diff --git a/.mailmap b/.mailmap index 406b99f7ea8b..4a14ece4cdb7 100644 --- a/.mailmap +++ b/.mailmap @@ -29,6 +29,7 @@ Alexandre Belloni Alexei Starovoitov Alexei Starovoitov +Alex Hung Alex Shi Alex Shi Alex Shi @@ -382,6 +383,7 @@ Santosh Shilimkar Santosh Shilimkar Sarangdhar Joshi Sascha Hauer +Satya Priya S.Çağlar Onur Sean Christopherson Sean Nyekjaer diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index de70e5d0e76a..b25d51b36676 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6967,3 +6967,14 @@ memory, and other data can't be written using xmon commands. off xmon is disabled. + + amd_pstate= [X86] + disable + Do not enable amd_pstate as the default + scaling driver for the supported processors + passive + Use amd_pstate as a scaling driver, driver requests a + desired performance on this abstract scale and the power + management firmware translates the requests into actual + hardware states (core frequency, data fabric and memory + clocks etc.) diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst index 8f3d30c5a0d8..06e23538f79c 100644 --- a/Documentation/admin-guide/pm/amd-pstate.rst +++ b/Documentation/admin-guide/pm/amd-pstate.rst @@ -283,23 +283,19 @@ efficiency frequency management method on AMD processors. Kernel Module Options for ``amd-pstate`` ========================================= -.. _shared_mem: +Passive Mode +------------ -``shared_mem`` -Use a module param (shared_mem) to enable related processors manually with -**amd_pstate.shared_mem=1**. -Due to the performance issue on the processors with `Shared Memory Support -`_, we disable it presently and will re-enable this by default -once we address performance issue with this solution. +``amd_pstate=passive`` -To check whether the current processor is using `Full MSR Support `_ -or `Shared Memory Support `_ : :: - - ray@hr-test1:~$ lscpu | grep cppc - Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm - -If the CPU flags have ``cppc``, then this processor supports `Full MSR Support -`_. Otherwise, it supports `Shared Memory Support `_. +It will be enabled if the ``amd_pstate=passive`` is passed to the kernel in the command line. +In this mode, ``amd_pstate`` driver software specifies a desired QoS target in the CPPC +performance scale as a relative number. This can be expressed as percentage of nominal +performance (infrastructure max). Below the nominal sustained performance level, +desired performance expresses the average performance level of the processor subject +to the Performance Reduction Tolerance register. Above the nominal performance level, +processor must provide at least nominal performance requested and go higher if current +operating conditions allow. ``cpupower`` tool support for ``amd-pstate`` diff --git a/Documentation/devicetree/bindings/iio/adc/aspeed,ast2600-adc.yaml b/Documentation/devicetree/bindings/iio/adc/aspeed,ast2600-adc.yaml index b283c8ca2bbf..5c08d8b6e995 100644 --- a/Documentation/devicetree/bindings/iio/adc/aspeed,ast2600-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/aspeed,ast2600-adc.yaml @@ -62,13 +62,6 @@ properties: description: Inform the driver that last channel will be used to sensor battery. - aspeed,trim-data-valid: - type: boolean - description: | - The ADC reference voltage can be calibrated to obtain the trimming - data which will be stored in otp. This property informs the driver that - the data store in the otp is valid. - required: - compatible - reg diff --git a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml index 2684562df4d9..be29e0b80995 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml @@ -24,7 +24,7 @@ properties: oneOf: - items: - enum: - - qcom,sc7280-bwmon + - qcom,sc7280-cpu-bwmon - qcom,sdm845-bwmon - const: qcom,msm8998-bwmon - const: qcom,msm8998-bwmon # BWMON v4 diff --git a/MAINTAINERS b/MAINTAINERS index b1361fa628c2..18e9f33118c4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10294,7 +10294,7 @@ T: git https://github.com/intel/gvt-linux.git F: drivers/gpu/drm/i915/gvt/ INTEL HID EVENT DRIVER -M: Alex Hung +M: Alex Hung L: platform-driver-x86@vger.kernel.org S: Maintained F: drivers/platform/x86/intel/hid.c @@ -18018,7 +18018,7 @@ L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/fbdev/savage/ -S390 +S390 ARCHITECTURE M: Heiko Carstens M: Vasily Gorbik M: Alexander Gordeev @@ -18073,6 +18073,15 @@ L: netdev@vger.kernel.org S: Supported F: drivers/s390/net/ +S390 MM +M: Alexander Gordeev +M: Gerald Schaefer +L: linux-s390@vger.kernel.org +S: Supported +T: git git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux.git +F: arch/s390/include/asm/pgtable.h +F: arch/s390/mm + S390 PCI SUBSYSTEM M: Niklas Schnelle M: Gerald Schaefer diff --git a/Makefile b/Makefile index 12f170481dfb..e848c6ea248b 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/microblaze/Makefile b/arch/microblaze/Makefile index 3f8a86c4336a..02e6be9c5b0d 100644 --- a/arch/microblaze/Makefile +++ b/arch/microblaze/Makefile @@ -67,12 +67,12 @@ linux.bin.ub linux.bin.gz: linux.bin linux.bin: vmlinux linux.bin linux.bin.gz linux.bin.ub: $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ - @echo 'Kernel: $(boot)/$@ is ready' ' (#'`cat .version`')' + @echo 'Kernel: $(boot)/$@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')' PHONY += simpleImage.$(DTB) simpleImage.$(DTB): vmlinux $(Q)$(MAKE) $(build)=$(boot) $(addprefix $(boot)/$@., ub unstrip strip) - @echo 'Kernel: $(boot)/$@ is ready' ' (#'`cat .version`')' + @echo 'Kernel: $(boot)/$@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')' define archhelp echo '* linux.bin - Create raw binary' diff --git a/arch/nios2/boot/Makefile b/arch/nios2/boot/Makefile index 8c3ad76602f3..29c11a06b750 100644 --- a/arch/nios2/boot/Makefile +++ b/arch/nios2/boot/Makefile @@ -20,7 +20,7 @@ $(obj)/vmlinux.bin: vmlinux FORCE $(obj)/vmlinux.gz: $(obj)/vmlinux.bin FORCE $(call if_changed,gzip) -$(obj)/vmImage: $(obj)/vmlinux.gz +$(obj)/vmImage: $(obj)/vmlinux.gz FORCE $(call if_changed,uimage) @$(kecho) 'Kernel: $@ is ready' diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index dd74fe664ed1..e4ef67e4da0a 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -46,7 +46,7 @@ struct save_area { u64 fprs[16]; u32 fpc; u32 prefix; - u64 todpreg; + u32 todpreg; u64 timer; u64 todcmp; u64 vxrs_low[16]; diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 9860ca5979f8..9e38ffaadb5d 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -83,7 +83,7 @@ cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \ $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE $(call if_changed,image) - @$(kecho) 'Kernel: $@ is ready' ' (#'`cat .version`')' + @$(kecho) 'Kernel: $@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')' OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index f49bc3ec76e6..a269049a43ce 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -77,7 +77,7 @@ static int hyperv_init_ghcb(void) static int hv_cpu_init(unsigned int cpu) { union hv_vp_assist_msr_contents msr = { 0 }; - struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; + struct hv_vp_assist_page **hvp = &hv_vp_assist_page[cpu]; int ret; ret = hv_common_cpu_init(cpu); @@ -87,34 +87,32 @@ static int hv_cpu_init(unsigned int cpu) if (!hv_vp_assist_page) return 0; - if (!*hvp) { - if (hv_root_partition) { - /* - * For root partition we get the hypervisor provided VP assist - * page, instead of allocating a new page. - */ - rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); - *hvp = memremap(msr.pfn << - HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT, - PAGE_SIZE, MEMREMAP_WB); - } else { - /* - * The VP assist page is an "overlay" page (see Hyper-V TLFS's - * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed - * out to make sure we always write the EOI MSR in - * hv_apic_eoi_write() *after* the EOI optimization is disabled - * in hv_cpu_die(), otherwise a CPU may not be stopped in the - * case of CPU offlining and the VM will hang. - */ + if (hv_root_partition) { + /* + * For root partition we get the hypervisor provided VP assist + * page, instead of allocating a new page. + */ + rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); + *hvp = memremap(msr.pfn << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT, + PAGE_SIZE, MEMREMAP_WB); + } else { + /* + * The VP assist page is an "overlay" page (see Hyper-V TLFS's + * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed + * out to make sure we always write the EOI MSR in + * hv_apic_eoi_write() *after* the EOI optimization is disabled + * in hv_cpu_die(), otherwise a CPU may not be stopped in the + * case of CPU offlining and the VM will hang. + */ + if (!*hvp) *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO); - if (*hvp) - msr.pfn = vmalloc_to_pfn(*hvp); - } - WARN_ON(!(*hvp)); - if (*hvp) { - msr.enable = 1; - wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); - } + if (*hvp) + msr.pfn = vmalloc_to_pfn(*hvp); + + } + if (!WARN_ON(!(*hvp))) { + msr.enable = 1; + wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); } return hyperv_init_ghcb(); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index b71f4f2ecdd5..b2da7cb64b31 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -305,6 +305,9 @@ #define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ #define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ + +#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ + /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index ec7bbac3a9f2..8009c8346d8f 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -58,24 +58,6 @@ static void tsx_enable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -static bool tsx_ctrl_is_supported(void) -{ - u64 ia32_cap = x86_read_arch_cap_msr(); - - /* - * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this - * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. - * - * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a - * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES - * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get - * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, - * tsx= cmdline requests will do nothing on CPUs without - * MSR_IA32_TSX_CTRL support. - */ - return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR); -} - static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) { if (boot_cpu_has_bug(X86_BUG_TAA)) @@ -135,7 +117,7 @@ static void tsx_clear_cpuid(void) rdmsrl(MSR_TSX_FORCE_ABORT, msr); msr |= MSR_TFA_TSX_CPUID_CLEAR; wrmsrl(MSR_TSX_FORCE_ABORT, msr); - } else if (tsx_ctrl_is_supported()) { + } else if (cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL)) { rdmsrl(MSR_IA32_TSX_CTRL, msr); msr |= TSX_CTRL_CPUID_CLEAR; wrmsrl(MSR_IA32_TSX_CTRL, msr); @@ -158,7 +140,8 @@ static void tsx_dev_mode_disable(void) u64 mcu_opt_ctrl; /* Check if RTM_ALLOW exists */ - if (!boot_cpu_has_bug(X86_BUG_TAA) || !tsx_ctrl_is_supported() || + if (!boot_cpu_has_bug(X86_BUG_TAA) || + !cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL) || !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL)) return; @@ -191,7 +174,20 @@ void __init tsx_init(void) return; } - if (!tsx_ctrl_is_supported()) { + /* + * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this + * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. + * + * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a + * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES + * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get + * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, + * tsx= cmdline requests will do nothing on CPUs without + * MSR_IA32_TSX_CTRL support. + */ + if (x86_read_arch_cap_msr() & ARCH_CAP_TSX_CTRL_MSR) { + setup_force_cpu_cap(X86_FEATURE_MSR_TSX_CTRL); + } else { tsx_ctrl_state = TSX_CTRL_NOT_SUPPORTED; return; } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1ccb769f62af..b6f96d47e596 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2443,6 +2443,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, { bool list_unstable, zapped_root = false; + lockdep_assert_held_write(&kvm->mmu_lock); trace_kvm_mmu_prepare_zap_page(sp); ++kvm->stat.mmu_shadow_zapped; *nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list); @@ -4262,14 +4263,14 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; - r = make_mmu_pages_available(vcpu); - if (r) - goto out_unlock; - - if (is_tdp_mmu_fault) + if (is_tdp_mmu_fault) { r = kvm_tdp_mmu_map(vcpu, fault); - else + } else { + r = make_mmu_pages_available(vcpu); + if (r) + goto out_unlock; r = __direct_map(vcpu, fault); + } out_unlock: if (is_tdp_mmu_fault) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 4c620999d230..995bc0f90759 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1091,6 +1091,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm) static void nested_svm_triple_fault(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + + if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SHUTDOWN)) + return; + + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN); } @@ -1125,6 +1131,9 @@ void svm_free_nested(struct vcpu_svm *svm) if (!svm->nested.initialized) return; + if (WARN_ON_ONCE(svm->vmcb != svm->vmcb01.ptr)) + svm_switch_vmcb(svm, &svm->vmcb01); + svm_vcpu_free_msrpm(svm->nested.msrpm); svm->nested.msrpm = NULL; @@ -1143,9 +1152,6 @@ void svm_free_nested(struct vcpu_svm *svm) svm->nested.initialized = false; } -/* - * Forcibly leave nested mode in order to be able to reset the VCPU later on. - */ void svm_leave_nested(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 4b6d2b050e57..ce362e88a567 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -346,12 +346,6 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) return 0; } -static int is_external_interrupt(u32 info) -{ - info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; - return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR); -} - static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1438,6 +1432,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) */ svm_clear_current_vmcb(svm->vmcb); + svm_leave_nested(vcpu); svm_free_nested(svm); sev_free_vcpu(vcpu); @@ -3425,15 +3420,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 0; } - if (is_external_interrupt(svm->vmcb->control.exit_int_info) && - exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR && - exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH && - exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI) - printk(KERN_ERR "%s: unexpected exit_int_info 0x%x " - "exit_code 0x%x\n", - __func__, svm->vmcb->control.exit_int_info, - exit_code); - if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0c62352dda6a..5b0d4859e4b7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4854,6 +4854,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu) { + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); } @@ -6440,9 +6441,6 @@ out: return kvm_state.size; } -/* - * Forcibly leave nested mode in order to be able to reset the VCPU later on. - */ void vmx_leave_nested(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 490ec23c8450..2835bd796639 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -628,6 +628,12 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto ex->payload = payload; } +/* Forcibly leave the nested mode in cases like a vCPU reset */ +static void kvm_leave_nested(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops.nested_ops->leave_nested(vcpu); +} + static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error, u32 error_code, bool has_payload, unsigned long payload, bool reinject) @@ -5195,7 +5201,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, if (events->flags & KVM_VCPUEVENT_VALID_SMM) { if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { - kvm_x86_ops.nested_ops->leave_nested(vcpu); + kvm_leave_nested(vcpu); kvm_smm_changed(vcpu, events->smi.smm); } @@ -9805,7 +9811,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) int kvm_check_nested_events(struct kvm_vcpu *vcpu) { - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { kvm_x86_ops.nested_ops->triple_fault(vcpu); return 1; } @@ -10560,15 +10566,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 0; goto out; } - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { - if (is_guest_mode(vcpu)) { + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + if (is_guest_mode(vcpu)) kvm_x86_ops.nested_ops->triple_fault(vcpu); - } else { + + if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; vcpu->mmio_needed = 0; r = 0; - goto out; } + goto out; } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ @@ -11997,8 +12004,18 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) WARN_ON_ONCE(!init_event && (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu))); + /* + * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's + * possible to INIT the vCPU while L2 is active. Force the vCPU back + * into L1 as EFER.SVME is cleared on INIT (along with all other EFER + * bits), i.e. virtualization is disabled. + */ + if (is_guest_mode(vcpu)) + kvm_leave_nested(vcpu); + kvm_lapic_reset(vcpu, init_event); + WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu)); vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 2dae413bd62a..f3098c0e386a 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -954,6 +954,14 @@ static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu) return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result); } +static inline int max_evtchn_port(struct kvm *kvm) +{ + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) + return EVTCHN_2L_NR_CHANNELS; + else + return COMPAT_EVTCHN_2L_NR_CHANNELS; +} + static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports, evtchn_port_t *ports) { @@ -1042,6 +1050,10 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, *r = -EFAULT; goto out; } + if (ports[i] >= max_evtchn_port(vcpu->kvm)) { + *r = -EINVAL; + goto out; + } } if (sched_poll.nr_ports == 1) @@ -1215,6 +1227,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) bool longmode; u64 input, params[6], r = -ENOSYS; bool handled = false; + u8 cpl; input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX); @@ -1242,9 +1255,17 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) params[5] = (u64)kvm_r9_read(vcpu); } #endif + cpl = static_call(kvm_x86_get_cpl)(vcpu); trace_kvm_xen_hypercall(input, params[0], params[1], params[2], params[3], params[4], params[5]); + /* + * Only allow hypercall acceleration for CPL0. The rare hypercalls that + * are permitted in guest userspace can be handled by the VMM. + */ + if (unlikely(cpl > 0)) + goto handle_in_userspace; + switch (input) { case __HYPERVISOR_xen_version: if (params[0] == XENVER_version && vcpu->kvm->arch.xen.xen_version) { @@ -1279,10 +1300,11 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) if (handled) return kvm_xen_hypercall_set_result(vcpu, r); +handle_in_userspace: vcpu->run->exit_reason = KVM_EXIT_XEN; vcpu->run->xen.type = KVM_EXIT_XEN_HCALL; vcpu->run->xen.u.hcall.longmode = longmode; - vcpu->run->xen.u.hcall.cpl = static_call(kvm_x86_get_cpl)(vcpu); + vcpu->run->xen.u.hcall.cpl = cpl; vcpu->run->xen.u.hcall.input = input; vcpu->run->xen.u.hcall.params[0] = params[0]; vcpu->run->xen.u.hcall.params[1] = params[1]; @@ -1297,14 +1319,6 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) return 0; } -static inline int max_evtchn_port(struct kvm *kvm) -{ - if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) - return EVTCHN_2L_NR_CHANNELS; - else - return COMPAT_EVTCHN_2L_NR_CHANNELS; -} - static void kvm_xen_check_poller(struct kvm_vcpu *vcpu, int port) { int poll_evtchn = vcpu->arch.xen.poll_evtchn; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 78c5bc654cff..6453fbaedb08 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -217,9 +217,15 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, * Mappings have to be page-aligned */ offset = phys_addr & ~PAGE_MASK; - phys_addr &= PHYSICAL_PAGE_MASK; + phys_addr &= PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; + /* + * Mask out any bits not part of the actual physical + * address, like memory encryption bits. + */ + phys_addr &= PHYSICAL_PAGE_MASK; + retval = memtype_reserve(phys_addr, (u64)phys_addr + size, pcm, &new_pcm); if (retval) { diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 4cd39f304e20..93ae33248f42 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -513,16 +513,23 @@ static int pm_cpu_check(const struct x86_cpu_id *c) static void pm_save_spec_msr(void) { - u32 spec_msr_id[] = { - MSR_IA32_SPEC_CTRL, - MSR_IA32_TSX_CTRL, - MSR_TSX_FORCE_ABORT, - MSR_IA32_MCU_OPT_CTRL, - MSR_AMD64_LS_CFG, - MSR_AMD64_DE_CFG, + struct msr_enumeration { + u32 msr_no; + u32 feature; + } msr_enum[] = { + { MSR_IA32_SPEC_CTRL, X86_FEATURE_MSR_SPEC_CTRL }, + { MSR_IA32_TSX_CTRL, X86_FEATURE_MSR_TSX_CTRL }, + { MSR_TSX_FORCE_ABORT, X86_FEATURE_TSX_FORCE_ABORT }, + { MSR_IA32_MCU_OPT_CTRL, X86_FEATURE_SRBDS_CTRL }, + { MSR_AMD64_LS_CFG, X86_FEATURE_LS_CFG_SSBD }, + { MSR_AMD64_DE_CFG, X86_FEATURE_LFENCE_RDTSC }, }; + int i; - msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); + for (i = 0; i < ARRAY_SIZE(msr_enum); i++) { + if (boot_cpu_has(msr_enum[i].feature)) + msr_build_context(&msr_enum[i].msr_no, 1); + } } static int pm_check_save_msr(void) diff --git a/block/blk-mq.c b/block/blk-mq.c index 6a789cda68a5..228a6696d835 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4045,9 +4045,14 @@ EXPORT_SYMBOL(__blk_mq_alloc_disk); struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, struct lock_class_key *lkclass) { + struct gendisk *disk; + if (!blk_get_queue(q)) return NULL; - return __alloc_disk_node(q, NUMA_NO_NODE, lkclass); + disk = __alloc_disk_node(q, NUMA_NO_NODE, lkclass); + if (!disk) + blk_put_queue(q); + return disk; } EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue); diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index f96cb01e9604..e9de9d846b73 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -57,10 +57,8 @@ #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD) struct ublk_rq_data { - union { - struct callback_head work; - struct llist_node node; - }; + struct llist_node node; + struct callback_head work; }; struct ublk_uring_cmd_pdu { @@ -766,15 +764,31 @@ static inline void __ublk_rq_task_work(struct request *req) ubq_complete_io_cmd(io, UBLK_IO_RES_OK); } +static inline void ublk_forward_io_cmds(struct ublk_queue *ubq) +{ + struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); + struct ublk_rq_data *data, *tmp; + + io_cmds = llist_reverse_order(io_cmds); + llist_for_each_entry_safe(data, tmp, io_cmds, node) + __ublk_rq_task_work(blk_mq_rq_from_pdu(data)); +} + +static inline void ublk_abort_io_cmds(struct ublk_queue *ubq) +{ + struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); + struct ublk_rq_data *data, *tmp; + + llist_for_each_entry_safe(data, tmp, io_cmds, node) + __ublk_abort_rq(ubq, blk_mq_rq_from_pdu(data)); +} + static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd) { struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); struct ublk_queue *ubq = pdu->ubq; - struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); - struct ublk_rq_data *data; - llist_for_each_entry(data, io_cmds, node) - __ublk_rq_task_work(blk_mq_rq_from_pdu(data)); + ublk_forward_io_cmds(ubq); } static void ublk_rq_task_work_fn(struct callback_head *work) @@ -782,14 +796,20 @@ static void ublk_rq_task_work_fn(struct callback_head *work) struct ublk_rq_data *data = container_of(work, struct ublk_rq_data, work); struct request *req = blk_mq_rq_from_pdu(data); + struct ublk_queue *ubq = req->mq_hctx->driver_data; - __ublk_rq_task_work(req); + ublk_forward_io_cmds(ubq); } -static void ublk_submit_cmd(struct ublk_queue *ubq, const struct request *rq) +static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq) { - struct ublk_io *io = &ubq->ios[rq->tag]; + struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq); + struct ublk_io *io; + if (!llist_add(&data->node, &ubq->io_cmds)) + return; + + io = &ubq->ios[rq->tag]; /* * If the check pass, we know that this is a re-issued request aborted * previously in monitor_work because the ubq_daemon(cmd's task) is @@ -803,11 +823,11 @@ static void ublk_submit_cmd(struct ublk_queue *ubq, const struct request *rq) * guarantees that here is a re-issued request aborted previously. */ if (unlikely(io->flags & UBLK_IO_FLAG_ABORTED)) { - struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); - struct ublk_rq_data *data; - - llist_for_each_entry(data, io_cmds, node) - __ublk_abort_rq(ubq, blk_mq_rq_from_pdu(data)); + ublk_abort_io_cmds(ubq); + } else if (ublk_can_use_task_work(ubq)) { + if (task_work_add(ubq->ubq_daemon, &data->work, + TWA_SIGNAL_NO_IPI)) + ublk_abort_io_cmds(ubq); } else { struct io_uring_cmd *cmd = io->cmd; struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); @@ -817,23 +837,6 @@ static void ublk_submit_cmd(struct ublk_queue *ubq, const struct request *rq) } } -static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq, - bool last) -{ - struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq); - - if (ublk_can_use_task_work(ubq)) { - enum task_work_notify_mode notify_mode = last ? - TWA_SIGNAL_NO_IPI : TWA_NONE; - - if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode)) - __ublk_abort_rq(ubq, rq); - } else { - if (llist_add(&data->node, &ubq->io_cmds)) - ublk_submit_cmd(ubq, rq); - } -} - static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -865,19 +868,11 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } - ublk_queue_cmd(ubq, rq, bd->last); + ublk_queue_cmd(ubq, rq); return BLK_STS_OK; } -static void ublk_commit_rqs(struct blk_mq_hw_ctx *hctx) -{ - struct ublk_queue *ubq = hctx->driver_data; - - if (ublk_can_use_task_work(ubq)) - __set_notify_signal(ubq->ubq_daemon); -} - static int ublk_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data, unsigned int hctx_idx) { @@ -899,7 +894,6 @@ static int ublk_init_rq(struct blk_mq_tag_set *set, struct request *req, static const struct blk_mq_ops ublk_mq_ops = { .queue_rq = ublk_queue_rq, - .commit_rqs = ublk_commit_rqs, .init_hctx = ublk_init_hctx, .init_request = ublk_init_rq, }; @@ -1197,7 +1191,7 @@ static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id, struct ublk_queue *ubq = ublk_get_queue(ub, q_id); struct request *req = blk_mq_tag_to_rq(ub->tag_set.tags[q_id], tag); - ublk_queue_cmd(ubq, req, true); + ublk_queue_cmd(ubq, req); } static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index a7ff77550e17..933bb960490d 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -806,6 +806,9 @@ static u64 __arch_timer_check_delta(void) /* * XGene-1 implements CVAL in terms of TVAL, meaning * that the maximum timer range is 32bit. Shame on them. + * + * Note that TVAL is signed, thus has only 31 of its + * 32 bits to express magnitude. */ MIDR_ALL_VERSIONS(MIDR_CPU_MODEL(ARM_CPU_IMP_APM, APM_CPU_PART_POTENZA)), @@ -813,8 +816,8 @@ static u64 __arch_timer_check_delta(void) }; if (is_midr_in_range_list(read_cpuid_id(), broken_cval_midrs)) { - pr_warn_once("Broken CNTx_CVAL_EL1, limiting width to 32bits"); - return CLOCKSOURCE_MASK(32); + pr_warn_once("Broken CNTx_CVAL_EL1, using 31 bit TVAL instead.\n"); + return CLOCKSOURCE_MASK(31); } #endif return CLOCKSOURCE_MASK(arch_counter_get_width()); diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86 index 310779b07daf..00476e94db90 100644 --- a/drivers/cpufreq/Kconfig.x86 +++ b/drivers/cpufreq/Kconfig.x86 @@ -35,7 +35,7 @@ config X86_PCC_CPUFREQ If in doubt, say N. config X86_AMD_PSTATE - tristate "AMD Processor P-State driver" + bool "AMD Processor P-State driver" depends on X86 && ACPI select ACPI_PROCESSOR select ACPI_CPPC_LIB if X86_64 diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index ace7d50cf2ac..204e39006dda 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -59,12 +59,8 @@ * we disable it by default to go acpi-cpufreq on these processors and add a * module parameter to be able to enable it manually for debugging. */ -static bool shared_mem = false; -module_param(shared_mem, bool, 0444); -MODULE_PARM_DESC(shared_mem, - "enable amd-pstate on processors with shared memory solution (false = disabled (default), true = enabled)"); - static struct cpufreq_driver amd_pstate_driver; +static int cppc_load __initdata; static inline int pstate_enable(bool enable) { @@ -424,12 +420,22 @@ static void amd_pstate_boost_init(struct amd_cpudata *cpudata) amd_pstate_driver.boost_enabled = true; } +static void amd_perf_ctl_reset(unsigned int cpu) +{ + wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0); +} + static int amd_pstate_cpu_init(struct cpufreq_policy *policy) { int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret; struct device *dev; struct amd_cpudata *cpudata; + /* + * Resetting PERF_CTL_MSR will put the CPU in P0 frequency, + * which is ideal for initialization process. + */ + amd_perf_ctl_reset(policy->cpu); dev = get_cpu_device(policy->cpu); if (!dev) return -ENODEV; @@ -616,6 +622,15 @@ static int __init amd_pstate_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) return -ENODEV; + /* + * by default the pstate driver is disabled to load + * enable the amd_pstate passive mode driver explicitly + * with amd_pstate=passive in kernel command line + */ + if (!cppc_load) { + pr_debug("driver load is disabled, boot with amd_pstate=passive to enable this\n"); + return -ENODEV; + } if (!acpi_cpc_valid()) { pr_warn_once("the _CPC object is not present in SBIOS or ACPI disabled\n"); @@ -630,13 +645,11 @@ static int __init amd_pstate_init(void) if (boot_cpu_has(X86_FEATURE_CPPC)) { pr_debug("AMD CPPC MSR based functionality is supported\n"); amd_pstate_driver.adjust_perf = amd_pstate_adjust_perf; - } else if (shared_mem) { + } else { + pr_debug("AMD CPPC shared memory based functionality is supported\n"); static_call_update(amd_pstate_enable, cppc_enable); static_call_update(amd_pstate_init_perf, cppc_init_perf); static_call_update(amd_pstate_update_perf, cppc_update_perf); - } else { - pr_info("This processor supports shared memory solution, you can enable it with amd_pstate.shared_mem=1\n"); - return -ENODEV; } /* enable amd pstate feature */ @@ -653,16 +666,22 @@ static int __init amd_pstate_init(void) return ret; } +device_initcall(amd_pstate_init); -static void __exit amd_pstate_exit(void) +static int __init amd_pstate_param(char *str) { - cpufreq_unregister_driver(&amd_pstate_driver); + if (!str) + return -EINVAL; - amd_pstate_enable(false); + if (!strcmp(str, "disable")) { + cppc_load = 0; + pr_info("driver is explicitly disabled\n"); + } else if (!strcmp(str, "passive")) + cppc_load = 1; + + return 0; } - -module_init(amd_pstate_init); -module_exit(amd_pstate_exit); +early_param("amd_pstate", amd_pstate_param); MODULE_AUTHOR("Huang Rui "); MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver"); diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig index 6c416955da53..bbe0a7cabb75 100644 --- a/drivers/fpga/Kconfig +++ b/drivers/fpga/Kconfig @@ -246,7 +246,9 @@ config FPGA_MGR_VERSAL_FPGA config FPGA_M10_BMC_SEC_UPDATE tristate "Intel MAX10 BMC Secure Update driver" - depends on MFD_INTEL_M10_BMC && FW_UPLOAD + depends on MFD_INTEL_M10_BMC + select FW_LOADER + select FW_UPLOAD help Secure update support for the Intel MAX10 board management controller. diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 5b120402d405..cc23b90cae02 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -533,13 +533,17 @@ static void vmbus_add_channel_work(struct work_struct *work) * Add the new device to the bus. This will kick off device-driver * binding which eventually invokes the device driver's AddDevice() * method. + * + * If vmbus_device_register() fails, the 'device_obj' is freed in + * vmbus_device_release() as called by device_unregister() in the + * error path of vmbus_device_register(). In the outside error + * path, there's no need to free it. */ ret = vmbus_device_register(newchannel->device_obj); if (ret != 0) { pr_err("unable to add child device object (relid %d)\n", newchannel->offermsg.child_relid); - kfree(newchannel->device_obj); goto err_deq_chan; } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 8b2e413bf19c..e592c481f7ae 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2082,6 +2082,7 @@ int vmbus_device_register(struct hv_device *child_device_obj) ret = device_register(&child_device_obj->device); if (ret) { pr_err("Unable to register child device\n"); + put_device(&child_device_obj->device); return ret; } diff --git a/drivers/iio/accel/bma400_core.c b/drivers/iio/accel/bma400_core.c index 490c342ef72a..6e4d10a7cd32 100644 --- a/drivers/iio/accel/bma400_core.c +++ b/drivers/iio/accel/bma400_core.c @@ -805,8 +805,10 @@ static int bma400_get_steps_reg(struct bma400_data *data, int *val) ret = regmap_bulk_read(data->regmap, BMA400_STEP_CNT0_REG, steps_raw, BMA400_STEP_RAW_LEN); - if (ret) + if (ret) { + kfree(steps_raw); return ret; + } *val = get_unaligned_le24(steps_raw); kfree(steps_raw); return IIO_VAL_INT; diff --git a/drivers/iio/adc/aspeed_adc.c b/drivers/iio/adc/aspeed_adc.c index 9341e0e0eb55..998e8bcc06e1 100644 --- a/drivers/iio/adc/aspeed_adc.c +++ b/drivers/iio/adc/aspeed_adc.c @@ -202,6 +202,8 @@ static int aspeed_adc_set_trim_data(struct iio_dev *indio_dev) ((scu_otp) & (data->model_data->trim_locate->field)) >> __ffs(data->model_data->trim_locate->field); + if (!trimming_val) + trimming_val = 0x8; } dev_dbg(data->dev, "trimming val = %d, offset = %08x, fields = %08x\n", @@ -563,12 +565,9 @@ static int aspeed_adc_probe(struct platform_device *pdev) if (ret) return ret; - if (of_find_property(data->dev->of_node, "aspeed,trim-data-valid", - NULL)) { - ret = aspeed_adc_set_trim_data(indio_dev); - if (ret) - return ret; - } + ret = aspeed_adc_set_trim_data(indio_dev); + if (ret) + return ret; if (of_find_property(data->dev->of_node, "aspeed,battery-sensing", NULL)) { diff --git a/drivers/iio/health/afe4403.c b/drivers/iio/health/afe4403.c index 3bb4028c5d74..df3bc5c3d378 100644 --- a/drivers/iio/health/afe4403.c +++ b/drivers/iio/health/afe4403.c @@ -245,14 +245,14 @@ static int afe4403_read_raw(struct iio_dev *indio_dev, int *val, int *val2, long mask) { struct afe4403_data *afe = iio_priv(indio_dev); - unsigned int reg = afe4403_channel_values[chan->address]; - unsigned int field = afe4403_channel_leds[chan->address]; + unsigned int reg, field; int ret; switch (chan->type) { case IIO_INTENSITY: switch (mask) { case IIO_CHAN_INFO_RAW: + reg = afe4403_channel_values[chan->address]; ret = afe4403_read(afe, reg, val); if (ret) return ret; @@ -262,6 +262,7 @@ static int afe4403_read_raw(struct iio_dev *indio_dev, case IIO_CURRENT: switch (mask) { case IIO_CHAN_INFO_RAW: + field = afe4403_channel_leds[chan->address]; ret = regmap_field_read(afe->fields[field], val); if (ret) return ret; diff --git a/drivers/iio/health/afe4404.c b/drivers/iio/health/afe4404.c index 8fca787b2524..836da31b7e30 100644 --- a/drivers/iio/health/afe4404.c +++ b/drivers/iio/health/afe4404.c @@ -250,20 +250,20 @@ static int afe4404_read_raw(struct iio_dev *indio_dev, int *val, int *val2, long mask) { struct afe4404_data *afe = iio_priv(indio_dev); - unsigned int value_reg = afe4404_channel_values[chan->address]; - unsigned int led_field = afe4404_channel_leds[chan->address]; - unsigned int offdac_field = afe4404_channel_offdacs[chan->address]; + unsigned int value_reg, led_field, offdac_field; int ret; switch (chan->type) { case IIO_INTENSITY: switch (mask) { case IIO_CHAN_INFO_RAW: + value_reg = afe4404_channel_values[chan->address]; ret = regmap_read(afe->regmap, value_reg, val); if (ret) return ret; return IIO_VAL_INT; case IIO_CHAN_INFO_OFFSET: + offdac_field = afe4404_channel_offdacs[chan->address]; ret = regmap_field_read(afe->fields[offdac_field], val); if (ret) return ret; @@ -273,6 +273,7 @@ static int afe4404_read_raw(struct iio_dev *indio_dev, case IIO_CURRENT: switch (mask) { case IIO_CHAN_INFO_RAW: + led_field = afe4404_channel_leds[chan->address]; ret = regmap_field_read(afe->fields[led_field], val); if (ret) return ret; @@ -295,19 +296,20 @@ static int afe4404_write_raw(struct iio_dev *indio_dev, int val, int val2, long mask) { struct afe4404_data *afe = iio_priv(indio_dev); - unsigned int led_field = afe4404_channel_leds[chan->address]; - unsigned int offdac_field = afe4404_channel_offdacs[chan->address]; + unsigned int led_field, offdac_field; switch (chan->type) { case IIO_INTENSITY: switch (mask) { case IIO_CHAN_INFO_OFFSET: + offdac_field = afe4404_channel_offdacs[chan->address]; return regmap_field_write(afe->fields[offdac_field], val); } break; case IIO_CURRENT: switch (mask) { case IIO_CHAN_INFO_RAW: + led_field = afe4404_channel_leds[chan->address]; return regmap_field_write(afe->fields[led_field], val); } break; diff --git a/drivers/iio/industrialio-sw-trigger.c b/drivers/iio/industrialio-sw-trigger.c index 994f03a71520..d86a3305d9e8 100644 --- a/drivers/iio/industrialio-sw-trigger.c +++ b/drivers/iio/industrialio-sw-trigger.c @@ -58,8 +58,12 @@ int iio_register_sw_trigger_type(struct iio_sw_trigger_type *t) t->group = configfs_register_default_group(iio_triggers_group, t->name, &iio_trigger_type_group_type); - if (IS_ERR(t->group)) + if (IS_ERR(t->group)) { + mutex_lock(&iio_trigger_types_lock); + list_del(&t->list); + mutex_unlock(&iio_trigger_types_lock); ret = PTR_ERR(t->group); + } return ret; } diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index 7cf6e8490123..0d4447df7200 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -293,6 +293,8 @@ config RPR0521 tristate "ROHM RPR0521 ALS and proximity sensor driver" depends on I2C select REGMAP_I2C + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help Say Y here if you want to build support for ROHM's RPR0521 ambient light and proximity sensor device. diff --git a/drivers/iio/light/apds9960.c b/drivers/iio/light/apds9960.c index b62c139baf41..38d4c7644bef 100644 --- a/drivers/iio/light/apds9960.c +++ b/drivers/iio/light/apds9960.c @@ -54,9 +54,6 @@ #define APDS9960_REG_CONTROL_PGAIN_MASK_SHIFT 2 #define APDS9960_REG_CONFIG_2 0x90 -#define APDS9960_REG_CONFIG_2_GGAIN_MASK 0x60 -#define APDS9960_REG_CONFIG_2_GGAIN_MASK_SHIFT 5 - #define APDS9960_REG_ID 0x92 #define APDS9960_REG_STATUS 0x93 @@ -77,6 +74,9 @@ #define APDS9960_REG_GCONF_1_GFIFO_THRES_MASK_SHIFT 6 #define APDS9960_REG_GCONF_2 0xa3 +#define APDS9960_REG_GCONF_2_GGAIN_MASK 0x60 +#define APDS9960_REG_GCONF_2_GGAIN_MASK_SHIFT 5 + #define APDS9960_REG_GOFFSET_U 0xa4 #define APDS9960_REG_GOFFSET_D 0xa5 #define APDS9960_REG_GPULSE 0xa6 @@ -396,9 +396,9 @@ static int apds9960_set_pxs_gain(struct apds9960_data *data, int val) } ret = regmap_update_bits(data->regmap, - APDS9960_REG_CONFIG_2, - APDS9960_REG_CONFIG_2_GGAIN_MASK, - idx << APDS9960_REG_CONFIG_2_GGAIN_MASK_SHIFT); + APDS9960_REG_GCONF_2, + APDS9960_REG_GCONF_2_GGAIN_MASK, + idx << APDS9960_REG_GCONF_2_GGAIN_MASK_SHIFT); if (!ret) data->pxs_gain = idx; mutex_unlock(&data->lock); diff --git a/drivers/nvmem/lan9662-otpc.c b/drivers/nvmem/lan9662-otpc.c index 377bf34c2946..56fc19f092a7 100644 --- a/drivers/nvmem/lan9662-otpc.c +++ b/drivers/nvmem/lan9662-otpc.c @@ -36,7 +36,7 @@ struct lan9662_otp { void __iomem *base; }; -static bool lan9662_otp_wait_flag_clear(void __iomem *reg, u32 flag) +static int lan9662_otp_wait_flag_clear(void __iomem *reg, u32 flag) { u32 val; diff --git a/drivers/nvmem/rmem.c b/drivers/nvmem/rmem.c index b11c3c974b3d..80cb187f1481 100644 --- a/drivers/nvmem/rmem.c +++ b/drivers/nvmem/rmem.c @@ -37,9 +37,9 @@ static int rmem_read(void *context, unsigned int offset, * but as of Dec 2020 this isn't possible on arm64. */ addr = memremap(priv->mem->base, available, MEMREMAP_WB); - if (IS_ERR(addr)) { + if (!addr) { dev_err(priv->dev, "Failed to remap memory region\n"); - return PTR_ERR(addr); + return -ENOMEM; } count = memory_read_from_buffer(val, bytes, &off, addr, available); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index ba64284eaf9f..f1ec8931dfbc 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -1613,7 +1613,7 @@ out: } static u32 hv_compose_msi_req_v1( - struct pci_create_interrupt *int_pkt, const struct cpumask *affinity, + struct pci_create_interrupt *int_pkt, u32 slot, u8 vector, u16 vector_count) { int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE; @@ -1631,6 +1631,35 @@ static u32 hv_compose_msi_req_v1( return sizeof(*int_pkt); } +/* + * The vCPU selected by hv_compose_multi_msi_req_get_cpu() and + * hv_compose_msi_req_get_cpu() is a "dummy" vCPU because the final vCPU to be + * interrupted is specified later in hv_irq_unmask() and communicated to Hyper-V + * via the HVCALL_RETARGET_INTERRUPT hypercall. But the choice of dummy vCPU is + * not irrelevant because Hyper-V chooses the physical CPU to handle the + * interrupts based on the vCPU specified in message sent to the vPCI VSP in + * hv_compose_msi_msg(). Hyper-V's choice of pCPU is not visible to the guest, + * but assigning too many vPCI device interrupts to the same pCPU can cause a + * performance bottleneck. So we spread out the dummy vCPUs to influence Hyper-V + * to spread out the pCPUs that it selects. + * + * For the single-MSI and MSI-X cases, it's OK for hv_compose_msi_req_get_cpu() + * to always return the same dummy vCPU, because a second call to + * hv_compose_msi_msg() contains the "real" vCPU, causing Hyper-V to choose a + * new pCPU for the interrupt. But for the multi-MSI case, the second call to + * hv_compose_msi_msg() exits without sending a message to the vPCI VSP, so the + * original dummy vCPU is used. This dummy vCPU must be round-robin'ed so that + * the pCPUs are spread out. All interrupts for a multi-MSI device end up using + * the same pCPU, even though the vCPUs will be spread out by later calls + * to hv_irq_unmask(), but that is the best we can do now. + * + * With Hyper-V in Nov 2022, the HVCALL_RETARGET_INTERRUPT hypercall does *not* + * cause Hyper-V to reselect the pCPU based on the specified vCPU. Such an + * enhancement is planned for a future version. With that enhancement, the + * dummy vCPU selection won't matter, and interrupts for the same multi-MSI + * device will be spread across multiple pCPUs. + */ + /* * Create MSI w/ dummy vCPU set targeting just one vCPU, overwritten * by subsequent retarget in hv_irq_unmask(). @@ -1640,18 +1669,39 @@ static int hv_compose_msi_req_get_cpu(const struct cpumask *affinity) return cpumask_first_and(affinity, cpu_online_mask); } -static u32 hv_compose_msi_req_v2( - struct pci_create_interrupt2 *int_pkt, const struct cpumask *affinity, - u32 slot, u8 vector, u16 vector_count) +/* + * Make sure the dummy vCPU values for multi-MSI don't all point to vCPU0. + */ +static int hv_compose_multi_msi_req_get_cpu(void) { + static DEFINE_SPINLOCK(multi_msi_cpu_lock); + + /* -1 means starting with CPU 0 */ + static int cpu_next = -1; + + unsigned long flags; int cpu; + spin_lock_irqsave(&multi_msi_cpu_lock, flags); + + cpu_next = cpumask_next_wrap(cpu_next, cpu_online_mask, nr_cpu_ids, + false); + cpu = cpu_next; + + spin_unlock_irqrestore(&multi_msi_cpu_lock, flags); + + return cpu; +} + +static u32 hv_compose_msi_req_v2( + struct pci_create_interrupt2 *int_pkt, int cpu, + u32 slot, u8 vector, u16 vector_count) +{ int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE2; int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; int_pkt->int_desc.vector_count = vector_count; int_pkt->int_desc.delivery_mode = DELIVERY_MODE; - cpu = hv_compose_msi_req_get_cpu(affinity); int_pkt->int_desc.processor_array[0] = hv_cpu_number_to_vp_number(cpu); int_pkt->int_desc.processor_count = 1; @@ -1660,18 +1710,15 @@ static u32 hv_compose_msi_req_v2( } static u32 hv_compose_msi_req_v3( - struct pci_create_interrupt3 *int_pkt, const struct cpumask *affinity, + struct pci_create_interrupt3 *int_pkt, int cpu, u32 slot, u32 vector, u16 vector_count) { - int cpu; - int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE3; int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; int_pkt->int_desc.reserved = 0; int_pkt->int_desc.vector_count = vector_count; int_pkt->int_desc.delivery_mode = DELIVERY_MODE; - cpu = hv_compose_msi_req_get_cpu(affinity); int_pkt->int_desc.processor_array[0] = hv_cpu_number_to_vp_number(cpu); int_pkt->int_desc.processor_count = 1; @@ -1715,12 +1762,18 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct pci_create_interrupt3 v3; } int_pkts; } __packed ctxt; + bool multi_msi; u64 trans_id; u32 size; int ret; + int cpu; + + msi_desc = irq_data_get_msi_desc(data); + multi_msi = !msi_desc->pci.msi_attrib.is_msix && + msi_desc->nvec_used > 1; /* Reuse the previous allocation */ - if (data->chip_data) { + if (data->chip_data && multi_msi) { int_desc = data->chip_data; msg->address_hi = int_desc->address >> 32; msg->address_lo = int_desc->address & 0xffffffff; @@ -1728,7 +1781,6 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return; } - msi_desc = irq_data_get_msi_desc(data); pdev = msi_desc_to_pci_dev(msi_desc); dest = irq_data_get_effective_affinity_mask(data); pbus = pdev->bus; @@ -1738,11 +1790,18 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) if (!hpdev) goto return_null_message; + /* Free any previous message that might have already been composed. */ + if (data->chip_data && !multi_msi) { + int_desc = data->chip_data; + data->chip_data = NULL; + hv_int_desc_free(hpdev, int_desc); + } + int_desc = kzalloc(sizeof(*int_desc), GFP_ATOMIC); if (!int_desc) goto drop_reference; - if (!msi_desc->pci.msi_attrib.is_msix && msi_desc->nvec_used > 1) { + if (multi_msi) { /* * If this is not the first MSI of Multi MSI, we already have * a mapping. Can exit early. @@ -1767,9 +1826,11 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) */ vector = 32; vector_count = msi_desc->nvec_used; + cpu = hv_compose_multi_msi_req_get_cpu(); } else { vector = hv_msi_get_int_vector(data); vector_count = 1; + cpu = hv_compose_msi_req_get_cpu(dest); } /* @@ -1785,7 +1846,6 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) switch (hbus->protocol_version) { case PCI_PROTOCOL_VERSION_1_1: size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1, - dest, hpdev->desc.win_slot.slot, (u8)vector, vector_count); @@ -1794,7 +1854,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) case PCI_PROTOCOL_VERSION_1_2: case PCI_PROTOCOL_VERSION_1_3: size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2, - dest, + cpu, hpdev->desc.win_slot.slot, (u8)vector, vector_count); @@ -1802,7 +1862,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) case PCI_PROTOCOL_VERSION_1_4: size = hv_compose_msi_req_v3(&ctxt.int_pkts.v3, - dest, + cpu, hpdev->desc.win_slot.slot, vector, vector_count); diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 863fabe05bdc..307ee6f71042 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -725,7 +725,14 @@ static int ab8500_btemp_probe(struct platform_device *pdev) /* Get thermal zone and ADC */ di->tz = thermal_zone_get_zone_by_name("battery-thermal"); if (IS_ERR(di->tz)) { - return dev_err_probe(dev, PTR_ERR(di->tz), + ret = PTR_ERR(di->tz); + /* + * This usually just means we are probing before the thermal + * zone, so just defer. + */ + if (ret == -ENODEV) + ret = -EPROBE_DEFER; + return dev_err_probe(dev, ret, "failed to get battery thermal zone\n"); } di->bat_ctrl = devm_iio_channel_get(dev, "bat_ctrl"); diff --git a/drivers/power/supply/ip5xxx_power.c b/drivers/power/supply/ip5xxx_power.c index 218e8e689a3f..00221e9c0bfc 100644 --- a/drivers/power/supply/ip5xxx_power.c +++ b/drivers/power/supply/ip5xxx_power.c @@ -352,7 +352,7 @@ static int ip5xxx_battery_get_property(struct power_supply *psy, ret = ip5xxx_battery_read_adc(ip5xxx, IP5XXX_BATIADC_DAT0, IP5XXX_BATIADC_DAT1, &raw); - val->intval = DIV_ROUND_CLOSEST(raw * 745985, 1000); + val->intval = DIV_ROUND_CLOSEST(raw * 149197, 200); return 0; case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT: diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c index 635f051b0821..f20a6ac584cc 100644 --- a/drivers/power/supply/rk817_charger.c +++ b/drivers/power/supply/rk817_charger.c @@ -121,7 +121,7 @@ struct rk817_charger { #define ADC_TO_CHARGE_UAH(adc_value, res_div) \ (adc_value / 3600 * 172 / res_div) -static u8 rk817_chg_cur_to_reg(u32 chg_cur_ma) +static int rk817_chg_cur_to_reg(u32 chg_cur_ma) { if (chg_cur_ma >= 3500) return CHG_3_5A; @@ -864,8 +864,8 @@ static int rk817_battery_init(struct rk817_charger *charger, { struct rk808 *rk808 = charger->rk808; u32 tmp, max_chg_vol_mv, max_chg_cur_ma; - u8 max_chg_vol_reg, chg_term_i_reg, max_chg_cur_reg; - int ret, chg_term_ma; + u8 max_chg_vol_reg, chg_term_i_reg; + int ret, chg_term_ma, max_chg_cur_reg; u8 bulk_reg[2]; /* Get initial plug state */ @@ -1116,14 +1116,12 @@ static int rk817_charger_probe(struct platform_device *pdev) charger->bat_ps = devm_power_supply_register(&pdev->dev, &rk817_bat_desc, &pscfg); - - charger->chg_ps = devm_power_supply_register(&pdev->dev, - &rk817_chg_desc, &pscfg); - - if (IS_ERR(charger->chg_ps)) + if (IS_ERR(charger->bat_ps)) return dev_err_probe(dev, -EINVAL, "Battery failed to probe\n"); + charger->chg_ps = devm_power_supply_register(&pdev->dev, + &rk817_chg_desc, &pscfg); if (IS_ERR(charger->chg_ps)) return dev_err_probe(dev, -EINVAL, "Charger failed to probe\n"); diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index bcccad8f7516..e8c00a884f1f 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5154,6 +5154,7 @@ static void regulator_dev_release(struct device *dev) { struct regulator_dev *rdev = dev_get_drvdata(dev); + debugfs_remove_recursive(rdev->debugfs); kfree(rdev->constraints); of_node_put(rdev->dev.of_node); kfree(rdev); @@ -5644,11 +5645,15 @@ wash: mutex_lock(®ulator_list_mutex); regulator_ena_gpio_free(rdev); mutex_unlock(®ulator_list_mutex); + put_device(&rdev->dev); + rdev = NULL; clean: if (dangling_of_gpiod) gpiod_put(config->ena_gpiod); + if (rdev && rdev->dev.of_node) + of_node_put(rdev->dev.of_node); + kfree(rdev); kfree(config); - put_device(&rdev->dev); rinse: if (dangling_cfg_gpiod) gpiod_put(cfg->ena_gpiod); @@ -5677,7 +5682,6 @@ void regulator_unregister(struct regulator_dev *rdev) mutex_lock(®ulator_list_mutex); - debugfs_remove_recursive(rdev->debugfs); WARN_ON(rdev->open_count); regulator_remove_coupling(rdev); unset_regulator_supplies(rdev); diff --git a/drivers/regulator/rt5759-regulator.c b/drivers/regulator/rt5759-regulator.c index 6b96899eb27e..8488417f4b2c 100644 --- a/drivers/regulator/rt5759-regulator.c +++ b/drivers/regulator/rt5759-regulator.c @@ -243,6 +243,7 @@ static int rt5759_regulator_register(struct rt5759_priv *priv) if (priv->chip_type == CHIP_TYPE_RT5759A) reg_desc->uV_step = RT5759A_STEP_UV; + memset(®_cfg, 0, sizeof(reg_cfg)); reg_cfg.dev = priv->dev; reg_cfg.of_node = np; reg_cfg.init_data = of_get_regulator_init_data(priv->dev, np, reg_desc); diff --git a/drivers/regulator/slg51000-regulator.c b/drivers/regulator/slg51000-regulator.c index 75a941fb3c2b..1b2eee95ad3f 100644 --- a/drivers/regulator/slg51000-regulator.c +++ b/drivers/regulator/slg51000-regulator.c @@ -457,6 +457,8 @@ static int slg51000_i2c_probe(struct i2c_client *client) chip->cs_gpiod = cs_gpiod; } + usleep_range(10000, 11000); + i2c_set_clientdata(client, chip); chip->chip_irq = client->irq; chip->dev = dev; diff --git a/drivers/regulator/twl6030-regulator.c b/drivers/regulator/twl6030-regulator.c index 430265c404d6..f3856750944f 100644 --- a/drivers/regulator/twl6030-regulator.c +++ b/drivers/regulator/twl6030-regulator.c @@ -67,6 +67,7 @@ struct twlreg_info { #define TWL6030_CFG_STATE_SLEEP 0x03 #define TWL6030_CFG_STATE_GRP_SHIFT 5 #define TWL6030_CFG_STATE_APP_SHIFT 2 +#define TWL6030_CFG_STATE_MASK 0x03 #define TWL6030_CFG_STATE_APP_MASK (0x03 << TWL6030_CFG_STATE_APP_SHIFT) #define TWL6030_CFG_STATE_APP(v) (((v) & TWL6030_CFG_STATE_APP_MASK) >>\ TWL6030_CFG_STATE_APP_SHIFT) @@ -128,13 +129,14 @@ static int twl6030reg_is_enabled(struct regulator_dev *rdev) if (grp < 0) return grp; grp &= P1_GRP_6030; + val = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_STATE); + val = TWL6030_CFG_STATE_APP(val); } else { + val = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_STATE); + val &= TWL6030_CFG_STATE_MASK; grp = 1; } - val = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_STATE); - val = TWL6030_CFG_STATE_APP(val); - return grp && (val == TWL6030_CFG_STATE_ON); } @@ -187,7 +189,12 @@ static int twl6030reg_get_status(struct regulator_dev *rdev) val = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_STATE); - switch (TWL6030_CFG_STATE_APP(val)) { + if (info->features & TWL6032_SUBCLASS) + val &= TWL6030_CFG_STATE_MASK; + else + val = TWL6030_CFG_STATE_APP(val); + + switch (val) { case TWL6030_CFG_STATE_ON: return REGULATOR_STATUS_NORMAL; @@ -530,6 +537,7 @@ static const struct twlreg_info TWL6030_INFO_##label = { \ #define TWL6032_ADJUSTABLE_LDO(label, offset) \ static const struct twlreg_info TWL6032_INFO_##label = { \ .base = offset, \ + .features = TWL6032_SUBCLASS, \ .desc = { \ .name = #label, \ .id = TWL6032_REG_##label, \ @@ -562,6 +570,7 @@ static const struct twlreg_info TWLFIXED_INFO_##label = { \ #define TWL6032_ADJUSTABLE_SMPS(label, offset) \ static const struct twlreg_info TWLSMPS_INFO_##label = { \ .base = offset, \ + .features = TWL6032_SUBCLASS, \ .desc = { \ .name = #label, \ .id = TWL6032_REG_##label, \ diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index cb83f81da416..df17f0f9cb0f 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -1954,7 +1954,7 @@ dasd_copy_pair_show(struct device *dev, break; } } - if (!copy->entry[i].primary) + if (i == DASD_CP_ENTRIES) goto out; /* print all secondary */ diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 662730f3b027..5d0b9991e91a 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -4722,7 +4722,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, struct dasd_device *basedev; struct req_iterator iter; struct dasd_ccw_req *cqr; - unsigned int first_offs; unsigned int trkcount; unsigned long *idaws; unsigned int size; @@ -4756,7 +4755,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, last_trk = (blk_rq_pos(req) + blk_rq_sectors(req) - 1) / DASD_RAW_SECTORS_PER_TRACK; trkcount = last_trk - first_trk + 1; - first_offs = 0; if (rq_data_dir(req) == READ) cmd = DASD_ECKD_CCW_READ_TRACK; @@ -4800,13 +4798,13 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_raw(struct dasd_device *startdev, if (use_prefix) { prefix_LRE(ccw++, data, first_trk, last_trk, cmd, basedev, - startdev, 1, first_offs + 1, trkcount, 0, 0); + startdev, 1, 0, trkcount, 0, 0); } else { define_extent(ccw++, data, first_trk, last_trk, cmd, basedev, 0); ccw[-1].flags |= CCW_FLAG_CC; data += sizeof(struct DE_eckd_data); - locate_record_ext(ccw++, data, first_trk, first_offs + 1, + locate_record_ext(ccw++, data, first_trk, 0, trkcount, cmd, basedev, 0, 0); } @@ -5500,7 +5498,7 @@ dasd_eckd_ioctl(struct dasd_block *block, unsigned int cmd, void __user *argp) * Dump the range of CCWs into 'page' buffer * and return number of printed chars. */ -static int +static void dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page) { int len, count; @@ -5518,16 +5516,21 @@ dasd_eckd_dump_ccw_range(struct ccw1 *from, struct ccw1 *to, char *page) else datap = (char *) ((addr_t) from->cda); - /* dump data (max 32 bytes) */ - for (count = 0; count < from->count && count < 32; count++) { - if (count % 8 == 0) len += sprintf(page + len, " "); - if (count % 4 == 0) len += sprintf(page + len, " "); + /* dump data (max 128 bytes) */ + for (count = 0; count < from->count && count < 128; count++) { + if (count % 32 == 0) + len += sprintf(page + len, "\n"); + if (count % 8 == 0) + len += sprintf(page + len, " "); + if (count % 4 == 0) + len += sprintf(page + len, " "); len += sprintf(page + len, "%02x", datap[count]); } len += sprintf(page + len, "\n"); from++; } - return len; + if (len > 0) + printk(KERN_ERR "%s", page); } static void @@ -5619,37 +5622,33 @@ static void dasd_eckd_dump_sense_ccw(struct dasd_device *device, if (req) { /* req == NULL for unsolicited interrupts */ /* dump the Channel Program (max 140 Bytes per line) */ - /* Count CCW and print first CCWs (maximum 1024 % 140 = 7) */ + /* Count CCW and print first CCWs (maximum 7) */ first = req->cpaddr; for (last = first; last->flags & (CCW_FLAG_CC | CCW_FLAG_DC); last++); to = min(first + 6, last); - len = sprintf(page, PRINTK_HEADER - " Related CP in req: %p\n", req); - dasd_eckd_dump_ccw_range(first, to, page + len); - printk(KERN_ERR "%s", page); + printk(KERN_ERR PRINTK_HEADER " Related CP in req: %p\n", req); + dasd_eckd_dump_ccw_range(first, to, page); /* print failing CCW area (maximum 4) */ /* scsw->cda is either valid or zero */ - len = 0; from = ++to; fail = (struct ccw1 *)(addr_t) irb->scsw.cmd.cpa; /* failing CCW */ if (from < fail - 2) { from = fail - 2; /* there is a gap - print header */ - len += sprintf(page, PRINTK_HEADER "......\n"); + printk(KERN_ERR PRINTK_HEADER "......\n"); } to = min(fail + 1, last); - len += dasd_eckd_dump_ccw_range(from, to, page + len); + dasd_eckd_dump_ccw_range(from, to, page + len); /* print last CCWs (maximum 2) */ + len = 0; from = max(from, ++to); if (from < last - 1) { from = last - 1; /* there is a gap - print header */ - len += sprintf(page + len, PRINTK_HEADER "......\n"); + printk(KERN_ERR PRINTK_HEADER "......\n"); } - len += dasd_eckd_dump_ccw_range(from, last, page + len); - if (len > 0) - printk(KERN_ERR "%s", page); + dasd_eckd_dump_ccw_range(from, last, page + len); } free_page((unsigned long) page); } diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index d0ddf2cc9786..9327dcdd6e5e 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -401,7 +401,7 @@ dasd_ioctl_copy_pair_swap(struct block_device *bdev, void __user *argp) return -EFAULT; } if (memchr_inv(data.reserved, 0, sizeof(data.reserved))) { - pr_warn("%s: Ivalid swap data specified.\n", + pr_warn("%s: Invalid swap data specified\n", dev_name(&device->cdev->dev)); dasd_put_device(device); return DASD_COPYPAIRSWAP_INVALID; diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 59ac98f2bd27..b02c631f3b71 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -233,8 +233,11 @@ static void __init ap_init_qci_info(void) if (!ap_qci_info) return; ap_qci_info_old = kzalloc(sizeof(*ap_qci_info_old), GFP_KERNEL); - if (!ap_qci_info_old) + if (!ap_qci_info_old) { + kfree(ap_qci_info); + ap_qci_info = NULL; return; + } if (ap_fetch_qci_info(ap_qci_info) != 0) { kfree(ap_qci_info); kfree(ap_qci_info_old); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index bc46721aa01c..3c5b7e4227b2 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -303,16 +303,21 @@ enum storvsc_request_type { }; /* - * SRB status codes and masks; a subset of the codes used here. + * SRB status codes and masks. In the 8-bit field, the two high order bits + * are flags, while the remaining 6 bits are an integer status code. The + * definitions here include only the subset of the integer status codes that + * are tested for in this driver. */ - #define SRB_STATUS_AUTOSENSE_VALID 0x80 #define SRB_STATUS_QUEUE_FROZEN 0x40 -#define SRB_STATUS_INVALID_LUN 0x20 -#define SRB_STATUS_SUCCESS 0x01 -#define SRB_STATUS_ABORTED 0x02 -#define SRB_STATUS_ERROR 0x04 -#define SRB_STATUS_DATA_OVERRUN 0x12 + +/* SRB status integer codes */ +#define SRB_STATUS_SUCCESS 0x01 +#define SRB_STATUS_ABORTED 0x02 +#define SRB_STATUS_ERROR 0x04 +#define SRB_STATUS_INVALID_REQUEST 0x06 +#define SRB_STATUS_DATA_OVERRUN 0x12 +#define SRB_STATUS_INVALID_LUN 0x20 #define SRB_STATUS(status) \ (status & ~(SRB_STATUS_AUTOSENSE_VALID | SRB_STATUS_QUEUE_FROZEN)) @@ -969,38 +974,25 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, void (*process_err_fn)(struct work_struct *work); struct hv_host_device *host_dev = shost_priv(host); - /* - * In some situations, Hyper-V sets multiple bits in the - * srb_status, such as ABORTED and ERROR. So process them - * individually, with the most specific bits first. - */ + switch (SRB_STATUS(vm_srb->srb_status)) { + case SRB_STATUS_ERROR: + case SRB_STATUS_ABORTED: + case SRB_STATUS_INVALID_REQUEST: + if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID) { + /* Check for capacity change */ + if ((asc == 0x2a) && (ascq == 0x9)) { + process_err_fn = storvsc_device_scan; + /* Retry the I/O that triggered this. */ + set_host_byte(scmnd, DID_REQUEUE); + goto do_work; + } - if (vm_srb->srb_status & SRB_STATUS_INVALID_LUN) { - set_host_byte(scmnd, DID_NO_CONNECT); - process_err_fn = storvsc_remove_lun; - goto do_work; - } - - if (vm_srb->srb_status & SRB_STATUS_ABORTED) { - if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID && - /* Capacity data has changed */ - (asc == 0x2a) && (ascq == 0x9)) { - process_err_fn = storvsc_device_scan; /* - * Retry the I/O that triggered this. + * Otherwise, let upper layer deal with the + * error when sense message is present */ - set_host_byte(scmnd, DID_REQUEUE); - goto do_work; - } - } - - if (vm_srb->srb_status & SRB_STATUS_ERROR) { - /* - * Let upper layer deal with error when - * sense message is present. - */ - if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID) return; + } /* * If there is an error; offline the device since all @@ -1023,6 +1015,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, default: set_host_byte(scmnd, DID_ERROR); } + return; + + case SRB_STATUS_INVALID_LUN: + set_host_byte(scmnd, DID_NO_CONNECT); + process_err_fn = storvsc_remove_lun; + goto do_work; + } return; diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index c67715f6f756..f9aa50ff14d4 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -600,11 +600,11 @@ int cdnsp_halt_endpoint(struct cdnsp_device *pdev, trace_cdnsp_ep_halt(value ? "Set" : "Clear"); - if (value) { - ret = cdnsp_cmd_stop_ep(pdev, pep); - if (ret) - return ret; + ret = cdnsp_cmd_stop_ep(pdev, pep); + if (ret) + return ret; + if (value) { if (GET_EP_CTX_STATE(pep->out_ctx) == EP_STATE_STOPPED) { cdnsp_queue_halt_endpoint(pdev, pep->idx); cdnsp_ring_cmd_db(pdev); @@ -613,10 +613,6 @@ int cdnsp_halt_endpoint(struct cdnsp_device *pdev, pep->ep_state |= EP_HALTED; } else { - /* - * In device mode driver can call reset endpoint command - * from any endpoint state. - */ cdnsp_queue_reset_ep(pdev, pep->idx); cdnsp_ring_cmd_db(pdev); ret = cdnsp_wait_for_cmd_compl(pdev); diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c index 794e413800ae..2f29431f612e 100644 --- a/drivers/usb/cdns3/cdnsp-ring.c +++ b/drivers/usb/cdns3/cdnsp-ring.c @@ -1763,10 +1763,15 @@ static u32 cdnsp_td_remainder(struct cdnsp_device *pdev, int trb_buff_len, unsigned int td_total_len, struct cdnsp_request *preq, - bool more_trbs_coming) + bool more_trbs_coming, + bool zlp) { u32 maxp, total_packet_count; + /* Before ZLP driver needs set TD_SIZE = 1. */ + if (zlp) + return 1; + /* One TRB with a zero-length data packet. */ if (!more_trbs_coming || (transferred == 0 && trb_buff_len == 0) || trb_buff_len == td_total_len) @@ -1960,7 +1965,8 @@ int cdnsp_queue_bulk_tx(struct cdnsp_device *pdev, struct cdnsp_request *preq) /* Set the TRB length, TD size, and interrupter fields. */ remainder = cdnsp_td_remainder(pdev, enqd_len, trb_buff_len, full_len, preq, - more_trbs_coming); + more_trbs_coming, + zero_len_trb); length_field = TRB_LEN(trb_buff_len) | TRB_TD_SIZE(remainder) | TRB_INTR_TARGET(0); @@ -2025,7 +2031,7 @@ int cdnsp_queue_ctrl_tx(struct cdnsp_device *pdev, struct cdnsp_request *preq) if (preq->request.length > 0) { remainder = cdnsp_td_remainder(pdev, 0, preq->request.length, - preq->request.length, preq, 1); + preq->request.length, preq, 1, 0); length_field = TRB_LEN(preq->request.length) | TRB_TD_SIZE(remainder) | TRB_INTR_TARGET(0); @@ -2076,7 +2082,8 @@ int cdnsp_cmd_stop_ep(struct cdnsp_device *pdev, struct cdnsp_ep *pep) u32 ep_state = GET_EP_CTX_STATE(pep->out_ctx); int ret = 0; - if (ep_state == EP_STATE_STOPPED || ep_state == EP_STATE_DISABLED) { + if (ep_state == EP_STATE_STOPPED || ep_state == EP_STATE_DISABLED || + ep_state == EP_STATE_HALTED) { trace_cdnsp_ep_stopped_or_disabled(pep->out_ctx); goto ep_stopped; } @@ -2225,7 +2232,7 @@ static int cdnsp_queue_isoc_tx(struct cdnsp_device *pdev, /* Set the TRB length, TD size, & interrupter fields. */ remainder = cdnsp_td_remainder(pdev, running_total, trb_buff_len, td_len, preq, - more_trbs_coming); + more_trbs_coming, 0); length_field = TRB_LEN(trb_buff_len) | TRB_INTR_TARGET(0); diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index 0ecf20eeceee..4be6a873bd07 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -37,15 +37,6 @@ struct dwc3_exynos { struct regulator *vdd10; }; -static int dwc3_exynos_remove_child(struct device *dev, void *unused) -{ - struct platform_device *pdev = to_platform_device(dev); - - platform_device_unregister(pdev); - - return 0; -} - static int dwc3_exynos_probe(struct platform_device *pdev) { struct dwc3_exynos *exynos; @@ -142,7 +133,7 @@ static int dwc3_exynos_remove(struct platform_device *pdev) struct dwc3_exynos *exynos = platform_get_drvdata(pdev); int i; - device_for_each_child(&pdev->dev, NULL, dwc3_exynos_remove_child); + of_platform_depopulate(&pdev->dev); for (i = exynos->num_clks - 1; i >= 0; i--) clk_disable_unprepare(exynos->clks[i]); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 026d4029bda6..6d524fa76443 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -291,7 +291,8 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, * * DWC_usb3 3.30a and DWC_usb31 1.90a programming guide section 3.2.2 */ - if (dwc->gadget->speed <= USB_SPEED_HIGH) { + if (dwc->gadget->speed <= USB_SPEED_HIGH || + DWC3_DEPCMD_CMD(cmd) == DWC3_DEPCMD_ENDTRANSFER) { reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); if (unlikely(reg & DWC3_GUSB2PHYCFG_SUSPHY)) { saved_config |= DWC3_GUSB2PHYCFG_SUSPHY; @@ -1023,12 +1024,6 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) reg &= ~DWC3_DALEPENA_EP(dep->number); dwc3_writel(dwc->regs, DWC3_DALEPENA, reg); - /* Clear out the ep descriptors for non-ep0 */ - if (dep->number > 1) { - dep->endpoint.comp_desc = NULL; - dep->endpoint.desc = NULL; - } - dwc3_remove_requests(dwc, dep, -ESHUTDOWN); dep->stream_capable = false; @@ -1043,6 +1038,12 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) mask |= (DWC3_EP_DELAY_STOP | DWC3_EP_TRANSFER_STARTED); dep->flags &= mask; + /* Clear out the ep descriptors for non-ep0 */ + if (dep->number > 1) { + dep->endpoint.comp_desc = NULL; + dep->endpoint.desc = NULL; + } + return 0; } diff --git a/drivers/usb/gadget/function/uvc_v4l2.c b/drivers/usb/gadget/function/uvc_v4l2.c index c4ed48d6b8a4..a189b08bba80 100644 --- a/drivers/usb/gadget/function/uvc_v4l2.c +++ b/drivers/usb/gadget/function/uvc_v4l2.c @@ -199,16 +199,6 @@ uvc_send_response(struct uvc_device *uvc, struct uvc_request_data *data) * V4L2 ioctls */ -struct uvc_format { - u8 bpp; - u32 fcc; -}; - -static struct uvc_format uvc_formats[] = { - { 16, V4L2_PIX_FMT_YUYV }, - { 0, V4L2_PIX_FMT_MJPEG }, -}; - static int uvc_v4l2_querycap(struct file *file, void *fh, struct v4l2_capability *cap) { @@ -242,47 +232,6 @@ uvc_v4l2_get_format(struct file *file, void *fh, struct v4l2_format *fmt) return 0; } -static int -uvc_v4l2_set_format(struct file *file, void *fh, struct v4l2_format *fmt) -{ - struct video_device *vdev = video_devdata(file); - struct uvc_device *uvc = video_get_drvdata(vdev); - struct uvc_video *video = &uvc->video; - struct uvc_format *format; - unsigned int imagesize; - unsigned int bpl; - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(uvc_formats); ++i) { - format = &uvc_formats[i]; - if (format->fcc == fmt->fmt.pix.pixelformat) - break; - } - - if (i == ARRAY_SIZE(uvc_formats)) { - uvcg_info(&uvc->func, "Unsupported format 0x%08x.\n", - fmt->fmt.pix.pixelformat); - return -EINVAL; - } - - bpl = format->bpp * fmt->fmt.pix.width / 8; - imagesize = bpl ? bpl * fmt->fmt.pix.height : fmt->fmt.pix.sizeimage; - - video->fcc = format->fcc; - video->bpp = format->bpp; - video->width = fmt->fmt.pix.width; - video->height = fmt->fmt.pix.height; - video->imagesize = imagesize; - - fmt->fmt.pix.field = V4L2_FIELD_NONE; - fmt->fmt.pix.bytesperline = bpl; - fmt->fmt.pix.sizeimage = imagesize; - fmt->fmt.pix.colorspace = V4L2_COLORSPACE_SRGB; - fmt->fmt.pix.priv = 0; - - return 0; -} - static int uvc_v4l2_try_format(struct file *file, void *fh, struct v4l2_format *fmt) { @@ -323,6 +272,27 @@ uvc_v4l2_try_format(struct file *file, void *fh, struct v4l2_format *fmt) return 0; } +static int +uvc_v4l2_set_format(struct file *file, void *fh, struct v4l2_format *fmt) +{ + struct video_device *vdev = video_devdata(file); + struct uvc_device *uvc = video_get_drvdata(vdev); + struct uvc_video *video = &uvc->video; + int ret; + + ret = uvc_v4l2_try_format(file, fh, fmt); + if (ret) + return ret; + + video->fcc = fmt->fmt.pix.pixelformat; + video->bpp = fmt->fmt.pix.bytesperline * 8 / video->width; + video->width = fmt->fmt.pix.width; + video->height = fmt->fmt.pix.height; + video->imagesize = fmt->fmt.pix.sizeimage; + + return ret; +} + static int uvc_v4l2_enum_frameintervals(struct file *file, void *fh, struct v4l2_frmivalenum *fival) diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index f422f9c58ba7..1ea6d2e5b218 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -67,8 +67,27 @@ static bool is_vmpck_empty(struct snp_guest_dev *snp_dev) return true; } +/* + * If an error is received from the host or AMD Secure Processor (ASP) there + * are two options. Either retry the exact same encrypted request or discontinue + * using the VMPCK. + * + * This is because in the current encryption scheme GHCB v2 uses AES-GCM to + * encrypt the requests. The IV for this scheme is the sequence number. GCM + * cannot tolerate IV reuse. + * + * The ASP FW v1.51 only increments the sequence numbers on a successful + * guest<->ASP back and forth and only accepts messages at its exact sequence + * number. + * + * So if the sequence number were to be reused the encryption scheme is + * vulnerable. If the sequence number were incremented for a fresh IV the ASP + * will reject the request. + */ static void snp_disable_vmpck(struct snp_guest_dev *snp_dev) { + dev_alert(snp_dev->dev, "Disabling vmpck_id %d to prevent IV reuse.\n", + vmpck_id); memzero_explicit(snp_dev->vmpck, VMPCK_KEY_LEN); snp_dev->vmpck = NULL; } @@ -321,34 +340,71 @@ static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code, in if (rc) return rc; - /* Call firmware to process the request */ + /* + * Call firmware to process the request. In this function the encrypted + * message enters shared memory with the host. So after this call the + * sequence number must be incremented or the VMPCK must be deleted to + * prevent reuse of the IV. + */ rc = snp_issue_guest_request(exit_code, &snp_dev->input, &err); + + /* + * If the extended guest request fails due to having too small of a + * certificate data buffer, retry the same guest request without the + * extended data request in order to increment the sequence number + * and thus avoid IV reuse. + */ + if (exit_code == SVM_VMGEXIT_EXT_GUEST_REQUEST && + err == SNP_GUEST_REQ_INVALID_LEN) { + const unsigned int certs_npages = snp_dev->input.data_npages; + + exit_code = SVM_VMGEXIT_GUEST_REQUEST; + + /* + * If this call to the firmware succeeds, the sequence number can + * be incremented allowing for continued use of the VMPCK. If + * there is an error reflected in the return value, this value + * is checked further down and the result will be the deletion + * of the VMPCK and the error code being propagated back to the + * user as an ioctl() return code. + */ + rc = snp_issue_guest_request(exit_code, &snp_dev->input, &err); + + /* + * Override the error to inform callers the given extended + * request buffer size was too small and give the caller the + * required buffer size. + */ + err = SNP_GUEST_REQ_INVALID_LEN; + snp_dev->input.data_npages = certs_npages; + } + if (fw_err) *fw_err = err; - if (rc) - return rc; + if (rc) { + dev_alert(snp_dev->dev, + "Detected error from ASP request. rc: %d, fw_err: %llu\n", + rc, *fw_err); + goto disable_vmpck; + } - /* - * The verify_and_dec_payload() will fail only if the hypervisor is - * actively modifying the message header or corrupting the encrypted payload. - * This hints that hypervisor is acting in a bad faith. Disable the VMPCK so that - * the key cannot be used for any communication. The key is disabled to ensure - * that AES-GCM does not use the same IV while encrypting the request payload. - */ rc = verify_and_dec_payload(snp_dev, resp_buf, resp_sz); if (rc) { dev_alert(snp_dev->dev, - "Detected unexpected decode failure, disabling the vmpck_id %d\n", - vmpck_id); - snp_disable_vmpck(snp_dev); - return rc; + "Detected unexpected decode failure from ASP. rc: %d\n", + rc); + goto disable_vmpck; } /* Increment to new message sequence after payload decryption was successful. */ snp_inc_msg_seqno(snp_dev); return 0; + +disable_vmpck: + snp_disable_vmpck(snp_dev); + return rc; } static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index a9543f01184c..dcb510f38dda 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -4663,7 +4663,12 @@ int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, int ret; int i; - ASSERT(!path->nowait); + /* + * The nowait semantics are used only for write paths, where we don't + * use the tree mod log and sequence numbers. + */ + if (time_seq) + ASSERT(!path->nowait); nritems = btrfs_header_nritems(path->nodes[0]); if (nritems == 0) @@ -4683,7 +4688,14 @@ again: if (path->need_commit_sem) { path->need_commit_sem = 0; need_commit_sem = true; - down_read(&fs_info->commit_root_sem); + if (path->nowait) { + if (!down_read_trylock(&fs_info->commit_root_sem)) { + ret = -EAGAIN; + goto done; + } + } else { + down_read(&fs_info->commit_root_sem); + } } ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); } @@ -4759,7 +4771,7 @@ again: next = c; ret = read_block_for_search(root, path, &next, level, slot, &key); - if (ret == -EAGAIN) + if (ret == -EAGAIN && !path->nowait) goto again; if (ret < 0) { @@ -4769,6 +4781,10 @@ again: if (!path->skip_locking) { ret = btrfs_try_tree_read_lock(next); + if (!ret && path->nowait) { + ret = -EAGAIN; + goto done; + } if (!ret && time_seq) { /* * If we don't get the lock, we may be racing @@ -4799,7 +4815,7 @@ again: ret = read_block_for_search(root, path, &next, level, 0, &key); - if (ret == -EAGAIN) + if (ret == -EAGAIN && !path->nowait) goto again; if (ret < 0) { @@ -4807,8 +4823,16 @@ again: goto done; } - if (!path->skip_locking) - btrfs_tree_read_lock(next); + if (!path->skip_locking) { + if (path->nowait) { + if (!btrfs_try_tree_read_lock(next)) { + ret = -EAGAIN; + goto done; + } + } else { + btrfs_tree_read_lock(next); + } + } } ret = 0; done: diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d5dd8bed1488..5ba2e810dc6e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3105,6 +3105,8 @@ static int btrfs_ioctl_get_subvol_info(struct inode *inode, void __user *argp) } } + btrfs_free_path(path); + path = NULL; if (copy_to_user(argp, subvol_info, sizeof(*subvol_info))) ret = -EFAULT; @@ -3194,6 +3196,8 @@ static int btrfs_ioctl_get_subvol_rootref(struct btrfs_root *root, } out: + btrfs_free_path(path); + if (!ret || ret == -EOVERFLOW) { rootrefs->num_items = found; /* update min_treeid for next search */ @@ -3205,7 +3209,6 @@ out: } kfree(rootrefs); - btrfs_free_path(path); return ret; } @@ -4231,6 +4234,8 @@ static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg) ipath->fspath->val[i] = rel_ptr; } + btrfs_free_path(path); + path = NULL; ret = copy_to_user((void __user *)(unsigned long)ipa->fspath, ipath->fspath, size); if (ret) { @@ -4281,21 +4286,20 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, size = min_t(u32, loi->size, SZ_16M); } + inodes = init_data_container(size); + if (IS_ERR(inodes)) { + ret = PTR_ERR(inodes); + goto out_loi; + } + path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto out; } - - inodes = init_data_container(size); - if (IS_ERR(inodes)) { - ret = PTR_ERR(inodes); - inodes = NULL; - goto out; - } - ret = iterate_inodes_from_logical(loi->logical, fs_info, path, inodes, ignore_offset); + btrfs_free_path(path); if (ret == -EINVAL) ret = -ENOENT; if (ret < 0) @@ -4307,7 +4311,6 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, ret = -EFAULT; out: - btrfs_free_path(path); kvfree(inodes); out_loi: kfree(loi); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 9334c3157c22..b74105a10f16 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2951,14 +2951,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, dstgroup->rsv_rfer = inherit->lim.rsv_rfer; dstgroup->rsv_excl = inherit->lim.rsv_excl; - ret = update_qgroup_limit_item(trans, dstgroup); - if (ret) { - qgroup_mark_inconsistent(fs_info); - btrfs_info(fs_info, - "unable to update quota limit for %llu", - dstgroup->qgroupid); - goto unlock; - } + qgroup_dirty(fs_info, dstgroup); } if (srcid) { diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 145c84b44fd0..1c4b693ee4a3 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5702,6 +5702,7 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *dst_path, u64 ext_len; u64 clone_len; u64 clone_data_offset; + bool crossed_src_i_size = false; if (slot >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(clone_root->root, path); @@ -5759,8 +5760,10 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *dst_path, if (key.offset >= clone_src_i_size) break; - if (key.offset + ext_len > clone_src_i_size) + if (key.offset + ext_len > clone_src_i_size) { ext_len = clone_src_i_size - key.offset; + crossed_src_i_size = true; + } clone_data_offset = btrfs_file_extent_offset(leaf, ei); if (btrfs_file_extent_disk_bytenr(leaf, ei) == disk_byte) { @@ -5821,6 +5824,25 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_path *dst_path, ret = send_clone(sctx, offset, clone_len, clone_root); } + } else if (crossed_src_i_size && clone_len < len) { + /* + * If we are at i_size of the clone source inode and we + * can not clone from it, terminate the loop. This is + * to avoid sending two write operations, one with a + * length matching clone_len and the final one after + * this loop with a length of len - clone_len. + * + * When using encoded writes (BTRFS_SEND_FLAG_COMPRESSED + * was passed to the send ioctl), this helps avoid + * sending an encoded write for an offset that is not + * sector size aligned, in case the i_size of the source + * inode is not sector size aligned. That will make the + * receiver fallback to decompression of the data and + * writing it using regular buffered IO, therefore while + * not incorrect, it's not optimal due decompression and + * possible re-compression at the receiver. + */ + break; } else { ret = send_extent_data(sctx, dst_path, offset, clone_len); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 699b54b3acaa..74fef1f49c35 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -2321,8 +2321,11 @@ int __init btrfs_init_sysfs(void) #ifdef CONFIG_BTRFS_DEBUG ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_debug_feature_attr_group); - if (ret) - goto out2; + if (ret) { + sysfs_unmerge_group(&btrfs_kset->kobj, + &btrfs_static_feature_attr_group); + goto out_remove_group; + } #endif return 0; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 813986e38258..c3cf3dabe0b1 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3694,15 +3694,29 @@ static int process_dir_items_leaf(struct btrfs_trans_handle *trans, u64 *last_old_dentry_offset) { struct btrfs_root *log = inode->root->log_root; - struct extent_buffer *src = path->nodes[0]; - const int nritems = btrfs_header_nritems(src); + struct extent_buffer *src; + const int nritems = btrfs_header_nritems(path->nodes[0]); const u64 ino = btrfs_ino(inode); bool last_found = false; int batch_start = 0; int batch_size = 0; int i; - for (i = path->slots[0]; i < nritems; i++) { + /* + * We need to clone the leaf, release the read lock on it, and use the + * clone before modifying the log tree. See the comment at copy_items() + * about why we need to do this. + */ + src = btrfs_clone_extent_buffer(path->nodes[0]); + if (!src) + return -ENOMEM; + + i = path->slots[0]; + btrfs_release_path(path); + path->nodes[0] = src; + path->slots[0] = i; + + for (; i < nritems; i++) { struct btrfs_dir_item *di; struct btrfs_key key; int ret; @@ -4303,7 +4317,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, { struct btrfs_root *log = inode->root->log_root; struct btrfs_file_extent_item *extent; - struct extent_buffer *src = src_path->nodes[0]; + struct extent_buffer *src; int ret = 0; struct btrfs_key *ins_keys; u32 *ins_sizes; @@ -4314,6 +4328,43 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, const bool skip_csum = (inode->flags & BTRFS_INODE_NODATASUM); const u64 i_size = i_size_read(&inode->vfs_inode); + /* + * To keep lockdep happy and avoid deadlocks, clone the source leaf and + * use the clone. This is because otherwise we would be changing the log + * tree, to insert items from the subvolume tree or insert csum items, + * while holding a read lock on a leaf from the subvolume tree, which + * creates a nasty lock dependency when COWing log tree nodes/leaves: + * + * 1) Modifying the log tree triggers an extent buffer allocation while + * holding a write lock on a parent extent buffer from the log tree. + * Allocating the pages for an extent buffer, or the extent buffer + * struct, can trigger inode eviction and finally the inode eviction + * will trigger a release/remove of a delayed node, which requires + * taking the delayed node's mutex; + * + * 2) Allocating a metadata extent for a log tree can trigger the async + * reclaim thread and make us wait for it to release enough space and + * unblock our reservation ticket. The reclaim thread can start + * flushing delayed items, and that in turn results in the need to + * lock delayed node mutexes and in the need to write lock extent + * buffers of a subvolume tree - all this while holding a write lock + * on the parent extent buffer in the log tree. + * + * So one task in scenario 1) running in parallel with another task in + * scenario 2) could lead to a deadlock, one wanting to lock a delayed + * node mutex while having a read lock on a leaf from the subvolume, + * while the other is holding the delayed node's mutex and wants to + * write lock the same subvolume leaf for flushing delayed items. + */ + src = btrfs_clone_extent_buffer(src_path->nodes[0]); + if (!src) + return -ENOMEM; + + i = src_path->slots[0]; + btrfs_release_path(src_path); + src_path->nodes[0] = src; + src_path->slots[0] = i; + ins_data = kmalloc(nr * sizeof(struct btrfs_key) + nr * sizeof(u32), GFP_NOFS); if (!ins_data) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 1912abf6d020..c9e2b0c85309 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -134,7 +134,8 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones, super[i] = page_address(page[i]); } - if (super[0]->generation > super[1]->generation) + if (btrfs_super_generation(super[0]) > + btrfs_super_generation(super[1])) sector = zones[1].start; else sector = zones[0].start; @@ -466,7 +467,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) goto out; } - zones = kcalloc(BTRFS_REPORT_NR_ZONES, sizeof(struct blk_zone), GFP_KERNEL); + zones = kvcalloc(BTRFS_REPORT_NR_ZONES, sizeof(struct blk_zone), GFP_KERNEL); if (!zones) { ret = -ENOMEM; goto out; @@ -585,7 +586,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) } - kfree(zones); + kvfree(zones); switch (bdev_zoned_model(bdev)) { case BLK_ZONED_HM: @@ -617,7 +618,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) return 0; out: - kfree(zones); + kvfree(zones); out_free_zone_info: btrfs_destroy_dev_zone_info(device); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index fe220686bba4..712a43161448 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1281,7 +1281,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, rc = filemap_write_and_wait_range(src_inode->i_mapping, off, off + len - 1); if (rc) - goto out; + goto unlock; /* should we flush first and last page first */ truncate_inode_pages(&target_inode->i_data, 0); @@ -1297,6 +1297,8 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, * that target is updated on the server */ CIFS_I(target_inode)->time = 0; + +unlock: /* although unlocking in the reverse order from locking is not * strictly necessary here it is a little cleaner to be consistent */ diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 92e4278ec35d..9e7d9f0baa18 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -302,14 +302,14 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) /* now drop the ref to the current iface */ if (old_iface && iface) { - kref_put(&old_iface->refcount, release_iface); cifs_dbg(FYI, "replacing iface: %pIS with %pIS\n", &old_iface->sockaddr, &iface->sockaddr); - } else if (old_iface) { kref_put(&old_iface->refcount, release_iface); + } else if (old_iface) { cifs_dbg(FYI, "releasing ref to iface: %pIS\n", &old_iface->sockaddr); + kref_put(&old_iface->refcount, release_iface); } else { WARN_ON(!iface); cifs_dbg(FYI, "adding new iface: %pIS\n", &iface->sockaddr); diff --git a/fs/file.c b/fs/file.c index 5f9c802a5d8d..c942c89ca4cd 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1003,7 +1003,16 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask) struct files_struct *files = current->files; struct file *file; - if (atomic_read(&files->count) == 1) { + /* + * If another thread is concurrently calling close_fd() followed + * by put_files_struct(), we must not observe the old table + * entry combined with the new refcount - otherwise we could + * return a file that is concurrently being freed. + * + * atomic_read_acquire() pairs with atomic_dec_and_test() in + * put_files_struct(). + */ + if (atomic_read_acquire(&files->count) == 1) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return 0; diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 8de970d6146f..94b8ed4ef870 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -1794,9 +1794,9 @@ int ksmbd_vfs_copy_file_ranges(struct ksmbd_work *work, ret = vfs_copy_file_range(src_fp->filp, src_off, dst_fp->filp, dst_off, len, 0); if (ret == -EOPNOTSUPP || ret == -EXDEV) - ret = generic_copy_file_range(src_fp->filp, src_off, - dst_fp->filp, dst_off, - len, 0); + ret = vfs_copy_file_range(src_fp->filp, src_off, + dst_fp->filp, dst_off, len, + COPY_FILE_SPLICE); if (ret < 0) return ret; diff --git a/fs/namei.c b/fs/namei.c index 578c2110df02..9155ecb547ce 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3591,6 +3591,7 @@ static int vfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir = d_inode(parentpath->dentry); struct inode *inode; int error; + int open_flag = file->f_flags; /* we want directory to be writable */ error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); @@ -3613,7 +3614,7 @@ static int vfs_tmpfile(struct user_namespace *mnt_userns, if (error) return error; inode = file_inode(file); - if (!(file->f_flags & O_EXCL)) { + if (!(open_flag & O_EXCL)) { spin_lock(&inode->i_lock); inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index f650afedd67f..849a720ab43f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -596,8 +596,8 @@ ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, ret = vfs_copy_file_range(src, src_pos, dst, dst_pos, count, 0); if (ret == -EOPNOTSUPP || ret == -EXDEV) - ret = generic_copy_file_range(src, src_pos, dst, dst_pos, - count, 0); + ret = vfs_copy_file_range(src, src_pos, dst, dst_pos, count, + COPY_FILE_SPLICE); return ret; } @@ -871,10 +871,11 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct svc_rqst *rqstp = sd->u.data; struct page *page = buf->page; // may be a compound one unsigned offset = buf->offset; + struct page *last_page; - page += offset / PAGE_SIZE; - for (int i = sd->len; i > 0; i -= PAGE_SIZE) - svc_rqst_replace_page(rqstp, page++); + last_page = page + (offset + sd->len - 1) / PAGE_SIZE; + for (page += offset / PAGE_SIZE; page <= last_page; page++) + svc_rqst_replace_page(rqstp, page); if (rqstp->rq_res.page_len == 0) // first call rqstp->rq_res.page_base = offset % PAGE_SIZE; rqstp->rq_res.page_len += sd->len; diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 77ff8e95421f..dc359b56fdfa 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -495,14 +495,22 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum, int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum) { struct buffer_head *bh; + void *kaddr; + struct nilfs_segment_usage *su; int ret; + down_write(&NILFS_MDT(sufile)->mi_sem); ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh); if (!ret) { mark_buffer_dirty(bh); nilfs_mdt_mark_dirty(sufile); + kaddr = kmap_atomic(bh->b_page); + su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); + nilfs_segment_usage_set_dirty(su); + kunmap_atomic(kaddr); brelse(bh); } + up_write(&NILFS_MDT(sufile)->mi_sem); return ret; } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 5101131e6047..440960110a42 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -115,7 +115,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #endif show_val_kb(m, "PageTables: ", global_node_page_state(NR_PAGETABLE)); - show_val_kb(m, "SecPageTables: ", + show_val_kb(m, "SecPageTables: ", global_node_page_state(NR_SECONDARY_PAGETABLE)); show_val_kb(m, "NFS_Unstable: ", 0); diff --git a/fs/read_write.c b/fs/read_write.c index 328ce8cf9a85..24b9668d6377 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1388,6 +1388,8 @@ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { + lockdep_assert(sb_write_started(file_inode(file_out)->i_sb)); + return do_splice_direct(file_in, &pos_in, file_out, &pos_out, len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); } @@ -1424,7 +1426,9 @@ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, * and several different sets of file_operations, but they all end up * using the same ->copy_file_range() function pointer. */ - if (file_out->f_op->copy_file_range) { + if (flags & COPY_FILE_SPLICE) { + /* cross sb splice is allowed */ + } else if (file_out->f_op->copy_file_range) { if (file_in->f_op->copy_file_range != file_out->f_op->copy_file_range) return -EXDEV; @@ -1474,8 +1478,9 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, size_t len, unsigned int flags) { ssize_t ret; + bool splice = flags & COPY_FILE_SPLICE; - if (flags != 0) + if (flags & ~COPY_FILE_SPLICE) return -EINVAL; ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, @@ -1501,14 +1506,14 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * same sb using clone, but for filesystems where both clone and copy * are supported (e.g. nfs,cifs), we only call the copy method. */ - if (file_out->f_op->copy_file_range) { + if (!splice && file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); goto done; } - if (file_in->f_op->remap_file_range && + if (!splice && file_in->f_op->remap_file_range && file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, @@ -1528,6 +1533,8 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * consistent story about which filesystems support copy_file_range() * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). + * + * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE. */ ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); @@ -1582,6 +1589,10 @@ SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, pos_out = f_out.file->f_pos; } + ret = -EINVAL; + if (flags != 0) + goto out; + ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len, flags); if (ret > 0) { diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index abc9a85106f2..2c53fbb8d918 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -40,6 +40,13 @@ static void zonefs_account_active(struct inode *inode) if (zi->i_ztype != ZONEFS_ZTYPE_SEQ) return; + /* + * For zones that transitioned to the offline or readonly condition, + * we only need to clear the active state. + */ + if (zi->i_flags & (ZONEFS_ZONE_OFFLINE | ZONEFS_ZONE_READONLY)) + goto out; + /* * If the zone is active, that is, if it is explicitly open or * partially written, check if it was already accounted as active. @@ -53,6 +60,7 @@ static void zonefs_account_active(struct inode *inode) return; } +out: /* The zone is not active. If it was, update the active count */ if (zi->i_flags & ZONEFS_ZONE_ACTIVE) { zi->i_flags &= ~ZONEFS_ZONE_ACTIVE; @@ -324,6 +332,7 @@ static loff_t zonefs_check_zone_condition(struct inode *inode, inode->i_flags |= S_IMMUTABLE; inode->i_mode &= ~0777; zone->wp = zone->start; + zi->i_flags |= ZONEFS_ZONE_OFFLINE; return 0; case BLK_ZONE_COND_READONLY: /* @@ -342,8 +351,10 @@ static loff_t zonefs_check_zone_condition(struct inode *inode, zone->cond = BLK_ZONE_COND_OFFLINE; inode->i_mode &= ~0777; zone->wp = zone->start; + zi->i_flags |= ZONEFS_ZONE_OFFLINE; return 0; } + zi->i_flags |= ZONEFS_ZONE_READONLY; inode->i_mode &= ~0222; return i_size_read(inode); case BLK_ZONE_COND_FULL: @@ -1922,18 +1933,18 @@ static int __init zonefs_init(void) if (ret) return ret; - ret = register_filesystem(&zonefs_type); + ret = zonefs_sysfs_init(); if (ret) goto destroy_inodecache; - ret = zonefs_sysfs_init(); + ret = register_filesystem(&zonefs_type); if (ret) - goto unregister_fs; + goto sysfs_exit; return 0; -unregister_fs: - unregister_filesystem(&zonefs_type); +sysfs_exit: + zonefs_sysfs_exit(); destroy_inodecache: zonefs_destroy_inodecache(); @@ -1942,9 +1953,9 @@ destroy_inodecache: static void __exit zonefs_exit(void) { + unregister_filesystem(&zonefs_type); zonefs_sysfs_exit(); zonefs_destroy_inodecache(); - unregister_filesystem(&zonefs_type); } MODULE_AUTHOR("Damien Le Moal"); diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h index 4b3de66c3233..1dbe78119ff1 100644 --- a/fs/zonefs/zonefs.h +++ b/fs/zonefs/zonefs.h @@ -39,8 +39,10 @@ static inline enum zonefs_ztype zonefs_zone_type(struct blk_zone *zone) return ZONEFS_ZTYPE_SEQ; } -#define ZONEFS_ZONE_OPEN (1 << 0) -#define ZONEFS_ZONE_ACTIVE (1 << 1) +#define ZONEFS_ZONE_OPEN (1U << 0) +#define ZONEFS_ZONE_ACTIVE (1U << 1) +#define ZONEFS_ZONE_OFFLINE (1U << 2) +#define ZONEFS_ZONE_READONLY (1U << 3) /* * In-memory inode data. diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 9f6e25467844..444236dadcf0 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -20,7 +20,6 @@ struct fault_attr { atomic_t space; unsigned long verbose; bool task_filter; - bool no_warn; unsigned long stacktrace_depth; unsigned long require_start; unsigned long require_end; @@ -32,6 +31,10 @@ struct fault_attr { struct dentry *dname; }; +enum fault_flags { + FAULT_NOWARN = 1 << 0, +}; + #define FAULT_ATTR_INITIALIZER { \ .interval = 1, \ .times = ATOMIC_INIT(1), \ @@ -40,11 +43,11 @@ struct fault_attr { .ratelimit_state = RATELIMIT_STATE_INIT_DISABLED, \ .verbose = 2, \ .dname = NULL, \ - .no_warn = false, \ } #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER int setup_fault_attr(struct fault_attr *attr, char *str); +bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags); bool should_fail(struct fault_attr *attr, ssize_t size); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS diff --git a/include/linux/fs.h b/include/linux/fs.h index c913106fdd65..36febade5bea 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2089,6 +2089,14 @@ struct dir_context { */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) +/* + * These flags control the behavior of vfs_copy_file_range(). + * They are not available to the user via syscall. + * + * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops + */ +#define COPY_FILE_SPLICE (1 << 0) + struct iov_iter; struct io_uring_cmd; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 18592bdf4c1b..637a60607c7d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -776,6 +776,7 @@ struct kvm { struct srcu_struct srcu; struct srcu_struct irq_srcu; pid_t userspace_pid; + bool override_halt_poll_ns; unsigned int max_halt_poll_ns; u32 dirty_ring_size; bool vm_bugged; diff --git a/include/linux/license.h b/include/linux/license.h index 7cce390f120b..ad937f57f2cb 100644 --- a/include/linux/license.h +++ b/include/linux/license.h @@ -2,6 +2,8 @@ #ifndef __LICENSE_H #define __LICENSE_H +#include + static inline int license_is_gpl_compatible(const char *license) { return (strcmp(license, "GPL") == 0 diff --git a/include/sound/sof/dai.h b/include/sound/sof/dai.h index 83fd81c82e4c..9fbd3832bcdc 100644 --- a/include/sound/sof/dai.h +++ b/include/sound/sof/dai.h @@ -84,8 +84,8 @@ enum sof_ipc_dai_type { SOF_DAI_AMD_BT, /**< AMD ACP BT*/ SOF_DAI_AMD_SP, /**< AMD ACP SP */ SOF_DAI_AMD_DMIC, /**< AMD ACP DMIC */ - SOF_DAI_AMD_HS, /**< Amd HS */ SOF_DAI_MEDIATEK_AFE, /**< Mediatek AFE */ + SOF_DAI_AMD_HS, /**< Amd HS */ }; /* general purpose DAI configuration */ diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 935af4947917..760455dfa860 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -171,15 +171,15 @@ TRACE_EVENT(mm_collapse_huge_page_swapin, TRACE_EVENT(mm_khugepaged_scan_file, - TP_PROTO(struct mm_struct *mm, struct page *page, const char *filename, + TP_PROTO(struct mm_struct *mm, struct page *page, struct file *file, int present, int swap, int result), - TP_ARGS(mm, page, filename, present, swap, result), + TP_ARGS(mm, page, file, present, swap, result), TP_STRUCT__entry( __field(struct mm_struct *, mm) __field(unsigned long, pfn) - __string(filename, filename) + __string(filename, file->f_path.dentry->d_iname) __field(int, present) __field(int, swap) __field(int, result) @@ -188,7 +188,7 @@ TRACE_EVENT(mm_khugepaged_scan_file, TP_fast_assign( __entry->mm = mm; __entry->pfn = page ? page_to_pfn(page) : -1; - __assign_str(filename, filename); + __assign_str(filename, file->f_path.dentry->d_iname); __entry->present = present; __entry->swap = swap; __entry->result = result; diff --git a/init/Kconfig b/init/Kconfig index 8b9ccff2b17a..971df9846f20 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -87,7 +87,7 @@ config CC_HAS_ASM_GOTO_OUTPUT config CC_HAS_ASM_GOTO_TIED_OUTPUT depends on CC_HAS_ASM_GOTO_OUTPUT # Detect buggy gcc and clang, fixed in gcc-11 clang-14. - def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .\n": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null) + def_bool $(success,echo 'int foo(int *x) { asm goto (".long (%l[bar]) - .": "+m"(*x) ::: bar); return *x; bar: return 0; }' | $CC -x c - -c -o /dev/null) config TOOLS_SUPPORT_RELR def_bool $(success,env "CC=$(CC)" "LD=$(LD)" "NM=$(NM)" "OBJCOPY=$(OBJCOPY)" $(srctree)/scripts/tools-support-relr.sh) diff --git a/io_uring/filetable.c b/io_uring/filetable.c index 7b473259f3f4..68dfc6936aa7 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -101,8 +101,6 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, err: if (needs_switch) io_rsrc_node_switch(ctx, ctx->file_data); - if (ret) - fput(file); return ret; } diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index cef5ff924e63..50bc3af44953 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -238,9 +238,14 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx) static inline int io_run_task_work(void) { + /* + * Always check-and-clear the task_work notification signal. With how + * signaling works for task_work, we can find it set with nothing to + * run. We need to clear it for that case, like get_signal() does. + */ + if (test_thread_flag(TIF_NOTIFY_SIGNAL)) + clear_notify_signal(); if (task_work_pending(current)) { - if (test_thread_flag(TIF_NOTIFY_SIGNAL)) - clear_notify_signal(); __set_current_state(TASK_RUNNING); task_work_run(); return 1; diff --git a/io_uring/poll.c b/io_uring/poll.c index 055632e9092a..d9bf1767867e 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -40,7 +40,14 @@ struct io_poll_table { }; #define IO_POLL_CANCEL_FLAG BIT(31) -#define IO_POLL_REF_MASK GENMASK(30, 0) +#define IO_POLL_RETRY_FLAG BIT(30) +#define IO_POLL_REF_MASK GENMASK(29, 0) + +/* + * We usually have 1-2 refs taken, 128 is more than enough and we want to + * maximise the margin between this amount and the moment when it overflows. + */ +#define IO_POLL_REF_BIAS 128 #define IO_WQE_F_DOUBLE 1 @@ -58,6 +65,21 @@ static inline bool wqe_is_double(struct wait_queue_entry *wqe) return priv & IO_WQE_F_DOUBLE; } +static bool io_poll_get_ownership_slowpath(struct io_kiocb *req) +{ + int v; + + /* + * poll_refs are already elevated and we don't have much hope for + * grabbing the ownership. Instead of incrementing set a retry flag + * to notify the loop that there might have been some change. + */ + v = atomic_fetch_or(IO_POLL_RETRY_FLAG, &req->poll_refs); + if (v & IO_POLL_REF_MASK) + return false; + return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); +} + /* * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can * bump it and acquire ownership. It's disallowed to modify requests while not @@ -66,6 +88,8 @@ static inline bool wqe_is_double(struct wait_queue_entry *wqe) */ static inline bool io_poll_get_ownership(struct io_kiocb *req) { + if (unlikely(atomic_read(&req->poll_refs) >= IO_POLL_REF_BIAS)) + return io_poll_get_ownership_slowpath(req); return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK); } @@ -235,6 +259,16 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) */ if ((v & IO_POLL_REF_MASK) != 1) req->cqe.res = 0; + if (v & IO_POLL_RETRY_FLAG) { + req->cqe.res = 0; + /* + * We won't find new events that came in between + * vfs_poll and the ref put unless we clear the flag + * in advance. + */ + atomic_andnot(IO_POLL_RETRY_FLAG, &req->poll_refs); + v &= ~IO_POLL_RETRY_FLAG; + } /* the mask was stashed in __io_poll_execute */ if (!req->cqe.res) { @@ -274,7 +308,8 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) * Release all references, retry if someone tried to restart * task_work while we were executing it. */ - } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs)); + } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs) & + IO_POLL_REF_MASK); return IOU_POLL_NO_ACTION; } @@ -518,7 +553,6 @@ static int __io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags) { struct io_ring_ctx *ctx = req->ctx; - int v; INIT_HLIST_NODE(&req->hash_node); req->work.cancel_seq = atomic_read(&ctx->cancel_seq); @@ -586,11 +620,10 @@ static int __io_arm_poll_handler(struct io_kiocb *req, if (ipt->owning) { /* - * Release ownership. If someone tried to queue a tw while it was - * locked, kick it off for them. + * Try to release ownership. If we see a change of state, e.g. + * poll was waken up, queue up a tw, it'll deal with it. */ - v = atomic_dec_return(&req->poll_refs); - if (unlikely(v & IO_POLL_REF_MASK)) + if (atomic_cmpxchg(&req->poll_refs, 1, 0) != 1) __io_poll_execute(req, 0); } return 0; diff --git a/ipc/shm.c b/ipc/shm.c index 7d86f058fb86..bd2fcc4d454e 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -275,10 +275,8 @@ static inline void shm_rmid(struct shmid_kernel *s) } -static int __shm_open(struct vm_area_struct *vma) +static int __shm_open(struct shm_file_data *sfd) { - struct file *file = vma->vm_file; - struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); @@ -302,7 +300,15 @@ static int __shm_open(struct vm_area_struct *vma) /* This is called by fork, once for every shm attach. */ static void shm_open(struct vm_area_struct *vma) { - int err = __shm_open(vma); + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + int err; + + /* Always call underlying open if present */ + if (sfd->vm_ops->open) + sfd->vm_ops->open(vma); + + err = __shm_open(sfd); /* * We raced in the idr lookup or with shm_destroy(). * Either way, the ID is busted. @@ -359,10 +365,8 @@ static bool shm_may_destroy(struct shmid_kernel *shp) * The descriptor has already been removed from the current->mm->mmap list * and will later be kfree()d. */ -static void shm_close(struct vm_area_struct *vma) +static void __shm_close(struct shm_file_data *sfd) { - struct file *file = vma->vm_file; - struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; struct ipc_namespace *ns = sfd->ns; @@ -388,6 +392,18 @@ done: up_write(&shm_ids(ns).rwsem); } +static void shm_close(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + + /* Always call underlying close if present */ + if (sfd->vm_ops->close) + sfd->vm_ops->close(vma); + + __shm_close(sfd); +} + /* Called with ns->shm_ids(ns).rwsem locked */ static int shm_try_destroy_orphaned(int id, void *p, void *data) { @@ -583,13 +599,13 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma) * IPC ID that was removed, and possibly even reused by another shm * segment already. Propagate this case as an error to caller. */ - ret = __shm_open(vma); + ret = __shm_open(sfd); if (ret) return ret; ret = call_mmap(sfd->file, vma); if (ret) { - shm_close(vma); + __shm_close(sfd); return ret; } sfd->vm_ops = vma->vm_ops; diff --git a/kernel/events/core.c b/kernel/events/core.c index 2ce6a93b5eb3..8598325c4713 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9259,6 +9259,19 @@ int perf_event_account_interrupt(struct perf_event *event) return __perf_event_account_interrupt(event, 1); } +static inline bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs) +{ + /* + * Due to interrupt latency (AKA "skid"), we may enter the + * kernel before taking an overflow, even if the PMU is only + * counting user events. + */ + if (event->attr.exclude_kernel && !user_mode(regs)) + return false; + + return true; +} + /* * Generic event overflow handling, sampling. */ @@ -9292,6 +9305,13 @@ static int __perf_event_overflow(struct perf_event *event, } if (event->attr.sigtrap) { + /* + * The desired behaviour of sigtrap vs invalid samples is a bit + * tricky; on the one hand, one should not loose the SIGTRAP if + * it is the first event, on the other hand, we should also not + * trigger the WARN or override the data address. + */ + bool valid_sample = sample_is_allowed(event, regs); unsigned int pending_id = 1; if (regs) @@ -9299,7 +9319,7 @@ static int __perf_event_overflow(struct perf_event *event, if (!event->pending_sigtrap) { event->pending_sigtrap = pending_id; local_inc(&event->ctx->nr_pending); - } else if (event->attr.exclude_kernel) { + } else if (event->attr.exclude_kernel && valid_sample) { /* * Should not be able to return to user space without * consuming pending_sigtrap; with exceptions: @@ -9314,7 +9334,10 @@ static int __perf_event_overflow(struct perf_event *event, */ WARN_ON_ONCE(event->pending_sigtrap != pending_id); } - event->pending_addr = data->addr; + + event->pending_addr = 0; + if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR)) + event->pending_addr = data->addr; irq_work_queue(&event->pending_irq); } diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c index cbb0bed958ab..7670a811a565 100644 --- a/kernel/gcov/clang.c +++ b/kernel/gcov/clang.c @@ -280,6 +280,8 @@ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src) for (i = 0; i < sfn_ptr->num_counters; i++) dfn_ptr->counters[i] += sfn_ptr->counters[i]; + + sfn_ptr = list_next_entry(sfn_ptr, head); } } diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index cce5023be96b..919f8e9a04d7 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -25,9 +25,6 @@ struct sugov_policy { unsigned int next_freq; unsigned int cached_raw_freq; - /* max CPU capacity, which is equal for all CPUs in freq. domain */ - unsigned long max; - /* The next fields are only needed if fast switch cannot be used: */ struct irq_work irq_work; struct kthread_work work; @@ -51,6 +48,7 @@ struct sugov_cpu { unsigned long util; unsigned long bw_dl; + unsigned long max; /* The field below is for single-CPU policies only: */ #ifdef CONFIG_NO_HZ_COMMON @@ -160,6 +158,7 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); + sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu); sg_cpu->bw_dl = cpu_bw_dl(rq); sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu), FREQUENCY_UTIL, NULL); @@ -254,7 +253,6 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, */ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time) { - struct sugov_policy *sg_policy = sg_cpu->sg_policy; unsigned long boost; /* No boost currently required */ @@ -282,8 +280,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time) * sg_cpu->util is already in capacity scale; convert iowait_boost * into the same scale so we can compare. */ - boost = sg_cpu->iowait_boost * sg_policy->max; - boost >>= SCHED_CAPACITY_SHIFT; + boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT; boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL); if (sg_cpu->util < boost) sg_cpu->util = boost; @@ -340,7 +337,7 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time, if (!sugov_update_single_common(sg_cpu, time, flags)) return; - next_f = get_next_freq(sg_policy, sg_cpu->util, sg_policy->max); + next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max); /* * Do not reduce the frequency if the CPU has not been idle * recently, as the reduction is likely to be premature then. @@ -376,7 +373,6 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, unsigned int flags) { struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); - struct sugov_policy *sg_policy = sg_cpu->sg_policy; unsigned long prev_util = sg_cpu->util; /* @@ -403,8 +399,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, sg_cpu->util = prev_util; cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl), - map_util_perf(sg_cpu->util), - sg_policy->max); + map_util_perf(sg_cpu->util), sg_cpu->max); sg_cpu->sg_policy->last_freq_update_time = time; } @@ -413,19 +408,25 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) { struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; - unsigned long util = 0; + unsigned long util = 0, max = 1; unsigned int j; for_each_cpu(j, policy->cpus) { struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j); + unsigned long j_util, j_max; sugov_get_util(j_sg_cpu); sugov_iowait_apply(j_sg_cpu, time); + j_util = j_sg_cpu->util; + j_max = j_sg_cpu->max; - util = max(j_sg_cpu->util, util); + if (j_util * max > j_max * util) { + util = j_util; + max = j_max; + } } - return get_next_freq(sg_policy, util, sg_policy->max); + return get_next_freq(sg_policy, util, max); } static void @@ -751,7 +752,7 @@ static int sugov_start(struct cpufreq_policy *policy) { struct sugov_policy *sg_policy = policy->governor_data; void (*uu)(struct update_util_data *data, u64 time, unsigned int flags); - unsigned int cpu = cpumask_first(policy->cpus); + unsigned int cpu; sg_policy->freq_update_delay_ns = sg_policy->tunables->rate_limit_us * NSEC_PER_USEC; sg_policy->last_freq_update_time = 0; @@ -759,7 +760,6 @@ static int sugov_start(struct cpufreq_policy *policy) sg_policy->work_in_progress = false; sg_policy->limits_changed = false; sg_policy->cached_raw_freq = 0; - sg_policy->max = arch_scale_cpu_capacity(cpu); sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c3c0b077ade3..a1005415f0f4 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2107,6 +2107,7 @@ config KPROBES_SANITY_TEST depends on DEBUG_KERNEL depends on KPROBES depends on KUNIT + select STACKTRACE if ARCH_CORRECT_STACKTRACE_ON_KRETPROBE default KUNIT_ALL_TESTS help This option provides for testing basic kprobes functionality on diff --git a/lib/fault-inject.c b/lib/fault-inject.c index 96e092de5b72..adb2f9355ee6 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -41,9 +41,6 @@ EXPORT_SYMBOL_GPL(setup_fault_attr); static void fail_dump(struct fault_attr *attr) { - if (attr->no_warn) - return; - if (attr->verbose > 0 && __ratelimit(&attr->ratelimit_state)) { printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure.\n" "name %pd, interval %lu, probability %lu, " @@ -103,7 +100,7 @@ static inline bool fail_stacktrace(struct fault_attr *attr) * http://www.nongnu.org/failmalloc/ */ -bool should_fail(struct fault_attr *attr, ssize_t size) +bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags) { if (in_task()) { unsigned int fail_nth = READ_ONCE(current->fail_nth); @@ -146,13 +143,19 @@ bool should_fail(struct fault_attr *attr, ssize_t size) return false; fail: - fail_dump(attr); + if (!(flags & FAULT_NOWARN)) + fail_dump(attr); if (atomic_read(&attr->times) != -1) atomic_dec_not_zero(&attr->times); return true; } + +bool should_fail(struct fault_attr *attr, ssize_t size) +{ + return should_fail_ex(attr, size, 0); +} EXPORT_SYMBOL_GPL(should_fail); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS diff --git a/lib/vdso/Makefile b/lib/vdso/Makefile index c415a685d61b..e814061d6aa0 100644 --- a/lib/vdso/Makefile +++ b/lib/vdso/Makefile @@ -17,6 +17,6 @@ $(error ARCH_REL_TYPE_ABS is not set) endif quiet_cmd_vdso_check = VDSOCHK $@ - cmd_vdso_check = if $(OBJDUMP) -R $@ | egrep -h "$(ARCH_REL_TYPE_ABS)"; \ + cmd_vdso_check = if $(OBJDUMP) -R $@ | grep -E -h "$(ARCH_REL_TYPE_ABS)"; \ then (echo >&2 "$@: dynamic relocations are not supported"; \ rm -f $@; /bin/false); fi diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 9f1219a67e3f..5ce403378c20 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -2339,6 +2339,10 @@ static int damon_sysfs_upd_schemes_stats(struct damon_sysfs_kdamond *kdamond) damon_for_each_scheme(scheme, ctx) { struct damon_sysfs_stats *sysfs_stats; + /* user could have removed the scheme sysfs dir */ + if (schemes_idx >= sysfs_schemes->nr) + break; + sysfs_stats = sysfs_schemes->schemes_arr[schemes_idx++]->stats; sysfs_stats->nr_tried = scheme->stat.nr_tried; sysfs_stats->sz_tried = scheme->stat.sz_tried; diff --git a/mm/failslab.c b/mm/failslab.c index 58df9789f1d2..ffc420c0e767 100644 --- a/mm/failslab.c +++ b/mm/failslab.c @@ -16,6 +16,8 @@ static struct { bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags) { + int flags = 0; + /* No fault-injection for bootstrap cache */ if (unlikely(s == kmem_cache)) return false; @@ -30,10 +32,16 @@ bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags) if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB)) return false; + /* + * In some cases, it expects to specify __GFP_NOWARN + * to avoid printing any information(not just a warning), + * thus avoiding deadlocks. See commit 6b9dbedbe349 for + * details. + */ if (gfpflags & __GFP_NOWARN) - failslab.attr.no_warn = true; + flags |= FAULT_NOWARN; - return should_fail(&failslab.attr, s->object_size); + return should_fail_ex(&failslab.attr, s->object_size, flags); } static int __init setup_failslab(char *str) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e48f8ef45b17..f1385c3b6c96 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1800,6 +1800,7 @@ static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, /* we rely on prep_new_huge_page to set the destructor */ set_compound_order(page, order); + __ClearPageReserved(page); __SetPageHead(page); for (i = 0; i < nr_pages; i++) { p = nth_page(page, i); @@ -1816,7 +1817,8 @@ static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, * on the head page when they need know if put_page() is needed * after get_user_pages(). */ - __ClearPageReserved(p); + if (i != 0) /* head page cleared above */ + __ClearPageReserved(p); /* * Subtle and very unlikely * diff --git a/mm/kfence/report.c b/mm/kfence/report.c index 7e496856c2eb..46ecea18c4ca 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -75,18 +75,23 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfence_") || str_has_prefix(buf, ARCH_FUNC_PREFIX "__kfence_") || + str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmem_cache_free") || !strncmp(buf, ARCH_FUNC_PREFIX "__slab_free", len)) { /* - * In case of tail calls from any of the below - * to any of the above. + * In case of tail calls from any of the below to any of + * the above, optimized by the compiler such that the + * stack trace would omit the initial entry point below. */ fallback = skipnr + 1; } - /* Also the *_bulk() variants by only checking prefixes. */ + /* + * The below list should only include the initial entry points + * into the slab allocators. Includes the *_bulk() variants by + * checking prefixes. + */ if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfree") || str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_free") || - str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmem_cache_free") || str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmalloc") || str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_alloc")) goto found; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 4734315f7940..a8d5ef2a77d2 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -97,8 +97,8 @@ struct collapse_control { /* Num pages scanned per node */ u32 node_load[MAX_NUMNODES]; - /* Last target selected in hpage_collapse_find_target_node() */ - int last_target_node; + /* nodemask for allocation fallback */ + nodemask_t alloc_nmask; }; /** @@ -734,7 +734,6 @@ static void khugepaged_alloc_sleep(void) struct collapse_control khugepaged_collapse_control = { .is_khugepaged = true, - .last_target_node = NUMA_NO_NODE, }; static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc) @@ -783,16 +782,11 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc) target_node = nid; } - /* do some balance if several nodes have the same hit record */ - if (target_node <= cc->last_target_node) - for (nid = cc->last_target_node + 1; nid < MAX_NUMNODES; - nid++) - if (max_value == cc->node_load[nid]) { - target_node = nid; - break; - } + for_each_online_node(nid) { + if (max_value == cc->node_load[nid]) + node_set(nid, cc->alloc_nmask); + } - cc->last_target_node = target_node; return target_node; } #else @@ -802,9 +796,10 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc) } #endif -static bool hpage_collapse_alloc_page(struct page **hpage, gfp_t gfp, int node) +static bool hpage_collapse_alloc_page(struct page **hpage, gfp_t gfp, int node, + nodemask_t *nmask) { - *hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER); + *hpage = __alloc_pages(gfp, HPAGE_PMD_ORDER, node, nmask); if (unlikely(!*hpage)) { count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return false; @@ -955,12 +950,11 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm, static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm, struct collapse_control *cc) { - /* Only allocate from the target node */ gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : - GFP_TRANSHUGE) | __GFP_THISNODE; + GFP_TRANSHUGE); int node = hpage_collapse_find_target_node(cc); - if (!hpage_collapse_alloc_page(hpage, gfp, node)) + if (!hpage_collapse_alloc_page(hpage, gfp, node, &cc->alloc_nmask)) return SCAN_ALLOC_HUGE_PAGE_FAIL; if (unlikely(mem_cgroup_charge(page_folio(*hpage), mm, gfp))) return SCAN_CGROUP_CHARGE_FAIL; @@ -1144,6 +1138,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, goto out; memset(cc->node_load, 0, sizeof(cc->node_load)); + nodes_clear(cc->alloc_nmask); pte = pte_offset_map_lock(mm, pmd, address, &ptl); for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { @@ -2077,6 +2072,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, present = 0; swap = 0; memset(cc->node_load, 0, sizeof(cc->node_load)); + nodes_clear(cc->alloc_nmask); rcu_read_lock(); xas_for_each(&xas, page, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, page)) @@ -2157,8 +2153,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, } } - trace_mm_khugepaged_scan_file(mm, page, file->f_path.dentry->d_iname, - present, swap, result); + trace_mm_khugepaged_scan_file(mm, page, file, present, swap, result); return result; } #else @@ -2576,7 +2571,6 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, if (!cc) return -ENOMEM; cc->is_khugepaged = false; - cc->last_target_node = NUMA_NO_NODE; mmgrab(mm); lru_add_drain_all(); @@ -2602,6 +2596,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); + nodes_clear(cc->alloc_nmask); if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, addr); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2d8549ae1b30..a1a35c12635e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3026,7 +3026,7 @@ struct obj_cgroup *get_obj_cgroup_from_page(struct page *page) { struct obj_cgroup *objcg; - if (!memcg_kmem_enabled() || memcg_kmem_bypass()) + if (!memcg_kmem_enabled()) return NULL; if (PageMemcgKmem(page)) { diff --git a/mm/memory.c b/mm/memory.c index 84854e3b6177..2d43a75f1d6a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3764,7 +3764,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) */ get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); - vmf->page->pgmap->ops->migrate_to_ram(vmf); + ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); put_page(vmf->page); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 6fa682eef7a0..721b2365dbca 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -357,7 +357,8 @@ static bool migrate_vma_check_page(struct page *page, struct page *fault_page) } /* - * Unmaps pages for migration. Returns number of unmapped pages. + * Unmaps pages for migration. Returns number of source pfns marked as + * migrating. */ static unsigned long migrate_device_unmap(unsigned long *src_pfns, unsigned long npages, @@ -373,8 +374,11 @@ static unsigned long migrate_device_unmap(unsigned long *src_pfns, struct page *page = migrate_pfn_to_page(src_pfns[i]); struct folio *folio; - if (!page) + if (!page) { + if (src_pfns[i] & MIGRATE_PFN_MIGRATE) + unmapped++; continue; + } /* ZONE_DEVICE pages are not on LRU */ if (!is_zone_device_page(page)) { diff --git a/mm/mmap.c b/mm/mmap.c index efac6f3ae762..e0c92b500df7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -456,7 +456,7 @@ void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas) * vma_mas_szero() - Set a given range to zero. Used when modifying a * vm_area_struct start or end. * - * @mm: The struct_mm + * @mas: The maple tree ma_state * @start: The start address to zero * @end: The end address to zero. */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 218b28ee49ed..6e60657875d3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3887,6 +3887,8 @@ __setup("fail_page_alloc=", setup_fail_page_alloc); static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { + int flags = 0; + if (order < fail_page_alloc.min_order) return false; if (gfp_mask & __GFP_NOFAIL) @@ -3897,10 +3899,11 @@ static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; + /* See comment in __should_failslab() */ if (gfp_mask & __GFP_NOWARN) - fail_page_alloc.attr.no_warn = true; + flags |= FAULT_NOWARN; - return should_fail(&fail_page_alloc.attr, 1 << order); + return should_fail_ex(&fail_page_alloc.attr, 1 << order, flags); } #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS diff --git a/mm/page_ext.c b/mm/page_ext.c index affe80243b6d..ddf1968560f0 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -166,7 +166,7 @@ struct page_ext *page_ext_get(struct page *page) /** * page_ext_put() - Working with page extended information is done. - * @page_ext - Page extended information received from page_ext_get(). + * @page_ext: Page extended information received from page_ext_get(). * * The page extended information of the page may not be valid after this * function is called. diff --git a/mm/swapfile.c b/mm/swapfile.c index 5fc1237a9f21..72e481aacd5d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -973,23 +973,23 @@ done: scan: spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { - if (swap_offset_available_and_locked(si, offset)) - goto checks; if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } + if (swap_offset_available_and_locked(si, offset)) + goto checks; } offset = si->lowest_bit; while (offset < scan_base) { - if (swap_offset_available_and_locked(si, offset)) - goto checks; if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } + if (swap_offset_available_and_locked(si, offset)) + goto checks; offset++; } spin_lock(&si->lock); diff --git a/mm/vmscan.c b/mm/vmscan.c index 1486a21f7992..a65ebc0c6847 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2517,8 +2517,20 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ - if (stat.nr_unqueued_dirty == nr_taken) + if (stat.nr_unqueued_dirty == nr_taken) { wakeup_flusher_threads(WB_REASON_VMSCAN); + /* + * For cgroupv1 dirty throttling is achieved by waking up + * the kernel flusher here and later waiting on folios + * which are in writeback to finish (see shrink_folio_list()). + * + * Flusher may not be able to issue writeback quickly + * enough for cgroupv1 writeback throttling to work + * on a large system. + */ + if (!writeback_throttling_sane(sc)) + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); + } sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; @@ -4979,10 +4991,13 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap int scanned; int reclaimed; LIST_HEAD(list); + LIST_HEAD(clean); struct folio *folio; + struct folio *next; enum vm_event_item item; struct reclaim_stat stat; struct lru_gen_mm_walk *walk; + bool skip_retry = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); @@ -4999,20 +5014,37 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap if (list_empty(&list)) return scanned; - +retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false); + sc->nr_reclaimed += reclaimed; - list_for_each_entry(folio, &list, lru) { - /* restore LRU_REFS_FLAGS cleared by isolate_folio() */ - if (folio_test_workingset(folio)) - folio_set_referenced(folio); + list_for_each_entry_safe_reverse(folio, next, &list, lru) { + if (!folio_evictable(folio)) { + list_del(&folio->lru); + folio_putback_lru(folio); + continue; + } - /* don't add rejected pages to the oldest generation */ if (folio_test_reclaim(folio) && - (folio_test_dirty(folio) || folio_test_writeback(folio))) - folio_clear_active(folio); - else - folio_set_active(folio); + (folio_test_dirty(folio) || folio_test_writeback(folio))) { + /* restore LRU_REFS_FLAGS cleared by isolate_folio() */ + if (folio_test_workingset(folio)) + folio_set_referenced(folio); + continue; + } + + if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) || + folio_mapped(folio) || folio_test_locked(folio) || + folio_test_dirty(folio) || folio_test_writeback(folio)) { + /* don't add rejected folios to the oldest generation */ + set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, + BIT(PG_active)); + continue; + } + + /* retry folios that may have missed folio_rotate_reclaimable() */ + list_move(&folio->lru, &clean); + sc->nr_scanned -= folio_nr_pages(folio); } spin_lock_irq(&lruvec->lru_lock); @@ -5034,7 +5066,13 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap mem_cgroup_uncharge_list(&list); free_unref_page_list(&list); - sc->nr_reclaimed += reclaimed; + INIT_LIST_HEAD(&list); + list_splice_init(&clean, &list); + + if (!list_empty(&list)) { + skip_retry = true; + goto retry; + } if (need_swapping && type == LRU_GEN_ANON) *need_swapping = true; @@ -5852,8 +5890,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; + bool proportional_reclaim; struct blk_plug plug; - bool scan_adjusted; if (lru_gen_enabled()) { lru_gen_shrink_lruvec(lruvec, sc); @@ -5876,8 +5914,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ - scan_adjusted = (!cgroup_reclaim(sc) && !current_is_kswapd() && - sc->priority == DEF_PRIORITY); + proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && + sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || @@ -5897,7 +5935,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) cond_resched(); - if (nr_reclaimed < nr_to_reclaim || scan_adjusted) + if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; /* @@ -5948,8 +5986,6 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); - - scan_adjusted = true; } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; diff --git a/scripts/Makefile.package b/scripts/Makefile.package index 8bbcced67c22..2a90139ecbe1 100644 --- a/scripts/Makefile.package +++ b/scripts/Makefile.package @@ -30,8 +30,8 @@ KBUILD_PKG_ROOTCMD ?="fakeroot -u" export KDEB_SOURCENAME # Include only those top-level files that are needed by make, plus the GPL copy TAR_CONTENT := Documentation LICENSES arch block certs crypto drivers fs \ - include init io_uring ipc kernel lib mm net samples scripts \ - security sound tools usr virt \ + include init io_uring ipc kernel lib mm net rust \ + samples scripts security sound tools usr virt \ .config .scmversion Makefile \ Kbuild Kconfig COPYING $(wildcard localversion*) MKSPEC := $(srctree)/scripts/package/mkspec diff --git a/scripts/faddr2line b/scripts/faddr2line index 5514c23f45c2..0e73aca4f908 100755 --- a/scripts/faddr2line +++ b/scripts/faddr2line @@ -74,7 +74,8 @@ command -v ${ADDR2LINE} >/dev/null 2>&1 || die "${ADDR2LINE} isn't installed" find_dir_prefix() { local objfile=$1 - local start_kernel_addr=$(${READELF} --symbols --wide $objfile | ${AWK} '$8 == "start_kernel" {printf "0x%s", $2}') + local start_kernel_addr=$(${READELF} --symbols --wide $objfile | sed 's/\[.*\]//' | + ${AWK} '$8 == "start_kernel" {printf "0x%s", $2}') [[ -z $start_kernel_addr ]] && return local file_line=$(${ADDR2LINE} -e $objfile $start_kernel_addr) @@ -178,7 +179,7 @@ __faddr2line() { found=2 break fi - done < <(${READELF} --symbols --wide $objfile | ${AWK} -v sec=$sym_sec '$7 == sec' | sort --key=2) + done < <(${READELF} --symbols --wide $objfile | sed 's/\[.*\]//' | ${AWK} -v sec=$sym_sec '$7 == sec' | sort --key=2) if [[ $found = 0 ]]; then warn "can't find symbol: sym_name: $sym_name sym_sec: $sym_sec sym_addr: $sym_addr sym_elf_size: $sym_elf_size" @@ -259,7 +260,7 @@ __faddr2line() { DONE=1 - done < <(${READELF} --symbols --wide $objfile | ${AWK} -v fn=$sym_name '$4 == "FUNC" && $8 == fn') + done < <(${READELF} --symbols --wide $objfile | sed 's/\[.*\]//' | ${AWK} -v fn=$sym_name '$4 == "FUNC" && $8 == fn') } [[ $# -lt 2 ]] && usage diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index b7aee23fc387..47ef6bc30c0e 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -113,15 +113,19 @@ EXPORT_SYMBOL(snd_seq_dump_var_event); * expand the variable length event to linear buffer space. */ -static int seq_copy_in_kernel(char **bufptr, const void *src, int size) +static int seq_copy_in_kernel(void *ptr, void *src, int size) { + char **bufptr = ptr; + memcpy(*bufptr, src, size); *bufptr += size; return 0; } -static int seq_copy_in_user(char __user **bufptr, const void *src, int size) +static int seq_copy_in_user(void *ptr, void *src, int size) { + char __user **bufptr = ptr; + if (copy_to_user(*bufptr, src, size)) return -EFAULT; *bufptr += size; @@ -151,8 +155,7 @@ int snd_seq_expand_var_event(const struct snd_seq_event *event, int count, char return newlen; } err = snd_seq_dump_var_event(event, - in_kernel ? (snd_seq_dump_func_t)seq_copy_in_kernel : - (snd_seq_dump_func_t)seq_copy_in_user, + in_kernel ? seq_copy_in_kernel : seq_copy_in_user, &buf); return err < 0 ? err : newlen; } diff --git a/sound/soc/codecs/hdac_hda.h b/sound/soc/codecs/hdac_hda.h index fc19c34ca00e..b65560981abb 100644 --- a/sound/soc/codecs/hdac_hda.h +++ b/sound/soc/codecs/hdac_hda.h @@ -14,7 +14,7 @@ enum { HDAC_HDMI_1_DAI_ID, HDAC_HDMI_2_DAI_ID, HDAC_HDMI_3_DAI_ID, - HDAC_LAST_DAI_ID = HDAC_HDMI_3_DAI_ID, + HDAC_DAI_ID_NUM }; struct hdac_hda_pcm { @@ -24,7 +24,7 @@ struct hdac_hda_pcm { struct hdac_hda_priv { struct hda_codec *codec; - struct hdac_hda_pcm pcm[HDAC_LAST_DAI_ID]; + struct hdac_hda_pcm pcm[HDAC_DAI_ID_NUM]; bool need_display_power; }; diff --git a/sound/soc/codecs/max98373-i2c.c b/sound/soc/codecs/max98373-i2c.c index 3e04c7f0cce4..ec0905df65d1 100644 --- a/sound/soc/codecs/max98373-i2c.c +++ b/sound/soc/codecs/max98373-i2c.c @@ -549,6 +549,10 @@ static int max98373_i2c_probe(struct i2c_client *i2c) max98373->cache = devm_kcalloc(&i2c->dev, max98373->cache_num, sizeof(*max98373->cache), GFP_KERNEL); + if (!max98373->cache) { + ret = -ENOMEM; + return ret; + } for (i = 0; i < max98373->cache_num; i++) max98373->cache[i].reg = max98373_i2c_cache_reg[i]; diff --git a/sound/soc/codecs/rt711-sdca-sdw.c b/sound/soc/codecs/rt711-sdca-sdw.c index 4120842fe699..88a8392a58ed 100644 --- a/sound/soc/codecs/rt711-sdca-sdw.c +++ b/sound/soc/codecs/rt711-sdca-sdw.c @@ -230,7 +230,7 @@ static int rt711_sdca_read_prop(struct sdw_slave *slave) } /* set the timeout values */ - prop->clk_stop_timeout = 20; + prop->clk_stop_timeout = 700; /* wake-up event */ prop->wake_capable = 1; diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index 4b2135eba74d..a916f4619ea3 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -1794,6 +1794,7 @@ static void sgtl5000_i2c_remove(struct i2c_client *client) { struct sgtl5000_priv *sgtl5000 = i2c_get_clientdata(client); + regmap_write(sgtl5000->regmap, SGTL5000_CHIP_CLK_CTRL, SGTL5000_CHIP_CLK_CTRL_DEFAULT); regmap_write(sgtl5000->regmap, SGTL5000_CHIP_DIG_POWER, SGTL5000_DIG_POWER_DEFAULT); regmap_write(sgtl5000->regmap, SGTL5000_CHIP_ANA_POWER, SGTL5000_ANA_POWER_DEFAULT); diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index b4b4355c6728..b901e4c65e8a 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -2503,6 +2503,14 @@ static void wm8962_configure_bclk(struct snd_soc_component *component) snd_soc_component_update_bits(component, WM8962_CLOCKING2, WM8962_SYSCLK_ENA_MASK, WM8962_SYSCLK_ENA); + /* DSPCLK_DIV field in WM8962_CLOCKING1 register is used to generate + * correct frequency of LRCLK and BCLK. Sometimes the read-only value + * can't be updated timely after enabling SYSCLK. This results in wrong + * calculation values. Delay is introduced here to wait for newest + * value from register. The time of the delay should be at least + * 500~1000us according to test. + */ + usleep_range(500, 1000); dspclk = snd_soc_component_read(component, WM8962_CLOCKING1); if (snd_soc_component_get_bias_level(component) != SND_SOC_BIAS_ON) diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index fb87d6d23408..35a16c3f9591 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -822,11 +822,6 @@ static int __soc_pcm_open(struct snd_soc_pcm_runtime *rtd, ret = snd_soc_dai_startup(dai, substream); if (ret < 0) goto err; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - dai->tx_mask = 0; - else - dai->rx_mask = 0; } /* Dynamic PCM DAI links compat checks use dynamic capabilities */ @@ -1252,6 +1247,8 @@ static void dpcm_be_reparent(struct snd_soc_pcm_runtime *fe, return; be_substream = snd_soc_dpcm_get_substream(be, stream); + if (!be_substream) + return; for_each_dpcm_fe(be, stream, dpcm) { if (dpcm->fe == fe) diff --git a/sound/soc/stm/stm32_i2s.c b/sound/soc/stm/stm32_i2s.c index ce7f6942308f..f3dd9f8e621c 100644 --- a/sound/soc/stm/stm32_i2s.c +++ b/sound/soc/stm/stm32_i2s.c @@ -1077,7 +1077,7 @@ static int stm32_i2s_parse_dt(struct platform_device *pdev, if (irq < 0) return irq; - ret = devm_request_irq(&pdev->dev, irq, stm32_i2s_isr, IRQF_ONESHOT, + ret = devm_request_irq(&pdev->dev, irq, stm32_i2s_isr, 0, dev_name(&pdev->dev), i2s); if (ret) { dev_err(&pdev->dev, "irq request returned %d\n", ret); diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 2f0d705db9db..05d980fb083d 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -41,6 +41,7 @@ /x86_64/svm_vmcall_test /x86_64/svm_int_ctl_test /x86_64/svm_nested_soft_inject_test +/x86_64/svm_nested_shutdown_test /x86_64/sync_regs_test /x86_64/tsc_msrs_test /x86_64/tsc_scaling_sync diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 0172eb6cb6ee..4a2caef2c939 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -101,6 +101,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_shutdown_test TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_soft_inject_test TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index e8ca0d8a6a7e..5da0c5e2a7af 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -748,6 +748,19 @@ struct ex_regs { uint64_t rflags; }; +struct idt_entry { + uint16_t offset0; + uint16_t selector; + uint16_t ist : 3; + uint16_t : 5; + uint16_t type : 4; + uint16_t : 1; + uint16_t dpl : 2; + uint16_t p : 1; + uint16_t offset1; + uint32_t offset2; uint32_t reserved; +}; + void vm_init_descriptor_tables(struct kvm_vm *vm); void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu); void vm_install_exception_handler(struct kvm_vm *vm, int vector, diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 39c4409ef56a..41c1c73c464d 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1074,19 +1074,6 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) } } -struct idt_entry { - uint16_t offset0; - uint16_t selector; - uint16_t ist : 3; - uint16_t : 5; - uint16_t type : 4; - uint16_t : 1; - uint16_t dpl : 2; - uint16_t p : 1; - uint16_t offset1; - uint32_t offset2; uint32_t reserved; -}; - static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, int dpl, unsigned short selector) { diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c new file mode 100644 index 000000000000..e73fcdef47bb --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_nested_shutdown_test + * + * Copyright (C) 2022, Red Hat, Inc. + * + * Nested SVM testing: test that unintercepted shutdown in L2 doesn't crash the host + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" + +static void l2_guest_code(struct svm_test_data *svm) +{ + __asm__ __volatile__("ud2"); +} + +static void l1_guest_code(struct svm_test_data *svm, struct idt_entry *idt) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + vmcb->control.intercept &= ~(BIT(INTERCEPT_SHUTDOWN)); + + idt[6].p = 0; // #UD is intercepted but its injection will cause #NP + idt[11].p = 0; // #NP is not intercepted and will cause another + // #NP that will be converted to #DF + idt[8].p = 0; // #DF will cause #NP which will cause SHUTDOWN + + run_guest(vmcb, svm->vmcb_gpa); + + /* should not reach here */ + GUEST_ASSERT(0); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_run *run; + vm_vaddr_t svm_gva; + struct kvm_vm *vm; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + vcpu_alloc_svm(vm, &svm_gva); + + vcpu_args_set(vcpu, 2, svm_gva, vm->idt); + run = vcpu->run; + + vcpu_run(vcpu); + TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, + "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c index 70b44f0b52fe..ead5d878a71c 100644 --- a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c +++ b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c @@ -3,6 +3,7 @@ #include "kvm_util.h" #include "processor.h" #include "vmx.h" +#include "svm_util.h" #include #include @@ -20,10 +21,11 @@ static void l2_guest_code(void) : : [port] "d" (ARBITRARY_IO_PORT) : "rax"); } -void l1_guest_code(struct vmx_pages *vmx) -{ #define L2_GUEST_STACK_SIZE 64 - unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; +unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + +void l1_guest_code_vmx(struct vmx_pages *vmx) +{ GUEST_ASSERT(vmx->vmcs_gpa); GUEST_ASSERT(prepare_for_vmx_operation(vmx)); @@ -38,24 +40,53 @@ void l1_guest_code(struct vmx_pages *vmx) GUEST_DONE(); } +void l1_guest_code_svm(struct svm_test_data *svm) +{ + struct vmcb *vmcb = svm->vmcb; + + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* don't intercept shutdown to test the case of SVM allowing to do so */ + vmcb->control.intercept &= ~(BIT(INTERCEPT_SHUTDOWN)); + + run_guest(vmcb, svm->vmcb_gpa); + + /* should not reach here, L1 should crash */ + GUEST_ASSERT(0); +} + int main(void) { struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vcpu_events events; - vm_vaddr_t vmx_pages_gva; struct ucall uc; - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + bool has_vmx = kvm_cpu_has(X86_FEATURE_VMX); + bool has_svm = kvm_cpu_has(X86_FEATURE_SVM); + + TEST_REQUIRE(has_vmx || has_svm); TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_TRIPLE_FAULT_EVENT)); - vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); - vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1); + if (has_vmx) { + vm_vaddr_t vmx_pages_gva; + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_vmx); + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vcpu, 1, vmx_pages_gva); + } else { + vm_vaddr_t svm_gva; + + vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_svm); + vcpu_alloc_svm(vm, &svm_gva); + vcpu_args_set(vcpu, 1, svm_gva); + } + + vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1); run = vcpu->run; - vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vcpu, 1, vmx_pages_gva); vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, @@ -78,13 +109,21 @@ int main(void) "No triple fault pending"); vcpu_run(vcpu); - switch (get_ucall(vcpu, &uc)) { - case UCALL_DONE: - break; - case UCALL_ABORT: - REPORT_GUEST_ASSERT(uc); - default: - TEST_FAIL("Unexpected ucall: %lu", uc.cmd); - } + if (has_svm) { + TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, + "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + } else { + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } + } + return 0; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 25d7872b29c1..fab4d3790578 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1198,8 +1198,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) goto out_err_no_arch_destroy_vm; } - kvm->max_halt_poll_ns = halt_poll_ns; - r = kvm_arch_init_vm(kvm, type); if (r) goto out_err_no_arch_destroy_vm; @@ -3377,9 +3375,6 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) if (val < grow_start) val = grow_start; - if (val > vcpu->kvm->max_halt_poll_ns) - val = vcpu->kvm->max_halt_poll_ns; - vcpu->halt_poll_ns = val; out: trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); @@ -3483,6 +3478,24 @@ static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, } } +static unsigned int kvm_vcpu_max_halt_poll_ns(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + if (kvm->override_halt_poll_ns) { + /* + * Ensure kvm->max_halt_poll_ns is not read before + * kvm->override_halt_poll_ns. + * + * Pairs with the smp_wmb() when enabling KVM_CAP_HALT_POLL. + */ + smp_rmb(); + return READ_ONCE(kvm->max_halt_poll_ns); + } + + return READ_ONCE(halt_poll_ns); +} + /* * Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc... If halt * polling is enabled, busy wait for a short time before blocking to avoid the @@ -3491,12 +3504,18 @@ static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, */ void kvm_vcpu_halt(struct kvm_vcpu *vcpu) { + unsigned int max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); - bool do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; ktime_t start, cur, poll_end; bool waited = false; + bool do_halt_poll; u64 halt_ns; + if (vcpu->halt_poll_ns > max_halt_poll_ns) + vcpu->halt_poll_ns = max_halt_poll_ns; + + do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; + start = cur = poll_end = ktime_get(); if (do_halt_poll) { ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns); @@ -3535,18 +3554,21 @@ out: update_halt_poll_stats(vcpu, start, poll_end, !waited); if (halt_poll_allowed) { + /* Recompute the max halt poll time in case it changed. */ + max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); + if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); - } else if (vcpu->kvm->max_halt_poll_ns) { + } else if (max_halt_poll_ns) { if (halt_ns <= vcpu->halt_poll_ns) ; /* we had a long block, shrink polling */ else if (vcpu->halt_poll_ns && - halt_ns > vcpu->kvm->max_halt_poll_ns) + halt_ns > max_halt_poll_ns) shrink_halt_poll_ns(vcpu); /* we had a short halt and our poll time is too small */ - else if (vcpu->halt_poll_ns < vcpu->kvm->max_halt_poll_ns && - halt_ns < vcpu->kvm->max_halt_poll_ns) + else if (vcpu->halt_poll_ns < max_halt_poll_ns && + halt_ns < max_halt_poll_ns) grow_halt_poll_ns(vcpu); } else { vcpu->halt_poll_ns = 0; @@ -4581,6 +4603,16 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, return -EINVAL; kvm->max_halt_poll_ns = cap->args[0]; + + /* + * Ensure kvm->override_halt_poll_ns does not become visible + * before kvm->max_halt_poll_ns. + * + * Pairs with the smp_rmb() in kvm_vcpu_max_halt_poll_ns(). + */ + smp_wmb(); + kvm->override_halt_poll_ns = true; + return 0; } case KVM_CAP_DIRTY_LOG_RING: diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c index 346e47f15572..7c248193ca26 100644 --- a/virt/kvm/pfncache.c +++ b/virt/kvm/pfncache.c @@ -297,7 +297,12 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, if (!gpc->valid || old_uhva != gpc->uhva) { ret = hva_to_pfn_retry(kvm, gpc); } else { - /* If the HVA→PFN mapping was already valid, don't unmap it. */ + /* + * If the HVA→PFN mapping was already valid, don't unmap it. + * But do update gpc->khva because the offset within the page + * may have changed. + */ + gpc->khva = old_khva + page_offset; old_pfn = KVM_PFN_ERR_FAULT; old_khva = NULL; ret = 0;