struct hinic_dev *nic_dev, u32 en) u16 out_size = sizeof(vlan_filter); int err; - if (!hwdev) - return -EINVAL; - vlan_filter.func_idx = HINIC_HWIF_FUNC_IDX(hwif); vlan_filter.enable = en; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 8ea1a238dcef..d3d6415553ed 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -4475,9 +4475,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, goto error_pvid; i40e_vlan_stripping_enable(vsi); - i40e_vc_reset_vf(vf, true); - /* During reset the VF got a new VSI, so refresh a pointer. */ - vsi = pf->vsi[vf->lan_vsi_idx]; + /* Locked once because multiple functions below iterate list */ spin_lock_bh(&vsi->mac_filter_hash_lock); @@ -4563,6 +4561,10 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, */ vf->port_vlan_id = le16_to_cpu(vsi->info.pvid); + i40e_vc_reset_vf(vf, true); + /* During reset the VF got a new VSI, so refresh a pointer. */ + vsi = pf->vsi[vf->lan_vsi_idx]; + ret = i40e_config_vf_promiscuous_mode(vf, vsi->id, allmulti, alluni); if (ret) { dev_err(&pf->pdev->dev, "Unable to config vf promiscuous mode\n"); diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 85fba85fbb23..e110ba346185 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -521,7 +521,7 @@ void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter); void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags); -void iavf_schedule_request_stats(struct iavf_adapter *adapter); +void iavf_schedule_aq_request(struct iavf_adapter *adapter, u64 flags); void iavf_schedule_finish_config(struct iavf_adapter *adapter); void iavf_reset(struct iavf_adapter *adapter); void iavf_set_ethtool_ops(struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index a34303ad057d..90397293525f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -362,7 +362,7 @@ static void iavf_get_ethtool_stats(struct net_device *netdev, unsigned int i; /* Explicitly request stats refresh */ - iavf_schedule_request_stats(adapter); + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_REQUEST_STATS); iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 7b300c86ceda..6a2e6d64bc3a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -314,15 +314,13 @@ void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags) } /** - * iavf_schedule_request_stats - Set the flags and schedule statistics request + * iavf_schedule_aq_request - Set the flags and schedule aq request * @adapter: board private structure - * - * Sets IAVF_FLAG_AQ_REQUEST_STATS flag so iavf_watchdog_task() will explicitly - * request and refresh ethtool stats + * @flags: requested aq flags **/ -void iavf_schedule_request_stats(struct iavf_adapter *adapter) +void iavf_schedule_aq_request(struct iavf_adapter *adapter, u64 flags) { - adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS; + adapter->aq_required |= flags; mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); } @@ -823,7 +821,7 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, list_add_tail(&f->list, &adapter->vlan_filter_list); f->state = IAVF_VLAN_ADD; adapter->num_vlan_filters++; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); } clearout: @@ -845,7 +843,7 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) f = iavf_find_vlan(adapter, vlan); if (f) { f->state = IAVF_VLAN_REMOVE; - adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER); } spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -1421,7 +1419,8 @@ void iavf_down(struct iavf_adapter *adapter) iavf_clear_fdir_filters(adapter); iavf_clear_adv_rss_conf(adapter); - if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)) { + if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) && + !(test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))) { /* cancel any current operation */ adapter->current_op = VIRTCHNL_OP_UNKNOWN; /* Schedule operations to close down the HW. Don't wait diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 93bce729be76..7ab6dd58e400 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -868,6 +868,18 @@ static void igc_ethtool_get_stats(struct net_device *netdev, spin_unlock(&adapter->stats64_lock); } +static int igc_ethtool_get_previous_rx_coalesce(struct igc_adapter *adapter) +{ + return (adapter->rx_itr_setting <= 3) ? + adapter->rx_itr_setting : adapter->rx_itr_setting >> 2; +} + +static int igc_ethtool_get_previous_tx_coalesce(struct igc_adapter *adapter) +{ + return (adapter->tx_itr_setting <= 3) ? + adapter->tx_itr_setting : adapter->tx_itr_setting >> 2; +} + static int igc_ethtool_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, @@ -875,17 +887,8 @@ static int igc_ethtool_get_coalesce(struct net_device *netdev, { struct igc_adapter *adapter = netdev_priv(netdev); - if (adapter->rx_itr_setting <= 3) - ec->rx_coalesce_usecs = adapter->rx_itr_setting; - else - ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2; - - if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS)) { - if (adapter->tx_itr_setting <= 3) - ec->tx_coalesce_usecs = adapter->tx_itr_setting; - else - ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2; - } + ec->rx_coalesce_usecs = igc_ethtool_get_previous_rx_coalesce(adapter); + ec->tx_coalesce_usecs = igc_ethtool_get_previous_tx_coalesce(adapter); return 0; } @@ -910,8 +913,12 @@ static int igc_ethtool_set_coalesce(struct net_device *netdev, ec->tx_coalesce_usecs == 2) return -EINVAL; - if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs) + if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && + ec->tx_coalesce_usecs != igc_ethtool_get_previous_tx_coalesce(adapter)) { + NL_SET_ERR_MSG_MOD(extack, + "Queue Pair mode enabled, both Rx and Tx coalescing controlled by rx-usecs"); return -EINVAL; + } /* If ITR is disabled, disable DMAC */ if (ec->rx_coalesce_usecs == 0) { diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 293b45717683..98de34d0ce07 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6491,7 +6491,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, struct igc_ring *ring; int i, drops; - if (unlikely(test_bit(__IGC_DOWN, &adapter->state))) + if (unlikely(!netif_carrier_ok(dev))) return -ENETDOWN; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 4424de2ffd70..dbc518ff8276 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -734,13 +734,13 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb, dma_map_sg_err: if (si > 0) { dma_unmap_single(iq->dev, sglist[0].dma_ptr[0], - sglist[0].len[0], DMA_TO_DEVICE); - sglist[0].len[0] = 0; + sglist[0].len[3], DMA_TO_DEVICE); + sglist[0].len[3] = 0; } while (si > 1) { dma_unmap_page(iq->dev, sglist[si >> 2].dma_ptr[si & 3], - sglist[si >> 2].len[si & 3], DMA_TO_DEVICE); - sglist[si >> 2].len[si & 3] = 0; + sglist[si >> 2].len[3 - (si & 3)], DMA_TO_DEVICE); + sglist[si >> 2].len[3 - (si & 3)] = 0; si--; } tx_buffer->gather = 0; diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c index 5a520d37bea0..d0adb82d65c3 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.c @@ -69,12 +69,12 @@ int octep_iq_process_completions(struct octep_iq *iq, u16 budget) compl_sg++; dma_unmap_single(iq->dev, tx_buffer->sglist[0].dma_ptr[0], - tx_buffer->sglist[0].len[0], DMA_TO_DEVICE); + tx_buffer->sglist[0].len[3], DMA_TO_DEVICE); i = 1; /* entry 0 is main skb, unmapped above */ while (frags--) { dma_unmap_page(iq->dev, tx_buffer->sglist[i >> 2].dma_ptr[i & 3], - tx_buffer->sglist[i >> 2].len[i & 3], DMA_TO_DEVICE); + tx_buffer->sglist[i >> 2].len[3 - (i & 3)], DMA_TO_DEVICE); i++; } @@ -131,13 +131,13 @@ static void octep_iq_free_pending(struct octep_iq *iq) dma_unmap_single(iq->dev, tx_buffer->sglist[0].dma_ptr[0], - tx_buffer->sglist[0].len[0], + tx_buffer->sglist[0].len[3], DMA_TO_DEVICE); i = 1; /* entry 0 is main skb, unmapped above */ while (frags--) { dma_unmap_page(iq->dev, tx_buffer->sglist[i >> 2].dma_ptr[i & 3], - tx_buffer->sglist[i >> 2].len[i & 3], DMA_TO_DEVICE); + tx_buffer->sglist[i >> 2].len[3 - (i & 3)], DMA_TO_DEVICE); i++; } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h index 2ef57980eb47..21e75ff9f5e7 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h @@ -17,7 +17,21 @@ #define TX_BUFTYPE_NET_SG 2 #define NUM_TX_BUFTYPES 3 -/* Hardware format for Scatter/Gather list */ +/* Hardware format for Scatter/Gather list + * + * 63 48|47 32|31 16|15 0 + * ----------------------------------------- + * | Len 0 | Len 1 | Len 2 | Len 3 | + * ----------------------------------------- + * | Ptr 0 | + * ----------------------------------------- + * | Ptr 1 | + * ----------------------------------------- + * | Ptr 2 | + * ----------------------------------------- + * | Ptr 3 | + * ----------------------------------------- + */ struct octep_tx_sglist_desc { u16 len[4]; dma_addr_t dma_ptr[4]; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index e77d43848955..53b2a4ef5298 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -29,7 +29,8 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, struct bpf_prog *prog, struct nix_cqe_rx_s *cqe, - struct otx2_cq_queue *cq); + struct otx2_cq_queue *cq, + bool *need_xdp_flush); static int otx2_nix_cq_op_status(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) @@ -337,7 +338,7 @@ static bool otx2_check_rcv_errors(struct otx2_nic *pfvf, static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf, struct napi_struct *napi, struct otx2_cq_queue *cq, - struct nix_cqe_rx_s *cqe) + struct nix_cqe_rx_s *cqe, bool *need_xdp_flush) { struct nix_rx_parse_s *parse = &cqe->parse; struct nix_rx_sg_s *sg = &cqe->sg; @@ -353,7 +354,7 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf, } if (pfvf->xdp_prog) - if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq)) + if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq, need_xdp_flush)) return; skb = napi_get_frags(napi); @@ -388,6 +389,7 @@ static int otx2_rx_napi_handler(struct otx2_nic *pfvf, struct napi_struct *napi, struct otx2_cq_queue *cq, int budget) { + bool need_xdp_flush = false; struct nix_cqe_rx_s *cqe; int processed_cqe = 0; @@ -409,13 +411,15 @@ process_cqe: cq->cq_head++; cq->cq_head &= (cq->cqe_cnt - 1); - otx2_rcv_pkt_handler(pfvf, napi, cq, cqe); + otx2_rcv_pkt_handler(pfvf, napi, cq, cqe, &need_xdp_flush); cqe->hdr.cqe_type = NIX_XQE_TYPE_INVALID; cqe->sg.seg_addr = 0x00; processed_cqe++; cq->pend_cqe--; } + if (need_xdp_flush) + xdp_do_flush(); /* Free CQEs to HW */ otx2_write64(pfvf, NIX_LF_CQ_OP_DOOR, @@ -1354,7 +1358,8 @@ bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx) static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, struct bpf_prog *prog, struct nix_cqe_rx_s *cqe, - struct otx2_cq_queue *cq) + struct otx2_cq_queue *cq, + bool *need_xdp_flush) { unsigned char *hard_start, *data; int qidx = cq->cq_idx; @@ -1391,8 +1396,10 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize, DMA_FROM_DEVICE); - if (!err) + if (!err) { + *need_xdp_flush = true; return true; + } put_page(page); break; default: diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c index c07f25e791c7..fe4e166de8a0 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c @@ -243,10 +243,9 @@ static void vcap_test_api_init(struct vcap_admin *admin) } /* Helper function to create a rule of a specific size */ -static struct vcap_rule * -test_vcap_xn_rule_creator(struct kunit *test, int cid, enum vcap_user user, - u16 priority, - int id, int size, int expected_addr) +static void test_vcap_xn_rule_creator(struct kunit *test, int cid, + enum vcap_user user, u16 priority, + int id, int size, int expected_addr) { struct vcap_rule *rule; struct vcap_rule_internal *ri; @@ -311,7 +310,7 @@ test_vcap_xn_rule_creator(struct kunit *test, int cid, enum vcap_user user, ret = vcap_add_rule(rule); KUNIT_EXPECT_EQ(test, 0, ret); KUNIT_EXPECT_EQ(test, expected_addr, ri->addr); - return rule; + vcap_free_rule(rule); } /* Prepare testing rule deletion */ @@ -995,6 +994,16 @@ static void vcap_api_encode_rule_actionset_test(struct kunit *test) KUNIT_EXPECT_EQ(test, (u32)0x00000000, actwords[11]); } +static void vcap_free_ckf(struct vcap_rule *rule) +{ + struct vcap_client_keyfield *ckf, *next_ckf; + + list_for_each_entry_safe(ckf, next_ckf, &rule->keyfields, ctrl.list) { + list_del(&ckf->ctrl.list); + kfree(ckf); + } +} + static void vcap_api_rule_add_keyvalue_test(struct kunit *test) { struct vcap_admin admin = { @@ -1027,6 +1036,7 @@ static void vcap_api_rule_add_keyvalue_test(struct kunit *test) KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, kf->ctrl.type); KUNIT_EXPECT_EQ(test, 0x0, kf->data.u1.value); KUNIT_EXPECT_EQ(test, 0x1, kf->data.u1.mask); + vcap_free_ckf(rule); INIT_LIST_HEAD(&rule->keyfields); ret = vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, VCAP_BIT_1); @@ -1039,6 +1049,7 @@ static void vcap_api_rule_add_keyvalue_test(struct kunit *test) KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, kf->ctrl.type); KUNIT_EXPECT_EQ(test, 0x1, kf->data.u1.value); KUNIT_EXPECT_EQ(test, 0x1, kf->data.u1.mask); + vcap_free_ckf(rule); INIT_LIST_HEAD(&rule->keyfields); ret = vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, @@ -1052,6 +1063,7 @@ static void vcap_api_rule_add_keyvalue_test(struct kunit *test) KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, kf->ctrl.type); KUNIT_EXPECT_EQ(test, 0x0, kf->data.u1.value); KUNIT_EXPECT_EQ(test, 0x0, kf->data.u1.mask); + vcap_free_ckf(rule); INIT_LIST_HEAD(&rule->keyfields); ret = vcap_rule_add_key_u32(rule, VCAP_KF_TYPE, 0x98765432, 0xff00ffab); @@ -1064,6 +1076,7 @@ static void vcap_api_rule_add_keyvalue_test(struct kunit *test) KUNIT_EXPECT_EQ(test, VCAP_FIELD_U32, kf->ctrl.type); KUNIT_EXPECT_EQ(test, 0x98765432, kf->data.u32.value); KUNIT_EXPECT_EQ(test, 0xff00ffab, kf->data.u32.mask); + vcap_free_ckf(rule); INIT_LIST_HEAD(&rule->keyfields); ret = vcap_rule_add_key_u128(rule, VCAP_KF_L3_IP6_SIP, &dip); @@ -1078,6 +1091,18 @@ static void vcap_api_rule_add_keyvalue_test(struct kunit *test) KUNIT_EXPECT_EQ(test, dip.value[idx], kf->data.u128.value[idx]); for (idx = 0; idx < ARRAY_SIZE(dip.mask); ++idx) KUNIT_EXPECT_EQ(test, dip.mask[idx], kf->data.u128.mask[idx]); + vcap_free_ckf(rule); +} + +static void vcap_free_caf(struct vcap_rule *rule) +{ + struct vcap_client_actionfield *caf, *next_caf; + + list_for_each_entry_safe(caf, next_caf, + &rule->actionfields, ctrl.list) { + list_del(&caf->ctrl.list); + kfree(caf); + } } static void vcap_api_rule_add_actionvalue_test(struct kunit *test) @@ -1105,6 +1130,7 @@ static void vcap_api_rule_add_actionvalue_test(struct kunit *test) KUNIT_EXPECT_EQ(test, VCAP_AF_POLICE_ENA, af->ctrl.action); KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, af->ctrl.type); KUNIT_EXPECT_EQ(test, 0x0, af->data.u1.value); + vcap_free_caf(rule); INIT_LIST_HEAD(&rule->actionfields); ret = vcap_rule_add_action_bit(rule, VCAP_AF_POLICE_ENA, VCAP_BIT_1); @@ -1116,6 +1142,7 @@ static void vcap_api_rule_add_actionvalue_test(struct kunit *test) KUNIT_EXPECT_EQ(test, VCAP_AF_POLICE_ENA, af->ctrl.action); KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, af->ctrl.type); KUNIT_EXPECT_EQ(test, 0x1, af->data.u1.value); + vcap_free_caf(rule); INIT_LIST_HEAD(&rule->actionfields); ret = vcap_rule_add_action_bit(rule, VCAP_AF_POLICE_ENA, VCAP_BIT_ANY); @@ -1127,6 +1154,7 @@ static void vcap_api_rule_add_actionvalue_test(struct kunit *test) KUNIT_EXPECT_EQ(test, VCAP_AF_POLICE_ENA, af->ctrl.action); KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, af->ctrl.type); KUNIT_EXPECT_EQ(test, 0x0, af->data.u1.value); + vcap_free_caf(rule); INIT_LIST_HEAD(&rule->actionfields); ret = vcap_rule_add_action_u32(rule, VCAP_AF_TYPE, 0x98765432); @@ -1138,6 +1166,7 @@ static void vcap_api_rule_add_actionvalue_test(struct kunit *test) KUNIT_EXPECT_EQ(test, VCAP_AF_TYPE, af->ctrl.action); KUNIT_EXPECT_EQ(test, VCAP_FIELD_U32, af->ctrl.type); KUNIT_EXPECT_EQ(test, 0x98765432, af->data.u32.value); + vcap_free_caf(rule); INIT_LIST_HEAD(&rule->actionfields); ret = vcap_rule_add_action_u32(rule, VCAP_AF_MASK_MODE, 0xaabbccdd); @@ -1149,6 +1178,7 @@ static void vcap_api_rule_add_actionvalue_test(struct kunit *test) KUNIT_EXPECT_EQ(test, VCAP_AF_MASK_MODE, af->ctrl.action); KUNIT_EXPECT_EQ(test, VCAP_FIELD_U32, af->ctrl.type); KUNIT_EXPECT_EQ(test, 0xaabbccdd, af->data.u32.value); + vcap_free_caf(rule); } static void vcap_api_rule_find_keyset_basic_test(struct kunit *test) @@ -1408,6 +1438,10 @@ static void vcap_api_encode_rule_test(struct kunit *test) ret = list_empty(&is2_admin.rules); KUNIT_EXPECT_EQ(test, false, ret); KUNIT_EXPECT_EQ(test, 0, ret); + + vcap_enable_lookups(&test_vctrl, &test_netdev, 0, 0, + rule->cookie, false); + vcap_free_rule(rule); /* Check that the rule has been freed: tricky to access since this @@ -1418,6 +1452,8 @@ static void vcap_api_encode_rule_test(struct kunit *test) KUNIT_EXPECT_EQ(test, true, ret); ret = list_empty(&rule->actionfields); KUNIT_EXPECT_EQ(test, true, ret); + + vcap_del_rule(&test_vctrl, &test_netdev, id); } static void vcap_api_set_rule_counter_test(struct kunit *test) @@ -1561,6 +1597,11 @@ static void vcap_api_rule_insert_in_order_test(struct kunit *test) test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 20, 400, 6, 774); test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 30, 300, 3, 771); test_vcap_xn_rule_creator(test, 10000, VCAP_USER_QOS, 40, 200, 2, 768); + + vcap_del_rule(&test_vctrl, &test_netdev, 200); + vcap_del_rule(&test_vctrl, &test_netdev, 300); + vcap_del_rule(&test_vctrl, &test_netdev, 400); + vcap_del_rule(&test_vctrl, &test_netdev, 500); } static void vcap_api_rule_insert_reverse_order_test(struct kunit *test) @@ -1619,6 +1660,11 @@ static void vcap_api_rule_insert_reverse_order_test(struct kunit *test) ++idx; } KUNIT_EXPECT_EQ(test, 768, admin.last_used_addr); + + vcap_del_rule(&test_vctrl, &test_netdev, 500); + vcap_del_rule(&test_vctrl, &test_netdev, 400); + vcap_del_rule(&test_vctrl, &test_netdev, 300); + vcap_del_rule(&test_vctrl, &test_netdev, 200); } static void vcap_api_rule_remove_at_end_test(struct kunit *test) @@ -1819,6 +1865,9 @@ static void vcap_api_rule_remove_in_front_test(struct kunit *test) KUNIT_EXPECT_EQ(test, 786, test_init_start); KUNIT_EXPECT_EQ(test, 8, test_init_count); KUNIT_EXPECT_EQ(test, 794, admin.last_used_addr); + + vcap_del_rule(&test_vctrl, &test_netdev, 200); + vcap_del_rule(&test_vctrl, &test_netdev, 300); } static struct kunit_case vcap_api_rule_remove_test_cases[] = { diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index 6aac98bcb9f4..aae4131f146a 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -187,6 +187,7 @@ typedef void (*ionic_desc_cb)(struct ionic_queue *q, struct ionic_desc_info *desc_info, struct ionic_cq_info *cq_info, void *cb_arg); +#define IONIC_MAX_BUF_LEN ((u16)-1) #define IONIC_PAGE_SIZE PAGE_SIZE #define IONIC_PAGE_SPLIT_SZ (PAGE_SIZE / 2) #define IONIC_PAGE_GFP_MASK (GFP_ATOMIC | __GFP_NOWARN |\ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 26798fc635db..44466e8c5d77 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -207,7 +207,8 @@ static struct sk_buff *ionic_rx_frags(struct ionic_queue *q, return NULL; } - frag_len = min_t(u16, len, IONIC_PAGE_SIZE - buf_info->page_offset); + frag_len = min_t(u16, len, min_t(u32, IONIC_MAX_BUF_LEN, + IONIC_PAGE_SIZE - buf_info->page_offset)); len -= frag_len; dma_sync_single_for_cpu(dev, @@ -452,7 +453,8 @@ void ionic_rx_fill(struct ionic_queue *q) /* fill main descriptor - buf[0] */ desc->addr = cpu_to_le64(buf_info->dma_addr + buf_info->page_offset); - frag_len = min_t(u16, len, IONIC_PAGE_SIZE - buf_info->page_offset); + frag_len = min_t(u16, len, min_t(u32, IONIC_MAX_BUF_LEN, + IONIC_PAGE_SIZE - buf_info->page_offset)); desc->len = cpu_to_le16(frag_len); remain_len -= frag_len; buf_info++; @@ -471,7 +473,9 @@ void ionic_rx_fill(struct ionic_queue *q) } sg_elem->addr = cpu_to_le64(buf_info->dma_addr + buf_info->page_offset); - frag_len = min_t(u16, remain_len, IONIC_PAGE_SIZE - buf_info->page_offset); + frag_len = min_t(u16, remain_len, min_t(u32, IONIC_MAX_BUF_LEN, + IONIC_PAGE_SIZE - + buf_info->page_offset)); sg_elem->len = cpu_to_le16(frag_len); remain_len -= frag_len; buf_info++; diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c index 047322b04d4f..834f000ba1c4 100644 --- a/drivers/net/ethernet/sfc/tc.c +++ b/drivers/net/ethernet/sfc/tc.c @@ -136,6 +136,8 @@ static struct efx_tc_mac_pedit_action *efx_tc_flower_get_mac(struct efx_nic *efx if (old) { /* don't need our new entry */ kfree(ped); + if (IS_ERR(old)) /* oh dear, it's actually an error */ + return ERR_CAST(old); if (!refcount_inc_not_zero(&old->ref)) return ERR_PTR(-EAGAIN); /* existing entry found, ref taken */ @@ -602,6 +604,8 @@ static int efx_tc_flower_record_encap_match(struct efx_nic *efx, kfree(encap); if (pseudo) /* don't need our new pseudo either */ efx_tc_flower_release_encap_match(efx, pseudo); + if (IS_ERR(old)) /* oh dear, it's actually an error */ + return PTR_ERR(old); /* check old and new em_types are compatible */ switch (old->type) { case EFX_TC_EM_DIRECT: @@ -700,6 +704,8 @@ static struct efx_tc_recirc_id *efx_tc_get_recirc_id(struct efx_nic *efx, if (old) { /* don't need our new entry */ kfree(rid); + if (IS_ERR(old)) /* oh dear, it's actually an error */ + return ERR_CAST(old); if (!refcount_inc_not_zero(&old->ref)) return ERR_PTR(-EAGAIN); /* existing entry found */ @@ -1482,7 +1488,10 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, old = rhashtable_lookup_get_insert_fast(&efx->tc->match_action_ht, &rule->linkage, efx_tc_match_action_ht_params); - if (old) { + if (IS_ERR(old)) { + rc = PTR_ERR(old); + goto release; + } else if (old) { netif_dbg(efx, drv, efx->net_dev, "Ignoring already-offloaded rule (cookie %lx)\n", tc->cookie); @@ -1697,7 +1706,10 @@ static int efx_tc_flower_replace_lhs(struct efx_nic *efx, old = rhashtable_lookup_get_insert_fast(&efx->tc->lhs_rule_ht, &rule->linkage, efx_tc_lhs_rule_ht_params); - if (old) { + if (IS_ERR(old)) { + rc = PTR_ERR(old); + goto release; + } else if (old) { netif_dbg(efx, drv, efx->net_dev, "Already offloaded rule (cookie %lx)\n", tc->cookie); rc = -EEXIST; @@ -1858,7 +1870,10 @@ static int efx_tc_flower_replace(struct efx_nic *efx, old = rhashtable_lookup_get_insert_fast(&efx->tc->match_action_ht, &rule->linkage, efx_tc_match_action_ht_params); - if (old) { + if (IS_ERR(old)) { + rc = PTR_ERR(old); + goto release; + } else if (old) { netif_dbg(efx, drv, efx->net_dev, "Already offloaded rule (cookie %lx)\n", tc->cookie); NL_SET_ERR_MSG_MOD(extack, "Rule already offloaded"); diff --git a/drivers/net/ethernet/sfc/tc_conntrack.c b/drivers/net/ethernet/sfc/tc_conntrack.c index 8e06bfbcbea1..44bb57670340 100644 --- a/drivers/net/ethernet/sfc/tc_conntrack.c +++ b/drivers/net/ethernet/sfc/tc_conntrack.c @@ -298,7 +298,10 @@ static int efx_tc_ct_replace(struct efx_tc_ct_zone *ct_zone, old = rhashtable_lookup_get_insert_fast(&efx->tc->ct_ht, &conn->linkage, efx_tc_ct_ht_params); - if (old) { + if (IS_ERR(old)) { + rc = PTR_ERR(old); + goto release; + } else if (old) { netif_dbg(efx, drv, efx->net_dev, "Already offloaded conntrack (cookie %lx)\n", tc->cookie); rc = -EEXIST; @@ -482,6 +485,8 @@ struct efx_tc_ct_zone *efx_tc_ct_register_zone(struct efx_nic *efx, u16 zone, if (old) { /* don't need our new entry */ kfree(ct_zone); + if (IS_ERR(old)) /* oh dear, it's actually an error */ + return ERR_CAST(old); if (!refcount_inc_not_zero(&old->ref)) return ERR_PTR(-EAGAIN); /* existing entry found */ diff --git a/drivers/net/ethernet/sfc/tc_counters.c b/drivers/net/ethernet/sfc/tc_counters.c index 0fafb47ea082..c44088424323 100644 --- a/drivers/net/ethernet/sfc/tc_counters.c +++ b/drivers/net/ethernet/sfc/tc_counters.c @@ -236,6 +236,8 @@ struct efx_tc_counter_index *efx_tc_flower_get_counter_index( if (old) { /* don't need our new entry */ kfree(ctr); + if (IS_ERR(old)) /* oh dear, it's actually an error */ + return ERR_CAST(old); if (!refcount_inc_not_zero(&old->ref)) return ERR_PTR(-EAGAIN); /* existing entry found */ diff --git a/drivers/net/ethernet/sfc/tc_encap_actions.c b/drivers/net/ethernet/sfc/tc_encap_actions.c index 7e8bcdb222ad..87443f9dfd22 100644 --- a/drivers/net/ethernet/sfc/tc_encap_actions.c +++ b/drivers/net/ethernet/sfc/tc_encap_actions.c @@ -132,6 +132,8 @@ static int efx_bind_neigh(struct efx_nic *efx, /* don't need our new entry */ put_net_track(neigh->net, &neigh->ns_tracker); kfree(neigh); + if (IS_ERR(old)) /* oh dear, it's actually an error */ + return PTR_ERR(old); if (!refcount_inc_not_zero(&old->ref)) return -EAGAIN; /* existing entry found, ref taken */ @@ -640,6 +642,8 @@ struct efx_tc_encap_action *efx_tc_flower_create_encap_md( if (old) { /* don't need our new entry */ kfree(encap); + if (IS_ERR(old)) /* oh dear, it's actually an error */ + return ERR_CAST(old); if (!refcount_inc_not_zero(&old->ref)) return ERR_PTR(-EAGAIN); /* existing entry found, ref taken */ diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 403cb397d4d3..1e996c29043d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -70,7 +70,7 @@ struct stmmac_txq_stats { u64 tx_tso_frames; u64 tx_tso_nfrags; struct u64_stats_sync syncp; -}; +} ____cacheline_aligned_in_smp; struct stmmac_rxq_stats { u64 rx_bytes; @@ -79,7 +79,7 @@ struct stmmac_rxq_stats { u64 rx_normal_irq_n; u64 napi_poll; struct u64_stats_sync syncp; -}; +} ____cacheline_aligned_in_smp; /* Extra statistic and debug information exposed by ethtool */ struct stmmac_extra_stats { @@ -202,6 +202,9 @@ struct stmmac_extra_stats { unsigned long mtl_est_hlbf; unsigned long mtl_est_btre; unsigned long mtl_est_btrlm; + /* per queue statistics */ + struct stmmac_txq_stats txq_stats[MTL_MAX_TX_QUEUES]; + struct stmmac_rxq_stats rxq_stats[MTL_MAX_RX_QUEUES]; unsigned long rx_dropped; unsigned long rx_errors; unsigned long tx_dropped; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 01e77368eef1..465ff1fd4785 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -441,8 +441,8 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv, struct stmmac_extra_stats *x, u32 chan, u32 dir) { - struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[chan]; - struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[chan]; + struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; + struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; int ret = 0; u32 v; @@ -455,9 +455,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv, if (v & EMAC_TX_INT) { ret |= handle_tx; - u64_stats_update_begin(&tx_q->txq_stats.syncp); - tx_q->txq_stats.tx_normal_irq_n++; - u64_stats_update_end(&tx_q->txq_stats.syncp); + u64_stats_update_begin(&txq_stats->syncp); + txq_stats->tx_normal_irq_n++; + u64_stats_update_end(&txq_stats->syncp); } if (v & EMAC_TX_DMA_STOP_INT) @@ -479,9 +479,9 @@ static int sun8i_dwmac_dma_interrupt(struct stmmac_priv *priv, if (v & EMAC_RX_INT) { ret |= handle_rx; - u64_stats_update_begin(&rx_q->rxq_stats.syncp); - rx_q->rxq_stats.rx_normal_irq_n++; - u64_stats_update_end(&rx_q->rxq_stats.syncp); + u64_stats_update_begin(&rxq_stats->syncp); + rxq_stats->rx_normal_irq_n++; + u64_stats_update_end(&rxq_stats->syncp); } if (v & EMAC_RX_BUF_UA_INT) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 980e5f8a37ec..9470d3fd2ded 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -171,8 +171,8 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, const struct dwmac4_addrs *dwmac4_addrs = priv->plat->dwmac4_addrs; u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(dwmac4_addrs, chan)); u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(dwmac4_addrs, chan)); - struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[chan]; - struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[chan]; + struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; + struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; int ret = 0; if (dir == DMA_DIR_RX) @@ -201,15 +201,15 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, } /* TX/RX NORMAL interrupts */ if (likely(intr_status & DMA_CHAN_STATUS_RI)) { - u64_stats_update_begin(&rx_q->rxq_stats.syncp); - rx_q->rxq_stats.rx_normal_irq_n++; - u64_stats_update_end(&rx_q->rxq_stats.syncp); + u64_stats_update_begin(&rxq_stats->syncp); + rxq_stats->rx_normal_irq_n++; + u64_stats_update_end(&rxq_stats->syncp); ret |= handle_rx; } if (likely(intr_status & DMA_CHAN_STATUS_TI)) { - u64_stats_update_begin(&tx_q->txq_stats.syncp); - tx_q->txq_stats.tx_normal_irq_n++; - u64_stats_update_end(&tx_q->txq_stats.syncp); + u64_stats_update_begin(&txq_stats->syncp); + txq_stats->tx_normal_irq_n++; + u64_stats_update_end(&txq_stats->syncp); ret |= handle_tx; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index aaa09b16b016..7907d62d3437 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -162,8 +162,8 @@ static void show_rx_process_state(unsigned int status) int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_extra_stats *x, u32 chan, u32 dir) { - struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[chan]; - struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[chan]; + struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; + struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; int ret = 0; /* read the status register (CSR5) */ u32 intr_status = readl(ioaddr + DMA_STATUS); @@ -215,16 +215,16 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, u32 value = readl(ioaddr + DMA_INTR_ENA); /* to schedule NAPI on real RIE event. */ if (likely(value & DMA_INTR_ENA_RIE)) { - u64_stats_update_begin(&rx_q->rxq_stats.syncp); - rx_q->rxq_stats.rx_normal_irq_n++; - u64_stats_update_end(&rx_q->rxq_stats.syncp); + u64_stats_update_begin(&rxq_stats->syncp); + rxq_stats->rx_normal_irq_n++; + u64_stats_update_end(&rxq_stats->syncp); ret |= handle_rx; } } if (likely(intr_status & DMA_STATUS_TI)) { - u64_stats_update_begin(&tx_q->txq_stats.syncp); - tx_q->txq_stats.tx_normal_irq_n++; - u64_stats_update_end(&tx_q->txq_stats.syncp); + u64_stats_update_begin(&txq_stats->syncp); + txq_stats->tx_normal_irq_n++; + u64_stats_update_end(&txq_stats->syncp); ret |= handle_tx; } if (unlikely(intr_status & DMA_STATUS_ERI)) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index fa69d64a8694..3cde695fec91 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -337,8 +337,8 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv, struct stmmac_extra_stats *x, u32 chan, u32 dir) { - struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[chan]; - struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[chan]; + struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[chan]; + struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[chan]; u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan)); u32 intr_en = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan)); int ret = 0; @@ -367,15 +367,15 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv, /* TX/RX NORMAL interrupts */ if (likely(intr_status & XGMAC_NIS)) { if (likely(intr_status & XGMAC_RI)) { - u64_stats_update_begin(&rx_q->rxq_stats.syncp); - rx_q->rxq_stats.rx_normal_irq_n++; - u64_stats_update_end(&rx_q->rxq_stats.syncp); + u64_stats_update_begin(&rxq_stats->syncp); + rxq_stats->rx_normal_irq_n++; + u64_stats_update_end(&rxq_stats->syncp); ret |= handle_rx; } if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) { - u64_stats_update_begin(&tx_q->txq_stats.syncp); - tx_q->txq_stats.tx_normal_irq_n++; - u64_stats_update_end(&tx_q->txq_stats.syncp); + u64_stats_update_begin(&txq_stats->syncp); + txq_stats->tx_normal_irq_n++; + u64_stats_update_end(&txq_stats->syncp); ret |= handle_tx; } } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 3401e888a9f6..cd7a9768de5f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -78,7 +78,6 @@ struct stmmac_tx_queue { dma_addr_t dma_tx_phy; dma_addr_t tx_tail_addr; u32 mss; - struct stmmac_txq_stats txq_stats; }; struct stmmac_rx_buffer { @@ -123,7 +122,6 @@ struct stmmac_rx_queue { unsigned int len; unsigned int error; } state; - struct stmmac_rxq_stats rxq_stats; }; struct stmmac_channel { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index b7ac7abecdd3..6aa5c0556d22 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -548,14 +548,14 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data) pos = data; for (q = 0; q < tx_cnt; q++) { - struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[q]; + struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[q]; struct stmmac_txq_stats snapshot; data = pos; do { - start = u64_stats_fetch_begin(&tx_q->txq_stats.syncp); - snapshot = tx_q->txq_stats; - } while (u64_stats_fetch_retry(&tx_q->txq_stats.syncp, start)); + start = u64_stats_fetch_begin(&txq_stats->syncp); + snapshot = *txq_stats; + } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); p = (char *)&snapshot + offsetof(struct stmmac_txq_stats, tx_pkt_n); for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) { @@ -566,14 +566,14 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data) pos = data; for (q = 0; q < rx_cnt; q++) { - struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[q]; + struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[q]; struct stmmac_rxq_stats snapshot; data = pos; do { - start = u64_stats_fetch_begin(&rx_q->rxq_stats.syncp); - snapshot = rx_q->rxq_stats; - } while (u64_stats_fetch_retry(&rx_q->rxq_stats.syncp, start)); + start = u64_stats_fetch_begin(&rxq_stats->syncp); + snapshot = *rxq_stats; + } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); p = (char *)&snapshot + offsetof(struct stmmac_rxq_stats, rx_pkt_n); for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) { @@ -637,14 +637,14 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, pos = j; for (i = 0; i < rx_queues_count; i++) { - struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[i]; + struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[i]; struct stmmac_rxq_stats snapshot; j = pos; do { - start = u64_stats_fetch_begin(&rx_q->rxq_stats.syncp); - snapshot = rx_q->rxq_stats; - } while (u64_stats_fetch_retry(&rx_q->rxq_stats.syncp, start)); + start = u64_stats_fetch_begin(&rxq_stats->syncp); + snapshot = *rxq_stats; + } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); data[j++] += snapshot.rx_pkt_n; data[j++] += snapshot.rx_normal_irq_n; @@ -654,14 +654,14 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, pos = j; for (i = 0; i < tx_queues_count; i++) { - struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[i]; + struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[i]; struct stmmac_txq_stats snapshot; j = pos; do { - start = u64_stats_fetch_begin(&tx_q->txq_stats.syncp); - snapshot = tx_q->txq_stats; - } while (u64_stats_fetch_retry(&tx_q->txq_stats.syncp, start)); + start = u64_stats_fetch_begin(&txq_stats->syncp); + snapshot = *txq_stats; + } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); data[j++] += snapshot.tx_pkt_n; data[j++] += snapshot.tx_normal_irq_n; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 2206789802bf..83c567a89a46 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2426,6 +2426,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) { struct netdev_queue *nq = netdev_get_tx_queue(priv->dev, queue); struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; + struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[queue]; struct xsk_buff_pool *pool = tx_q->xsk_pool; unsigned int entry = tx_q->cur_tx; struct dma_desc *tx_desc = NULL; @@ -2505,9 +2506,9 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, priv->dma_conf.dma_tx_size); entry = tx_q->cur_tx; } - flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp); - tx_q->txq_stats.tx_set_ic_bit += tx_set_ic_bit; - u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags); + flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); + txq_stats->tx_set_ic_bit += tx_set_ic_bit; + u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); if (tx_desc) { stmmac_flush_tx_descriptors(priv, queue); @@ -2547,6 +2548,7 @@ static void stmmac_bump_dma_threshold(struct stmmac_priv *priv, u32 chan) static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) { struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; + struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[queue]; unsigned int bytes_compl = 0, pkts_compl = 0; unsigned int entry, xmits = 0, count = 0; u32 tx_packets = 0, tx_errors = 0; @@ -2706,11 +2708,11 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) if (tx_q->dirty_tx != tx_q->cur_tx) stmmac_tx_timer_arm(priv, queue); - flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp); - tx_q->txq_stats.tx_packets += tx_packets; - tx_q->txq_stats.tx_pkt_n += tx_packets; - tx_q->txq_stats.tx_clean++; - u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags); + flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); + txq_stats->tx_packets += tx_packets; + txq_stats->tx_pkt_n += tx_packets; + txq_stats->tx_clean++; + u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); priv->xstats.tx_errors += tx_errors; @@ -4114,6 +4116,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) int nfrags = skb_shinfo(skb)->nr_frags; u32 queue = skb_get_queue_mapping(skb); unsigned int first_entry, tx_packets; + struct stmmac_txq_stats *txq_stats; int tmp_pay_len = 0, first_tx; struct stmmac_tx_queue *tx_q; bool has_vlan, set_ic; @@ -4124,6 +4127,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) int i; tx_q = &priv->dma_conf.tx_queue[queue]; + txq_stats = &priv->xstats.txq_stats[queue]; first_tx = tx_q->cur_tx; /* Compute header lengths */ @@ -4282,13 +4286,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); } - flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp); - tx_q->txq_stats.tx_bytes += skb->len; - tx_q->txq_stats.tx_tso_frames++; - tx_q->txq_stats.tx_tso_nfrags += nfrags; + flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); + txq_stats->tx_bytes += skb->len; + txq_stats->tx_tso_frames++; + txq_stats->tx_tso_nfrags += nfrags; if (set_ic) - tx_q->txq_stats.tx_set_ic_bit++; - u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags); + txq_stats->tx_set_ic_bit++; + u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); if (priv->sarc_type) stmmac_set_desc_sarc(priv, first, priv->sarc_type); @@ -4359,6 +4363,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) u32 queue = skb_get_queue_mapping(skb); int nfrags = skb_shinfo(skb)->nr_frags; int gso = skb_shinfo(skb)->gso_type; + struct stmmac_txq_stats *txq_stats; struct dma_edesc *tbs_desc = NULL; struct dma_desc *desc, *first; struct stmmac_tx_queue *tx_q; @@ -4368,6 +4373,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) dma_addr_t des; tx_q = &priv->dma_conf.tx_queue[queue]; + txq_stats = &priv->xstats.txq_stats[queue]; first_tx = tx_q->cur_tx; if (priv->tx_path_in_lpi_mode && priv->eee_sw_timer_en) @@ -4519,11 +4525,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue)); } - flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp); - tx_q->txq_stats.tx_bytes += skb->len; + flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); + txq_stats->tx_bytes += skb->len; if (set_ic) - tx_q->txq_stats.tx_set_ic_bit++; - u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags); + txq_stats->tx_set_ic_bit++; + u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); if (priv->sarc_type) stmmac_set_desc_sarc(priv, first, priv->sarc_type); @@ -4730,6 +4736,7 @@ static unsigned int stmmac_rx_buf2_len(struct stmmac_priv *priv, static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue, struct xdp_frame *xdpf, bool dma_map) { + struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[queue]; struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; unsigned int entry = tx_q->cur_tx; struct dma_desc *tx_desc; @@ -4789,9 +4796,9 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue, unsigned long flags; tx_q->tx_count_frames = 0; stmmac_set_tx_ic(priv, tx_desc); - flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp); - tx_q->txq_stats.tx_set_ic_bit++; - u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags); + flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); + txq_stats->tx_set_ic_bit++; + u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); } stmmac_enable_dma_transmission(priv, priv->ioaddr); @@ -4936,7 +4943,7 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue, struct dma_desc *p, struct dma_desc *np, struct xdp_buff *xdp) { - struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[queue]; + struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[queue]; struct stmmac_channel *ch = &priv->channel[queue]; unsigned int len = xdp->data_end - xdp->data; enum pkt_hash_types hash_type; @@ -4966,10 +4973,10 @@ static void stmmac_dispatch_skb_zc(struct stmmac_priv *priv, u32 queue, skb_record_rx_queue(skb, queue); napi_gro_receive(&ch->rxtx_napi, skb); - flags = u64_stats_update_begin_irqsave(&rx_q->rxq_stats.syncp); - rx_q->rxq_stats.rx_pkt_n++; - rx_q->rxq_stats.rx_bytes += len; - u64_stats_update_end_irqrestore(&rx_q->rxq_stats.syncp, flags); + flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); + rxq_stats->rx_pkt_n++; + rxq_stats->rx_bytes += len; + u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); } static bool stmmac_rx_refill_zc(struct stmmac_priv *priv, u32 queue, u32 budget) @@ -5042,6 +5049,7 @@ static struct stmmac_xdp_buff *xsk_buff_to_stmmac_ctx(struct xdp_buff *xdp) static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue) { + struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[queue]; struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[queue]; unsigned int count = 0, error = 0, len = 0; int dirty = stmmac_rx_dirty(priv, queue); @@ -5205,9 +5213,9 @@ read_again: stmmac_finalize_xdp_rx(priv, xdp_status); - flags = u64_stats_update_begin_irqsave(&rx_q->rxq_stats.syncp); - rx_q->rxq_stats.rx_pkt_n += count; - u64_stats_update_end_irqrestore(&rx_q->rxq_stats.syncp, flags); + flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); + rxq_stats->rx_pkt_n += count; + u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); priv->xstats.rx_dropped += rx_dropped; priv->xstats.rx_errors += rx_errors; @@ -5235,6 +5243,7 @@ read_again: static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) { u32 rx_errors = 0, rx_dropped = 0, rx_bytes = 0, rx_packets = 0; + struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[queue]; struct stmmac_rx_queue *rx_q = &priv->dma_conf.rx_queue[queue]; struct stmmac_channel *ch = &priv->channel[queue]; unsigned int count = 0, error = 0, len = 0; @@ -5496,11 +5505,11 @@ drain_data: stmmac_rx_refill(priv, queue); - flags = u64_stats_update_begin_irqsave(&rx_q->rxq_stats.syncp); - rx_q->rxq_stats.rx_packets += rx_packets; - rx_q->rxq_stats.rx_bytes += rx_bytes; - rx_q->rxq_stats.rx_pkt_n += count; - u64_stats_update_end_irqrestore(&rx_q->rxq_stats.syncp, flags); + flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); + rxq_stats->rx_packets += rx_packets; + rxq_stats->rx_bytes += rx_bytes; + rxq_stats->rx_pkt_n += count; + u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); priv->xstats.rx_dropped += rx_dropped; priv->xstats.rx_errors += rx_errors; @@ -5513,15 +5522,15 @@ static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget) struct stmmac_channel *ch = container_of(napi, struct stmmac_channel, rx_napi); struct stmmac_priv *priv = ch->priv_data; - struct stmmac_rx_queue *rx_q; + struct stmmac_rxq_stats *rxq_stats; u32 chan = ch->index; unsigned long flags; int work_done; - rx_q = &priv->dma_conf.rx_queue[chan]; - flags = u64_stats_update_begin_irqsave(&rx_q->rxq_stats.syncp); - rx_q->rxq_stats.napi_poll++; - u64_stats_update_end_irqrestore(&rx_q->rxq_stats.syncp, flags); + rxq_stats = &priv->xstats.rxq_stats[chan]; + flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); + rxq_stats->napi_poll++; + u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); work_done = stmmac_rx(priv, budget, chan); if (work_done < budget && napi_complete_done(napi, work_done)) { @@ -5540,15 +5549,15 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget) struct stmmac_channel *ch = container_of(napi, struct stmmac_channel, tx_napi); struct stmmac_priv *priv = ch->priv_data; - struct stmmac_tx_queue *tx_q; + struct stmmac_txq_stats *txq_stats; u32 chan = ch->index; unsigned long flags; int work_done; - tx_q = &priv->dma_conf.tx_queue[chan]; - flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp); - tx_q->txq_stats.napi_poll++; - u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags); + txq_stats = &priv->xstats.txq_stats[chan]; + flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); + txq_stats->napi_poll++; + u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); work_done = stmmac_tx_clean(priv, budget, chan); work_done = min(work_done, budget); @@ -5570,20 +5579,20 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget) container_of(napi, struct stmmac_channel, rxtx_napi); struct stmmac_priv *priv = ch->priv_data; int rx_done, tx_done, rxtx_done; - struct stmmac_rx_queue *rx_q; - struct stmmac_tx_queue *tx_q; + struct stmmac_rxq_stats *rxq_stats; + struct stmmac_txq_stats *txq_stats; u32 chan = ch->index; unsigned long flags; - rx_q = &priv->dma_conf.rx_queue[chan]; - flags = u64_stats_update_begin_irqsave(&rx_q->rxq_stats.syncp); - rx_q->rxq_stats.napi_poll++; - u64_stats_update_end_irqrestore(&rx_q->rxq_stats.syncp, flags); + rxq_stats = &priv->xstats.rxq_stats[chan]; + flags = u64_stats_update_begin_irqsave(&rxq_stats->syncp); + rxq_stats->napi_poll++; + u64_stats_update_end_irqrestore(&rxq_stats->syncp, flags); - tx_q = &priv->dma_conf.tx_queue[chan]; - flags = u64_stats_update_begin_irqsave(&tx_q->txq_stats.syncp); - tx_q->txq_stats.napi_poll++; - u64_stats_update_end_irqrestore(&tx_q->txq_stats.syncp, flags); + txq_stats = &priv->xstats.txq_stats[chan]; + flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); + txq_stats->napi_poll++; + u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); tx_done = stmmac_tx_clean(priv, budget, chan); tx_done = min(tx_done, budget); @@ -6926,7 +6935,7 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64 int q; for (q = 0; q < tx_cnt; q++) { - struct stmmac_txq_stats *txq_stats = &priv->dma_conf.tx_queue[q].txq_stats; + struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[q]; u64 tx_packets; u64 tx_bytes; @@ -6941,7 +6950,7 @@ static void stmmac_get_stats64(struct net_device *dev, struct rtnl_link_stats64 } for (q = 0; q < rx_cnt; q++) { - struct stmmac_rxq_stats *rxq_stats = &priv->dma_conf.rx_queue[q].rxq_stats; + struct stmmac_rxq_stats *rxq_stats = &priv->xstats.rxq_stats[q]; u64 rx_packets; u64 rx_bytes; @@ -7342,9 +7351,9 @@ int stmmac_dvr_probe(struct device *device, priv->dev = ndev; for (i = 0; i < MTL_MAX_RX_QUEUES; i++) - u64_stats_init(&priv->dma_conf.rx_queue[i].rxq_stats.syncp); + u64_stats_init(&priv->xstats.rxq_stats[i].syncp); for (i = 0; i < MTL_MAX_TX_QUEUES; i++) - u64_stats_init(&priv->dma_conf.tx_queue[i].txq_stats.syncp); + u64_stats_init(&priv->xstats.txq_stats[i].syncp); stmmac_set_ethtool_ops(ndev); priv->pause = pause; diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 88b5b1b47779..0a3346650e03 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -199,6 +199,7 @@ config TI_ICSSG_PRUETH config TI_ICSS_IEP tristate "TI PRU ICSS IEP driver" + depends on PTP_1588_CLOCK_OPTIONAL depends on TI_PRUSS default TI_PRUSS help diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index e8b94580194e..508d9a392ab1 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2115,7 +2115,12 @@ static const struct ethtool_ops team_ethtool_ops = { static void team_setup_by_port(struct net_device *dev, struct net_device *port_dev) { - dev->header_ops = port_dev->header_ops; + struct team *team = netdev_priv(dev); + + if (port_dev->type == ARPHRD_ETHER) + dev->header_ops = team->header_ops_cache; + else + dev->header_ops = port_dev->header_ops; dev->type = port_dev->type; dev->hard_header_len = port_dev->hard_header_len; dev->needed_headroom = port_dev->needed_headroom; @@ -2162,8 +2167,11 @@ static int team_dev_type_check_change(struct net_device *dev, static void team_setup(struct net_device *dev) { + struct team *team = netdev_priv(dev); + ether_setup(dev); dev->max_mtu = ETH_MAX_MTU; + team->header_ops_cache = dev->header_ops; dev->netdev_ops = &team_netdev_ops; dev->ethtool_ops = &team_ethtool_ops; diff --git a/drivers/net/thunderbolt/main.c b/drivers/net/thunderbolt/main.c index 0c1e8970ee58..0a53ec293d04 100644 --- a/drivers/net/thunderbolt/main.c +++ b/drivers/net/thunderbolt/main.c @@ -1049,12 +1049,11 @@ static bool tbnet_xmit_csum_and_map(struct tbnet *net, struct sk_buff *skb, *tucso = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, 0, ip_hdr(skb)->protocol, 0); - } else if (skb_is_gso_v6(skb)) { + } else if (skb_is_gso(skb) && skb_is_gso_v6(skb)) { tucso = dest + ((void *)&(tcp_hdr(skb)->check) - data); *tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); - return false; } else if (protocol == htons(ETH_P_IPV6)) { tucso = dest + skb_checksum_start_offset(skb) + skb->csum_offset; *tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index e463f59e95c2..5b5597073b00 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -4331,6 +4331,10 @@ static size_t vxlan_get_size(const struct net_device *dev) nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LOCALBYPASS */ + nla_total_size(0) + /* IFLA_VXLAN_GBP */ + nla_total_size(0) + /* IFLA_VXLAN_GPE */ + nla_total_size(0) + /* IFLA_VXLAN_REMCSUM_NOPARTIAL */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_VNIFILTER */ 0; } diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index e85ff946e8c8..9c8fd69ae5ad 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -229,6 +229,7 @@ int pcie_aer_is_native(struct pci_dev *dev) return pcie_ports_native || host->native_aer; } +EXPORT_SYMBOL_NS_GPL(pcie_aer_is_native, CXL); static int pci_enable_pcie_error_reporting(struct pci_dev *dev) { diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h index 58a2b1a1cae4..1f3803bde7ee 100644 --- a/drivers/pci/pcie/portdrv.h +++ b/drivers/pci/pcie/portdrv.h @@ -29,10 +29,8 @@ extern bool pcie_ports_dpc_native; #ifdef CONFIG_PCIEAER int pcie_aer_init(void); -int pcie_aer_is_native(struct pci_dev *dev); #else static inline int pcie_aer_init(void) { return 0; } -static inline int pcie_aer_is_native(struct pci_dev *dev) { return 0; } #endif #ifdef CONFIG_HOTPLUG_PCI_PCIE diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index 6851d10d6582..a68df4133403 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/module.h> #include <linux/slab.h> @@ -231,19 +232,15 @@ static inline u32 ipc_data_readl(struct intel_scu_ipc_dev *scu, u32 offset) /* Wait till scu status is busy */ static inline int busy_loop(struct intel_scu_ipc_dev *scu) { - unsigned long end = jiffies + IPC_TIMEOUT; - - do { - u32 status; - - status = ipc_read_status(scu); - if (!(status & IPC_STATUS_BUSY)) - return (status & IPC_STATUS_ERR) ? -EIO : 0; + u8 status; + int err; - usleep_range(50, 100); - } while (time_before(jiffies, end)); + err = readx_poll_timeout(ipc_read_status, scu, status, !(status & IPC_STATUS_BUSY), + 100, jiffies_to_usecs(IPC_TIMEOUT)); + if (err) + return err; - return -ETIMEDOUT; + return (status & IPC_STATUS_ERR) ? -EIO : 0; } /* Wait till ipc ioc interrupt is received or timeout in 10 HZ */ @@ -251,10 +248,12 @@ static inline int ipc_wait_for_interrupt(struct intel_scu_ipc_dev *scu) { int status; - if (!wait_for_completion_timeout(&scu->cmd_complete, IPC_TIMEOUT)) - return -ETIMEDOUT; + wait_for_completion_timeout(&scu->cmd_complete, IPC_TIMEOUT); status = ipc_read_status(scu); + if (status & IPC_STATUS_BUSY) + return -ETIMEDOUT; + if (status & IPC_STATUS_ERR) return -EIO; @@ -266,6 +265,24 @@ static int intel_scu_ipc_check_status(struct intel_scu_ipc_dev *scu) return scu->irq > 0 ? ipc_wait_for_interrupt(scu) : busy_loop(scu); } +static struct intel_scu_ipc_dev *intel_scu_ipc_get(struct intel_scu_ipc_dev *scu) +{ + u8 status; + + if (!scu) + scu = ipcdev; + if (!scu) + return ERR_PTR(-ENODEV); + + status = ipc_read_status(scu); + if (status & IPC_STATUS_BUSY) { + dev_dbg(&scu->dev, "device is busy\n"); + return ERR_PTR(-EBUSY); + } + + return scu; +} + /* Read/Write power control(PMIC in Langwell, MSIC in PenWell) registers */ static int pwr_reg_rdwr(struct intel_scu_ipc_dev *scu, u16 *addr, u8 *data, u32 count, u32 op, u32 id) @@ -279,11 +296,10 @@ static int pwr_reg_rdwr(struct intel_scu_ipc_dev *scu, u16 *addr, u8 *data, memset(cbuf, 0, sizeof(cbuf)); mutex_lock(&ipclock); - if (!scu) - scu = ipcdev; - if (!scu) { + scu = intel_scu_ipc_get(scu); + if (IS_ERR(scu)) { mutex_unlock(&ipclock); - return -ENODEV; + return PTR_ERR(scu); } for (nc = 0; nc < count; nc++, offset += 2) { @@ -438,13 +454,12 @@ int intel_scu_ipc_dev_simple_command(struct intel_scu_ipc_dev *scu, int cmd, int err; mutex_lock(&ipclock); - if (!scu) - scu = ipcdev; - if (!scu) { + scu = intel_scu_ipc_get(scu); + if (IS_ERR(scu)) { mutex_unlock(&ipclock); - return -ENODEV; + return PTR_ERR(scu); } - scu = ipcdev; + cmdval = sub << 12 | cmd; ipc_command(scu, cmdval); err = intel_scu_ipc_check_status(scu); @@ -484,11 +499,10 @@ int intel_scu_ipc_dev_command_with_size(struct intel_scu_ipc_dev *scu, int cmd, return -EINVAL; mutex_lock(&ipclock); - if (!scu) - scu = ipcdev; - if (!scu) { + scu = intel_scu_ipc_get(scu); + if (IS_ERR(scu)) { mutex_unlock(&ipclock); - return -ENODEV; + return PTR_ERR(scu); } memcpy(inbuf, in, inlen); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index d70c89d32534..41584427dc32 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -4116,9 +4116,11 @@ static void hotkey_resume(void) { tpacpi_disable_brightness_delay(); + mutex_lock(&hotkey_mutex); if (hotkey_status_set(true) < 0 || hotkey_mask_set(hotkey_acpi_mask) < 0) pr_err("error while attempting to reset the event firmware interface\n"); + mutex_unlock(&hotkey_mutex); tpacpi_send_radiosw_update(); tpacpi_input_send_tabletsw(); diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c index 5ad5f3b3a6b5..d49268336553 100644 --- a/drivers/regulator/helpers.c +++ b/drivers/regulator/helpers.c @@ -197,7 +197,7 @@ int regulator_set_voltage_sel_pickable_regmap(struct regulator_dev *rdev, sel += rdev->desc->linear_ranges[i].min_sel; range = rdev->desc->linear_range_selectors_bitfield[i]; - range <<= ffs(rdev->desc->vsel_mask) - 1; + range <<= ffs(rdev->desc->vsel_range_mask) - 1; if (rdev->desc->vsel_reg == rdev->desc->vsel_range_reg) { ret = regmap_update_bits(rdev->regmap, diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 9ab8555180a3..8e14cea15f98 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -724,6 +724,10 @@ iscsi_sw_tcp_conn_bind(struct iscsi_cls_session *cls_session, return -EEXIST; } + err = -EINVAL; + if (!sk_is_tcp(sock->sk)) + goto free_socket; + err = iscsi_conn_bind(cls_session, cls_conn, is_leading); if (err) goto free_socket; diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index a8a74c7cb79f..498e35c8db2c 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -662,7 +662,7 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx, if (spi_imx->count >= 512) ctrl |= 0xFFF << MX51_ECSPI_CTRL_BL_OFFSET; else - ctrl |= (spi_imx->count*8 - 1) + ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1) << MX51_ECSPI_CTRL_BL_OFFSET; } diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index a7381e774b95..57d767a68e7b 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -72,6 +72,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x4da4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0x51a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x54a4), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0x5794), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7a24), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7aa4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7e23), (unsigned long)&cnl_info }, diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c index 45a4acc95661..c964f41dcc42 100644 --- a/drivers/spi/spi-nxp-fspi.c +++ b/drivers/spi/spi-nxp-fspi.c @@ -1084,6 +1084,13 @@ static int nxp_fspi_default_setup(struct nxp_fspi *f) fspi_writel(f, FSPI_AHBCR_PREF_EN | FSPI_AHBCR_RDADDROPT, base + FSPI_AHBCR); + /* Reset the FLSHxCR1 registers. */ + reg = FSPI_FLSHXCR1_TCSH(0x3) | FSPI_FLSHXCR1_TCSS(0x3); + fspi_writel(f, reg, base + FSPI_FLSHA1CR1); + fspi_writel(f, reg, base + FSPI_FLSHA2CR1); + fspi_writel(f, reg, base + FSPI_FLSHB1CR1); + fspi_writel(f, reg, base + FSPI_FLSHB2CR1); + /* AHB Read - Set lut sequence ID for all CS. */ fspi_writel(f, SEQID_LUT, base + FSPI_FLSHA1CR2); fspi_writel(f, SEQID_LUT, base + FSPI_FLSHA2CR2); diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index b6d66caba4c0..ef665f470c5b 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -277,6 +277,7 @@ struct stm32_spi_cfg { * @fifo_size: size of the embedded fifo in bytes * @cur_midi: master inter-data idleness in ns * @cur_speed: speed configured in Hz + * @cur_half_period: time of a half bit in us * @cur_bpw: number of bits in a single SPI data frame * @cur_fthlv: fifo threshold level (data frames in a single data packet) * @cur_comm: SPI communication mode @@ -304,6 +305,7 @@ struct stm32_spi { unsigned int cur_midi; unsigned int cur_speed; + unsigned int cur_half_period; unsigned int cur_bpw; unsigned int cur_fthlv; unsigned int cur_comm; @@ -468,6 +470,8 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz, spi->cur_speed = spi->clk_rate / (1 << mbrdiv); + spi->cur_half_period = DIV_ROUND_CLOSEST(USEC_PER_SEC, 2 * spi->cur_speed); + return mbrdiv - 1; } @@ -709,6 +713,10 @@ static void stm32h7_spi_disable(struct stm32_spi *spi) return; } + /* Add a delay to make sure that transmission is ended. */ + if (spi->cur_half_period) + udelay(spi->cur_half_period); + if (spi->cur_usedma && spi->dma_tx) dmaengine_terminate_async(spi->dma_tx); if (spi->cur_usedma && spi->dma_rx) diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c index 94d9a33d9af5..9a46b2478f4e 100644 --- a/drivers/spi/spi-zynqmp-gqspi.c +++ b/drivers/spi/spi-zynqmp-gqspi.c @@ -1340,9 +1340,9 @@ static int zynqmp_qspi_probe(struct platform_device *pdev) return 0; clk_dis_all: - pm_runtime_put_sync(&pdev->dev); - pm_runtime_set_suspended(&pdev->dev); pm_runtime_disable(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); clk_disable_unprepare(xqspi->refclk); clk_dis_pclk: clk_disable_unprepare(xqspi->pclk); @@ -1366,11 +1366,15 @@ static void zynqmp_qspi_remove(struct platform_device *pdev) { struct zynqmp_qspi *xqspi = platform_get_drvdata(pdev); + pm_runtime_get_sync(&pdev->dev); + zynqmp_gqspi_write(xqspi, GQSPI_EN_OFST, 0x0); + + pm_runtime_disable(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_set_suspended(&pdev->dev); clk_disable_unprepare(xqspi->refclk); clk_disable_unprepare(xqspi->pclk); - pm_runtime_set_suspended(&pdev->dev); - pm_runtime_disable(&pdev->dev); } MODULE_DEVICE_TABLE(of, zynqmp_qspi_of_match); diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index 6c20c9f90a05..4e6a97db894e 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -185,9 +185,6 @@ trip_point_hyst_store(struct device *dev, struct device_attribute *attr, if (sscanf(attr->attr.name, "trip_point_%d_hyst", &trip_id) != 1) return -EINVAL; - if (kstrtoint(buf, 10, &trip.hysteresis)) - return -EINVAL; - mutex_lock(&tz->lock); if (!device_is_registered(dev)) { @@ -198,7 +195,11 @@ trip_point_hyst_store(struct device *dev, struct device_attribute *attr, ret = __thermal_zone_get_trip(tz, trip_id, &trip); if (ret) goto unlock; - + + ret = kstrtoint(buf, 10, &trip.hysteresis); + if (ret) + goto unlock; + ret = thermal_zone_set_trip(tz, trip_id, &trip); unlock: mutex_unlock(&tz->lock); diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig index 1b5a319971ed..30577b1d3de5 100644 --- a/drivers/video/console/Kconfig +++ b/drivers/video/console/Kconfig @@ -73,6 +73,7 @@ config DUMMY_CONSOLE_ROWS config FRAMEBUFFER_CONSOLE bool "Framebuffer Console support" depends on FB_CORE && !UML + default DRM_FBDEV_EMULATION select VT_HW_CONSOLE_BINDING select CRC32 select FONT_SUPPORT diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index eac0ba39581e..c29754b65c0e 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -1762,7 +1762,7 @@ config FB_COBALT config FB_SH7760 bool "SH7760/SH7763/SH7720/SH7721 LCDC support" - depends on FB && (CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7763 \ + depends on FB=y && (CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7763 \ || CPU_SUBTYPE_SH7720 || CPU_SUBTYPE_SH7721) select FB_IOMEM_HELPERS help diff --git a/drivers/video/fbdev/core/Kconfig b/drivers/video/fbdev/core/Kconfig index baf7e852c75b..5ac1b0637531 100644 --- a/drivers/video/fbdev/core/Kconfig +++ b/drivers/video/fbdev/core/Kconfig @@ -28,7 +28,7 @@ config FIRMWARE_EDID config FB_DEVICE bool "Provide legacy /dev/fb* device" depends on FB_CORE - default y + default FB help Say Y here if you want the legacy /dev/fb* device file and interfaces within sysfs anc procfs. It is only required if you diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 3bdd5b59661d..0bb86e6c4d0a 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -1704,7 +1704,7 @@ void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl) generic_handle_irq(irq); } -static int __xen_evtchn_do_upcall(void) +int xen_evtchn_do_upcall(void) { struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu); int ret = vcpu_info->evtchn_upcall_pending ? IRQ_HANDLED : IRQ_NONE; @@ -1735,24 +1735,7 @@ static int __xen_evtchn_do_upcall(void) return ret; } - -void xen_evtchn_do_upcall(struct pt_regs *regs) -{ - struct pt_regs *old_regs = set_irq_regs(regs); - - irq_enter(); - - __xen_evtchn_do_upcall(); - - irq_exit(); - set_irq_regs(old_regs); -} - -int xen_hvm_evtchn_do_upcall(void) -{ - return __xen_evtchn_do_upcall(); -} -EXPORT_SYMBOL_GPL(xen_hvm_evtchn_do_upcall); +EXPORT_SYMBOL_GPL(xen_evtchn_do_upcall); /* Rebind a new event channel to an existing irq. */ void rebind_evtchn_irq(evtchn_port_t evtchn, int irq) diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index fcc819131572..544d3f9010b9 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -64,7 +64,7 @@ static uint64_t get_callback_via(struct pci_dev *pdev) static irqreturn_t do_hvm_evtchn_intr(int irq, void *dev_id) { - return xen_hvm_evtchn_do_upcall(); + return xen_evtchn_do_upcall(); } static int xen_allocate_irq(struct pci_dev *pdev) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index ac3fca5a5e41..6954ae763b86 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -484,10 +484,8 @@ static void end_bio_extent_writepage(struct btrfs_bio *bbio) bvec->bv_offset, bvec->bv_len); btrfs_finish_ordered_extent(bbio->ordered, page, start, len, !error); - if (error) { - btrfs_page_clear_uptodate(fs_info, page, start, len); + if (error) mapping_set_error(page->mapping, error); - } btrfs_page_clear_writeback(fs_info, page, start, len); } @@ -1456,8 +1454,6 @@ done: if (ret) { btrfs_mark_ordered_io_finished(BTRFS_I(inode), page, page_start, PAGE_SIZE, !ret); - btrfs_page_clear_uptodate(btrfs_sb(inode->i_sb), page, - page_start, PAGE_SIZE); mapping_set_error(page->mapping, ret); } unlock_page(page); @@ -1624,8 +1620,6 @@ static void extent_buffer_write_end_io(struct btrfs_bio *bbio) struct page *page = bvec->bv_page; u32 len = bvec->bv_len; - if (!uptodate) - btrfs_page_clear_uptodate(fs_info, page, start, len); btrfs_page_clear_writeback(fs_info, page, start, len); bio_offset += len; } @@ -2201,7 +2195,6 @@ void extent_write_locked_range(struct inode *inode, struct page *locked_page, if (ret) { btrfs_mark_ordered_io_finished(BTRFS_I(inode), page, cur, cur_len, !ret); - btrfs_page_clear_uptodate(fs_info, page, cur, cur_len); mapping_set_error(page->mapping, ret); } btrfs_page_unlock_writer(fs_info, page, cur, cur_len); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index ca46a529d56b..361535c71c0f 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1106,6 +1106,25 @@ void btrfs_check_nocow_unlock(struct btrfs_inode *inode) btrfs_drew_write_unlock(&inode->root->snapshot_lock); } +static void update_time_for_write(struct inode *inode) +{ + struct timespec64 now, ctime; + + if (IS_NOCMTIME(inode)) + return; + + now = current_time(inode); + if (!timespec64_equal(&inode->i_mtime, &now)) + inode->i_mtime = now; + + ctime = inode_get_ctime(inode); + if (!timespec64_equal(&ctime, &now)) + inode_set_ctime_to_ts(inode, now); + + if (IS_I_VERSION(inode)) + inode_inc_iversion(inode); +} + static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, size_t count) { @@ -1137,10 +1156,7 @@ static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, * need to start yet another transaction to update the inode as we will * update the inode when we finish writing whatever data we write. */ - if (!IS_NOCMTIME(inode)) { - inode->i_mtime = inode_set_ctime_current(inode); - inode_inc_iversion(inode); - } + update_time_for_write(inode); start_pos = round_down(pos, fs_info->sectorsize); oldsize = i_size_read(inode); @@ -1451,8 +1467,13 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_flags & IOCB_NOWAIT) ilock_flags |= BTRFS_ILOCK_TRY; - /* If the write DIO is within EOF, use a shared lock */ - if (iocb->ki_pos + iov_iter_count(from) <= i_size_read(inode)) + /* + * If the write DIO is within EOF, use a shared lock and also only if + * security bits will likely not be dropped by file_remove_privs() called + * from btrfs_write_check(). Either will need to be rechecked after the + * lock was acquired. + */ + if (iocb->ki_pos + iov_iter_count(from) <= i_size_read(inode) && IS_NOSEC(inode)) ilock_flags |= BTRFS_ILOCK_SHARED; relock: @@ -1460,6 +1481,13 @@ relock: if (err < 0) return err; + /* Shared lock cannot be used with security bits set. */ + if ((ilock_flags & BTRFS_ILOCK_SHARED) && !IS_NOSEC(inode)) { + btrfs_inode_unlock(BTRFS_I(inode), ilock_flags); + ilock_flags &= ~BTRFS_ILOCK_SHARED; + goto relock; + } + err = generic_write_checks(iocb, from); if (err <= 0) { btrfs_inode_unlock(BTRFS_I(inode), ilock_flags); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f09fbdc43f0f..7814b9d654ce 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1085,9 +1085,6 @@ static void submit_uncompressed_range(struct btrfs_inode *inode, btrfs_mark_ordered_io_finished(inode, locked_page, page_start, PAGE_SIZE, !ret); - btrfs_page_clear_uptodate(inode->root->fs_info, - locked_page, page_start, - PAGE_SIZE); mapping_set_error(locked_page->mapping, ret); unlock_page(locked_page); } @@ -2791,7 +2788,6 @@ out_page: mapping_set_error(page->mapping, ret); btrfs_mark_ordered_io_finished(inode, page, page_start, PAGE_SIZE, !ret); - btrfs_page_clear_uptodate(fs_info, page, page_start, PAGE_SIZE); clear_page_dirty_for_io(page); } btrfs_page_clear_checked(fs_info, page, page_start, PAGE_SIZE); @@ -5769,20 +5765,24 @@ out: static int btrfs_get_dir_last_index(struct btrfs_inode *dir, u64 *index) { - if (dir->index_cnt == (u64)-1) { - int ret; + int ret = 0; + btrfs_inode_lock(dir, 0); + if (dir->index_cnt == (u64)-1) { ret = btrfs_inode_delayed_dir_index_count(dir); if (ret) { ret = btrfs_set_inode_index_count(dir); if (ret) - return ret; + goto out; } } - *index = dir->index_cnt; + /* index_cnt is the index number of next new entry, so decrement it. */ + *index = dir->index_cnt - 1; +out: + btrfs_inode_unlock(dir, 0); - return 0; + return ret; } /* @@ -5817,6 +5817,19 @@ static int btrfs_opendir(struct inode *inode, struct file *file) return 0; } +static loff_t btrfs_dir_llseek(struct file *file, loff_t offset, int whence) +{ + struct btrfs_file_private *private = file->private_data; + int ret; + + ret = btrfs_get_dir_last_index(BTRFS_I(file_inode(file)), + &private->last_index); + if (ret) + return ret; + + return generic_file_llseek(file, offset, whence); +} + struct dir_entry { u64 ino; u64 offset; @@ -10868,7 +10881,7 @@ static const struct inode_operations btrfs_dir_inode_operations = { }; static const struct file_operations btrfs_dir_file_operations = { - .llseek = generic_file_llseek, + .llseek = btrfs_dir_llseek, .read = generic_read_dir, .iterate_shared = btrfs_real_readdir, .open = btrfs_opendir, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 09bfe68d2ea3..cffdd6f7f8e8 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2150,7 +2150,7 @@ static struct file_system_type btrfs_fs_type = { .name = "btrfs", .mount = btrfs_mount, .kill_sb = btrfs_kill_super, - .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | FS_MGTIME, + .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA, }; static struct file_system_type btrfs_root_fs_type = { @@ -2158,8 +2158,7 @@ static struct file_system_type btrfs_root_fs_type = { .name = "btrfs", .mount = btrfs_mount_root, .kill_sb = btrfs_kill_super, - .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | - FS_ALLOW_IDMAP | FS_MGTIME, + .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("btrfs"); diff --git a/fs/btrfs/verity.c b/fs/btrfs/verity.c index c5ff16f9e9fa..744f4f4d4c68 100644 --- a/fs/btrfs/verity.c +++ b/fs/btrfs/verity.c @@ -715,7 +715,7 @@ static struct page *btrfs_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) { - struct page *page; + struct folio *folio; u64 off = (u64)index << PAGE_SHIFT; loff_t merkle_pos = merkle_file_pos(inode); int ret; @@ -726,29 +726,36 @@ static struct page *btrfs_read_merkle_tree_page(struct inode *inode, return ERR_PTR(-EFBIG); index += merkle_pos >> PAGE_SHIFT; again: - page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); - if (page) { - if (PageUptodate(page)) - return page; + folio = __filemap_get_folio(inode->i_mapping, index, FGP_ACCESSED, 0); + if (!IS_ERR(folio)) { + if (folio_test_uptodate(folio)) + goto out; - lock_page(page); - /* - * We only insert uptodate pages, so !Uptodate has to be - * an error - */ - if (!PageUptodate(page)) { - unlock_page(page); - put_page(page); + folio_lock(folio); + /* If it's not uptodate after we have the lock, we got a read error. */ + if (!folio_test_uptodate(folio)) { + folio_unlock(folio); + folio_put(folio); return ERR_PTR(-EIO); } - unlock_page(page); - return page; + folio_unlock(folio); + goto out; } - page = __page_cache_alloc(mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS)); - if (!page) + folio = filemap_alloc_folio(mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS), + 0); + if (!folio) return ERR_PTR(-ENOMEM); + ret = filemap_add_folio(inode->i_mapping, folio, index, GFP_NOFS); + if (ret) { + folio_put(folio); + /* Did someone else insert a folio here? */ + if (ret == -EEXIST) + goto again; + return ERR_PTR(ret); + } + /* * Merkle item keys are indexed from byte 0 in the merkle tree. * They have the form: @@ -756,28 +763,19 @@ again: * [ inode objectid, BTRFS_MERKLE_ITEM_KEY, offset in bytes ] */ ret = read_key_bytes(BTRFS_I(inode), BTRFS_VERITY_MERKLE_ITEM_KEY, off, - page_address(page), PAGE_SIZE, page); + folio_address(folio), PAGE_SIZE, &folio->page); if (ret < 0) { - put_page(page); + folio_put(folio); return ERR_PTR(ret); } if (ret < PAGE_SIZE) - memzero_page(page, ret, PAGE_SIZE - ret); + folio_zero_segment(folio, ret, PAGE_SIZE); - SetPageUptodate(page); - ret = add_to_page_cache_lru(page, inode->i_mapping, index, GFP_NOFS); + folio_mark_uptodate(folio); + folio_unlock(folio); - if (!ret) { - /* Inserted and ready for fsverity */ - unlock_page(page); - } else { - put_page(page); - /* Did someone race us into inserting this page? */ - if (ret == -EEXIST) - goto again; - page = ERR_PTR(ret); - } - return page; +out: + return folio_file_page(folio, index); } /* diff --git a/fs/buffer.c b/fs/buffer.c index 2379564e5aea..a6785cd07081 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2011,7 +2011,7 @@ void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to) } EXPORT_SYMBOL(folio_zero_new_buffers); -static void +static int iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, const struct iomap *iomap) { @@ -2025,7 +2025,8 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, * current block, then do not map the buffer and let the caller * handle it. */ - BUG_ON(offset >= iomap->offset + iomap->length); + if (offset >= iomap->offset + iomap->length) + return -EIO; switch (iomap->type) { case IOMAP_HOLE: @@ -2037,7 +2038,7 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); - break; + return 0; case IOMAP_DELALLOC: if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) @@ -2045,7 +2046,7 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, set_buffer_uptodate(bh); set_buffer_mapped(bh); set_buffer_delay(bh); - break; + return 0; case IOMAP_UNWRITTEN: /* * For unwritten regions, we always need to ensure that regions @@ -2062,7 +2063,10 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> inode->i_blkbits; set_buffer_mapped(bh); - break; + return 0; + default: + WARN_ON_ONCE(1); + return -EIO; } } @@ -2103,13 +2107,12 @@ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); - if (get_block) { + if (get_block) err = get_block(inode, block, bh, 1); - if (err) - break; - } else { - iomap_to_bh(inode, block, bh, iomap); - } + else + err = iomap_to_bh(inode, block, bh, iomap); + if (err) + break; if (buffer_new(bh)) { clean_bdev_bh_alias(bh); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 38217422f938..dbebd8b3127e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -7314,7 +7314,7 @@ static struct file_system_type ext4_fs_type = { .init_fs_context = ext4_init_fs_context, .parameters = ext4_param_specs, .kill_sb = ext4_kill_sb, - .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("ext4"); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 9cbf8d98489a..4a280be229a6 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -2010,7 +2010,9 @@ static long gfs2_scan_glock_lru(int nr) if (!test_bit(GLF_LOCK, &gl->gl_flags)) { if (!spin_trylock(&gl->gl_lockref.lock)) continue; - if (!gl->gl_lockref.count) { + if (gl->gl_lockref.count <= 1 && + (gl->gl_state == LM_ST_UNLOCKED || + demote_ok(gl))) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); freed++; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index d26759a98b10..f41ca89d216b 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -567,15 +567,16 @@ static void freeze_go_callback(struct gfs2_glock *gl, bool remote) struct super_block *sb = sdp->sd_vfs; if (!remote || - gl->gl_state != LM_ST_SHARED || + (gl->gl_state != LM_ST_SHARED && + gl->gl_state != LM_ST_UNLOCKED) || gl->gl_demote_state != LM_ST_UNLOCKED) return; /* * Try to get an active super block reference to prevent racing with - * unmount (see trylock_super()). But note that unmount isn't the only - * place where a write lock on s_umount is taken, and we can fail here - * because of things like remount as well. + * unmount (see super_trylock_shared()). But note that unmount isn't + * the only place where a write lock on s_umount is taken, and we can + * fail here because of things like remount as well. */ if (down_read_trylock(&sb->s_umount)) { atomic_inc(&sb->s_active); diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 21ada332d555..1429945215a0 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -50,7 +50,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip, ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE); if (ret) return ret; - if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON) + if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON && + sdp->sd_args.ar_quota != GFS2_QUOTA_QUIET) return 0; ret = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid, ap); if (ret) diff --git a/fs/inode.c b/fs/inode.c index 35fd688168c5..84bc3c76e5cc 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2102,52 +2102,10 @@ int file_remove_privs(struct file *file) } EXPORT_SYMBOL(file_remove_privs); -/** - * current_mgtime - Return FS time (possibly fine-grained) - * @inode: inode. - * - * Return the current time truncated to the time granularity supported by - * the fs, as suitable for a ctime/mtime change. If the ctime is flagged - * as having been QUERIED, get a fine-grained timestamp. - */ -struct timespec64 current_mgtime(struct inode *inode) -{ - struct timespec64 now, ctime; - atomic_long_t *pnsec = (atomic_long_t *)&inode->__i_ctime.tv_nsec; - long nsec = atomic_long_read(pnsec); - - if (nsec & I_CTIME_QUERIED) { - ktime_get_real_ts64(&now); - return timestamp_truncate(now, inode); - } - - ktime_get_coarse_real_ts64(&now); - now = timestamp_truncate(now, inode); - - /* - * If we've recently fetched a fine-grained timestamp - * then the coarse-grained one may still be earlier than the - * existing ctime. Just keep the existing value if so. - */ - ctime = inode_get_ctime(inode); - if (timespec64_compare(&ctime, &now) > 0) - now = ctime; - - return now; -} -EXPORT_SYMBOL(current_mgtime); - -static struct timespec64 current_ctime(struct inode *inode) -{ - if (is_mgtime(inode)) - return current_mgtime(inode); - return current_time(inode); -} - static int inode_needs_update_time(struct inode *inode) { int sync_it = 0; - struct timespec64 now = current_ctime(inode); + struct timespec64 now = current_time(inode); struct timespec64 ctime; /* First try to exhaust all avenues to not sync */ @@ -2578,43 +2536,9 @@ EXPORT_SYMBOL(current_time); */ struct timespec64 inode_set_ctime_current(struct inode *inode) { - struct timespec64 now; - struct timespec64 ctime; - - ctime.tv_nsec = READ_ONCE(inode->__i_ctime.tv_nsec); - if (!(ctime.tv_nsec & I_CTIME_QUERIED)) { - now = current_time(inode); + struct timespec64 now = current_time(inode); - /* Just copy it into place if it's not multigrain */ - if (!is_mgtime(inode)) { - inode_set_ctime_to_ts(inode, now); - return now; - } - - /* - * If we've recently updated with a fine-grained timestamp, - * then the coarse-grained one may still be earlier than the - * existing ctime. Just keep the existing value if so. - */ - ctime.tv_sec = inode->__i_ctime.tv_sec; - if (timespec64_compare(&ctime, &now) > 0) - return ctime; - - /* - * Ctime updates are usually protected by the inode_lock, but - * we can still race with someone setting the QUERIED flag. - * Try to swap the new nsec value into place. If it's changed - * in the interim, then just go with a fine-grained timestamp. - */ - if (cmpxchg(&inode->__i_ctime.tv_nsec, ctime.tv_nsec, - now.tv_nsec) != ctime.tv_nsec) - goto fine_grained; - inode->__i_ctime.tv_sec = now.tv_sec; - return now; - } -fine_grained: - ktime_get_real_ts64(&now); - inode_set_ctime_to_ts(inode, timestamp_truncate(now, inode)); + inode_set_ctime(inode, now.tv_sec, now.tv_nsec); return now; } EXPORT_SYMBOL(inode_set_ctime_current); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index ae8673ce08b1..644479ccefbd 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -640,11 +640,13 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos, size_t poff, plen; /* - * If the write completely overlaps the current folio, then + * If the write or zeroing completely overlaps the current folio, then * entire folio will be dirtied so there is no need for * per-block state tracking structures to be attached to this folio. + * For the unshare case, we must read in the ondisk contents because we + * are not changing pagecache contents. */ - if (pos <= folio_pos(folio) && + if (!(iter->flags & IOMAP_UNSHARE) && pos <= folio_pos(folio) && pos + len >= folio_pos(folio) + folio_size(folio)) return 0; @@ -1261,7 +1263,6 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); - long status = 0; loff_t written = 0; /* don't bother with blocks that are not shared to start with */ @@ -1272,28 +1273,33 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) return length; do { - unsigned long offset = offset_in_page(pos); - unsigned long bytes = min_t(loff_t, PAGE_SIZE - offset, length); struct folio *folio; + int status; + size_t offset; + size_t bytes = min_t(u64, SIZE_MAX, length); status = iomap_write_begin(iter, pos, bytes, &folio); if (unlikely(status)) return status; - if (iter->iomap.flags & IOMAP_F_STALE) + if (iomap->flags & IOMAP_F_STALE) break; - status = iomap_write_end(iter, pos, bytes, bytes, folio); - if (WARN_ON_ONCE(status == 0)) + offset = offset_in_folio(folio, pos); + if (bytes > folio_size(folio) - offset) + bytes = folio_size(folio) - offset; + + bytes = iomap_write_end(iter, pos, bytes, bytes, folio); + if (WARN_ON_ONCE(bytes == 0)) return -EIO; cond_resched(); - pos += status; - written += status; - length -= status; + pos += bytes; + written += bytes; + length -= bytes; balance_dirty_pages_ratelimited(iter->inode->i_mapping); - } while (length); + } while (length > 0); return written; } diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 3404707ddbe7..2cd3ccf4c439 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -47,12 +47,14 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) xas_for_each(&xas, folio, last_page) { loff_t pg_end; bool pg_failed = false; + bool folio_started; if (xas_retry(&xas, folio)) continue; pg_end = folio_pos(folio) + folio_size(folio) - 1; + folio_started = false; for (;;) { loff_t sreq_end; @@ -60,8 +62,10 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) pg_failed = true; break; } - if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { folio_start_fscache(folio); + folio_started = true; + } pg_failed |= subreq_failed; sreq_end = subreq->start + subreq->len - 1; if (pg_end < sreq_end) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 47d892a1d363..f6c74f424691 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -93,12 +93,10 @@ nfs_direct_handle_truncated(struct nfs_direct_req *dreq, dreq->max_count = dreq_len; if (dreq->count > dreq_len) dreq->count = dreq_len; - - if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) - dreq->error = hdr->error; - else /* Clear outstanding error if this is EOF */ - dreq->error = 0; } + + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && !dreq->error) + dreq->error = hdr->error; } static void @@ -120,6 +118,18 @@ nfs_direct_count_bytes(struct nfs_direct_req *dreq, dreq->count = dreq_len; } +static void nfs_direct_truncate_request(struct nfs_direct_req *dreq, + struct nfs_page *req) +{ + loff_t offs = req_offset(req); + size_t req_start = (size_t)(offs - dreq->io_start); + + if (req_start < dreq->max_count) + dreq->max_count = req_start; + if (req_start < dreq->count) + dreq->count = req_start; +} + /** * nfs_swap_rw - NFS address space operation for swap I/O * @iocb: target I/O control block @@ -488,7 +498,9 @@ static void nfs_direct_add_page_head(struct list_head *list, kref_get(&head->wb_kref); } -static void nfs_direct_join_group(struct list_head *list, struct inode *inode) +static void nfs_direct_join_group(struct list_head *list, + struct nfs_commit_info *cinfo, + struct inode *inode) { struct nfs_page *req, *subreq; @@ -510,7 +522,7 @@ static void nfs_direct_join_group(struct list_head *list, struct inode *inode) nfs_release_request(subreq); } } while ((subreq = subreq->wb_this_page) != req); - nfs_join_page_group(req, inode); + nfs_join_page_group(req, cinfo, inode); } } @@ -528,20 +540,15 @@ nfs_direct_write_scan_commit_list(struct inode *inode, static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) { struct nfs_pageio_descriptor desc; - struct nfs_page *req, *tmp; + struct nfs_page *req; LIST_HEAD(reqs); struct nfs_commit_info cinfo; - LIST_HEAD(failed); nfs_init_cinfo_from_dreq(&cinfo, dreq); nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo); - nfs_direct_join_group(&reqs, dreq->inode); + nfs_direct_join_group(&reqs, &cinfo, dreq->inode); - dreq->count = 0; - dreq->max_count = 0; - list_for_each_entry(req, &reqs, wb_list) - dreq->max_count += req->wb_bytes; nfs_clear_pnfs_ds_commit_verifiers(&dreq->ds_cinfo); get_dreq(dreq); @@ -549,27 +556,40 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; - list_for_each_entry_safe(req, tmp, &reqs, wb_list) { + while (!list_empty(&reqs)) { + req = nfs_list_entry(reqs.next); /* Bump the transmission count */ req->wb_nio++; if (!nfs_pageio_add_request(&desc, req)) { - nfs_list_move_request(req, &failed); - spin_lock(&cinfo.inode->i_lock); - dreq->flags = 0; - if (desc.pg_error < 0) + spin_lock(&dreq->lock); + if (dreq->error < 0) { + desc.pg_error = dreq->error; + } else if (desc.pg_error != -EAGAIN) { + dreq->flags = 0; + if (!desc.pg_error) + desc.pg_error = -EIO; dreq->error = desc.pg_error; - else - dreq->error = -EIO; - spin_unlock(&cinfo.inode->i_lock); + } else + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + break; } nfs_release_request(req); } nfs_pageio_complete(&desc); - while (!list_empty(&failed)) { - req = nfs_list_entry(failed.next); + while (!list_empty(&reqs)) { + req = nfs_list_entry(reqs.next); nfs_list_remove_request(req); nfs_unlock_and_release_request(req); + if (desc.pg_error == -EAGAIN) { + nfs_mark_request_commit(req, NULL, &cinfo, 0); + } else { + spin_lock(&dreq->lock); + nfs_direct_truncate_request(dreq, req); + spin_unlock(&dreq->lock); + nfs_release_request(req); + } } if (put_dreq(dreq)) @@ -589,8 +609,6 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) if (status < 0) { /* Errors in commit are fatal */ dreq->error = status; - dreq->max_count = 0; - dreq->count = 0; dreq->flags = NFS_ODIRECT_DONE; } else { status = dreq->error; @@ -601,7 +619,12 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) while (!list_empty(&data->pages)) { req = nfs_list_entry(data->pages.next); nfs_list_remove_request(req); - if (status >= 0 && !nfs_write_match_verf(verf, req)) { + if (status < 0) { + spin_lock(&dreq->lock); + nfs_direct_truncate_request(dreq, req); + spin_unlock(&dreq->lock); + nfs_release_request(req); + } else if (!nfs_write_match_verf(verf, req)) { dreq->flags = NFS_ODIRECT_RESCHED_WRITES; /* * Despite the reboot, the write was successful, @@ -609,7 +632,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) */ req->wb_nio = 0; nfs_mark_request_commit(req, NULL, &cinfo, 0); - } else /* Error or match */ + } else nfs_release_request(req); nfs_unlock_and_release_request(req); } @@ -662,6 +685,7 @@ static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq) while (!list_empty(&reqs)) { req = nfs_list_entry(reqs.next); nfs_list_remove_request(req); + nfs_direct_truncate_request(dreq, req); nfs_release_request(req); nfs_unlock_and_release_request(req); } @@ -711,7 +735,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) } nfs_direct_count_bytes(dreq, hdr); - if (test_bit(NFS_IOHDR_UNSTABLE_WRITES, &hdr->flags)) { + if (test_bit(NFS_IOHDR_UNSTABLE_WRITES, &hdr->flags) && + !test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { if (!dreq->flags) dreq->flags = NFS_ODIRECT_DO_COMMIT; flags = dreq->flags; @@ -755,18 +780,23 @@ static void nfs_write_sync_pgio_error(struct list_head *head, int error) static void nfs_direct_write_reschedule_io(struct nfs_pgio_header *hdr) { struct nfs_direct_req *dreq = hdr->dreq; + struct nfs_page *req; + struct nfs_commit_info cinfo; trace_nfs_direct_write_reschedule_io(dreq); + nfs_init_cinfo_from_dreq(&cinfo, dreq); spin_lock(&dreq->lock); - if (dreq->error == 0) { + if (dreq->error == 0) dreq->flags = NFS_ODIRECT_RESCHED_WRITES; - /* fake unstable write to let common nfs resend pages */ - hdr->verf.committed = NFS_UNSTABLE; - hdr->good_bytes = hdr->args.offset + hdr->args.count - - hdr->io_start; - } + set_bit(NFS_IOHDR_REDO, &hdr->flags); spin_unlock(&dreq->lock); + while (!list_empty(&hdr->pages)) { + req = nfs_list_entry(hdr->pages.next); + nfs_list_remove_request(req); + nfs_unlock_request(req); + nfs_mark_request_commit(req, NULL, &cinfo, 0); + } } static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { @@ -794,9 +824,11 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, { struct nfs_pageio_descriptor desc; struct inode *inode = dreq->inode; + struct nfs_commit_info cinfo; ssize_t result = 0; size_t requested_bytes = 0; size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE); + bool defer = false; trace_nfs_direct_write_schedule_iovec(dreq); @@ -837,17 +869,37 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, break; } - nfs_lock_request(req); - if (!nfs_pageio_add_request(&desc, req)) { - result = desc.pg_error; - nfs_unlock_and_release_request(req); - break; - } pgbase = 0; bytes -= req_len; requested_bytes += req_len; pos += req_len; dreq->bytes_left -= req_len; + + if (defer) { + nfs_mark_request_commit(req, NULL, &cinfo, 0); + continue; + } + + nfs_lock_request(req); + if (nfs_pageio_add_request(&desc, req)) + continue; + + /* Exit on hard errors */ + if (desc.pg_error < 0 && desc.pg_error != -EAGAIN) { + result = desc.pg_error; + nfs_unlock_and_release_request(req); + break; + } + + /* If the error is soft, defer remaining requests */ + nfs_init_cinfo_from_dreq(&cinfo, dreq); + spin_lock(&dreq->lock); + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + nfs_unlock_request(req); + nfs_mark_request_commit(req, NULL, &cinfo, 0); + desc.pg_error = 0; + defer = true; } nfs_direct_release_pages(pagevec, npages); kvfree(pagevec); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 7deb3cd76abe..a1dc33864906 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1235,6 +1235,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, case -EPFNOSUPPORT: case -EPROTONOSUPPORT: case -EOPNOTSUPP: + case -EINVAL: case -ECONNREFUSED: case -ECONNRESET: case -EHOSTDOWN: diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 27fb25567ce7..11e3a285594c 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -417,6 +417,8 @@ static void nfs4_add_trunk(struct nfs_client *clp, struct nfs_client *old) .net = old->cl_net, .servername = old->cl_hostname, }; + int max_connect = test_bit(NFS_CS_PNFS, &clp->cl_flags) ? + clp->cl_max_connect : old->cl_max_connect; if (clp->cl_proto != old->cl_proto) return; @@ -430,7 +432,7 @@ static void nfs4_add_trunk(struct nfs_client *clp, struct nfs_client *old) xprt_args.addrlen = clp_salen; rpc_clnt_add_xprt(old->cl_rpcclient, &xprt_args, - rpc_clnt_test_and_add_xprt, NULL); + rpc_clnt_test_and_add_xprt, &max_connect); } /** @@ -1010,6 +1012,8 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); __set_bit(NFS_CS_DS, &cl_init.init_flags); + __set_bit(NFS_CS_PNFS, &cl_init.init_flags); + cl_init.max_connect = NFS_MAX_TRANSPORTS; /* * Set an authflavor equual to the MDS value. Use the MDS nfs_client * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 794343790ea8..3508d8238826 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2703,8 +2703,12 @@ static int _nfs4_proc_open(struct nfs4_opendata *data, return status; } if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) { + struct nfs_fh *fh = &o_res->fh; + nfs4_sequence_free_slot(&o_res->seq_res); - nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, NULL); + if (o_arg->claim == NFS4_OPEN_CLAIM_FH) + fh = NFS_FH(d_inode(data->dentry)); + nfs4_proc_getattr(server, fh, o_res->f_attr, NULL); } return 0; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f4cca8f00c0c..8c1ee1a1a28f 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -59,7 +59,8 @@ static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops; static const struct nfs_commit_completion_ops nfs_commit_completion_ops; static const struct nfs_rw_ops nfs_rw_write_ops; static void nfs_inode_remove_request(struct nfs_page *req); -static void nfs_clear_request_commit(struct nfs_page *req); +static void nfs_clear_request_commit(struct nfs_commit_info *cinfo, + struct nfs_page *req); static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, struct inode *inode); static struct nfs_page * @@ -502,8 +503,8 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, * the (former) group. All subrequests are removed from any write or commit * lists, unlinked from the group and destroyed. */ -void -nfs_join_page_group(struct nfs_page *head, struct inode *inode) +void nfs_join_page_group(struct nfs_page *head, struct nfs_commit_info *cinfo, + struct inode *inode) { struct nfs_page *subreq; struct nfs_page *destroy_list = NULL; @@ -533,7 +534,7 @@ nfs_join_page_group(struct nfs_page *head, struct inode *inode) * Commit list removal accounting is done after locks are dropped */ subreq = head; do { - nfs_clear_request_commit(subreq); + nfs_clear_request_commit(cinfo, subreq); subreq = subreq->wb_this_page; } while (subreq != head); @@ -566,8 +567,10 @@ static struct nfs_page *nfs_lock_and_join_requests(struct folio *folio) { struct inode *inode = folio_file_mapping(folio)->host; struct nfs_page *head; + struct nfs_commit_info cinfo; int ret; + nfs_init_cinfo_from_inode(&cinfo, inode); /* * A reference is taken only on the head request which acts as a * reference to the whole page group - the group will not be destroyed @@ -584,7 +587,7 @@ static struct nfs_page *nfs_lock_and_join_requests(struct folio *folio) return ERR_PTR(ret); } - nfs_join_page_group(head, inode); + nfs_join_page_group(head, &cinfo, inode); return head; } @@ -955,18 +958,16 @@ static void nfs_folio_clear_commit(struct folio *folio) } /* Called holding the request lock on @req */ -static void -nfs_clear_request_commit(struct nfs_page *req) +static void nfs_clear_request_commit(struct nfs_commit_info *cinfo, + struct nfs_page *req) { if (test_bit(PG_CLEAN, &req->wb_flags)) { struct nfs_open_context *ctx = nfs_req_openctx(req); struct inode *inode = d_inode(ctx->dentry); - struct nfs_commit_info cinfo; - nfs_init_cinfo_from_inode(&cinfo, inode); mutex_lock(&NFS_I(inode)->commit_mutex); - if (!pnfs_clear_request_commit(req, &cinfo)) { - nfs_request_remove_commit_list(req, &cinfo); + if (!pnfs_clear_request_commit(req, cinfo)) { + nfs_request_remove_commit_list(req, cinfo); } mutex_unlock(&NFS_I(inode)->commit_mutex); nfs_folio_clear_commit(nfs_page_to_folio(req)); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 9dda7e54b2d0..9a8f32f21ff5 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -289,9 +289,7 @@ struct proc_maps_private { struct inode *inode; struct task_struct *task; struct mm_struct *mm; -#ifdef CONFIG_MMU struct vma_iterator iter; -#endif #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index a8ac0dd8041e..7cebd397cc26 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -175,15 +175,28 @@ static int show_map(struct seq_file *m, void *_p) return nommu_vma_show(m, _p); } -static void *m_start(struct seq_file *m, loff_t *pos) +static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv, + loff_t *ppos) +{ + struct vm_area_struct *vma = vma_next(&priv->iter); + + if (vma) { + *ppos = vma->vm_start; + } else { + *ppos = -1UL; + } + + return vma; +} + +static void *m_start(struct seq_file *m, loff_t *ppos) { struct proc_maps_private *priv = m->private; + unsigned long last_addr = *ppos; struct mm_struct *mm; - struct vm_area_struct *vma; - unsigned long addr = *pos; - /* See m_next(). Zero at the start or after lseek. */ - if (addr == -1UL) + /* See proc_get_vma(). Zero at the start or after lseek. */ + if (last_addr == -1UL) return NULL; /* pin the task and mm whilst we play with them */ @@ -192,44 +205,41 @@ static void *m_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-ESRCH); mm = priv->mm; - if (!mm || !mmget_not_zero(mm)) + if (!mm || !mmget_not_zero(mm)) { + put_task_struct(priv->task); + priv->task = NULL; return NULL; + } if (mmap_read_lock_killable(mm)) { mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; return ERR_PTR(-EINTR); } - /* start the next element from addr */ - vma = find_vma(mm, addr); - if (vma) - return vma; + vma_iter_init(&priv->iter, mm, last_addr); - mmap_read_unlock(mm); - mmput(mm); - return NULL; + return proc_get_vma(priv, ppos); } -static void m_stop(struct seq_file *m, void *_vml) +static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; + struct mm_struct *mm = priv->mm; - if (!IS_ERR_OR_NULL(_vml)) { - mmap_read_unlock(priv->mm); - mmput(priv->mm); - } - if (priv->task) { - put_task_struct(priv->task); - priv->task = NULL; - } + if (!priv->task) + return; + + mmap_read_unlock(mm); + mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; } -static void *m_next(struct seq_file *m, void *_p, loff_t *pos) +static void *m_next(struct seq_file *m, void *_p, loff_t *ppos) { - struct vm_area_struct *vma = _p; - - *pos = vma->vm_end; - return find_vma(vma->vm_mm, vma->vm_end); + return proc_get_vma(m->private, ppos); } static const struct seq_operations proc_pid_maps_ops = { diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index b17f067e4ada..e2be8aedb26e 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -452,6 +452,9 @@ void invalidate_all_cached_dirs(struct cifs_tcon *tcon) struct cached_fid *cfid, *q; LIST_HEAD(entry); + if (cfids == NULL) + return; + spin_lock(&cfids->cfid_list_lock); list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { list_move(&cfid->entry, &entry); @@ -651,6 +654,9 @@ void free_cached_dirs(struct cached_fids *cfids) struct cached_fid *cfid, *q; LIST_HEAD(entry); + if (cfids == NULL) + return; + if (cfids->laundromat) { kthread_stop(cfids->laundromat); cfids->laundromat = NULL; diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 032d8716f671..02082621d8e0 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1807,6 +1807,7 @@ static inline bool is_retryable_error(int error) #define MID_RETRY_NEEDED 8 /* session closed while this request out */ #define MID_RESPONSE_MALFORMED 0x10 #define MID_SHUTDOWN 0x20 +#define MID_RESPONSE_READY 0x40 /* ready for other process handle the rsp */ /* Flags */ #define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */ @@ -1943,7 +1944,7 @@ require use of the stronger protocol */ * cifsInodeInfo->lock_sem cifsInodeInfo->llist cifs_init_once * ->can_cache_brlcks * cifsInodeInfo->deferred_lock cifsInodeInfo->deferred_closes cifsInodeInfo_alloc - * cached_fid->fid_mutex cifs_tcon->crfid tconInfoAlloc + * cached_fid->fid_mutex cifs_tcon->crfid tcon_info_alloc * cifsFileInfo->fh_mutex cifsFileInfo cifs_new_fileinfo * cifsFileInfo->file_info_lock cifsFileInfo->count cifs_new_fileinfo * ->invalidHandle initiate_cifs_search diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 7d8035846680..0c37eefa18a5 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -512,7 +512,7 @@ extern int CIFSSMBLogoff(const unsigned int xid, struct cifs_ses *ses); extern struct cifs_ses *sesInfoAlloc(void); extern void sesInfoFree(struct cifs_ses *); -extern struct cifs_tcon *tconInfoAlloc(void); +extern struct cifs_tcon *tcon_info_alloc(bool dir_leases_enabled); extern void tconInfoFree(struct cifs_tcon *); extern int cifs_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server, diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 687754791bf0..3902e90dca6b 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -1882,7 +1882,8 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) } } - tcon = tconInfoAlloc(); + /* no need to setup directory caching on IPC share, so pass in false */ + tcon = tcon_info_alloc(false); if (tcon == NULL) return -ENOMEM; @@ -2492,7 +2493,10 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) goto out_fail; } - tcon = tconInfoAlloc(); + if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) + tcon = tcon_info_alloc(true); + else + tcon = tcon_info_alloc(false); if (tcon == NULL) { rc = -ENOMEM; goto out_fail; diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 366b755ca913..35b176457bbe 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -113,18 +113,22 @@ sesInfoFree(struct cifs_ses *buf_to_free) } struct cifs_tcon * -tconInfoAlloc(void) +tcon_info_alloc(bool dir_leases_enabled) { struct cifs_tcon *ret_buf; ret_buf = kzalloc(sizeof(*ret_buf), GFP_KERNEL); if (!ret_buf) return NULL; - ret_buf->cfids = init_cached_dirs(); - if (!ret_buf->cfids) { - kfree(ret_buf); - return NULL; + + if (dir_leases_enabled == true) { + ret_buf->cfids = init_cached_dirs(); + if (!ret_buf->cfids) { + kfree(ret_buf); + return NULL; + } } + /* else ret_buf->cfids is already set to NULL above */ atomic_inc(&tconInfoAllocCount); ret_buf->status = TID_NEW; diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index b41e2e872b22..0b89f7008ac0 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -539,6 +539,9 @@ static int parse_create_response(struct cifs_open_info_data *data, int rc = 0; switch (rsp->hdr.Status) { + case STATUS_IO_REPARSE_TAG_NOT_HANDLED: + reparse_point = true; + break; case STATUS_STOPPED_ON_SYMLINK: rc = smb2_parse_symlink_response(cifs_sb, iov, &data->symlink_target); diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c index 194799ddd382..1a90dd78b238 100644 --- a/fs/smb/client/smb2maperror.c +++ b/fs/smb/client/smb2maperror.c @@ -877,8 +877,6 @@ static const struct status_to_posix_error smb2_error_map_table[] = { "STATUS_IO_REPARSE_TAG_MISMATCH"}, {STATUS_IO_REPARSE_DATA_INVALID, -EIO, "STATUS_IO_REPARSE_DATA_INVALID"}, - {STATUS_IO_REPARSE_TAG_NOT_HANDLED, -EIO, - "STATUS_IO_REPARSE_TAG_NOT_HANDLED"}, {STATUS_REPARSE_POINT_NOT_RESOLVED, -EIO, "STATUS_REPARSE_POINT_NOT_RESOLVED"}, {STATUS_DIRECTORY_IS_A_REPARSE_POINT, -EIO, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 44d4943e9c56..c75a80bb6d9e 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -848,7 +848,7 @@ add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode) iov[num].iov_base = create_posix_buf(mode); if (mode == ACL_NO_MODE) - cifs_dbg(FYI, "Invalid mode\n"); + cifs_dbg(FYI, "%s: no mode\n", __func__); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_posix); @@ -3878,7 +3878,7 @@ void smb2_reconnect_server(struct work_struct *work) goto done; /* allocate a dummy tcon struct used for reconnect */ - tcon = tconInfoAlloc(); + tcon = tcon_info_alloc(false); if (!tcon) { resched = true; list_for_each_entry_safe(ses, ses2, &tmp_ses_list, rlist) { diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 2a2aec8c6112..94df9eec3d8d 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1401,10 +1401,13 @@ create_conn: server->smbd_conn = smbd_get_connection( server, (struct sockaddr *) &server->dstaddr); - if (server->smbd_conn) + if (server->smbd_conn) { cifs_dbg(VFS, "RDMA transport re-established\n"); - - return server->smbd_conn ? 0 : -ENOENT; + trace_smb3_smbd_connect_done(server->hostname, server->conn_id, &server->dstaddr); + return 0; + } + trace_smb3_smbd_connect_err(server->hostname, server->conn_id, &server->dstaddr); + return -ENOENT; } static void destroy_caches_and_workqueue(struct smbd_connection *info) diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index a7e4755bed0f..de199ec9f726 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -935,6 +935,8 @@ DEFINE_EVENT(smb3_connect_class, smb3_##name, \ TP_ARGS(hostname, conn_id, addr)) DEFINE_SMB3_CONNECT_EVENT(connect_done); +DEFINE_SMB3_CONNECT_EVENT(smbd_connect_done); +DEFINE_SMB3_CONNECT_EVENT(smbd_connect_err); DECLARE_EVENT_CLASS(smb3_connect_err_class, TP_PROTO(char *hostname, __u64 conn_id, diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index d52057a511ee..14710afdc2a3 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -35,6 +35,8 @@ void cifs_wake_up_task(struct mid_q_entry *mid) { + if (mid->mid_state == MID_RESPONSE_RECEIVED) + mid->mid_state = MID_RESPONSE_READY; wake_up_process(mid->callback_data); } @@ -87,7 +89,8 @@ static void __release_mid(struct kref *refcount) struct TCP_Server_Info *server = midEntry->server; if (midEntry->resp_buf && (midEntry->mid_flags & MID_WAIT_CANCELLED) && - midEntry->mid_state == MID_RESPONSE_RECEIVED && + (midEntry->mid_state == MID_RESPONSE_RECEIVED || + midEntry->mid_state == MID_RESPONSE_READY) && server->ops->handle_cancelled_mid) server->ops->handle_cancelled_mid(midEntry, server); @@ -737,7 +740,8 @@ wait_for_response(struct TCP_Server_Info *server, struct mid_q_entry *midQ) int error; error = wait_event_state(server->response_q, - midQ->mid_state != MID_REQUEST_SUBMITTED, + midQ->mid_state != MID_REQUEST_SUBMITTED && + midQ->mid_state != MID_RESPONSE_RECEIVED, (TASK_KILLABLE|TASK_FREEZABLE_UNSAFE)); if (error < 0) return -ERESTARTSYS; @@ -890,7 +894,7 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) spin_lock(&server->mid_lock); switch (mid->mid_state) { - case MID_RESPONSE_RECEIVED: + case MID_RESPONSE_READY: spin_unlock(&server->mid_lock); return rc; case MID_RETRY_NEEDED: @@ -989,6 +993,9 @@ cifs_compound_callback(struct mid_q_entry *mid) credits.instance = server->reconnect_instance; add_credits(server, &credits, mid->optype); + + if (mid->mid_state == MID_RESPONSE_RECEIVED) + mid->mid_state = MID_RESPONSE_READY; } static void @@ -1209,7 +1216,8 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, send_cancel(server, &rqst[i], midQ[i]); spin_lock(&server->mid_lock); midQ[i]->mid_flags |= MID_WAIT_CANCELLED; - if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) { + if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED || + midQ[i]->mid_state == MID_RESPONSE_RECEIVED) { midQ[i]->callback = cifs_cancelled_callback; cancelled_mid[i] = true; credits[i].value = 0; @@ -1230,7 +1238,7 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, } if (!midQ[i]->resp_buf || - midQ[i]->mid_state != MID_RESPONSE_RECEIVED) { + midQ[i]->mid_state != MID_RESPONSE_READY) { rc = -EIO; cifs_dbg(FYI, "Bad MID state?\n"); goto out; @@ -1417,7 +1425,8 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, if (rc != 0) { send_cancel(server, &rqst, midQ); spin_lock(&server->mid_lock); - if (midQ->mid_state == MID_REQUEST_SUBMITTED) { + if (midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED) { /* no longer considered to be "in-flight" */ midQ->callback = release_mid; spin_unlock(&server->mid_lock); @@ -1434,7 +1443,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, } if (!midQ->resp_buf || !out_buf || - midQ->mid_state != MID_RESPONSE_RECEIVED) { + midQ->mid_state != MID_RESPONSE_READY) { rc = -EIO; cifs_server_dbg(VFS, "Bad MID state?\n"); goto out; @@ -1558,14 +1567,16 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, /* Wait for a reply - allow signals to interrupt. */ rc = wait_event_interruptible(server->response_q, - (!(midQ->mid_state == MID_REQUEST_SUBMITTED)) || + (!(midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED)) || ((server->tcpStatus != CifsGood) && (server->tcpStatus != CifsNew))); /* Were we interrupted by a signal ? */ spin_lock(&server->srv_lock); if ((rc == -ERESTARTSYS) && - (midQ->mid_state == MID_REQUEST_SUBMITTED) && + (midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED) && ((server->tcpStatus == CifsGood) || (server->tcpStatus == CifsNew))) { spin_unlock(&server->srv_lock); @@ -1596,7 +1607,8 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, if (rc) { send_cancel(server, &rqst, midQ); spin_lock(&server->mid_lock); - if (midQ->mid_state == MID_REQUEST_SUBMITTED) { + if (midQ->mid_state == MID_REQUEST_SUBMITTED || + midQ->mid_state == MID_RESPONSE_RECEIVED) { /* no longer considered to be "in-flight" */ midQ->callback = release_mid; spin_unlock(&server->mid_lock); @@ -1616,7 +1628,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, return rc; /* rcvd frame is ok */ - if (out_buf == NULL || midQ->mid_state != MID_RESPONSE_RECEIVED) { + if (out_buf == NULL || midQ->mid_state != MID_RESPONSE_READY) { rc = -EIO; cifs_tcon_dbg(VFS, "Bad MID state?\n"); goto out; diff --git a/fs/stat.c b/fs/stat.c index 6e60389d6a15..d43a5cc1bfa4 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -27,37 +27,6 @@ #include "mount.h" /** - * fill_mg_cmtime - Fill in the mtime and ctime and flag ctime as QUERIED - * @stat: where to store the resulting values - * @request_mask: STATX_* values requested - * @inode: inode from which to grab the c/mtime - * - * Given @inode, grab the ctime and mtime out if it and store the result - * in @stat. When fetching the value, flag it as queried so the next write - * will use a fine-grained timestamp. - */ -void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode) -{ - atomic_long_t *pnsec = (atomic_long_t *)&inode->__i_ctime.tv_nsec; - - /* If neither time was requested, then don't report them */ - if (!(request_mask & (STATX_CTIME|STATX_MTIME))) { - stat->result_mask &= ~(STATX_CTIME|STATX_MTIME); - return; - } - - stat->mtime = inode->i_mtime; - stat->ctime.tv_sec = inode->__i_ctime.tv_sec; - /* - * Atomically set the QUERIED flag and fetch the new value with - * the flag masked off. - */ - stat->ctime.tv_nsec = atomic_long_fetch_or(I_CTIME_QUERIED, pnsec) & - ~I_CTIME_QUERIED; -} -EXPORT_SYMBOL(fill_mg_cmtime); - -/** * generic_fillattr - Fill in the basic attributes from the inode struct * @idmap: idmap of the mount the inode was found from * @request_mask: statx request_mask @@ -89,14 +58,8 @@ void generic_fillattr(struct mnt_idmap *idmap, u32 request_mask, stat->rdev = inode->i_rdev; stat->size = i_size_read(inode); stat->atime = inode->i_atime; - - if (is_mgtime(inode)) { - fill_mg_cmtime(stat, request_mask, inode); - } else { - stat->mtime = inode->i_mtime; - stat->ctime = inode_get_ctime(inode); - } - + stat->mtime = inode->i_mtime; + stat->ctime = inode_get_ctime(inode); stat->blksize = i_blocksize(inode); stat->blocks = inode->i_blocks; diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 9f64e7332796..5f1714089884 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -70,6 +70,7 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); static int dcache_dir_open_wrapper(struct inode *inode, struct file *file); +static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx); static int eventfs_release(struct inode *inode, struct file *file); static const struct inode_operations eventfs_root_dir_inode_operations = { @@ -79,7 +80,7 @@ static const struct inode_operations eventfs_root_dir_inode_operations = { static const struct file_operations eventfs_file_operations = { .open = dcache_dir_open_wrapper, .read = generic_read_dir, - .iterate_shared = dcache_readdir, + .iterate_shared = dcache_readdir_wrapper, .llseek = generic_file_llseek, .release = eventfs_release, }; @@ -396,6 +397,11 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, return ret; } +struct dentry_list { + void *cursor; + struct dentry **dentries; +}; + /** * eventfs_release - called to release eventfs file/dir * @inode: inode to be released @@ -404,26 +410,25 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, static int eventfs_release(struct inode *inode, struct file *file) { struct tracefs_inode *ti; - struct eventfs_inode *ei; - struct eventfs_file *ef; - struct dentry *dentry; - int idx; + struct dentry_list *dlist = file->private_data; + void *cursor; + int i; ti = get_tracefs(inode); if (!(ti->flags & TRACEFS_EVENT_INODE)) return -EINVAL; - ei = ti->private; - idx = srcu_read_lock(&eventfs_srcu); - list_for_each_entry_srcu(ef, &ei->e_top_files, list, - srcu_read_lock_held(&eventfs_srcu)) { - mutex_lock(&eventfs_mutex); - dentry = ef->dentry; - mutex_unlock(&eventfs_mutex); - if (dentry) - dput(dentry); + if (WARN_ON_ONCE(!dlist)) + return -EINVAL; + + for (i = 0; dlist->dentries[i]; i++) { + dput(dlist->dentries[i]); } - srcu_read_unlock(&eventfs_srcu, idx); + + cursor = dlist->cursor; + kfree(dlist->dentries); + kfree(dlist); + file->private_data = cursor; return dcache_dir_close(inode, file); } @@ -442,22 +447,70 @@ static int dcache_dir_open_wrapper(struct inode *inode, struct file *file) struct tracefs_inode *ti; struct eventfs_inode *ei; struct eventfs_file *ef; + struct dentry_list *dlist; + struct dentry **dentries = NULL; struct dentry *dentry = file_dentry(file); + struct dentry *d; struct inode *f_inode = file_inode(file); + int cnt = 0; int idx; + int ret; ti = get_tracefs(f_inode); if (!(ti->flags & TRACEFS_EVENT_INODE)) return -EINVAL; + if (WARN_ON_ONCE(file->private_data)) + return -EINVAL; + + dlist = kmalloc(sizeof(*dlist), GFP_KERNEL); + if (!dlist) + return -ENOMEM; + ei = ti->private; idx = srcu_read_lock(&eventfs_srcu); list_for_each_entry_srcu(ef, &ei->e_top_files, list, srcu_read_lock_held(&eventfs_srcu)) { - create_dentry(ef, dentry, false); + d = create_dentry(ef, dentry, false); + if (d) { + struct dentry **tmp; + + tmp = krealloc(dentries, sizeof(d) * (cnt + 2), GFP_KERNEL); + if (!tmp) + break; + tmp[cnt] = d; + tmp[cnt + 1] = NULL; + cnt++; + dentries = tmp; + } } srcu_read_unlock(&eventfs_srcu, idx); - return dcache_dir_open(inode, file); + ret = dcache_dir_open(inode, file); + + /* + * dcache_dir_open() sets file->private_data to a dentry cursor. + * Need to save that but also save all the dentries that were + * opened by this function. + */ + dlist->cursor = file->private_data; + dlist->dentries = dentries; + file->private_data = dlist; + return ret; +} + +/* + * This just sets the file->private_data back to the cursor and back. + */ +static int dcache_readdir_wrapper(struct file *file, struct dir_context *ctx) +{ + struct dentry_list *dlist = file->private_data; + int ret; + + file->private_data = dlist->cursor; + ret = dcache_readdir(file, ctx); + dlist->cursor = file->private_data; + file->private_data = dlist; + return ret; } /** diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index c9d653168ad0..ed0bc8cbc703 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -147,7 +147,7 @@ config XFS_ONLINE_SCRUB_STATS bool "XFS online metadata check usage data collection" default y depends on XFS_ONLINE_SCRUB - select FS_DEBUG + select XFS_DEBUG help If you say Y here, the kernel will gather usage data about the online metadata check subsystem. This includes the number diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index 2420865f3007..a5100a11faf9 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -131,4 +131,26 @@ void xlog_check_buf_cancel_table(struct xlog *log); #define xlog_check_buf_cancel_table(log) do { } while (0) #endif +/* + * Transform a regular reservation into one suitable for recovery of a log + * intent item. + * + * Intent recovery only runs a single step of the transaction chain and defers + * the rest to a separate transaction. Therefore, we reduce logcount to 1 here + * to avoid livelocks if the log grant space is nearly exhausted due to the + * recovered intent pinning the tail. Keep the same logflags to avoid tripping + * asserts elsewhere. Struct copies abound below. + */ +static inline struct xfs_trans_res +xlog_recover_resv(const struct xfs_trans_res *r) +{ + struct xfs_trans_res ret = { + .tr_logres = r->tr_logres, + .tr_logcount = 1, + .tr_logflags = r->tr_logflags, + }; + + return ret; +} + #endif /* __XFS_LOG_RECOVER_H__ */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 5e174685a77c..6264daaab37b 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -266,7 +266,8 @@ xfs_validate_sb_write( return -EFSCORRUPTED; } - if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { + if (!xfs_is_readonly(mp) && + xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) { xfs_alert(mp, "Corruption detected in superblock read-only compatible features (0x%x)!", (sbp->sb_features_ro_compat & diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index ad22656376d3..6b2296ff248a 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -62,12 +62,12 @@ xfs_trans_ichgtime( ASSERT(tp); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - /* If the mtime changes, then ctime must also change */ - ASSERT(flags & XFS_ICHGTIME_CHG); + tv = current_time(inode); - tv = inode_set_ctime_current(inode); if (flags & XFS_ICHGTIME_MOD) inode->i_mtime = tv; + if (flags & XFS_ICHGTIME_CHG) + inode_set_ctime_to_ts(inode, tv); if (flags & XFS_ICHGTIME_CREATE) ip->i_crtime = tv; } diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 7d3aa14d81b5..4849efcaa33a 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -588,6 +588,8 @@ out_nofix: out_teardown: error = xchk_teardown(sc, error); out_sc: + if (error != -ENOENT) + xchk_stats_merge(mp, sm, &run); kfree(sc); out: trace_xchk_done(XFS_I(file_inode(file)), sm, error); @@ -595,8 +597,6 @@ out: sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT; error = 0; } - if (error != -ENOENT) - xchk_stats_merge(mp, sm, &run); return error; need_drain: error = xchk_teardown(sc, 0); diff --git a/fs/xfs/scrub/stats.c b/fs/xfs/scrub/stats.c index aeb92624176b..cd91db4a5548 100644 --- a/fs/xfs/scrub/stats.c +++ b/fs/xfs/scrub/stats.c @@ -185,7 +185,10 @@ xchk_stats_merge_one( { struct xchk_scrub_stats *css; - ASSERT(sm->sm_type < XFS_SCRUB_TYPE_NR); + if (sm->sm_type >= XFS_SCRUB_TYPE_NR) { + ASSERT(sm->sm_type < XFS_SCRUB_TYPE_NR); + return; + } css = &cs->cs_stats[sm->sm_type]; spin_lock(&css->css_lock); diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index 5db87b34fb6e..89c7a9f4f930 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -333,7 +333,6 @@ xfs_attr_inactive( int error = 0; mp = dp->i_mount; - ASSERT(! XFS_NOT_DQATTACHED(mp, dp)); xfs_ilock(dp, lock_mode); if (!xfs_inode_has_attr_fork(dp)) diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c index 2788a6f2edcd..36fe2abb16e6 100644 --- a/fs/xfs/xfs_attr_item.c +++ b/fs/xfs/xfs_attr_item.c @@ -547,7 +547,7 @@ xfs_attri_item_recover( struct xfs_inode *ip; struct xfs_da_args *args; struct xfs_trans *tp; - struct xfs_trans_res tres; + struct xfs_trans_res resv; struct xfs_attri_log_format *attrp; struct xfs_attri_log_nameval *nv = attrip->attri_nameval; int error; @@ -618,8 +618,9 @@ xfs_attri_item_recover( goto out; } - xfs_init_attr_trans(args, &tres, &total); - error = xfs_trans_alloc(mp, &tres, total, 0, XFS_TRANS_RESERVE, &tp); + xfs_init_attr_trans(args, &resv, &total); + resv = xlog_recover_resv(&resv); + error = xfs_trans_alloc(mp, &resv, total, 0, XFS_TRANS_RESERVE, &tp); if (error) goto out; diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 7551c3ec4ea5..e736a0844c89 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -490,6 +490,7 @@ xfs_bui_item_recover( struct list_head *capture_list) { struct xfs_bmap_intent fake = { }; + struct xfs_trans_res resv; struct xfs_bui_log_item *buip = BUI_ITEM(lip); struct xfs_trans *tp; struct xfs_inode *ip = NULL; @@ -515,7 +516,8 @@ xfs_bui_item_recover( return error; /* Allocate transaction and do the work. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp); if (error) goto err_rele; diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c index 1064c2342876..f71ea786a6d2 100644 --- a/fs/xfs/xfs_export.c +++ b/fs/xfs/xfs_export.c @@ -146,6 +146,12 @@ xfs_nfs_get_inode( return ERR_PTR(error); } + error = xfs_inode_reload_unlinked(ip); + if (error) { + xfs_irele(ip); + return ERR_PTR(error); + } + if (VFS_I(ip)->i_generation != generation) { xfs_irele(ip); return ERR_PTR(-ESTALE); diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index f1a5ecf099aa..3fa8789820ad 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -660,6 +660,7 @@ xfs_efi_item_recover( struct xfs_log_item *lip, struct list_head *capture_list) { + struct xfs_trans_res resv; struct xfs_efi_log_item *efip = EFI_ITEM(lip); struct xfs_mount *mp = lip->li_log->l_mp; struct xfs_efd_log_item *efdp; @@ -683,7 +684,8 @@ xfs_efi_item_recover( } } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, 0, 0, 0, &tp); if (error) return error; efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents); diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 10403ba9b58f..736e5545f584 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -565,6 +565,19 @@ err: } #endif /* CONFIG_XFS_RT */ +static inline bool +rmap_not_shareable(struct xfs_mount *mp, const struct xfs_rmap_irec *r) +{ + if (!xfs_has_reflink(mp)) + return true; + if (XFS_RMAP_NON_INODE_OWNER(r->rm_owner)) + return true; + if (r->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK | + XFS_RMAP_UNWRITTEN)) + return true; + return false; +} + /* Execute a getfsmap query against the regular data device. */ STATIC int __xfs_getfsmap_datadev( @@ -598,7 +611,6 @@ __xfs_getfsmap_datadev( * low to the fsmap low key and max out the high key to the end * of the AG. */ - info->low.rm_startblock = XFS_FSB_TO_AGBNO(mp, start_fsb); info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset); error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]); if (error) @@ -608,12 +620,9 @@ __xfs_getfsmap_datadev( /* Adjust the low key if we are continuing from where we left off. */ if (info->low.rm_blockcount == 0) { - /* empty */ - } else if (XFS_RMAP_NON_INODE_OWNER(info->low.rm_owner) || - (info->low.rm_flags & (XFS_RMAP_ATTR_FORK | - XFS_RMAP_BMBT_BLOCK | - XFS_RMAP_UNWRITTEN))) { - info->low.rm_startblock += info->low.rm_blockcount; + /* No previous record from which to continue */ + } else if (rmap_not_shareable(mp, &info->low)) { + /* Last record seen was an unshareable extent */ info->low.rm_owner = 0; info->low.rm_offset = 0; @@ -621,8 +630,10 @@ __xfs_getfsmap_datadev( if (XFS_FSB_TO_DADDR(mp, start_fsb) >= eofs) return 0; } else { + /* Last record seen was a shareable file data extent */ info->low.rm_offset += info->low.rm_blockcount; } + info->low.rm_startblock = XFS_FSB_TO_AGBNO(mp, start_fsb); info->high.rm_startblock = -1U; info->high.rm_owner = ULLONG_MAX; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index e541f5c0bc25..3c210ac83713 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -113,7 +113,7 @@ xfs_inode_alloc( INIT_LIST_HEAD(&ip->i_ioend_list); spin_lock_init(&ip->i_ioend_lock); ip->i_next_unlinked = NULLAGINO; - ip->i_prev_unlinked = NULLAGINO; + ip->i_prev_unlinked = 0; return ip; } @@ -443,7 +443,7 @@ xfs_inodegc_queue_all( int cpu; bool ret = false; - for_each_online_cpu(cpu) { + for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) { mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0); @@ -463,7 +463,7 @@ xfs_inodegc_wait_all( int error = 0; flush_workqueue(mp->m_inodegc_wq); - for_each_online_cpu(cpu) { + for_each_cpu(cpu, &mp->m_inodegc_cpumask) { struct xfs_inodegc *gc; gc = per_cpu_ptr(mp->m_inodegc, cpu); @@ -1845,9 +1845,17 @@ xfs_inodegc_worker( struct xfs_inodegc, work); struct llist_node *node = llist_del_all(&gc->list); struct xfs_inode *ip, *n; + struct xfs_mount *mp = gc->mp; unsigned int nofs_flag; - ASSERT(gc->cpu == smp_processor_id()); + /* + * Clear the cpu mask bit and ensure that we have seen the latest + * update of the gc structure associated with this CPU. This matches + * with the release semantics used when setting the cpumask bit in + * xfs_inodegc_queue. + */ + cpumask_clear_cpu(gc->cpu, &mp->m_inodegc_cpumask); + smp_mb__after_atomic(); WRITE_ONCE(gc->items, 0); @@ -1862,7 +1870,7 @@ xfs_inodegc_worker( nofs_flag = memalloc_nofs_save(); ip = llist_entry(node, struct xfs_inode, i_gclist); - trace_xfs_inodegc_worker(ip->i_mount, READ_ONCE(gc->shrinker_hits)); + trace_xfs_inodegc_worker(mp, READ_ONCE(gc->shrinker_hits)); WRITE_ONCE(gc->shrinker_hits, 0); llist_for_each_entry_safe(ip, n, node, i_gclist) { @@ -2057,6 +2065,7 @@ xfs_inodegc_queue( struct xfs_inodegc *gc; int items; unsigned int shrinker_hits; + unsigned int cpu_nr; unsigned long queue_delay = 1; trace_xfs_inode_set_need_inactive(ip); @@ -2064,18 +2073,28 @@ xfs_inodegc_queue( ip->i_flags |= XFS_NEED_INACTIVE; spin_unlock(&ip->i_flags_lock); - gc = get_cpu_ptr(mp->m_inodegc); + cpu_nr = get_cpu(); + gc = this_cpu_ptr(mp->m_inodegc); llist_add(&ip->i_gclist, &gc->list); items = READ_ONCE(gc->items); WRITE_ONCE(gc->items, items + 1); shrinker_hits = READ_ONCE(gc->shrinker_hits); /* + * Ensure the list add is always seen by anyone who finds the cpumask + * bit set. This effectively gives the cpumask bit set operation + * release ordering semantics. + */ + smp_mb__before_atomic(); + if (!cpumask_test_cpu(cpu_nr, &mp->m_inodegc_cpumask)) + cpumask_test_and_set_cpu(cpu_nr, &mp->m_inodegc_cpumask); + + /* * We queue the work while holding the current CPU so that the work * is scheduled to run on this CPU. */ if (!xfs_is_inodegc_enabled(mp)) { - put_cpu_ptr(gc); + put_cpu(); return; } @@ -2085,7 +2104,7 @@ xfs_inodegc_queue( trace_xfs_inodegc_queue(mp, __return_address); mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work, queue_delay); - put_cpu_ptr(gc); + put_cpu(); if (xfs_inodegc_want_flush_work(ip, items, shrinker_hits)) { trace_xfs_inodegc_throttle(mp, __return_address); @@ -2094,47 +2113,6 @@ xfs_inodegc_queue( } /* - * Fold the dead CPU inodegc queue into the current CPUs queue. - */ -void -xfs_inodegc_cpu_dead( - struct xfs_mount *mp, - unsigned int dead_cpu) -{ - struct xfs_inodegc *dead_gc, *gc; - struct llist_node *first, *last; - unsigned int count = 0; - - dead_gc = per_cpu_ptr(mp->m_inodegc, dead_cpu); - cancel_delayed_work_sync(&dead_gc->work); - - if (llist_empty(&dead_gc->list)) - return; - - first = dead_gc->list.first; - last = first; - while (last->next) { - last = last->next; - count++; - } - dead_gc->list.first = NULL; - dead_gc->items = 0; - - /* Add pending work to current CPU */ - gc = get_cpu_ptr(mp->m_inodegc); - llist_add_batch(first, last, &gc->list); - count += READ_ONCE(gc->items); - WRITE_ONCE(gc->items, count); - - if (xfs_is_inodegc_enabled(mp)) { - trace_xfs_inodegc_queue(mp, __return_address); - mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work, - 0); - } - put_cpu_ptr(gc); -} - -/* * We set the inode flag atomically with the radix tree tag. Once we get tag * lookups on the radix tree, this inode flag can go away. * @@ -2195,7 +2173,7 @@ xfs_inodegc_shrinker_count( if (!xfs_is_inodegc_enabled(mp)) return 0; - for_each_online_cpu(cpu) { + for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) return XFS_INODEGC_SHRINKER_COUNT; @@ -2220,7 +2198,7 @@ xfs_inodegc_shrinker_scan( trace_xfs_inodegc_shrinker_scan(mp, sc, __return_address); - for_each_online_cpu(cpu) { + for_each_cpu(cpu, &mp->m_inodegc_cpumask) { gc = per_cpu_ptr(mp->m_inodegc, cpu); if (!llist_empty(&gc->list)) { unsigned int h = READ_ONCE(gc->shrinker_hits); diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index 2fa6f2e09d07..905944dafbe5 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -79,7 +79,6 @@ void xfs_inodegc_push(struct xfs_mount *mp); int xfs_inodegc_flush(struct xfs_mount *mp); void xfs_inodegc_stop(struct xfs_mount *mp); void xfs_inodegc_start(struct xfs_mount *mp); -void xfs_inodegc_cpu_dead(struct xfs_mount *mp, unsigned int cpu); int xfs_inodegc_register_shrinker(struct xfs_mount *mp); #endif diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 360fe83a334f..f94f7b374041 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1642,8 +1642,11 @@ xfs_inode_needs_inactive( if (VFS_I(ip)->i_mode == 0) return false; - /* If this is a read-only mount, don't do this (would generate I/O) */ - if (xfs_is_readonly(mp)) + /* + * If this is a read-only mount, don't do this (would generate I/O) + * unless we're in log recovery and cleaning the iunlinked list. + */ + if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log)) return false; /* If the log isn't running, push inodes straight to reclaim. */ @@ -1703,8 +1706,11 @@ xfs_inactive( mp = ip->i_mount; ASSERT(!xfs_iflags_test(ip, XFS_IRECOVERY)); - /* If this is a read-only mount, don't do this (would generate I/O) */ - if (xfs_is_readonly(mp)) + /* + * If this is a read-only mount, don't do this (would generate I/O) + * unless we're in log recovery and cleaning the iunlinked list. + */ + if (xfs_is_readonly(mp) && !xlog_recovery_needed(mp->m_log)) goto out; /* Metadata inodes require explicit resource cleanup. */ @@ -1736,9 +1742,13 @@ xfs_inactive( ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0)) truncate = 1; - error = xfs_qm_dqattach(ip); - if (error) - goto out; + if (xfs_iflags_test(ip, XFS_IQUOTAUNCHECKED)) { + xfs_qm_dqdetach(ip); + } else { + error = xfs_qm_dqattach(ip); + if (error) + goto out; + } if (S_ISLNK(VFS_I(ip)->i_mode)) error = xfs_inactive_symlink(ip); @@ -1822,12 +1832,17 @@ xfs_iunlink_lookup( rcu_read_lock(); ip = radix_tree_lookup(&pag->pag_ici_root, agino); + if (!ip) { + /* Caller can handle inode not being in memory. */ + rcu_read_unlock(); + return NULL; + } /* - * Inode not in memory or in RCU freeing limbo should not happen. - * Warn about this and let the caller handle the failure. + * Inode in RCU freeing limbo should not happen. Warn about this and + * let the caller handle the failure. */ - if (WARN_ON_ONCE(!ip || !ip->i_ino)) { + if (WARN_ON_ONCE(!ip->i_ino)) { rcu_read_unlock(); return NULL; } @@ -1836,7 +1851,10 @@ xfs_iunlink_lookup( return ip; } -/* Update the prev pointer of the next agino. */ +/* + * Update the prev pointer of the next agino. Returns -ENOLINK if the inode + * is not in cache. + */ static int xfs_iunlink_update_backref( struct xfs_perag *pag, @@ -1851,7 +1869,8 @@ xfs_iunlink_update_backref( ip = xfs_iunlink_lookup(pag, next_agino); if (!ip) - return -EFSCORRUPTED; + return -ENOLINK; + ip->i_prev_unlinked = prev_agino; return 0; } @@ -1895,6 +1914,64 @@ xfs_iunlink_update_bucket( return 0; } +/* + * Load the inode @next_agino into the cache and set its prev_unlinked pointer + * to @prev_agino. Caller must hold the AGI to synchronize with other changes + * to the unlinked list. + */ +STATIC int +xfs_iunlink_reload_next( + struct xfs_trans *tp, + struct xfs_buf *agibp, + xfs_agino_t prev_agino, + xfs_agino_t next_agino) +{ + struct xfs_perag *pag = agibp->b_pag; + struct xfs_mount *mp = pag->pag_mount; + struct xfs_inode *next_ip = NULL; + xfs_ino_t ino; + int error; + + ASSERT(next_agino != NULLAGINO); + +#ifdef DEBUG + rcu_read_lock(); + next_ip = radix_tree_lookup(&pag->pag_ici_root, next_agino); + ASSERT(next_ip == NULL); + rcu_read_unlock(); +#endif + + xfs_info_ratelimited(mp, + "Found unrecovered unlinked inode 0x%x in AG 0x%x. Initiating recovery.", + next_agino, pag->pag_agno); + + /* + * Use an untrusted lookup just to be cautious in case the AGI has been + * corrupted and now points at a free inode. That shouldn't happen, + * but we'd rather shut down now since we're already running in a weird + * situation. + */ + ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, next_agino); + error = xfs_iget(mp, tp, ino, XFS_IGET_UNTRUSTED, 0, &next_ip); + if (error) + return error; + + /* If this is not an unlinked inode, something is very wrong. */ + if (VFS_I(next_ip)->i_nlink != 0) { + error = -EFSCORRUPTED; + goto rele; + } + + next_ip->i_prev_unlinked = prev_agino; + trace_xfs_iunlink_reload_next(next_ip); +rele: + ASSERT(!(VFS_I(next_ip)->i_state & I_DONTCACHE)); + if (xfs_is_quotacheck_running(mp) && next_ip) + xfs_iflags_set(next_ip, XFS_IQUOTAUNCHECKED); + xfs_irele(next_ip); + return error; +} + static int xfs_iunlink_insert_inode( struct xfs_trans *tp, @@ -1926,6 +2003,8 @@ xfs_iunlink_insert_inode( * inode. */ error = xfs_iunlink_update_backref(pag, agino, next_agino); + if (error == -ENOLINK) + error = xfs_iunlink_reload_next(tp, agibp, agino, next_agino); if (error) return error; @@ -1941,6 +2020,7 @@ xfs_iunlink_insert_inode( } /* Point the head of the list to point to this inode. */ + ip->i_prev_unlinked = NULLAGINO; return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino); } @@ -2020,6 +2100,9 @@ xfs_iunlink_remove_inode( */ error = xfs_iunlink_update_backref(pag, ip->i_prev_unlinked, ip->i_next_unlinked); + if (error == -ENOLINK) + error = xfs_iunlink_reload_next(tp, agibp, ip->i_prev_unlinked, + ip->i_next_unlinked); if (error) return error; @@ -2040,7 +2123,7 @@ xfs_iunlink_remove_inode( } ip->i_next_unlinked = NULLAGINO; - ip->i_prev_unlinked = NULLAGINO; + ip->i_prev_unlinked = 0; return error; } @@ -3529,3 +3612,103 @@ xfs_iunlock2_io_mmap( if (ip1 != ip2) inode_unlock(VFS_I(ip1)); } + +/* + * Reload the incore inode list for this inode. Caller should ensure that + * the link count cannot change, either by taking ILOCK_SHARED or otherwise + * preventing other threads from executing. + */ +int +xfs_inode_reload_unlinked_bucket( + struct xfs_trans *tp, + struct xfs_inode *ip) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_buf *agibp; + struct xfs_agi *agi; + struct xfs_perag *pag; + xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, ip->i_ino); + xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino); + xfs_agino_t prev_agino, next_agino; + unsigned int bucket; + bool foundit = false; + int error; + + /* Grab the first inode in the list */ + pag = xfs_perag_get(mp, agno); + error = xfs_ialloc_read_agi(pag, tp, &agibp); + xfs_perag_put(pag); + if (error) + return error; + + bucket = agino % XFS_AGI_UNLINKED_BUCKETS; + agi = agibp->b_addr; + + trace_xfs_inode_reload_unlinked_bucket(ip); + + xfs_info_ratelimited(mp, + "Found unrecovered unlinked inode 0x%x in AG 0x%x. Initiating list recovery.", + agino, agno); + + prev_agino = NULLAGINO; + next_agino = be32_to_cpu(agi->agi_unlinked[bucket]); + while (next_agino != NULLAGINO) { + struct xfs_inode *next_ip = NULL; + + if (next_agino == agino) { + /* Found this inode, set its backlink. */ + next_ip = ip; + next_ip->i_prev_unlinked = prev_agino; + foundit = true; + } + if (!next_ip) { + /* Inode already in memory. */ + next_ip = xfs_iunlink_lookup(pag, next_agino); + } + if (!next_ip) { + /* Inode not in memory, reload. */ + error = xfs_iunlink_reload_next(tp, agibp, prev_agino, + next_agino); + if (error) + break; + + next_ip = xfs_iunlink_lookup(pag, next_agino); + } + if (!next_ip) { + /* No incore inode at all? We reloaded it... */ + ASSERT(next_ip != NULL); + error = -EFSCORRUPTED; + break; + } + + prev_agino = next_agino; + next_agino = next_ip->i_next_unlinked; + } + + xfs_trans_brelse(tp, agibp); + /* Should have found this inode somewhere in the iunlinked bucket. */ + if (!error && !foundit) + error = -EFSCORRUPTED; + return error; +} + +/* Decide if this inode is missing its unlinked list and reload it. */ +int +xfs_inode_reload_unlinked( + struct xfs_inode *ip) +{ + struct xfs_trans *tp; + int error; + + error = xfs_trans_alloc_empty(ip->i_mount, &tp); + if (error) + return error; + + xfs_ilock(ip, XFS_ILOCK_SHARED); + if (xfs_inode_unlinked_incomplete(ip)) + error = xfs_inode_reload_unlinked_bucket(tp, ip); + xfs_iunlock(ip, XFS_ILOCK_SHARED); + xfs_trans_cancel(tp); + + return error; +} diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 7547caf2f2ab..0c5bdb91152e 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -68,8 +68,21 @@ typedef struct xfs_inode { uint64_t i_diflags2; /* XFS_DIFLAG2_... */ struct timespec64 i_crtime; /* time created */ - /* unlinked list pointers */ + /* + * Unlinked list pointers. These point to the next and previous inodes + * in the AGI unlinked bucket list, respectively. These fields can + * only be updated with the AGI locked. + * + * i_next_unlinked caches di_next_unlinked. + */ xfs_agino_t i_next_unlinked; + + /* + * If the inode is not on an unlinked list, this field is zero. If the + * inode is the first element in an unlinked list, this field is + * NULLAGINO. Otherwise, i_prev_unlinked points to the previous inode + * in the unlinked list. + */ xfs_agino_t i_prev_unlinked; /* VFS inode */ @@ -81,6 +94,11 @@ typedef struct xfs_inode { struct list_head i_ioend_list; } xfs_inode_t; +static inline bool xfs_inode_on_unlinked_list(const struct xfs_inode *ip) +{ + return ip->i_prev_unlinked != 0; +} + static inline bool xfs_inode_has_attr_fork(struct xfs_inode *ip) { return ip->i_forkoff > 0; @@ -326,6 +344,9 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip) */ #define XFS_INACTIVATING (1 << 13) +/* Quotacheck is running but inode has not been added to quota counts. */ +#define XFS_IQUOTAUNCHECKED (1 << 14) + /* All inode state flags related to inode reclaim. */ #define XFS_ALL_IRECLAIM_FLAGS (XFS_IRECLAIMABLE | \ XFS_IRECLAIM | \ @@ -340,7 +361,7 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip) #define XFS_IRECLAIM_RESET_FLAGS \ (XFS_IRECLAIMABLE | XFS_IRECLAIM | \ XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | XFS_NEED_INACTIVE | \ - XFS_INACTIVATING) + XFS_INACTIVATING | XFS_IQUOTAUNCHECKED) /* * Flags for inode locking. @@ -575,4 +596,13 @@ void xfs_end_io(struct work_struct *work); int xfs_ilock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2); void xfs_iunlock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2); +static inline bool +xfs_inode_unlinked_incomplete( + struct xfs_inode *ip) +{ + return VFS_I(ip)->i_nlink == 0 && !xfs_inode_on_unlinked_list(ip); +} +int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip); +int xfs_inode_reload_unlinked(struct xfs_inode *ip); + #endif /* __XFS_INODE_H__ */ diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 2ededd3f6b8c..1c1e6171209d 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -573,10 +573,10 @@ xfs_vn_getattr( stat->gid = vfsgid_into_kgid(vfsgid); stat->ino = ip->i_ino; stat->atime = inode->i_atime; + stat->mtime = inode->i_mtime; + stat->ctime = inode_get_ctime(inode); stat->blocks = XFS_FSB_TO_BB(mp, ip->i_nblocks + ip->i_delayed_blks); - fill_mg_cmtime(stat, request_mask, inode); - if (xfs_has_v3inodes(mp)) { if (request_mask & STATX_BTIME) { stat->result_mask |= STATX_BTIME; @@ -917,7 +917,7 @@ xfs_setattr_size( if (newsize != oldsize && !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) { iattr->ia_ctime = iattr->ia_mtime = - current_mgtime(inode); + current_time(inode); iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME; } diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index c2093cb56092..ccf0c4ff4490 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -80,6 +80,15 @@ xfs_bulkstat_one_int( if (error) goto out; + if (xfs_inode_unlinked_incomplete(ip)) { + error = xfs_inode_reload_unlinked_bucket(tp, ip); + if (error) { + xfs_iunlock(ip, XFS_ILOCK_SHARED); + xfs_irele(ip); + return error; + } + } + ASSERT(ip != NULL); ASSERT(ip->i_imap.im_blkno != 0); inode = VFS_I(ip); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 79004d193e54..51c100c86177 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -715,15 +715,7 @@ xfs_log_mount( * just worked. */ if (!xfs_has_norecovery(mp)) { - /* - * log recovery ignores readonly state and so we need to clear - * mount-based read only state so it can write to disk. - */ - bool readonly = test_and_clear_bit(XFS_OPSTATE_READONLY, - &mp->m_opstate); error = xlog_recover(log); - if (readonly) - set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); if (error) { xfs_warn(mp, "log mount/recovery failed: error %d", error); @@ -772,7 +764,6 @@ xfs_log_mount_finish( struct xfs_mount *mp) { struct xlog *log = mp->m_log; - bool readonly; int error = 0; if (xfs_has_norecovery(mp)) { @@ -781,12 +772,6 @@ xfs_log_mount_finish( } /* - * log recovery ignores readonly state and so we need to clear - * mount-based read only state so it can write to disk. - */ - readonly = test_and_clear_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); - - /* * During the second phase of log recovery, we need iget and * iput to behave like they do for an active filesystem. * xfs_fs_drop_inode needs to be able to prevent the deletion @@ -835,8 +820,6 @@ xfs_log_mount_finish( xfs_buftarg_drain(mp->m_ddev_targp); clear_bit(XLOG_RECOVERY_NEEDED, &log->l_opstate); - if (readonly) - set_bit(XFS_OPSTATE_READONLY, &mp->m_opstate); /* Make sure the log is dead if we're returning failure. */ ASSERT(!error || xlog_is_shutdown(log)); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index eccbfb99e894..ebc70aaa299c 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -124,7 +124,7 @@ xlog_cil_push_pcp_aggregate( struct xlog_cil_pcp *cilpcp; int cpu; - for_each_online_cpu(cpu) { + for_each_cpu(cpu, &ctx->cil_pcpmask) { cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); ctx->ticket->t_curr_res += cilpcp->space_reserved; @@ -165,7 +165,13 @@ xlog_cil_insert_pcp_aggregate( if (!test_and_clear_bit(XLOG_CIL_PCP_SPACE, &cil->xc_flags)) return; - for_each_online_cpu(cpu) { + /* + * We can race with other cpus setting cil_pcpmask. However, we've + * atomically cleared PCP_SPACE which forces other threads to add to + * the global space used count. cil_pcpmask is a superset of cilpcp + * structures that could have a nonzero space_used. + */ + for_each_cpu(cpu, &ctx->cil_pcpmask) { int old, prev; cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); @@ -554,6 +560,7 @@ xlog_cil_insert_items( int iovhdr_res = 0, split_res = 0, ctx_res = 0; int space_used; int order; + unsigned int cpu_nr; struct xlog_cil_pcp *cilpcp; ASSERT(tp); @@ -577,7 +584,12 @@ xlog_cil_insert_items( * can't be scheduled away between split sample/update operations that * are done without outside locking to serialise them. */ - cilpcp = get_cpu_ptr(cil->xc_pcp); + cpu_nr = get_cpu(); + cilpcp = this_cpu_ptr(cil->xc_pcp); + + /* Tell the future push that there was work added by this CPU. */ + if (!cpumask_test_cpu(cpu_nr, &ctx->cil_pcpmask)) + cpumask_test_and_set_cpu(cpu_nr, &ctx->cil_pcpmask); /* * We need to take the CIL checkpoint unit reservation on the first @@ -663,7 +675,7 @@ xlog_cil_insert_items( continue; list_add_tail(&lip->li_cil, &cilpcp->log_items); } - put_cpu_ptr(cilpcp); + put_cpu(); /* * If we've overrun the reservation, dump the tx details before we move @@ -1791,38 +1803,6 @@ out_shutdown: } /* - * Move dead percpu state to the relevant CIL context structures. - * - * We have to lock the CIL context here to ensure that nothing is modifying - * the percpu state, either addition or removal. Both of these are done under - * the CIL context lock, so grabbing that exclusively here will ensure we can - * safely drain the cilpcp for the CPU that is dying. - */ -void -xlog_cil_pcp_dead( - struct xlog *log, - unsigned int cpu) -{ - struct xfs_cil *cil = log->l_cilp; - struct xlog_cil_pcp *cilpcp = per_cpu_ptr(cil->xc_pcp, cpu); - struct xfs_cil_ctx *ctx; - - down_write(&cil->xc_ctx_lock); - ctx = cil->xc_ctx; - if (ctx->ticket) - ctx->ticket->t_curr_res += cilpcp->space_reserved; - cilpcp->space_reserved = 0; - - if (!list_empty(&cilpcp->log_items)) - list_splice_init(&cilpcp->log_items, &ctx->log_items); - if (!list_empty(&cilpcp->busy_extents)) - list_splice_init(&cilpcp->busy_extents, &ctx->busy_extents); - atomic_add(cilpcp->space_used, &ctx->space_used); - cilpcp->space_used = 0; - up_write(&cil->xc_ctx_lock); -} - -/* * Perform initial CIL structure initialisation. */ int diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 1bd2963e8fbd..af87648331d5 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -231,6 +231,12 @@ struct xfs_cil_ctx { struct work_struct discard_endio_work; struct work_struct push_work; atomic_t order_id; + + /* + * CPUs that could have added items to the percpu CIL data. Access is + * coordinated with xc_ctx_lock. + */ + struct cpumask cil_pcpmask; }; /* @@ -278,9 +284,6 @@ struct xfs_cil { wait_queue_head_t xc_push_wait; /* background push throttle */ void __percpu *xc_pcp; /* percpu CIL structures */ -#ifdef CONFIG_HOTPLUG_CPU - struct list_head xc_pcp_list; -#endif } ____cacheline_aligned_in_smp; /* xc_flags bit values */ @@ -705,9 +708,4 @@ xlog_kvmalloc( return p; } -/* - * CIL CPU dead notifier - */ -void xlog_cil_pcp_dead(struct xlog *log, unsigned int cpu); - #endif /* __XFS_LOG_PRIV_H__ */ diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 82c81d20459d..13b94d2e605b 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -329,7 +329,7 @@ xlog_find_verify_cycle( * try a smaller size. We need to be able to read at least * a log sector, or we're out of luck. */ - bufblks = 1 << ffs(nbblks); + bufblks = roundup_pow_of_two(nbblks); while (bufblks > log->l_logBBsize) bufblks >>= 1; while (!(buffer = xlog_alloc_buffer(log, bufblks))) { @@ -1528,7 +1528,7 @@ xlog_write_log_records( * a smaller size. We need to be able to write at least a * log sector, or we're out of luck. */ - bufblks = 1 << ffs(blocks); + bufblks = roundup_pow_of_two(blocks); while (bufblks > log->l_logBBsize) bufblks >>= 1; while (!(buffer = xlog_alloc_buffer(log, bufblks))) { diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index a25eece3be2b..d19cca099bc3 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -60,6 +60,7 @@ struct xfs_error_cfg { * Per-cpu deferred inode inactivation GC lists. */ struct xfs_inodegc { + struct xfs_mount *mp; struct llist_head list; struct delayed_work work; int error; @@ -67,9 +68,7 @@ struct xfs_inodegc { /* approximate count of inodes in the list */ unsigned int items; unsigned int shrinker_hits; -#if defined(DEBUG) || defined(XFS_WARN) unsigned int cpu; -#endif }; /* @@ -98,7 +97,6 @@ typedef struct xfs_mount { xfs_buftarg_t *m_ddev_targp; /* saves taking the address */ xfs_buftarg_t *m_logdev_targp;/* ptr to log device */ xfs_buftarg_t *m_rtdev_targp; /* ptr to rt device */ - struct list_head m_mount_list; /* global mount list */ void __percpu *m_inodegc; /* percpu inodegc structures */ /* @@ -249,6 +247,9 @@ typedef struct xfs_mount { unsigned int *m_errortag; struct xfs_kobj m_errortag_kobj; #endif + + /* cpus that have inodes queued for inactivation */ + struct cpumask m_inodegc_cpumask; } xfs_mount_t; #define M_IGEO(mp) (&(mp)->m_ino_geo) @@ -404,6 +405,8 @@ __XFS_HAS_FEAT(nouuid, NOUUID) #define XFS_OPSTATE_WARNED_SHRINK 8 /* Kernel has logged a warning about logged xattr updates being used. */ #define XFS_OPSTATE_WARNED_LARP 9 +/* Mount time quotacheck is running */ +#define XFS_OPSTATE_QUOTACHECK_RUNNING 10 #define __XFS_IS_OPSTATE(name, NAME) \ static inline bool xfs_is_ ## name (struct xfs_mount *mp) \ @@ -426,6 +429,11 @@ __XFS_IS_OPSTATE(inode32, INODE32) __XFS_IS_OPSTATE(readonly, READONLY) __XFS_IS_OPSTATE(inodegc_enabled, INODEGC_ENABLED) __XFS_IS_OPSTATE(blockgc_enabled, BLOCKGC_ENABLED) +#ifdef CONFIG_XFS_QUOTA +__XFS_IS_OPSTATE(quotacheck_running, QUOTACHECK_RUNNING) +#else +# define xfs_is_quotacheck_running(mp) (false) +#endif static inline bool xfs_should_warn(struct xfs_mount *mp, long nr) @@ -443,7 +451,8 @@ xfs_should_warn(struct xfs_mount *mp, long nr) { (1UL << XFS_OPSTATE_BLOCKGC_ENABLED), "blockgc" }, \ { (1UL << XFS_OPSTATE_WARNED_SCRUB), "wscrub" }, \ { (1UL << XFS_OPSTATE_WARNED_SHRINK), "wshrink" }, \ - { (1UL << XFS_OPSTATE_WARNED_LARP), "wlarp" } + { (1UL << XFS_OPSTATE_WARNED_LARP), "wlarp" }, \ + { (1UL << XFS_OPSTATE_QUOTACHECK_RUNNING), "quotacheck" } /* * Max and min values for mount-option defined I/O diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 6abcc34fafd8..7256090c3895 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -1160,6 +1160,10 @@ xfs_qm_dqusage_adjust( if (error) return error; + error = xfs_inode_reload_unlinked(ip); + if (error) + goto error0; + ASSERT(ip->i_delayed_blks == 0); if (XFS_IS_REALTIME_INODE(ip)) { @@ -1173,6 +1177,7 @@ xfs_qm_dqusage_adjust( } nblks = (xfs_qcnt_t)ip->i_nblocks - rtblks; + xfs_iflags_clear(ip, XFS_IQUOTAUNCHECKED); /* * Add the (disk blocks and inode) resources occupied by this @@ -1319,8 +1324,10 @@ xfs_qm_quotacheck( flags |= XFS_PQUOTA_CHKD; } + xfs_set_quotacheck_running(mp); error = xfs_iwalk_threaded(mp, 0, 0, xfs_qm_dqusage_adjust, 0, true, NULL); + xfs_clear_quotacheck_running(mp); /* * On error, the inode walk may have partially populated the dquot diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index edd8587658d5..2d4444d61e98 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -477,6 +477,7 @@ xfs_cui_item_recover( struct xfs_log_item *lip, struct list_head *capture_list) { + struct xfs_trans_res resv; struct xfs_cui_log_item *cuip = CUI_ITEM(lip); struct xfs_cud_log_item *cudp; struct xfs_trans *tp; @@ -514,8 +515,9 @@ xfs_cui_item_recover( * doesn't fit. We need to reserve enough blocks to handle a * full btree split on either end of the refcount range. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, - mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp); + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, mp->m_refc_maxlevels * 2, 0, + XFS_TRANS_RESERVE, &tp); if (error) return error; diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 520c7ebdfed8..0e0e747028da 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -507,6 +507,7 @@ xfs_rui_item_recover( struct xfs_log_item *lip, struct list_head *capture_list) { + struct xfs_trans_res resv; struct xfs_rui_log_item *ruip = RUI_ITEM(lip); struct xfs_rud_log_item *rudp; struct xfs_trans *tp; @@ -530,8 +531,9 @@ xfs_rui_item_recover( } } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, - mp->m_rmap_maxlevels, 0, XFS_TRANS_RESERVE, &tp); + resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate); + error = xfs_trans_alloc(mp, &resv, mp->m_rmap_maxlevels, 0, + XFS_TRANS_RESERVE, &tp); if (error) return error; rudp = xfs_trans_get_rud(tp, ruip); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 1f77014c6e1a..819a3568b28f 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -56,28 +56,6 @@ static struct kset *xfs_kset; /* top-level xfs sysfs dir */ static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */ #endif -#ifdef CONFIG_HOTPLUG_CPU -static LIST_HEAD(xfs_mount_list); -static DEFINE_SPINLOCK(xfs_mount_list_lock); - -static inline void xfs_mount_list_add(struct xfs_mount *mp) -{ - spin_lock(&xfs_mount_list_lock); - list_add(&mp->m_mount_list, &xfs_mount_list); - spin_unlock(&xfs_mount_list_lock); -} - -static inline void xfs_mount_list_del(struct xfs_mount *mp) -{ - spin_lock(&xfs_mount_list_lock); - list_del(&mp->m_mount_list); - spin_unlock(&xfs_mount_list_lock); -} -#else /* !CONFIG_HOTPLUG_CPU */ -static inline void xfs_mount_list_add(struct xfs_mount *mp) {} -static inline void xfs_mount_list_del(struct xfs_mount *mp) {} -#endif - enum xfs_dax_mode { XFS_DAX_INODE = 0, XFS_DAX_ALWAYS = 1, @@ -1135,9 +1113,8 @@ xfs_inodegc_init_percpu( for_each_possible_cpu(cpu) { gc = per_cpu_ptr(mp->m_inodegc, cpu); -#if defined(DEBUG) || defined(XFS_WARN) gc->cpu = cpu; -#endif + gc->mp = mp; init_llist_head(&gc->list); gc->items = 0; gc->error = 0; @@ -1168,7 +1145,6 @@ xfs_fs_put_super( xfs_freesb(mp); xchk_mount_stats_free(mp); free_percpu(mp->m_stats.xs_stats); - xfs_mount_list_del(mp); xfs_inodegc_free_percpu(mp); xfs_destroy_percpu_counters(mp); xfs_destroy_mount_workqueues(mp); @@ -1577,13 +1553,6 @@ xfs_fs_fill_super( if (error) goto out_destroy_counters; - /* - * All percpu data structures requiring cleanup when a cpu goes offline - * must be allocated before adding this @mp to the cpu-dead handler's - * mount list. - */ - xfs_mount_list_add(mp); - /* Allocate stats memory before we do operations that might use it */ mp->m_stats.xs_stats = alloc_percpu(struct xfsstats); if (!mp->m_stats.xs_stats) { @@ -1781,7 +1750,6 @@ xfs_fs_fill_super( out_free_stats: free_percpu(mp->m_stats.xs_stats); out_destroy_inodegc: - xfs_mount_list_del(mp); xfs_inodegc_free_percpu(mp); out_destroy_counters: xfs_destroy_percpu_counters(mp); @@ -2065,7 +2033,7 @@ static struct file_system_type xfs_fs_type = { .init_fs_context = xfs_init_fs_context, .parameters = xfs_fs_parameters, .kill_sb = xfs_kill_sb, - .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("xfs"); @@ -2326,49 +2294,6 @@ xfs_destroy_workqueues(void) destroy_workqueue(xfs_alloc_wq); } -#ifdef CONFIG_HOTPLUG_CPU -static int -xfs_cpu_dead( - unsigned int cpu) -{ - struct xfs_mount *mp, *n; - - spin_lock(&xfs_mount_list_lock); - list_for_each_entry_safe(mp, n, &xfs_mount_list, m_mount_list) { - spin_unlock(&xfs_mount_list_lock); - xfs_inodegc_cpu_dead(mp, cpu); - xlog_cil_pcp_dead(mp->m_log, cpu); - spin_lock(&xfs_mount_list_lock); - } - spin_unlock(&xfs_mount_list_lock); - return 0; -} - -static int __init -xfs_cpu_hotplug_init(void) -{ - int error; - - error = cpuhp_setup_state_nocalls(CPUHP_XFS_DEAD, "xfs:dead", NULL, - xfs_cpu_dead); - if (error < 0) - xfs_alert(NULL, -"Failed to initialise CPU hotplug, error %d. XFS is non-functional.", - error); - return error; -} - -static void -xfs_cpu_hotplug_destroy(void) -{ - cpuhp_remove_state_nocalls(CPUHP_XFS_DEAD); -} - -#else /* !CONFIG_HOTPLUG_CPU */ -static inline int xfs_cpu_hotplug_init(void) { return 0; } -static inline void xfs_cpu_hotplug_destroy(void) {} -#endif - STATIC int __init init_xfs_fs(void) { @@ -2385,13 +2310,9 @@ init_xfs_fs(void) xfs_dir_startup(); - error = xfs_cpu_hotplug_init(); - if (error) - goto out; - error = xfs_init_caches(); if (error) - goto out_destroy_hp; + goto out; error = xfs_init_workqueues(); if (error) @@ -2475,8 +2396,6 @@ init_xfs_fs(void) xfs_destroy_workqueues(); out_destroy_caches: xfs_destroy_caches(); - out_destroy_hp: - xfs_cpu_hotplug_destroy(); out: return error; } @@ -2500,7 +2419,6 @@ exit_xfs_fs(void) xfs_destroy_workqueues(); xfs_destroy_caches(); xfs_uuid_table_free(); - xfs_cpu_hotplug_destroy(); } module_init(init_xfs_fs); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 902c7f67a117..3926cf7f2a6e 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3824,6 +3824,51 @@ TRACE_EVENT(xfs_iunlink_update_dinode, __entry->new_ptr) ); +TRACE_EVENT(xfs_iunlink_reload_next, + TP_PROTO(struct xfs_inode *ip), + TP_ARGS(ip), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_agnumber_t, agno) + __field(xfs_agino_t, agino) + __field(xfs_agino_t, prev_agino) + __field(xfs_agino_t, next_agino) + ), + TP_fast_assign( + __entry->dev = ip->i_mount->m_super->s_dev; + __entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino); + __entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino); + __entry->prev_agino = ip->i_prev_unlinked; + __entry->next_agino = ip->i_next_unlinked; + ), + TP_printk("dev %d:%d agno 0x%x agino 0x%x prev_unlinked 0x%x next_unlinked 0x%x", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->agno, + __entry->agino, + __entry->prev_agino, + __entry->next_agino) +); + +TRACE_EVENT(xfs_inode_reload_unlinked_bucket, + TP_PROTO(struct xfs_inode *ip), + TP_ARGS(ip), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_agnumber_t, agno) + __field(xfs_agino_t, agino) + ), + TP_fast_assign( + __entry->dev = ip->i_mount->m_super->s_dev; + __entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino); + __entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino); + ), + TP_printk("dev %d:%d agno 0x%x agino 0x%x bucket %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->agno, + __entry->agino, + __entry->agino % XFS_AGI_UNLINKED_BUCKETS) +); + DECLARE_EVENT_CLASS(xfs_ag_inode_class, TP_PROTO(struct xfs_inode *ip), TP_ARGS(ip), diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index 43e5c219aaed..a3975f325f4e 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -46,6 +46,17 @@ xfs_attr_grab_log_assist( if (xfs_sb_version_haslogxattrs(&mp->m_sb)) return 0; + /* + * Check if the filesystem featureset is new enough to set this log + * incompat feature bit. Strictly speaking, the minimum requirement is + * a V5 filesystem for the superblock field, but we'll require rmap + * or reflink to avoid having to deal with really old kernels. + */ + if (!xfs_has_reflink(mp) && !xfs_has_rmapbt(mp)) { + error = -EOPNOTSUPP; + goto drop_incompat; + } + /* Enable log-assisted xattrs. */ error = xfs_add_incompat_log_feature(mp, XFS_SB_FEAT_INCOMPAT_LOG_XATTRS); diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index bb3cb005873e..8adf09dbc473 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -94,7 +94,7 @@ struct arch_timer_cpu { int __init kvm_timer_hyp_init(bool has_gic); int kvm_timer_enable(struct kvm_vcpu *vcpu); -int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu); +void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu); void kvm_timer_sync_user(struct kvm_vcpu *vcpu); bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu); diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 31029f4f7be8..4df71290b676 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -77,7 +77,7 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu); void kvm_vcpu_pmu_resync_el0(void); #define kvm_vcpu_has_pmu(vcpu) \ - (test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features)) + (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PMU_V3)) /* * Updates the vcpu's view of the pmu events for this cpu. @@ -101,6 +101,7 @@ void kvm_vcpu_pmu_resync_el0(void); }) u8 kvm_arm_pmu_get_pmuver_limit(void); +u64 kvm_pmu_evtyper_mask(struct kvm *kvm); #else struct kvm_pmu { @@ -172,6 +173,10 @@ static inline u8 kvm_arm_pmu_get_pmuver_limit(void) { return 0; } +static inline u64 kvm_pmu_evtyper_mask(struct kvm *kvm) +{ + return 0; +} static inline void kvm_vcpu_pmu_resync_el0(void) {} #endif diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h index 6e55b9283789..e8fb624013d1 100644 --- a/include/kvm/arm_psci.h +++ b/include/kvm/arm_psci.h @@ -26,7 +26,7 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu) * revisions. It is thus safe to return the latest, unless * userspace has instructed us otherwise. */ - if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) { + if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2)) { if (vcpu->kvm->arch.psci_version) return vcpu->kvm->arch.psci_version; diff --git a/include/linux/aer.h b/include/linux/aer.h index 2dd175f5debd..29cc10220952 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -42,11 +42,13 @@ struct aer_capability_regs { #if defined(CONFIG_PCIEAER) int pci_aer_clear_nonfatal_status(struct pci_dev *dev); +int pcie_aer_is_native(struct pci_dev *dev); #else static inline int pci_aer_clear_nonfatal_status(struct pci_dev *dev) { return -EINVAL; } +static inline int pcie_aer_is_native(struct pci_dev *dev) { return 0; } #endif void cper_print_aer(struct pci_dev *dev, int aer_severity, diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 7c67c17321d4..083f85653716 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -67,6 +67,8 @@ #define ARM_SMCCC_VERSION_1_3 0x10003 #define ARM_SMCCC_1_3_SVE_HINT 0x10000 +#define ARM_SMCCC_CALL_HINTS ARM_SMCCC_1_3_SVE_HINT + #define ARM_SMCCC_VERSION_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 18f5744dfb5d..b83ef19da13d 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -459,8 +459,6 @@ raw_atomic_read_acquire(const atomic_t *v) { #if defined(arch_atomic_read_acquire) return arch_atomic_read_acquire(v); -#elif defined(arch_atomic_read) - return arch_atomic_read(v); #else int ret; @@ -508,8 +506,6 @@ raw_atomic_set_release(atomic_t *v, int i) { #if defined(arch_atomic_set_release) arch_atomic_set_release(v, i); -#elif defined(arch_atomic_set) - arch_atomic_set(v, i); #else if (__native_word(atomic_t)) { smp_store_release(&(v)->counter, i); @@ -2575,8 +2571,6 @@ raw_atomic64_read_acquire(const atomic64_t *v) { #if defined(arch_atomic64_read_acquire) return arch_atomic64_read_acquire(v); -#elif defined(arch_atomic64_read) - return arch_atomic64_read(v); #else s64 ret; @@ -2624,8 +2618,6 @@ raw_atomic64_set_release(atomic64_t *v, s64 i) { #if defined(arch_atomic64_set_release) arch_atomic64_set_release(v, i); -#elif defined(arch_atomic64_set) - arch_atomic64_set(v, i); #else if (__native_word(atomic64_t)) { smp_store_release(&(v)->counter, i); @@ -4657,4 +4649,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 202b45c7db600ce36198eb1f1fc2c2d5268ace2d +// 2fdd6702823fa842f9cea57a002e6e4476ae780c diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index a3462a9b8e18..a9cb10b0e2e9 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -49,7 +49,7 @@ word \ ____BTF_ID(symbol, word) #define __ID(prefix) \ - __PASTE(prefix, __COUNTER__) + __PASTE(__PASTE(prefix, __COUNTER__), __LINE__) /* * The BTF_ID defines unique symbol for each ID pointing diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 06dda85f0424..068f7738be22 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -90,7 +90,6 @@ enum cpuhp_state { CPUHP_FS_BUFF_DEAD, CPUHP_PRINTK_DEAD, CPUHP_MM_MEMCQ_DEAD, - CPUHP_XFS_DEAD, CPUHP_PERCPU_CNT_DEAD, CPUHP_RADIX_DEAD, CPUHP_PAGE_ALLOC, diff --git a/include/linux/fs.h b/include/linux/fs.h index 4aeb3fa11927..b528f063e8ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1508,47 +1508,18 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb, kgid_has_mapping(fs_userns, kgid); } -struct timespec64 current_mgtime(struct inode *inode); struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); -/* - * Multigrain timestamps - * - * Conditionally use fine-grained ctime and mtime timestamps when there - * are users actively observing them via getattr. The primary use-case - * for this is NFS clients that use the ctime to distinguish between - * different states of the file, and that are often fooled by multiple - * operations that occur in the same coarse-grained timer tick. - * - * The kernel always keeps normalized struct timespec64 values in the ctime, - * which means that only the first 30 bits of the value are used. Use the - * 31st bit of the ctime's tv_nsec field as a flag to indicate that the value - * has been queried since it was last updated. - */ -#define I_CTIME_QUERIED (1L<<30) - /** * inode_get_ctime - fetch the current ctime from the inode * @inode: inode from which to fetch ctime * - * Grab the current ctime tv_nsec field from the inode, mask off the - * I_CTIME_QUERIED flag and return it. This is mostly intended for use by - * internal consumers of the ctime that aren't concerned with ensuring a - * fine-grained update on the next change (e.g. when preparing to store - * the value in the backing store for later retrieval). - * - * This is safe to call regardless of whether the underlying filesystem - * is using multigrain timestamps. + * Grab the current ctime from the inode and return it. */ static inline struct timespec64 inode_get_ctime(const struct inode *inode) { - struct timespec64 ctime; - - ctime.tv_sec = inode->__i_ctime.tv_sec; - ctime.tv_nsec = inode->__i_ctime.tv_nsec & ~I_CTIME_QUERIED; - - return ctime; + return inode->__i_ctime; } /** @@ -2334,7 +2305,6 @@ struct file_system_type { #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ -#define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; @@ -2358,17 +2328,6 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) -/** - * is_mgtime: is this inode using multigrain timestamps - * @inode: inode to test for multigrain timestamps - * - * Return true if the inode uses multigrain timestamps, false otherwise. - */ -static inline bool is_mgtime(const struct inode *inode) -{ - return inode->i_sb->s_type->fs_flags & FS_MGTIME; -} - extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -3054,7 +3013,6 @@ extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); -void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 1b9b15a492fa..cdc684e04a2f 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -189,6 +189,8 @@ struct team { struct net_device *dev; /* associated netdevice */ struct team_pcpu_stats __percpu *pcpu_stats; + const struct header_ops *header_ops_cache; + struct mutex lock; /* used for overall locking, e.g. port lists write */ /* diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 3df5499f7936..842623d708c2 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -54,7 +54,7 @@ extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D]; int kasan_populate_early_shadow(const void *shadow_start, const void *shadow_end); -#ifndef __HAVE_ARCH_SHADOW_MAP +#ifndef kasan_mem_to_shadow static inline void *kasan_mem_to_shadow(const void *addr) { return (void *)((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ab94ad4597d0..e4e24da16d2c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -920,7 +920,7 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } -void mem_cgroup_handle_over_high(void); +void mem_cgroup_handle_over_high(gfp_t gfp_mask); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); @@ -1458,7 +1458,7 @@ static inline void mem_cgroup_unlock_pages(void) rcu_read_unlock(); } -static inline void mem_cgroup_handle_over_high(void) +static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 20eeba8b009d..cd628c4b011e 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -48,6 +48,7 @@ struct nfs_client { #define NFS_CS_NOPING 6 /* - don't ping on connect */ #define NFS_CS_DS 7 /* - Server is a DS */ #define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */ +#define NFS_CS_PNFS 9 /* - Server used for pnfs */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index aa9f4c6ebe26..1c315f854ea8 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -157,7 +157,9 @@ extern void nfs_unlock_request(struct nfs_page *req); extern void nfs_unlock_and_release_request(struct nfs_page *); extern struct nfs_page *nfs_page_group_lock_head(struct nfs_page *req); extern int nfs_page_group_lock_subrequests(struct nfs_page *head); -extern void nfs_join_page_group(struct nfs_page *head, struct inode *inode); +extern void nfs_join_page_group(struct nfs_page *head, + struct nfs_commit_info *cinfo, + struct inode *inode); extern int nfs_page_group_lock(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h index e3899bd77f5c..9c226adf938a 100644 --- a/include/linux/perf/arm_pmuv3.h +++ b/include/linux/perf/arm_pmuv3.h @@ -234,9 +234,12 @@ /* * Event filters for PMUv3 */ -#define ARMV8_PMU_EXCLUDE_EL1 (1U << 31) -#define ARMV8_PMU_EXCLUDE_EL0 (1U << 30) -#define ARMV8_PMU_INCLUDE_EL2 (1U << 27) +#define ARMV8_PMU_EXCLUDE_EL1 (1U << 31) +#define ARMV8_PMU_EXCLUDE_EL0 (1U << 30) +#define ARMV8_PMU_EXCLUDE_NS_EL1 (1U << 29) +#define ARMV8_PMU_EXCLUDE_NS_EL0 (1U << 28) +#define ARMV8_PMU_INCLUDE_EL2 (1U << 27) +#define ARMV8_PMU_EXCLUDE_EL3 (1U << 26) /* * PMUSERENR: user enable reg diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h index 285189454449..f8f3e958e9cf 100644 --- a/include/linux/resume_user_mode.h +++ b/include/linux/resume_user_mode.h @@ -55,7 +55,7 @@ static inline void resume_user_mode_work(struct pt_regs *regs) } #endif - mem_cgroup_handle_over_high(); + mem_cgroup_handle_over_high(GFP_KERNEL); blkcg_maybe_throttle_current(); rseq_handle_notify_resume(NULL, regs); diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 987a59d977c5..e9bd2f65d7f4 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -512,8 +512,8 @@ do { \ static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) { - do_raw_write_seqcount_begin(s); seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); + do_raw_write_seqcount_begin(s); } /** diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 5b4fb3c791bc..2f8dc47f1eb0 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -779,7 +779,9 @@ xdr_stream_decode_uint32_array(struct xdr_stream *xdr, if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return -EBADMSG; - p = xdr_inline_decode(xdr, size_mul(len, sizeof(*p))); + if (U32_MAX >= SIZE_MAX / sizeof(*p) && len > SIZE_MAX / sizeof(*p)) + return -EBADMSG; + p = xdr_inline_decode(xdr, len * sizeof(*p)); if (unlikely(!p)) return -EBADMSG; if (array == NULL) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index dd40c75011d2..7c816359d5a9 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1682,7 +1682,7 @@ struct nft_trans_gc { struct net *net; struct nft_set *set; u32 seq; - u8 count; + u16 count; void *priv[NFT_TRANS_GC_BATCHCOUNT]; struct rcu_head rcu; }; @@ -1700,8 +1700,9 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans); void nft_trans_gc_elem_add(struct nft_trans_gc *gc, void *priv); -struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, - unsigned int gc_seq); +struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, + unsigned int gc_seq); +struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc); void nft_setelem_data_deactivate(const struct net *net, const struct nft_set *set, diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h index 44a3f565264d..0577f0cdd231 100644 --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -6,26 +6,26 @@ #define _TRACE_XEN_H #include <linux/tracepoint.h> -#include <asm/paravirt_types.h> +#include <asm/xen/hypervisor.h> #include <asm/xen/trace_types.h> struct multicall_entry; /* Multicalls */ DECLARE_EVENT_CLASS(xen_mc__batch, - TP_PROTO(enum paravirt_lazy_mode mode), + TP_PROTO(enum xen_lazy_mode mode), TP_ARGS(mode), TP_STRUCT__entry( - __field(enum paravirt_lazy_mode, mode) + __field(enum xen_lazy_mode, mode) ), TP_fast_assign(__entry->mode = mode), TP_printk("start batch LAZY_%s", - (__entry->mode == PARAVIRT_LAZY_MMU) ? "MMU" : - (__entry->mode == PARAVIRT_LAZY_CPU) ? "CPU" : "NONE") + (__entry->mode == XEN_LAZY_MMU) ? "MMU" : + (__entry->mode == XEN_LAZY_CPU) ? "CPU" : "NONE") ); #define DEFINE_XEN_MC_BATCH(name) \ DEFINE_EVENT(xen_mc__batch, name, \ - TP_PROTO(enum paravirt_lazy_mode mode), \ + TP_PROTO(enum xen_lazy_mode mode), \ TP_ARGS(mode)) DEFINE_XEN_MC_BATCH(xen_mc_batch); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8790b3962e4b..0448700890f7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1962,7 +1962,9 @@ union bpf_attr { * performed again, if the helper is used in combination with * direct packet access. * Return - * 0 on success, or a negative error in case of failure. + * 0 on success, or a negative error in case of failure. Positive + * error indicates a potential drop or congestion in the target + * device. The particular positive error codes are not defined. * * u64 bpf_get_current_pid_tgid(void) * Description diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 7c3fc3980881..5c6c4269f7ef 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -29,6 +29,11 @@ struct TAG { MEMBERS } ATTRS NAME; \ } +#ifdef __cplusplus +/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */ +#define __DECLARE_FLEX_ARRAY(T, member) \ + T member[0] +#else /** * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union * @@ -49,3 +54,5 @@ #ifndef __counted_by #define __counted_by(m) #endif + +#endif /* _UAPI_LINUX_STDDEF_H */ diff --git a/include/xen/arm/hypervisor.h b/include/xen/arm/hypervisor.h index 43ef24dd030e..9995695204f5 100644 --- a/include/xen/arm/hypervisor.h +++ b/include/xen/arm/hypervisor.h @@ -7,18 +7,6 @@ extern struct shared_info *HYPERVISOR_shared_info; extern struct start_info *xen_start_info; -/* Lazy mode for batching updates / context switch */ -enum paravirt_lazy_mode { - PARAVIRT_LAZY_NONE, - PARAVIRT_LAZY_MMU, - PARAVIRT_LAZY_CPU, -}; - -static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void) -{ - return PARAVIRT_LAZY_NONE; -} - #ifdef CONFIG_XEN void __init xen_early_init(void); #else diff --git a/include/xen/events.h b/include/xen/events.h index 95d5e28de324..23932b0673dc 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -105,8 +105,7 @@ int irq_from_virq(unsigned int cpu, unsigned int virq); evtchn_port_t evtchn_from_irq(unsigned irq); int xen_set_callback_via(uint64_t via); -void xen_evtchn_do_upcall(struct pt_regs *regs); -int xen_hvm_evtchn_do_upcall(void); +int xen_evtchn_do_upcall(void); /* Bind a pirq for a physical interrupt to an irq. */ int xen_bind_pirq_gsi_to_irq(unsigned gsi, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 1095bbe29859..8090d7fb11ef 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -8501,7 +8501,7 @@ bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, tname = btf_name_by_offset(btf, walk_type->name_off); ret = snprintf(safe_tname, sizeof(safe_tname), "%s%s", tname, suffix); - if (ret < 0) + if (ret >= sizeof(safe_tname)) return false; safe_id = btf_find_by_name_kind(btf, safe_tname, BTF_INFO_KIND(walk_type->info)); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 5b2741aa0d9b..03b3d4492980 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -785,7 +785,8 @@ found: * to descendants * @cgrp: The cgroup which descendants to traverse * @link: A link for which to replace BPF program - * @type: Type of attach operation + * @new_prog: &struct bpf_prog for the target BPF program with its refcnt + * incremented * * Must be called with cgroup_mutex held. */ @@ -1334,7 +1335,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering * @sk: The socket sending or receiving traffic * @skb: The skb that is being sent or received - * @type: The type of program to be executed + * @atype: The type of program to be executed * * If no socket is passed, or the socket is not of type INET or INET6, * this function does nothing and returns 0. @@ -1424,7 +1425,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); /** * __cgroup_bpf_run_filter_sk() - Run a program on a sock * @sk: sock structure to manipulate - * @type: The type of program to be executed + * @atype: The type of program to be executed * * socket is passed is expected to be of type INET or INET6. * @@ -1449,7 +1450,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * provided by user sockaddr * @sk: sock struct that will use sockaddr * @uaddr: sockaddr struct provided by user - * @type: The type of program to be executed + * @atype: The type of program to be executed * @t_ctx: Pointer to attach type specific context * @flags: Pointer to u32 which contains higher bits of BPF program * return value (OR'ed together). @@ -1496,7 +1497,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains * sk with connection information (IP addresses, etc.) May not contain * cgroup info if it is a req sock. - * @type: The type of program to be executed + * @atype: The type of program to be executed * * socket passed is expected to be of type INET or INET6. * @@ -1670,7 +1671,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = { * @ppos: value-result argument: value is position at which read from or write * to sysctl is happening, result is new position if program overrode it, * initial value otherwise - * @type: type of program to be executed + * @atype: type of program to be executed * * Program is run when sysctl is being accessed, either read or written, and * can allow or deny such access. diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index 9c49ae53deaf..cf1941516643 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -459,8 +459,7 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c) * Typical case will be between 11K and 116K closer to 11K. * bpf progs can and should share bpf_mem_cache when possible. */ - -static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) +static void init_refill_work(struct bpf_mem_cache *c) { init_irq_work(&c->refill_work, bpf_mem_refill); if (c->unit_size <= 256) { @@ -476,7 +475,10 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) c->high_watermark = max(96 * 256 / c->unit_size, 3); } c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1); +} +static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) +{ /* To avoid consuming memory assume that 1st run of bpf * prog won't be doing more than 4 map_update_elem from * irq disabled region @@ -484,6 +486,31 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false); } +static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx) +{ + struct llist_node *first; + unsigned int obj_size; + + /* For per-cpu allocator, the size of free objects in free list doesn't + * match with unit_size and now there is no way to get the size of + * per-cpu pointer saved in free object, so just skip the checking. + */ + if (c->percpu_size) + return 0; + + first = c->free_llist.first; + if (!first) + return 0; + + obj_size = ksize(first); + if (obj_size != c->unit_size) { + WARN_ONCE(1, "bpf_mem_cache[%u]: unexpected object size %u, expect %u\n", + idx, obj_size, c->unit_size); + return -EINVAL; + } + return 0; +} + /* When size != 0 bpf_mem_cache for each cpu. * This is typical bpf hash map use case when all elements have equal size. * @@ -494,10 +521,10 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) { static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096}; + int cpu, i, err, unit_size, percpu_size = 0; struct bpf_mem_caches *cc, __percpu *pcc; struct bpf_mem_cache *c, __percpu *pc; struct obj_cgroup *objcg = NULL; - int cpu, i, unit_size, percpu_size = 0; if (size) { pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL); @@ -521,6 +548,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; + init_refill_work(c); prefill_mem_cache(c, cpu); } ma->cache = pc; @@ -534,6 +562,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL); if (!pcc) return -ENOMEM; + err = 0; #ifdef CONFIG_MEMCG_KMEM objcg = get_obj_cgroup_from_current(); #endif @@ -544,11 +573,30 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) c->unit_size = sizes[i]; c->objcg = objcg; c->tgt = c; + + init_refill_work(c); + /* Another bpf_mem_cache will be used when allocating + * c->unit_size in bpf_mem_alloc(), so doesn't prefill + * for the bpf_mem_cache because these free objects will + * never be used. + */ + if (i != bpf_mem_cache_idx(c->unit_size)) + continue; prefill_mem_cache(c, cpu); + err = check_obj_size(c, i); + if (err) + goto out; } } + +out: ma->caches = pcc; - return 0; + /* refill_work is either zeroed or initialized, so it is safe to + * call irq_work_sync(). + */ + if (err) + bpf_mem_alloc_destroy(ma); + return err; } static void drain_mem_cache(struct bpf_mem_cache *c) @@ -916,3 +964,41 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) return !ret ? NULL : ret + LLIST_NODE_SZ; } + +/* Most of the logic is taken from setup_kmalloc_cache_index_table() */ +static __init int bpf_mem_cache_adjust_size(void) +{ + unsigned int size, index; + + /* Normally KMALLOC_MIN_SIZE is 8-bytes, but it can be + * up-to 256-bytes. + */ + size = KMALLOC_MIN_SIZE; + if (size <= 192) + index = size_index[(size - 1) / 8]; + else + index = fls(size - 1) - 1; + for (size = 8; size < KMALLOC_MIN_SIZE && size <= 192; size += 8) + size_index[(size - 1) / 8] = index; + + /* The minimal alignment is 64-bytes, so disable 96-bytes cache and + * use 128-bytes cache instead. + */ + if (KMALLOC_MIN_SIZE >= 64) { + index = size_index[(128 - 1) / 8]; + for (size = 64 + 8; size <= 96; size += 8) + size_index[(size - 1) / 8] = index; + } + + /* The minimal alignment is 128-bytes, so disable 192-bytes cache and + * use 256-bytes cache instead. + */ + if (KMALLOC_MIN_SIZE >= 128) { + index = fls(256 - 1) - 1; + for (size = 128 + 8; size <= 192; size += 8) + size_index[(size - 1) / 8] = index; + } + + return 0; +} +subsys_initcall(bpf_mem_cache_adjust_size); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 3e4f2ec1af06..87d6693d8233 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -199,12 +199,14 @@ static int __bpf_prog_dev_bound_init(struct bpf_prog *prog, struct net_device *n offload->netdev = netdev; ondev = bpf_offload_find_netdev(offload->netdev); + /* When program is offloaded require presence of "true" + * bpf_offload_netdev, avoid the one created for !ondev case below. + */ + if (bpf_prog_is_offloaded(prog->aux) && (!ondev || !ondev->offdev)) { + err = -EINVAL; + goto err_free; + } if (!ondev) { - if (bpf_prog_is_offloaded(prog->aux)) { - err = -EINVAL; - goto err_free; - } - /* When only binding to the device, explicitly * create an entry in the hashtable. */ diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 8d2ddcb7566b..d869f51ea93a 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -98,7 +98,12 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete) int err = 0; void *ptr; - raw_spin_lock_irqsave(&qs->lock, flags); + if (in_nmi()) { + if (!raw_spin_trylock_irqsave(&qs->lock, flags)) + return -EBUSY; + } else { + raw_spin_lock_irqsave(&qs->lock, flags); + } if (queue_stack_map_is_empty(qs)) { memset(value, 0, qs->map.value_size); @@ -128,7 +133,12 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete) void *ptr; u32 index; - raw_spin_lock_irqsave(&qs->lock, flags); + if (in_nmi()) { + if (!raw_spin_trylock_irqsave(&qs->lock, flags)) + return -EBUSY; + } else { + raw_spin_lock_irqsave(&qs->lock, flags); + } if (queue_stack_map_is_empty(qs)) { memset(value, 0, qs->map.value_size); @@ -193,7 +203,12 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value, if (flags & BPF_NOEXIST || flags > BPF_EXIST) return -EINVAL; - raw_spin_lock_irqsave(&qs->lock, irq_flags); + if (in_nmi()) { + if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags)) + return -EBUSY; + } else { + raw_spin_lock_irqsave(&qs->lock, irq_flags); + } if (queue_stack_map_is_full(qs)) { if (!replace) { diff --git a/kernel/pid.c b/kernel/pid.c index fee14a4486a3..6500ef956f2f 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -609,7 +609,7 @@ int pidfd_create(struct pid *pid, unsigned int flags) } /** - * pidfd_open() - Open new pid file descriptor. + * sys_pidfd_open() - Open new pid file descriptor. * * @pid: pid for which to retrieve a pidfd * @flags: flags to pass diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2299a5cfbfb9..802551e0009b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9269,7 +9269,7 @@ void __init init_idle(struct task_struct *idle, int cpu) * PF_KTHREAD should already be set at this point; regardless, make it * look like a proper per-CPU kthread. */ - idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY; + idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY; kthread_set_per_cpu(idle, cpu); #ifdef CONFIG_SMP diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 342f58a329f5..5007b25c5bc6 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -373,6 +373,7 @@ EXPORT_SYMBOL_GPL(play_idle_precise); void cpu_startup_entry(enum cpuhp_state state) { + current->flags |= PF_IDLE; arch_cpu_idle_prepare(); cpuhp_online_idle(state); while (1) diff --git a/kernel/task_work.c b/kernel/task_work.c index 065e1ef8fc8d..95a7e1b7f1da 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -78,6 +78,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work, * task_work_cancel_match - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @match: match function to call + * @data: data to be passed in to match function * * RETURNS: * The found work or NULL if not found. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index a7264b2c17ad..868008f56fec 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2853,6 +2853,17 @@ static int get_modules_for_addrs(struct module ***mods, unsigned long *addrs, u3 return arr.mods_cnt; } +static int addrs_check_error_injection_list(unsigned long *addrs, u32 cnt) +{ + u32 i; + + for (i = 0; i < cnt; i++) { + if (!within_error_injection_list(addrs[i])) + return -EINVAL; + } + return 0; +} + int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_kprobe_multi_link *link = NULL; @@ -2930,6 +2941,11 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error; } + if (prog->kprobe_override && addrs_check_error_injection_list(addrs, cnt)) { + err = -EINVAL; + goto error; + } + link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { err = -ENOMEM; @@ -3207,8 +3223,10 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr rcu_read_lock(); task = get_pid_task(find_vpid(pid), PIDTYPE_PID); rcu_read_unlock(); - if (!task) + if (!task) { + err = -ESRCH; goto error_path_put; + } } err = -ENOMEM; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index a1651edc48d5..28daf0ce95c5 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -354,6 +354,11 @@ static void rb_init_page(struct buffer_data_page *bpage) local_set(&bpage->commit, 0); } +static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage) +{ + return local_read(&bpage->page->commit); +} + static void free_buffer_page(struct buffer_page *bpage) { free_page((unsigned long)bpage->page); @@ -2003,7 +2008,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) * Increment overrun to account for the lost events. */ local_add(page_entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(to_remove_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); } @@ -2367,11 +2372,6 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read); } -static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) -{ - return local_read(&bpage->page->commit); -} - static struct ring_buffer_event * rb_iter_head_event(struct ring_buffer_iter *iter) { @@ -2517,7 +2517,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer, * the counters. */ local_add(entries, &cpu_buffer->overrun); - local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); + local_sub(rb_page_commit(next_page), &cpu_buffer->entries_bytes); local_inc(&cpu_buffer->pages_lost); /* @@ -2660,9 +2660,6 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, event = __rb_page_index(tail_page, tail); - /* account for padding bytes */ - local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); - /* * Save the original length to the meta data. * This will be used by the reader to add lost event @@ -2676,7 +2673,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, * write counter enough to allow another writer to slip * in on this page. * We put in a discarded commit instead, to make sure - * that this space is not used again. + * that this space is not used again, and this space will + * not be accounted into 'entries_bytes'. * * If we are less than the minimum size, we don't need to * worry about it. @@ -2701,6 +2699,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer, /* time delta must be non zero */ event->time_delta = 1; + /* account for padding bytes */ + local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes); + /* Make sure the padding is visible before the tail_page->write update */ smp_wmb(); @@ -4215,7 +4216,7 @@ u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu) EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); /** - * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer + * ring_buffer_bytes_cpu - get the number of bytes unconsumed in a cpu buffer * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ @@ -4723,6 +4724,7 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) length = rb_event_length(event); cpu_buffer->reader_page->read += length; + cpu_buffer->read_bytes += length; } static void rb_advance_iter(struct ring_buffer_iter *iter) @@ -5816,7 +5818,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); - cpu_buffer->read_bytes += BUF_PAGE_SIZE; + cpu_buffer->read_bytes += rb_page_commit(reader); /* swap the pages */ rb_init_page(bpage); diff --git a/lib/argv_split.c b/lib/argv_split.c index 1a19a0a93dc1..e28db8e3b58c 100644 --- a/lib/argv_split.c +++ b/lib/argv_split.c @@ -28,7 +28,7 @@ static int count_argc(const char *str) /** * argv_free - free an argv - * @argv - the argument vector to be freed + * @argv: the argument vector to be freed * * Frees an argv and the strings it points to. */ @@ -46,7 +46,7 @@ EXPORT_SYMBOL(argv_free); * @str: the string to be split * @argcp: returned argument count * - * Returns an array of pointers to strings which are split out from + * Returns: an array of pointers to strings which are split out from * @str. This is performed by strictly splitting on white-space; no * quote processing is performed. Multiple whitespace characters are * considered to be a single argument separator. The returned array diff --git a/lib/scatterlist.c b/lib/scatterlist.c index c65566b4dc66..68b45c82c37a 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -265,7 +265,8 @@ EXPORT_SYMBOL(sg_free_table); * @table: The sg table header to use * @nents: Number of entries in sg list * @max_ents: The maximum number of entries the allocator returns per call - * @nents_first_chunk: Number of entries int the (preallocated) first + * @first_chunk: first SGL if preallocated (may be %NULL) + * @nents_first_chunk: Number of entries in the (preallocated) first * scatterlist chunk, 0 means no such preallocated chunk provided by user * @gfp_mask: GFP allocation mask * @alloc_fn: Allocator to use @@ -788,6 +789,7 @@ EXPORT_SYMBOL(__sg_page_iter_dma_next); * @miter: sg mapping iter to be started * @sgl: sg list to iterate over * @nents: number of sg entries + * @flags: sg iterator flags * * Description: * Starts mapping iterator @miter. diff --git a/mm/filemap.c b/mm/filemap.c index 582f5317ff71..4ea4387053e8 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3475,13 +3475,11 @@ skip: */ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, - unsigned long addr, unsigned int nr_pages) + unsigned long addr, unsigned int nr_pages, + unsigned int *mmap_miss) { vm_fault_t ret = 0; - struct vm_area_struct *vma = vmf->vma; - struct file *file = vma->vm_file; struct page *page = folio_page(folio, start); - unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); unsigned int count = 0; pte_t *old_ptep = vmf->pte; @@ -3489,8 +3487,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, if (PageHWPoison(page + count)) goto skip; - if (mmap_miss > 0) - mmap_miss--; + (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be @@ -3525,7 +3522,35 @@ skip: } vmf->pte = old_ptep; - WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); + + return ret; +} + +static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, + struct folio *folio, unsigned long addr, + unsigned int *mmap_miss) +{ + vm_fault_t ret = 0; + struct page *page = &folio->page; + + if (PageHWPoison(page)) + return ret; + + (*mmap_miss)++; + + /* + * NOTE: If there're PTE markers, we'll leave them to be + * handled in the specific fault path, and it'll prohibit + * the fault-around logic. + */ + if (!pte_none(ptep_get(vmf->pte))) + return ret; + + if (vmf->address == addr) + ret = VM_FAULT_NOPAGE; + + set_pte_range(vmf, folio, page, 1, addr); + folio_ref_inc(folio); return ret; } @@ -3541,7 +3566,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; vm_fault_t ret = 0; - int nr_pages = 0; + unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved; rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); @@ -3569,25 +3594,27 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, end = folio->index + folio_nr_pages(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; - /* - * NOTE: If there're PTE markers, we'll leave them to be - * handled in the specific fault path, and it'll prohibit the - * fault-around logic. - */ - if (!pte_none(ptep_get(vmf->pte))) - goto unlock; - - ret |= filemap_map_folio_range(vmf, folio, - xas.xa_index - folio->index, addr, nr_pages); + if (!folio_test_large(folio)) + ret |= filemap_map_order0_folio(vmf, + folio, addr, &mmap_miss); + else + ret |= filemap_map_folio_range(vmf, folio, + xas.xa_index - folio->index, addr, + nr_pages, &mmap_miss); -unlock: folio_unlock(folio); folio_put(folio); - folio = next_uptodate_folio(&xas, mapping, end_pgoff); - } while (folio); + } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); pte_unmap_unlock(vmf->pte, vmf->ptl); out: rcu_read_unlock(); + + mmap_miss_saved = READ_ONCE(file->f_ra.mmap_miss); + if (mmap_miss >= mmap_miss_saved) + WRITE_ONCE(file->f_ra.mmap_miss, 0); + else + WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss_saved - mmap_miss); + return ret; } EXPORT_SYMBOL(filemap_map_pages); diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index f70e3d7a602e..d37831b8511c 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -291,7 +291,7 @@ struct kasan_stack_ring { #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -#ifndef __HAVE_ARCH_SHADOW_MAP +#ifndef kasan_shadow_to_mem static inline const void *kasan_shadow_to_mem(const void *shadow_addr) { return (void *)(((unsigned long)shadow_addr - KASAN_SHADOW_OFFSET) @@ -299,15 +299,13 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr) } #endif +#ifndef addr_has_metadata static __always_inline bool addr_has_metadata(const void *addr) { -#ifdef __HAVE_ARCH_SHADOW_MAP - return (kasan_mem_to_shadow((void *)addr) != NULL); -#else return (kasan_reset_tag(addr) >= kasan_shadow_to_mem((void *)KASAN_SHADOW_START)); -#endif } +#endif /** * kasan_check_range - Check memory region, and report if invalid access. diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a4d3282493b6..d13dde2f8b56 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2555,7 +2555,7 @@ static unsigned long calculate_high_delay(struct mem_cgroup *memcg, * Scheduled by try_charge() to be executed from the userland return path * and reclaims memory over the high limit. */ -void mem_cgroup_handle_over_high(void) +void mem_cgroup_handle_over_high(gfp_t gfp_mask) { unsigned long penalty_jiffies; unsigned long pflags; @@ -2583,7 +2583,7 @@ retry_reclaim: */ nr_reclaimed = reclaim_high(memcg, in_retry ? SWAP_CLUSTER_MAX : nr_pages, - GFP_KERNEL); + gfp_mask); /* * memory.high is breached and reclaim is unable to keep up. Throttle @@ -2819,7 +2819,7 @@ done_restock: if (current->memcg_nr_pages_over_high > MEMCG_CHARGE_BATCH && !(current->flags & PF_MEMALLOC) && gfpflags_allow_blocking(gfp_mask)) { - mem_cgroup_handle_over_high(); + mem_cgroup_handle_over_high(gfp_mask); } return 0; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0c5be12f9336..95546f376302 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2400,7 +2400,7 @@ void free_unref_page(struct page *page, unsigned int order) struct per_cpu_pages *pcp; struct zone *zone; unsigned long pfn = page_to_pfn(page); - int migratetype; + int migratetype, pcpmigratetype; if (!free_unref_page_prepare(page, pfn, order)) return; @@ -2408,24 +2408,24 @@ void free_unref_page(struct page *page, unsigned int order) /* * We only track unmovable, reclaimable and movable on pcp lists. * Place ISOLATE pages on the isolated list because they are being - * offlined but treat HIGHATOMIC as movable pages so we can get those - * areas back if necessary. Otherwise, we may have to free + * offlined but treat HIGHATOMIC and CMA as movable pages so we can + * get those areas back if necessary. Otherwise, we may have to free * excessively into the page allocator */ - migratetype = get_pcppage_migratetype(page); + migratetype = pcpmigratetype = get_pcppage_migratetype(page); if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { if (unlikely(is_migrate_isolate(migratetype))) { free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE); return; } - migratetype = MIGRATE_MOVABLE; + pcpmigratetype = MIGRATE_MOVABLE; } zone = page_zone(page); pcp_trylock_prepare(UP_flags); pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (pcp) { - free_unref_page_commit(zone, pcp, page, migratetype, order); + free_unref_page_commit(zone, pcp, page, pcpmigratetype, order); pcp_spin_unlock(pcp); } else { free_one_page(zone, page, pfn, order, migratetype, FPI_NONE); diff --git a/mm/shmem.c b/mm/shmem.c index 02e62fccc80d..69595d341882 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -4586,7 +4586,7 @@ static struct file_system_type shmem_fs_type = { #endif .kill_sb = kill_litter_super, #ifdef CONFIG_SHMEM - .fs_flags = FS_USERNS_MOUNT | FS_ALLOW_IDMAP | FS_MGTIME, + .fs_flags = FS_USERNS_MOUNT | FS_ALLOW_IDMAP, #else .fs_flags = FS_USERNS_MOUNT, #endif diff --git a/net/ax25/Kconfig b/net/ax25/Kconfig index d3a9843a043d..fdb666607f10 100644 --- a/net/ax25/Kconfig +++ b/net/ax25/Kconfig @@ -10,7 +10,7 @@ menuconfig HAMRADIO If you want to connect your Linux box to an amateur radio, answer Y here. You want to read <https://www.tapr.org/> and more specifically about AX.25 on Linux - <http://www.linux-ax25.org/>. + <https://linux-ax25.in-berlin.de>. Note that the answer to this question won't directly affect the kernel: saying N will just cause the configurator to skip all @@ -61,7 +61,7 @@ config AX25_DAMA_SLAVE configuration. Linux cannot yet act as a DAMA server. This option only compiles DAMA slave support into the kernel. It still needs to be enabled at runtime. For more about DAMA see - <http://www.linux-ax25.org>. If unsure, say Y. + <https://linux-ax25.in-berlin.de>. If unsure, say Y. # placeholder until implemented config AX25_DAMA_MASTER @@ -87,9 +87,9 @@ config NETROM A comprehensive listing of all the software for Linux amateur radio users as well as information about how to configure an AX.25 port is contained in the Linux Ham Wiki, available from - <http://www.linux-ax25.org>. You also might want to check out the - file <file:Documentation/networking/ax25.rst>. More information about - digital amateur radio in general is on the WWW at + <https://linux-ax25.in-berlin.de>. You also might want to check out + the file <file:Documentation/networking/ax25.rst>. More information + about digital amateur radio in general is on the WWW at <https://www.tapr.org/>. To compile this driver as a module, choose M here: the @@ -106,9 +106,9 @@ config ROSE A comprehensive listing of all the software for Linux amateur radio users as well as information about how to configure an AX.25 port is contained in the Linux Ham Wiki, available from - <http://www.linux-ax25.org>. You also might want to check out the - file <file:Documentation/networking/ax25.rst>. More information about - digital amateur radio in general is on the WWW at + <https://linux-ax25.in-berlin.de>. You also might want to check out + the file <file:Documentation/networking/ax25.rst>. More information + about digital amateur radio in general is on the WWW at <https://www.tapr.org/>. To compile this driver as a module, choose M here: the diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 9d7bc8b96b53..7431f89e897b 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -124,7 +124,7 @@ static int deliver_clone(const struct net_bridge_port *prev, skb = skb_clone(skb, GFP_ATOMIC); if (!skb) { - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return -ENOMEM; } @@ -268,7 +268,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, skb = skb_copy(skb, GFP_ATOMIC); if (!skb) { - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index c34a0b0901b0..c729528b5e85 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -181,12 +181,12 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if ((mdst && mdst->host_joined) || br_multicast_is_router(brmctx, skb)) { local_rcv = true; - br->dev->stats.multicast++; + DEV_STATS_INC(br->dev, multicast); } mcast_hit = true; } else { local_rcv = true; - br->dev->stats.multicast++; + DEV_STATS_INC(br->dev, multicast); } break; case BR_PKT_UNICAST: diff --git a/net/core/dev.c b/net/core/dev.c index ccff2b6ef958..85df22f05c38 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -69,7 +69,7 @@ */ #include <linux/uaccess.h> -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/types.h> @@ -1080,7 +1080,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) return -EINVAL; /* Use one page as a bit array of possible slots */ - inuse = (unsigned long *) get_zeroed_page(GFP_ATOMIC); + inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC); if (!inuse) return -ENOMEM; @@ -1109,7 +1109,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) } i = find_first_zero_bit(inuse, max_netdevices); - free_page((unsigned long) inuse); + bitmap_free(inuse); } snprintf(buf, IFNAMSIZ, name, i); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index b3b3af0e7844..272f09251343 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1446,7 +1446,7 @@ proto_again: break; } - nhoff += ntohs(hdr->message_length); + nhoff += sizeof(struct ptp_header); fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8f56e8723c73..69453b936bd5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -254,13 +254,8 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) int err; struct net *net = dev_net(skb->dev); - /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, - * which is in byte 7 of the dccp header. - * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us. - * - * Later on, we want to access the sequence number fields, which are - * beyond 8 bytes, so we have to pskb_may_pull() ourselves. - */ + if (!pskb_may_pull(skb, offset + sizeof(*dh))) + return -EINVAL; dh = (struct dccp_hdr *)(skb->data + offset); if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) return -EINVAL; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 33f6ccf6ba77..c693a570682f 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -83,13 +83,8 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, __u64 seq; struct net *net = dev_net(skb->dev); - /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, - * which is in byte 7 of the dccp header. - * Our caller (icmpv6_notify()) already pulled 8 bytes for us. - * - * Later on, we want to access the sequence number fields, which are - * beyond 8 bytes, so we have to pskb_may_pull() ourselves. - */ + if (!pskb_may_pull(skb, offset + sizeof(*dh))) + return -EINVAL; dh = (struct dccp_hdr *)(skb->data + offset); if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) return -EINVAL; diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c index 6d37bab35c8f..16ed7bfd29e4 100644 --- a/net/handshake/handshake-test.c +++ b/net/handshake/handshake-test.c @@ -235,7 +235,7 @@ static void handshake_req_submit_test4(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, req, result); handshake_req_cancel(sock->sk); - sock_release(sock); + fput(filp); } static void handshake_req_submit_test5(struct kunit *test) @@ -272,7 +272,7 @@ static void handshake_req_submit_test5(struct kunit *test) /* Assert */ KUNIT_EXPECT_EQ(test, err, -EAGAIN); - sock_release(sock); + fput(filp); hn->hn_pending = saved; } @@ -306,7 +306,7 @@ static void handshake_req_submit_test6(struct kunit *test) KUNIT_EXPECT_EQ(test, err, -EBUSY); handshake_req_cancel(sock->sk); - sock_release(sock); + fput(filp); } static void handshake_req_cancel_test1(struct kunit *test) @@ -340,7 +340,7 @@ static void handshake_req_cancel_test1(struct kunit *test) /* Assert */ KUNIT_EXPECT_TRUE(test, result); - sock_release(sock); + fput(filp); } static void handshake_req_cancel_test2(struct kunit *test) @@ -382,7 +382,7 @@ static void handshake_req_cancel_test2(struct kunit *test) /* Assert */ KUNIT_EXPECT_TRUE(test, result); - sock_release(sock); + fput(filp); } static void handshake_req_cancel_test3(struct kunit *test) @@ -427,7 +427,7 @@ static void handshake_req_cancel_test3(struct kunit *test) /* Assert */ KUNIT_EXPECT_FALSE(test, result); - sock_release(sock); + fput(filp); } static struct handshake_req *handshake_req_destroy_test; @@ -471,7 +471,7 @@ static void handshake_req_destroy_test1(struct kunit *test) handshake_req_cancel(sock->sk); /* Act */ - sock_release(sock); + fput(filp); /* Assert */ KUNIT_EXPECT_PTR_EQ(test, handshake_req_destroy_test, req); diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index b77f1189d19d..6d14d935ee82 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -288,13 +288,13 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) /* And leave the HSR tag. */ if (ethhdr->h_proto == htons(ETH_P_HSR)) { - pull_size = sizeof(struct ethhdr); + pull_size = sizeof(struct hsr_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; } /* And leave the HSR sup tag. */ - pull_size = sizeof(struct hsr_tag); + pull_size = sizeof(struct hsr_sup_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 6851e33df7d1..18e01791ad79 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -83,7 +83,7 @@ struct hsr_vlan_ethhdr { struct hsr_sup_tlv { u8 HSR_TLV_type; u8 HSR_TLV_length; -}; +} __packed; /* HSR/PRP Supervision Frame data types. * Field names as defined in the IEC:2010 standard for HSR. diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 66f419e7f9a7..a57062283219 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1213,6 +1213,7 @@ EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { + struct net_device *dev; struct ip_options opt; int res; @@ -1230,7 +1231,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb) opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; + res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c254accb14de..cd15ec73073e 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1269,12 +1269,13 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) if (rcv_wnd == rcv_wnd_old) break; - if (before64(rcv_wnd_new, rcv_wnd)) { + + rcv_wnd_old = rcv_wnd; + if (before64(rcv_wnd_new, rcv_wnd_old)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICTUPDATE); goto raise_win; } MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT); - rcv_wnd_old = rcv_wnd; } return; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a7fc16f5175d..e252539b1e19 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -405,7 +405,7 @@ drop: return false; } -static void mptcp_stop_timer(struct sock *sk) +static void mptcp_stop_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -770,6 +770,46 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) return moved; } +static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) +{ + int err = sock_error(ssk); + int ssk_state; + + if (!err) + return false; + + /* only propagate errors on fallen-back sockets or + * on MPC connect + */ + if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk))) + return false; + + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); + WRITE_ONCE(sk->sk_err, -err); + + /* This barrier is coupled with smp_rmb() in mptcp_poll() */ + smp_wmb(); + sk_error_report(sk); + return true; +} + +void __mptcp_error_report(struct sock *sk) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) + if (__mptcp_subflow_error_report(sk, mptcp_subflow_tcp_sock(subflow))) + break; +} + /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ @@ -852,6 +892,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++; mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); + mptcp_stop_tout_timer(sk); return true; } @@ -871,12 +912,12 @@ static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list } } -static bool mptcp_timer_pending(struct sock *sk) +static bool mptcp_rtx_timer_pending(struct sock *sk) { return timer_pending(&inet_csk(sk)->icsk_retransmit_timer); } -static void mptcp_reset_timer(struct sock *sk) +static void mptcp_reset_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned long tout; @@ -1010,10 +1051,10 @@ static void __mptcp_clean_una(struct sock *sk) out: if (snd_una == READ_ONCE(msk->snd_nxt) && snd_una == READ_ONCE(msk->write_seq)) { - if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) - mptcp_stop_timer(sk); + if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) + mptcp_stop_rtx_timer(sk); } else { - mptcp_reset_timer(sk); + mptcp_reset_rtx_timer(sk); } } @@ -1586,8 +1627,8 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) mptcp_push_release(ssk, &info); /* ensure the rtx timer is running */ - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); if (do_check_data_fin) mptcp_check_send_data_fin(sk); } @@ -1650,8 +1691,8 @@ out: if (copied) { tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); if (msk->snd_data_fin_enable && msk->snd_nxt + 1 == msk->write_seq) @@ -2220,7 +2261,7 @@ static void mptcp_retransmit_timer(struct timer_list *t) sock_put(sk); } -static void mptcp_timeout_timer(struct timer_list *t) +static void mptcp_tout_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); @@ -2329,18 +2370,14 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, bool dispose_it, need_push = false; /* If the first subflow moved to a close state before accept, e.g. due - * to an incoming reset, mptcp either: - * - if either the subflow or the msk are dead, destroy the context - * (the subflow socket is deleted by inet_child_forget) and the msk - * - otherwise do nothing at the moment and take action at accept and/or - * listener shutdown - user-space must be able to accept() the closed - * socket. + * to an incoming reset or listener shutdown, the subflow socket is + * already deleted by inet_child_forget() and the mptcp socket can't + * survive too. */ - if (msk->in_accept_queue && msk->first == ssk) { - if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD)) - return; - + if (msk->in_accept_queue && msk->first == ssk && + (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) { /* ensure later check in mptcp_worker() will dispose the msk */ + mptcp_set_close_tout(sk, tcp_jiffies32 - (TCP_TIMEWAIT_LEN + 1)); sock_set_flag(sk, SOCK_DEAD); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); mptcp_subflow_drop_ctx(ssk); @@ -2392,6 +2429,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, } out_release: + __mptcp_subflow_error_report(sk, ssk); release_sock(ssk); sock_put(ssk); @@ -2402,6 +2440,22 @@ out_release: out: if (need_push) __mptcp_push_pending(sk, 0); + + /* Catch every 'all subflows closed' scenario, including peers silently + * closing them, e.g. due to timeout. + * For established sockets, allow an additional timeout before closing, + * as the protocol can still create more subflows. + */ + if (list_is_singular(&msk->conn_list) && msk->first && + inet_sk_state_load(msk->first) == TCP_CLOSE) { + if (sk->sk_state != TCP_ESTABLISHED || + msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) { + inet_sk_state_store(sk, TCP_CLOSE); + mptcp_close_wake_up(sk); + } else { + mptcp_start_tout_timer(sk); + } + } } void mptcp_close_ssk(struct sock *sk, struct sock *ssk, @@ -2445,23 +2499,14 @@ static void __mptcp_close_subflow(struct sock *sk) } -static bool mptcp_should_close(const struct sock *sk) +static bool mptcp_close_tout_expired(const struct sock *sk) { - s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp; - struct mptcp_subflow_context *subflow; - - if (delta >= TCP_TIMEWAIT_LEN || mptcp_sk(sk)->in_accept_queue) - return true; + if (!inet_csk(sk)->icsk_mtup.probe_timestamp || + sk->sk_state == TCP_CLOSE) + return false; - /* if all subflows are in closed status don't bother with additional - * timeout - */ - mptcp_for_each_subflow(mptcp_sk(sk), subflow) { - if (inet_sk_state_load(mptcp_subflow_tcp_sock(subflow)) != - TCP_CLOSE) - return false; - } - return true; + return time_after32(tcp_jiffies32, + inet_csk(sk)->icsk_mtup.probe_timestamp + TCP_TIMEWAIT_LEN); } static void mptcp_check_fastclose(struct mptcp_sock *msk) @@ -2588,27 +2633,28 @@ static void __mptcp_retrans(struct sock *sk) reset_timer: mptcp_check_and_set_pending(sk); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); } /* schedule the timeout timer for the relevant event: either close timeout * or mp_fail timeout. The close timeout takes precedence on the mp_fail one */ -void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout) +void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) { struct sock *sk = (struct sock *)msk; unsigned long timeout, close_timeout; - if (!fail_tout && !sock_flag(sk, SOCK_DEAD)) + if (!fail_tout && !inet_csk(sk)->icsk_mtup.probe_timestamp) return; - close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN; + close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + + TCP_TIMEWAIT_LEN; /* the close timeout takes precedence on the fail one, and here at least one of * them is active */ - timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout; + timeout = inet_csk(sk)->icsk_mtup.probe_timestamp ? close_timeout : fail_tout; sk_reset_timer(sk, &sk->sk_timer, timeout); } @@ -2627,8 +2673,6 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) mptcp_subflow_reset(ssk); WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); unlock_sock_fast(ssk, slow); - - mptcp_reset_timeout(msk, 0); } static void mptcp_do_fastclose(struct sock *sk) @@ -2665,18 +2709,14 @@ static void mptcp_worker(struct work_struct *work) if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) __mptcp_close_subflow(sk); - /* There is no point in keeping around an orphaned sk timedout or - * closed, but we need the msk around to reply to incoming DATA_FIN, - * even if it is orphaned and in FIN_WAIT2 state - */ - if (sock_flag(sk, SOCK_DEAD)) { - if (mptcp_should_close(sk)) - mptcp_do_fastclose(sk); + if (mptcp_close_tout_expired(sk)) { + mptcp_do_fastclose(sk); + mptcp_close_wake_up(sk); + } - if (sk->sk_state == TCP_CLOSE) { - __mptcp_destroy_sock(sk); - goto unlock; - } + if (sock_flag(sk, SOCK_DEAD) && sk->sk_state == TCP_CLOSE) { + __mptcp_destroy_sock(sk); + goto unlock; } if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) @@ -2717,7 +2757,7 @@ static void __mptcp_init_sock(struct sock *sk) /* re-use the csk retrans timer for MPTCP-level retrans */ timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); - timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0); + timer_setup(&sk->sk_timer, mptcp_tout_timer, 0); } static void mptcp_ca_reset(struct sock *sk) @@ -2808,8 +2848,8 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) } else { pr_debug("Sending DATA_FIN on subflow %p", ssk); tcp_send_ack(ssk); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); } break; } @@ -2892,7 +2932,7 @@ static void __mptcp_destroy_sock(struct sock *sk) might_sleep(); - mptcp_stop_timer(sk); + mptcp_stop_rtx_timer(sk); sk_stop_timer(sk, &sk->sk_timer); msk->pm.status = 0; mptcp_release_sched(msk); @@ -2975,7 +3015,6 @@ bool __mptcp_close(struct sock *sk, long timeout) cleanup: /* orphan all the subflows */ - inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); @@ -3012,7 +3051,7 @@ cleanup: __mptcp_destroy_sock(sk); do_cancel_work = true; } else { - mptcp_reset_timeout(msk, 0); + mptcp_start_tout_timer(sk); } return do_cancel_work; @@ -3075,8 +3114,8 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_check_listen_stop(sk); inet_sk_state_store(sk, TCP_CLOSE); - mptcp_stop_timer(sk); - sk_stop_timer(sk, &sk->sk_timer); + mptcp_stop_rtx_timer(sk); + mptcp_stop_tout_timer(sk); if (msk->token) mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 7254b3562575..ed61d6850cce 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -718,7 +718,29 @@ void mptcp_get_options(const struct sk_buff *skb, void mptcp_finish_connect(struct sock *sk); void __mptcp_set_connected(struct sock *sk); -void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout); +void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout); + +static inline void mptcp_stop_tout_timer(struct sock *sk) +{ + if (!inet_csk(sk)->icsk_mtup.probe_timestamp) + return; + + sk_stop_timer(sk, &sk->sk_timer); + inet_csk(sk)->icsk_mtup.probe_timestamp = 0; +} + +static inline void mptcp_set_close_tout(struct sock *sk, unsigned long tout) +{ + /* avoid 0 timestamp, as that means no close timeout */ + inet_csk(sk)->icsk_mtup.probe_timestamp = tout ? : 1; +} + +static inline void mptcp_start_tout_timer(struct sock *sk) +{ + mptcp_set_close_tout(sk, tcp_jiffies32); + mptcp_reset_tout_timer(mptcp_sk(sk), 0); +} + static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9bf3c7bc1762..918c1a235790 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1226,7 +1226,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) WRITE_ONCE(subflow->fail_tout, fail_tout); tcp_send_ack(ssk); - mptcp_reset_timeout(msk, subflow->fail_tout); + mptcp_reset_tout_timer(msk, subflow->fail_tout); } static bool subflow_check_data_avail(struct sock *ssk) @@ -1362,42 +1362,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) *full_space = mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } -void __mptcp_error_report(struct sock *sk) -{ - struct mptcp_subflow_context *subflow; - struct mptcp_sock *msk = mptcp_sk(sk); - - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - int err = sock_error(ssk); - int ssk_state; - - if (!err) - continue; - - /* only propagate errors on fallen-back sockets or - * on MPC connect - */ - if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) - continue; - - /* We need to propagate only transition to CLOSE state. - * Orphaned socket will see such state change via - * subflow_sched_work_if_closed() and that path will properly - * destroy the msk as needed. - */ - ssk_state = inet_sk_state_load(ssk); - if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) - inet_sk_state_store(sk, ssk_state); - WRITE_ONCE(sk->sk_err, -err); - - /* This barrier is coupled with smp_rmb() in mptcp_poll() */ - smp_wmb(); - sk_error_report(sk); - break; - } -} - static void subflow_error_report(struct sock *ssk) { struct sock *sk = mptcp_subflow_ctx(ssk)->conn; @@ -1588,6 +1552,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, mptcp_sock_graft(ssk, sk->sk_socket); iput(SOCK_INODE(sf)); WRITE_ONCE(msk->allow_infinite_fallback, false); + mptcp_stop_tout_timer(sk); return 0; failed_unlink: diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index 62fb1031763d..f8854bff286c 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -89,6 +89,11 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp, if ((had_link == has_link) || chained) return 0; + if (had_link) + netif_carrier_off(ndp->ndev.dev); + else + netif_carrier_on(ndp->ndev.dev); + if (!ndp->multi_package && !nc->package->multi_channel) { if (had_link) { ndp->flags |= NCSI_DEV_RESHUFFLE; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e564b5174261..35d2f9c9ada0 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -683,6 +683,14 @@ __ip_set_put(struct ip_set *set) * a separate reference counter */ static void +__ip_set_get_netlink(struct ip_set *set) +{ + write_lock_bh(&ip_set_ref_lock); + set->ref_netlink++; + write_unlock_bh(&ip_set_ref_lock); +} + +static void __ip_set_put_netlink(struct ip_set *set) { write_lock_bh(&ip_set_ref_lock); @@ -1693,11 +1701,11 @@ call_ad(struct net *net, struct sock *ctnl, struct sk_buff *skb, do { if (retried) { - __ip_set_get(set); + __ip_set_get_netlink(set); nfnl_unlock(NFNL_SUBSYS_IPSET); cond_resched(); nfnl_lock(NFNL_SUBSYS_IPSET); - __ip_set_put(set); + __ip_set_put_netlink(set); } ip_set_lock(set); diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index c7a6114091ae..b21799d468d2 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -381,6 +381,8 @@ __bpf_kfunc struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) struct nf_conn *nfct = (struct nf_conn *)nfct_i; int err; + if (!nf_ct_is_confirmed(nfct)) + nfct->timeout += nfct_time_stamp; nfct->status |= IPS_CONFIRMED; err = nf_conntrack_hash_check_insert(nfct); if (err < 0) { diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 0b513f7bf9f3..dd62cc12e775 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -40,10 +40,10 @@ static const u8 nf_ct_ext_type_len[NF_CT_EXT_NUM] = { [NF_CT_EXT_ECACHE] = sizeof(struct nf_conntrack_ecache), #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP - [NF_CT_EXT_TSTAMP] = sizeof(struct nf_conn_acct), + [NF_CT_EXT_TSTAMP] = sizeof(struct nf_conn_tstamp), #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT - [NF_CT_EXT_TIMEOUT] = sizeof(struct nf_conn_tstamp), + [NF_CT_EXT_TIMEOUT] = sizeof(struct nf_conn_timeout), #endif #ifdef CONFIG_NF_CONNTRACK_LABELS [NF_CT_EXT_LABELS] = sizeof(struct nf_conn_labels), diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e429ebba74b3..4356189360fb 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1219,6 +1219,10 @@ static int nf_tables_updtable(struct nft_ctx *ctx) flags & NFT_TABLE_F_OWNER)) return -EOPNOTSUPP; + /* No dormant off/on/off/on games in single transaction */ + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return -EINVAL; + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) @@ -1432,7 +1436,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -1446,8 +1450,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, set)) continue; - if (nft_set_is_anonymous(set) && - !list_empty(&set->bindings)) + if (nft_set_is_anonymous(set)) continue; err = nft_delset(ctx, set); @@ -1477,7 +1480,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -2910,6 +2913,9 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, return PTR_ERR(chain); } + if (nft_chain_binding(chain)) + return -EOPNOTSUPP; + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (nla[NFTA_CHAIN_HOOK]) { @@ -3449,6 +3455,8 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, struct net *net = sock_net(skb->sk); const struct nft_rule *rule, *prule; unsigned int s_idx = cb->args[0]; + unsigned int entries = 0; + int ret = 0; u64 handle; prule = NULL; @@ -3471,9 +3479,11 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, - table, chain, rule, handle, reset) < 0) - return 1; - + table, chain, rule, handle, reset) < 0) { + ret = 1; + break; + } + entries++; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: prule = rule; @@ -3481,10 +3491,10 @@ cont_skip: (*idx)++; } - if (reset && *idx) - audit_log_rule_reset(table, cb->seq, *idx); + if (reset && entries) + audit_log_rule_reset(table, cb->seq, entries); - return 0; + return ret; } static int nf_tables_dump_rules(struct sk_buff *skb, @@ -3971,6 +3981,11 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { + if (nft_chain_binding(chain)) { + err = -EOPNOTSUPP; + goto err_destroy_flow_rule; + } + err = nft_delrule(&ctx, old_rule); if (err < 0) goto err_destroy_flow_rule; @@ -4078,7 +4093,7 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) return -EOPNOTSUPP; } @@ -4112,7 +4127,7 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; @@ -7183,8 +7198,10 @@ static int nf_tables_delsetelem(struct sk_buff *skb, if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings) && - (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) + if (nft_set_is_anonymous(set)) + return -EOPNOTSUPP; + + if (!list_empty(&set->bindings) && (set->flags & NFT_SET_CONSTANT)) return -EBUSY; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); @@ -9562,12 +9579,15 @@ static int nft_trans_gc_space(struct nft_trans_gc *trans) struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, unsigned int gc_seq, gfp_t gfp) { + struct nft_set *set; + if (nft_trans_gc_space(gc)) return gc; + set = gc->set; nft_trans_gc_queue_work(gc); - return nft_trans_gc_alloc(gc->set, gc_seq, gfp); + return nft_trans_gc_alloc(set, gc_seq, gfp); } void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) @@ -9582,15 +9602,18 @@ void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) { + struct nft_set *set; + if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) return NULL; if (nft_trans_gc_space(gc)) return gc; + set = gc->set; call_rcu(&gc->rcu, nft_trans_gc_trans_free); - return nft_trans_gc_alloc(gc->set, 0, gfp); + return nft_trans_gc_alloc(set, 0, gfp); } void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) @@ -9605,8 +9628,9 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) call_rcu(&trans->rcu, nft_trans_gc_trans_free); } -struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, - unsigned int gc_seq) +static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq, + bool sync) { struct nft_set_elem_catchall *catchall; const struct nft_set *set = gc->set; @@ -9622,7 +9646,11 @@ struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, nft_set_elem_dead(ext); dead_elem: - gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (sync) + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + else + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) return NULL; @@ -9632,6 +9660,17 @@ dead_elem: return gc; } +struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, + unsigned int gc_seq) +{ + return nft_trans_gc_catchall(gc, gc_seq, false); +} + +struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) +{ + return nft_trans_gc_catchall(gc, 0, true); +} + static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -11054,7 +11093,7 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 524763659f25..2013de934cef 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -338,12 +338,9 @@ static void nft_rhash_gc(struct work_struct *work) while ((he = rhashtable_walk_next(&hti))) { if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) { - nft_trans_gc_destroy(gc); - gc = NULL; - goto try_later; - } - continue; + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; } /* Ruleset has been updated, try later. */ @@ -372,7 +369,7 @@ dead_elem: nft_trans_gc_elem_add(gc, he); } - gc = nft_trans_gc_catchall(gc, gc_seq); + gc = nft_trans_gc_catchall_async(gc, gc_seq); try_later: /* catchall list iteration requires rcu read side lock. */ diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 6af9c9ed4b5c..c0dcc40de358 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1596,7 +1596,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (!gc) - break; + return; nft_pipapo_gc_deactivate(net, set, e); pipapo_drop(m, rulemap); @@ -1610,7 +1610,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) } } - gc = nft_trans_gc_catchall(gc, 0); + gc = nft_trans_gc_catchall_sync(gc); if (gc) { nft_trans_gc_queue_sync_done(gc); priv->last_gc = jiffies; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index f250b5399344..487572dcd614 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -622,8 +622,7 @@ static void nft_rbtree_gc(struct work_struct *work) if (!gc) goto done; - write_lock_bh(&priv->lock); - write_seqcount_begin(&priv->count); + read_lock_bh(&priv->lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { /* Ruleset has been updated, try later. */ @@ -670,11 +669,10 @@ dead_elem: nft_trans_gc_elem_add(gc, rbe); } - gc = nft_trans_gc_catchall(gc, gc_seq); + gc = nft_trans_gc_catchall_async(gc, gc_seq); try_later: - write_seqcount_end(&priv->count); - write_unlock_bh(&priv->lock); + read_unlock_bh(&priv->lock); if (gc) nft_trans_gc_queue_async_done(gc); diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index d36f3f6b4351..b15cf316b23a 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -86,11 +86,13 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ADDR_RESOLVED: - rdma_set_service_type(cm_id, conn->c_tos); - rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32); - /* XXX do we need to clean up if this fails? */ - ret = rdma_resolve_route(cm_id, - RDS_RDMA_RESOLVE_TIMEOUT_MS); + if (conn) { + rdma_set_service_type(cm_id, conn->c_tos); + rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32); + /* XXX do we need to clean up if this fails? */ + ret = rdma_resolve_route(cm_id, + RDS_RDMA_RESOLVE_TIMEOUT_MS); + } break; case RDMA_CM_EVENT_ROUTE_RESOLVED: diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8d75290f1a31..37b0b212b934 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2725,7 +2725,7 @@ out_unparsable: out_verifier: trace_rpc_bad_verifier(task); - goto out_err; + goto out_garbage; out_msg_denied: error = -EACCES; @@ -2751,6 +2751,7 @@ out_msg_denied: case rpc_autherr_rejectedverf: case rpcsec_gsserr_credproblem: case rpcsec_gsserr_ctxproblem: + rpcauth_invalcred(task); if (!task->tk_cred_retry) break; task->tk_cred_retry--; @@ -2907,19 +2908,22 @@ static const struct rpc_call_ops rpc_cb_add_xprt_call_ops = { * @clnt: pointer to struct rpc_clnt * @xps: pointer to struct rpc_xprt_switch, * @xprt: pointer struct rpc_xprt - * @dummy: unused + * @in_max_connect: pointer to the max_connect value for the passed in xprt transport */ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt_switch *xps, struct rpc_xprt *xprt, - void *dummy) + void *in_max_connect) { struct rpc_cb_add_xprt_calldata *data; struct rpc_task *task; + int max_connect = clnt->cl_max_connect; - if (xps->xps_nunique_destaddr_xprts + 1 > clnt->cl_max_connect) { + if (in_max_connect) + max_connect = *(int *)in_max_connect; + if (xps->xps_nunique_destaddr_xprts + 1 > max_connect) { rcu_read_lock(); pr_warn("SUNRPC: reached max allowed number (%d) did not add " - "transport to server: %s\n", clnt->cl_max_connect, + "transport to server: %s\n", max_connect, rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR)); rcu_read_unlock(); return -EINVAL; diff --git a/scripts/atomic/gen-atomic-fallback.sh b/scripts/atomic/gen-atomic-fallback.sh index c0c8a85d7c81..a45154cefa48 100755 --- a/scripts/atomic/gen-atomic-fallback.sh +++ b/scripts/atomic/gen-atomic-fallback.sh @@ -102,7 +102,7 @@ gen_proto_order_variant() fi # Allow ACQUIRE/RELEASE/RELAXED ops to be defined in terms of FULL ops - if [ ! -z "${order}" ]; then + if [ ! -z "${order}" ] && ! meta_is_implicitly_relaxed "${meta}"; then printf "#elif defined(arch_${basename})\n" printf "\t${retstmt}arch_${basename}(${args});\n" fi diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index 5179edd1b627..c8047f4441e6 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -111,12 +111,11 @@ lx-symbols command.""" return "{textaddr} {sections}".format( textaddr=textaddr, sections="".join(args)) - def load_module_symbols(self, module, module_file=None): + def load_module_symbols(self, module): module_name = module['name'].string() module_addr = str(module['mem'][constants.LX_MOD_TEXT]['base']).split()[0] - if not module_file: - module_file = self._get_module_file(module_name) + module_file = self._get_module_file(module_name) if not module_file and not self.module_files_updated: self._update_module_files() module_file = self._get_module_file(module_name) @@ -139,19 +138,6 @@ lx-symbols command.""" else: gdb.write("no module object found for '{0}'\n".format(module_name)) - def load_ko_symbols(self, mod_path): - self.loaded_modules = [] - module_list = modules.module_list() - - for module in module_list: - module_name = module['name'].string() - module_pattern = ".*/{0}\.ko(?:.debug)?$".format( - module_name.replace("_", r"[_\-]")) - if re.match(module_pattern, mod_path) and os.path.exists(mod_path): - self.load_module_symbols(module, mod_path) - return - raise gdb.GdbError("%s is not a valid .ko\n" % mod_path) - def load_all_symbols(self): gdb.write("loading vmlinux\n") @@ -190,11 +176,6 @@ lx-symbols command.""" self.module_files = [] self.module_files_updated = False - argv = gdb.string_to_argv(arg) - if len(argv) == 1: - self.load_ko_symbols(argv[0]) - return - self.load_all_symbols() if hasattr(gdb, 'Breakpoint'): diff --git a/sound/core/init.c b/sound/core/init.c index d61bde1225f2..22c0d217b860 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -278,9 +278,6 @@ static int snd_card_init(struct snd_card *card, struct device *parent, size_t extra_size) { int err; -#ifdef CONFIG_SND_DEBUG - char name[8]; -#endif if (extra_size > 0) card->private_data = (char *)card + sizeof(struct snd_card); @@ -364,8 +361,8 @@ static int snd_card_init(struct snd_card *card, struct device *parent, } #ifdef CONFIG_SND_DEBUG - sprintf(name, "card%d", idx); - card->debugfs_root = debugfs_create_dir(name, sound_debugfs_root); + card->debugfs_root = debugfs_create_dir(dev_name(&card->card_dev), + sound_debugfs_root); #endif return 0; diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index ba06484ac4aa..1431cb997808 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1770,7 +1770,7 @@ static void snd_rawmidi_proc_info_read(struct snd_info_entry *entry, if (IS_ENABLED(CONFIG_SND_UMP)) snd_iprintf(buffer, "Type: %s\n", rawmidi_is_ump(rmidi) ? "UMP" : "Legacy"); - if (rmidi->ops->proc_read) + if (rmidi->ops && rmidi->ops->proc_read) rmidi->ops->proc_read(entry, buffer); mutex_lock(&rmidi->open_mutex); if (rmidi->info_flags & SNDRV_RAWMIDI_INFO_OUTPUT) { diff --git a/sound/core/seq/seq_midi.c b/sound/core/seq/seq_midi.c index 44302d98950e..18320a248aa7 100644 --- a/sound/core/seq/seq_midi.c +++ b/sound/core/seq/seq_midi.c @@ -349,9 +349,9 @@ snd_seq_midisynth_probe(struct device *_dev) if (! port->name[0]) { if (info->name[0]) { if (ports > 1) - snprintf(port->name, sizeof(port->name), "%s-%u", info->name, p); + scnprintf(port->name, sizeof(port->name), "%s-%u", info->name, p); else - snprintf(port->name, sizeof(port->name), "%s", info->name); + scnprintf(port->name, sizeof(port->name), "%s", info->name); } else { /* last resort */ if (ports > 1) diff --git a/sound/core/seq/seq_ump_client.c b/sound/core/seq/seq_ump_client.c index f26a1812dfa7..2db371d79930 100644 --- a/sound/core/seq/seq_ump_client.c +++ b/sound/core/seq/seq_ump_client.c @@ -207,7 +207,7 @@ static void fill_port_info(struct snd_seq_port_info *port, SNDRV_SEQ_PORT_TYPE_PORT; port->midi_channels = 16; if (*group->name) - snprintf(port->name, sizeof(port->name), "Group %d (%s)", + snprintf(port->name, sizeof(port->name), "Group %d (%.53s)", group->group + 1, group->name); else sprintf(port->name, "Group %d", group->group + 1); @@ -416,6 +416,25 @@ static void setup_client_midi_version(struct seq_ump_client *client) snd_seq_kernel_client_put(cptr); } +/* set up client's group_filter bitmap */ +static void setup_client_group_filter(struct seq_ump_client *client) +{ + struct snd_seq_client *cptr; + unsigned int filter; + int p; + + cptr = snd_seq_kernel_client_get(client->seq_client); + if (!cptr) + return; + filter = ~(1U << 0); /* always allow groupless messages */ + for (p = 0; p < SNDRV_UMP_MAX_GROUPS; p++) { + if (client->groups[p].active) + filter &= ~(1U << (p + 1)); + } + cptr->group_filter = filter; + snd_seq_kernel_client_put(cptr); +} + /* UMP group change notification */ static void handle_group_notify(struct work_struct *work) { @@ -424,6 +443,7 @@ static void handle_group_notify(struct work_struct *work) update_group_attrs(client); update_port_infos(client); + setup_client_group_filter(client); } /* UMP FB change notification */ @@ -492,6 +512,8 @@ static int snd_seq_ump_probe(struct device *_dev) goto error; } + setup_client_group_filter(client); + err = create_ump_endpoint_port(client); if (err < 0) goto error; diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c index 7cc84e137999..b141024830ec 100644 --- a/sound/core/seq/seq_ump_convert.c +++ b/sound/core/seq/seq_ump_convert.c @@ -1197,6 +1197,8 @@ int snd_seq_deliver_to_ump(struct snd_seq_client *source, struct snd_seq_event *event, int atomic, int hop) { + if (dest->group_filter & (1U << dest_port->ump_group)) + return 0; /* group filtered - skip the event */ if (event->type == SNDRV_SEQ_EVENT_SYSEX) return cvt_sysex_to_ump(dest, dest_port, event, atomic, hop); else if (snd_seq_client_is_midi2(dest)) diff --git a/sound/firewire/bebob/bebob_midi.c b/sound/firewire/bebob/bebob_midi.c index 6f597d03e7c1..b1425bf98c3b 100644 --- a/sound/firewire/bebob/bebob_midi.c +++ b/sound/firewire/bebob/bebob_midi.c @@ -84,9 +84,9 @@ static void set_midi_substream_names(struct snd_bebob *bebob, struct snd_rawmidi_substream *subs; list_for_each_entry(subs, &str->substreams, list) { - snprintf(subs->name, sizeof(subs->name), - "%s MIDI %d", - bebob->card->shortname, subs->number + 1); + scnprintf(subs->name, sizeof(subs->name), + "%s MIDI %d", + bebob->card->shortname, subs->number + 1); } } diff --git a/sound/firewire/dice/dice-midi.c b/sound/firewire/dice/dice-midi.c index 4c2998034313..78988e44b8bc 100644 --- a/sound/firewire/dice/dice-midi.c +++ b/sound/firewire/dice/dice-midi.c @@ -88,8 +88,8 @@ static void set_midi_substream_names(struct snd_dice *dice, struct snd_rawmidi_substream *subs; list_for_each_entry(subs, &str->substreams, list) { - snprintf(subs->name, sizeof(subs->name), - "%s MIDI %d", dice->card->shortname, subs->number + 1); + scnprintf(subs->name, sizeof(subs->name), + "%s MIDI %d", dice->card->shortname, subs->number + 1); } } diff --git a/sound/firewire/digi00x/digi00x-midi.c b/sound/firewire/digi00x/digi00x-midi.c index 68eb8c39afa6..8f4bace16050 100644 --- a/sound/firewire/digi00x/digi00x-midi.c +++ b/sound/firewire/digi00x/digi00x-midi.c @@ -100,14 +100,14 @@ static void set_substream_names(struct snd_dg00x *dg00x, list_for_each_entry(subs, &str->substreams, list) { if (!is_console) { - snprintf(subs->name, sizeof(subs->name), - "%s MIDI %d", - dg00x->card->shortname, - subs->number + 1); + scnprintf(subs->name, sizeof(subs->name), + "%s MIDI %d", + dg00x->card->shortname, + subs->number + 1); } else { - snprintf(subs->name, sizeof(subs->name), - "%s control", - dg00x->card->shortname); + scnprintf(subs->name, sizeof(subs->name), + "%s control", + dg00x->card->shortname); } } } diff --git a/sound/firewire/fireface/ff-midi.c b/sound/firewire/fireface/ff-midi.c index 25821d186b87..da3054fdcc7d 100644 --- a/sound/firewire/fireface/ff-midi.c +++ b/sound/firewire/fireface/ff-midi.c @@ -79,8 +79,8 @@ static void set_midi_substream_names(struct snd_rawmidi_str *stream, struct snd_rawmidi_substream *substream; list_for_each_entry(substream, &stream->substreams, list) { - snprintf(substream->name, sizeof(substream->name), - "%s MIDI %d", name, substream->number + 1); + scnprintf(substream->name, sizeof(substream->name), + "%s MIDI %d", name, substream->number + 1); } } diff --git a/sound/firewire/fireworks/fireworks.c b/sound/firewire/fireworks/fireworks.c index dd4298876ac0..e3ed4e094ccd 100644 --- a/sound/firewire/fireworks/fireworks.c +++ b/sound/firewire/fireworks/fireworks.c @@ -93,11 +93,11 @@ get_hardware_info(struct snd_efw *efw) strcpy(efw->card->driver, "Fireworks"); strcpy(efw->card->shortname, hwinfo->model_name); strcpy(efw->card->mixername, hwinfo->model_name); - snprintf(efw->card->longname, sizeof(efw->card->longname), - "%s %s v%s, GUID %08x%08x at %s, S%d", - hwinfo->vendor_name, hwinfo->model_name, version, - hwinfo->guid_hi, hwinfo->guid_lo, - dev_name(&efw->unit->device), 100 << fw_dev->max_speed); + scnprintf(efw->card->longname, sizeof(efw->card->longname), + "%s %s v%s, GUID %08x%08x at %s, S%d", + hwinfo->vendor_name, hwinfo->model_name, version, + hwinfo->guid_hi, hwinfo->guid_lo, + dev_name(&efw->unit->device), 100 << fw_dev->max_speed); if (hwinfo->flags & BIT(FLAG_RESP_ADDR_CHANGABLE)) efw->resp_addr_changable = true; diff --git a/sound/firewire/fireworks/fireworks_midi.c b/sound/firewire/fireworks/fireworks_midi.c index 84621e356848..350bf4d299c2 100644 --- a/sound/firewire/fireworks/fireworks_midi.c +++ b/sound/firewire/fireworks/fireworks_midi.c @@ -84,8 +84,8 @@ static void set_midi_substream_names(struct snd_efw *efw, struct snd_rawmidi_substream *subs; list_for_each_entry(subs, &str->substreams, list) { - snprintf(subs->name, sizeof(subs->name), - "%s MIDI %d", efw->card->shortname, subs->number + 1); + scnprintf(subs->name, sizeof(subs->name), + "%s MIDI %d", efw->card->shortname, subs->number + 1); } } diff --git a/sound/firewire/motu/motu-midi.c b/sound/firewire/motu/motu-midi.c index 2365f7dfde26..eebc7e790ee2 100644 --- a/sound/firewire/motu/motu-midi.c +++ b/sound/firewire/motu/motu-midi.c @@ -88,8 +88,8 @@ static void set_midi_substream_names(struct snd_motu *motu, struct snd_rawmidi_substream *subs; list_for_each_entry(subs, &str->substreams, list) { - snprintf(subs->name, sizeof(subs->name), - "%s MIDI %d", motu->card->shortname, subs->number + 1); + scnprintf(subs->name, sizeof(subs->name), + "%s MIDI %d", motu->card->shortname, subs->number + 1); } } diff --git a/sound/firewire/oxfw/oxfw-midi.c b/sound/firewire/oxfw/oxfw-midi.c index 775cba3f1f02..c215fa6f7a03 100644 --- a/sound/firewire/oxfw/oxfw-midi.c +++ b/sound/firewire/oxfw/oxfw-midi.c @@ -129,9 +129,9 @@ static void set_midi_substream_names(struct snd_oxfw *oxfw, struct snd_rawmidi_substream *subs; list_for_each_entry(subs, &str->substreams, list) { - snprintf(subs->name, sizeof(subs->name), - "%s MIDI %d", - oxfw->card->shortname, subs->number + 1); + scnprintf(subs->name, sizeof(subs->name), + "%s MIDI %d", + oxfw->card->shortname, subs->number + 1); } } diff --git a/sound/firewire/oxfw/oxfw.c b/sound/firewire/oxfw/oxfw.c index 63d40f1a914f..241a697ce26b 100644 --- a/sound/firewire/oxfw/oxfw.c +++ b/sound/firewire/oxfw/oxfw.c @@ -108,11 +108,11 @@ static int name_card(struct snd_oxfw *oxfw, const struct ieee1394_device_id *ent strcpy(oxfw->card->mixername, m); strcpy(oxfw->card->shortname, m); - snprintf(oxfw->card->longname, sizeof(oxfw->card->longname), - "%s %s (OXFW%x %04x), GUID %08x%08x at %s, S%d", - v, m, firmware >> 20, firmware & 0xffff, - fw_dev->config_rom[3], fw_dev->config_rom[4], - dev_name(&oxfw->unit->device), 100 << fw_dev->max_speed); + scnprintf(oxfw->card->longname, sizeof(oxfw->card->longname), + "%s %s (OXFW%x %04x), GUID %08x%08x at %s, S%d", + v, m, firmware >> 20, firmware & 0xffff, + fw_dev->config_rom[3], fw_dev->config_rom[4], + dev_name(&oxfw->unit->device), 100 << fw_dev->max_speed); end: return err; } diff --git a/sound/firewire/tascam/tascam-midi.c b/sound/firewire/tascam/tascam-midi.c index 02eed2dce435..c57fac4f1968 100644 --- a/sound/firewire/tascam/tascam-midi.c +++ b/sound/firewire/tascam/tascam-midi.c @@ -108,9 +108,9 @@ int snd_tscm_create_midi_devices(struct snd_tscm *tscm) /* TODO: support virtual MIDI ports. */ if (subs->number < tscm->spec->midi_capture_ports) { /* Hardware MIDI ports. */ - snprintf(subs->name, sizeof(subs->name), - "%s MIDI %d", - tscm->card->shortname, subs->number + 1); + scnprintf(subs->name, sizeof(subs->name), + "%s MIDI %d", + tscm->card->shortname, subs->number + 1); } } @@ -123,9 +123,9 @@ int snd_tscm_create_midi_devices(struct snd_tscm *tscm) list_for_each_entry(subs, &stream->substreams, list) { if (subs->number < tscm->spec->midi_playback_ports) { /* Hardware MIDI ports only. */ - snprintf(subs->name, sizeof(subs->name), - "%s MIDI %d", - tscm->card->shortname, subs->number + 1); + scnprintf(subs->name, sizeof(subs->name), + "%s MIDI %d", + tscm->card->shortname, subs->number + 1); } } diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c index 5cb92f7ccbca..b57d72ea4503 100644 --- a/sound/hda/intel-sdw-acpi.c +++ b/sound/hda/intel-sdw-acpi.c @@ -23,7 +23,7 @@ static int ctrl_link_mask; module_param_named(sdw_link_mask, ctrl_link_mask, int, 0444); MODULE_PARM_DESC(sdw_link_mask, "Intel link mask (one bit per link)"); -static bool is_link_enabled(struct fwnode_handle *fw_node, int i) +static bool is_link_enabled(struct fwnode_handle *fw_node, u8 idx) { struct fwnode_handle *link; char name[32]; @@ -31,7 +31,7 @@ static bool is_link_enabled(struct fwnode_handle *fw_node, int i) /* Find master handle */ snprintf(name, sizeof(name), - "mipi-sdw-link-%d-subproperties", i); + "mipi-sdw-link-%hhu-subproperties", idx); link = fwnode_get_named_child_node(fw_node, name); if (!link) @@ -51,8 +51,8 @@ static int sdw_intel_scan_controller(struct sdw_intel_acpi_info *info) { struct acpi_device *adev = acpi_fetch_acpi_dev(info->handle); - int ret, i; - u8 count; + u8 count, i; + int ret; if (!adev) return -EINVAL; diff --git a/sound/isa/ad1848/ad1848.c b/sound/isa/ad1848/ad1848.c index c471ac2aa450..401d8df28d87 100644 --- a/sound/isa/ad1848/ad1848.c +++ b/sound/isa/ad1848/ad1848.c @@ -96,13 +96,13 @@ static int snd_ad1848_probe(struct device *dev, unsigned int n) strscpy(card->shortname, chip->pcm->name, sizeof(card->shortname)); if (!thinkpad[n]) - snprintf(card->longname, sizeof(card->longname), - "%s at 0x%lx, irq %d, dma %d", - chip->pcm->name, chip->port, irq[n], dma1[n]); + scnprintf(card->longname, sizeof(card->longname), + "%s at 0x%lx, irq %d, dma %d", + chip->pcm->name, chip->port, irq[n], dma1[n]); else - snprintf(card->longname, sizeof(card->longname), - "%s at 0x%lx, irq %d, dma %d [Thinkpad]", - chip->pcm->name, chip->port, irq[n], dma1[n]); + scnprintf(card->longname, sizeof(card->longname), + "%s at 0x%lx, irq %d, dma %d [Thinkpad]", + chip->pcm->name, chip->port, irq[n], dma1[n]); error = snd_card_register(card); if (error < 0) diff --git a/sound/isa/cs423x/cs4231.c b/sound/isa/cs423x/cs4231.c index 1e8923385366..c87be4be6df1 100644 --- a/sound/isa/cs423x/cs4231.c +++ b/sound/isa/cs423x/cs4231.c @@ -98,13 +98,13 @@ static int snd_cs4231_probe(struct device *dev, unsigned int n) strscpy(card->shortname, chip->pcm->name, sizeof(card->shortname)); if (dma2[n] < 0) - snprintf(card->longname, sizeof(card->longname), - "%s at 0x%lx, irq %d, dma %d", - chip->pcm->name, chip->port, irq[n], dma1[n]); + scnprintf(card->longname, sizeof(card->longname), + "%s at 0x%lx, irq %d, dma %d", + chip->pcm->name, chip->port, irq[n], dma1[n]); else - snprintf(card->longname, sizeof(card->longname), - "%s at 0x%lx, irq %d, dma %d&%d", - chip->pcm->name, chip->port, irq[n], dma1[n], dma2[n]); + scnprintf(card->longname, sizeof(card->longname), + "%s at 0x%lx, irq %d, dma %d&%d", + chip->pcm->name, chip->port, irq[n], dma1[n], dma2[n]); error = snd_wss_mixer(chip); if (error < 0) diff --git a/sound/isa/cs423x/cs4236.c b/sound/isa/cs423x/cs4236.c index 10112e1bb25d..7226cbf2d7de 100644 --- a/sound/isa/cs423x/cs4236.c +++ b/sound/isa/cs423x/cs4236.c @@ -367,14 +367,14 @@ static int snd_cs423x_probe(struct snd_card *card, int dev) strscpy(card->driver, chip->pcm->name, sizeof(card->driver)); strscpy(card->shortname, chip->pcm->name, sizeof(card->shortname)); if (dma2[dev] < 0) - snprintf(card->longname, sizeof(card->longname), - "%s at 0x%lx, irq %i, dma %i", - chip->pcm->name, chip->port, irq[dev], dma1[dev]); + scnprintf(card->longname, sizeof(card->longname), + "%s at 0x%lx, irq %i, dma %i", + chip->pcm->name, chip->port, irq[dev], dma1[dev]); else - snprintf(card->longname, sizeof(card->longname), - "%s at 0x%lx, irq %i, dma %i&%d", - chip->pcm->name, chip->port, irq[dev], dma1[dev], - dma2[dev]); + scnprintf(card->longname, sizeof(card->longname), + "%s at 0x%lx, irq %i, dma %i&%d", + chip->pcm->name, chip->port, irq[dev], dma1[dev], + dma2[dev]); err = snd_wss_timer(chip, 0); if (err < 0) diff --git a/sound/isa/es1688/es1688.c b/sound/isa/es1688/es1688.c index f935b56eeec7..97728bf45474 100644 --- a/sound/isa/es1688/es1688.c +++ b/sound/isa/es1688/es1688.c @@ -130,9 +130,9 @@ static int snd_es1688_probe(struct snd_card *card, unsigned int n) strscpy(card->driver, "ES1688", sizeof(card->driver)); strscpy(card->shortname, chip->pcm->name, sizeof(card->shortname)); - snprintf(card->longname, sizeof(card->longname), - "%s at 0x%lx, irq %i, dma %i", chip->pcm->name, chip->port, - chip->irq, chip->dma8); + scnprintf(card->longname, sizeof(card->longname), + "%s at 0x%lx, irq %i, dma %i", chip->pcm->name, chip->port, + chip->irq, chip->dma8); if (fm_port[n] == SNDRV_AUTO_PORT) fm_port[n] = port[n]; /* share the same port */ diff --git a/sound/isa/opti9xx/miro.c b/sound/isa/opti9xx/miro.c index 59242baed576..59792f2fada1 100644 --- a/sound/isa/opti9xx/miro.c +++ b/sound/isa/opti9xx/miro.c @@ -1344,10 +1344,10 @@ static int snd_miro_probe(struct snd_card *card) } strcpy(card->driver, "miro"); - snprintf(card->longname, sizeof(card->longname), - "%s: OPTi%s, %s at 0x%lx, irq %d, dma %d&%d", - card->shortname, miro->name, codec->pcm->name, - miro->wss_base + 4, miro->irq, miro->dma1, miro->dma2); + scnprintf(card->longname, sizeof(card->longname), + "%s: OPTi%s, %s at 0x%lx, irq %d, dma %d&%d", + card->shortname, miro->name, codec->pcm->name, + miro->wss_base + 4, miro->irq, miro->dma1, miro->dma2); if (mpu_port <= 0 || mpu_port == SNDRV_AUTO_PORT) rmidi = NULL; diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c index 4beeb32fe2a7..c33f67dd5133 100644 --- a/sound/isa/opti9xx/opti92x-ad1848.c +++ b/sound/isa/opti9xx/opti92x-ad1848.c @@ -859,15 +859,15 @@ static int snd_opti9xx_probe(struct snd_card *card) strcpy(card->driver, chip->name); sprintf(card->shortname, "OPTi %s", card->driver); #if defined(CS4231) || defined(OPTi93X) - snprintf(card->longname, sizeof(card->longname), - "%s, %s at 0x%lx, irq %d, dma %d&%d", - card->shortname, codec->pcm->name, - chip->wss_base + 4, irq, dma1, xdma2); + scnprintf(card->longname, sizeof(card->longname), + "%s, %s at 0x%lx, irq %d, dma %d&%d", + card->shortname, codec->pcm->name, + chip->wss_base + 4, irq, dma1, xdma2); #else - snprintf(card->longname, sizeof(card->longname), - "%s, %s at 0x%lx, irq %d, dma %d", - card->shortname, codec->pcm->name, chip->wss_base + 4, irq, - dma1); + scnprintf(card->longname, sizeof(card->longname), + "%s, %s at 0x%lx, irq %d, dma %d", + card->shortname, codec->pcm->name, chip->wss_base + 4, irq, + dma1); #endif /* CS4231 || OPTi93X */ if (mpu_port <= 0 || mpu_port == SNDRV_AUTO_PORT) diff --git a/sound/isa/sscape.c b/sound/isa/sscape.c index 0bc0025f7c19..cc56fafd27b1 100644 --- a/sound/isa/sscape.c +++ b/sound/isa/sscape.c @@ -557,7 +557,7 @@ static int sscape_upload_microcode(struct snd_card *card, int version) char name[14]; int err; - snprintf(name, sizeof(name), "sndscape.co%d", version); + scnprintf(name, sizeof(name), "sndscape.co%d", version); err = request_firmware(&init_fw, name, card->dev); if (err < 0) { diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c index 1415baac9c36..08e34b184780 100644 --- a/sound/pci/cmipci.c +++ b/sound/pci/cmipci.c @@ -3102,11 +3102,13 @@ static int snd_cmipci_create(struct snd_card *card, struct pci_dev *pci, } sprintf(card->shortname, "C-Media CMI%d", val); if (cm->chip_version < 68) - sprintf(modelstr, " (model %d)", cm->chip_version); + scnprintf(modelstr, sizeof(modelstr), + " (model %d)", cm->chip_version); else modelstr[0] = '\0'; - sprintf(card->longname, "%s%s at %#lx, irq %i", - card->shortname, modelstr, cm->iobase, cm->irq); + scnprintf(card->longname, sizeof(card->longname), + "%s%s at %#lx, irq %i", + card->shortname, modelstr, cm->iobase, cm->irq); if (cm->chip_version >= 39) { val = snd_cmipci_read_b(cm, CM_REG_MPU_PCI + 1); diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c index 76b9c685560b..7adc1d373d65 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -105,7 +105,7 @@ static void cs35l56_hda_playback_hook(struct device *dev, int action) } } -static int __maybe_unused cs35l56_hda_runtime_suspend(struct device *dev) +static int cs35l56_hda_runtime_suspend(struct device *dev) { struct cs35l56_hda *cs35l56 = dev_get_drvdata(dev); @@ -115,7 +115,7 @@ static int __maybe_unused cs35l56_hda_runtime_suspend(struct device *dev) return cs35l56_runtime_suspend_common(&cs35l56->base); } -static int __maybe_unused cs35l56_hda_runtime_resume(struct device *dev) +static int cs35l56_hda_runtime_resume(struct device *dev) { struct cs35l56_hda *cs35l56 = dev_get_drvdata(dev); int ret; @@ -218,7 +218,7 @@ static int cs35l56_hda_posture_get(struct snd_kcontrol *kcontrol, ucontrol->value.integer.value[0] = pos; - return ret; + return 0; } static int cs35l56_hda_posture_put(struct snd_kcontrol *kcontrol, @@ -865,15 +865,13 @@ static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int id) sub = acpi_get_subsystem_id(ACPI_HANDLE(cs35l56->base.dev)); if (IS_ERR(sub)) { - /* If no ACPI SUB, return 0 and fallback to legacy firmware path, otherwise fail */ - if (PTR_ERR(sub) == -ENODATA) - return 0; - else - return PTR_ERR(sub); + dev_info(cs35l56->base.dev, + "Read ACPI _SUB failed(%ld): fallback to generic firmware\n", + PTR_ERR(sub)); + } else { + cs35l56->system_name = sub; } - cs35l56->system_name = sub; - cs35l56->base.reset_gpio = devm_gpiod_get_index_optional(cs35l56->base.dev, "reset", cs35l56->index, @@ -1003,6 +1001,7 @@ void cs35l56_hda_remove(struct device *dev) { struct cs35l56_hda *cs35l56 = dev_get_drvdata(dev); + pm_runtime_dont_use_autosuspend(cs35l56->base.dev); pm_runtime_get_sync(cs35l56->base.dev); pm_runtime_disable(cs35l56->base.dev); @@ -1016,7 +1015,7 @@ void cs35l56_hda_remove(struct device *dev) EXPORT_SYMBOL_NS_GPL(cs35l56_hda_remove, SND_HDA_SCODEC_CS35L56); const struct dev_pm_ops cs35l56_hda_pm_ops = { - SET_RUNTIME_PM_OPS(cs35l56_hda_runtime_suspend, cs35l56_hda_runtime_resume, NULL) + RUNTIME_PM_OPS(cs35l56_hda_runtime_suspend, cs35l56_hda_runtime_resume, NULL) SYSTEM_SLEEP_PM_OPS(cs35l56_hda_system_suspend, cs35l56_hda_system_resume) LATE_SYSTEM_SLEEP_PM_OPS(cs35l56_hda_system_suspend_late, cs35l56_hda_system_resume_early) diff --git a/sound/pci/hda/cs35l56_hda_i2c.c b/sound/pci/hda/cs35l56_hda_i2c.c index 83e4acdd89ac..757a4d193e0f 100644 --- a/sound/pci/hda/cs35l56_hda_i2c.c +++ b/sound/pci/hda/cs35l56_hda_i2c.c @@ -21,7 +21,6 @@ static int cs35l56_hda_i2c_probe(struct i2c_client *clt) return -ENOMEM; cs35l56->base.dev = &clt->dev; - cs35l56->base.can_hibernate = true; cs35l56->base.regmap = devm_regmap_init_i2c(clt, &cs35l56_regmap_i2c); if (IS_ERR(cs35l56->base.regmap)) { ret = PTR_ERR(cs35l56->base.regmap); diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index dbf7aa88e0e3..bf685d01259d 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -998,7 +998,11 @@ static int add_control_with_pfx(struct hda_gen_spec *spec, int type, const char *sfx, int cidx, unsigned long val) { char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; - snprintf(name, sizeof(name), "%s %s %s", pfx, dir, sfx); + int len; + + len = snprintf(name, sizeof(name), "%s %s %s", pfx, dir, sfx); + if (snd_BUG_ON(len >= sizeof(name))) + return -EINVAL; if (!add_control(spec, type, name, cidx, val)) return -ENOMEM; return 0; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 765d95e79861..ca765ac4765f 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2211,6 +2211,7 @@ static const struct snd_pci_quirk power_save_denylist[] = { SND_PCI_QUIRK(0x8086, 0x2068, "Intel NUC7i3BNB", 0), /* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */ SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0), + SND_PCI_QUIRK(0x17aa, 0x316e, "Lenovo ThinkCentre M70q", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1689623 */ SND_PCI_QUIRK(0x17aa, 0x367b, "Lenovo IdeaCentre B550", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */ diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b7e78bfcffd8..751783f3a15c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7073,8 +7073,10 @@ static void alc287_fixup_bind_dacs(struct hda_codec *codec, snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn); spec->gen.preferred_dacs = preferred_pairs; spec->gen.auto_mute_via_amp = 1; - snd_hda_codec_write_cache(codec, 0x14, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, - 0x0); /* Make sure 0x14 was disable */ + if (spec->gen.autocfg.speaker_pins[0] != 0x14) { + snd_hda_codec_write_cache(codec, 0x14, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, + 0x0); /* Make sure 0x14 was disable */ + } } @@ -9812,7 +9814,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1d1f, "ASUS ROG Strix G17 2023 (G713PV)", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE), - SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS), @@ -10574,6 +10577,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x17, 0x90170110}, {0x19, 0x03a11030}, {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0287, 0x17aa, "Lenovo", ALC287_FIXUP_THINKPAD_I2S_SPK, + {0x17, 0x90170110}, /* 0x231f with RTK I2S AMP */ + {0x19, 0x04a11040}, + {0x21, 0x04211020}), SND_HDA_PIN_QUIRK(0x10ec0286, 0x1025, "Acer", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE, {0x12, 0x90a60130}, {0x17, 0x90170110}, diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c index b37c877c2c16..9dee0345f22c 100644 --- a/sound/pci/riptide/riptide.c +++ b/sound/pci/riptide/riptide.c @@ -2105,15 +2105,15 @@ __snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id strcpy(card->driver, "RIPTIDE"); strcpy(card->shortname, "Riptide"); #ifdef SUPPORT_JOYSTICK - snprintf(card->longname, sizeof(card->longname), - "%s at 0x%lx, irq %i mpu 0x%x opl3 0x%x gameport 0x%x", - card->shortname, chip->port, chip->irq, chip->mpuaddr, - chip->opladdr, chip->gameaddr); + scnprintf(card->longname, sizeof(card->longname), + "%s at 0x%lx, irq %i mpu 0x%x opl3 0x%x gameport 0x%x", + card->shortname, chip->port, chip->irq, chip->mpuaddr, + chip->opladdr, chip->gameaddr); #else - snprintf(card->longname, sizeof(card->longname), - "%s at 0x%lx, irq %i mpu 0x%x opl3 0x%x", - card->shortname, chip->port, chip->irq, chip->mpuaddr, - chip->opladdr); + scnprintf(card->longname, sizeof(card->longname), + "%s at 0x%lx, irq %i mpu 0x%x opl3 0x%x", + card->shortname, chip->port, chip->irq, chip->mpuaddr, + chip->opladdr); #endif snd_riptide_proc_init(chip); err = snd_card_register(card); diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 3ec15b46fa35..94e9eb8e73f2 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -217,6 +217,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82QF"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "82TL"), } }, @@ -224,6 +231,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82UG"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "82V2"), } }, @@ -265,6 +279,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), + DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 B7ED"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Alienware"), DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m17 R5 AMD"), } diff --git a/sound/soc/codecs/aw88395/aw88395_lib.c b/sound/soc/codecs/aw88395/aw88395_lib.c index 8ee1baa03269..87dd0ccade4c 100644 --- a/sound/soc/codecs/aw88395/aw88395_lib.c +++ b/sound/soc/codecs/aw88395/aw88395_lib.c @@ -452,11 +452,13 @@ static int aw_dev_parse_reg_bin_with_hdr(struct aw_device *aw_dev, if ((aw_bin->all_bin_parse_num != 1) || (aw_bin->header_info[0].bin_data_type != DATA_TYPE_REGISTER)) { dev_err(aw_dev->dev, "bin num or type error"); + ret = -EINVAL; goto parse_bin_failed; } if (aw_bin->header_info[0].valid_data_len % 4) { dev_err(aw_dev->dev, "bin data len get error!"); + ret = -EINVAL; goto parse_bin_failed; } diff --git a/sound/soc/codecs/cs35l56-i2c.c b/sound/soc/codecs/cs35l56-i2c.c index 9f4f2f4f23f5..d10e0e2380e8 100644 --- a/sound/soc/codecs/cs35l56-i2c.c +++ b/sound/soc/codecs/cs35l56-i2c.c @@ -27,7 +27,6 @@ static int cs35l56_i2c_probe(struct i2c_client *client) return -ENOMEM; cs35l56->base.dev = dev; - cs35l56->base.can_hibernate = true; i2c_set_clientdata(client, cs35l56); cs35l56->base.regmap = devm_regmap_init_i2c(client, regmap_config); diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 600b79c62ec4..f2e7c6d0be46 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -1207,6 +1207,7 @@ void cs35l56_remove(struct cs35l56_private *cs35l56) flush_workqueue(cs35l56->dsp_wq); destroy_workqueue(cs35l56->dsp_wq); + pm_runtime_dont_use_autosuspend(cs35l56->base.dev); pm_runtime_suspend(cs35l56->base.dev); pm_runtime_disable(cs35l56->base.dev); diff --git a/sound/soc/codecs/cs42l42-sdw.c b/sound/soc/codecs/cs42l42-sdw.c index eeab07c850f9..974bae4abfad 100644 --- a/sound/soc/codecs/cs42l42-sdw.c +++ b/sound/soc/codecs/cs42l42-sdw.c @@ -344,6 +344,16 @@ static int cs42l42_sdw_update_status(struct sdw_slave *peripheral, switch (status) { case SDW_SLAVE_ATTACHED: dev_dbg(cs42l42->dev, "ATTACHED\n"); + + /* + * The SoundWire core can report stale ATTACH notifications + * if we hard-reset CS42L42 in probe() but it had already been + * enumerated. Reject the ATTACH if we haven't yet seen an + * UNATTACH report for the device being in reset. + */ + if (cs42l42->sdw_waiting_first_unattach) + break; + /* * Initialise codec, this only needs to be done once. * When resuming from suspend, resume callback will handle re-init of codec, @@ -354,6 +364,16 @@ static int cs42l42_sdw_update_status(struct sdw_slave *peripheral, break; case SDW_SLAVE_UNATTACHED: dev_dbg(cs42l42->dev, "UNATTACHED\n"); + + if (cs42l42->sdw_waiting_first_unattach) { + /* + * SoundWire core has seen that CS42L42 is not on + * the bus so release RESET and wait for ATTACH. + */ + cs42l42->sdw_waiting_first_unattach = false; + gpiod_set_value_cansleep(cs42l42->reset_gpio, 1); + } + break; default: break; diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index a0de0329406a..2961340f15e2 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -2320,7 +2320,26 @@ int cs42l42_common_probe(struct cs42l42_private *cs42l42, if (cs42l42->reset_gpio) { dev_dbg(cs42l42->dev, "Found reset GPIO\n"); - gpiod_set_value_cansleep(cs42l42->reset_gpio, 1); + + /* + * ACPI can override the default GPIO state we requested + * so ensure that we start with RESET low. + */ + gpiod_set_value_cansleep(cs42l42->reset_gpio, 0); + + /* Ensure minimum reset pulse width */ + usleep_range(10, 500); + + /* + * On SoundWire keep the chip in reset until we get an UNATTACH + * notification from the SoundWire core. This acts as a + * synchronization point to reject stale ATTACH notifications + * if the chip was already enumerated before we reset it. + */ + if (cs42l42->sdw_peripheral) + cs42l42->sdw_waiting_first_unattach = true; + else + gpiod_set_value_cansleep(cs42l42->reset_gpio, 1); } usleep_range(CS42L42_BOOT_TIME_US, CS42L42_BOOT_TIME_US * 2); diff --git a/sound/soc/codecs/cs42l42.h b/sound/soc/codecs/cs42l42.h index 4bd7b85a5747..7785125b73ab 100644 --- a/sound/soc/codecs/cs42l42.h +++ b/sound/soc/codecs/cs42l42.h @@ -53,6 +53,7 @@ struct cs42l42_private { u8 stream_use; bool hp_adc_up_pending; bool suspended; + bool sdw_waiting_first_unattach; bool init_done; }; diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c index 1a95c370fc4c..5643c666d7d0 100644 --- a/sound/soc/codecs/cs42l43.c +++ b/sound/soc/codecs/cs42l43.c @@ -2077,7 +2077,8 @@ static const struct cs42l43_irq cs42l43_irqs[] = { static int cs42l43_request_irq(struct cs42l43_codec *priv, struct irq_domain *dom, const char * const name, - unsigned int irq, irq_handler_t handler) + unsigned int irq, irq_handler_t handler, + unsigned long flags) { int ret; @@ -2087,8 +2088,8 @@ static int cs42l43_request_irq(struct cs42l43_codec *priv, dev_dbg(priv->dev, "Request IRQ %d for %s\n", ret, name); - ret = devm_request_threaded_irq(priv->dev, ret, NULL, handler, IRQF_ONESHOT, - name, priv); + ret = devm_request_threaded_irq(priv->dev, ret, NULL, handler, + IRQF_ONESHOT | flags, name, priv); if (ret) return dev_err_probe(priv->dev, ret, "Failed to request IRQ %s\n", name); @@ -2124,11 +2125,11 @@ static int cs42l43_shutter_irq(struct cs42l43_codec *priv, return 0; } - ret = cs42l43_request_irq(priv, dom, close_name, close_irq, handler); + ret = cs42l43_request_irq(priv, dom, close_name, close_irq, handler, IRQF_SHARED); if (ret) return ret; - return cs42l43_request_irq(priv, dom, open_name, open_irq, handler); + return cs42l43_request_irq(priv, dom, open_name, open_irq, handler, IRQF_SHARED); } static int cs42l43_codec_probe(struct platform_device *pdev) @@ -2178,7 +2179,8 @@ static int cs42l43_codec_probe(struct platform_device *pdev) for (i = 0; i < ARRAY_SIZE(cs42l43_irqs); i++) { ret = cs42l43_request_irq(priv, dom, cs42l43_irqs[i].name, - cs42l43_irqs[i].irq, cs42l43_irqs[i].handler); + cs42l43_irqs[i].irq, + cs42l43_irqs[i].handler, 0); if (ret) goto err_pm; } diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index 15e1a62b9e57..e8cdc166bdaa 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -2403,13 +2403,11 @@ static irqreturn_t rt5640_irq(int irq, void *data) struct rt5640_priv *rt5640 = data; int delay = 0; - if (rt5640->jd_src == RT5640_JD_SRC_HDA_HEADER) { - cancel_delayed_work_sync(&rt5640->jack_work); + if (rt5640->jd_src == RT5640_JD_SRC_HDA_HEADER) delay = 100; - } if (rt5640->jack) - queue_delayed_work(system_long_wq, &rt5640->jack_work, delay); + mod_delayed_work(system_long_wq, &rt5640->jack_work, delay); return IRQ_HANDLED; } @@ -2565,10 +2563,9 @@ static void rt5640_enable_jack_detect(struct snd_soc_component *component, if (jack_data && jack_data->use_platform_clock) rt5640->use_platform_clock = jack_data->use_platform_clock; - ret = devm_request_threaded_irq(component->dev, rt5640->irq, - NULL, rt5640_irq, - IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, - "rt5640", rt5640); + ret = request_irq(rt5640->irq, rt5640_irq, + IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + "rt5640", rt5640); if (ret) { dev_warn(component->dev, "Failed to request IRQ %d: %d\n", rt5640->irq, ret); rt5640_disable_jack_detect(component); @@ -2621,14 +2618,14 @@ static void rt5640_enable_hda_jack_detect( rt5640->jack = jack; - ret = devm_request_threaded_irq(component->dev, rt5640->irq, - NULL, rt5640_irq, IRQF_TRIGGER_RISING | IRQF_ONESHOT, - "rt5640", rt5640); + ret = request_irq(rt5640->irq, rt5640_irq, + IRQF_TRIGGER_RISING | IRQF_ONESHOT, "rt5640", rt5640); if (ret) { dev_warn(component->dev, "Failed to request IRQ %d: %d\n", rt5640->irq, ret); - rt5640->irq = -ENXIO; + rt5640->jack = NULL; return; } + rt5640->irq_requested = true; /* sync initial jack state */ queue_delayed_work(system_long_wq, &rt5640->jack_work, 0); @@ -2801,12 +2798,12 @@ static int rt5640_suspend(struct snd_soc_component *component) { struct rt5640_priv *rt5640 = snd_soc_component_get_drvdata(component); - if (rt5640->irq) { + if (rt5640->jack) { /* disable jack interrupts during system suspend */ disable_irq(rt5640->irq); + rt5640_cancel_work(rt5640); } - rt5640_cancel_work(rt5640); snd_soc_component_force_bias_level(component, SND_SOC_BIAS_OFF); rt5640_reset(component); regcache_cache_only(rt5640->regmap, true); @@ -2829,9 +2826,6 @@ static int rt5640_resume(struct snd_soc_component *component) regcache_cache_only(rt5640->regmap, false); regcache_sync(rt5640->regmap); - if (rt5640->irq) - enable_irq(rt5640->irq); - if (rt5640->jack) { if (rt5640->jd_src == RT5640_JD_SRC_HDA_HEADER) { snd_soc_component_update_bits(component, @@ -2859,6 +2853,7 @@ static int rt5640_resume(struct snd_soc_component *component) } } + enable_irq(rt5640->irq); queue_delayed_work(system_long_wq, &rt5640->jack_work, 0); } diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c index 0a50180750e8..7689fe3cc86d 100644 --- a/sound/soc/codecs/wm8960.c +++ b/sound/soc/codecs/wm8960.c @@ -1468,8 +1468,10 @@ static int wm8960_i2c_probe(struct i2c_client *i2c) } wm8960->regmap = devm_regmap_init_i2c(i2c, &wm8960_regmap); - if (IS_ERR(wm8960->regmap)) - return PTR_ERR(wm8960->regmap); + if (IS_ERR(wm8960->regmap)) { + ret = PTR_ERR(wm8960->regmap); + goto bulk_disable; + } if (pdata) memcpy(&wm8960->pdata, pdata, sizeof(struct wm8960_data)); @@ -1479,13 +1481,14 @@ static int wm8960_i2c_probe(struct i2c_client *i2c) ret = i2c_master_recv(i2c, &val, sizeof(val)); if (ret >= 0) { dev_err(&i2c->dev, "Not wm8960, wm8960 reg can not read by i2c\n"); - return -EINVAL; + ret = -EINVAL; + goto bulk_disable; } ret = wm8960_reset(wm8960->regmap); if (ret != 0) { dev_err(&i2c->dev, "Failed to issue reset\n"); - return ret; + goto bulk_disable; } if (wm8960->pdata.shared_lrclk) { @@ -1494,7 +1497,7 @@ static int wm8960_i2c_probe(struct i2c_client *i2c) if (ret != 0) { dev_err(&i2c->dev, "Failed to enable LRCM: %d\n", ret); - return ret; + goto bulk_disable; } } @@ -1528,7 +1531,13 @@ static int wm8960_i2c_probe(struct i2c_client *i2c) ret = devm_snd_soc_register_component(&i2c->dev, &soc_component_dev_wm8960, &wm8960_dai, 1); + if (ret) + goto bulk_disable; + return 0; + +bulk_disable: + regulator_bulk_disable(ARRAY_SIZE(wm8960->supplies), wm8960->supplies); return ret; } diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 6fc34f41b175..d1b9238d391e 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -687,7 +687,10 @@ int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name, int type, struct wm_coeff_ctl *ctl; int ret; + mutex_lock(&dsp->cs_dsp.pwr_lock); ret = cs_dsp_coeff_write_ctrl(cs_ctl, 0, buf, len); + mutex_unlock(&dsp->cs_dsp.pwr_lock); + if (ret < 0) return ret; @@ -703,8 +706,14 @@ EXPORT_SYMBOL_GPL(wm_adsp_write_ctl); int wm_adsp_read_ctl(struct wm_adsp *dsp, const char *name, int type, unsigned int alg, void *buf, size_t len) { - return cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg), - 0, buf, len); + int ret; + + mutex_lock(&dsp->cs_dsp.pwr_lock); + ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg), + 0, buf, len); + mutex_unlock(&dsp->cs_dsp.pwr_lock); + + return ret; } EXPORT_SYMBOL_GPL(wm_adsp_read_ctl); diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-audmix.c index 0b58df56f4da..aeb81aa61184 100644 --- a/sound/soc/fsl/imx-audmix.c +++ b/sound/soc/fsl/imx-audmix.c @@ -315,7 +315,7 @@ static int imx_audmix_probe(struct platform_device *pdev) if (IS_ERR(priv->cpu_mclk)) { ret = PTR_ERR(priv->cpu_mclk); dev_err(&cpu_pdev->dev, "failed to get DAI mclk1: %d\n", ret); - return -EINVAL; + return ret; } priv->audmix_pdev = audmix_pdev; diff --git a/sound/soc/fsl/imx-pcm-rpmsg.c b/sound/soc/fsl/imx-pcm-rpmsg.c index d63782b8bdef..bb736d45c9e0 100644 --- a/sound/soc/fsl/imx-pcm-rpmsg.c +++ b/sound/soc/fsl/imx-pcm-rpmsg.c @@ -19,6 +19,7 @@ static struct snd_pcm_hardware imx_rpmsg_pcm_hardware = { .info = SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_BLOCK_TRANSFER | + SNDRV_PCM_INFO_BATCH | SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_MMAP_VALID | SNDRV_PCM_INFO_NO_PERIOD_WAKEUP | diff --git a/sound/soc/fsl/imx-rpmsg.c b/sound/soc/fsl/imx-rpmsg.c index 3c7b95db2eac..b578f9a32d7f 100644 --- a/sound/soc/fsl/imx-rpmsg.c +++ b/sound/soc/fsl/imx-rpmsg.c @@ -89,6 +89,14 @@ static int imx_rpmsg_probe(struct platform_device *pdev) SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBC_CFC; + /* + * i.MX rpmsg sound cards work on codec slave mode. MCLK will be + * disabled by CPU DAI driver in hw_free(). Some codec requires MCLK + * present at power up/down sequence. So need to set ignore_pmdown_time + * to power down codec immediately before MCLK is turned off. + */ + data->dai.ignore_pmdown_time = 1; + /* Optional codec node */ ret = of_parse_phandle_with_fixed_args(np, "audio-codec", 0, 0, &args); if (ret) { diff --git a/sound/soc/intel/avs/boards/hdaudio.c b/sound/soc/intel/avs/boards/hdaudio.c index cb00bc86ac94..8876558f19a1 100644 --- a/sound/soc/intel/avs/boards/hdaudio.c +++ b/sound/soc/intel/avs/boards/hdaudio.c @@ -55,6 +55,9 @@ static int avs_create_dai_links(struct device *dev, struct hda_codec *codec, int return -ENOMEM; dl[i].codecs->name = devm_kstrdup(dev, cname, GFP_KERNEL); + if (!dl[i].codecs->name) + return -ENOMEM; + dl[i].codecs->dai_name = pcm->name; dl[i].num_codecs = 1; dl[i].num_cpus = 1; diff --git a/sound/soc/meson/axg-spdifin.c b/sound/soc/meson/axg-spdifin.c index d86880169075..bc2f2849ecfb 100644 --- a/sound/soc/meson/axg-spdifin.c +++ b/sound/soc/meson/axg-spdifin.c @@ -112,34 +112,6 @@ static int axg_spdifin_prepare(struct snd_pcm_substream *substream, return 0; } -static int axg_spdifin_startup(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); - int ret; - - ret = clk_prepare_enable(priv->refclk); - if (ret) { - dev_err(dai->dev, - "failed to enable spdifin reference clock\n"); - return ret; - } - - regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, - SPDIFIN_CTRL0_EN); - - return 0; -} - -static void axg_spdifin_shutdown(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); - - regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, 0); - clk_disable_unprepare(priv->refclk); -} - static void axg_spdifin_write_mode_param(struct regmap *map, int mode, unsigned int val, unsigned int num_per_reg, @@ -251,17 +223,32 @@ static int axg_spdifin_dai_probe(struct snd_soc_dai *dai) ret = axg_spdifin_sample_mode_config(dai, priv); if (ret) { dev_err(dai->dev, "mode configuration failed\n"); - clk_disable_unprepare(priv->pclk); - return ret; + goto pclk_err; } + ret = clk_prepare_enable(priv->refclk); + if (ret) { + dev_err(dai->dev, + "failed to enable spdifin reference clock\n"); + goto pclk_err; + } + + regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, + SPDIFIN_CTRL0_EN); + return 0; + +pclk_err: + clk_disable_unprepare(priv->pclk); + return ret; } static int axg_spdifin_dai_remove(struct snd_soc_dai *dai) { struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); + regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, 0); + clk_disable_unprepare(priv->refclk); clk_disable_unprepare(priv->pclk); return 0; } @@ -270,8 +257,6 @@ static const struct snd_soc_dai_ops axg_spdifin_ops = { .probe = axg_spdifin_dai_probe, .remove = axg_spdifin_dai_remove, .prepare = axg_spdifin_prepare, - .startup = axg_spdifin_startup, - .shutdown = axg_spdifin_shutdown, }; static int axg_spdifin_iec958_info(struct snd_kcontrol *kcontrol, diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index e29c2fee9521..1bd7114c472a 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -1303,6 +1303,7 @@ audio_graph: if (i >= RSND_MAX_COMPONENT) { dev_info(dev, "reach to max component\n"); of_node_put(node); + of_node_put(ports); break; } } diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index eb0723876851..54704250c0a2 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -985,6 +985,7 @@ static int __soc_pcm_hw_params(struct snd_soc_pcm_runtime *rtd, { struct snd_soc_dai *cpu_dai; struct snd_soc_dai *codec_dai; + struct snd_pcm_hw_params tmp_params; int i, ret = 0; snd_soc_dpcm_mutex_assert_held(rtd); @@ -998,7 +999,6 @@ static int __soc_pcm_hw_params(struct snd_soc_pcm_runtime *rtd, goto out; for_each_rtd_codec_dais(rtd, i, codec_dai) { - struct snd_pcm_hw_params codec_params; unsigned int tdm_mask = snd_soc_dai_tdm_mask_get(codec_dai, substream->stream); /* @@ -1019,23 +1019,22 @@ static int __soc_pcm_hw_params(struct snd_soc_pcm_runtime *rtd, continue; /* copy params for each codec */ - codec_params = *params; + tmp_params = *params; /* fixup params based on TDM slot masks */ if (tdm_mask) - soc_pcm_codec_params_fixup(&codec_params, tdm_mask); + soc_pcm_codec_params_fixup(&tmp_params, tdm_mask); ret = snd_soc_dai_hw_params(codec_dai, substream, - &codec_params); + &tmp_params); if(ret < 0) goto out; - soc_pcm_set_dai_params(codec_dai, &codec_params); - snd_soc_dapm_update_dai(substream, &codec_params, codec_dai); + soc_pcm_set_dai_params(codec_dai, &tmp_params); + snd_soc_dapm_update_dai(substream, &tmp_params, codec_dai); } for_each_rtd_cpu_dais(rtd, i, cpu_dai) { - struct snd_pcm_hw_params cpu_params; unsigned int ch_mask = 0; int j; @@ -1047,7 +1046,7 @@ static int __soc_pcm_hw_params(struct snd_soc_pcm_runtime *rtd, continue; /* copy params for each cpu */ - cpu_params = *params; + tmp_params = *params; if (!rtd->dai_link->codec_ch_maps) goto hw_params; @@ -1062,16 +1061,16 @@ static int __soc_pcm_hw_params(struct snd_soc_pcm_runtime *rtd, /* fixup cpu channel number */ if (ch_mask) - soc_pcm_codec_params_fixup(&cpu_params, ch_mask); + soc_pcm_codec_params_fixup(&tmp_params, ch_mask); hw_params: - ret = snd_soc_dai_hw_params(cpu_dai, substream, &cpu_params); + ret = snd_soc_dai_hw_params(cpu_dai, substream, &tmp_params); if (ret < 0) goto out; /* store the parameters for each DAI */ - soc_pcm_set_dai_params(cpu_dai, &cpu_params); - snd_soc_dapm_update_dai(substream, &cpu_params, cpu_dai); + soc_pcm_set_dai_params(cpu_dai, &tmp_params); + snd_soc_dapm_update_dai(substream, &tmp_params, cpu_dai); } ret = snd_soc_pcm_component_hw_params(substream, params); diff --git a/sound/soc/soc-utils.c b/sound/soc/soc-utils.c index 11607c5f5d5a..9c746e4edef7 100644 --- a/sound/soc/soc-utils.c +++ b/sound/soc/soc-utils.c @@ -217,6 +217,7 @@ int snd_soc_dai_is_dummy(struct snd_soc_dai *dai) return 1; return 0; } +EXPORT_SYMBOL_GPL(snd_soc_dai_is_dummy); int snd_soc_component_is_dummy(struct snd_soc_component *component) { diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c index 30db685cc5f4..2d1616b81485 100644 --- a/sound/soc/sof/core.c +++ b/sound/soc/sof/core.c @@ -486,10 +486,9 @@ int snd_sof_device_remove(struct device *dev) snd_sof_ipc_free(sdev); snd_sof_free_debug(sdev); snd_sof_remove(sdev); + sof_ops_free(sdev); } - sof_ops_free(sdev); - /* release firmware */ snd_sof_fw_unload(sdev); diff --git a/sound/soc/sof/intel/mtl.c b/sound/soc/sof/intel/mtl.c index b84ca58da9d5..f9412517eaf2 100644 --- a/sound/soc/sof/intel/mtl.c +++ b/sound/soc/sof/intel/mtl.c @@ -460,7 +460,7 @@ int mtl_dsp_cl_init(struct snd_sof_dev *sdev, int stream_tag, bool imr_boot) /* step 3: wait for IPC DONE bit from ROM */ ret = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR, chip->ipc_ack, status, ((status & chip->ipc_ack_mask) == chip->ipc_ack_mask), - HDA_DSP_REG_POLL_INTERVAL_US, MTL_DSP_PURGE_TIMEOUT_US); + HDA_DSP_REG_POLL_INTERVAL_US, HDA_DSP_INIT_TIMEOUT_US); if (ret < 0) { if (hda->boot_iteration == HDA_FW_BOOT_ATTEMPTS) dev_err(sdev->dev, "timeout waiting for purge IPC done\n"); diff --git a/sound/soc/sof/intel/mtl.h b/sound/soc/sof/intel/mtl.h index 02181490f12a..95696b3d7c4c 100644 --- a/sound/soc/sof/intel/mtl.h +++ b/sound/soc/sof/intel/mtl.h @@ -62,7 +62,6 @@ #define MTL_DSP_IRQSTS_IPC BIT(0) #define MTL_DSP_IRQSTS_SDW BIT(6) -#define MTL_DSP_PURGE_TIMEOUT_US 20000000 /* 20s */ #define MTL_DSP_REG_POLL_INTERVAL_US 10 /* 10 us */ /* Memory windows */ diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index f2a30cd31378..7cb63e6b24dc 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -231,7 +231,7 @@ static int sof_ipc4_get_audio_fmt(struct snd_soc_component *scomp, ret = sof_update_ipc_object(scomp, available_fmt, SOF_AUDIO_FMT_NUM_TOKENS, swidget->tuples, - swidget->num_tuples, sizeof(available_fmt), 1); + swidget->num_tuples, sizeof(*available_fmt), 1); if (ret) { dev_err(scomp->dev, "Failed to parse audio format token count\n"); return ret; diff --git a/sound/soc/sof/sof-audio.c b/sound/soc/sof/sof-audio.c index e7ef77012c35..e5405f854a91 100644 --- a/sound/soc/sof/sof-audio.c +++ b/sound/soc/sof/sof-audio.c @@ -212,7 +212,8 @@ widget_free: sof_widget_free_unlocked(sdev, swidget); use_count_decremented = true; core_put: - snd_sof_dsp_core_put(sdev, swidget->core); + if (!use_count_decremented) + snd_sof_dsp_core_put(sdev, swidget->core); pipe_widget_free: if (swidget->id != snd_soc_dapm_scheduler) sof_widget_free_unlocked(sdev, swidget->spipe->pipe_widget); diff --git a/sound/soc/tegra/tegra_audio_graph_card.c b/sound/soc/tegra/tegra_audio_graph_card.c index 1f2c5018bf5a..4737e776d383 100644 --- a/sound/soc/tegra/tegra_audio_graph_card.c +++ b/sound/soc/tegra/tegra_audio_graph_card.c @@ -10,6 +10,7 @@ #include <linux/platform_device.h> #include <sound/graph_card.h> #include <sound/pcm_params.h> +#include <sound/soc-dai.h> #define MAX_PLLA_OUT0_DIV 128 @@ -44,6 +45,21 @@ struct tegra_audio_cdata { unsigned int plla_out0_rates[NUM_RATE_TYPE]; }; +static bool need_clk_update(struct snd_soc_dai *dai) +{ + if (snd_soc_dai_is_dummy(dai) || + !dai->driver->ops || + !dai->driver->name) + return false; + + if (strstr(dai->driver->name, "I2S") || + strstr(dai->driver->name, "DMIC") || + strstr(dai->driver->name, "DSPK")) + return true; + + return false; +} + /* Setup PLL clock as per the given sample rate */ static int tegra_audio_graph_update_pll(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) @@ -140,19 +156,7 @@ static int tegra_audio_graph_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0); int err; - /* - * This gets called for each DAI link (FE or BE) when DPCM is used. - * We may not want to update PLLA rate for each call. So PLLA update - * must be restricted to external I/O links (I2S, DMIC or DSPK) since - * they actually depend on it. I/O modules update their clocks in - * hw_param() of their respective component driver and PLLA rate - * update here helps them to derive appropriate rates. - * - * TODO: When more HW accelerators get added (like sample rate - * converter, volume gain controller etc., which don't really - * depend on PLLA) we need a better way to filter here. - */ - if (cpu_dai->driver->ops && rtd->dai_link->no_pcm) { + if (need_clk_update(cpu_dai)) { err = tegra_audio_graph_update_pll(substream, params); if (err) return err; diff --git a/sound/usb/caiaq/device.c b/sound/usb/caiaq/device.c index 49f63f878e6f..b5cbf1f195c4 100644 --- a/sound/usb/caiaq/device.c +++ b/sound/usb/caiaq/device.c @@ -485,7 +485,7 @@ static int init_card(struct snd_usb_caiaqdev *cdev) } usb_make_path(usb_dev, usbpath, sizeof(usbpath)); - snprintf(card->longname, sizeof(card->longname), "%s %s (%s)", + scnprintf(card->longname, sizeof(card->longname), "%s %s (%s)", cdev->vendor_name, cdev->product_name, usbpath); setup_card(cdev); diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 9105ec623120..985b1aea9cdc 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1929,7 +1929,6 @@ static int parse_clock_source_unit(struct mixer_build *state, int unitid, struct uac_clock_source_descriptor *hdr = _ftr; struct usb_mixer_elem_info *cval; struct snd_kcontrol *kctl; - char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; int ret; if (state->mixer->protocol != UAC_VERSION_2) @@ -1966,10 +1965,9 @@ static int parse_clock_source_unit(struct mixer_build *state, int unitid, kctl->private_free = snd_usb_mixer_elem_free; ret = snd_usb_copy_string_desc(state->chip, hdr->iClockSource, - name, sizeof(name)); + kctl->id.name, sizeof(kctl->id.name)); if (ret > 0) - snprintf(kctl->id.name, sizeof(kctl->id.name), - "%s Validity", name); + append_ctl_name(kctl, " Validity"); else snprintf(kctl->id.name, sizeof(kctl->id.name), "Clock Source %d Validity", hdr->bClockID); diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c index 9d11bb08667e..d260be8cb6bc 100644 --- a/sound/usb/mixer_scarlett_gen2.c +++ b/sound/usb/mixer_scarlett_gen2.c @@ -3205,8 +3205,8 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer) /* Add input phantom controls */ if (info->inputs_per_phantom == 1) { for (i = 0; i < info->phantom_count; i++) { - snprintf(s, sizeof(s), fmt, i + 1, - "Phantom Power", "Switch"); + scnprintf(s, sizeof(s), fmt, i + 1, + "Phantom Power", "Switch"); err = scarlett2_add_new_ctl( mixer, &scarlett2_phantom_ctl, i, 1, s, &private->phantom_ctls[i]); @@ -3218,8 +3218,8 @@ static int scarlett2_add_line_in_ctls(struct usb_mixer_interface *mixer) int from = i * info->inputs_per_phantom + 1; int to = (i + 1) * info->inputs_per_phantom; - snprintf(s, sizeof(s), fmt2, from, to, - "Phantom Power", "Switch"); + scnprintf(s, sizeof(s), fmt2, from, to, + "Phantom Power", "Switch"); err = scarlett2_add_new_ctl( mixer, &scarlett2_phantom_ctl, i, 1, s, &private->phantom_ctls[i]); diff --git a/sound/xen/xen_snd_front_cfg.c b/sound/xen/xen_snd_front_cfg.c index 63b0398c3276..55ecf766ca67 100644 --- a/sound/xen/xen_snd_front_cfg.c +++ b/sound/xen/xen_snd_front_cfg.c @@ -483,7 +483,7 @@ int xen_snd_front_cfg_card(struct xen_snd_front_info *front_info, *stream_cnt = 0; num_devices = 0; do { - snprintf(node, sizeof(node), "%d", num_devices); + scnprintf(node, sizeof(node), "%d", num_devices); if (!xenbus_exists(XBT_NIL, xb_dev->nodename, node)) break; diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h index 71e54b1e3796..2f882d5cb30f 100644 --- a/tools/include/linux/btf_ids.h +++ b/tools/include/linux/btf_ids.h @@ -38,7 +38,7 @@ asm( \ ____BTF_ID(symbol) #define __ID(prefix) \ - __PASTE(prefix, __COUNTER__) + __PASTE(__PASTE(prefix, __COUNTER__), __LINE__) /* * The BTF_ID defines unique symbol for each ID pointing diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h index a03d9bba5151..f3c82ab5b14c 100644 --- a/tools/include/linux/mm.h +++ b/tools/include/linux/mm.h @@ -11,8 +11,6 @@ #define PHYS_ADDR_MAX (~(phys_addr_t)0) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) -#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) #define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) @@ -29,7 +27,7 @@ static inline void *phys_to_virt(unsigned long address) return __va(address); } -void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); +void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid); static inline void totalram_pages_inc(void) { diff --git a/tools/include/linux/seq_file.h b/tools/include/linux/seq_file.h index 102fd9217f1f..f6bc226af0c1 100644 --- a/tools/include/linux/seq_file.h +++ b/tools/include/linux/seq_file.h @@ -1,4 +1,6 @@ #ifndef _TOOLS_INCLUDE_LINUX_SEQ_FILE_H #define _TOOLS_INCLUDE_LINUX_SEQ_FILE_H +struct seq_file; + #endif /* _TOOLS_INCLUDE_LINUX_SEQ_FILE_H */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 8790b3962e4b..0448700890f7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1962,7 +1962,9 @@ union bpf_attr { * performed again, if the helper is used in combination with * direct packet access. * Return - * 0 on success, or a negative error in case of failure. + * 0 on success, or a negative error in case of failure. Positive + * error indicates a potential drop or congestion in the target + * device. The particular positive error codes are not defined. * * u64 bpf_get_current_pid_tgid(void) * Description diff --git a/tools/testing/memblock/internal.h b/tools/testing/memblock/internal.h index fdb7f5db7308..f6c6e5474c3a 100644 --- a/tools/testing/memblock/internal.h +++ b/tools/testing/memblock/internal.h @@ -20,4 +20,8 @@ void memblock_free_pages(struct page *page, unsigned long pfn, { } +static inline void accept_memory(phys_addr_t start, phys_addr_t end) +{ +} + #endif diff --git a/tools/testing/memblock/mmzone.c b/tools/testing/memblock/mmzone.c index 7b0909e8b759..d3d58851864e 100644 --- a/tools/testing/memblock/mmzone.c +++ b/tools/testing/memblock/mmzone.c @@ -11,7 +11,7 @@ struct pglist_data *next_online_pgdat(struct pglist_data *pgdat) return NULL; } -void reserve_bootmem_region(phys_addr_t start, phys_addr_t end) +void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid) { } diff --git a/tools/testing/memblock/tests/basic_api.c b/tools/testing/memblock/tests/basic_api.c index 411647094cc3..57bf2688edfd 100644 --- a/tools/testing/memblock/tests/basic_api.c +++ b/tools/testing/memblock/tests/basic_api.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later +#include "basic_api.h" #include <string.h> #include <linux/memblock.h> -#include "basic_api.h" #define EXPECTED_MEMBLOCK_REGIONS 128 #define FUNC_ADD "memblock_add" diff --git a/tools/testing/memblock/tests/common.h b/tools/testing/memblock/tests/common.h index 4f23302ee677..b5ec59aa62d7 100644 --- a/tools/testing/memblock/tests/common.h +++ b/tools/testing/memblock/tests/common.h @@ -5,6 +5,7 @@ #include <stdlib.h> #include <assert.h> #include <linux/types.h> +#include <linux/seq_file.h> #include <linux/memblock.h> #include <linux/sizes.h> #include <linux/printk.h> diff --git a/tools/testing/selftests/alsa/conf.c b/tools/testing/selftests/alsa/conf.c index d7aafe5a1993..2f1685a3eae1 100644 --- a/tools/testing/selftests/alsa/conf.c +++ b/tools/testing/selftests/alsa/conf.c @@ -431,7 +431,6 @@ long conf_get_long(snd_config_t *root, const char *key1, const char *key2, long int conf_get_bool(snd_config_t *root, const char *key1, const char *key2, int def) { snd_config_t *cfg; - long l; int ret; if (!root) diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c index c95d63e553f4..21e482b23f50 100644 --- a/tools/testing/selftests/alsa/mixer-test.c +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -188,7 +188,7 @@ static int wait_for_event(struct ctl_data *ctl, int timeout) { unsigned short revents; snd_ctl_event_t *event; - int count, err; + int err; unsigned int mask = 0; unsigned int ev_id; @@ -430,7 +430,6 @@ static bool strend(const char *haystack, const char *needle) static void test_ctl_name(struct ctl_data *ctl) { bool name_ok = true; - bool check; ksft_print_msg("%d.%d %s\n", ctl->card->card, ctl->elem, ctl->name); @@ -863,7 +862,6 @@ static bool test_ctl_write_invalid_value(struct ctl_data *ctl, snd_ctl_elem_value_t *val) { int err; - long val_read; /* Ideally this will fail... */ err = snd_ctl_elem_write(ctl->card->handle, val); @@ -883,8 +881,7 @@ static bool test_ctl_write_invalid_value(struct ctl_data *ctl, static bool test_ctl_write_invalid_boolean(struct ctl_data *ctl) { - int err, i; - long val_read; + int i; bool fail = false; snd_ctl_elem_value_t *val; snd_ctl_elem_value_alloca(&val); @@ -994,8 +991,7 @@ static bool test_ctl_write_invalid_integer64(struct ctl_data *ctl) static bool test_ctl_write_invalid_enumerated(struct ctl_data *ctl) { - int err, i; - unsigned int val_read; + int i; bool fail = false; snd_ctl_elem_value_t *val; snd_ctl_elem_value_alloca(&val); @@ -1027,7 +1023,6 @@ static bool test_ctl_write_invalid_enumerated(struct ctl_data *ctl) static void test_ctl_write_invalid(struct ctl_data *ctl) { bool pass; - int err; /* If the control is turned off let's be polite */ if (snd_ctl_elem_info_is_inactive(ctl->info)) { diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c index 2f5e3c462194..c0a39818c5a4 100644 --- a/tools/testing/selftests/alsa/pcm-test.c +++ b/tools/testing/selftests/alsa/pcm-test.c @@ -257,7 +257,7 @@ static void find_pcms(void) static void test_pcm_time(struct pcm_data *data, enum test_class class, const char *test_name, snd_config_t *pcm_cfg) { - char name[64], key[128], msg[256]; + char name[64], msg[256]; const int duration_s = 2, margin_ms = 100; const int duration_ms = duration_s * 1000; const char *cs; @@ -567,7 +567,7 @@ int main(void) { struct card_data *card; struct pcm_data *pcm; - snd_config_t *global_config, *cfg, *pcm_cfg; + snd_config_t *global_config, *cfg; int num_pcm_tests = 0, num_tests, num_std_pcm_tests; int ret; void *thread_ret; diff --git a/tools/testing/selftests/alsa/test-pcmtest-driver.c b/tools/testing/selftests/alsa/test-pcmtest-driver.c index 357adc722cba..a52ecd43dbe3 100644 --- a/tools/testing/selftests/alsa/test-pcmtest-driver.c +++ b/tools/testing/selftests/alsa/test-pcmtest-driver.c @@ -313,7 +313,6 @@ TEST_F(pcmtest, ni_playback) { */ TEST_F(pcmtest, reset_ioctl) { snd_pcm_t *handle; - unsigned char *it; int test_res; struct pcmtest_test_params *params = &self->params; diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 7f768d335698..3babaf3eee5c 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -1,14 +1,8 @@ bpf_cookie/multi_kprobe_attach_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 bpf_cookie/multi_kprobe_link_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 fexit_sleep # The test never returns. The remaining tests cannot start. -kprobe_multi_bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -kprobe_multi_test/attach_api_addrs # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -kprobe_multi_test/attach_api_pattern # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -kprobe_multi_test/attach_api_syms # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -kprobe_multi_test/bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -kprobe_multi_test/link_api_addrs # link_fd unexpected link_fd: actual -95 < expected 0 -kprobe_multi_test/link_api_syms # link_fd unexpected link_fd: actual -95 < expected 0 -kprobe_multi_test/skel_api # libbpf: failed to load BPF skeleton 'kprobe_multi': -3 +kprobe_multi_bench_attach # needs CONFIG_FPROBE +kprobe_multi_test # needs CONFIG_FPROBE module_attach # prog 'kprobe_multi': failed to auto-attach: -95 fentry_test/fentry_many_args # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524 fexit_test/fexit_many_args # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524 diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 1c7584e8dd9e..e41eb33b2704 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -4,6 +4,7 @@ CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y CONFIG_BPF=y CONFIG_BPF_EVENTS=y CONFIG_BPF_JIT=y +CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_BPF_LIRC_MODE2=y CONFIG_BPF_LSM=y CONFIG_BPF_STREAM_PARSER=y diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64 index b650b2e617b8..2e70a6048278 100644 --- a/tools/testing/selftests/bpf/config.x86_64 +++ b/tools/testing/selftests/bpf/config.x86_64 @@ -20,7 +20,6 @@ CONFIG_BLK_DEV_THROTTLING=y CONFIG_BONDING=y CONFIG_BOOTTIME_TRACING=y CONFIG_BPF_JIT_ALWAYS_ON=y -CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_BPF_PRELOAD=y CONFIG_BPF_PRELOAD_UMD=y CONFIG_BPFILTER=y diff --git a/tools/testing/selftests/bpf/prog_tests/empty_skb.c b/tools/testing/selftests/bpf/prog_tests/empty_skb.c index 3b77d8a422db..261228eb68e8 100644 --- a/tools/testing/selftests/bpf/prog_tests/empty_skb.c +++ b/tools/testing/selftests/bpf/prog_tests/empty_skb.c @@ -24,6 +24,7 @@ void test_empty_skb(void) int *ifindex; int err; int ret; + int lwt_egress_ret; /* expected retval at lwt/egress */ bool success_on_tc; } tests[] = { /* Empty packets are always rejected. */ @@ -57,6 +58,7 @@ void test_empty_skb(void) .data_size_in = sizeof(eth_hlen), .ifindex = &veth_ifindex, .ret = -ERANGE, + .lwt_egress_ret = -ERANGE, .success_on_tc = true, }, { @@ -70,6 +72,7 @@ void test_empty_skb(void) .data_size_in = sizeof(eth_hlen), .ifindex = &ipip_ifindex, .ret = -ERANGE, + .lwt_egress_ret = -ERANGE, }, /* ETH_HLEN+1-sized packet should be redirected. */ @@ -79,6 +82,7 @@ void test_empty_skb(void) .data_in = eth_hlen_pp, .data_size_in = sizeof(eth_hlen_pp), .ifindex = &veth_ifindex, + .lwt_egress_ret = 1, /* veth_xmit NET_XMIT_DROP */ }, { .msg = "ipip ETH_HLEN+1 packet ingress", @@ -108,8 +112,12 @@ void test_empty_skb(void) for (i = 0; i < ARRAY_SIZE(tests); i++) { bpf_object__for_each_program(prog, bpf_obj->obj) { - char buf[128]; + bool at_egress = strstr(bpf_program__name(prog), "egress") != NULL; bool at_tc = !strncmp(bpf_program__section_name(prog), "tc", 2); + int expected_ret; + char buf[128]; + + expected_ret = at_egress && !at_tc ? tests[i].lwt_egress_ret : tests[i].ret; tattr.data_in = tests[i].data_in; tattr.data_size_in = tests[i].data_size_in; @@ -128,7 +136,7 @@ void test_empty_skb(void) if (at_tc && tests[i].success_on_tc) ASSERT_GE(bpf_obj->bss->ret, 0, buf); else - ASSERT_EQ(bpf_obj->bss->ret, tests[i].ret, buf); + ASSERT_EQ(bpf_obj->bss->ret, expected_ret, buf); } } diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index 179fe300534f..4041cfa670eb 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -3,6 +3,7 @@ #include "kprobe_multi.skel.h" #include "trace_helpers.h" #include "kprobe_multi_empty.skel.h" +#include "kprobe_multi_override.skel.h" #include "bpf/libbpf_internal.h" #include "bpf/hashmap.h" @@ -453,6 +454,40 @@ cleanup: } } +static void test_attach_override(void) +{ + struct kprobe_multi_override *skel = NULL; + struct bpf_link *link = NULL; + + skel = kprobe_multi_override__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kprobe_multi_empty__open_and_load")) + goto cleanup; + + /* The test_override calls bpf_override_return so it should fail + * to attach to bpf_fentry_test1 function, which is not on error + * injection list. + */ + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_override, + "bpf_fentry_test1", NULL); + if (!ASSERT_ERR_PTR(link, "override_attached_bpf_fentry_test1")) { + bpf_link__destroy(link); + goto cleanup; + } + + /* The should_fail_bio function is on error injection list, + * attach should succeed. + */ + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_override, + "should_fail_bio", NULL); + if (!ASSERT_OK_PTR(link, "override_attached_should_fail_bio")) + goto cleanup; + + bpf_link__destroy(link); + +cleanup: + kprobe_multi_override__destroy(skel); +} + void serial_test_kprobe_multi_bench_attach(void) { if (test__start_subtest("kernel")) @@ -480,4 +515,6 @@ void test_kprobe_multi_test(void) test_attach_api_syms(); if (test__start_subtest("attach_api_fails")) test_attach_api_fails(); + if (test__start_subtest("attach_override")) + test_attach_override(); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c new file mode 100644 index 000000000000..0cca4e8ae38e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#define _GNU_SOURCE +#include <sched.h> +#include <pthread.h> +#include <stdbool.h> +#include <bpf/btf.h> +#include <test_progs.h> + +#include "test_bpf_ma.skel.h" + +void test_test_bpf_ma(void) +{ + struct test_bpf_ma *skel; + struct btf *btf; + int i, err; + + skel = test_bpf_ma__open(); + if (!ASSERT_OK_PTR(skel, "open")) + return; + + btf = bpf_object__btf(skel->obj); + if (!ASSERT_OK_PTR(btf, "btf")) + goto out; + + for (i = 0; i < ARRAY_SIZE(skel->rodata->data_sizes); i++) { + char name[32]; + int id; + + snprintf(name, sizeof(name), "bin_data_%u", skel->rodata->data_sizes[i]); + id = btf__find_by_name_kind(btf, name, BTF_KIND_STRUCT); + if (!ASSERT_GT(id, 0, "bin_data")) + goto out; + skel->rodata->data_btf_ids[i] = id; + } + + err = test_bpf_ma__load(skel); + if (!ASSERT_OK(err, "load")) + goto out; + + err = test_bpf_ma__attach(skel); + if (!ASSERT_OK(err, "attach")) + goto out; + + skel->bss->pid = getpid(); + usleep(1); + ASSERT_OK(skel->bss->err, "test error"); +out: + test_bpf_ma__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_dev_bound_only.c b/tools/testing/selftests/bpf/prog_tests/xdp_dev_bound_only.c new file mode 100644 index 000000000000..7dd18c6d06c6 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_dev_bound_only.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <net/if.h> +#include <test_progs.h> +#include <network_helpers.h> + +#define LOCAL_NETNS "xdp_dev_bound_only_netns" + +static int load_dummy_prog(char *name, __u32 ifindex, __u32 flags) +{ + struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN() }; + LIBBPF_OPTS(bpf_prog_load_opts, opts); + + opts.prog_flags = flags; + opts.prog_ifindex = ifindex; + return bpf_prog_load(BPF_PROG_TYPE_XDP, name, "GPL", insns, ARRAY_SIZE(insns), &opts); +} + +/* A test case for bpf_offload_netdev->offload handling bug: + * - create a veth device (does not support offload); + * - create a device bound XDP program with BPF_F_XDP_DEV_BOUND_ONLY flag + * (such programs are not offloaded); + * - create a device bound XDP program without flags (such programs are offloaded). + * This might lead to 'BUG: kernel NULL pointer dereference'. + */ +void test_xdp_dev_bound_only_offdev(void) +{ + struct nstoken *tok = NULL; + __u32 ifindex; + int fd1 = -1; + int fd2 = -1; + + SYS(out, "ip netns add " LOCAL_NETNS); + tok = open_netns(LOCAL_NETNS); + if (!ASSERT_OK_PTR(tok, "open_netns")) + goto out; + SYS(out, "ip link add eth42 type veth"); + ifindex = if_nametoindex("eth42"); + if (!ASSERT_NEQ(ifindex, 0, "if_nametoindex")) { + perror("if_nametoindex"); + goto out; + } + fd1 = load_dummy_prog("dummy1", ifindex, BPF_F_XDP_DEV_BOUND_ONLY); + if (!ASSERT_GE(fd1, 0, "load_dummy_prog #1")) { + perror("load_dummy_prog #1"); + goto out; + } + /* Program with ifindex is considered offloaded, however veth + * does not support offload => error should be reported. + */ + fd2 = load_dummy_prog("dummy2", ifindex, 0); + ASSERT_EQ(fd2, -EINVAL, "load_dummy_prog #2 (offloaded)"); + +out: + close(fd1); + close(fd2); + close_netns(tok); + /* eth42 was added inside netns, removing the netns will + * also remove eth42 veth pair. + */ + SYS_NOFAIL("ip netns del " LOCAL_NETNS); +} diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_override.c b/tools/testing/selftests/bpf/progs/kprobe_multi_override.c new file mode 100644 index 000000000000..28f8487c9059 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kprobe_multi_override.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("kprobe.multi") +int test_override(struct pt_regs *ctx) +{ + bpf_override_return(ctx, 123); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c new file mode 100644 index 000000000000..ecde41ae0fc8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_experimental.h" +#include "bpf_misc.h" + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +struct generic_map_value { + void *data; +}; + +char _license[] SEC("license") = "GPL"; + +const unsigned int data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096}; +const volatile unsigned int data_btf_ids[ARRAY_SIZE(data_sizes)] = {}; + +int err = 0; +int pid = 0; + +#define DEFINE_ARRAY_WITH_KPTR(_size) \ + struct bin_data_##_size { \ + char data[_size - sizeof(void *)]; \ + }; \ + struct map_value_##_size { \ + struct bin_data_##_size __kptr * data; \ + /* To emit BTF info for bin_data_xx */ \ + struct bin_data_##_size not_used; \ + }; \ + struct { \ + __uint(type, BPF_MAP_TYPE_ARRAY); \ + __type(key, int); \ + __type(value, struct map_value_##_size); \ + __uint(max_entries, 128); \ + } array_##_size SEC(".maps"); + +static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int batch, + unsigned int idx) +{ + struct generic_map_value *value; + unsigned int i, key; + void *old, *new; + + for (i = 0; i < batch; i++) { + key = i; + value = bpf_map_lookup_elem(map, &key); + if (!value) { + err = 1; + return; + } + new = bpf_obj_new_impl(data_btf_ids[idx], NULL); + if (!new) { + err = 2; + return; + } + old = bpf_kptr_xchg(&value->data, new); + if (old) { + bpf_obj_drop(old); + err = 3; + return; + } + } + for (i = 0; i < batch; i++) { + key = i; + value = bpf_map_lookup_elem(map, &key); + if (!value) { + err = 4; + return; + } + old = bpf_kptr_xchg(&value->data, NULL); + if (!old) { + err = 5; + return; + } + bpf_obj_drop(old); + } +} + +#define CALL_BATCH_ALLOC_FREE(size, batch, idx) \ + batch_alloc_free((struct bpf_map *)(&array_##size), batch, idx) + +DEFINE_ARRAY_WITH_KPTR(8); +DEFINE_ARRAY_WITH_KPTR(16); +DEFINE_ARRAY_WITH_KPTR(32); +DEFINE_ARRAY_WITH_KPTR(64); +DEFINE_ARRAY_WITH_KPTR(96); +DEFINE_ARRAY_WITH_KPTR(128); +DEFINE_ARRAY_WITH_KPTR(192); +DEFINE_ARRAY_WITH_KPTR(256); +DEFINE_ARRAY_WITH_KPTR(512); +DEFINE_ARRAY_WITH_KPTR(1024); +DEFINE_ARRAY_WITH_KPTR(2048); +DEFINE_ARRAY_WITH_KPTR(4096); + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int test_bpf_mem_alloc_free(void *ctx) +{ + if ((u32)bpf_get_current_pid_tgid() != pid) + return 0; + + /* Alloc 128 8-bytes objects in batch to trigger refilling, + * then free 128 8-bytes objects in batch to trigger freeing. + */ + CALL_BATCH_ALLOC_FREE(8, 128, 0); + CALL_BATCH_ALLOC_FREE(16, 128, 1); + CALL_BATCH_ALLOC_FREE(32, 128, 2); + CALL_BATCH_ALLOC_FREE(64, 128, 3); + CALL_BATCH_ALLOC_FREE(96, 128, 4); + CALL_BATCH_ALLOC_FREE(128, 128, 5); + CALL_BATCH_ALLOC_FREE(192, 128, 6); + CALL_BATCH_ALLOC_FREE(256, 128, 7); + CALL_BATCH_ALLOC_FREE(512, 64, 8); + CALL_BATCH_ALLOC_FREE(1024, 32, 9); + CALL_BATCH_ALLOC_FREE(2048, 16, 10); + CALL_BATCH_ALLOC_FREE(4096, 8, 11); + + return 0; +} diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 31f1c935cd07..98107e0452d3 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -1880,7 +1880,7 @@ int main(int argc, char **argv) } } - get_unpriv_disabled(); + unpriv_disabled = get_unpriv_disabled(); if (unpriv && unpriv_disabled) { printf("Cannot run as unprivileged user with sysctl %s.\n", UNPRIV_SYSCTL); diff --git a/tools/testing/selftests/fchmodat2/Makefile b/tools/testing/selftests/fchmodat2/Makefile index 20839f8e43f2..71ec34bf1501 100644 --- a/tools/testing/selftests/fchmodat2/Makefile +++ b/tools/testing/selftests/fchmodat2/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-or-later -CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined $(KHDR_INCLUDES) +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan $(KHDR_INCLUDES) TEST_GEN_PROGS := fchmodat2_test include ../lib.mk diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index 47bb914ab2fa..9a3be80e8bc9 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -135,8 +135,8 @@ static void guest_at(void) uint64_t par; asm volatile("at s1e1r, %0" :: "r" (guest_test_memory)); - par = read_sysreg(par_el1); isb(); + par = read_sysreg(par_el1); /* Bit 1 indicates whether the AT was successful */ GUEST_ASSERT_EQ(par & 1, 0); @@ -842,6 +842,7 @@ static void help(char *name) .name = SCAT2(ro_memslot_no_syndrome, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ .pt_memslot_flags = KVM_MEM_READONLY, \ + .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \ .expected_events = { .fail_vcpu_runs = 1 }, \ @@ -865,6 +866,7 @@ static void help(char *name) .name = SCAT2(ro_memslot_no_syn_and_dlog, _access), \ .data_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ .pt_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ + .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .guest_test_check = { _test_check }, \ .fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \ @@ -894,6 +896,7 @@ static void help(char *name) .data_memslot_flags = KVM_MEM_READONLY, \ .pt_memslot_flags = KVM_MEM_READONLY, \ .mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \ + .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .uffd_data_handler = _uffd_data_handler, \ .uffd_pt_handler = uffd_pt_handler, \ diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 3e36019eeb4a..5d7f28b02d73 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -387,7 +387,7 @@ char *strdup_printf(const char *fmt, ...) char *str; va_start(ap, fmt); - vasprintf(&str, fmt, ap); + TEST_ASSERT(vasprintf(&str, fmt, ap) >= 0, "vasprintf() failed"); va_end(ap); return str; diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index d8ecacd03ecf..9f99ea42f45f 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -12,19 +12,37 @@ #define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK) +static bool isa_ext_cant_disable[KVM_RISCV_ISA_EXT_MAX]; + bool filter_reg(__u64 reg) { + switch (reg & ~REG_MASK) { /* - * Some ISA extensions are optional and not present on all host, - * but they can't be disabled through ISA_EXT registers when present. - * So, to make life easy, just filtering out these kind of registers. + * Same set of ISA_EXT registers are not present on all host because + * ISA_EXT registers are visible to the KVM user space based on the + * ISA extensions available on the host. Also, disabling an ISA + * extension using corresponding ISA_EXT register does not affect + * the visibility of the ISA_EXT register itself. + * + * Based on above, we should filter-out all ISA_EXT registers. */ - switch (reg & ~REG_MASK) { + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_A: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_C: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_D: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_F: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_H: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_I: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_M: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVPBMT: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOM: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOZ: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_V: + case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVNAPOT: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR: @@ -32,6 +50,15 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI: case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM: return true; + /* AIA registers are always available when Ssaia can't be disabled */ + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siselect): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio2): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(sieh): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siph): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1h): + case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio2h): + return isa_ext_cant_disable[KVM_RISCV_ISA_EXT_SSAIA]; default: break; } @@ -50,24 +77,27 @@ static inline bool vcpu_has_ext(struct kvm_vcpu *vcpu, int ext) unsigned long value; ret = __vcpu_get_reg(vcpu, RISCV_ISA_EXT_REG(ext), &value); - if (ret) { - printf("Failed to get ext %d", ext); - return false; - } - - return !!value; + return (ret) ? false : !!value; } void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) { + unsigned long isa_ext_state[KVM_RISCV_ISA_EXT_MAX] = { 0 }; struct vcpu_reg_sublist *s; + int rc; + + for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) + __vcpu_get_reg(vcpu, RISCV_ISA_EXT_REG(i), &isa_ext_state[i]); /* * Disable all extensions which were enabled by default * if they were available in the risc-v host. */ - for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) - __vcpu_set_reg(vcpu, RISCV_ISA_EXT_REG(i), 0); + for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) { + rc = __vcpu_set_reg(vcpu, RISCV_ISA_EXT_REG(i), 0); + if (rc && isa_ext_state[i]) + isa_ext_cant_disable[i] = true; + } for_each_sublist(c, s) { if (!s->feature) @@ -506,10 +536,6 @@ static __u64 base_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(time), KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(compare), KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state), - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_A, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_C, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_I, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_M, KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01, KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME, KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI, diff --git a/tools/testing/selftests/net/hsr/hsr_ping.sh b/tools/testing/selftests/net/hsr/hsr_ping.sh index df9143538708..1c6457e54625 100755 --- a/tools/testing/selftests/net/hsr/hsr_ping.sh +++ b/tools/testing/selftests/net/hsr/hsr_ping.sh @@ -41,61 +41,6 @@ cleanup() done } -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi - -trap cleanup EXIT - -for i in "$ns1" "$ns2" "$ns3" ;do - ip netns add $i || exit $ksft_skip - ip -net $i link set lo up -done - -echo "INFO: preparing interfaces." -# Three HSR nodes. Each node has one link to each of its neighbour, two links in total. -# -# ns1eth1 ----- ns2eth1 -# hsr1 hsr2 -# ns1eth2 ns2eth2 -# | | -# ns3eth1 ns3eth2 -# \ / -# hsr3 -# -# Interfaces -ip link add ns1eth1 netns "$ns1" type veth peer name ns2eth1 netns "$ns2" -ip link add ns1eth2 netns "$ns1" type veth peer name ns3eth1 netns "$ns3" -ip link add ns3eth2 netns "$ns3" type veth peer name ns2eth2 netns "$ns2" - -# HSRv0. -ip -net "$ns1" link add name hsr1 type hsr slave1 ns1eth1 slave2 ns1eth2 supervision 45 version 0 proto 0 -ip -net "$ns2" link add name hsr2 type hsr slave1 ns2eth1 slave2 ns2eth2 supervision 45 version 0 proto 0 -ip -net "$ns3" link add name hsr3 type hsr slave1 ns3eth1 slave2 ns3eth2 supervision 45 version 0 proto 0 - -# IP for HSR -ip -net "$ns1" addr add 100.64.0.1/24 dev hsr1 -ip -net "$ns1" addr add dead:beef:1::1/64 dev hsr1 nodad -ip -net "$ns2" addr add 100.64.0.2/24 dev hsr2 -ip -net "$ns2" addr add dead:beef:1::2/64 dev hsr2 nodad -ip -net "$ns3" addr add 100.64.0.3/24 dev hsr3 -ip -net "$ns3" addr add dead:beef:1::3/64 dev hsr3 nodad - -# All Links up -ip -net "$ns1" link set ns1eth1 up -ip -net "$ns1" link set ns1eth2 up -ip -net "$ns1" link set hsr1 up - -ip -net "$ns2" link set ns2eth1 up -ip -net "$ns2" link set ns2eth2 up -ip -net "$ns2" link set hsr2 up - -ip -net "$ns3" link set ns3eth1 up -ip -net "$ns3" link set ns3eth2 up -ip -net "$ns3" link set hsr3 up - # $1: IP address is_v6() { @@ -164,93 +109,168 @@ stop_if_error() fi } - -echo "INFO: Initial validation ping." -# Each node has to be able each one. -do_ping "$ns1" 100.64.0.2 -do_ping "$ns2" 100.64.0.1 -do_ping "$ns3" 100.64.0.1 -stop_if_error "Initial validation failed." - -do_ping "$ns1" 100.64.0.3 -do_ping "$ns2" 100.64.0.3 -do_ping "$ns3" 100.64.0.2 - -do_ping "$ns1" dead:beef:1::2 -do_ping "$ns1" dead:beef:1::3 -do_ping "$ns2" dead:beef:1::1 -do_ping "$ns2" dead:beef:1::2 -do_ping "$ns3" dead:beef:1::1 -do_ping "$ns3" dead:beef:1::2 - -stop_if_error "Initial validation failed." +do_complete_ping_test() +{ + echo "INFO: Initial validation ping." + # Each node has to be able each one. + do_ping "$ns1" 100.64.0.2 + do_ping "$ns2" 100.64.0.1 + do_ping "$ns3" 100.64.0.1 + stop_if_error "Initial validation failed." + + do_ping "$ns1" 100.64.0.3 + do_ping "$ns2" 100.64.0.3 + do_ping "$ns3" 100.64.0.2 + + do_ping "$ns1" dead:beef:1::2 + do_ping "$ns1" dead:beef:1::3 + do_ping "$ns2" dead:beef:1::1 + do_ping "$ns2" dead:beef:1::2 + do_ping "$ns3" dead:beef:1::1 + do_ping "$ns3" dead:beef:1::2 + + stop_if_error "Initial validation failed." # Wait until supervisor all supervision frames have been processed and the node # entries have been merged. Otherwise duplicate frames will be observed which is # valid at this stage. -WAIT=5 -while [ ${WAIT} -gt 0 ] -do - grep 00:00:00:00:00:00 /sys/kernel/debug/hsr/hsr*/node_table - if [ $? -ne 0 ] - then - break - fi - sleep 1 - let WAIT = WAIT - 1 -done + WAIT=5 + while [ ${WAIT} -gt 0 ] + do + grep 00:00:00:00:00:00 /sys/kernel/debug/hsr/hsr*/node_table + if [ $? -ne 0 ] + then + break + fi + sleep 1 + let "WAIT = WAIT - 1" + done # Just a safety delay in case the above check didn't handle it. -sleep 1 + sleep 1 + + echo "INFO: Longer ping test." + do_ping_long "$ns1" 100.64.0.2 + do_ping_long "$ns1" dead:beef:1::2 + do_ping_long "$ns1" 100.64.0.3 + do_ping_long "$ns1" dead:beef:1::3 -echo "INFO: Longer ping test." -do_ping_long "$ns1" 100.64.0.2 -do_ping_long "$ns1" dead:beef:1::2 -do_ping_long "$ns1" 100.64.0.3 -do_ping_long "$ns1" dead:beef:1::3 + stop_if_error "Longer ping test failed." -stop_if_error "Longer ping test failed." + do_ping_long "$ns2" 100.64.0.1 + do_ping_long "$ns2" dead:beef:1::1 + do_ping_long "$ns2" 100.64.0.3 + do_ping_long "$ns2" dead:beef:1::2 + stop_if_error "Longer ping test failed." -do_ping_long "$ns2" 100.64.0.1 -do_ping_long "$ns2" dead:beef:1::1 -do_ping_long "$ns2" 100.64.0.3 -do_ping_long "$ns2" dead:beef:1::2 -stop_if_error "Longer ping test failed." + do_ping_long "$ns3" 100.64.0.1 + do_ping_long "$ns3" dead:beef:1::1 + do_ping_long "$ns3" 100.64.0.2 + do_ping_long "$ns3" dead:beef:1::2 + stop_if_error "Longer ping test failed." -do_ping_long "$ns3" 100.64.0.1 -do_ping_long "$ns3" dead:beef:1::1 -do_ping_long "$ns3" 100.64.0.2 -do_ping_long "$ns3" dead:beef:1::2 -stop_if_error "Longer ping test failed." + echo "INFO: Cutting one link." + do_ping_long "$ns1" 100.64.0.3 & -echo "INFO: Cutting one link." -do_ping_long "$ns1" 100.64.0.3 & + sleep 3 + ip -net "$ns3" link set ns3eth1 down + wait -sleep 3 -ip -net "$ns3" link set ns3eth1 down -wait + ip -net "$ns3" link set ns3eth1 up -ip -net "$ns3" link set ns3eth1 up + stop_if_error "Failed with one link down." -stop_if_error "Failed with one link down." + echo "INFO: Delay the link and drop a few packages." + tc -net "$ns3" qdisc add dev ns3eth1 root netem delay 50ms + tc -net "$ns2" qdisc add dev ns2eth1 root netem delay 5ms loss 25% -echo "INFO: Delay the link and drop a few packages." -tc -net "$ns3" qdisc add dev ns3eth1 root netem delay 50ms -tc -net "$ns2" qdisc add dev ns2eth1 root netem delay 5ms loss 25% + do_ping_long "$ns1" 100.64.0.2 + do_ping_long "$ns1" 100.64.0.3 -do_ping_long "$ns1" 100.64.0.2 -do_ping_long "$ns1" 100.64.0.3 + stop_if_error "Failed with delay and packetloss." -stop_if_error "Failed with delay and packetloss." + do_ping_long "$ns2" 100.64.0.1 + do_ping_long "$ns2" 100.64.0.3 -do_ping_long "$ns2" 100.64.0.1 -do_ping_long "$ns2" 100.64.0.3 + stop_if_error "Failed with delay and packetloss." -stop_if_error "Failed with delay and packetloss." + do_ping_long "$ns3" 100.64.0.1 + do_ping_long "$ns3" 100.64.0.2 + stop_if_error "Failed with delay and packetloss." + + echo "INFO: All good." +} + +setup_hsr_interfaces() +{ + local HSRv="$1" + + echo "INFO: preparing interfaces for HSRv${HSRv}." +# Three HSR nodes. Each node has one link to each of its neighbour, two links in total. +# +# ns1eth1 ----- ns2eth1 +# hsr1 hsr2 +# ns1eth2 ns2eth2 +# | | +# ns3eth1 ns3eth2 +# \ / +# hsr3 +# + # Interfaces + ip link add ns1eth1 netns "$ns1" type veth peer name ns2eth1 netns "$ns2" + ip link add ns1eth2 netns "$ns1" type veth peer name ns3eth1 netns "$ns3" + ip link add ns3eth2 netns "$ns3" type veth peer name ns2eth2 netns "$ns2" + + # HSRv0/1 + ip -net "$ns1" link add name hsr1 type hsr slave1 ns1eth1 slave2 ns1eth2 supervision 45 version $HSRv proto 0 + ip -net "$ns2" link add name hsr2 type hsr slave1 ns2eth1 slave2 ns2eth2 supervision 45 version $HSRv proto 0 + ip -net "$ns3" link add name hsr3 type hsr slave1 ns3eth1 slave2 ns3eth2 supervision 45 version $HSRv proto 0 + + # IP for HSR + ip -net "$ns1" addr add 100.64.0.1/24 dev hsr1 + ip -net "$ns1" addr add dead:beef:1::1/64 dev hsr1 nodad + ip -net "$ns2" addr add 100.64.0.2/24 dev hsr2 + ip -net "$ns2" addr add dead:beef:1::2/64 dev hsr2 nodad + ip -net "$ns3" addr add 100.64.0.3/24 dev hsr3 + ip -net "$ns3" addr add dead:beef:1::3/64 dev hsr3 nodad + + # All Links up + ip -net "$ns1" link set ns1eth1 up + ip -net "$ns1" link set ns1eth2 up + ip -net "$ns1" link set hsr1 up + + ip -net "$ns2" link set ns2eth1 up + ip -net "$ns2" link set ns2eth2 up + ip -net "$ns2" link set hsr2 up + + ip -net "$ns3" link set ns3eth1 up + ip -net "$ns3" link set ns3eth2 up + ip -net "$ns3" link set hsr3 up +} + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +trap cleanup EXIT + +for i in "$ns1" "$ns2" "$ns3" ;do + ip netns add $i || exit $ksft_skip + ip -net $i link set lo up +done + +setup_hsr_interfaces 0 +do_complete_ping_test +cleanup + +for i in "$ns1" "$ns2" "$ns3" ;do + ip netns add $i || exit $ksft_skip + ip -net $i link set lo up +done -do_ping_long "$ns3" 100.64.0.1 -do_ping_long "$ns3" 100.64.0.2 -stop_if_error "Failed with delay and packetloss." +setup_hsr_interfaces 1 +do_complete_ping_test -echo "INFO: All good." exit $ret diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 297d972558fb..464853a7f982 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -613,11 +613,11 @@ TEST_F(tls, sendmsg_large) msg.msg_iov = &vec; msg.msg_iovlen = 1; - EXPECT_EQ(sendmsg(self->cfd, &msg, 0), send_len); + EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); } while (recvs++ < sends) { - EXPECT_NE(recv(self->fd, mem, send_len, 0), -1); + EXPECT_NE(recv(self->cfd, mem, send_len, 0), -1); } free(mem); @@ -646,9 +646,9 @@ TEST_F(tls, sendmsg_multiple) msg.msg_iov = vec; msg.msg_iovlen = iov_len; - EXPECT_EQ(sendmsg(self->cfd, &msg, 0), total_len); + EXPECT_EQ(sendmsg(self->fd, &msg, 0), total_len); buf = malloc(total_len); - EXPECT_NE(recv(self->fd, buf, total_len, 0), -1); + EXPECT_NE(recv(self->cfd, buf, total_len, 0), -1); for (i = 0; i < iov_len; i++) { EXPECT_EQ(memcmp(test_strs[i], buf + len_cmp, strlen(test_strs[i])), diff --git a/tools/testing/selftests/netfilter/.gitignore b/tools/testing/selftests/netfilter/.gitignore index 4cb887b57413..4b2928e1c19d 100644 --- a/tools/testing/selftests/netfilter/.gitignore +++ b/tools/testing/selftests/netfilter/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only nf-queue connect_close +audit_logread diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 3686bfa6c58d..321db8850da0 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -6,13 +6,13 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ - conntrack_vrf.sh nft_synproxy.sh rpath.sh + conntrack_vrf.sh nft_synproxy.sh rpath.sh nft_audit.sh HOSTPKG_CONFIG := pkg-config CFLAGS += $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null) LDLIBS += $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) -TEST_GEN_FILES = nf-queue connect_close +TEST_GEN_FILES = nf-queue connect_close audit_logread include ../lib.mk diff --git a/tools/testing/selftests/netfilter/audit_logread.c b/tools/testing/selftests/netfilter/audit_logread.c new file mode 100644 index 000000000000..a0a880fc2d9d --- /dev/null +++ b/tools/testing/selftests/netfilter/audit_logread.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <poll.h> +#include <signal.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <unistd.h> +#include <linux/audit.h> +#include <linux/netlink.h> + +static int fd; + +#define MAX_AUDIT_MESSAGE_LENGTH 8970 +struct audit_message { + struct nlmsghdr nlh; + union { + struct audit_status s; + char data[MAX_AUDIT_MESSAGE_LENGTH]; + } u; +}; + +int audit_recv(int fd, struct audit_message *rep) +{ + struct sockaddr_nl addr; + socklen_t addrlen = sizeof(addr); + int ret; + + do { + ret = recvfrom(fd, rep, sizeof(*rep), 0, + (struct sockaddr *)&addr, &addrlen); + } while (ret < 0 && errno == EINTR); + + if (ret < 0 || + addrlen != sizeof(addr) || + addr.nl_pid != 0 || + rep->nlh.nlmsg_type == NLMSG_ERROR) /* short-cut for now */ + return -1; + + return ret; +} + +int audit_send(int fd, uint16_t type, uint32_t key, uint32_t val) +{ + static int seq = 0; + struct audit_message msg = { + .nlh = { + .nlmsg_len = NLMSG_SPACE(sizeof(msg.u.s)), + .nlmsg_type = type, + .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK, + .nlmsg_seq = ++seq, + }, + .u.s = { + .mask = key, + .enabled = key == AUDIT_STATUS_ENABLED ? val : 0, + .pid = key == AUDIT_STATUS_PID ? val : 0, + } + }; + struct sockaddr_nl addr = { + .nl_family = AF_NETLINK, + }; + int ret; + + do { + ret = sendto(fd, &msg, msg.nlh.nlmsg_len, 0, + (struct sockaddr *)&addr, sizeof(addr)); + } while (ret < 0 && errno == EINTR); + + if (ret != (int)msg.nlh.nlmsg_len) + return -1; + return 0; +} + +int audit_set(int fd, uint32_t key, uint32_t val) +{ + struct audit_message rep = { 0 }; + int ret; + + ret = audit_send(fd, AUDIT_SET, key, val); + if (ret) + return ret; + + ret = audit_recv(fd, &rep); + if (ret < 0) + return ret; + return 0; +} + +int readlog(int fd) +{ + struct audit_message rep = { 0 }; + int ret = audit_recv(fd, &rep); + const char *sep = ""; + char *k, *v; + + if (ret < 0) + return ret; + + if (rep.nlh.nlmsg_type != AUDIT_NETFILTER_CFG) + return 0; + + /* skip the initial "audit(...): " part */ + strtok(rep.u.data, " "); + + while ((k = strtok(NULL, "="))) { + v = strtok(NULL, " "); + + /* these vary and/or are uninteresting, ignore */ + if (!strcmp(k, "pid") || + !strcmp(k, "comm") || + !strcmp(k, "subj")) + continue; + + /* strip the varying sequence number */ + if (!strcmp(k, "table")) + *strchrnul(v, ':') = '\0'; + + printf("%s%s=%s", sep, k, v); + sep = " "; + } + if (*sep) { + printf("\n"); + fflush(stdout); + } + return 0; +} + +void cleanup(int sig) +{ + audit_set(fd, AUDIT_STATUS_ENABLED, 0); + close(fd); + if (sig) + exit(0); +} + +int main(int argc, char **argv) +{ + struct sigaction act = { + .sa_handler = cleanup, + }; + + fd = socket(PF_NETLINK, SOCK_RAW, NETLINK_AUDIT); + if (fd < 0) { + perror("Can't open netlink socket"); + return -1; + } + + if (sigaction(SIGTERM, &act, NULL) < 0 || + sigaction(SIGINT, &act, NULL) < 0) { + perror("Can't set signal handler"); + close(fd); + return -1; + } + + audit_set(fd, AUDIT_STATUS_ENABLED, 1); + audit_set(fd, AUDIT_STATUS_PID, getpid()); + + while (1) + readlog(fd); +} diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config index 4faf2ce021d9..7c42b1b2c69b 100644 --- a/tools/testing/selftests/netfilter/config +++ b/tools/testing/selftests/netfilter/config @@ -6,3 +6,4 @@ CONFIG_NFT_REDIR=m CONFIG_NFT_MASQ=m CONFIG_NFT_FLOW_OFFLOAD=m CONFIG_NF_CT_NETLINK=m +CONFIG_AUDIT=y diff --git a/tools/testing/selftests/netfilter/nft_audit.sh b/tools/testing/selftests/netfilter/nft_audit.sh new file mode 100755 index 000000000000..83c271b1c735 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_audit.sh @@ -0,0 +1,108 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Check that audit logs generated for nft commands are as expected. + +SKIP_RC=4 +RC=0 + +nft --version >/dev/null 2>&1 || { + echo "SKIP: missing nft tool" + exit $SKIP_RC +} + +logfile=$(mktemp) +echo "logging into $logfile" +./audit_logread >"$logfile" & +logread_pid=$! +trap 'kill $logread_pid; rm -f $logfile' EXIT +exec 3<"$logfile" + +do_test() { # (cmd, log) + echo -n "testing for cmd: $1 ... " + cat <&3 >/dev/null + $1 >/dev/null || exit 1 + sleep 0.1 + res=$(diff -a -u <(echo "$2") - <&3) + [ $? -eq 0 ] && { echo "OK"; return; } + echo "FAIL" + echo "$res" + ((RC++)) +} + +nft flush ruleset + +for table in t1 t2; do + do_test "nft add table $table" \ + "table=$table family=2 entries=1 op=nft_register_table" + + do_test "nft add chain $table c1" \ + "table=$table family=2 entries=1 op=nft_register_chain" + + do_test "nft add chain $table c2; add chain $table c3" \ + "table=$table family=2 entries=2 op=nft_register_chain" + + cmd="add rule $table c1 counter" + + do_test "nft $cmd" \ + "table=$table family=2 entries=1 op=nft_register_rule" + + do_test "nft $cmd; $cmd" \ + "table=$table family=2 entries=2 op=nft_register_rule" + + cmd="" + sep="" + for chain in c2 c3; do + for i in {1..3}; do + cmd+="$sep add rule $table $chain counter" + sep=";" + done + done + do_test "nft $cmd" \ + "table=$table family=2 entries=6 op=nft_register_rule" +done + +do_test 'nft reset rules t1 c2' \ +'table=t1 family=2 entries=3 op=nft_reset_rule' + +do_test 'nft reset rules table t1' \ +'table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule' + +do_test 'nft reset rules' \ +'table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule' + +for ((i = 0; i < 500; i++)); do + echo "add rule t2 c3 counter accept comment \"rule $i\"" +done | do_test 'nft -f -' \ +'table=t2 family=2 entries=500 op=nft_register_rule' + +do_test 'nft reset rules t2 c3' \ +'table=t2 family=2 entries=189 op=nft_reset_rule +table=t2 family=2 entries=188 op=nft_reset_rule +table=t2 family=2 entries=126 op=nft_reset_rule' + +do_test 'nft reset rules t2' \ +'table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=186 op=nft_reset_rule +table=t2 family=2 entries=188 op=nft_reset_rule +table=t2 family=2 entries=129 op=nft_reset_rule' + +do_test 'nft reset rules' \ +'table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule +table=t1 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=3 op=nft_reset_rule +table=t2 family=2 entries=180 op=nft_reset_rule +table=t2 family=2 entries=188 op=nft_reset_rule +table=t2 family=2 entries=135 op=nft_reset_rule' + +exit $RC diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile index 843ba56d8e49..254d676a2689 100644 --- a/tools/testing/selftests/openat2/Makefile +++ b/tools/testing/selftests/openat2/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-or-later -CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test include ../lib.mk diff --git a/tools/testing/selftests/proc/proc-empty-vm.c b/tools/testing/selftests/proc/proc-empty-vm.c index b16c13688b88..ee71ce52cb6a 100644 --- a/tools/testing/selftests/proc/proc-empty-vm.c +++ b/tools/testing/selftests/proc/proc-empty-vm.c @@ -267,6 +267,7 @@ static const char g_smaps_rollup[] = "Private_Dirty: 0 kB\n" "Referenced: 0 kB\n" "Anonymous: 0 kB\n" +"KSM: 0 kB\n" "LazyFree: 0 kB\n" "AnonHugePages: 0 kB\n" "ShmemPmdMapped: 0 kB\n" |