diff --git a/Documentation/networking/nf_flowtable.txt b/Documentation/networking/nf_flowtable.txt index ca2136c76042..0bf32d1121be 100644 --- a/Documentation/networking/nf_flowtable.txt +++ b/Documentation/networking/nf_flowtable.txt @@ -76,7 +76,7 @@ flowtable and add one rule to your forward chain. table inet x { flowtable f { - hook ingress priority 0 devices = { eth0, eth1 }; + hook ingress priority 0; devices = { eth0, eth1 }; } chain y { type filter hook forward priority 0; policy accept; diff --git a/Documentation/sphinx/parallel-wrapper.sh b/Documentation/sphinx/parallel-wrapper.sh index 7daf5133bdd3..e54c44ce117d 100644 --- a/Documentation/sphinx/parallel-wrapper.sh +++ b/Documentation/sphinx/parallel-wrapper.sh @@ -30,4 +30,4 @@ if [ -n "$parallel" ] ; then parallel="-j$parallel" fi -exec "$sphinx" "$parallel" "$@" +exec "$sphinx" $parallel "$@" diff --git a/Makefile b/Makefile index 0f64b92fa39a..a1e5190e4721 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 5 -SUBLEVEL = 7 +SUBLEVEL = 8 EXTRAVERSION = NAME = Kleptomaniac Octopus diff --git a/arch/arm/boot/dts/stihxxx-b2120.dtsi b/arch/arm/boot/dts/stihxxx-b2120.dtsi index 60e11045ad76..d051f080e52e 100644 --- a/arch/arm/boot/dts/stihxxx-b2120.dtsi +++ b/arch/arm/boot/dts/stihxxx-b2120.dtsi @@ -46,7 +46,7 @@ simple-audio-card,dai-link@1 { /* DAC */ format = "i2s"; mclk-fs = <256>; - frame-inversion = <1>; + frame-inversion; cpu { sound-dai = <&sti_uni_player2>; }; diff --git a/arch/arm/include/asm/vdso/vsyscall.h b/arch/arm/include/asm/vdso/vsyscall.h index c4166f317071..cff87d8d30da 100644 --- a/arch/arm/include/asm/vdso/vsyscall.h +++ b/arch/arm/include/asm/vdso/vsyscall.h @@ -34,9 +34,9 @@ struct vdso_data *__arm_get_k_vdso_data(void) #define __arch_get_k_vdso_data __arm_get_k_vdso_data static __always_inline -int __arm_update_vdso_data(void) +bool __arm_update_vdso_data(void) { - return !cntvct_ok; + return cntvct_ok; } #define __arch_update_vdso_data __arm_update_vdso_data diff --git a/arch/mips/include/asm/sync.h b/arch/mips/include/asm/sync.h index 7c6a1095f556..aabd097933fe 100644 --- a/arch/mips/include/asm/sync.h +++ b/arch/mips/include/asm/sync.h @@ -155,9 +155,11 @@ * effective barrier as noted by commit 6b07d38aaa52 ("MIPS: Octeon: Use * optimized memory barrier primitives."). Here we specify that the affected * sync instructions should be emitted twice. + * Note that this expression is evaluated by the assembler (not the compiler), + * and that the assembler evaluates '==' as 0 or -1, not 0 or 1. */ #ifdef CONFIG_CPU_CAVIUM_OCTEON -# define __SYNC_rpt(type) (1 + (type == __SYNC_wmb)) +# define __SYNC_rpt(type) (1 - (type == __SYNC_wmb)) #else # define __SYNC_rpt(type) 1 #endif diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 6176b9acba95..d0d832ab3d3b 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -134,7 +134,7 @@ void release_vpe(struct vpe *v) { list_del(&v->list); if (v->load_addr) - release_progmem(v); + release_progmem(v->load_addr); kfree(v); } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index f4cad5163bf2..ffb3d94bf0cc 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -156,6 +156,6 @@ void __init trap_init(void) csr_write(CSR_SCRATCH, 0); /* Set the exception vector address */ csr_write(CSR_TVEC, &handle_exception); - /* Enable all interrupts */ - csr_write(CSR_IE, -1); + /* Enable interrupts */ + csr_write(CSR_IE, IE_SIE | IE_EIE); } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 3be51aa06e67..dff6623804c2 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4765,6 +4765,7 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_ATOM_TREMONT_D: + case INTEL_FAM6_ATOM_TREMONT: x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(hw_cache_event_ids)); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index e1daf4151e11..4814c964692c 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,17 +40,18 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM,CNL + * Available model: SLM,AMT,GLM,CNL,TNT * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM, - * CNL,KBL,CML + * CNL,KBL,CML,TNT * Scope: Core * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, - * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL + * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL, + * TNT * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 @@ -60,17 +61,18 @@ * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, - * KBL,CML,ICL,TGL + * KBL,CML,ICL,TGL,TNT * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, - * GLM,CNL,KBL,CML,ICL,TGL + * GLM,CNL,KBL,CML,ICL,TGL,TNT * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 - * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW - * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, + * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL, + * TNT * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 @@ -87,7 +89,8 @@ * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 - * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL + * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, + * TNT * Scope: Package (physical package) * */ @@ -640,8 +643,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT_D, glm_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT, glm_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE, icl_cstates), diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 6f86650b3f77..a949f6f55991 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -75,8 +75,9 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_ATOM_GOLDMONT_D: - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + case INTEL_FAM6_ATOM_TREMONT_D: + case INTEL_FAM6_ATOM_TREMONT: case INTEL_FAM6_XEON_PHI_KNL: case INTEL_FAM6_XEON_PHI_KNM: diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index e49b77283924..181c992f448c 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -57,6 +57,7 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) } DECLARE_STATIC_KEY_FALSE(rdt_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); /** * struct mon_evt - Entry in the event list of a resource diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 397206f23d14..773124b0e18a 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -514,7 +514,7 @@ void mbm_handle_overflow(struct work_struct *work) mutex_lock(&rdtgroup_mutex); - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) goto out_unlock; d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]); @@ -543,7 +543,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) return; cpu = cpumask_any(&dom->cpu_mask); dom->mbm_work_cpu = cpu; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index f05123acaa64..a1daebe2a60f 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1150,7 +1150,7 @@ void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, if (!kvm_apic_present(vcpu)) continue; if (!kvm_apic_match_dest(vcpu, NULL, - irq->delivery_mode, + irq->shorthand, irq->dest_id, irq->dest_mode)) continue; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index aace3b6ca2f7..2b3d8feec313 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1307,6 +1307,47 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) } } +/* + * The default MMIO mask is a single bit (excluding the present bit), + * which could conflict with the memory encryption bit. Check for + * memory encryption support and override the default MMIO mask if + * memory encryption is enabled. + */ +static __init void svm_adjust_mmio_mask(void) +{ + unsigned int enc_bit, mask_bit; + u64 msr, mask; + + /* If there is no memory encryption support, use existing mask */ + if (cpuid_eax(0x80000000) < 0x8000001f) + return; + + /* If memory encryption is not enabled, use existing mask */ + rdmsrl(MSR_K8_SYSCFG, msr); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + return; + + enc_bit = cpuid_ebx(0x8000001f) & 0x3f; + mask_bit = boot_cpu_data.x86_phys_bits; + + /* Increment the mask bit if it is the same as the encryption bit */ + if (enc_bit == mask_bit) + mask_bit++; + + /* + * If the mask bit location is below 52, then some bits above the + * physical addressing limit will always be reserved, so use the + * rsvd_bits() function to generate the mask. This mask, along with + * the present bit, will be used to generate a page fault with + * PFER.RSV = 1. + * + * If the mask bit location is 52 (or above), then clear the mask. + */ + mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0; + + kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1361,6 +1402,8 @@ static __init int svm_hardware_setup(void) } } + svm_adjust_mmio_mask(); + for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index af5a36dfc88a..63addc413d99 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4781,32 +4781,28 @@ static int handle_vmread(struct kvm_vcpu *vcpu) { unsigned long field; u64 field_value; + struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); int len; gva_t gva = 0; - struct vmcs12 *vmcs12; + struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) + : get_vmcs12(vcpu); struct x86_exception e; short offset; if (!nested_vmx_check_permission(vcpu)) return 1; - if (to_vmx(vcpu)->nested.current_vmptr == -1ull) + /* + * In VMX non-root operation, when the VMCS-link pointer is -1ull, + * any VMREAD sets the ALU flags for VMfailInvalid. + */ + if (vmx->nested.current_vmptr == -1ull || + (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) return nested_vmx_failInvalid(vcpu); - if (!is_guest_mode(vcpu)) - vmcs12 = get_vmcs12(vcpu); - else { - /* - * When vmcs->vmcs_link_pointer is -1ull, any VMREAD - * to shadowed-field sets the ALU flags for VMfailInvalid. - */ - if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) - return nested_vmx_failInvalid(vcpu); - vmcs12 = get_shadow_vmcs12(vcpu); - } - /* Decode instruction info and find the field to read */ field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); @@ -4885,13 +4881,20 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) */ u64 field_value = 0; struct x86_exception e; - struct vmcs12 *vmcs12; + struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu) + : get_vmcs12(vcpu); short offset; if (!nested_vmx_check_permission(vcpu)) return 1; - if (vmx->nested.current_vmptr == -1ull) + /* + * In VMX non-root operation, when the VMCS-link pointer is -1ull, + * any VMWRITE sets the ALU flags for VMfailInvalid. + */ + if (vmx->nested.current_vmptr == -1ull || + (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)) return nested_vmx_failInvalid(vcpu); if (vmx_instruction_info & (1u << 10)) @@ -4910,6 +4913,12 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf)); + + offset = vmcs_field_to_offset(field); + if (offset < 0) + return nested_vmx_failValid(vcpu, + VMXERR_UNSUPPORTED_VMCS_COMPONENT); + /* * If the vCPU supports "VMWRITE to any supported field in the * VMCS," then the "read-only" fields are actually read/write. @@ -4919,29 +4928,12 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return nested_vmx_failValid(vcpu, VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT); - if (!is_guest_mode(vcpu)) { - vmcs12 = get_vmcs12(vcpu); - - /* - * Ensure vmcs12 is up-to-date before any VMWRITE that dirties - * vmcs12, else we may crush a field or consume a stale value. - */ - if (!is_shadow_field_rw(field)) - copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - } else { - /* - * When vmcs->vmcs_link_pointer is -1ull, any VMWRITE - * to shadowed-field sets the ALU flags for VMfailInvalid. - */ - if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) - return nested_vmx_failInvalid(vcpu); - vmcs12 = get_shadow_vmcs12(vcpu); - } - - offset = vmcs_field_to_offset(field); - if (offset < 0) - return nested_vmx_failValid(vcpu, - VMXERR_UNSUPPORTED_VMCS_COMPONENT); + /* + * Ensure vmcs12 is up-to-date before any VMWRITE that dirties + * vmcs12, else we may crush a field or consume a stale value. + */ + if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field)) + copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); /* * Some Intel CPUs intentionally drop the reserved bits of the AR byte diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index be438bc7cfa3..3e381b31b9a6 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7179,6 +7179,7 @@ static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, else intercept = nested_vmx_check_io_bitmaps(vcpu, port, size); + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; } @@ -7208,6 +7209,20 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, case x86_intercept_outs: return vmx_check_intercept_io(vcpu, info); + case x86_intercept_lgdt: + case x86_intercept_lidt: + case x86_intercept_lldt: + case x86_intercept_ltr: + case x86_intercept_sgdt: + case x86_intercept_sidt: + case x86_intercept_sldt: + case x86_intercept_str: + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC)) + return X86EMUL_CONTINUE; + + /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ + break; + /* TODO: check more intercepts... */ default: break; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e594fd2719dd..dafb5aff200f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9225,12 +9225,6 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - vcpu->arch.apf.msr_val = 0; - - vcpu_load(vcpu); - kvm_mmu_unload(vcpu); - vcpu_put(vcpu); - kvm_arch_vcpu_free(vcpu); } diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c index b5516b04ffc0..d827a4a3e946 100644 --- a/drivers/acpi/acpi_watchdog.c +++ b/drivers/acpi/acpi_watchdog.c @@ -126,12 +126,11 @@ void __init acpi_watchdog_init(void) gas = &entries[i].register_region; res.start = gas->address; + res.end = res.start + ACPI_ACCESS_BYTE_WIDTH(gas->access_width) - 1; if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { res.flags = IORESOURCE_MEM; - res.end = res.start + ALIGN(gas->access_width, 4) - 1; } else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { res.flags = IORESOURCE_IO; - res.end = res.start + gas->access_width - 1; } else { pr_warn("Unsupported address space: %u\n", gas->space_id); diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig index 50200d1c06ea..6095b6df8a81 100644 --- a/drivers/bus/Kconfig +++ b/drivers/bus/Kconfig @@ -139,7 +139,6 @@ config TEGRA_ACONNECT tristate "Tegra ACONNECT Bus Driver" depends on ARCH_TEGRA_210_SOC depends on OF && PM - select PM_CLK help Driver for the Tegra ACONNECT bus which is used to interface with the devices inside the Audio Processing Engine (APE) for Tegra210. diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 22c6a2e61236..8ac390c2b514 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -775,10 +775,14 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result, flags = ipmi_ssif_lock_cond(ssif_info, &oflags); msg = ssif_info->curr_msg; if (msg) { + if (data) { + if (len > IPMI_MAX_MSG_LENGTH) + len = IPMI_MAX_MSG_LENGTH; + memcpy(msg->rsp, data, len); + } else { + len = 0; + } msg->rsp_size = len; - if (msg->rsp_size > IPMI_MAX_MSG_LENGTH) - msg->rsp_size = IPMI_MAX_MSG_LENGTH; - memcpy(msg->rsp, data, msg->rsp_size); ssif_info->curr_msg = NULL; } diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c index 7ed313ad6e43..d9e17b91c68e 100644 --- a/drivers/clk/qcom/clk-rpmh.c +++ b/drivers/clk/qcom/clk-rpmh.c @@ -481,9 +481,9 @@ static int clk_rpmh_probe(struct platform_device *pdev) } static const struct of_device_id clk_rpmh_match_table[] = { + { .compatible = "qcom,sc7180-rpmh-clk", .data = &clk_rpmh_sc7180}, { .compatible = "qcom,sdm845-rpmh-clk", .data = &clk_rpmh_sdm845}, { .compatible = "qcom,sm8150-rpmh-clk", .data = &clk_rpmh_sm8150}, - { .compatible = "qcom,sc7180-rpmh-clk", .data = &clk_rpmh_sc7180}, { } }; MODULE_DEVICE_TABLE(of, clk_rpmh_match_table); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 4adac3a8c265..b60d349e3b1e 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1074,9 +1074,17 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy) pol = policy->last_policy; } else if (def_gov) { pol = cpufreq_parse_policy(def_gov->name); - } else { - return -ENODATA; + /* + * In case the default governor is neiter "performance" + * nor "powersave", fall back to the initial policy + * value set by the driver. + */ + if (pol == CPUFREQ_POLICY_UNKNOWN) + pol = policy->policy; } + if (pol != CPUFREQ_POLICY_PERFORMANCE && + pol != CPUFREQ_POLICY_POWERSAVE) + return -ENODATA; } return cpufreq_set_policy(policy, gov, pol); diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index e99f082d15df..c5a34be182ca 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -738,7 +738,6 @@ struct devfreq *devfreq_add_device(struct device *dev, { struct devfreq *devfreq; struct devfreq_governor *governor; - static atomic_t devfreq_no = ATOMIC_INIT(-1); int err = 0; if (!dev || !profile || !governor_name) { @@ -800,8 +799,7 @@ struct devfreq *devfreq_add_device(struct device *dev, devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev); atomic_set(&devfreq->suspend_count, 0); - dev_set_name(&devfreq->dev, "devfreq%d", - atomic_inc_return(&devfreq_no)); + dev_set_name(&devfreq->dev, "%s", dev_name(dev)); err = device_register(&devfreq->dev); if (err) { mutex_unlock(&devfreq->lock); diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index 95662a4ff4c4..99bbaf629b8d 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -256,7 +256,7 @@ int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm) pdev = pci_get_device(PCI_VENDOR_ID_INTEL, did, NULL); if (!pdev) { - skx_printk(KERN_ERR, "Can't get tolm/tohm\n"); + edac_dbg(2, "Can't get tolm/tohm\n"); return -ENODEV; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 30a1e3ac21d6..4169abc32219 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1357,7 +1357,7 @@ amdgpu_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe, static struct drm_driver kms_driver = { .driver_features = - DRIVER_USE_AGP | DRIVER_ATOMIC | + DRIVER_ATOMIC | DRIVER_GEM | DRIVER_RENDER | DRIVER_MODESET | DRIVER_SYNCOBJ | DRIVER_SYNCOBJ_TIMELINE, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h index b499a3de8bb6..c75cc97eca44 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h @@ -192,6 +192,7 @@ struct amdgpu_gmc { uint32_t srbm_soft_reset; bool prt_warning; uint64_t stolen_size; + uint32_t sdpif_register; /* apertures */ u64 shared_aperture_start; u64 shared_aperture_end; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index a5b68b5e452f..0b88c9f877ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1203,6 +1203,19 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev) } } +/** + * gmc_v9_0_restore_registers - restores regs + * + * @adev: amdgpu_device pointer + * + * This restores register values, saved at suspend. + */ +static void gmc_v9_0_restore_registers(struct amdgpu_device *adev) +{ + if (adev->asic_type == CHIP_RAVEN) + WREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0, adev->gmc.sdpif_register); +} + /** * gmc_v9_0_gart_enable - gart enable * @@ -1307,6 +1320,20 @@ static int gmc_v9_0_hw_init(void *handle) return r; } +/** + * gmc_v9_0_save_registers - saves regs + * + * @adev: amdgpu_device pointer + * + * This saves potential register values that should be + * restored upon resume + */ +static void gmc_v9_0_save_registers(struct amdgpu_device *adev) +{ + if (adev->asic_type == CHIP_RAVEN) + adev->gmc.sdpif_register = RREG32(mmDCHUBBUB_SDPIF_MMIO_CNTRL_0); +} + /** * gmc_v9_0_gart_disable - gart disable * @@ -1343,9 +1370,16 @@ static int gmc_v9_0_hw_fini(void *handle) static int gmc_v9_0_suspend(void *handle) { + int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - return gmc_v9_0_hw_fini(adev); + r = gmc_v9_0_hw_fini(adev); + if (r) + return r; + + gmc_v9_0_save_registers(adev); + + return 0; } static int gmc_v9_0_resume(void *handle) @@ -1353,6 +1387,7 @@ static int gmc_v9_0_resume(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v9_0_restore_registers(adev); r = gmc_v9_0_hw_init(adev); if (r) return r; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile index b864869cc7e3..6fa7422c51da 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile @@ -91,6 +91,12 @@ ifdef CONFIG_DRM_AMD_DC_DCN2_1 ############################################################################### CLK_MGR_DCN21 = rn_clk_mgr.o rn_clk_mgr_vbios_smu.o +# prevent build errors regarding soft-float vs hard-float FP ABI tags +# this code is currently unused on ppc64, as it applies to Renoir APUs only +ifdef CONFIG_PPC64 +CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn21/rn_clk_mgr.o := $(call cc-option,-mno-gnu-attribute) +endif + AMD_DAL_CLK_MGR_DCN21 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn21/,$(CLK_MGR_DCN21)) AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN21) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index dbf063856846..5f683d118d2a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -149,6 +149,12 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base, rn_vbios_smu_set_min_deep_sleep_dcfclk(clk_mgr, clk_mgr_base->clks.dcfclk_deep_sleep_khz); } + // workaround: Limit dppclk to 100Mhz to avoid lower eDP panel switch to plus 4K monitor underflow. + if (!IS_DIAG_DC(dc->ctx->dce_environment)) { + if (new_clocks->dppclk_khz < 100000) + new_clocks->dppclk_khz = 100000; + } + if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) { if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz) dpp_clock_lowered = true; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index 793c0cec407f..5fcffb29317e 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -398,7 +398,7 @@ static bool acquire( { enum gpio_result result; - if (!is_engine_available(engine)) + if ((engine == NULL) || !is_engine_available(engine)) return false; result = dal_ddc_open(ddc, GPIO_MODE_HARDWARE, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index ac8c18fadefc..448bc9b39942 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -493,7 +493,6 @@ static void dcn20_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx) dpp->funcs->dpp_dppclk_control(dpp, false, false); hubp->power_gated = true; - dc->optimized_required = false; /* We're powering off, no need to optimize */ dc->hwss.plane_atomic_power_down(dc, pipe_ctx->plane_res.dpp, diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 83cda43a1b6b..77741b18c85b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -57,6 +57,7 @@ #include "dcn20/dcn20_dccg.h" #include "dcn21_hubbub.h" #include "dcn10/dcn10_resource.h" +#include "dce110/dce110_resource.h" #include "dcn20/dcn20_dwb.h" #include "dcn20/dcn20_mmhubbub.h" @@ -867,6 +868,7 @@ static const struct dc_debug_options debug_defaults_diags = { enum dcn20_clk_src_array_id { DCN20_CLK_SRC_PLL0, DCN20_CLK_SRC_PLL1, + DCN20_CLK_SRC_PLL2, DCN20_CLK_SRC_TOTAL_DCN21 }; @@ -1730,6 +1732,10 @@ static bool construct( dcn21_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL1, &clk_src_regs[1], false); + pool->base.clock_sources[DCN20_CLK_SRC_PLL2] = + dcn21_clock_source_create(ctx, ctx->dc_bios, + CLOCK_SOURCE_COMBO_PHY_PLL2, + &clk_src_regs[2], false); pool->base.clk_src_count = DCN20_CLK_SRC_TOTAL_DCN21; diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h index b6f74bf4af02..27bb8c1ab858 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_12_0_offset.h @@ -7376,6 +7376,8 @@ #define mmCRTC4_CRTC_DRR_CONTROL 0x0f3e #define mmCRTC4_CRTC_DRR_CONTROL_BASE_IDX 2 +#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0 0x395d +#define mmDCHUBBUB_SDPIF_MMIO_CNTRL_0_BASE_IDX 2 // addressBlock: dce_dc_fmt4_dispdec // base address: 0x2000 diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index f2418a1cfe68..b5875063b97c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -257,8 +257,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *i915) with_intel_runtime_pm(&i915->runtime_pm, wakeref) { freed = i915_gem_shrink(i915, -1UL, NULL, I915_SHRINK_BOUND | - I915_SHRINK_UNBOUND | - I915_SHRINK_ACTIVE); + I915_SHRINK_UNBOUND); } return freed; @@ -337,7 +336,6 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr) freed_pages = 0; with_intel_runtime_pm(&i915->runtime_pm, wakeref) freed_pages += i915_gem_shrink(i915, -1UL, NULL, - I915_SHRINK_ACTIVE | I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_WRITEBACK); diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 2477a1e5a166..ae139f0877ae 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -151,12 +151,12 @@ static void dmabuf_gem_object_free(struct kref *kref) dmabuf_obj = container_of(pos, struct intel_vgpu_dmabuf_obj, list); if (dmabuf_obj == obj) { + list_del(pos); intel_gvt_hypervisor_put_vfio_device(vgpu); idr_remove(&vgpu->object_idr, dmabuf_obj->dmabuf_id); kfree(dmabuf_obj->info); kfree(dmabuf_obj); - list_del(pos); break; } } diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 85bd9bf4f6ee..487af6ea9972 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -560,9 +560,9 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, intel_vgpu_reset_mmio(vgpu, dmlr); populate_pvinfo_page(vgpu); - intel_vgpu_reset_display(vgpu); if (dmlr) { + intel_vgpu_reset_display(vgpu); intel_vgpu_reset_cfg_space(vgpu); /* only reset the failsafe mode when dmlr reset */ vgpu->failsafe = false; diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index c84f0a8b3f2c..b73fbb65e14b 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -441,6 +441,14 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv) if (ret) goto err_msm_uninit; + if (!dev->dma_parms) { + dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms), + GFP_KERNEL); + if (!dev->dma_parms) + return -ENOMEM; + } + dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); + msm_gem_shrinker_init(ddev); switch (get_mdp_ver(pdev)) { diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index fd74e2611185..8696af1ee14d 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -37,6 +37,7 @@ #include <linux/vga_switcheroo.h> #include <linux/mmu_notifier.h> +#include <drm/drm_agpsupport.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_drv.h> #include <drm/drm_fb_helper.h> @@ -325,6 +326,7 @@ static int radeon_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { unsigned long flags = 0; + struct drm_device *dev; int ret; if (!ent) @@ -365,7 +367,44 @@ static int radeon_pci_probe(struct pci_dev *pdev, if (ret) return ret; - return drm_get_pci_dev(pdev, ent, &kms_driver); + dev = drm_dev_alloc(&kms_driver, &pdev->dev); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + ret = pci_enable_device(pdev); + if (ret) + goto err_free; + + dev->pdev = pdev; +#ifdef __alpha__ + dev->hose = pdev->sysdata; +#endif + + pci_set_drvdata(pdev, dev); + + if (pci_find_capability(dev->pdev, PCI_CAP_ID_AGP)) + dev->agp = drm_agp_init(dev); + if (dev->agp) { + dev->agp->agp_mtrr = arch_phys_wc_add( + dev->agp->agp_info.aper_base, + dev->agp->agp_info.aper_size * + 1024 * 1024); + } + + ret = drm_dev_register(dev, ent->driver_data); + if (ret) + goto err_agp; + + return 0; + +err_agp: + if (dev->agp) + arch_phys_wc_del(dev->agp->agp_mtrr); + kfree(dev->agp); + pci_disable_device(pdev); +err_free: + drm_dev_put(dev); + return ret; } static void @@ -575,7 +614,7 @@ radeon_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe, static struct drm_driver kms_driver = { .driver_features = - DRIVER_USE_AGP | DRIVER_GEM | DRIVER_RENDER, + DRIVER_GEM | DRIVER_RENDER, .load = radeon_driver_load_kms, .open = radeon_driver_open_kms, .postclose = radeon_driver_postclose_kms, diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index e85c554eeaa9..2bb0187c5bc7 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -31,6 +31,7 @@ #include <linux/uaccess.h> #include <linux/vga_switcheroo.h> +#include <drm/drm_agpsupport.h> #include <drm/drm_fb_helper.h> #include <drm/drm_file.h> #include <drm/drm_ioctl.h> @@ -77,6 +78,11 @@ void radeon_driver_unload_kms(struct drm_device *dev) radeon_modeset_fini(rdev); radeon_device_fini(rdev); + if (dev->agp) + arch_phys_wc_del(dev->agp->agp_mtrr); + kfree(dev->agp); + dev->agp = NULL; + done_free: kfree(rdev); dev->dev_private = NULL; diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index ae79a7c66737..fa704153cb00 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -730,7 +730,7 @@ static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi) if (data->has_sp) { input2 = input_allocate_device(); if (!input2) { - input_free_device(input2); + ret = -ENOMEM; goto exit; } diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 851fe54ea59e..359616e3efbb 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1741,7 +1741,9 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, rsize = ((report->size - 1) >> 3) + 1; - if (rsize > HID_MAX_BUFFER_SIZE) + if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE) + rsize = HID_MAX_BUFFER_SIZE - 1; + else if (rsize > HID_MAX_BUFFER_SIZE) rsize = HID_MAX_BUFFER_SIZE; if (csize < rsize) { diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index c436e12feb23..6c55682c5974 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -41,8 +41,9 @@ static const struct hid_device_id ite_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) }, { HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) }, /* ITE8595 USB kbd ctlr, with Synaptics touchpad connected to it. */ - { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, - USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_SYNAPTICS, + USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index a970b809d778..4140dea693e9 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -932,9 +932,9 @@ void hiddev_disconnect(struct hid_device *hid) hiddev->exist = 0; if (hiddev->open) { - mutex_unlock(&hiddev->existancelock); hid_hw_close(hiddev->hid); wake_up_interruptible(&hiddev->wait); + mutex_unlock(&hiddev->existancelock); } else { mutex_unlock(&hiddev->existancelock); kfree(hiddev); diff --git a/drivers/i2c/busses/i2c-altera.c b/drivers/i2c/busses/i2c-altera.c index 5255d3755411..1de23b4f3809 100644 --- a/drivers/i2c/busses/i2c-altera.c +++ b/drivers/i2c/busses/i2c-altera.c @@ -171,7 +171,7 @@ static void altr_i2c_init(struct altr_i2c_dev *idev) /* SCL Low Time */ writel(t_low, idev->base + ALTR_I2C_SCL_LOW); /* SDA Hold Time, 300ns */ - writel(div_u64(300 * clk_mhz, 1000), idev->base + ALTR_I2C_SDA_HOLD); + writel(3 * clk_mhz / 10, idev->base + ALTR_I2C_SDA_HOLD); /* Mask all master interrupt bits */ altr_i2c_int_enable(idev, ALTR_I2C_ALL_IRQ, false); diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c index 25dcd73acd63..8f0e1f802f2d 100644 --- a/drivers/i2c/busses/i2c-jz4780.c +++ b/drivers/i2c/busses/i2c-jz4780.c @@ -73,25 +73,6 @@ #define JZ4780_I2C_STA_TFNF BIT(1) #define JZ4780_I2C_STA_ACT BIT(0) -static const char * const jz4780_i2c_abrt_src[] = { - "ABRT_7B_ADDR_NOACK", - "ABRT_10ADDR1_NOACK", - "ABRT_10ADDR2_NOACK", - "ABRT_XDATA_NOACK", - "ABRT_GCALL_NOACK", - "ABRT_GCALL_READ", - "ABRT_HS_ACKD", - "SBYTE_ACKDET", - "ABRT_HS_NORSTRT", - "SBYTE_NORSTRT", - "ABRT_10B_RD_NORSTRT", - "ABRT_MASTER_DIS", - "ARB_LOST", - "SLVFLUSH_TXFIFO", - "SLV_ARBLOST", - "SLVRD_INTX", -}; - #define JZ4780_I2C_INTST_IGC BIT(11) #define JZ4780_I2C_INTST_ISTT BIT(10) #define JZ4780_I2C_INTST_ISTP BIT(9) @@ -529,21 +510,8 @@ static irqreturn_t jz4780_i2c_irq(int irqno, void *dev_id) static void jz4780_i2c_txabrt(struct jz4780_i2c *i2c, int src) { - int i; - - dev_err(&i2c->adap.dev, "txabrt: 0x%08x\n", src); - dev_err(&i2c->adap.dev, "device addr=%x\n", - jz4780_i2c_readw(i2c, JZ4780_I2C_TAR)); - dev_err(&i2c->adap.dev, "send cmd count:%d %d\n", - i2c->cmd, i2c->cmd_buf[i2c->cmd]); - dev_err(&i2c->adap.dev, "receive data count:%d %d\n", - i2c->cmd, i2c->data_buf[i2c->cmd]); - - for (i = 0; i < 16; i++) { - if (src & BIT(i)) - dev_dbg(&i2c->adap.dev, "I2C TXABRT[%d]=%s\n", - i, jz4780_i2c_abrt_src[i]); - } + dev_dbg(&i2c->adap.dev, "txabrt: 0x%08x, cmd: %d, send: %d, recv: %d\n", + src, i2c->cmd, i2c->cmd_buf[i2c->cmd], i2c->data_buf[i2c->cmd]); } static inline int jz4780_i2c_xfer_read(struct jz4780_i2c *i2c, diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index 5617434cbfb4..416341ada172 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -423,7 +423,7 @@ struct hns_roce_mr_table { struct hns_roce_wq { u64 *wrid; /* Work request ID */ spinlock_t lock; - int wqe_cnt; /* WQE num */ + u32 wqe_cnt; /* WQE num */ int max_gs; int offset; int wqe_shift; /* WQE size */ @@ -647,7 +647,6 @@ struct hns_roce_qp { u8 sdb_en; u32 doorbell_qpn; u32 sq_signal_bits; - u32 sq_next_wqe; struct hns_roce_wq sq; struct ib_umem *umem; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 2a2b2112f886..a31a21433f65 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -74,8 +74,8 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp, unsigned long flags = 0; void *wqe = NULL; __le32 doorbell[2]; + u32 wqe_idx = 0; int nreq = 0; - u32 ind = 0; int ret = 0; u8 *smac; int loopback; @@ -88,7 +88,7 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp, } spin_lock_irqsave(&qp->sq.lock, flags); - ind = qp->sq_next_wqe; + for (nreq = 0; wr; ++nreq, wr = wr->next) { if (hns_roce_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)) { ret = -ENOMEM; @@ -96,6 +96,8 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp, goto out; } + wqe_idx = (qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1); + if (unlikely(wr->num_sge > qp->sq.max_gs)) { dev_err(dev, "num_sge=%d > qp->sq.max_gs=%d\n", wr->num_sge, qp->sq.max_gs); @@ -104,9 +106,8 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp, goto out; } - wqe = get_send_wqe(qp, ind & (qp->sq.wqe_cnt - 1)); - qp->sq.wrid[(qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1)] = - wr->wr_id; + wqe = get_send_wqe(qp, wqe_idx); + qp->sq.wrid[wqe_idx] = wr->wr_id; /* Corresponding to the RC and RD type wqe process separately */ if (ibqp->qp_type == IB_QPT_GSI) { @@ -210,7 +211,6 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp, cpu_to_le32((wr->sg_list[1].addr) >> 32); ud_sq_wqe->l_key1 = cpu_to_le32(wr->sg_list[1].lkey); - ind++; } else if (ibqp->qp_type == IB_QPT_RC) { u32 tmp_len = 0; @@ -308,7 +308,6 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp, ctrl->flag |= cpu_to_le32(wr->num_sge << HNS_ROCE_WQE_SGE_NUM_BIT); } - ind++; } } @@ -336,7 +335,6 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp, doorbell[1] = sq_db.u32_8; hns_roce_write64_k(doorbell, qp->sq.db_reg_l); - qp->sq_next_wqe = ind; } spin_unlock_irqrestore(&qp->sq.lock, flags); @@ -348,12 +346,6 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, const struct ib_recv_wr **bad_wr) { - int ret = 0; - int nreq = 0; - int ind = 0; - int i = 0; - u32 reg_val; - unsigned long flags = 0; struct hns_roce_rq_wqe_ctrl *ctrl = NULL; struct hns_roce_wqe_data_seg *scat = NULL; struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); @@ -361,9 +353,14 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp, struct device *dev = &hr_dev->pdev->dev; struct hns_roce_rq_db rq_db; __le32 doorbell[2] = {0}; + unsigned long flags = 0; + unsigned int wqe_idx; + int ret = 0; + int nreq = 0; + int i = 0; + u32 reg_val; spin_lock_irqsave(&hr_qp->rq.lock, flags); - ind = hr_qp->rq.head & (hr_qp->rq.wqe_cnt - 1); for (nreq = 0; wr; ++nreq, wr = wr->next) { if (hns_roce_wq_overflow(&hr_qp->rq, nreq, @@ -373,6 +370,8 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp, goto out; } + wqe_idx = (hr_qp->rq.head + nreq) & (hr_qp->rq.wqe_cnt - 1); + if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) { dev_err(dev, "rq:num_sge=%d > qp->sq.max_gs=%d\n", wr->num_sge, hr_qp->rq.max_gs); @@ -381,7 +380,7 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp, goto out; } - ctrl = get_recv_wqe(hr_qp, ind); + ctrl = get_recv_wqe(hr_qp, wqe_idx); roce_set_field(ctrl->rwqe_byte_12, RQ_WQE_CTRL_RWQE_BYTE_12_RWQE_SGE_NUM_M, @@ -393,9 +392,7 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp, for (i = 0; i < wr->num_sge; i++) set_data_seg(scat + i, wr->sg_list + i); - hr_qp->rq.wrid[ind] = wr->wr_id; - - ind = (ind + 1) & (hr_qp->rq.wqe_cnt - 1); + hr_qp->rq.wrid[wqe_idx] = wr->wr_id; } out: @@ -2701,7 +2698,6 @@ static int hns_roce_v1_m_sqp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, hr_qp->rq.tail = 0; hr_qp->sq.head = 0; hr_qp->sq.tail = 0; - hr_qp->sq_next_wqe = 0; } kfree(context); @@ -3315,7 +3311,6 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, hr_qp->rq.tail = 0; hr_qp->sq.head = 0; hr_qp->sq.tail = 0; - hr_qp->sq_next_wqe = 0; } out: kfree(context); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index cb8071a3e0d5..87186446dffb 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -110,7 +110,7 @@ static void set_atomic_seg(struct hns_roce_wqe_atomic_seg *aseg, } static void set_extend_sge(struct hns_roce_qp *qp, const struct ib_send_wr *wr, - unsigned int *sge_ind) + unsigned int *sge_ind, int valid_num_sge) { struct hns_roce_v2_wqe_data_seg *dseg; struct ib_sge *sg; @@ -123,7 +123,7 @@ static void set_extend_sge(struct hns_roce_qp *qp, const struct ib_send_wr *wr, if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) num_in_wqe = HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE; - extend_sge_num = wr->num_sge - num_in_wqe; + extend_sge_num = valid_num_sge - num_in_wqe; sg = wr->sg_list + num_in_wqe; shift = qp->hr_buf.page_shift; @@ -159,14 +159,16 @@ static void set_extend_sge(struct hns_roce_qp *qp, const struct ib_send_wr *wr, static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr, struct hns_roce_v2_rc_send_wqe *rc_sq_wqe, void *wqe, unsigned int *sge_ind, + int valid_num_sge, const struct ib_send_wr **bad_wr) { struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); struct hns_roce_v2_wqe_data_seg *dseg = wqe; struct hns_roce_qp *qp = to_hr_qp(ibqp); + int j = 0; int i; - if (wr->send_flags & IB_SEND_INLINE && wr->num_sge) { + if (wr->send_flags & IB_SEND_INLINE && valid_num_sge) { if (le32_to_cpu(rc_sq_wqe->msg_len) > hr_dev->caps.max_sq_inline) { *bad_wr = wr; @@ -190,7 +192,7 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr, roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_INLINE_S, 1); } else { - if (wr->num_sge <= HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE) { + if (valid_num_sge <= HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE) { for (i = 0; i < wr->num_sge; i++) { if (likely(wr->sg_list[i].length)) { set_data_seg_v2(dseg, wr->sg_list + i); @@ -203,19 +205,21 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr, V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S, (*sge_ind) & (qp->sge.sge_cnt - 1)); - for (i = 0; i < HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE; i++) { + for (i = 0; i < wr->num_sge && + j < HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE; i++) { if (likely(wr->sg_list[i].length)) { set_data_seg_v2(dseg, wr->sg_list + i); dseg++; + j++; } } - set_extend_sge(qp, wr, sge_ind); + set_extend_sge(qp, wr, sge_ind, valid_num_sge); } roce_set_field(rc_sq_wqe->byte_16, V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M, - V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, wr->num_sge); + V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, valid_num_sge); } return 0; @@ -239,10 +243,11 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, struct device *dev = hr_dev->dev; struct hns_roce_v2_db sq_db; struct ib_qp_attr attr; - unsigned int sge_ind; unsigned int owner_bit; + unsigned int sge_idx; + unsigned int wqe_idx; unsigned long flags; - unsigned int ind; + int valid_num_sge; void *wqe = NULL; bool loopback; int attr_mask; @@ -269,8 +274,7 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, } spin_lock_irqsave(&qp->sq.lock, flags); - ind = qp->sq_next_wqe; - sge_ind = qp->next_sge; + sge_idx = qp->next_sge; for (nreq = 0; wr; ++nreq, wr = wr->next) { if (hns_roce_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)) { @@ -279,6 +283,8 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, goto out; } + wqe_idx = (qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1); + if (unlikely(wr->num_sge > qp->sq.max_gs)) { dev_err(dev, "num_sge=%d > qp->sq.max_gs=%d\n", wr->num_sge, qp->sq.max_gs); @@ -287,14 +293,20 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, goto out; } - wqe = get_send_wqe(qp, ind & (qp->sq.wqe_cnt - 1)); - qp->sq.wrid[(qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1)] = - wr->wr_id; - + wqe = get_send_wqe(qp, wqe_idx); + qp->sq.wrid[wqe_idx] = wr->wr_id; owner_bit = ~(((qp->sq.head + nreq) >> ilog2(qp->sq.wqe_cnt)) & 0x1); + valid_num_sge = 0; tmp_len = 0; + for (i = 0; i < wr->num_sge; i++) { + if (likely(wr->sg_list[i].length)) { + tmp_len += wr->sg_list[i].length; + valid_num_sge++; + } + } + /* Corresponding to the QP type, wqe process separately */ if (ibqp->qp_type == IB_QPT_GSI) { ud_sq_wqe = wqe; @@ -330,9 +342,6 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, V2_UD_SEND_WQE_BYTE_4_OPCODE_S, HNS_ROCE_V2_WQE_OP_SEND); - for (i = 0; i < wr->num_sge; i++) - tmp_len += wr->sg_list[i].length; - ud_sq_wqe->msg_len = cpu_to_le32(le32_to_cpu(ud_sq_wqe->msg_len) + tmp_len); @@ -368,12 +377,12 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, roce_set_field(ud_sq_wqe->byte_16, V2_UD_SEND_WQE_BYTE_16_SGE_NUM_M, V2_UD_SEND_WQE_BYTE_16_SGE_NUM_S, - wr->num_sge); + valid_num_sge); roce_set_field(ud_sq_wqe->byte_20, V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M, V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S, - sge_ind & (qp->sge.sge_cnt - 1)); + sge_idx & (qp->sge.sge_cnt - 1)); roce_set_field(ud_sq_wqe->byte_24, V2_UD_SEND_WQE_BYTE_24_UDPSPN_M, @@ -423,13 +432,10 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, memcpy(&ud_sq_wqe->dgid[0], &ah->av.dgid[0], GID_LEN_V2); - set_extend_sge(qp, wr, &sge_ind); - ind++; + set_extend_sge(qp, wr, &sge_idx, valid_num_sge); } else if (ibqp->qp_type == IB_QPT_RC) { rc_sq_wqe = wqe; memset(rc_sq_wqe, 0, sizeof(*rc_sq_wqe)); - for (i = 0; i < wr->num_sge; i++) - tmp_len += wr->sg_list[i].length; rc_sq_wqe->msg_len = cpu_to_le32(le32_to_cpu(rc_sq_wqe->msg_len) + tmp_len); @@ -550,15 +556,14 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, roce_set_field(rc_sq_wqe->byte_16, V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M, V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, - wr->num_sge); + valid_num_sge); } else if (wr->opcode != IB_WR_REG_MR) { ret = set_rwqe_data_seg(ibqp, wr, rc_sq_wqe, - wqe, &sge_ind, bad_wr); + wqe, &sge_idx, + valid_num_sge, bad_wr); if (ret) goto out; } - - ind++; } else { dev_err(dev, "Illegal qp_type(0x%x)\n", ibqp->qp_type); spin_unlock_irqrestore(&qp->sq.lock, flags); @@ -588,8 +593,7 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp, hns_roce_write64(hr_dev, (__le32 *)&sq_db, qp->sq.db_reg_l); - qp->sq_next_wqe = ind; - qp->next_sge = sge_ind; + qp->next_sge = sge_idx; if (qp->state == IB_QPS_ERR) { attr_mask = IB_QP_STATE; @@ -623,13 +627,12 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, unsigned long flags; void *wqe = NULL; int attr_mask; + u32 wqe_idx; int ret = 0; int nreq; - int ind; int i; spin_lock_irqsave(&hr_qp->rq.lock, flags); - ind = hr_qp->rq.head & (hr_qp->rq.wqe_cnt - 1); if (hr_qp->state == IB_QPS_RESET) { spin_unlock_irqrestore(&hr_qp->rq.lock, flags); @@ -645,6 +648,8 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, goto out; } + wqe_idx = (hr_qp->rq.head + nreq) & (hr_qp->rq.wqe_cnt - 1); + if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) { dev_err(dev, "rq:num_sge=%d > qp->sq.max_gs=%d\n", wr->num_sge, hr_qp->rq.max_gs); @@ -653,7 +658,7 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, goto out; } - wqe = get_recv_wqe(hr_qp, ind); + wqe = get_recv_wqe(hr_qp, wqe_idx); dseg = (struct hns_roce_v2_wqe_data_seg *)wqe; for (i = 0; i < wr->num_sge; i++) { if (!wr->sg_list[i].length) @@ -669,8 +674,8 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, /* rq support inline data */ if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE) { - sge_list = hr_qp->rq_inl_buf.wqe_list[ind].sg_list; - hr_qp->rq_inl_buf.wqe_list[ind].sge_cnt = + sge_list = hr_qp->rq_inl_buf.wqe_list[wqe_idx].sg_list; + hr_qp->rq_inl_buf.wqe_list[wqe_idx].sge_cnt = (u32)wr->num_sge; for (i = 0; i < wr->num_sge; i++) { sge_list[i].addr = @@ -679,9 +684,7 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, } } - hr_qp->rq.wrid[ind] = wr->wr_id; - - ind = (ind + 1) & (hr_qp->rq.wqe_cnt - 1); + hr_qp->rq.wrid[wqe_idx] = wr->wr_id; } out: @@ -4464,7 +4467,6 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp, hr_qp->rq.tail = 0; hr_qp->sq.head = 0; hr_qp->sq.tail = 0; - hr_qp->sq_next_wqe = 0; hr_qp->next_sge = 0; if (hr_qp->rq.wqe_cnt) *hr_qp->rdb.db_record = 0; diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index 3bccfef40e7e..ac86363ce1a2 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -1225,10 +1225,9 @@ static void siw_cm_llp_data_ready(struct sock *sk) read_lock(&sk->sk_callback_lock); cep = sk_to_cep(sk); - if (!cep) { - WARN_ON(1); + if (!cep) goto out; - } + siw_dbg_cep(cep, "state: %d\n", cep->state); switch (cep->state) { diff --git a/drivers/macintosh/therm_windtunnel.c b/drivers/macintosh/therm_windtunnel.c index 8c744578122a..a0d87ed9da69 100644 --- a/drivers/macintosh/therm_windtunnel.c +++ b/drivers/macintosh/therm_windtunnel.c @@ -300,9 +300,11 @@ static int control_loop(void *dummy) /* i2c probing and setup */ /************************************************************************/ -static int -do_attach( struct i2c_adapter *adapter ) +static void do_attach(struct i2c_adapter *adapter) { + struct i2c_board_info info = { }; + struct device_node *np; + /* scan 0x48-0x4f (DS1775) and 0x2c-2x2f (ADM1030) */ static const unsigned short scan_ds1775[] = { 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, @@ -313,25 +315,24 @@ do_attach( struct i2c_adapter *adapter ) I2C_CLIENT_END }; - if( strncmp(adapter->name, "uni-n", 5) ) - return 0; - - if( !x.running ) { - struct i2c_board_info info; + if (x.running || strncmp(adapter->name, "uni-n", 5)) + return; - memset(&info, 0, sizeof(struct i2c_board_info)); - strlcpy(info.type, "therm_ds1775", I2C_NAME_SIZE); + np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,ds1775"); + if (np) { + of_node_put(np); + } else { + strlcpy(info.type, "MAC,ds1775", I2C_NAME_SIZE); i2c_new_probed_device(adapter, &info, scan_ds1775, NULL); + } - strlcpy(info.type, "therm_adm1030", I2C_NAME_SIZE); + np = of_find_compatible_node(adapter->dev.of_node, NULL, "MAC,adm1030"); + if (np) { + of_node_put(np); + } else { + strlcpy(info.type, "MAC,adm1030", I2C_NAME_SIZE); i2c_new_probed_device(adapter, &info, scan_adm1030, NULL); - - if( x.thermostat && x.fan ) { - x.running = 1; - x.poll_task = kthread_run(control_loop, NULL, "g4fand"); - } } - return 0; } static int @@ -404,8 +405,8 @@ attach_thermostat( struct i2c_client *cl ) enum chip { ds1775, adm1030 }; static const struct i2c_device_id therm_windtunnel_id[] = { - { "therm_ds1775", ds1775 }, - { "therm_adm1030", adm1030 }, + { "MAC,ds1775", ds1775 }, + { "MAC,adm1030", adm1030 }, { } }; MODULE_DEVICE_TABLE(i2c, therm_windtunnel_id); @@ -414,6 +415,7 @@ static int do_probe(struct i2c_client *cl, const struct i2c_device_id *id) { struct i2c_adapter *adapter = cl->adapter; + int ret = 0; if( !i2c_check_functionality(adapter, I2C_FUNC_SMBUS_WORD_DATA | I2C_FUNC_SMBUS_WRITE_BYTE) ) @@ -421,11 +423,19 @@ do_probe(struct i2c_client *cl, const struct i2c_device_id *id) switch (id->driver_data) { case adm1030: - return attach_fan( cl ); + ret = attach_fan(cl); + break; case ds1775: - return attach_thermostat(cl); + ret = attach_thermostat(cl); + break; } - return 0; + + if (!x.running && x.thermostat && x.fan) { + x.running = 1; + x.poll_task = kthread_run(control_loop, NULL, "g4fand"); + } + + return ret; } static struct i2c_driver g4fan_driver = { diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 48d5ec770b94..d10805e5e623 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3526,6 +3526,47 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res, } } +#ifdef CONFIG_LOCKDEP +static int bond_get_lowest_level_rcu(struct net_device *dev) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int cur = 0, max = 0; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + next = NULL; + while (1) { + ldev = netdev_next_lower_dev_rcu(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + if (max <= cur) + max = cur; + break; + } + + if (!next) { + if (!cur) + return max; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return max; +} +#endif + static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -3533,11 +3574,17 @@ static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 temp; struct list_head *iter; struct slave *slave; + int nest_level = 0; - spin_lock(&bond->stats_lock); - memcpy(stats, &bond->bond_stats, sizeof(*stats)); rcu_read_lock(); +#ifdef CONFIG_LOCKDEP + nest_level = bond_get_lowest_level_rcu(bond_dev); +#endif + + spin_lock_nested(&bond->stats_lock, nest_level); + memcpy(stats, &bond->bond_stats, sizeof(*stats)); + bond_for_each_slave_rcu(bond, slave, iter) { const struct rtnl_link_stats64 *new = dev_get_stats(slave->dev, &temp); @@ -3547,10 +3594,10 @@ static void bond_get_stats(struct net_device *bond_dev, /* save off the slave stats for the next run */ memcpy(&slave->slave_stats, new, sizeof(*new)); } - rcu_read_unlock(); memcpy(&bond->bond_stats, stats, sizeof(*stats)); spin_unlock(&bond->stats_lock); + rcu_read_unlock(); } static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) @@ -3640,6 +3687,8 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd case BOND_RELEASE_OLD: case SIOCBONDRELEASE: res = bond_release(bond_dev, slave_dev); + if (!res) + netdev_update_lockdep_key(slave_dev); break; case BOND_SETHWADDR_OLD: case SIOCBONDSETHWADDR: diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index ddb3916d3506..215c10923289 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1398,6 +1398,8 @@ static int bond_option_slaves_set(struct bonding *bond, case '-': slave_dbg(bond->dev, dev, "Releasing interface\n"); ret = bond_release(bond->dev, dev); + if (!ret) + netdev_update_lockdep_key(dev); break; default: diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 6a1ff4d43e3a..38b16efda4a9 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1353,6 +1353,9 @@ void b53_vlan_add(struct dsa_switch *ds, int port, b53_get_vlan_entry(dev, vid, vl); + if (vid == 0 && vid == b53_default_pvid(dev)) + untagged = true; + vl->members |= BIT(port); if (untagged && !dsa_is_cpu_port(ds, port)) vl->untag |= BIT(port); diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index ea62604fdf8c..1fb58f9ad80b 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -200,6 +200,11 @@ static void comp_ctxt_release(struct ena_com_admin_queue *queue, static struct ena_comp_ctx *get_comp_ctxt(struct ena_com_admin_queue *queue, u16 command_id, bool capture) { + if (unlikely(!queue->comp_ctx)) { + pr_err("Completion context is NULL\n"); + return NULL; + } + if (unlikely(command_id >= queue->q_depth)) { pr_err("command id is larger than the queue size. cmd_id: %u queue size %d\n", command_id, queue->q_depth); @@ -1041,9 +1046,41 @@ static int ena_com_get_feature(struct ena_com_dev *ena_dev, feature_ver); } +int ena_com_get_current_hash_function(struct ena_com_dev *ena_dev) +{ + return ena_dev->rss.hash_func; +} + +static void ena_com_hash_key_fill_default_key(struct ena_com_dev *ena_dev) +{ + struct ena_admin_feature_rss_flow_hash_control *hash_key = + (ena_dev->rss).hash_key; + + netdev_rss_key_fill(&hash_key->key, sizeof(hash_key->key)); + /* The key is stored in the device in u32 array + * as well as the API requires the key to be passed in this + * format. Thus the size of our array should be divided by 4 + */ + hash_key->keys_num = sizeof(hash_key->key) / sizeof(u32); +} + static int ena_com_hash_key_allocate(struct ena_com_dev *ena_dev) { struct ena_rss *rss = &ena_dev->rss; + struct ena_admin_feature_rss_flow_hash_control *hash_key; + struct ena_admin_get_feat_resp get_resp; + int rc; + + hash_key = (ena_dev->rss).hash_key; + + rc = ena_com_get_feature_ex(ena_dev, &get_resp, + ENA_ADMIN_RSS_HASH_FUNCTION, + ena_dev->rss.hash_key_dma_addr, + sizeof(ena_dev->rss.hash_key), 0); + if (unlikely(rc)) { + hash_key = NULL; + return -EOPNOTSUPP; + } rss->hash_key = dma_alloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_key), @@ -1254,30 +1291,6 @@ static int ena_com_ind_tbl_convert_to_device(struct ena_com_dev *ena_dev) return 0; } -static int ena_com_ind_tbl_convert_from_device(struct ena_com_dev *ena_dev) -{ - u16 dev_idx_to_host_tbl[ENA_TOTAL_NUM_QUEUES] = { (u16)-1 }; - struct ena_rss *rss = &ena_dev->rss; - u8 idx; - u16 i; - - for (i = 0; i < ENA_TOTAL_NUM_QUEUES; i++) - dev_idx_to_host_tbl[ena_dev->io_sq_queues[i].idx] = i; - - for (i = 0; i < 1 << rss->tbl_log_size; i++) { - if (rss->rss_ind_tbl[i].cq_idx > ENA_TOTAL_NUM_QUEUES) - return -EINVAL; - idx = (u8)rss->rss_ind_tbl[i].cq_idx; - - if (dev_idx_to_host_tbl[idx] > ENA_TOTAL_NUM_QUEUES) - return -EINVAL; - - rss->host_rss_ind_tbl[i] = dev_idx_to_host_tbl[idx]; - } - - return 0; -} - static void ena_com_update_intr_delay_resolution(struct ena_com_dev *ena_dev, u16 intr_delay_resolution) { @@ -2297,15 +2310,16 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev, switch (func) { case ENA_ADMIN_TOEPLITZ: - if (key_len > sizeof(hash_key->key)) { - pr_err("key len (%hu) is bigger than the max supported (%zu)\n", - key_len, sizeof(hash_key->key)); - return -EINVAL; + if (key) { + if (key_len != sizeof(hash_key->key)) { + pr_err("key len (%hu) doesn't equal the supported size (%zu)\n", + key_len, sizeof(hash_key->key)); + return -EINVAL; + } + memcpy(hash_key->key, key, key_len); + rss->hash_init_val = init_val; + hash_key->keys_num = key_len >> 2; } - - memcpy(hash_key->key, key, key_len); - rss->hash_init_val = init_val; - hash_key->keys_num = key_len >> 2; break; case ENA_ADMIN_CRC32: rss->hash_init_val = init_val; @@ -2342,7 +2356,11 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev, if (unlikely(rc)) return rc; - rss->hash_func = get_resp.u.flow_hash_func.selected_func; + /* ffs() returns 1 in case the lsb is set */ + rss->hash_func = ffs(get_resp.u.flow_hash_func.selected_func); + if (rss->hash_func) + rss->hash_func--; + if (func) *func = rss->hash_func; @@ -2606,10 +2624,6 @@ int ena_com_indirect_table_get(struct ena_com_dev *ena_dev, u32 *ind_tbl) if (!ind_tbl) return 0; - rc = ena_com_ind_tbl_convert_from_device(ena_dev); - if (unlikely(rc)) - return rc; - for (i = 0; i < (1 << rss->tbl_log_size); i++) ind_tbl[i] = rss->host_rss_ind_tbl[i]; @@ -2626,9 +2640,15 @@ int ena_com_rss_init(struct ena_com_dev *ena_dev, u16 indr_tbl_log_size) if (unlikely(rc)) goto err_indr_tbl; + /* The following function might return unsupported in case the + * device doesn't support setting the key / hash function. We can safely + * ignore this error and have indirection table support only. + */ rc = ena_com_hash_key_allocate(ena_dev); - if (unlikely(rc)) + if (unlikely(rc) && rc != -EOPNOTSUPP) goto err_hash_key; + else if (rc != -EOPNOTSUPP) + ena_com_hash_key_fill_default_key(ena_dev); rc = ena_com_hash_ctrl_init(ena_dev); if (unlikely(rc)) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h index 0ce37d54ed10..469f298199a7 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_com.h @@ -44,6 +44,7 @@ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/wait.h> +#include <linux/netdevice.h> #include "ena_common_defs.h" #include "ena_admin_defs.h" @@ -655,6 +656,14 @@ int ena_com_rss_init(struct ena_com_dev *ena_dev, u16 log_size); */ void ena_com_rss_destroy(struct ena_com_dev *ena_dev); +/* ena_com_get_current_hash_function - Get RSS hash function + * @ena_dev: ENA communication layer struct + * + * Return the current hash function. + * @return: 0 or one of the ena_admin_hash_functions values. + */ +int ena_com_get_current_hash_function(struct ena_com_dev *ena_dev); + /* ena_com_fill_hash_function - Fill RSS hash function * @ena_dev: ENA communication layer struct * @func: The hash function (Toeplitz or crc) diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index fc96c66b44cb..971f02ea55a1 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -636,6 +636,28 @@ static u32 ena_get_rxfh_key_size(struct net_device *netdev) return ENA_HASH_KEY_SIZE; } +static int ena_indirection_table_get(struct ena_adapter *adapter, u32 *indir) +{ + struct ena_com_dev *ena_dev = adapter->ena_dev; + int i, rc; + + if (!indir) + return 0; + + rc = ena_com_indirect_table_get(ena_dev, indir); + if (rc) + return rc; + + /* Our internal representation of the indices is: even indices + * for Tx and uneven indices for Rx. We need to convert the Rx + * indices to be consecutive + */ + for (i = 0; i < ENA_RX_RSS_TABLE_SIZE; i++) + indir[i] = ENA_IO_RXQ_IDX_TO_COMBINED_IDX(indir[i]); + + return rc; +} + static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 *hfunc) { @@ -644,11 +666,25 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, u8 func; int rc; - rc = ena_com_indirect_table_get(adapter->ena_dev, indir); + rc = ena_indirection_table_get(adapter, indir); if (rc) return rc; + /* We call this function in order to check if the device + * supports getting/setting the hash function. + */ rc = ena_com_get_hash_function(adapter->ena_dev, &ena_func, key); + + if (rc) { + if (rc == -EOPNOTSUPP) { + key = NULL; + hfunc = NULL; + rc = 0; + } + + return rc; + } + if (rc) return rc; @@ -657,7 +693,7 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, func = ETH_RSS_HASH_TOP; break; case ENA_ADMIN_CRC32: - func = ETH_RSS_HASH_XOR; + func = ETH_RSS_HASH_CRC32; break; default: netif_err(adapter, drv, netdev, @@ -700,10 +736,13 @@ static int ena_set_rxfh(struct net_device *netdev, const u32 *indir, } switch (hfunc) { + case ETH_RSS_HASH_NO_CHANGE: + func = ena_com_get_current_hash_function(ena_dev); + break; case ETH_RSS_HASH_TOP: func = ENA_ADMIN_TOEPLITZ; break; - case ETH_RSS_HASH_XOR: + case ETH_RSS_HASH_CRC32: func = ENA_ADMIN_CRC32; break; default: @@ -812,6 +851,7 @@ static const struct ethtool_ops ena_ethtool_ops = { .set_channels = ena_set_channels, .get_tunable = ena_get_tunable, .set_tunable = ena_set_tunable, + .get_ts_info = ethtool_op_get_ts_info, }; void ena_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 948583fdcc28..1c1a41bd11da 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -3049,8 +3049,8 @@ static void check_for_missing_keep_alive(struct ena_adapter *adapter) if (adapter->keep_alive_timeout == ENA_HW_HINTS_NO_TIMEOUT) return; - keep_alive_expired = round_jiffies(adapter->last_keep_alive_jiffies + - adapter->keep_alive_timeout); + keep_alive_expired = adapter->last_keep_alive_jiffies + + adapter->keep_alive_timeout; if (unlikely(time_is_before_jiffies(keep_alive_expired))) { netif_err(adapter, drv, adapter->netdev, "Keep alive watchdog timeout.\n"); @@ -3152,7 +3152,7 @@ static void ena_timer_service(struct timer_list *t) } /* Reset the timer */ - mod_timer(&adapter->timer_service, jiffies + HZ); + mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); } static int ena_calc_max_io_queue_num(struct pci_dev *pdev, diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index bffd778f2ce3..2fe5eeea6b69 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -129,6 +129,8 @@ #define ENA_IO_TXQ_IDX(q) (2 * (q)) #define ENA_IO_RXQ_IDX(q) (2 * (q) + 1) +#define ENA_IO_TXQ_IDX_TO_COMBINED_IDX(q) ((q) / 2) +#define ENA_IO_RXQ_IDX_TO_COMBINED_IDX(q) (((q) - 1) / 2) #define ENA_MGMNT_IRQ_IDX 0 #define ENA_IO_IRQ_FIRST_IDX 1 diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index d8612131c55e..cc8031ae9aa3 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -2020,7 +2020,7 @@ static int xgene_enet_probe(struct platform_device *pdev) int ret; ndev = alloc_etherdev_mqs(sizeof(struct xgene_enet_pdata), - XGENE_NUM_RX_RING, XGENE_NUM_TX_RING); + XGENE_NUM_TX_RING, XGENE_NUM_RX_RING); if (!ndev) return -ENOMEM; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index a1f99bef4a68..7b55633d2cb9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -722,6 +722,11 @@ static int aq_ethtool_set_priv_flags(struct net_device *ndev, u32 flags) if (flags & ~AQ_PRIV_FLAGS_MASK) return -EOPNOTSUPP; + if (hweight32((flags | priv_flags) & AQ_HW_LOOPBACK_MASK) > 1) { + netdev_info(ndev, "Can't enable more than one loopback simultaneously\n"); + return -EINVAL; + } + cfg->priv_flags = flags; if ((priv_flags ^ flags) & BIT(AQ_HW_LOOPBACK_DMA_NET)) { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c index 6102251bb909..03ff92bc4a7f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c @@ -163,7 +163,7 @@ aq_check_approve_fvlan(struct aq_nic_s *aq_nic, } if ((aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) && - (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci), + (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci) & VLAN_VID_MASK, aq_nic->active_vlans))) { netdev_err(aq_nic->ndev, "ethtool: unknown vlan-id specified"); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index c85e3e29012c..e95f6a6bef73 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -533,8 +533,10 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb, dx_buff->len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) + if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) { + ret = 0; goto exit; + } first = dx_buff; dx_buff->len_pkt = skb->len; @@ -655,10 +657,6 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb) if (likely(frags)) { err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw, ring, frags); - if (err >= 0) { - ++ring->stats.tx.packets; - ring->stats.tx.bytes += skb->len; - } } else { err = NETDEV_TX_BUSY; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 2bb329606794..f74952674084 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -359,7 +359,8 @@ static int aq_suspend_common(struct device *dev, bool deep) netif_device_detach(nic->ndev); netif_tx_stop_all_queues(nic->ndev); - aq_nic_stop(nic); + if (netif_running(nic->ndev)) + aq_nic_stop(nic); if (deep) { aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol); @@ -375,7 +376,7 @@ static int atl_resume_common(struct device *dev, bool deep) { struct pci_dev *pdev = to_pci_dev(dev); struct aq_nic_s *nic; - int ret; + int ret = 0; nic = pci_get_drvdata(pdev); @@ -390,9 +391,11 @@ static int atl_resume_common(struct device *dev, bool deep) goto err_exit; } - ret = aq_nic_start(nic); - if (ret) - goto err_exit; + if (netif_running(nic->ndev)) { + ret = aq_nic_start(nic); + if (ret) + goto err_exit; + } netif_device_attach(nic->ndev); netif_tx_start_all_queues(nic->ndev); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 951d86f8b66e..bae95a618560 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -272,9 +272,12 @@ bool aq_ring_tx_clean(struct aq_ring_s *self) } } - if (unlikely(buff->is_eop)) - dev_kfree_skb_any(buff->skb); + if (unlikely(buff->is_eop)) { + ++self->stats.rx.packets; + self->stats.tx.bytes += buff->skb->len; + dev_kfree_skb_any(buff->skb); + } buff->pa = 0U; buff->eop_index = 0xffffU; self->sw_head = aq_ring_next_dx(self, self->sw_head); @@ -351,7 +354,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, err = 0; goto err_exit; } - if (buff->is_error || buff->is_cso_err) { + if (buff->is_error || + (buff->is_lro && buff->is_cso_err)) { buff_ = buff; do { next_ = buff_->next, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 991e4d31b094..2c96f20f6289 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -78,7 +78,8 @@ struct __packed aq_ring_buff_s { u32 is_cleaned:1; u32 is_error:1; u32 is_vlan:1; - u32 rsvd3:4; + u32 is_lro:1; + u32 rsvd3:3; u16 eop_index; u16 rsvd4; }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index ec041f78d063..fce587aaba33 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -823,6 +823,8 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, } } + buff->is_lro = !!(HW_ATL_B0_RXD_WB_STAT2_RSCCNT & + rxd_wb->status); if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) { buff->len = rxd_wb->pkt_len % AQ_CFG_RX_FRAME_MAX; @@ -835,8 +837,7 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, rxd_wb->pkt_len > AQ_CFG_RX_FRAME_MAX ? AQ_CFG_RX_FRAME_MAX : rxd_wb->pkt_len; - if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT & - rxd_wb->status) { + if (buff->is_lro) { /* LRO */ buff->next = rxd_wb->next_desc_ptr; ++ring->stats.rx.lro_packets; @@ -884,13 +885,16 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, { struct aq_nic_cfg_s *cfg = self->aq_nic_cfg; unsigned int i = 0U; + u32 vlan_promisc; + u32 l2_promisc; - hw_atl_rpfl2promiscuous_mode_en_set(self, - IS_FILTER_ENABLED(IFF_PROMISC)); + l2_promisc = IS_FILTER_ENABLED(IFF_PROMISC) || + !!(cfg->priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET)); + vlan_promisc = l2_promisc || cfg->is_vlan_force_promisc; - hw_atl_rpf_vlan_prom_mode_en_set(self, - IS_FILTER_ENABLED(IFF_PROMISC) || - cfg->is_vlan_force_promisc); + hw_atl_rpfl2promiscuous_mode_en_set(self, l2_promisc); + + hw_atl_rpf_vlan_prom_mode_en_set(self, vlan_promisc); hw_atl_rpfl2multicast_flr_en_set(self, IS_FILTER_ENABLED(IFF_ALLMULTI) && diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 9d62200b6c33..cc86038b1d96 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11775,6 +11775,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (version_printed++ == 0) pr_info("%s", version); + /* Clear any pending DMA transactions from crash kernel + * while loading driver in capture kernel. + */ + if (is_kdump_kernel()) { + pci_clear_master(pdev); + pcie_flr(pdev); + } + max_irqs = bnxt_get_max_irq(pdev); dev = alloc_etherdev_mq(sizeof(*bp), max_irqs); if (!dev) @@ -11972,10 +11980,10 @@ static void bnxt_shutdown(struct pci_dev *pdev) dev_close(dev); bnxt_ulp_shutdown(bp); + bnxt_clear_int_mode(bp); + pci_disable_device(pdev); if (system_state == SYSTEM_POWER_OFF) { - bnxt_clear_int_mode(bp); - pci_disable_device(pdev); pci_wake_from_d3(pdev, bp->wol); pci_set_power_state(pdev, PCI_D3hot); } diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 19fe4f4867c7..c16cc1cb5874 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -645,6 +645,7 @@ #define MACB_CAPS_GEM_HAS_PTP 0x00000040 #define MACB_CAPS_BD_RD_PREFETCH 0x00000080 #define MACB_CAPS_NEEDS_RSTONUBR 0x00000100 +#define MACB_CAPS_MACB_IS_EMAC 0x08000000 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 71bb0d56533a..20db44d7cda8 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -533,8 +533,21 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR); /* Clear all the bits we might set later */ - ctrl &= ~(GEM_BIT(GBE) | MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE) | - GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); + ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE)); + + if (bp->caps & MACB_CAPS_MACB_IS_EMAC) { + if (state->interface == PHY_INTERFACE_MODE_RMII) + ctrl |= MACB_BIT(RM9200_RMII); + } else { + ctrl &= ~(GEM_BIT(GBE) | GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); + + /* We do not support MLO_PAUSE_RX yet */ + if (state->pause & MLO_PAUSE_TX) + ctrl |= MACB_BIT(PAE); + + if (state->interface == PHY_INTERFACE_MODE_SGMII) + ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL); + } if (state->speed == SPEED_1000) ctrl |= GEM_BIT(GBE); @@ -544,13 +557,6 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, if (state->duplex) ctrl |= MACB_BIT(FD); - /* We do not support MLO_PAUSE_RX yet */ - if (state->pause & MLO_PAUSE_TX) - ctrl |= MACB_BIT(PAE); - - if (state->interface == PHY_INTERFACE_MODE_SGMII) - ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL); - /* Apply the new configuration, if any */ if (old_ctrl ^ ctrl) macb_or_gem_writel(bp, NCFGR, ctrl); @@ -569,9 +575,10 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode, unsigned int q; u32 ctrl; - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) - queue_writel(queue, IDR, - bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) + queue_writel(queue, IDR, + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); /* Disable Rx and Tx */ ctrl = macb_readl(bp, NCR) & ~(MACB_BIT(RE) | MACB_BIT(TE)); @@ -588,17 +595,19 @@ static void macb_mac_link_up(struct phylink_config *config, unsigned int mode, struct macb_queue *queue; unsigned int q; - macb_set_tx_clk(bp->tx_clk, bp->speed, ndev); + if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) { + macb_set_tx_clk(bp->tx_clk, bp->speed, ndev); - /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down - * cleared the pipeline and control registers. - */ - bp->macbgem_ops.mog_init_rings(bp); - macb_init_buffers(bp); + /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down + * cleared the pipeline and control registers. + */ + bp->macbgem_ops.mog_init_rings(bp); + macb_init_buffers(bp); - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) - queue_writel(queue, IER, - bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) + queue_writel(queue, IER, + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + } /* Enable Rx and Tx */ macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE)); @@ -3751,6 +3760,10 @@ static int at91ether_open(struct net_device *dev) u32 ctl; int ret; + ret = pm_runtime_get_sync(&lp->pdev->dev); + if (ret < 0) + return ret; + /* Clear internal statistics */ ctl = macb_readl(lp, NCR); macb_writel(lp, NCR, ctl | MACB_BIT(CLRSTAT)); @@ -3815,7 +3828,7 @@ static int at91ether_close(struct net_device *dev) q->rx_buffers, q->rx_buffers_dma); q->rx_buffers = NULL; - return 0; + return pm_runtime_put(&lp->pdev->dev); } /* Transmit packet */ @@ -3998,7 +4011,6 @@ static int at91ether_init(struct platform_device *pdev) struct net_device *dev = platform_get_drvdata(pdev); struct macb *bp = netdev_priv(dev); int err; - u32 reg; bp->queues[0].bp = bp; @@ -4012,11 +4024,7 @@ static int at91ether_init(struct platform_device *pdev) macb_writel(bp, NCR, 0); - reg = MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG); - if (bp->phy_interface == PHY_INTERFACE_MODE_RMII) - reg |= MACB_BIT(RM9200_RMII); - - macb_writel(bp, NCFGR, reg); + macb_writel(bp, NCFGR, MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG)); return 0; } @@ -4175,7 +4183,7 @@ static const struct macb_config sama5d4_config = { }; static const struct macb_config emac_config = { - .caps = MACB_CAPS_NEEDS_RSTONUBR, + .caps = MACB_CAPS_NEEDS_RSTONUBR | MACB_CAPS_MACB_IS_EMAC, .clk_init = at91ether_clk_init, .init = at91ether_init, }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 13dbd249f35f..5d74f5a60102 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -6106,6 +6106,9 @@ static int hclge_get_all_rules(struct hnae3_handle *handle, static void hclge_fd_get_flow_tuples(const struct flow_keys *fkeys, struct hclge_fd_rule_tuples *tuples) { +#define flow_ip6_src fkeys->addrs.v6addrs.src.in6_u.u6_addr32 +#define flow_ip6_dst fkeys->addrs.v6addrs.dst.in6_u.u6_addr32 + tuples->ether_proto = be16_to_cpu(fkeys->basic.n_proto); tuples->ip_proto = fkeys->basic.ip_proto; tuples->dst_port = be16_to_cpu(fkeys->ports.dst); @@ -6114,12 +6117,12 @@ static void hclge_fd_get_flow_tuples(const struct flow_keys *fkeys, tuples->src_ip[3] = be32_to_cpu(fkeys->addrs.v4addrs.src); tuples->dst_ip[3] = be32_to_cpu(fkeys->addrs.v4addrs.dst); } else { - memcpy(tuples->src_ip, - fkeys->addrs.v6addrs.src.in6_u.u6_addr32, - sizeof(tuples->src_ip)); - memcpy(tuples->dst_ip, - fkeys->addrs.v6addrs.dst.in6_u.u6_addr32, - sizeof(tuples->dst_ip)); + int i; + + for (i = 0; i < IPV6_SIZE; i++) { + tuples->src_ip[i] = be32_to_cpu(flow_ip6_src[i]); + tuples->dst_ip[i] = be32_to_cpu(flow_ip6_dst[i]); + } } } @@ -9821,6 +9824,13 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + ret = init_mgr_tbl(hdev); + if (ret) { + dev_err(&pdev->dev, + "failed to reinit manager table, ret = %d\n", ret); + return ret; + } + ret = hclge_init_fd_config(hdev); if (ret) { dev_err(&pdev->dev, "fd table init fail, ret=%d\n", ret); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 180224eab1ca..28db13253a5e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -566,7 +566,7 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) */ kinfo->num_tc = vport->vport_id ? 1 : min_t(u16, vport->alloc_tqps, hdev->tm_info.num_tc); - vport->qs_offset = (vport->vport_id ? hdev->tm_info.num_tc : 0) + + vport->qs_offset = (vport->vport_id ? HNAE3_MAX_TC : 0) + (vport->vport_id ? (vport->vport_id - 1) : 0); max_rss_size = min_t(u16, hdev->rss_size_max, diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 69523ac85639..56b9e445732b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2362,7 +2362,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) goto error_param; } - if (i40e_vc_validate_vqs_bitmaps(vqs)) { + if (!i40e_vc_validate_vqs_bitmaps(vqs)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2424,7 +2424,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) goto error_param; } - if (i40e_vc_validate_vqs_bitmaps(vqs)) { + if (!i40e_vc_validate_vqs_bitmaps(vqs)) { aq_ret = I40E_ERR_PARAM; goto error_param; } diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 77d6a0291e97..6939c14858b2 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -320,7 +320,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) if (err) return err; - dev_info(&vsi->back->pdev->dev, "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n", + dev_info(ice_pf_to_dev(vsi->back), "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n", ring->q_index); } else { if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) @@ -399,7 +399,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) /* Absolute queue number out of 2K needs to be passed */ err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); if (err) { - dev_err(&vsi->back->pdev->dev, + dev_err(ice_pf_to_dev(vsi->back), "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n", pf_q, err); return -EIO; @@ -422,7 +422,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) ice_alloc_rx_bufs_slow_zc(ring, ICE_DESC_UNUSED(ring)) : ice_alloc_rx_bufs(ring, ICE_DESC_UNUSED(ring)); if (err) - dev_info(&vsi->back->pdev->dev, + dev_info(ice_pf_to_dev(vsi->back), "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n", ring->xsk_umem ? "UMEM enabled " : "", ring->q_index, pf_q); @@ -817,13 +817,13 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, * queues at the hardware level anyway. */ if (status == ICE_ERR_RESET_ONGOING) { - dev_dbg(&vsi->back->pdev->dev, + dev_dbg(ice_pf_to_dev(vsi->back), "Reset in progress. LAN Tx queues already disabled\n"); } else if (status == ICE_ERR_DOES_NOT_EXIST) { - dev_dbg(&vsi->back->pdev->dev, + dev_dbg(ice_pf_to_dev(vsi->back), "LAN Tx queues do not exist, nothing to disable\n"); } else if (status) { - dev_err(&vsi->back->pdev->dev, + dev_err(ice_pf_to_dev(vsi->back), "Failed to disable LAN Tx queues, error: %d\n", status); return -ENODEV; } diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index fb1d930470c7..cb437a448305 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -937,7 +937,7 @@ void ice_deinit_hw(struct ice_hw *hw) */ enum ice_status ice_check_reset(struct ice_hw *hw) { - u32 cnt, reg = 0, grst_delay; + u32 cnt, reg = 0, grst_delay, uld_mask; /* Poll for Device Active state in case a recent CORER, GLOBR, * or EMPR has occurred. The grst delay value is in 100ms units. @@ -959,13 +959,20 @@ enum ice_status ice_check_reset(struct ice_hw *hw) return ICE_ERR_RESET_FAILED; } -#define ICE_RESET_DONE_MASK (GLNVM_ULD_CORER_DONE_M | \ - GLNVM_ULD_GLOBR_DONE_M) +#define ICE_RESET_DONE_MASK (GLNVM_ULD_PCIER_DONE_M |\ + GLNVM_ULD_PCIER_DONE_1_M |\ + GLNVM_ULD_CORER_DONE_M |\ + GLNVM_ULD_GLOBR_DONE_M |\ + GLNVM_ULD_POR_DONE_M |\ + GLNVM_ULD_POR_DONE_1_M |\ + GLNVM_ULD_PCIER_DONE_2_M) + + uld_mask = ICE_RESET_DONE_MASK; /* Device is Active; check Global Reset processes are done */ for (cnt = 0; cnt < ICE_PF_RESET_WAIT_COUNT; cnt++) { - reg = rd32(hw, GLNVM_ULD) & ICE_RESET_DONE_MASK; - if (reg == ICE_RESET_DONE_MASK) { + reg = rd32(hw, GLNVM_ULD) & uld_mask; + if (reg == uld_mask) { ice_debug(hw, ICE_DBG_INIT, "Global reset processes done. %d\n", cnt); break; diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index d870c1aedc17..265cf69b321b 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -713,13 +713,13 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app) return -EINVAL; mutex_lock(&pf->tc_mutex); - ret = dcb_ieee_delapp(netdev, app); - if (ret) - goto delapp_out; - old_cfg = &pf->hw.port_info->local_dcbx_cfg; - if (old_cfg->numapps == 1) + if (old_cfg->numapps <= 1) + goto delapp_out; + + ret = dcb_ieee_delapp(netdev, app); + if (ret) goto delapp_out; new_cfg = &pf->hw.port_info->desired_dcbx_cfg; @@ -882,7 +882,7 @@ ice_dcbnl_vsi_del_app(struct ice_vsi *vsi, sapp.protocol = app->prot_id; sapp.priority = app->priority; err = ice_dcbnl_delapp(vsi->netdev, &sapp); - dev_dbg(&vsi->back->pdev->dev, + dev_dbg(ice_pf_to_dev(vsi->back), "Deleting app for VSI idx=%d err=%d sel=%d proto=0x%x, prio=%d\n", vsi->idx, err, app->selector, app->prot_id, app->priority); } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 9ebd93e79aeb..9bd166e3dff3 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -165,13 +165,24 @@ static void ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { struct ice_netdev_priv *np = netdev_priv(netdev); + u8 oem_ver, oem_patch, nvm_ver_hi, nvm_ver_lo; struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + u16 oem_build; strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver)); strlcpy(drvinfo->version, ice_drv_ver, sizeof(drvinfo->version)); - strlcpy(drvinfo->fw_version, ice_nvm_version_str(&pf->hw), - sizeof(drvinfo->fw_version)); + + /* Display NVM version (from which the firmware version can be + * determined) which contains more pertinent information. + */ + ice_get_nvm_version(hw, &oem_ver, &oem_build, &oem_patch, + &nvm_ver_hi, &nvm_ver_lo); + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%x.%02x 0x%x %d.%d.%d", nvm_ver_hi, nvm_ver_lo, + hw->nvm.eetrack, oem_ver, oem_build, oem_patch); + strlcpy(drvinfo->bus_info, pci_name(pf->pdev), sizeof(drvinfo->bus_info)); drvinfo->n_priv_flags = ICE_PRIV_FLAG_ARRAY_SIZE; @@ -1043,7 +1054,7 @@ ice_set_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam) fec = ICE_FEC_NONE; break; default: - dev_warn(&vsi->back->pdev->dev, "Unsupported FEC mode: %d\n", + dev_warn(ice_pf_to_dev(vsi->back), "Unsupported FEC mode: %d\n", fecparam->fec); return -EINVAL; } diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index e8f32350fed2..6f4a70fa3903 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -276,8 +276,14 @@ #define GLNVM_GENS_SR_SIZE_S 5 #define GLNVM_GENS_SR_SIZE_M ICE_M(0x7, 5) #define GLNVM_ULD 0x000B6008 +#define GLNVM_ULD_PCIER_DONE_M BIT(0) +#define GLNVM_ULD_PCIER_DONE_1_M BIT(1) #define GLNVM_ULD_CORER_DONE_M BIT(3) #define GLNVM_ULD_GLOBR_DONE_M BIT(4) +#define GLNVM_ULD_POR_DONE_M BIT(5) +#define GLNVM_ULD_POR_DONE_1_M BIT(8) +#define GLNVM_ULD_PCIER_DONE_2_M BIT(9) +#define GLNVM_ULD_PE_DONE_M BIT(10) #define GLPCI_CNF2 0x000BE004 #define GLPCI_CNF2_CACHELINE_SIZE_M BIT(1) #define PF_FUNC_RID 0x0009E880 diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index e7449248fab4..b43bb51f6067 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -116,7 +116,7 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) vsi->num_tx_desc = ICE_DFLT_NUM_TX_DESC; break; default: - dev_dbg(&vsi->back->pdev->dev, + dev_dbg(ice_pf_to_dev(vsi->back), "Not setting number of Tx/Rx descriptors for VSI type %d\n", vsi->type); break; @@ -697,7 +697,7 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) vsi->num_txq = tx_count; if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) { - dev_dbg(&vsi->back->pdev->dev, "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n"); + dev_dbg(ice_pf_to_dev(vsi->back), "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n"); /* since there is a chance that num_rxq could have been changed * in the above for loop, make num_txq equal to num_rxq. */ @@ -1306,7 +1306,7 @@ int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) err = ice_setup_rx_ctx(vsi->rx_rings[i]); if (err) { - dev_err(&vsi->back->pdev->dev, + dev_err(ice_pf_to_dev(vsi->back), "ice_setup_rx_ctx failed for RxQ %d, err %d\n", i, err); return err; @@ -1476,7 +1476,7 @@ int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { - dev_err(&vsi->back->pdev->dev, "update VSI for VLAN insert failed, err %d aq_err %d\n", + dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %d aq_err %d\n", status, hw->adminq.sq_last_status); ret = -EIO; goto out; @@ -1522,7 +1522,7 @@ int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { - dev_err(&vsi->back->pdev->dev, "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n", + dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n", ena, status, hw->adminq.sq_last_status); ret = -EIO; goto out; @@ -1696,7 +1696,7 @@ ice_vsi_set_q_vectors_reg_idx(struct ice_vsi *vsi) struct ice_q_vector *q_vector = vsi->q_vectors[i]; if (!q_vector) { - dev_err(&vsi->back->pdev->dev, + dev_err(ice_pf_to_dev(vsi->back), "Failed to set reg_idx on q_vector %d VSI %d\n", i, vsi->vsi_num); goto clear_reg_idx; @@ -2647,25 +2647,6 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) } #endif /* CONFIG_DCB */ -/** - * ice_nvm_version_str - format the NVM version strings - * @hw: ptr to the hardware info - */ -char *ice_nvm_version_str(struct ice_hw *hw) -{ - u8 oem_ver, oem_patch, ver_hi, ver_lo; - static char buf[ICE_NVM_VER_LEN]; - u16 oem_build; - - ice_get_nvm_version(hw, &oem_ver, &oem_build, &oem_patch, &ver_hi, - &ver_lo); - - snprintf(buf, sizeof(buf), "%x.%02x 0x%x %d.%d.%d", ver_hi, ver_lo, - hw->nvm.eetrack, oem_ver, oem_build, oem_patch); - - return buf; -} - /** * ice_update_ring_stats - Update ring statistics * @ring: ring to update @@ -2737,6 +2718,6 @@ ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set) status = ice_remove_mac(&vsi->back->hw, &tmp_add_list); cfg_mac_fltr_exit: - ice_free_fltr_list(&vsi->back->pdev->dev, &tmp_add_list); + ice_free_fltr_list(ice_pf_to_dev(vsi->back), &tmp_add_list); return status; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 6e31e30aba39..0d2b1119c0e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -97,8 +97,6 @@ void ice_vsi_cfg_frame_size(struct ice_vsi *vsi); u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran); -char *ice_nvm_version_str(struct ice_hw *hw); - enum ice_status ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 69bff085acf7..7f71f06fa819 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -269,7 +269,7 @@ static int ice_cfg_promisc(struct ice_vsi *vsi, u8 promisc_m, bool set_promisc) */ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) { - struct device *dev = &vsi->back->pdev->dev; + struct device *dev = ice_pf_to_dev(vsi->back); struct net_device *netdev = vsi->netdev; bool promisc_forced_on = false; struct ice_pf *pf = vsi->back; @@ -1235,7 +1235,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf) u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >> GL_MDET_TX_TCLAN_QNUM_S); - if (netif_msg_rx_err(pf)) + if (netif_msg_tx_err(pf)) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff); @@ -1364,7 +1364,7 @@ static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up) if (vsi->type != ICE_VSI_PF) return 0; - dev = &vsi->back->pdev->dev; + dev = ice_pf_to_dev(vsi->back); pi = vsi->port_info; @@ -1682,7 +1682,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) */ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) { - struct device *dev = &vsi->back->pdev->dev; + struct device *dev = ice_pf_to_dev(vsi->back); int i; for (i = 0; i < vsi->num_xdp_txq; i++) { @@ -3241,11 +3241,6 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) goto err_exit_unroll; } - dev_info(dev, "firmware %d.%d.%d api %d.%d.%d nvm %s build 0x%08x\n", - hw->fw_maj_ver, hw->fw_min_ver, hw->fw_patch, - hw->api_maj_ver, hw->api_min_ver, hw->api_patch, - ice_nvm_version_str(hw), hw->fw_build); - ice_request_fw(pf); /* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be @@ -3863,14 +3858,14 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) /* Don't set any netdev advanced features with device in Safe Mode */ if (ice_is_safe_mode(vsi->back)) { - dev_err(&vsi->back->pdev->dev, + dev_err(ice_pf_to_dev(vsi->back), "Device is in Safe Mode - not enabling advanced netdev features\n"); return ret; } /* Do not change setting during reset */ if (ice_is_reset_in_progress(pf->state)) { - dev_err(&vsi->back->pdev->dev, + dev_err(ice_pf_to_dev(vsi->back), "Device is resetting, changing advanced netdev features temporarily unavailable.\n"); return -EBUSY; } @@ -4413,7 +4408,7 @@ int ice_vsi_setup_tx_rings(struct ice_vsi *vsi) int i, err = 0; if (!vsi->num_txq) { - dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Tx queues\n", + dev_err(ice_pf_to_dev(vsi->back), "VSI %d has 0 Tx queues\n", vsi->vsi_num); return -EINVAL; } @@ -4444,7 +4439,7 @@ int ice_vsi_setup_rx_rings(struct ice_vsi *vsi) int i, err = 0; if (!vsi->num_rxq) { - dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Rx queues\n", + dev_err(ice_pf_to_dev(vsi->back), "VSI %d has 0 Rx queues\n", vsi->vsi_num); return -EINVAL; } @@ -4973,7 +4968,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode) status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { - dev_err(&vsi->back->pdev->dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n", + dev_err(ice_pf_to_dev(vsi->back), "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n", bmode, status, hw->adminq.sq_last_status); ret = -EIO; goto out; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 35bbc4ff603c..6da048a6ca7c 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -10,7 +10,7 @@ */ void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val) { - u16 prev_ntu = rx_ring->next_to_use; + u16 prev_ntu = rx_ring->next_to_use & ~0x7; rx_ring->next_to_use = val; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index edb374296d1f..e2114f24a19e 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -508,7 +508,7 @@ static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 vid, bool enable) status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { - dev_info(&vsi->back->pdev->dev, "update VSI for port VLAN failed, err %d aq_err %d\n", + dev_info(ice_pf_to_dev(vsi->back), "update VSI for port VLAN failed, err %d aq_err %d\n", status, hw->adminq.sq_last_status); ret = -EIO; goto out; @@ -2019,7 +2019,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) continue; if (ice_vsi_ctrl_rx_ring(vsi, true, vf_q_id)) { - dev_err(&vsi->back->pdev->dev, + dev_err(ice_pf_to_dev(vsi->back), "Failed to enable Rx ring %d on VSI %d\n", vf_q_id, vsi->vsi_num); v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -2122,7 +2122,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) if (ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id, ring, &txq_meta)) { - dev_err(&vsi->back->pdev->dev, + dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Tx ring %d on VSI %d\n", vf_q_id, vsi->vsi_num); v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -2149,7 +2149,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) continue; if (ice_vsi_ctrl_rx_ring(vsi, false, vf_q_id)) { - dev_err(&vsi->back->pdev->dev, + dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Rx ring %d on VSI %d\n", vf_q_id, vsi->vsi_num); v_ret = VIRTCHNL_STATUS_ERR_PARAM; diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index 2da8eee27e98..ecbd4be145b8 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -114,6 +114,14 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) if (err != 4) break; + /* At this point the IFH was read correctly, so it is safe to + * presume that there is no error. The err needs to be reset + * otherwise a frame could come in CPU queue between the while + * condition and the check for error later on. And in that case + * the new frame is just removed and not processed. + */ + err = 0; + ocelot_parse_ifh(ifh, &info); ocelot_port = ocelot->ports[info.port]; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 5f9d2ec70446..61c06fbe10db 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -103,7 +103,7 @@ int ionic_heartbeat_check(struct ionic *ionic) { struct ionic_dev *idev = &ionic->idev; unsigned long hb_time; - u32 fw_status; + u8 fw_status; u32 hb; /* wait a little more than one second before testing again */ @@ -111,9 +111,12 @@ int ionic_heartbeat_check(struct ionic *ionic) if (time_before(hb_time, (idev->last_hb_time + ionic->watchdog_period))) return 0; - /* firmware is useful only if fw_status is non-zero */ - fw_status = ioread32(&idev->dev_info_regs->fw_status); - if (!fw_status) + /* firmware is useful only if the running bit is set and + * fw_status != 0xff (bad PCI read) + */ + fw_status = ioread8(&idev->dev_info_regs->fw_status); + if (fw_status == 0xff || + !(fw_status & IONIC_FW_STS_F_RUNNING)) return -ENXIO; /* early FW has no heartbeat, else FW will return non-zero */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h index ed23a05f2642..d5e8b4e2a96e 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_if.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h @@ -2348,6 +2348,7 @@ union ionic_dev_info_regs { u8 version; u8 asic_type; u8 asic_rev; +#define IONIC_FW_STS_F_RUNNING 0x1 u8 fw_status; u32 fw_heartbeat; char fw_version[IONIC_DEVINFO_FWVERS_BUFLEN]; diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index e8a1b27db84d..234c6f30effb 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -163,6 +163,8 @@ struct qede_rdma_dev { struct list_head entry; struct list_head rdma_event_list; struct workqueue_struct *rdma_wq; + struct kref refcnt; + struct completion event_comp; bool exp_recovery; }; diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c index ffabc2d2f082..2d873ae8a234 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c +++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c @@ -59,6 +59,9 @@ static void _qede_rdma_dev_add(struct qede_dev *edev) static int qede_rdma_create_wq(struct qede_dev *edev) { INIT_LIST_HEAD(&edev->rdma_info.rdma_event_list); + kref_init(&edev->rdma_info.refcnt); + init_completion(&edev->rdma_info.event_comp); + edev->rdma_info.rdma_wq = create_singlethread_workqueue("rdma_wq"); if (!edev->rdma_info.rdma_wq) { DP_NOTICE(edev, "qedr: Could not create workqueue\n"); @@ -83,8 +86,23 @@ static void qede_rdma_cleanup_event(struct qede_dev *edev) } } +static void qede_rdma_complete_event(struct kref *ref) +{ + struct qede_rdma_dev *rdma_dev = + container_of(ref, struct qede_rdma_dev, refcnt); + + /* no more events will be added after this */ + complete(&rdma_dev->event_comp); +} + static void qede_rdma_destroy_wq(struct qede_dev *edev) { + /* Avoid race with add_event flow, make sure it finishes before + * we start accessing the list and cleaning up the work + */ + kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event); + wait_for_completion(&edev->rdma_info.event_comp); + qede_rdma_cleanup_event(edev); destroy_workqueue(edev->rdma_info.rdma_wq); } @@ -310,15 +328,24 @@ static void qede_rdma_add_event(struct qede_dev *edev, if (!edev->rdma_info.qedr_dev) return; + /* We don't want the cleanup flow to start while we're allocating and + * scheduling the work + */ + if (!kref_get_unless_zero(&edev->rdma_info.refcnt)) + return; /* already being destroyed */ + event_node = qede_rdma_get_free_event_node(edev); if (!event_node) - return; + goto out; event_node->event = event; event_node->ptr = edev; INIT_WORK(&event_node->work, qede_rdma_handle_event); queue_work(edev->rdma_info.rdma_wq, &event_node->work); + +out: + kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event); } void qede_rdma_dev_event_open(struct qede_dev *edev) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index eab83e71567a..6c0732fc8c25 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -99,7 +99,7 @@ static struct netvsc_device *alloc_net_device(void) init_waitqueue_head(&net_device->wait_drain); net_device->destroy = false; - net_device->tx_disable = false; + net_device->tx_disable = true; net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f3f9eb8a402a..ee1ad7ae7555 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -977,6 +977,7 @@ static int netvsc_attach(struct net_device *ndev, } /* In any case device is now ready */ + nvdev->tx_disable = false; netif_device_attach(ndev); /* Note: enable and attach happen when sub-channels setup */ @@ -2354,6 +2355,8 @@ static int netvsc_probe(struct hv_device *dev, else net->max_mtu = ETH_DATA_LEN; + nvdev->tx_disable = false; + ret = register_netdevice(net); if (ret != 0) { pr_err("Unable to register netdev.\n"); diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c index 7e9975d25066..f1ded03f0229 100644 --- a/drivers/net/phy/mdio-bcm-iproc.c +++ b/drivers/net/phy/mdio-bcm-iproc.c @@ -178,6 +178,23 @@ static int iproc_mdio_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +int iproc_mdio_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct iproc_mdio_priv *priv = platform_get_drvdata(pdev); + + /* restore the mii clock configuration */ + iproc_mdio_config_clk(priv->base); + + return 0; +} + +static const struct dev_pm_ops iproc_mdio_pm_ops = { + .resume = iproc_mdio_resume +}; +#endif /* CONFIG_PM_SLEEP */ + static const struct of_device_id iproc_mdio_of_match[] = { { .compatible = "brcm,iproc-mdio", }, { /* sentinel */ }, @@ -188,6 +205,9 @@ static struct platform_driver iproc_mdio_driver = { .driver = { .name = "iproc-mdio", .of_match_table = iproc_mdio_of_match, +#ifdef CONFIG_PM_SLEEP + .pm = &iproc_mdio_pm_ops, +#endif }, .probe = iproc_mdio_probe, .remove = iproc_mdio_remove, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 9485c8d1de8a..3b7a3b8a5e06 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -61,7 +61,6 @@ enum qmi_wwan_flags { enum qmi_wwan_quirks { QMI_WWAN_QUIRK_DTR = 1 << 0, /* needs "set DTR" request */ - QMI_WWAN_QUIRK_QUECTEL_DYNCFG = 1 << 1, /* check num. endpoints */ }; struct qmimux_hdr { @@ -916,16 +915,6 @@ static const struct driver_info qmi_wwan_info_quirk_dtr = { .data = QMI_WWAN_QUIRK_DTR, }; -static const struct driver_info qmi_wwan_info_quirk_quectel_dyncfg = { - .description = "WWAN/QMI device", - .flags = FLAG_WWAN | FLAG_SEND_ZLP, - .bind = qmi_wwan_bind, - .unbind = qmi_wwan_unbind, - .manage_power = qmi_wwan_manage_power, - .rx_fixup = qmi_wwan_rx_fixup, - .data = QMI_WWAN_QUIRK_DTR | QMI_WWAN_QUIRK_QUECTEL_DYNCFG, -}; - #define HUAWEI_VENDOR_ID 0x12D1 /* map QMI/wwan function by a fixed interface number */ @@ -946,14 +935,18 @@ static const struct driver_info qmi_wwan_info_quirk_quectel_dyncfg = { #define QMI_GOBI_DEVICE(vend, prod) \ QMI_FIXED_INTF(vend, prod, 0) -/* Quectel does not use fixed interface numbers on at least some of their - * devices. We need to check the number of endpoints to ensure that we bind to - * the correct interface. +/* Many devices have QMI and DIAG functions which are distinguishable + * from other vendor specific functions by class, subclass and + * protocol all being 0xff. The DIAG function has exactly 2 endpoints + * and is silently rejected when probed. + * + * This makes it possible to match dynamically numbered QMI functions + * as seen on e.g. many Quectel modems. */ -#define QMI_QUIRK_QUECTEL_DYNCFG(vend, prod) \ +#define QMI_MATCH_FF_FF_FF(vend, prod) \ USB_DEVICE_AND_INTERFACE_INFO(vend, prod, USB_CLASS_VENDOR_SPEC, \ USB_SUBCLASS_VENDOR_SPEC, 0xff), \ - .driver_info = (unsigned long)&qmi_wwan_info_quirk_quectel_dyncfg + .driver_info = (unsigned long)&qmi_wwan_info_quirk_dtr static const struct usb_device_id products[] = { /* 1. CDC ECM like devices match on the control interface */ @@ -1059,10 +1052,10 @@ static const struct usb_device_id products[] = { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7), .driver_info = (unsigned long)&qmi_wwan_info, }, - {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0125)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ - {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0306)}, /* Quectel EP06/EG06/EM06 */ - {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0512)}, /* Quectel EG12/EM12 */ - {QMI_QUIRK_QUECTEL_DYNCFG(0x2c7c, 0x0800)}, /* Quectel RM500Q-GL */ + {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0125)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ + {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0306)}, /* Quectel EP06/EG06/EM06 */ + {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0512)}, /* Quectel EG12/EM12 */ + {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0800)}, /* Quectel RM500Q-GL */ /* 3. Combined interface devices matching on interface number */ {QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */ @@ -1363,6 +1356,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ + {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e preproduction config */ {QMI_FIXED_INTF(0x413c, 0x81e0, 0)}, /* Dell Wireless 5821e with eSIM support*/ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ @@ -1454,7 +1448,6 @@ static int qmi_wwan_probe(struct usb_interface *intf, { struct usb_device_id *id = (struct usb_device_id *)prod; struct usb_interface_descriptor *desc = &intf->cur_altsetting->desc; - const struct driver_info *info; /* Workaround to enable dynamic IDs. This disables usbnet * blacklisting functionality. Which, if required, can be @@ -1490,12 +1483,8 @@ static int qmi_wwan_probe(struct usb_interface *intf, * different. Ignore the current interface if the number of endpoints * equals the number for the diag interface (two). */ - info = (void *)id->driver_info; - - if (info->data & QMI_WWAN_QUIRK_QUECTEL_DYNCFG) { - if (desc->bNumEndpoints == 2) - return -ENODEV; - } + if (desc->bNumEndpoints == 2) + return -ENODEV; return usbnet_probe(intf, id); } diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h index 547ff3c578ee..fa5634af40f7 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.h +++ b/drivers/net/wireless/marvell/mwifiex/main.h @@ -1295,19 +1295,6 @@ mwifiex_copy_rates(u8 *dest, u32 pos, u8 *src, int len) return pos; } -/* This function return interface number with the same bss_type. - */ -static inline u8 -mwifiex_get_intf_num(struct mwifiex_adapter *adapter, u8 bss_type) -{ - u8 i, num = 0; - - for (i = 0; i < adapter->priv_num; i++) - if (adapter->priv[i] && adapter->priv[i]->bss_type == bss_type) - num++; - return num; -} - /* * This function returns the correct private structure pointer based * upon the BSS type and BSS number. diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c index 7caf1d26124a..f8f282ce39bd 100644 --- a/drivers/net/wireless/marvell/mwifiex/tdls.c +++ b/drivers/net/wireless/marvell/mwifiex/tdls.c @@ -894,7 +894,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv, u8 *peer, *pos, *end; u8 i, action, basic; u16 cap = 0; - int ie_len = 0; + int ies_len = 0; if (len < (sizeof(struct ethhdr) + 3)) return; @@ -916,7 +916,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv, pos = buf + sizeof(struct ethhdr) + 4; /* payload 1+ category 1 + action 1 + dialog 1 */ cap = get_unaligned_le16(pos); - ie_len = len - sizeof(struct ethhdr) - TDLS_REQ_FIX_LEN; + ies_len = len - sizeof(struct ethhdr) - TDLS_REQ_FIX_LEN; pos += 2; break; @@ -926,7 +926,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv, /* payload 1+ category 1 + action 1 + dialog 1 + status code 2*/ pos = buf + sizeof(struct ethhdr) + 6; cap = get_unaligned_le16(pos); - ie_len = len - sizeof(struct ethhdr) - TDLS_RESP_FIX_LEN; + ies_len = len - sizeof(struct ethhdr) - TDLS_RESP_FIX_LEN; pos += 2; break; @@ -934,7 +934,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv, if (len < (sizeof(struct ethhdr) + TDLS_CONFIRM_FIX_LEN)) return; pos = buf + sizeof(struct ethhdr) + TDLS_CONFIRM_FIX_LEN; - ie_len = len - sizeof(struct ethhdr) - TDLS_CONFIRM_FIX_LEN; + ies_len = len - sizeof(struct ethhdr) - TDLS_CONFIRM_FIX_LEN; break; default: mwifiex_dbg(priv->adapter, ERROR, "Unknown TDLS frame type.\n"); @@ -947,33 +947,33 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv, sta_ptr->tdls_cap.capab = cpu_to_le16(cap); - for (end = pos + ie_len; pos + 1 < end; pos += 2 + pos[1]) { - if (pos + 2 + pos[1] > end) + for (end = pos + ies_len; pos + 1 < end; pos += 2 + pos[1]) { + u8 ie_len = pos[1]; + + if (pos + 2 + ie_len > end) break; switch (*pos) { case WLAN_EID_SUPP_RATES: - if (pos[1] > 32) + if (ie_len > sizeof(sta_ptr->tdls_cap.rates)) return; - sta_ptr->tdls_cap.rates_len = pos[1]; - for (i = 0; i < pos[1]; i++) + sta_ptr->tdls_cap.rates_len = ie_len; + for (i = 0; i < ie_len; i++) sta_ptr->tdls_cap.rates[i] = pos[i + 2]; break; case WLAN_EID_EXT_SUPP_RATES: - if (pos[1] > 32) + if (ie_len > sizeof(sta_ptr->tdls_cap.rates)) return; basic = sta_ptr->tdls_cap.rates_len; - if (pos[1] > 32 - basic) + if (ie_len > sizeof(sta_ptr->tdls_cap.rates) - basic) return; - for (i = 0; i < pos[1]; i++) + for (i = 0; i < ie_len; i++) sta_ptr->tdls_cap.rates[basic + i] = pos[i + 2]; - sta_ptr->tdls_cap.rates_len += pos[1]; + sta_ptr->tdls_cap.rates_len += ie_len; break; case WLAN_EID_HT_CAPABILITY: - if (pos > end - sizeof(struct ieee80211_ht_cap) - 2) - return; - if (pos[1] != sizeof(struct ieee80211_ht_cap)) + if (ie_len != sizeof(struct ieee80211_ht_cap)) return; /* copy the ie's value into ht_capb*/ memcpy((u8 *)&sta_ptr->tdls_cap.ht_capb, pos + 2, @@ -981,59 +981,45 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv, sta_ptr->is_11n_enabled = 1; break; case WLAN_EID_HT_OPERATION: - if (pos > end - - sizeof(struct ieee80211_ht_operation) - 2) - return; - if (pos[1] != sizeof(struct ieee80211_ht_operation)) + if (ie_len != sizeof(struct ieee80211_ht_operation)) return; /* copy the ie's value into ht_oper*/ memcpy(&sta_ptr->tdls_cap.ht_oper, pos + 2, sizeof(struct ieee80211_ht_operation)); break; case WLAN_EID_BSS_COEX_2040: - if (pos > end - 3) - return; - if (pos[1] != 1) + if (ie_len != sizeof(pos[2])) return; sta_ptr->tdls_cap.coex_2040 = pos[2]; break; case WLAN_EID_EXT_CAPABILITY: - if (pos > end - sizeof(struct ieee_types_header)) - return; - if (pos[1] < sizeof(struct ieee_types_header)) + if (ie_len < sizeof(struct ieee_types_header)) return; - if (pos[1] > 8) + if (ie_len > 8) return; memcpy((u8 *)&sta_ptr->tdls_cap.extcap, pos, sizeof(struct ieee_types_header) + - min_t(u8, pos[1], 8)); + min_t(u8, ie_len, 8)); break; case WLAN_EID_RSN: - if (pos > end - sizeof(struct ieee_types_header)) + if (ie_len < sizeof(struct ieee_types_header)) return; - if (pos[1] < sizeof(struct ieee_types_header)) - return; - if (pos[1] > IEEE_MAX_IE_SIZE - + if (ie_len > IEEE_MAX_IE_SIZE - sizeof(struct ieee_types_header)) return; memcpy((u8 *)&sta_ptr->tdls_cap.rsn_ie, pos, sizeof(struct ieee_types_header) + - min_t(u8, pos[1], IEEE_MAX_IE_SIZE - + min_t(u8, ie_len, IEEE_MAX_IE_SIZE - sizeof(struct ieee_types_header))); break; case WLAN_EID_QOS_CAPA: - if (pos > end - 3) - return; - if (pos[1] != 1) + if (ie_len != sizeof(pos[2])) return; sta_ptr->tdls_cap.qos_info = pos[2]; break; case WLAN_EID_VHT_OPERATION: if (priv->adapter->is_hw_11ac_capable) { - if (pos > end - - sizeof(struct ieee80211_vht_operation) - 2) - return; - if (pos[1] != + if (ie_len != sizeof(struct ieee80211_vht_operation)) return; /* copy the ie's value into vhtoper*/ @@ -1043,10 +1029,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv, break; case WLAN_EID_VHT_CAPABILITY: if (priv->adapter->is_hw_11ac_capable) { - if (pos > end - - sizeof(struct ieee80211_vht_cap) - 2) - return; - if (pos[1] != sizeof(struct ieee80211_vht_cap)) + if (ie_len != sizeof(struct ieee80211_vht_cap)) return; /* copy the ie's value into vhtcap*/ memcpy((u8 *)&sta_ptr->tdls_cap.vhtcap, pos + 2, @@ -1056,9 +1039,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv, break; case WLAN_EID_AID: if (priv->adapter->is_hw_11ac_capable) { - if (pos > end - 4) - return; - if (pos[1] != 2) + if (ie_len != sizeof(u16)) return; sta_ptr->tdls_cap.aid = get_unaligned_le16((pos + 2)); diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index 720c89d6066e..4ac8cb262559 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -225,6 +225,7 @@ static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy) out: gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity); + usleep_range(10000, 15000); } static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 641c07347e8d..ada59df642d2 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -66,8 +66,8 @@ MODULE_PARM_DESC(streams, "turn on support for Streams write directives"); * nvme_reset_wq - hosts nvme reset works * nvme_delete_wq - hosts nvme delete works * - * nvme_wq will host works such are scan, aen handling, fw activation, - * keep-alive error recovery, periodic reconnects etc. nvme_reset_wq + * nvme_wq will host works such as scan, aen handling, fw activation, + * keep-alive, periodic reconnects etc. nvme_reset_wq * runs reset works which also flush works hosted on nvme_wq for * serialization purposes. nvme_delete_wq host controller deletion * works which flush reset works for serialization. @@ -976,7 +976,7 @@ static void nvme_keep_alive_end_io(struct request *rq, blk_status_t status) startka = true; spin_unlock_irqrestore(&ctrl->lock, flags); if (startka) - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ); } static int nvme_keep_alive(struct nvme_ctrl *ctrl) @@ -1006,7 +1006,7 @@ static void nvme_keep_alive_work(struct work_struct *work) dev_dbg(ctrl->device, "reschedule traffic based keep-alive timer\n"); ctrl->comp_seen = false; - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ); return; } @@ -1023,7 +1023,7 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl) if (unlikely(ctrl->kato == 0)) return; - schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); + queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ); } void nvme_stop_keep_alive(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index da392b50f73e..bb5e13ad1aff 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1078,9 +1078,9 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx) spin_lock(&nvmeq->cq_poll_lock); found = nvme_process_cq(nvmeq, &start, &end, -1); + nvme_complete_cqes(nvmeq, start, end); spin_unlock(&nvmeq->cq_poll_lock); - nvme_complete_cqes(nvmeq, start, end); return found; } @@ -1401,6 +1401,23 @@ static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown) nvme_poll_irqdisable(nvmeq, -1); } +/* + * Called only on a device that has been disabled and after all other threads + * that can check this device's completion queues have synced. This is the + * last chance for the driver to see a natural completion before + * nvme_cancel_request() terminates all incomplete requests. + */ +static void nvme_reap_pending_cqes(struct nvme_dev *dev) +{ + u16 start, end; + int i; + + for (i = dev->ctrl.queue_count - 1; i > 0; i--) { + nvme_process_cq(&dev->queues[i], &start, &end, -1); + nvme_complete_cqes(&dev->queues[i], start, end); + } +} + static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues, int entry_size) { @@ -2235,11 +2252,6 @@ static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode) if (timeout == 0) return false; - /* handle any remaining CQEs */ - if (opcode == nvme_admin_delete_cq && - !test_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags)) - nvme_poll_irqdisable(nvmeq, -1); - sent--; if (nr_queues) goto retry; @@ -2428,6 +2440,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_suspend_io_queues(dev); nvme_suspend_queue(&dev->queues[0]); nvme_pci_disable(dev); + nvme_reap_pending_cqes(dev); blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl); blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 2a47c6c5007e..3e85c5cacefd 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1088,7 +1088,7 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl) if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING)) return; - queue_work(nvme_wq, &ctrl->err_work); + queue_work(nvme_reset_wq, &ctrl->err_work); } static void nvme_rdma_wr_error(struct ib_cq *cq, struct ib_wc *wc, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 6d43b23a0fc8..49d4373b84eb 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -422,7 +422,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl) if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) return; - queue_work(nvme_wq, &to_tcp_ctrl(ctrl)->err_work); + queue_work(nvme_reset_wq, &to_tcp_ctrl(ctrl)->err_work); } static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue, @@ -1054,7 +1054,12 @@ static void nvme_tcp_io_work(struct work_struct *w) } else if (unlikely(result < 0)) { dev_err(queue->ctrl->ctrl.device, "failed to send request %d\n", result); - if (result != -EPIPE) + + /* + * Fail the request unless peer closed the connection, + * in which case error recovery flow will complete all. + */ + if ((result != -EPIPE) && (result != -ECONNRESET)) nvme_tcp_fail_request(queue->request); nvme_tcp_done_send_req(queue); return; diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index d704eccc548f..f01a57e5a5f3 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -771,7 +771,7 @@ static int smmu_pmu_probe(struct platform_device *pdev) smmu_pmu->reloc_base = smmu_pmu->reg_base; } - irq = platform_get_irq(pdev, 0); + irq = platform_get_irq_optional(pdev, 0); if (irq > 0) smmu_pmu->irq = irq; diff --git a/drivers/pwm/pwm-omap-dmtimer.c b/drivers/pwm/pwm-omap-dmtimer.c index e36fcad668a6..88a3c5690fea 100644 --- a/drivers/pwm/pwm-omap-dmtimer.c +++ b/drivers/pwm/pwm-omap-dmtimer.c @@ -256,7 +256,7 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev) if (!timer_pdev) { dev_err(&pdev->dev, "Unable to find Timer pdev\n"); ret = -ENODEV; - goto put; + goto err_find_timer_pdev; } timer_pdata = dev_get_platdata(&timer_pdev->dev); @@ -264,7 +264,7 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "dmtimer pdata structure NULL, deferring probe\n"); ret = -EPROBE_DEFER; - goto put; + goto err_platdata; } pdata = timer_pdata->timer_ops; @@ -283,19 +283,19 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev) !pdata->write_counter) { dev_err(&pdev->dev, "Incomplete dmtimer pdata structure\n"); ret = -EINVAL; - goto put; + goto err_platdata; } if (!of_get_property(timer, "ti,timer-pwm", NULL)) { dev_err(&pdev->dev, "Missing ti,timer-pwm capability\n"); ret = -ENODEV; - goto put; + goto err_timer_property; } dm_timer = pdata->request_by_node(timer); if (!dm_timer) { ret = -EPROBE_DEFER; - goto put; + goto err_request_timer; } omap = devm_kzalloc(&pdev->dev, sizeof(*omap), GFP_KERNEL); @@ -352,7 +352,14 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev) err_alloc_omap: pdata->free(dm_timer); -put: +err_request_timer: + +err_timer_property: +err_platdata: + + put_device(&timer_pdev->dev); +err_find_timer_pdev: + of_node_put(timer); return ret; @@ -372,6 +379,8 @@ static int pwm_omap_dmtimer_remove(struct platform_device *pdev) omap->pdata->free(omap->dm_timer); + put_device(&omap->dm_timer_pdev->dev); + mutex_destroy(&omap->mutex); return 0; diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index bb35ba4a8d24..4348fdff1c61 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -162,7 +162,7 @@ struct ap_card { unsigned int functions; /* AP device function bitfield. */ int queue_depth; /* AP queue depth.*/ int id; /* AP card number. */ - atomic_t total_request_count; /* # requests ever for this AP device.*/ + atomic64_t total_request_count; /* # requests ever for this AP device.*/ }; #define to_ap_card(x) container_of((x), struct ap_card, ap_dev.device) @@ -179,7 +179,7 @@ struct ap_queue { enum ap_state state; /* State of the AP device. */ int pendingq_count; /* # requests on pendingq list. */ int requestq_count; /* # requests on requestq list. */ - int total_request_count; /* # requests ever for this AP device.*/ + u64 total_request_count; /* # requests ever for this AP device.*/ int request_timeout; /* Request timeout in jiffies. */ struct timer_list timeout; /* Timer for request timeouts. */ struct list_head pendingq; /* List of message sent to AP queue. */ diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c index 63b4cc6cd7e5..e85bfca1ed16 100644 --- a/drivers/s390/crypto/ap_card.c +++ b/drivers/s390/crypto/ap_card.c @@ -63,13 +63,13 @@ static ssize_t request_count_show(struct device *dev, char *buf) { struct ap_card *ac = to_ap_card(dev); - unsigned int req_cnt; + u64 req_cnt; req_cnt = 0; spin_lock_bh(&ap_list_lock); - req_cnt = atomic_read(&ac->total_request_count); + req_cnt = atomic64_read(&ac->total_request_count); spin_unlock_bh(&ap_list_lock); - return snprintf(buf, PAGE_SIZE, "%d\n", req_cnt); + return snprintf(buf, PAGE_SIZE, "%llu\n", req_cnt); } static ssize_t request_count_store(struct device *dev, @@ -83,7 +83,7 @@ static ssize_t request_count_store(struct device *dev, for_each_ap_queue(aq, ac) aq->total_request_count = 0; spin_unlock_bh(&ap_list_lock); - atomic_set(&ac->total_request_count, 0); + atomic64_set(&ac->total_request_count, 0); return count; } diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 37c3bdc3642d..a317ab484932 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -479,12 +479,12 @@ static ssize_t request_count_show(struct device *dev, char *buf) { struct ap_queue *aq = to_ap_queue(dev); - unsigned int req_cnt; + u64 req_cnt; spin_lock_bh(&aq->lock); req_cnt = aq->total_request_count; spin_unlock_bh(&aq->lock); - return snprintf(buf, PAGE_SIZE, "%d\n", req_cnt); + return snprintf(buf, PAGE_SIZE, "%llu\n", req_cnt); } static ssize_t request_count_store(struct device *dev, @@ -676,7 +676,7 @@ void ap_queue_message(struct ap_queue *aq, struct ap_message *ap_msg) list_add_tail(&ap_msg->list, &aq->requestq); aq->requestq_count++; aq->total_request_count++; - atomic_inc(&aq->card->total_request_count); + atomic64_inc(&aq->card->total_request_count); /* Send/receive as many request from the queue as possible. */ ap_wait(ap_sm_event_loop(aq, AP_EVENT_POLL)); spin_unlock_bh(&aq->lock); diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 9157e728a362..7fa0262e91af 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -605,8 +605,8 @@ static inline bool zcrypt_card_compare(struct zcrypt_card *zc, weight += atomic_read(&zc->load); pref_weight += atomic_read(&pref_zc->load); if (weight == pref_weight) - return atomic_read(&zc->card->total_request_count) > - atomic_read(&pref_zc->card->total_request_count); + return atomic64_read(&zc->card->total_request_count) > + atomic64_read(&pref_zc->card->total_request_count); return weight > pref_weight; } @@ -1216,11 +1216,12 @@ static void zcrypt_qdepth_mask(char qdepth[], size_t max_adapters) spin_unlock(&zcrypt_list_lock); } -static void zcrypt_perdev_reqcnt(int reqcnt[], size_t max_adapters) +static void zcrypt_perdev_reqcnt(u32 reqcnt[], size_t max_adapters) { struct zcrypt_card *zc; struct zcrypt_queue *zq; int card; + u64 cnt; memset(reqcnt, 0, sizeof(int) * max_adapters); spin_lock(&zcrypt_list_lock); @@ -1232,8 +1233,9 @@ static void zcrypt_perdev_reqcnt(int reqcnt[], size_t max_adapters) || card >= max_adapters) continue; spin_lock(&zq->queue->lock); - reqcnt[card] = zq->queue->total_request_count; + cnt = zq->queue->total_request_count; spin_unlock(&zq->queue->lock); + reqcnt[card] = (cnt < UINT_MAX) ? (u32) cnt : UINT_MAX; } } local_bh_enable(); @@ -1411,9 +1413,9 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, return 0; } case ZCRYPT_PERDEV_REQCNT: { - int *reqcnt; + u32 *reqcnt; - reqcnt = kcalloc(AP_DEVICES, sizeof(int), GFP_KERNEL); + reqcnt = kcalloc(AP_DEVICES, sizeof(u32), GFP_KERNEL); if (!reqcnt) return -ENOMEM; zcrypt_perdev_reqcnt(reqcnt, AP_DEVICES); @@ -1470,7 +1472,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, } case Z90STAT_PERDEV_REQCNT: { /* the old ioctl supports only 64 adapters */ - int reqcnt[MAX_ZDEV_CARDIDS]; + u32 reqcnt[MAX_ZDEV_CARDIDS]; zcrypt_perdev_reqcnt(reqcnt, MAX_ZDEV_CARDIDS); if (copy_to_user((int __user *) arg, reqcnt, sizeof(reqcnt))) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 29facb913671..10edfd6fc930 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5142,7 +5142,7 @@ struct sk_buff *qeth_core_get_next_skb(struct qeth_card *card, } use_rx_sg = (card->options.cq == QETH_CQ_ENABLED) || - ((skb_len >= card->options.rx_sg_cb) && + (skb_len > card->options.rx_sg_cb && !atomic_read(&card->force_alloc_skb) && !IS_OSN(card)); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 47d37e75dda6..e26ad80ddfa3 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1815,15 +1815,14 @@ int qeth_l2_vnicc_set_state(struct qeth_card *card, u32 vnicc, bool state) QETH_CARD_TEXT(card, 2, "vniccsch"); - /* do not change anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and enable/disable are supported */ if (!(card->options.vnicc.sup_chars & vnicc) || !(card->options.vnicc.set_char_sup & vnicc)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* set enable/disable command and store wanted characteristic */ if (state) { cmd = IPA_VNICC_ENABLE; @@ -1869,14 +1868,13 @@ int qeth_l2_vnicc_get_state(struct qeth_card *card, u32 vnicc, bool *state) QETH_CARD_TEXT(card, 2, "vniccgch"); - /* do not get anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic is supported */ if (!(card->options.vnicc.sup_chars & vnicc)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* if card is ready, query current VNICC state */ if (qeth_card_hw_is_reachable(card)) rc = qeth_l2_vnicc_query_chars(card); @@ -1894,15 +1892,14 @@ int qeth_l2_vnicc_set_timeout(struct qeth_card *card, u32 timeout) QETH_CARD_TEXT(card, 2, "vniccsto"); - /* do not change anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and set_timeout are supported */ if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) || !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* do we need to do anything? */ if (card->options.vnicc.learning_timeout == timeout) return rc; @@ -1931,14 +1928,14 @@ int qeth_l2_vnicc_get_timeout(struct qeth_card *card, u32 *timeout) QETH_CARD_TEXT(card, 2, "vniccgto"); - /* do not get anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and get_timeout are supported */ if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) || !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING)) return -EOPNOTSUPP; + + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* if card is ready, get timeout. Otherwise, just return stored value */ *timeout = card->options.vnicc.learning_timeout; if (qeth_card_hw_is_reachable(card)) diff --git a/drivers/s390/scsi/zfcp_fsf.h b/drivers/s390/scsi/zfcp_fsf.h index 2b1e4da1944f..4bfb79f20588 100644 --- a/drivers/s390/scsi/zfcp_fsf.h +++ b/drivers/s390/scsi/zfcp_fsf.h @@ -410,7 +410,7 @@ struct fsf_qtcb_bottom_port { u8 cb_util; u8 a_util; u8 res2; - u16 temperature; + s16 temperature; u16 vcc; u16 tx_bias; u16 tx_power; diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c index 494b9fe9cc94..a711a0d15100 100644 --- a/drivers/s390/scsi/zfcp_sysfs.c +++ b/drivers/s390/scsi/zfcp_sysfs.c @@ -800,7 +800,7 @@ static ZFCP_DEV_ATTR(adapter_diag, b2b_credit, 0400, static ZFCP_DEV_ATTR(adapter_diag_sfp, _name, 0400, \ zfcp_sysfs_adapter_diag_sfp_##_name##_show, NULL) -ZFCP_DEFINE_DIAG_SFP_ATTR(temperature, temperature, 5, "%hu"); +ZFCP_DEFINE_DIAG_SFP_ATTR(temperature, temperature, 6, "%hd"); ZFCP_DEFINE_DIAG_SFP_ATTR(vcc, vcc, 5, "%hu"); ZFCP_DEFINE_DIAG_SFP_ATTR(tx_bias, tx_bias, 5, "%hu"); ZFCP_DEFINE_DIAG_SFP_ATTR(tx_power, tx_power, 5, "%hu"); diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index e0bd4cf17230..5b75a65103bd 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -161,6 +161,7 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data) { struct scsi_disk *sdkp = scsi_disk(disk); + sector_t capacity = logical_to_sectors(sdkp->device, sdkp->capacity); unsigned int nr, i; unsigned char *buf; size_t offset, buflen = 0; @@ -171,11 +172,15 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, /* Not a zoned device */ return -EOPNOTSUPP; + if (!capacity) + /* Device gone or invalid */ + return -ENODEV; + buf = sd_zbc_alloc_report_buffer(sdkp, nr_zones, &buflen); if (!buf) return -ENOMEM; - while (zone_idx < nr_zones && sector < get_capacity(disk)) { + while (zone_idx < nr_zones && sector < capacity) { ret = sd_zbc_do_report_zones(sdkp, buf, buflen, sectors_to_logical(sdkp->device, sector), true); if (ret) diff --git a/drivers/soc/tegra/fuse/fuse-tegra30.c b/drivers/soc/tegra/fuse/fuse-tegra30.c index b8daaf5b7291..efd158b4607c 100644 --- a/drivers/soc/tegra/fuse/fuse-tegra30.c +++ b/drivers/soc/tegra/fuse/fuse-tegra30.c @@ -36,7 +36,8 @@ defined(CONFIG_ARCH_TEGRA_124_SOC) || \ defined(CONFIG_ARCH_TEGRA_132_SOC) || \ defined(CONFIG_ARCH_TEGRA_210_SOC) || \ - defined(CONFIG_ARCH_TEGRA_186_SOC) + defined(CONFIG_ARCH_TEGRA_186_SOC) || \ + defined(CONFIG_ARCH_TEGRA_194_SOC) static u32 tegra30_fuse_read_early(struct tegra_fuse *fuse, unsigned int offset) { if (WARN_ON(!fuse->base)) diff --git a/drivers/thermal/broadcom/brcmstb_thermal.c b/drivers/thermal/broadcom/brcmstb_thermal.c index 5825ac581f56..680f1a070606 100644 --- a/drivers/thermal/broadcom/brcmstb_thermal.c +++ b/drivers/thermal/broadcom/brcmstb_thermal.c @@ -49,7 +49,7 @@ #define AVS_TMON_TP_TEST_ENABLE 0x20 /* Default coefficients */ -#define AVS_TMON_TEMP_SLOPE -487 +#define AVS_TMON_TEMP_SLOPE 487 #define AVS_TMON_TEMP_OFFSET 410040 /* HW related temperature constants */ @@ -108,23 +108,12 @@ struct brcmstb_thermal_priv { struct thermal_zone_device *thermal; }; -static void avs_tmon_get_coeffs(struct thermal_zone_device *tz, int *slope, - int *offset) -{ - *slope = thermal_zone_get_slope(tz); - *offset = thermal_zone_get_offset(tz); -} - /* Convert a HW code to a temperature reading (millidegree celsius) */ static inline int avs_tmon_code_to_temp(struct thermal_zone_device *tz, u32 code) { - const int val = code & AVS_TMON_TEMP_MASK; - int slope, offset; - - avs_tmon_get_coeffs(tz, &slope, &offset); - - return slope * val + offset; + return (AVS_TMON_TEMP_OFFSET - + (int)((code & AVS_TMON_TEMP_MAX) * AVS_TMON_TEMP_SLOPE)); } /* @@ -136,20 +125,18 @@ static inline int avs_tmon_code_to_temp(struct thermal_zone_device *tz, static inline u32 avs_tmon_temp_to_code(struct thermal_zone_device *tz, int temp, bool low) { - int slope, offset; - if (temp < AVS_TMON_TEMP_MIN) - return AVS_TMON_TEMP_MAX; /* Maximum code value */ - - avs_tmon_get_coeffs(tz, &slope, &offset); + return AVS_TMON_TEMP_MAX; /* Maximum code value */ - if (temp >= offset) + if (temp >= AVS_TMON_TEMP_OFFSET) return 0; /* Minimum code value */ if (low) - return (u32)(DIV_ROUND_UP(offset - temp, abs(slope))); + return (u32)(DIV_ROUND_UP(AVS_TMON_TEMP_OFFSET - temp, + AVS_TMON_TEMP_SLOPE)); else - return (u32)((offset - temp) / abs(slope)); + return (u32)((AVS_TMON_TEMP_OFFSET - temp) / + AVS_TMON_TEMP_SLOPE); } static int brcmstb_get_temp(void *data, int *temp) diff --git a/drivers/thermal/db8500_thermal.c b/drivers/thermal/db8500_thermal.c index 372dbbaaafb8..21d4d6e6409a 100644 --- a/drivers/thermal/db8500_thermal.c +++ b/drivers/thermal/db8500_thermal.c @@ -152,8 +152,8 @@ static irqreturn_t prcmu_high_irq_handler(int irq, void *irq_data) db8500_thermal_update_config(th, idx, THERMAL_TREND_RAISING, next_low, next_high); - dev_info(&th->tz->device, - "PRCMU set max %ld, min %ld\n", next_high, next_low); + dev_dbg(&th->tz->device, + "PRCMU set max %ld, min %ld\n", next_high, next_low); } else if (idx == num_points - 1) /* So we roof out 1 degree over the max point */ th->interpolated_temp = db8500_thermal_points[idx] + 1; diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index e158159671fa..18e205eeb9af 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1414,10 +1414,6 @@ static int vhost_net_release(struct inode *inode, struct file *f) static struct socket *get_raw_socket(int fd) { - struct { - struct sockaddr_ll sa; - char buf[MAX_ADDR_LEN]; - } uaddr; int r; struct socket *sock = sockfd_lookup(fd, &r); @@ -1430,11 +1426,7 @@ static struct socket *get_raw_socket(int fd) goto err; } - r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa, 0); - if (r < 0) - goto err; - - if (uaddr.sa.sll_family != AF_PACKET) { + if (sock->sk->sk_family != AF_PACKET) { r = -EPFNOSUPPORT; goto err; } diff --git a/drivers/watchdog/wdat_wdt.c b/drivers/watchdog/wdat_wdt.c index b069349b52f5..e1b1fcfc02af 100644 --- a/drivers/watchdog/wdat_wdt.c +++ b/drivers/watchdog/wdat_wdt.c @@ -389,7 +389,7 @@ static int wdat_wdt_probe(struct platform_device *pdev) memset(&r, 0, sizeof(r)); r.start = gas->address; - r.end = r.start + gas->access_width - 1; + r.end = r.start + ACPI_ACCESS_BYTE_WIDTH(gas->access_width) - 1; if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { r.flags = IORESOURCE_MEM; } else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 11929d2bb594..cd09e63d682b 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1418,6 +1418,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) struct ceph_cap_flush *prealloc_cf; ssize_t count, written = 0; int err, want, got; + bool direct_lock = false; loff_t pos; loff_t limit = max(i_size_read(inode), fsc->max_file_size); @@ -1428,8 +1429,11 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) if (!prealloc_cf) return -ENOMEM; + if ((iocb->ki_flags & (IOCB_DIRECT | IOCB_APPEND)) == IOCB_DIRECT) + direct_lock = true; + retry_snap: - if (iocb->ki_flags & IOCB_DIRECT) + if (direct_lock) ceph_start_io_direct(inode); else ceph_start_io_write(inode); @@ -1519,14 +1523,15 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) /* we might need to revert back to that point */ data = *from; - if (iocb->ki_flags & IOCB_DIRECT) { + if (iocb->ki_flags & IOCB_DIRECT) written = ceph_direct_read_write(iocb, &data, snapc, &prealloc_cf); - ceph_end_io_direct(inode); - } else { + else written = ceph_sync_write(iocb, &data, pos, snapc); + if (direct_lock) + ceph_end_io_direct(inode); + else ceph_end_io_write(inode); - } if (written > 0) iov_iter_advance(from, written); ceph_put_snap_context(snapc); @@ -1577,7 +1582,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out_unlocked; out: - if (iocb->ki_flags & IOCB_DIRECT) + if (direct_lock) ceph_end_io_direct(inode); else ceph_end_io_write(inode); diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index fb41e51dd574..25704beb9d4c 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -601,7 +601,7 @@ static void access_flags_to_mode(__le32 ace_flags, int type, umode_t *pmode, ((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS)) *pmode |= (S_IXUGO & (*pbits_to_set)); - cifs_dbg(NOISY, "access flags 0x%x mode now 0x%x\n", flags, *pmode); + cifs_dbg(NOISY, "access flags 0x%x mode now %04o\n", flags, *pmode); return; } @@ -630,7 +630,7 @@ static void mode_to_access_flags(umode_t mode, umode_t bits_to_use, if (mode & S_IXUGO) *pace_flags |= SET_FILE_EXEC_RIGHTS; - cifs_dbg(NOISY, "mode: 0x%x, access flags now 0x%x\n", + cifs_dbg(NOISY, "mode: %04o, access flags now 0x%x\n", mode, *pace_flags); return; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 0aa3623ae0e1..641825cfa767 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -4151,7 +4151,7 @@ int cifs_setup_cifs_sb(struct smb_vol *pvolume_info, cifs_sb->mnt_gid = pvolume_info->linux_gid; cifs_sb->mnt_file_mode = pvolume_info->file_mode; cifs_sb->mnt_dir_mode = pvolume_info->dir_mode; - cifs_dbg(FYI, "file mode: 0x%hx dir mode: 0x%hx\n", + cifs_dbg(FYI, "file mode: %04ho dir mode: %04ho\n", cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode); cifs_sb->actimeo = pvolume_info->actimeo; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index ca76a9287456..b3f3675e1878 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1649,7 +1649,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode) struct TCP_Server_Info *server; char *full_path; - cifs_dbg(FYI, "In cifs_mkdir, mode = 0x%hx inode = 0x%p\n", + cifs_dbg(FYI, "In cifs_mkdir, mode = %04ho inode = 0x%p\n", mode, inode); cifs_sb = CIFS_SB(inode->i_sb); diff --git a/fs/dax.c b/fs/dax.c index 1f1f0201cad1..0b0d8819cb1b 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1207,6 +1207,9 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, lockdep_assert_held(&inode->i_rwsem); } + if (iocb->ki_flags & IOCB_NOWAIT) + flags |= IOMAP_NOWAIT; + while (iov_iter_count(iter)) { ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops, iter, dax_iomap_actor); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 12806be10a18..71e2b80ff4aa 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2346,7 +2346,7 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct flex_groups **old_groups, **new_groups; - int size, i; + int size, i, j; if (!sbi->s_log_groups_per_flex) return 0; @@ -2367,8 +2367,8 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) sizeof(struct flex_groups)), GFP_KERNEL); if (!new_groups[i]) { - for (i--; i >= sbi->s_flex_groups_allocated; i--) - kvfree(new_groups[i]); + for (j = sbi->s_flex_groups_allocated; j < i; j++) + kvfree(new_groups[j]); kvfree(new_groups); ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", size); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index fc40a72f7827..930706e171fd 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -3132,7 +3132,8 @@ int f2fs_migrate_page(struct address_space *mapping, #ifdef CONFIG_SWAP /* Copied from generic_swapfile_activate() to check any holes */ -static int check_swap_activate(struct file *swap_file, unsigned int max) +static int check_swap_activate(struct swap_info_struct *sis, + struct file *swap_file, sector_t *span) { struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; @@ -3143,6 +3144,8 @@ static int check_swap_activate(struct file *swap_file, unsigned int max) sector_t last_block; sector_t lowest_block = -1; sector_t highest_block = 0; + int nr_extents = 0; + int ret; blkbits = inode->i_blkbits; blocks_per_page = PAGE_SIZE >> blkbits; @@ -3154,7 +3157,8 @@ static int check_swap_activate(struct file *swap_file, unsigned int max) probe_block = 0; page_no = 0; last_block = i_size_read(inode) >> blkbits; - while ((probe_block + blocks_per_page) <= last_block && page_no < max) { + while ((probe_block + blocks_per_page) <= last_block && + page_no < sis->max) { unsigned block_in_page; sector_t first_block; @@ -3194,13 +3198,27 @@ static int check_swap_activate(struct file *swap_file, unsigned int max) highest_block = first_block; } + /* + * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks + */ + ret = add_swap_extent(sis, page_no, 1, first_block); + if (ret < 0) + goto out; + nr_extents += ret; page_no++; probe_block += blocks_per_page; reprobe: continue; } - return 0; - + ret = nr_extents; + *span = 1 + highest_block - lowest_block; + if (page_no == 0) + page_no = 1; /* force Empty message */ + sis->max = page_no; + sis->pages = page_no - 1; + sis->highest_bit = page_no - 1; +out: + return ret; bad_bmap: pr_err("swapon: swapfile has holes\n"); return -EINVAL; @@ -3222,14 +3240,14 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, if (ret) return ret; - ret = check_swap_activate(file, sis->max); - if (ret) + ret = check_swap_activate(sis, file, span); + if (ret < 0) return ret; set_inode_flag(inode, FI_PIN_FILE); f2fs_precache_extents(inode); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); - return 0; + return ret; } static void f2fs_swap_deactivate(struct file *file) diff --git a/fs/io-wq.c b/fs/io-wq.c index 0dc4bb6de656..25ffb6685bae 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -666,11 +666,16 @@ static int io_wq_manager(void *data) /* create fixed workers */ refcount_set(&wq->refs, workers_to_create); for_each_node(node) { + if (!node_online(node)) + continue; if (!create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND)) goto err; workers_to_create--; } + while (workers_to_create--) + refcount_dec(&wq->refs); + complete(&wq->done); while (!kthread_should_stop()) { @@ -678,6 +683,9 @@ static int io_wq_manager(void *data) struct io_wqe *wqe = wq->wqes[node]; bool fork_worker[2] = { false, false }; + if (!node_online(node)) + continue; + spin_lock_irq(&wqe->lock); if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND)) fork_worker[IO_WQ_ACCT_BOUND] = true; @@ -793,7 +801,9 @@ static bool io_wq_for_each_worker(struct io_wqe *wqe, list_for_each_entry_rcu(worker, &wqe->all_list, all_list) { if (io_worker_get(worker)) { - ret = func(worker, data); + /* no task if node is/was offline */ + if (worker->task) + ret = func(worker, data); io_worker_release(worker); if (ret) break; @@ -1006,6 +1016,8 @@ void io_wq_flush(struct io_wq *wq) for_each_node(node) { struct io_wqe *wqe = wq->wqes[node]; + if (!node_online(node)) + continue; init_completion(&data.done); INIT_IO_WORK(&data.work, io_wq_flush_func); data.work.flags |= IO_WQ_WORK_INTERNAL; @@ -1038,12 +1050,15 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) for_each_node(node) { struct io_wqe *wqe; + int alloc_node = node; - wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, node); + if (!node_online(alloc_node)) + alloc_node = NUMA_NO_NODE; + wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node); if (!wqe) goto err; wq->wqes[node] = wqe; - wqe->node = node; + wqe->node = alloc_node; wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded; atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0); if (wq->user) { @@ -1051,7 +1066,6 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) task_rlimit(current, RLIMIT_NPROC); } atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0); - wqe->node = node; wqe->wq = wq; spin_lock_init(&wqe->lock); INIT_WQ_LIST(&wqe->work_list); diff --git a/fs/io_uring.c b/fs/io_uring.c index 678c62782ba3..60a483208998 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2166,6 +2166,11 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) sr->msg_flags = READ_ONCE(sqe->msg_flags); sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + if (!io) return 0; @@ -2258,6 +2263,11 @@ static int io_recvmsg_prep(struct io_kiocb *req, sr->msg_flags = READ_ONCE(sqe->msg_flags); sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + sr->msg_flags |= MSG_CMSG_COMPAT; +#endif + if (!io) return 0; @@ -4970,7 +4980,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) if (READ_ONCE(ctx->rings->sq.tail) - ctx->cached_sq_head != ctx->rings->sq_ring_entries) mask |= EPOLLOUT | EPOLLWRNORM; - if (READ_ONCE(ctx->rings->cq.head) != ctx->cached_cq_tail) + if (io_cqring_events(ctx, false)) mask |= EPOLLIN | EPOLLRDNORM; return mask; diff --git a/fs/namei.c b/fs/namei.c index 6cc88b6d68c8..70eb4bfeaebc 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1367,7 +1367,7 @@ static int follow_dotdot_rcu(struct nameidata *nd) nd->path.dentry = parent; nd->seq = seq; if (unlikely(!path_connected(&nd->path))) - return -ENOENT; + return -ECHILD; break; } else { struct mount *mnt = real_mount(nd->path.mnt); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 620de905cba9..3f892035c141 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -86,7 +86,6 @@ nfs4_file_open(struct inode *inode, struct file *filp) if (inode != d_inode(dentry)) goto out_drop; - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); nfs_file_set_open_context(filp, ctx); nfs_fscache_open_file(inode, filp); err = 0; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6ddb4f517d37..13c2de527718 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2962,10 +2962,13 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, struct dentry *dentry; struct nfs4_state *state; fmode_t acc_mode = _nfs4_ctx_to_accessmode(ctx); + struct inode *dir = d_inode(opendata->dir); + unsigned long dir_verifier; unsigned int seq; int ret; seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); + dir_verifier = nfs_save_change_attribute(dir); ret = _nfs4_proc_open(opendata, ctx); if (ret != 0) @@ -2993,8 +2996,19 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, dput(ctx->dentry); ctx->dentry = dentry = alias; } - nfs_set_verifier(dentry, - nfs_save_change_attribute(d_inode(opendata->dir))); + } + + switch(opendata->o_arg.claim) { + default: + break; + case NFS4_OPEN_CLAIM_NULL: + case NFS4_OPEN_CLAIM_DELEGATE_CUR: + case NFS4_OPEN_CLAIM_DELEGATE_PREV: + if (!opendata->rpc_done) + break; + if (opendata->o_res.delegation_type != 0) + dir_verifier = nfs_save_change_attribute(dir); + nfs_set_verifier(dentry, dir_verifier); } /* Parse layoutget results before we check for access */ diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index 54d6db61106f..edf43ddd7dce 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -129,7 +129,7 @@ static void __orphan_drop(struct ubifs_info *c, struct ubifs_orphan *o) static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph) { if (orph->del) { - dbg_gen("deleted twice ino %lu", orph->inum); + dbg_gen("deleted twice ino %lu", (unsigned long)orph->inum); return; } @@ -137,7 +137,7 @@ static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph) orph->del = 1; orph->dnext = c->orph_dnext; c->orph_dnext = orph; - dbg_gen("delete later ino %lu", orph->inum); + dbg_gen("delete later ino %lu", (unsigned long)orph->inum); return; } diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h index 94badfa1743e..91c2cb14276e 100644 --- a/fs/xfs/libxfs/xfs_attr.h +++ b/fs/xfs/libxfs/xfs_attr.h @@ -26,7 +26,7 @@ struct xfs_attr_list_context; *========================================================================*/ -#define ATTR_DONTFOLLOW 0x0001 /* -- unused, from IRIX -- */ +#define ATTR_DONTFOLLOW 0x0001 /* -- ignored, from IRIX -- */ #define ATTR_ROOT 0x0002 /* use attrs in root (trusted) namespace */ #define ATTR_TRUST 0x0004 /* -- unused, from IRIX -- */ #define ATTR_SECURE 0x0008 /* use attrs in security namespace */ @@ -37,7 +37,10 @@ struct xfs_attr_list_context; #define ATTR_KERNOVAL 0x2000 /* [kernel] get attr size only, not value */ #define ATTR_INCOMPLETE 0x4000 /* [kernel] return INCOMPLETE attr keys */ -#define ATTR_ALLOC 0x8000 /* allocate xattr buffer on demand */ +#define ATTR_ALLOC 0x8000 /* [kernel] allocate xattr buffer on demand */ + +#define ATTR_KERNEL_FLAGS \ + (ATTR_KERNOTIME | ATTR_KERNOVAL | ATTR_INCOMPLETE | ATTR_ALLOC) #define XFS_ATTR_FLAGS \ { ATTR_DONTFOLLOW, "DONTFOLLOW" }, \ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 7b35d62ede9f..edfbdb8f85e2 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -462,6 +462,8 @@ xfs_attrmulti_by_handle( error = 0; for (i = 0; i < am_hreq.opcount; i++) { + ops[i].am_flags &= ~ATTR_KERNEL_FLAGS; + ops[i].am_error = strncpy_from_user((char *)attr_name, ops[i].am_attrname, MAXNAMELEN); if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN) diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index c4c4f09113d3..bd9d9ebf85d8 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -450,6 +450,8 @@ xfs_compat_attrmulti_by_handle( error = 0; for (i = 0; i < am_hreq.opcount; i++) { + ops[i].am_flags &= ~ATTR_KERNEL_FLAGS; + ops[i].am_error = strncpy_from_user((char *)attr_name, compat_ptr(ops[i].am_attrname), MAXNAMELEN); diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 2f3f28c7cea3..9373662cdb44 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -532,11 +532,12 @@ typedef u64 acpi_integer; strnlen (a, ACPI_NAMESEG_SIZE) == ACPI_NAMESEG_SIZE) /* - * Algorithm to obtain access bit width. + * Algorithm to obtain access bit or byte width. * Can be used with access_width of struct acpi_generic_address and access_size of * struct acpi_resource_generic_register. */ #define ACPI_ACCESS_BIT_WIDTH(size) (1 << ((size) + 2)) +#define ACPI_ACCESS_BYTE_WIDTH(size) (1 << ((size) - 1)) /******************************************************************************* * diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h index ce4103208619..cec543d9e87b 100644 --- a/include/asm-generic/vdso/vsyscall.h +++ b/include/asm-generic/vdso/vsyscall.h @@ -12,9 +12,9 @@ static __always_inline struct vdso_data *__arch_get_k_vdso_data(void) #endif /* __arch_get_k_vdso_data */ #ifndef __arch_update_vdso_data -static __always_inline int __arch_update_vdso_data(void) +static __always_inline bool __arch_update_vdso_data(void) { - return 0; + return true; } #endif /* __arch_update_vdso_data */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4c636c42ad68..1cb5afed5515 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -524,7 +524,7 @@ struct request_queue { unsigned int sg_reserved_size; int node; #ifdef CONFIG_BLK_DEV_IO_TRACE - struct blk_trace *blk_trace; + struct blk_trace __rcu *blk_trace; struct mutex blk_trace_mutex; #endif /* diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7bb2d8de9f30..3b6ff5902edc 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -51,9 +51,13 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f **/ #define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ do { \ - struct blk_trace *bt = (q)->blk_trace; \ + struct blk_trace *bt; \ + \ + rcu_read_lock(); \ + bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__) @@ -61,10 +65,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f static inline bool blk_trace_note_message_enabled(struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; - if (likely(!bt)) - return false; - return bt->act_mask & BLK_TC_NOTIFY; + struct blk_trace *bt; + bool ret; + + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + ret = bt && (bt->act_mask & BLK_TC_NOTIFY); + rcu_read_unlock(); + return ret; } extern void blk_add_driver_data(struct request_queue *q, struct request *rq, diff --git a/include/linux/hid.h b/include/linux/hid.h index cd41f209043f..875f71132b14 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -492,7 +492,7 @@ struct hid_report_enum { }; #define HID_MIN_BUFFER_SIZE 64 /* make sure there is at least a packet size of space */ -#define HID_MAX_BUFFER_SIZE 4096 /* 4kb */ +#define HID_MAX_BUFFER_SIZE 8192 /* 8kb */ #define HID_CONTROL_FIFO_SIZE 256 /* to init devices with >100 reports */ #define HID_OUTPUT_FIFO_SIZE 64 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cac56fb59af8..1dabd86b232a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -72,6 +72,8 @@ void netdev_set_default_ethtool_ops(struct net_device *dev, #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ +#define MAX_NEST_DEV 8 + /* * Transmit return codes: transmit return codes originate from three different * namespaces: @@ -4323,11 +4325,8 @@ void *netdev_lower_get_next(struct net_device *dev, ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) -struct net_device *netdev_all_lower_get_next(struct net_device *dev, +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); -struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, - struct list_head **iter); - int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, void *data), diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 908d38dbcb91..5448c8b443db 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -121,6 +121,7 @@ struct ip_set_ext { u32 timeout; u8 packets_op; u8 bytes_op; + bool target; }; struct ip_set; @@ -187,6 +188,14 @@ struct ip_set_type_variant { /* Return true if "b" set is the same as "a" * according to the create set parameters */ bool (*same_set)(const struct ip_set *a, const struct ip_set *b); + /* Region-locking is used */ + bool region_lock; +}; + +struct ip_set_region { + spinlock_t lock; /* Region lock */ + size_t ext_size; /* Size of the dynamic extensions */ + u32 elements; /* Number of elements vs timeout */ }; /* The core set type structure */ @@ -501,7 +510,7 @@ ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, } #define IP_SET_INIT_KEXT(skb, opt, set) \ - { .bytes = (skb)->len, .packets = 1, \ + { .bytes = (skb)->len, .packets = 1, .target = true,\ .timeout = ip_set_adt_opt_timeout(opt, set) } #define IP_SET_INIT_UEXT(set) \ diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h index 1abe91ff6e4a..6d67e9a5af6b 100644 --- a/include/linux/sched/nohz.h +++ b/include/linux/sched/nohz.h @@ -15,9 +15,11 @@ static inline void nohz_balance_enter_idle(int cpu) { } #ifdef CONFIG_NO_HZ_COMMON void calc_load_nohz_start(void); +void calc_load_nohz_remote(struct rq *rq); void calc_load_nohz_stop(void); #else static inline void calc_load_nohz_start(void) { } +static inline void calc_load_nohz_remote(struct rq *rq) { } static inline void calc_load_nohz_stop(void) { } #endif /* CONFIG_NO_HZ_COMMON */ diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index d93017a7ce5c..e03827f702f3 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -5,6 +5,7 @@ #include <linux/types.h> #include <linux/in6.h> #include <linux/siphash.h> +#include <linux/string.h> #include <uapi/linux/if_ether.h> struct sk_buff; @@ -349,4 +350,12 @@ struct bpf_flow_dissector { void *data_end; }; +static inline void +flow_dissector_init_keys(struct flow_dissector_key_control *key_control, + struct flow_dissector_key_basic *key_basic) +{ + memset(key_control, 0, sizeof(*key_control)); + memset(key_basic, 0, sizeof(*key_basic)); +} + #endif diff --git a/include/uapi/linux/usb/charger.h b/include/uapi/linux/usb/charger.h index 5f72af35b3ed..ad22079125bf 100644 --- a/include/uapi/linux/usb/charger.h +++ b/include/uapi/linux/usb/charger.h @@ -14,18 +14,18 @@ * ACA (Accessory Charger Adapters) */ enum usb_charger_type { - UNKNOWN_TYPE, - SDP_TYPE, - DCP_TYPE, - CDP_TYPE, - ACA_TYPE, + UNKNOWN_TYPE = 0, + SDP_TYPE = 1, + DCP_TYPE = 2, + CDP_TYPE = 3, + ACA_TYPE = 4, }; /* USB charger state */ enum usb_charger_state { - USB_CHARGER_DEFAULT, - USB_CHARGER_PRESENT, - USB_CHARGER_ABSENT, + USB_CHARGER_DEFAULT = 0, + USB_CHARGER_PRESENT = 1, + USB_CHARGER_ABSENT = 2, }; #endif /* _UAPI__LINUX_USB_CHARGER_H */ diff --git a/kernel/audit.c b/kernel/audit.c index 8e09f0f55b4b..f971cd636426 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1100,13 +1100,11 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature audit_log_end(ab); } -static int audit_set_feature(struct sk_buff *skb) +static int audit_set_feature(struct audit_features *uaf) { - struct audit_features *uaf; int i; BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names)); - uaf = nlmsg_data(nlmsg_hdr(skb)); /* if there is ever a version 2 we should handle that here */ @@ -1174,6 +1172,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { u32 seq; void *data; + int data_len; int err; struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; @@ -1187,6 +1186,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) seq = nlh->nlmsg_seq; data = nlmsg_data(nlh); + data_len = nlmsg_len(nlh); switch (msg_type) { case AUDIT_GET: { @@ -1210,7 +1210,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) struct audit_status s; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); if (s.mask & AUDIT_STATUS_ENABLED) { err = audit_set_enabled(s.enabled); if (err < 0) @@ -1314,7 +1314,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return err; break; case AUDIT_SET_FEATURE: - err = audit_set_feature(skb); + if (data_len < sizeof(struct audit_features)) + return -EINVAL; + err = audit_set_feature(data); if (err) return err; break; @@ -1326,6 +1328,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ + char *str = data; + err = 0; if (msg_type == AUDIT_USER_TTY) { err = tty_audit_push(); @@ -1333,26 +1337,24 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) break; } audit_log_user_recv_msg(&ab, msg_type); - if (msg_type != AUDIT_USER_TTY) + if (msg_type != AUDIT_USER_TTY) { + /* ensure NULL termination */ + str[data_len - 1] = '\0'; audit_log_format(ab, " msg='%.*s'", AUDIT_MESSAGE_TEXT_MAX, - (char *)data); - else { - int size; - + str); + } else { audit_log_format(ab, " data="); - size = nlmsg_len(nlh); - if (size > 0 && - ((unsigned char *)data)[size - 1] == '\0') - size--; - audit_log_n_untrustedstring(ab, data, size); + if (data_len > 0 && str[data_len - 1] == '\0') + data_len--; + audit_log_n_untrustedstring(ab, str, data_len); } audit_log_end(ab); } break; case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: - if (nlmsg_len(nlh) < sizeof(struct audit_rule_data)) + if (data_len < sizeof(struct audit_rule_data)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { audit_log_common_recv_msg(audit_context(), &ab, @@ -1364,7 +1366,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) audit_log_end(ab); return -EPERM; } - err = audit_rule_change(msg_type, seq, data, nlmsg_len(nlh)); + err = audit_rule_change(msg_type, seq, data, data_len); break; case AUDIT_LIST_RULES: err = audit_list_rules_send(skb, seq); @@ -1379,7 +1381,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) case AUDIT_MAKE_EQUIV: { void *bufp = data; u32 sizes[2]; - size_t msglen = nlmsg_len(nlh); + size_t msglen = data_len; char *old, *new; err = -EINVAL; @@ -1455,7 +1457,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); /* check if new data is valid */ if ((s.enabled != 0 && s.enabled != 1) || (s.log_passwd != 0 && s.log_passwd != 1)) diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index b0126e9c0743..026e34da4ace 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -456,6 +456,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; + u32 f_val; err = -EINVAL; @@ -464,12 +465,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, goto exit_free; f->type = data->fields[i]; - f->val = data->values[i]; + f_val = data->values[i]; /* Support legacy tests for a valid loginuid */ - if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) { + if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; - f->val = 0; + f_val = 0; entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } @@ -485,7 +486,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_OBJ_UID: - f->uid = make_kuid(current_user_ns(), f->val); + f->uid = make_kuid(current_user_ns(), f_val); if (!uid_valid(f->uid)) goto exit_free; break; @@ -494,11 +495,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: - f->gid = make_kgid(current_user_ns(), f->val); + f->gid = make_kgid(current_user_ns(), f_val); if (!gid_valid(f->gid)) goto exit_free; break; case AUDIT_ARCH: + f->val = f_val; entry->rule.arch_f = f; break; case AUDIT_SUBJ_USER: @@ -511,11 +513,13 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } + entry->rule.buflen += f_val; + f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, (void **)&f->lsm_rule); /* Keep currently invalid fields around in case they @@ -524,68 +528,71 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, pr_warn("audit rule for LSM \'%s\' is invalid\n", str); err = 0; - } - if (err) { - kfree(str); + } else if (err) goto exit_free; - } else - f->lsm_str = str; break; case AUDIT_WATCH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - - err = audit_to_watch(&entry->rule, str, f->val, f->op); + } + err = audit_to_watch(&entry->rule, str, f_val, f->op); if (err) { kfree(str); goto exit_free; } + entry->rule.buflen += f_val; break; case AUDIT_DIR: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } err = audit_make_tree(&entry->rule, str, f->op); kfree(str); if (err) goto exit_free; + entry->rule.buflen += f_val; break; case AUDIT_INODE: + f->val = f_val; err = audit_to_inode(&entry->rule, f); if (err) goto exit_free; break; case AUDIT_FILTERKEY: - if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN) + if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; + } + entry->rule.buflen += f_val; entry->rule.filterkey = str; break; case AUDIT_EXE: - if (entry->rule.exe || f->val > PATH_MAX) + if (entry->rule.exe || f_val > PATH_MAX) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); + str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } - entry->rule.buflen += f->val; - - audit_mark = audit_alloc_mark(&entry->rule, str, f->val); + audit_mark = audit_alloc_mark(&entry->rule, str, f_val); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); goto exit_free; } + entry->rule.buflen += f_val; entry->rule.exe = audit_mark; break; + default: + f->val = f_val; + break; } } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index fd81882f0521..2625c241ac00 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -510,6 +510,8 @@ static void do_unoptimize_kprobes(void) arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); /* Loop free_list for disarming */ list_for_each_entry_safe(op, tmp, &freeing_list, list) { + /* Switching from detour code to origin */ + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; /* Disarm probes if marked disabled */ if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); @@ -665,6 +667,7 @@ static void force_unoptimize_kprobe(struct optimized_kprobe *op) { lockdep_assert_cpus_held(); arch_unoptimize_kprobe(op); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); } @@ -681,7 +684,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) if (!kprobe_optimized(p)) return; - op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (!list_empty(&op->list)) { if (optprobe_queued_unopt(op)) { /* Queued in unoptimizing queue */ diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index dadb7b7fba37..9bb6d2497b04 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -286,9 +286,9 @@ static int lockdep_stats_show(struct seq_file *m, void *v) seq_printf(m, " stack-trace entries: %11lu [max: %lu]\n", nr_stack_trace_entries, MAX_STACK_TRACE_ENTRIES); #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) - seq_printf(m, " number of stack traces: %llu\n", + seq_printf(m, " number of stack traces: %11llu\n", lockdep_stack_trace_count()); - seq_printf(m, " number of stack hash chains: %llu\n", + seq_printf(m, " number of stack hash chains: %11llu\n", lockdep_stack_hash_count()); #endif seq_printf(m, " combined max dependencies: %11u\n", diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index f504ac831779..df90d4d7ad2e 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -540,14 +540,13 @@ static void rcu_exp_wait_wake(unsigned long s) struct rcu_node *rnp; synchronize_sched_expedited_wait(); - rcu_exp_gp_seq_end(); - trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end")); - /* - * Switch over to wakeup mode, allowing the next GP, but -only- the - * next GP, to proceed. - */ + // Switch over to wakeup mode, allowing the next GP to proceed. + // End the previous grace period only after acquiring the mutex + // to ensure that only one GP runs concurrently with wakeups. mutex_lock(&rcu_state.exp_wake_mutex); + rcu_exp_gp_seq_end(); + trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end")); rcu_for_each_node_breadth_first(rnp) { if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b2564d62a0f7..9e7768dbd92d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3669,28 +3669,32 @@ static void sched_tick_remote(struct work_struct *work) * statistics and checks timeslices in a time-independent way, regardless * of when exactly it is running. */ - if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu)) + if (!tick_nohz_tick_stopped_cpu(cpu)) goto out_requeue; rq_lock_irq(rq, &rf); curr = rq->curr; - if (is_idle_task(curr) || cpu_is_offline(cpu)) + if (cpu_is_offline(cpu)) goto out_unlock; + curr = rq->curr; update_rq_clock(rq); - delta = rq_clock_task(rq) - curr->se.exec_start; - /* - * Make sure the next tick runs within a reasonable - * amount of time. - */ - WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); + if (!is_idle_task(curr)) { + /* + * Make sure the next tick runs within a reasonable + * amount of time. + */ + delta = rq_clock_task(rq) - curr->se.exec_start; + WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); + } curr->sched_class->task_tick(rq, curr, 0); + calc_load_nohz_remote(rq); out_unlock: rq_unlock_irq(rq, &rf); - out_requeue: + /* * Run the remote tick once per second (1Hz). This arbitrary * frequency is large enough to avoid overload but short enough @@ -7064,8 +7068,15 @@ void sched_move_task(struct task_struct *tsk) if (queued) enqueue_task(rq, tsk, queue_flags); - if (running) + if (running) { set_next_task(rq, tsk); + /* + * After changing group, the running task may have joined a + * throttled one but it's still the running task. Trigger a + * resched to make sure that task can still run. + */ + resched_curr(rq); + } task_rq_unlock(rq, tsk, &rf); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ba749f579714..b0ee5eedeccd 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5828,6 +5828,7 @@ static inline int select_idle_smt(struct task_struct *p, int target) */ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target) { + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask); struct sched_domain *this_sd; u64 avg_cost, avg_idle; u64 time, cost; @@ -5859,11 +5860,11 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t time = cpu_clock(this); - for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { + cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); + + for_each_cpu_wrap(cpu, cpus, target) { if (!--nr) return si_cpu; - if (!cpumask_test_cpu(cpu, p->cpus_ptr)) - continue; if (available_idle_cpu(cpu)) break; if (si_cpu == -1 && sched_idle_cpu(cpu)) diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 28a516575c18..de22da666ac7 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -231,16 +231,11 @@ static inline int calc_load_read_idx(void) return calc_load_idx & 1; } -void calc_load_nohz_start(void) +static void calc_load_nohz_fold(struct rq *rq) { - struct rq *this_rq = this_rq(); long delta; - /* - * We're going into NO_HZ mode, if there's any pending delta, fold it - * into the pending NO_HZ delta. - */ - delta = calc_load_fold_active(this_rq, 0); + delta = calc_load_fold_active(rq, 0); if (delta) { int idx = calc_load_write_idx(); @@ -248,6 +243,24 @@ void calc_load_nohz_start(void) } } +void calc_load_nohz_start(void) +{ + /* + * We're going into NO_HZ mode, if there's any pending delta, fold it + * into the pending NO_HZ delta. + */ + calc_load_nohz_fold(this_rq()); +} + +/* + * Keep track of the load for NOHZ_FULL, must be called between + * calc_load_nohz_{start,stop}(). + */ +void calc_load_nohz_remote(struct rq *rq) +{ + calc_load_nohz_fold(rq); +} + void calc_load_nohz_stop(void) { struct rq *this_rq = this_rq(); @@ -268,7 +281,7 @@ void calc_load_nohz_stop(void) this_rq->calc_load_update += LOAD_FREQ; } -static long calc_load_nohz_fold(void) +static long calc_load_nohz_read(void) { int idx = calc_load_read_idx(); long delta = 0; @@ -323,7 +336,7 @@ static void calc_global_nohz(void) } #else /* !CONFIG_NO_HZ_COMMON */ -static inline long calc_load_nohz_fold(void) { return 0; } +static inline long calc_load_nohz_read(void) { return 0; } static inline void calc_global_nohz(void) { } #endif /* CONFIG_NO_HZ_COMMON */ @@ -346,7 +359,7 @@ void calc_global_load(unsigned long ticks) /* * Fold the 'old' NO_HZ-delta to include all NO_HZ CPUs. */ - delta = calc_load_nohz_fold(); + delta = calc_load_nohz_read(); if (delta) atomic_long_add(delta, &calc_load_tasks); diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index 5ee0f7709410..9577c89179cd 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -28,11 +28,6 @@ static inline void update_vdso_data(struct vdso_data *vdata, vdata[CS_RAW].mult = tk->tkr_raw.mult; vdata[CS_RAW].shift = tk->tkr_raw.shift; - /* CLOCK_REALTIME */ - vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME]; - vdso_ts->sec = tk->xtime_sec; - vdso_ts->nsec = tk->tkr_mono.xtime_nsec; - /* CLOCK_MONOTONIC */ vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC]; vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; @@ -70,12 +65,6 @@ static inline void update_vdso_data(struct vdso_data *vdata, vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI]; vdso_ts->sec = tk->xtime_sec + (s64)tk->tai_offset; vdso_ts->nsec = tk->tkr_mono.xtime_nsec; - - /* - * Read without the seqlock held by clock_getres(). - * Note: No need to have a second copy. - */ - WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution); } void update_vsyscall(struct timekeeper *tk) @@ -84,20 +73,17 @@ void update_vsyscall(struct timekeeper *tk) struct vdso_timestamp *vdso_ts; u64 nsec; - if (__arch_update_vdso_data()) { - /* - * Some architectures might want to skip the update of the - * data page. - */ - return; - } - /* copy vsyscall data */ vdso_write_begin(vdata); vdata[CS_HRES_COARSE].clock_mode = __arch_get_clock_mode(tk); vdata[CS_RAW].clock_mode = __arch_get_clock_mode(tk); + /* CLOCK_REALTIME also required for time() */ + vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME]; + vdso_ts->sec = tk->xtime_sec; + vdso_ts->nsec = tk->tkr_mono.xtime_nsec; + /* CLOCK_REALTIME_COARSE */ vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE]; vdso_ts->sec = tk->xtime_sec; @@ -110,7 +96,18 @@ void update_vsyscall(struct timekeeper *tk) nsec = nsec + tk->wall_to_monotonic.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec); - update_vdso_data(vdata, tk); + /* + * Read without the seqlock held by clock_getres(). + * Note: No need to have a second copy. + */ + WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution); + + /* + * Architectures can opt out of updating the high resolution part + * of the VDSO. + */ + if (__arch_update_vdso_data()) + update_vdso_data(vdata, tk); __arch_update_vsyscall(vdata, tk); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 475e29498bca..a6d3016410eb 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -335,6 +335,7 @@ static void put_probe_ref(void) static void blk_trace_cleanup(struct blk_trace *bt) { + synchronize_rcu(); blk_trace_free(bt); put_probe_ref(); } @@ -629,8 +630,10 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name, static int __blk_trace_startstop(struct request_queue *q, int start) { int ret; - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (bt == NULL) return -EINVAL; @@ -740,8 +743,8 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) void blk_trace_shutdown(struct request_queue *q) { mutex_lock(&q->blk_trace_mutex); - - if (q->blk_trace) { + if (rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } @@ -752,8 +755,10 @@ void blk_trace_shutdown(struct request_queue *q) #ifdef CONFIG_BLK_CGROUP static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + /* We don't use the 'bt' value here except as an optimization... */ + bt = rcu_dereference_protected(q->blk_trace, 1); if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return 0; @@ -796,10 +801,14 @@ blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) static void blk_add_trace_rq(struct request *rq, int error, unsigned int nr_bytes, u32 what, u64 cgid) { - struct blk_trace *bt = rq->q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(rq->q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } if (blk_rq_is_passthrough(rq)) what |= BLK_TC_ACT(BLK_TC_PC); @@ -808,6 +817,7 @@ static void blk_add_trace_rq(struct request *rq, int error, __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq), rq->cmd_flags, what, error, 0, NULL, cgid); + rcu_read_unlock(); } static void blk_add_trace_rq_insert(void *ignore, @@ -853,14 +863,19 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq, static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, u32 what, int error) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, what, error, 0, NULL, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); } static void blk_add_trace_bio_bounce(void *ignore, @@ -905,11 +920,14 @@ static void blk_add_trace_getrq(void *ignore, if (bio) blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, NULL, 0); + rcu_read_unlock(); } } @@ -921,27 +939,35 @@ static void blk_add_trace_sleeprq(void *ignore, if (bio) blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, 0, 0, NULL, 0); + rcu_read_unlock(); } } static void blk_add_trace_plug(void *ignore, struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0); + rcu_read_unlock(); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, unsigned int depth, bool explicit) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(depth); u32 what; @@ -953,14 +979,17 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0); } + rcu_read_unlock(); } static void blk_add_trace_split(void *ignore, struct request_queue *q, struct bio *bio, unsigned int pdu) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(pdu); @@ -969,6 +998,7 @@ static void blk_add_trace_split(void *ignore, BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), &rpdu, blk_trace_bio_get_cgid(q, bio)); } + rcu_read_unlock(); } /** @@ -988,11 +1018,15 @@ static void blk_add_trace_bio_remap(void *ignore, struct request_queue *q, struct bio *bio, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(bio_dev(bio)); @@ -1001,6 +1035,7 @@ static void blk_add_trace_bio_remap(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); } /** @@ -1021,11 +1056,15 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); @@ -1034,6 +1073,7 @@ static void blk_add_trace_rq_remap(void *ignore, __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, sizeof(r), &r, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } /** @@ -1051,14 +1091,19 @@ void blk_add_driver_data(struct request_queue *q, struct request *rq, void *data, size_t len) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, 0, len, data, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data); @@ -1597,6 +1642,7 @@ static int blk_trace_remove_queue(struct request_queue *q) return -EINVAL; put_probe_ref(); + synchronize_rcu(); blk_trace_free(bt); return 0; } @@ -1758,6 +1804,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct hd_struct *p = dev_to_part(dev); struct request_queue *q; struct block_device *bdev; + struct blk_trace *bt; ssize_t ret = -ENXIO; bdev = bdget(part_devt(p)); @@ -1770,21 +1817,23 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - ret = sprintf(buf, "%u\n", !!q->blk_trace); + ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; } - if (q->blk_trace == NULL) + if (bt == NULL) ret = sprintf(buf, "disabled\n"); else if (attr == &dev_attr_act_mask) - ret = blk_trace_mask2str(buf, q->blk_trace->act_mask); + ret = blk_trace_mask2str(buf, bt->act_mask); else if (attr == &dev_attr_pid) - ret = sprintf(buf, "%u\n", q->blk_trace->pid); + ret = sprintf(buf, "%u\n", bt->pid); else if (attr == &dev_attr_start_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba); + ret = sprintf(buf, "%llu\n", bt->start_lba); else if (attr == &dev_attr_end_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); + ret = sprintf(buf, "%llu\n", bt->end_lba); out_unlock_bdev: mutex_unlock(&q->blk_trace_mutex); @@ -1801,6 +1850,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct block_device *bdev; struct request_queue *q; struct hd_struct *p; + struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL; @@ -1831,8 +1881,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - if (!!value == !!q->blk_trace) { + if (!!value == !!bt) { ret = 0; goto out_unlock_bdev; } @@ -1844,18 +1896,18 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } ret = 0; - if (q->blk_trace == NULL) + if (bt == NULL) ret = blk_trace_setup_queue(q, bdev); if (ret == 0) { if (attr == &dev_attr_act_mask) - q->blk_trace->act_mask = value; + bt->act_mask = value; else if (attr == &dev_attr_pid) - q->blk_trace->pid = value; + bt->pid = value; else if (attr == &dev_attr_start_lba) - q->blk_trace->start_lba = value; + bt->start_lba = value; else if (attr == &dev_attr_end_lba) - q->blk_trace->end_lba = value; + bt->end_lba = value; } out_unlock_bdev: diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5b6ee4aadc26..256ac508196f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1827,6 +1827,7 @@ static __init int init_trace_selftests(void) pr_info("Running postponed tracer tests:\n"); + tracing_selftest_running = true; list_for_each_entry_safe(p, n, &postponed_selftests, list) { /* This loop can take minutes when sanitizers are enabled, so * lets make sure we allow RCU processing. @@ -1849,6 +1850,7 @@ static __init int init_trace_selftests(void) list_del(&p->list); kfree(p); } + tracing_selftest_running = false; out: mutex_unlock(&trace_types_lock); diff --git a/mm/debug.c b/mm/debug.c index 0461df1207cb..6a52316af839 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -47,6 +47,7 @@ void __dump_page(struct page *page, const char *reason) struct address_space *mapping; bool page_poisoned = PagePoisoned(page); int mapcount; + char *type = ""; /* * If struct page is poisoned don't access Page*() functions as that @@ -78,9 +79,9 @@ void __dump_page(struct page *page, const char *reason) page, page_ref_count(page), mapcount, page->mapping, page_to_pgoff(page)); if (PageKsm(page)) - pr_warn("ksm flags: %#lx(%pGp)\n", page->flags, &page->flags); + type = "ksm "; else if (PageAnon(page)) - pr_warn("anon flags: %#lx(%pGp)\n", page->flags, &page->flags); + type = "anon "; else if (mapping) { if (mapping->host && mapping->host->i_dentry.first) { struct dentry *dentry; @@ -88,10 +89,11 @@ void __dump_page(struct page *page, const char *reason) pr_warn("%ps name:\"%pd\"\n", mapping->a_ops, dentry); } else pr_warn("%ps\n", mapping->a_ops); - pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags); } BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1); + pr_warn("%sflags: %#lx(%pGp)\n", type, page->flags, &page->flags); + hex_only: print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), page, diff --git a/mm/gup.c b/mm/gup.c index 7646bf993b25..5244b8090440 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2415,7 +2415,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, unsigned long addr, len, end; int nr = 0, ret = 0; - if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM))) + if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | + FOLL_FORCE))) return -EINVAL; start = untagged_addr(start) & PAGE_MASK; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a88093213674..54c106bdbafd 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -177,16 +177,13 @@ static ssize_t enabled_store(struct kobject *kobj, { ssize_t ret = count; - if (!memcmp("always", buf, - min(sizeof("always")-1, count))) { + if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("madvise", buf, - min(sizeof("madvise")-1, count))) { + } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("never", buf, - min(sizeof("never")-1, count))) { + } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); } else @@ -250,32 +247,27 @@ static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - if (!memcmp("always", buf, - min(sizeof("always")-1, count))) { + if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("defer+madvise", buf, - min(sizeof("defer+madvise")-1, count))) { + } else if (sysfs_streq(buf, "defer+madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("defer", buf, - min(sizeof("defer")-1, count))) { + } else if (sysfs_streq(buf, "defer")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("madvise", buf, - min(sizeof("madvise")-1, count))) { + } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); - } else if (!memcmp("never", buf, - min(sizeof("never")-1, count))) { + } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); @@ -2712,7 +2704,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) unsigned long flags; pgoff_t end; - VM_BUG_ON_PAGE(is_huge_zero_page(page), page); + VM_BUG_ON_PAGE(is_huge_zero_page(head), head); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageCompound(page), page); diff --git a/net/core/dev.c b/net/core/dev.c index 466f2e4144b0..c3da35f3c7e4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -146,7 +146,6 @@ #include "net-sysfs.h" #define MAX_GRO_SKBS 8 -#define MAX_NEST_DEV 8 /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) @@ -331,6 +330,12 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) name_node = netdev_name_node_lookup(net, name); if (!name_node) return -ENOENT; + /* lookup might have found our primary name or a name belonging + * to another device. + */ + if (name_node == dev->name_node || name_node->dev != dev) + return -EINVAL; + __netdev_name_node_alt_destroy(name_node); return 0; @@ -3607,26 +3612,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { - if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) && - qdisc_run_begin(q)) { - if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, - &q->state))) { - __qdisc_drop(skb, &to_free); - rc = NET_XMIT_DROP; - goto end_run; - } - qdisc_bstats_cpu_update(q, skb); - - rc = NET_XMIT_SUCCESS; - if (sch_direct_xmit(skb, q, dev, txq, NULL, true)) - __qdisc_run(q); - -end_run: - qdisc_run_end(q); - } else { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - qdisc_run(q); - } + rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + qdisc_run(q); if (unlikely(to_free)) kfree_skb_list(to_free); @@ -7153,8 +7140,8 @@ static int __netdev_walk_all_lower_dev(struct net_device *dev, return 0; } -static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, - struct list_head **iter) +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, + struct list_head **iter) { struct netdev_adjacent *lower; @@ -7166,6 +7153,7 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, return lower->dev; } +EXPORT_SYMBOL(netdev_next_lower_dev_rcu); static u8 __netdev_upper_depth(struct net_device *dev) { diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3e7e15278c46..bd7eba9066f8 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -974,7 +974,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh = nlmsg_data(nlh); frh->family = ops->family; - frh->table = rule->table; + frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f02705ff0e5e..1737bac74c45 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3499,27 +3499,25 @@ static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr, if (err) return err; - alt_ifname = nla_data(attr); + alt_ifname = nla_strdup(attr, GFP_KERNEL); + if (!alt_ifname) + return -ENOMEM; + if (cmd == RTM_NEWLINKPROP) { - alt_ifname = kstrdup(alt_ifname, GFP_KERNEL); - if (!alt_ifname) - return -ENOMEM; err = netdev_name_node_alt_create(dev, alt_ifname); - if (err) { - kfree(alt_ifname); - return err; - } + if (!err) + alt_ifname = NULL; } else if (cmd == RTM_DELLINKPROP) { err = netdev_name_node_alt_destroy(dev, alt_ifname); - if (err) - return err; } else { - WARN_ON(1); - return 0; + WARN_ON_ONCE(1); + err = -EINVAL; } - *changed = true; - return 0; + kfree(alt_ifname); + if (!err) + *changed = true; + return err; } static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 030d43c7c957..be5c5903cfe1 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1856,8 +1856,12 @@ int __udp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); + if (sk->sk_prot->rehash && + (sk->sk_userlocks & SOCK_BINDPORT_LOCK)) + sk->sk_prot->rehash(sk); + } if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index cfae0a1529a1..bde3bf180871 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1068,8 +1068,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, found++; break; } - if (rt_can_ecmp) - fallback_ins = fallback_ins ?: ins; + fallback_ins = fallback_ins ?: ins; goto next_iter; } @@ -1112,7 +1111,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, } if (fallback_ins && !found) { - /* No ECMP-able route found, replace first non-ECMP one */ + /* No matching route with same ecmp-able-ness found, replace + * first matching route + */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index affb51c11a25..119c7226c4be 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5152,6 +5152,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); + cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; nhn++; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e041af2f021a..88d7a692a965 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2959,7 +2959,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, (auth_transaction == 2 && ifmgd->auth_data->expected_transaction == 2)) { if (!ieee80211_mark_sta_auth(sdata, bssid)) - goto out_err; + return; /* ignore frame -- wait for timeout */ } else if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE && auth_transaction == 2) { sdata_info(sdata, "SAE peer confirmed\n"); @@ -2967,10 +2967,6 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, } cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); - return; - out_err: - mutex_unlock(&sdata->local->sta_mtx); - /* ignore frame -- wait for timeout */ } #define case_WLAN(type) \ diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 32a7a53833c0..decd46b38393 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1063,16 +1063,22 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elem_parse_failed = true; break; case WLAN_EID_VHT_OPERATION: - if (elen >= sizeof(struct ieee80211_vht_operation)) + if (elen >= sizeof(struct ieee80211_vht_operation)) { elems->vht_operation = (void *)pos; - else - elem_parse_failed = true; + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + break; + } + elem_parse_failed = true; break; case WLAN_EID_OPMODE_NOTIF: - if (elen > 0) + if (elen > 0) { elems->opmode_notif = pos; - else - elem_parse_failed = true; + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + break; + } + elem_parse_failed = true; break; case WLAN_EID_MESH_ID: elems->mesh_id = pos; @@ -2987,10 +2993,22 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, int cf0, cf1; int ccfs0, ccfs1, ccfs2; int ccf0, ccf1; + u32 vht_cap; + bool support_80_80 = false; + bool support_160 = false; if (!oper || !htop) return false; + vht_cap = hw->wiphy->bands[chandef->chan->band]->vht_cap.cap; + support_160 = (vht_cap & (IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK | + IEEE80211_VHT_CAP_EXT_NSS_BW_MASK)); + support_80_80 = ((vht_cap & + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) || + (vht_cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && + vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) || + ((vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) >> + IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT > 1)); ccfs0 = oper->center_freq_seg0_idx; ccfs1 = oper->center_freq_seg1_idx; ccfs2 = (le16_to_cpu(htop->operation_mode) & @@ -3018,10 +3036,10 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, unsigned int diff; diff = abs(ccf1 - ccf0); - if (diff == 8) { + if ((diff == 8) && support_160) { new.width = NL80211_CHAN_WIDTH_160; new.center_freq1 = cf1; - } else if (diff > 8) { + } else if ((diff > 8) && support_80_80) { new.width = NL80211_CHAN_WIDTH_80P80; new.center_freq2 = cf1; } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 69c107f9ba8d..8dd17589217d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -723,6 +723,20 @@ ip_set_rcu_get(struct net *net, ip_set_id_t index) return set; } +static inline void +ip_set_lock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_lock_bh(&set->lock); +} + +static inline void +ip_set_unlock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_unlock_bh(&set->lock); +} + int ip_set_test(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt) @@ -744,9 +758,9 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, if (ret == -EAGAIN) { /* Type requests element to be completed */ pr_debug("element must be completed, ADD is triggered\n"); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); ret = 1; } else { /* --return-nomatch: invert matched element */ @@ -775,9 +789,9 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -797,9 +811,9 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -1264,9 +1278,9 @@ ip_set_flush_set(struct ip_set *set) { pr_debug("set: %s\n", set->name); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->flush(set); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); } static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb, @@ -1713,9 +1727,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, bool eexist = flags & IPSET_FLAG_EXIST, retried = false; do { - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); retried = true; } while (ret == -EAGAIN && set->variant->resize && diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 7480ce55b5c8..e52d7b7597a0 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -7,13 +7,21 @@ #include <linux/rcupdate.h> #include <linux/jhash.h> #include <linux/types.h> +#include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/ipset/ip_set.h> -#define __ipset_dereference_protected(p, c) rcu_dereference_protected(p, c) -#define ipset_dereference_protected(p, set) \ - __ipset_dereference_protected(p, lockdep_is_held(&(set)->lock)) - -#define rcu_dereference_bh_nfnl(p) rcu_dereference_bh_check(p, 1) +#define __ipset_dereference(p) \ + rcu_dereference_protected(p, 1) +#define ipset_dereference_nfnl(p) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) +#define ipset_dereference_set(p, set) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ + lockdep_is_held(&(set)->lock)) +#define ipset_dereference_bh_nfnl(p) \ + rcu_dereference_bh_check(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) /* Hashing which uses arrays to resolve clashing. The hash table is resized * (doubled) when searching becomes too long. @@ -72,11 +80,35 @@ struct hbucket { __aligned(__alignof__(u64)); }; +/* Region size for locking == 2^HTABLE_REGION_BITS */ +#define HTABLE_REGION_BITS 10 +#define ahash_numof_locks(htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 1 \ + : jhash_size((htable_bits) - HTABLE_REGION_BITS)) +#define ahash_sizeof_regions(htable_bits) \ + (ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region)) +#define ahash_region(n, htable_bits) \ + ((n) % ahash_numof_locks(htable_bits)) +#define ahash_bucket_start(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 0 \ + : (h) * jhash_size(HTABLE_REGION_BITS)) +#define ahash_bucket_end(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? jhash_size(htable_bits) \ + : ((h) + 1) * jhash_size(HTABLE_REGION_BITS)) + +struct htable_gc { + struct delayed_work dwork; + struct ip_set *set; /* Set the gc belongs to */ + u32 region; /* Last gc run position */ +}; + /* The hash table: the table size stored here in order to make resizing easy */ struct htable { atomic_t ref; /* References for resizing */ - atomic_t uref; /* References for dumping */ + atomic_t uref; /* References for dumping and gc */ u8 htable_bits; /* size of hash table == 2^htable_bits */ + u32 maxelem; /* Maxelem per region */ + struct ip_set_region *hregion; /* Region locks and ext sizes */ struct hbucket __rcu *bucket[0]; /* hashtable buckets */ }; @@ -162,6 +194,10 @@ htable_bits(u32 hashsize) #define NLEN 0 #endif /* IP_SET_HASH_WITH_NETS */ +#define SET_ELEM_EXPIRED(set, d) \ + (SET_WITH_TIMEOUT(set) && \ + ip_set_timeout_expired(ext_timeout(d, set))) + #endif /* _IP_SET_HASH_GEN_H */ #ifndef MTYPE @@ -205,10 +241,12 @@ htable_bits(u32 hashsize) #undef mtype_test_cidrs #undef mtype_test #undef mtype_uref -#undef mtype_expire #undef mtype_resize +#undef mtype_ext_size +#undef mtype_resize_ad #undef mtype_head #undef mtype_list +#undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init #undef mtype_variant @@ -247,10 +285,12 @@ htable_bits(u32 hashsize) #define mtype_test_cidrs IPSET_TOKEN(MTYPE, _test_cidrs) #define mtype_test IPSET_TOKEN(MTYPE, _test) #define mtype_uref IPSET_TOKEN(MTYPE, _uref) -#define mtype_expire IPSET_TOKEN(MTYPE, _expire) #define mtype_resize IPSET_TOKEN(MTYPE, _resize) +#define mtype_ext_size IPSET_TOKEN(MTYPE, _ext_size) +#define mtype_resize_ad IPSET_TOKEN(MTYPE, _resize_ad) #define mtype_head IPSET_TOKEN(MTYPE, _head) #define mtype_list IPSET_TOKEN(MTYPE, _list) +#define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) @@ -275,8 +315,7 @@ htable_bits(u32 hashsize) /* The generic hash structure */ struct htype { struct htable __rcu *table; /* the hash table */ - struct timer_list gc; /* garbage collection when timeout enabled */ - struct ip_set *set; /* attached to this ip_set */ + struct htable_gc gc; /* gc workqueue */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ #ifdef IP_SET_HASH_WITH_MARKMASK @@ -288,21 +327,33 @@ struct htype { #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif + struct list_head ad; /* Resize add|del backlist */ struct mtype_elem next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_NETS struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */ #endif }; +/* ADD|DEL entries saved during resize */ +struct mtype_resize_ad { + struct list_head list; + enum ipset_adt ad; /* ADD|DEL element */ + struct mtype_elem d; /* Element value */ + struct ip_set_ext ext; /* Extensions for ADD */ + struct ip_set_ext mext; /* Target extensions for ADD */ + u32 flags; /* Flags for ADD */ +}; + #ifdef IP_SET_HASH_WITH_NETS /* Network cidr size book keeping when the hash stores different * sized networks. cidr == real cidr + 1 to support /0. */ static void -mtype_add_cidr(struct htype *h, u8 cidr, u8 n) +mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { int i, j; + spin_lock_bh(&set->lock); /* Add in increasing prefix order, so larger cidr first */ for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) { if (j != -1) { @@ -311,7 +362,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) j = i; } else if (h->nets[i].cidr[n] == cidr) { h->nets[CIDR_POS(cidr)].nets[n]++; - return; + goto unlock; } } if (j != -1) { @@ -320,24 +371,29 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) } h->nets[i].cidr[n] = cidr; h->nets[CIDR_POS(cidr)].nets[n] = 1; +unlock: + spin_unlock_bh(&set->lock); } static void -mtype_del_cidr(struct htype *h, u8 cidr, u8 n) +mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { u8 i, j, net_end = NLEN - 1; + spin_lock_bh(&set->lock); for (i = 0; i < NLEN; i++) { if (h->nets[i].cidr[n] != cidr) continue; h->nets[CIDR_POS(cidr)].nets[n]--; if (h->nets[CIDR_POS(cidr)].nets[n] > 0) - return; + goto unlock; for (j = i; j < net_end && h->nets[j].cidr[n]; j++) h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; h->nets[j].cidr[n] = 0; - return; + goto unlock; } +unlock: + spin_unlock_bh(&set->lock); } #endif @@ -345,7 +401,7 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 n) static size_t mtype_ahash_memsize(const struct htype *h, const struct htable *t) { - return sizeof(*h) + sizeof(*t); + return sizeof(*h) + sizeof(*t) + ahash_sizeof_regions(t->htable_bits); } /* Get the ith element from the array block n */ @@ -369,24 +425,29 @@ mtype_flush(struct ip_set *set) struct htype *h = set->data; struct htable *t; struct hbucket *n; - u32 i; - - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); - if (!n) - continue; - if (set->extensions & IPSET_EXT_DESTROY) - mtype_ext_cleanup(set, n); - /* FIXME: use slab cache */ - rcu_assign_pointer(hbucket(t, i), NULL); - kfree_rcu(n, rcu); + u32 r, i; + + t = ipset_dereference_nfnl(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); + if (!n) + continue; + if (set->extensions & IPSET_EXT_DESTROY) + mtype_ext_cleanup(set, n); + /* FIXME: use slab cache */ + rcu_assign_pointer(hbucket(t, i), NULL); + kfree_rcu(n, rcu); + } + t->hregion[r].ext_size = 0; + t->hregion[r].elements = 0; + spin_unlock_bh(&t->hregion[r].lock); } #ifdef IP_SET_HASH_WITH_NETS memset(h->nets, 0, sizeof(h->nets)); #endif - set->elements = 0; - set->ext_size = 0; } /* Destroy the hashtable part of the set */ @@ -397,7 +458,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -406,6 +467,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) kfree(n); } + ip_set_free(t->hregion); ip_set_free(t); } @@ -414,28 +476,21 @@ static void mtype_destroy(struct ip_set *set) { struct htype *h = set->data; + struct list_head *l, *lt; if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&h->gc); + cancel_delayed_work_sync(&h->gc.dwork); - mtype_ahash_destroy(set, - __ipset_dereference_protected(h->table, 1), true); + mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + list_for_each_safe(l, lt, &h->ad) { + list_del(l); + kfree(l); + } kfree(h); set->data = NULL; } -static void -mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) -{ - struct htype *h = set->data; - - timer_setup(&h->gc, gc, 0); - mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); - pr_debug("gc initialized, run in every %u\n", - IPSET_GC_PERIOD(set->timeout)); -} - static bool mtype_same_set(const struct ip_set *a, const struct ip_set *b) { @@ -454,11 +509,9 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } -/* Delete expired elements from the hashtable */ static void -mtype_expire(struct ip_set *set, struct htype *h) +mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) { - struct htable *t; struct hbucket *n, *tmp; struct mtype_elem *data; u32 i, j, d; @@ -466,10 +519,12 @@ mtype_expire(struct ip_set *set, struct htype *h) #ifdef IP_SET_HASH_WITH_NETS u8 k; #endif + u8 htable_bits = t->htable_bits; - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, htable_bits); + i < ahash_bucket_end(r, htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; for (j = 0, d = 0; j < n->pos; j++) { @@ -485,58 +540,100 @@ mtype_expire(struct ip_set *set, struct htype *h) smp_mb__after_atomic(); #ifdef IP_SET_HASH_WITH_NETS for (k = 0; k < IPSET_NET_COUNT; k++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, k)), k); #endif + t->hregion[r].elements--; ip_set_ext_destroy(set, data); - set->elements--; d++; } if (d >= AHASH_INIT_SIZE) { if (d >= n->size) { + t->hregion[r].ext_size -= + ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, i), NULL); kfree_rcu(n, rcu); continue; } tmp = kzalloc(sizeof(*tmp) + - (n->size - AHASH_INIT_SIZE) * dsize, - GFP_ATOMIC); + (n->size - AHASH_INIT_SIZE) * dsize, + GFP_ATOMIC); if (!tmp) - /* Still try to delete expired elements */ + /* Still try to delete expired elements. */ continue; tmp->size = n->size - AHASH_INIT_SIZE; for (j = 0, d = 0; j < n->pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); - memcpy(tmp->value + d * dsize, data, dsize); + memcpy(tmp->value + d * dsize, + data, dsize); set_bit(d, tmp->used); d++; } tmp->pos = d; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, i), tmp); kfree_rcu(n, rcu); } } + spin_unlock_bh(&t->hregion[r].lock); } static void -mtype_gc(struct timer_list *t) +mtype_gc(struct work_struct *work) { - struct htype *h = from_timer(h, t, gc); - struct ip_set *set = h->set; + struct htable_gc *gc; + struct ip_set *set; + struct htype *h; + struct htable *t; + u32 r, numof_locks; + unsigned int next_run; + + gc = container_of(work, struct htable_gc, dwork.work); + set = gc->set; + h = set->data; - pr_debug("called\n"); spin_lock_bh(&set->lock); - mtype_expire(set, h); + t = ipset_dereference_set(h->table, set); + atomic_inc(&t->uref); + numof_locks = ahash_numof_locks(t->htable_bits); + r = gc->region++; + if (r >= numof_locks) { + r = gc->region = 0; + } + next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks; + if (next_run < HZ/10) + next_run = HZ/10; spin_unlock_bh(&set->lock); - h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; - add_timer(&h->gc); + mtype_gc_do(set, h, t, r); + + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by expire: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + + queue_delayed_work(system_power_efficient_wq, &gc->dwork, next_run); + +} + +static void +mtype_gc_init(struct htable_gc *gc) +{ + INIT_DEFERRABLE_WORK(&gc->dwork, mtype_gc); + queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static int +mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); +static int +mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); + /* Resize a hash: create a new hash table with doubling the hashsize * and inserting the elements to it. Repeat until we succeed or * fail due to memory pressures. @@ -547,7 +644,7 @@ mtype_resize(struct ip_set *set, bool retried) struct htype *h = set->data; struct htable *t, *orig; u8 htable_bits; - size_t extsize, dsize = set->dsize; + size_t dsize = set->dsize; #ifdef IP_SET_HASH_WITH_NETS u8 flags; struct mtype_elem *tmp; @@ -555,7 +652,9 @@ mtype_resize(struct ip_set *set, bool retried) struct mtype_elem *data; struct mtype_elem *d; struct hbucket *n, *m; - u32 i, j, key; + struct list_head *l, *lt; + struct mtype_resize_ad *x; + u32 i, j, r, nr, key; int ret; #ifdef IP_SET_HASH_WITH_NETS @@ -563,10 +662,8 @@ mtype_resize(struct ip_set *set, bool retried) if (!tmp) return -ENOMEM; #endif - rcu_read_lock_bh(); - orig = rcu_dereference_bh_nfnl(h->table); + orig = ipset_dereference_bh_nfnl(h->table); htable_bits = orig->htable_bits; - rcu_read_unlock_bh(); retry: ret = 0; @@ -583,88 +680,124 @@ mtype_resize(struct ip_set *set, bool retried) ret = -ENOMEM; goto out; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits)); + if (!t->hregion) { + kfree(t); + ret = -ENOMEM; + goto out; + } t->htable_bits = htable_bits; + t->maxelem = h->maxelem / ahash_numof_locks(htable_bits); + for (i = 0; i < ahash_numof_locks(htable_bits); i++) + spin_lock_init(&t->hregion[i].lock); - spin_lock_bh(&set->lock); - orig = __ipset_dereference_protected(h->table, 1); - /* There can't be another parallel resizing, but dumping is possible */ + /* There can't be another parallel resizing, + * but dumping, gc, kernel side add/del are possible + */ + orig = ipset_dereference_bh_nfnl(h->table); atomic_set(&orig->ref, 1); atomic_inc(&orig->uref); - extsize = 0; pr_debug("attempt to resize set %s from %u to %u, t %p\n", set->name, orig->htable_bits, htable_bits, orig); - for (i = 0; i < jhash_size(orig->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(orig, i), 1); - if (!n) - continue; - for (j = 0; j < n->pos; j++) { - if (!test_bit(j, n->used)) + for (r = 0; r < ahash_numof_locks(orig->htable_bits); r++) { + /* Expire may replace a hbucket with another one */ + rcu_read_lock_bh(); + for (i = ahash_bucket_start(r, orig->htable_bits); + i < ahash_bucket_end(r, orig->htable_bits); i++) { + n = __ipset_dereference(hbucket(orig, i)); + if (!n) continue; - data = ahash_data(n, j, dsize); + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, dsize); + if (SET_ELEM_EXPIRED(set, data)) + continue; #ifdef IP_SET_HASH_WITH_NETS - /* We have readers running parallel with us, - * so the live data cannot be modified. - */ - flags = 0; - memcpy(tmp, data, dsize); - data = tmp; - mtype_data_reset_flags(data, &flags); + /* We have readers running parallel with us, + * so the live data cannot be modified. + */ + flags = 0; + memcpy(tmp, data, dsize); + data = tmp; + mtype_data_reset_flags(data, &flags); #endif - key = HKEY(data, h->initval, htable_bits); - m = __ipset_dereference_protected(hbucket(t, key), 1); - if (!m) { - m = kzalloc(sizeof(*m) + + key = HKEY(data, h->initval, htable_bits); + m = __ipset_dereference(hbucket(t, key)); + nr = ahash_region(key, htable_bits); + if (!m) { + m = kzalloc(sizeof(*m) + AHASH_INIT_SIZE * dsize, GFP_ATOMIC); - if (!m) { - ret = -ENOMEM; - goto cleanup; - } - m->size = AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - RCU_INIT_POINTER(hbucket(t, key), m); - } else if (m->pos >= m->size) { - struct hbucket *ht; - - if (m->size >= AHASH_MAX(h)) { - ret = -EAGAIN; - } else { - ht = kzalloc(sizeof(*ht) + + if (!m) { + ret = -ENOMEM; + goto cleanup; + } + m->size = AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + RCU_INIT_POINTER(hbucket(t, key), m); + } else if (m->pos >= m->size) { + struct hbucket *ht; + + if (m->size >= AHASH_MAX(h)) { + ret = -EAGAIN; + } else { + ht = kzalloc(sizeof(*ht) + (m->size + AHASH_INIT_SIZE) * dsize, GFP_ATOMIC); - if (!ht) - ret = -ENOMEM; + if (!ht) + ret = -ENOMEM; + } + if (ret < 0) + goto cleanup; + memcpy(ht, m, sizeof(struct hbucket) + + m->size * dsize); + ht->size = m->size + AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + kfree(m); + m = ht; + RCU_INIT_POINTER(hbucket(t, key), ht); } - if (ret < 0) - goto cleanup; - memcpy(ht, m, sizeof(struct hbucket) + - m->size * dsize); - ht->size = m->size + AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - kfree(m); - m = ht; - RCU_INIT_POINTER(hbucket(t, key), ht); - } - d = ahash_data(m, m->pos, dsize); - memcpy(d, data, dsize); - set_bit(m->pos++, m->used); + d = ahash_data(m, m->pos, dsize); + memcpy(d, data, dsize); + set_bit(m->pos++, m->used); + t->hregion[nr].elements++; #ifdef IP_SET_HASH_WITH_NETS - mtype_data_reset_flags(d, &flags); + mtype_data_reset_flags(d, &flags); #endif + } } + rcu_read_unlock_bh(); } - rcu_assign_pointer(h->table, t); - set->ext_size = extsize; - spin_unlock_bh(&set->lock); + /* There can't be any other writer. */ + rcu_assign_pointer(h->table, t); /* Give time to other readers of the set */ synchronize_rcu(); pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, orig->htable_bits, orig, t->htable_bits, t); - /* If there's nobody else dumping the table, destroy it */ + /* Add/delete elements processed by the SET target during resize. + * Kernel-side add cannot trigger a resize and userspace actions + * are serialized by the mutex. + */ + list_for_each_safe(l, lt, &h->ad) { + x = list_entry(l, struct mtype_resize_ad, list); + if (x->ad == IPSET_ADD) { + mtype_add(set, &x->d, &x->ext, &x->mext, x->flags); + } else { + mtype_del(set, &x->d, NULL, NULL, 0); + } + list_del(l); + kfree(l); + } + /* If there's nobody else using the table, destroy it */ if (atomic_dec_and_test(&orig->uref)) { pr_debug("Table destroy by resize %p\n", orig); mtype_ahash_destroy(set, orig, false); @@ -677,15 +810,44 @@ mtype_resize(struct ip_set *set, bool retried) return ret; cleanup: + rcu_read_unlock_bh(); atomic_set(&orig->ref, 0); atomic_dec(&orig->uref); - spin_unlock_bh(&set->lock); mtype_ahash_destroy(set, t, false); if (ret == -EAGAIN) goto retry; goto out; } +/* Get the current number of elements and ext_size in the set */ +static void +mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) +{ + struct htype *h = set->data; + const struct htable *t; + u32 i, j, r; + struct hbucket *n; + struct mtype_elem *data; + + t = rcu_dereference_bh(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = rcu_dereference_bh(hbucket(t, i)); + if (!n) + continue; + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, set->dsize); + if (!SET_ELEM_EXPIRED(set, data)) + (*elements)++; + } + } + *ext_size += t->hregion[r].ext_size; + } +} + /* Add an element to a hash and update the internal counters when succeeded, * otherwise report the proper error code. */ @@ -698,32 +860,49 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n, *old = ERR_PTR(-ENOENT); - int i, j = -1; + int i, j = -1, ret; bool flag_exist = flags & IPSET_FLAG_EXIST; bool deleted = false, forceadd = false, reuse = false; - u32 key, multi = 0; + u32 r, key, multi = 0, elements, maxelem; - if (set->elements >= h->maxelem) { - if (SET_WITH_TIMEOUT(set)) - /* FIXME: when set is full, we slow down here */ - mtype_expire(set, h); - if (set->elements >= h->maxelem && SET_WITH_FORCEADD(set)) + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(value, h->initval, t->htable_bits); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + elements = t->hregion[r].elements; + maxelem = t->maxelem; + if (elements >= maxelem) { + u32 e; + if (SET_WITH_TIMEOUT(set)) { + rcu_read_unlock_bh(); + mtype_gc_do(set, h, t, r); + rcu_read_lock_bh(); + } + maxelem = h->maxelem; + elements = 0; + for (e = 0; e < ahash_numof_locks(t->htable_bits); e++) + elements += t->hregion[e].elements; + if (elements >= maxelem && SET_WITH_FORCEADD(set)) forceadd = true; } + rcu_read_unlock_bh(); - t = ipset_dereference_protected(h->table, set); - key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) { - if (forceadd || set->elements >= h->maxelem) + if (forceadd || elements >= maxelem) goto set_full; old = NULL; n = kzalloc(sizeof(*n) + AHASH_INIT_SIZE * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } n->size = AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); goto copy_elem; } for (i = 0; i < n->pos; i++) { @@ -737,38 +916,37 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, } data = ahash_data(n, i, set->dsize); if (mtype_data_equal(data, d, &multi)) { - if (flag_exist || - (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)))) { + if (flag_exist || SET_ELEM_EXPIRED(set, data)) { /* Just the extensions could be overwritten */ j = i; goto overwrite_extensions; } - return -IPSET_ERR_EXIST; + ret = -IPSET_ERR_EXIST; + goto unlock; } /* Reuse first timed out entry */ - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)) && - j == -1) { + if (SET_ELEM_EXPIRED(set, data) && j == -1) { j = i; reuse = true; } } if (reuse || forceadd) { + if (j == -1) + j = 0; data = ahash_data(n, j, set->dsize); if (!deleted) { #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, i)), i); #endif ip_set_ext_destroy(set, data); - set->elements--; + t->hregion[r].elements--; } goto copy_data; } - if (set->elements >= h->maxelem) + if (elements >= maxelem) goto set_full; /* Create a new slot */ if (n->pos >= n->size) { @@ -776,28 +954,32 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); - return -EAGAIN; + ret = -EAGAIN; + goto resize; } old = n; n = kzalloc(sizeof(*n) + (old->size + AHASH_INIT_SIZE) * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } memcpy(n, old, sizeof(struct hbucket) + old->size * set->dsize); n->size = old->size + AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); } copy_elem: j = n->pos++; data = ahash_data(n, j, set->dsize); copy_data: - set->elements++; + t->hregion[r].elements++; #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_add_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); + mtype_add_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); #endif memcpy(data, d, sizeof(struct mtype_elem)); overwrite_extensions: @@ -820,13 +1002,41 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (old) kfree_rcu(old, rcu); } + ret = 0; +resize: + spin_unlock_bh(&t->hregion[r].lock); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side add, save values */ + struct mtype_resize_ad *x; + + x = kzalloc(sizeof(struct mtype_resize_ad), GFP_ATOMIC); + if (!x) + /* Don't bother */ + goto out; + x->ad = IPSET_ADD; + memcpy(&x->d, value, sizeof(struct mtype_elem)); + memcpy(&x->ext, ext, sizeof(struct ip_set_ext)); + memcpy(&x->mext, mext, sizeof(struct ip_set_ext)); + x->flags = flags; + spin_lock_bh(&set->lock); + list_add_tail(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + goto out; - return 0; set_full: if (net_ratelimit()) pr_warn("Set %s is full, maxelem %u reached\n", - set->name, h->maxelem); - return -IPSET_ERR_HASH_FULL; + set->name, maxelem); + ret = -IPSET_ERR_HASH_FULL; +unlock: + spin_unlock_bh(&t->hregion[r].lock); +out: + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by add: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + return ret; } /* Delete an element from the hash and free up space if possible. @@ -840,13 +1050,23 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n; - int i, j, k, ret = -IPSET_ERR_EXIST; + struct mtype_resize_ad *x = NULL; + int i, j, k, r, ret = -IPSET_ERR_EXIST; u32 key, multi = 0; size_t dsize = set->dsize; - t = ipset_dereference_protected(h->table, set); + /* Userspace add and resize is excluded by the mutex. + * Kernespace add does not trigger resize. + */ + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + rcu_read_unlock_bh(); + + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) goto out; for (i = 0, k = 0; i < n->pos; i++) { @@ -857,8 +1077,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, data = ahash_data(n, i, dsize); if (!mtype_data_equal(data, d, &multi)) continue; - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set))) + if (SET_ELEM_EXPIRED(set, data)) goto out; ret = 0; @@ -866,20 +1085,33 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, smp_mb__after_atomic(); if (i + 1 == n->pos) n->pos--; - set->elements--; + t->hregion[r].elements--; #ifdef IP_SET_HASH_WITH_NETS for (j = 0; j < IPSET_NET_COUNT; j++) - mtype_del_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, j)), - j); + mtype_del_cidr(set, h, + NCIDR_PUT(DCIDR_GET(d->cidr, j)), j); #endif ip_set_ext_destroy(set, data); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side del, + * save values + */ + x = kzalloc(sizeof(struct mtype_resize_ad), + GFP_ATOMIC); + if (x) { + x->ad = IPSET_DEL; + memcpy(&x->d, value, + sizeof(struct mtype_elem)); + x->flags = flags; + } + } for (; i < n->pos; i++) { if (!test_bit(i, n->used)) k++; } if (n->pos == 0 && k == 0) { - set->ext_size -= ext_size(n->size, dsize); + t->hregion[r].ext_size -= ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, key), NULL); kfree_rcu(n, rcu); } else if (k >= AHASH_INIT_SIZE) { @@ -898,7 +1130,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, k++; } tmp->pos = k; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, key), tmp); kfree_rcu(n, rcu); } @@ -906,6 +1139,16 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, } out: + spin_unlock_bh(&t->hregion[r].lock); + if (x) { + spin_lock_bh(&set->lock); + list_add(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by del: %p\n", t); + mtype_ahash_destroy(set, t, false); + } return ret; } @@ -991,6 +1234,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, int i, ret = 0; u32 key, multi = 0; + rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); #ifdef IP_SET_HASH_WITH_NETS /* If we test an IP address and not a network address, @@ -1022,6 +1266,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, goto out; } out: + rcu_read_unlock_bh(); return ret; } @@ -1033,23 +1278,14 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) const struct htable *t; struct nlattr *nested; size_t memsize; + u32 elements = 0; + size_t ext_size = 0; u8 htable_bits; - /* If any members have expired, set->elements will be wrong - * mytype_expire function will update it with the right count. - * we do not hold set->lock here, so grab it first. - * set->elements can still be incorrect in the case of a huge set, - * because elements might time out during the listing. - */ - if (SET_WITH_TIMEOUT(set)) { - spin_lock_bh(&set->lock); - mtype_expire(set, h); - spin_unlock_bh(&set->lock); - } - rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); - memsize = mtype_ahash_memsize(h, t) + set->ext_size; + t = rcu_dereference_bh(h->table); + mtype_ext_size(set, &elements, &ext_size); + memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size; htable_bits = t->htable_bits; rcu_read_unlock_bh(); @@ -1071,7 +1307,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) #endif if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || - nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements))) + nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; @@ -1091,15 +1327,15 @@ mtype_uref(struct ip_set *set, struct netlink_callback *cb, bool start) if (start) { rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); + t = ipset_dereference_bh_nfnl(h->table); atomic_inc(&t->uref); cb->args[IPSET_CB_PRIVATE] = (unsigned long)t; rcu_read_unlock_bh(); } else if (cb->args[IPSET_CB_PRIVATE]) { t = (struct htable *)cb->args[IPSET_CB_PRIVATE]; if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { - /* Resizing didn't destroy the hash table */ - pr_debug("Table destroy by dump: %p\n", t); + pr_debug("Table destroy after resize " + " by dump: %p\n", t); mtype_ahash_destroy(set, t, false); } cb->args[IPSET_CB_PRIVATE] = 0; @@ -1141,8 +1377,7 @@ mtype_list(const struct ip_set *set, if (!test_bit(i, n->used)) continue; e = ahash_data(n, i, set->dsize); - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(e, set))) + if (SET_ELEM_EXPIRED(set, e)) continue; pr_debug("list hash %lu hbucket %p i %u, data %p\n", cb->args[IPSET_CB_ARG0], n, i, e); @@ -1208,6 +1443,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .region_lock = true, }; #ifdef IP_SET_EMIT_CREATE @@ -1226,6 +1462,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, size_t hsize; struct htype *h; struct htable *t; + u32 i; pr_debug("Create set %s with family %s\n", set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6"); @@ -1294,6 +1531,15 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, kfree(h); return -ENOMEM; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); + if (!t->hregion) { + kfree(t); + kfree(h); + return -ENOMEM; + } + h->gc.set = set; + for (i = 0; i < ahash_numof_locks(hbits); i++) + spin_lock_init(&t->hregion[i].lock); h->maxelem = maxelem; #ifdef IP_SET_HASH_WITH_NETMASK h->netmask = netmask; @@ -1304,9 +1550,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, get_random_bytes(&h->initval, sizeof(h->initval)); t->htable_bits = hbits; + t->maxelem = h->maxelem / ahash_numof_locks(hbits); RCU_INIT_POINTER(h->table, t); - h->set = set; + INIT_LIST_HEAD(&h->ad); set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { @@ -1329,12 +1576,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) #endif - IPSET_TOKEN(HTYPE, 4_gc_init)(set, - IPSET_TOKEN(HTYPE, 4_gc)); + IPSET_TOKEN(HTYPE, 4_gc_init)(&h->gc); #ifndef IP_SET_PROTO_UNDEF else - IPSET_TOKEN(HTYPE, 6_gc_init)(set, - IPSET_TOKEN(HTYPE, 6_gc)); + IPSET_TOKEN(HTYPE, 6_gc_init)(&h->gc); #endif } pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index f8d2919cf9fd..037e8fce9b30 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -505,8 +505,8 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, static int nft_tunnel_ports_dump(struct sk_buff *skb, struct ip_tunnel_info *info) { - if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, htons(info->key.tp_src)) < 0 || - nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, htons(info->key.tp_dst)) < 0) + if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, info->key.tp_src) < 0 || + nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, info->key.tp_dst) < 0) return -1; return 0; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 6520d9ec1297..1b68a131083c 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -36,6 +36,7 @@ #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/mutex.h> #include <linux/kernel.h> +#include <linux/refcount.h> #include <uapi/linux/netfilter/xt_hashlimit.h> #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ @@ -114,7 +115,7 @@ struct dsthash_ent { struct xt_hashlimit_htable { struct hlist_node node; /* global list of all htables */ - int use; + refcount_t use; u_int8_t family; bool rnd_initialized; @@ -315,7 +316,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, for (i = 0; i < hinfo->cfg.size; i++) INIT_HLIST_HEAD(&hinfo->hash[i]); - hinfo->use = 1; + refcount_set(&hinfo->use, 1); hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; @@ -434,7 +435,7 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->name) && hinfo->family == family) { - hinfo->use++; + refcount_inc(&hinfo->use); return hinfo; } } @@ -443,12 +444,11 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, static void htable_put(struct xt_hashlimit_htable *hinfo) { - mutex_lock(&hashlimit_mutex); - if (--hinfo->use == 0) { + if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) { hlist_del(&hinfo->node); + mutex_unlock(&hashlimit_mutex); htable_destroy(hinfo); } - mutex_unlock(&hashlimit_mutex); } /* The algorithm used is the Simple Token Bucket Filter (TBF) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4e31721e7293..edf3e285e242 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1014,7 +1014,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nlk->netlink_bind && groups) { int group; - for (group = 0; group < nlk->ngroups; group++) { + /* nl_groups is a u32, so cap the maximum groups we can bind */ + for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); @@ -1033,7 +1034,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { - netlink_undo_bind(nlk->ngroups, groups, sk); + netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); goto unlock; } } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 7e54d2ab5254..d32d4233d337 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -305,6 +305,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_fl_filter *f; list_for_each_entry_rcu(mask, &head->masks, list) { + flow_dissector_init_keys(&skb_key.control, &skb_key.basic); fl_clear_masked_range(&skb_key, mask); skb_flow_dissect_meta(skb, &mask->dissector, &skb_key); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 4ab8208a2dd4..c6d83a64eac3 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -170,6 +170,16 @@ static inline bool sctp_chunk_length_valid(struct sctp_chunk *chunk, return true; } +/* Check for format error in an ABORT chunk */ +static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk) +{ + struct sctp_errhdr *err; + + sctp_walk_errors(err, chunk->chunk_hdr); + + return (void *)err == (void *)chunk->chunk_end; +} + /********************************************************** * These are the state functions for handling chunk events. **********************************************************/ @@ -2255,6 +2265,9 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2298,6 +2311,9 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Stop the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); @@ -2565,6 +2581,9 @@ enum sctp_disposition sctp_sf_do_9_1_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2582,16 +2601,8 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort( /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); - if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) { - struct sctp_errhdr *err; - - sctp_walk_errors(err, chunk->chunk_hdr); - if ((void *)err != (void *)chunk->chunk_end) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, - commands); - + if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) error = ((struct sctp_errhdr *)chunk->skb->data)->cause; - } sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET)); /* ASSOC_FAILED will DELETE_TCB. */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index cee5bf4a9bb9..90988a511cd5 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -470,6 +470,8 @@ static void smc_switch_to_fallback(struct smc_sock *smc) if (smc->sk.sk_socket && smc->sk.sk_socket->file) { smc->clcsock->file = smc->sk.sk_socket->file; smc->clcsock->file->private_data = smc->clcsock; + smc->clcsock->wq.fasync_list = + smc->sk.sk_socket->wq.fasync_list; } } diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 0879f7bed967..86cccc24e52e 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -372,7 +372,9 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline)); dclc.hdr.version = SMC_CLC_V1; dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0; - memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid)); + if (smc->conn.lgr && !smc->conn.lgr->is_smcd) + memcpy(dclc.id_for_peer, local_systemid, + sizeof(local_systemid)); dclc.peer_diagnosis = htonl(peer_diag_info); memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index f9b4fb92c0b1..693e8902161e 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2441,6 +2441,8 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) return -ETIMEDOUT; if (signal_pending(current)) return sock_intr_errno(*timeo_p); + if (sk->sk_state == TIPC_DISCONNECTING) + break; add_wait_queue(sk_sleep(sk), &wait); done = sk_wait_event(sk, timeo_p, tipc_sk_connected(sk), diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index cd91ad812291..e72d7d787935 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -592,7 +592,7 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn) { u64 record_sn = context->hint_record_sn; - struct tls_record_info *info; + struct tls_record_info *info, *last; info = context->retransmit_hint; if (!info || @@ -604,6 +604,24 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, struct tls_record_info, list); if (!info) return NULL; + /* send the start_marker record if seq number is before the + * tls offload start marker sequence number. This record is + * required to handle TCP packets which are before TLS offload + * started. + * And if it's not start marker, look if this seq number + * belongs to the list. + */ + if (likely(!tls_record_is_start_marker(info))) { + /* we have the first record, get the last record to see + * if this seq number belongs to the list. + */ + last = list_last_entry(&context->records_list, + struct tls_record_info, list); + + if (!between(seq, tls_record_start_seq(info), + last->end_seq)) + return NULL; + } record_sn = context->unacked_record_sn; } diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c index a9c0f368db5d..24e18405cdb4 100644 --- a/net/wireless/ethtool.c +++ b/net/wireless/ethtool.c @@ -7,9 +7,13 @@ void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct device *pdev = wiphy_dev(wdev->wiphy); - strlcpy(info->driver, wiphy_dev(wdev->wiphy)->driver->name, - sizeof(info->driver)); + if (pdev->driver) + strlcpy(info->driver, pdev->driver->name, + sizeof(info->driver)); + else + strlcpy(info->driver, "N/A", sizeof(info->driver)); strlcpy(info->version, init_utsname()->release, sizeof(info->version)); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 1e97ac5435b2..114397d737b3 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -437,6 +437,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT] = { .type = NLA_FLAG }, [NL80211_ATTR_CONTROL_PORT_OVER_NL80211] = { .type = NLA_FLAG }, [NL80211_ATTR_PRIVACY] = { .type = NLA_FLAG }, + [NL80211_ATTR_STATUS_CODE] = { .type = NLA_U16 }, [NL80211_ATTR_CIPHER_SUITE_GROUP] = { .type = NLA_U32 }, [NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 }, [NL80211_ATTR_PID] = { .type = NLA_U32 }, @@ -4799,8 +4800,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_he_obss_pd( info->attrs[NL80211_ATTR_HE_OBSS_PD], ¶ms.he_obss_pd); - if (err) - return err; + goto out; } nl80211_calculate_ap_params(¶ms); @@ -4822,6 +4822,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) } wdev_unlock(wdev); +out: kfree(params.acl); return err; diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 3fa32f83b2d7..a66fc0acad1e 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -291,13 +291,13 @@ DT_TMP_SCHEMA := $(objtree)/$(DT_BINDING_DIR)/processed-schema.yaml quiet_cmd_dtb_check = CHECK $@ cmd_dtb_check = $(DT_CHECKER) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ ; -define rule_dtc_dt_yaml +define rule_dtc $(call cmd_and_fixdep,dtc,yaml) $(call cmd,dtb_check) endef $(obj)/%.dt.yaml: $(src)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE - $(call if_changed_rule,dtc_dt_yaml) + $(call if_changed_rule,dtc) dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index ef8dfd47c7e3..0cac399ce713 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -263,7 +263,7 @@ static void ima_lsm_free_rule(struct ima_rule_entry *entry) static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) { struct ima_rule_entry *nentry; - int i, result; + int i; nentry = kmalloc(sizeof(*nentry), GFP_KERNEL); if (!nentry) @@ -277,7 +277,7 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) memset(nentry->lsm, 0, sizeof_field(struct ima_rule_entry, lsm)); for (i = 0; i < MAX_LSM_RULES; i++) { - if (!entry->lsm[i].rule) + if (!entry->lsm[i].args_p) continue; nentry->lsm[i].type = entry->lsm[i].type; @@ -286,13 +286,13 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) if (!nentry->lsm[i].args_p) goto out_err; - result = security_filter_rule_init(nentry->lsm[i].type, - Audit_equal, - nentry->lsm[i].args_p, - &nentry->lsm[i].rule); - if (result == -EINVAL) - pr_warn("ima: rule for LSM \'%d\' is undefined\n", - entry->lsm[i].type); + security_filter_rule_init(nentry->lsm[i].type, + Audit_equal, + nentry->lsm[i].args_p, + &nentry->lsm[i].rule); + if (!nentry->lsm[i].rule) + pr_warn("rule for LSM \'%s\' is undefined\n", + (char *)entry->lsm[i].args_p); } return nentry; @@ -329,7 +329,7 @@ static void ima_lsm_update_rules(void) list_for_each_entry_safe(entry, e, &ima_policy_rules, list) { needs_update = 0; for (i = 0; i < MAX_LSM_RULES; i++) { - if (entry->lsm[i].rule) { + if (entry->lsm[i].args_p) { needs_update = 1; break; } @@ -339,8 +339,7 @@ static void ima_lsm_update_rules(void) result = ima_lsm_update_rule(entry); if (result) { - pr_err("ima: lsm rule update error %d\n", - result); + pr_err("lsm rule update error %d\n", result); return; } } @@ -357,7 +356,7 @@ int ima_lsm_policy_change(struct notifier_block *nb, unsigned long event, } /** - * ima_match_rules - determine whether an inode matches the measure rule. + * ima_match_rules - determine whether an inode matches the policy rule. * @rule: a pointer to a rule * @inode: a pointer to an inode * @cred: a pointer to a credentials structure for user validation @@ -415,9 +414,12 @@ static bool ima_match_rules(struct ima_rule_entry *rule, struct inode *inode, int rc = 0; u32 osid; - if (!rule->lsm[i].rule) - continue; - + if (!rule->lsm[i].rule) { + if (!rule->lsm[i].args_p) + continue; + else + return false; + } switch (i) { case LSM_OBJ_USER: case LSM_OBJ_ROLE: @@ -823,8 +825,14 @@ static int ima_lsm_rule_init(struct ima_rule_entry *entry, entry->lsm[lsm_rule].args_p, &entry->lsm[lsm_rule].rule); if (!entry->lsm[lsm_rule].rule) { - kfree(entry->lsm[lsm_rule].args_p); - return -EINVAL; + pr_warn("rule for LSM \'%s\' is undefined\n", + (char *)entry->lsm[lsm_rule].args_p); + + if (ima_rules == &ima_default_rules) { + kfree(entry->lsm[lsm_rule].args_p); + result = -EINVAL; + } else + result = 0; } return result; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index de988589d99b..66cd97cc8b92 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -412,10 +412,10 @@ static int report__setup_sample_type(struct report *rep) PERF_SAMPLE_BRANCH_ANY)) rep->nonany_branch_mode = true; -#ifndef HAVE_LIBUNWIND_SUPPORT +#if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_DWARF_SUPPORT) if (dwarf_callchain_users) { - ui__warning("Please install libunwind development packages " - "during the perf build.\n"); + ui__warning("Please install libunwind or libdw " + "development packages during the perf build.\n"); } #endif diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index d4d3558fdef4..cfc6172ecab7 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -3062,6 +3062,7 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, continue; } + actions->ms.map = map; top = pstack__peek(browser->pstack); if (top == &browser->hists->dso_filter) { /* diff --git a/tools/perf/ui/gtk/Build b/tools/perf/ui/gtk/Build index ec22e899a224..9b5d5cbb7af7 100644 --- a/tools/perf/ui/gtk/Build +++ b/tools/perf/ui/gtk/Build @@ -7,3 +7,8 @@ gtk-y += util.o gtk-y += helpline.o gtk-y += progress.o gtk-y += annotate.o +gtk-y += zalloc.o + +$(OUTPUT)ui/gtk/zalloc.o: ../lib/zalloc.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index fdd5bddb3075..f67960bedebb 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -549,6 +549,7 @@ void maps__insert(struct maps *maps, struct map *map) if (maps_by_name == NULL) { __maps__free_maps_by_name(maps); + up_write(&maps->lock); return; } diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index cd1f5b3a7774..d6e106fbce11 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -2,7 +2,7 @@ all: TEST_PROGS := ftracetest -TEST_FILES := test.d +TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* include ../lib.mk diff --git a/tools/testing/selftests/livepatch/Makefile b/tools/testing/selftests/livepatch/Makefile index 3876d8d62494..1acc9e1fa3fb 100644 --- a/tools/testing/selftests/livepatch/Makefile +++ b/tools/testing/selftests/livepatch/Makefile @@ -8,4 +8,6 @@ TEST_PROGS := \ test-state.sh \ test-ftrace.sh +TEST_FILES := settings + include ../lib.mk diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 6dd403103800..60273f1bc7d9 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -910,6 +910,12 @@ ipv6_rt_replace_mpath() check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" log_test $? 0 "Multipath with single path via multipath attribute" + # multipath with dev-only + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1" + check_route6 "2001:db8:104::/64 dev veth1 metric 1024" + log_test $? 0 "Multipath with dev-only" + # route replace fails - invalid nexthop 1 add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3" diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index d6469535630a..f1053630bb6f 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -19,6 +19,8 @@ TEST_GEN_PROGS_EXTENDED = librseq.so TEST_PROGS = run_param_test.sh +TEST_FILES := settings + include ../lib.mk $(OUTPUT)/librseq.so: rseq.c rseq.h rseq-*.h diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile index de9c8566672a..90fa1a346908 100644 --- a/tools/testing/selftests/rtc/Makefile +++ b/tools/testing/selftests/rtc/Makefile @@ -6,4 +6,6 @@ TEST_GEN_PROGS = rtctest TEST_GEN_PROGS_EXTENDED = setdate +TEST_FILES := settings + include ../lib.mk diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2b3f36df3d85..75b7ee1af1c3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2287,12 +2287,12 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, if (slots->generation != ghc->generation) __kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len); - if (unlikely(!ghc->memslot)) - return kvm_write_guest(kvm, gpa, data, len); - if (kvm_is_error_hva(ghc->hva)) return -EFAULT; + if (unlikely(!ghc->memslot)) + return kvm_write_guest(kvm, gpa, data, len); + r = __copy_to_user((void __user *)ghc->hva + offset, data, len); if (r) return -EFAULT; @@ -2320,12 +2320,12 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, if (slots->generation != ghc->generation) __kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len); - if (unlikely(!ghc->memslot)) - return kvm_read_guest(kvm, ghc->gpa, data, len); - if (kvm_is_error_hva(ghc->hva)) return -EFAULT; + if (unlikely(!ghc->memslot)) + return kvm_read_guest(kvm, ghc->gpa, data, len); + r = __copy_from_user(data, (void __user *)ghc->hva, len); if (r) return -EFAULT;