diff options
183 files changed, 2724 insertions, 1148 deletions
diff --git a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml index a1b71b35319e..42f9843d1868 100644 --- a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml +++ b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml @@ -38,6 +38,10 @@ properties: managed: true + phys: + description: A reference to the SerDes lane(s) + maxItems: 1 + required: - reg diff --git a/Documentation/filesystems/caching/fscache.rst b/Documentation/filesystems/caching/fscache.rst index a74d7b052dc1..de1f32526cc1 100644 --- a/Documentation/filesystems/caching/fscache.rst +++ b/Documentation/filesystems/caching/fscache.rst @@ -318,10 +318,10 @@ where the columns are: Debugging ========= -If CONFIG_FSCACHE_DEBUG is enabled, the FS-Cache facility can have runtime -debugging enabled by adjusting the value in:: +If CONFIG_NETFS_DEBUG is enabled, the FS-Cache facility and NETFS support can +have runtime debugging enabled by adjusting the value in:: - /sys/module/fscache/parameters/debug + /sys/module/netfs/parameters/debug This is a bitmask of debugging streams to enable: @@ -343,6 +343,6 @@ This is a bitmask of debugging streams to enable: The appropriate set of values should be OR'd together and the result written to the control file. For example:: - echo $((1|8|512)) >/sys/module/fscache/parameters/debug + echo $((1|8|512)) >/sys/module/netfs/parameters/debug will turn on all function entry debugging. diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 33938468d62d..b3be87489108 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -2592,7 +2592,7 @@ Specifically: 0x6030 0000 0010 004a SPSR_ABT 64 spsr[KVM_SPSR_ABT] 0x6030 0000 0010 004c SPSR_UND 64 spsr[KVM_SPSR_UND] 0x6030 0000 0010 004e SPSR_IRQ 64 spsr[KVM_SPSR_IRQ] - 0x6060 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ] + 0x6030 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ] 0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] [1]_ 0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] [1]_ ... diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h index d81bac256abc..6199c9f7ec6e 100644 --- a/arch/arm64/include/asm/kvm_ptrauth.h +++ b/arch/arm64/include/asm/kvm_ptrauth.h @@ -104,7 +104,7 @@ alternative_else_nop_endif #define __ptrauth_save_key(ctxt, key) \ do { \ - u64 __val; \ + u64 __val; \ __val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \ ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val; \ __val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \ diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 58f09370d17e..8304eb342be9 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -19,6 +19,7 @@ if VIRTUALIZATION menuconfig KVM bool "Kernel-based Virtual Machine (KVM) support" + depends on AS_HAS_ARMV8_4 select KVM_COMMON select KVM_GENERIC_HARDWARE_ENABLING select KVM_GENERIC_MMU_NOTIFIER diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index a6497228c5a8..86a629aaf0a1 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -10,6 +10,9 @@ include $(srctree)/virt/kvm/Makefile.kvm obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM) += hyp/ +CFLAGS_sys_regs.o += -Wno-override-init +CFLAGS_handle_exit.o += -Wno-override-init + kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o stacktrace.o \ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index a7ca776b51ec..9bef7638342e 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -164,6 +164,7 @@ static int kvm_arm_default_max_vcpus(void) /** * kvm_arch_init_vm - initializes a VM data structure * @kvm: pointer to the KVM struct + * @type: kvm device type */ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { @@ -521,10 +522,10 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu) { - if (vcpu_has_ptrauth(vcpu)) { + if (vcpu_has_ptrauth(vcpu) && !is_protected_kvm_enabled()) { /* - * Either we're running running an L2 guest, and the API/APK - * bits come from L1's HCR_EL2, or API/APK are both set. + * Either we're running an L2 guest, and the API/APK bits come + * from L1's HCR_EL2, or API/APK are both set. */ if (unlikely(vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) { u64 val; @@ -541,16 +542,10 @@ static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu) * Save the host keys if there is any chance for the guest * to use pauth, as the entry code will reload the guest * keys in that case. - * Protected mode is the exception to that rule, as the - * entry into the EL2 code eagerly switch back and forth - * between host and hyp keys (and kvm_hyp_ctxt is out of - * reach anyway). */ - if (is_protected_kvm_enabled()) - return; - if (vcpu->arch.hcr_el2 & (HCR_API | HCR_APK)) { struct kvm_cpu_context *ctxt; + ctxt = this_cpu_ptr_hyp_sym(kvm_hyp_ctxt); ptrauth_save_keys(ctxt); } diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index f59ccfe11ab9..37ff87d782b6 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -27,7 +27,6 @@ #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/kvm_nested.h> -#include <asm/kvm_ptrauth.h> #include <asm/fpsimd.h> #include <asm/debug-monitors.h> #include <asm/processor.h> diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index 782b34b004be..b43426a493df 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -20,6 +20,8 @@ HOST_EXTRACFLAGS += -I$(objtree)/include lib-objs := clear_page.o copy_page.o memcpy.o memset.o lib-objs := $(addprefix ../../../lib/, $(lib-objs)) +CFLAGS_switch.nvhe.o += -Wno-override-init + hyp-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \ hyp-main.o hyp-smp.o psci-relay.o early_alloc.o page_alloc.o \ cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o stacktrace.o ffa.o diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 6af179c6356d..8f5c56d5b1cd 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -173,9 +173,8 @@ static void __pmu_switch_to_host(struct kvm_vcpu *vcpu) static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code) { /* - * Make sure we handle the exit for workarounds and ptrauth - * before the pKVM handling, as the latter could decide to - * UNDEF. + * Make sure we handle the exit for workarounds before the pKVM + * handling, as the latter could decide to UNDEF. */ return (kvm_hyp_handle_sysreg(vcpu, exit_code) || kvm_handle_pvm_sysreg(vcpu, exit_code)); diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile index 3b9e5464b5b3..afc4aed9231a 100644 --- a/arch/arm64/kvm/hyp/vhe/Makefile +++ b/arch/arm64/kvm/hyp/vhe/Makefile @@ -6,6 +6,8 @@ asflags-y := -D__KVM_VHE_HYPERVISOR__ ccflags-y := -D__KVM_VHE_HYPERVISOR__ +CFLAGS_switch.o += -Wno-override-init + obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ ../fpsimd.o ../hyp-entry.o ../exception.o diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index de789e0f1ae9..bab27f9d8cc6 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -786,7 +786,7 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) if (!WARN_ON(atomic_read(&mmu->refcnt))) kvm_free_stage2_pgd(mmu); } - kfree(kvm->arch.nested_mmus); + kvfree(kvm->arch.nested_mmus); kvm->arch.nested_mmus = NULL; kvm->arch.nested_mmus_size = 0; kvm_uninit_stage2_mmu(kvm); diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index bcbc8c986b1d..bc74d06398ef 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -45,7 +45,8 @@ static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter) * Let the xarray drive the iterator after the last SPI, as the iterator * has exhausted the sequentially-allocated INTID space. */ - if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1)) { + if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1) && + iter->nr_lpis) { if (iter->lpi_idx < iter->nr_lpis) xa_find_after(&dist->lpi_xa, &iter->intid, VGIC_LPI_MAX_INTID, @@ -112,7 +113,7 @@ static bool end_of_vgic(struct vgic_state_iter *iter) return iter->dist_id > 0 && iter->vcpu_id == iter->nr_cpus && iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS) && - iter->lpi_idx > iter->nr_lpis; + (!iter->nr_lpis || iter->lpi_idx > iter->nr_lpis); } static void *vgic_debug_start(struct seq_file *s, loff_t *pos) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 7f68cf58b978..41feb858ff9a 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -438,14 +438,13 @@ void kvm_vgic_destroy(struct kvm *kvm) unsigned long i; mutex_lock(&kvm->slots_lock); + mutex_lock(&kvm->arch.config_lock); vgic_debug_destroy(kvm); kvm_for_each_vcpu(i, vcpu, kvm) __kvm_vgic_vcpu_destroy(vcpu); - mutex_lock(&kvm->arch.config_lock); - kvm_vgic_dist_destroy(kvm); mutex_unlock(&kvm->arch.config_lock); diff --git a/arch/arm64/kvm/vgic/vgic-irqfd.c b/arch/arm64/kvm/vgic/vgic-irqfd.c index 8c711deb25aa..c314c016659a 100644 --- a/arch/arm64/kvm/vgic/vgic-irqfd.c +++ b/arch/arm64/kvm/vgic/vgic-irqfd.c @@ -9,7 +9,7 @@ #include <kvm/arm_vgic.h> #include "vgic.h" -/** +/* * vgic_irqfd_set_irq: inject the IRQ corresponding to the * irqchip routing entry * @@ -75,7 +75,8 @@ static void kvm_populate_msi(struct kvm_kernel_irq_routing_entry *e, msi->flags = e->msi.flags; msi->devid = e->msi.devid; } -/** + +/* * kvm_set_msi: inject the MSI corresponding to the * MSI routing entry * @@ -98,7 +99,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, return vgic_its_inject_msi(kvm, &msi); } -/** +/* * kvm_arch_set_irq_inatomic: fast-path for irqfd injection */ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 40bb43f20bf3..ba945ba78cc7 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2040,6 +2040,7 @@ typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry, * @start_id: the ID of the first entry in the table * (non zero for 2d level tables) * @fn: function to apply on each entry + * @opaque: pointer to opaque data * * Return: < 0 on error, 0 if last element was identified, 1 otherwise * (the last element may not be found on second level tables) @@ -2079,7 +2080,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, return 1; } -/** +/* * vgic_its_save_ite - Save an interrupt translation entry at @gpa */ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, @@ -2099,6 +2100,8 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, /** * vgic_its_restore_ite - restore an interrupt translation entry + * + * @its: its handle * @event_id: id used for indexing * @ptr: pointer to the ITE entry * @opaque: pointer to the its_device @@ -2231,6 +2234,7 @@ static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev) * @its: ITS handle * @dev: ITS device * @ptr: GPA + * @dte_esz: device table entry size */ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, gpa_t ptr, int dte_esz) @@ -2313,7 +2317,7 @@ static int vgic_its_device_cmp(void *priv, const struct list_head *a, return 1; } -/** +/* * vgic_its_save_device_tables - Save the device table and all ITT * into guest RAM * @@ -2386,7 +2390,7 @@ static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr, return ret; } -/** +/* * vgic_its_restore_device_tables - Restore the device table and all ITT * from guest RAM to internal data structs */ @@ -2478,7 +2482,7 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) return 1; } -/** +/* * vgic_its_save_collection_table - Save the collection table into * guest RAM */ @@ -2518,7 +2522,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its) return ret; } -/** +/* * vgic_its_restore_collection_table - reads the collection table * in guest memory and restores the ITS internal state. Requires the * BASER registers to be restored before. @@ -2556,7 +2560,7 @@ static int vgic_its_restore_collection_table(struct vgic_its *its) return ret; } -/** +/* * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM * according to v0 ABI */ @@ -2571,7 +2575,7 @@ static int vgic_its_save_tables_v0(struct vgic_its *its) return vgic_its_save_collection_table(its); } -/** +/* * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM * to internal data structs according to V0 ABI * diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index ed6e412cd74b..3eecdd2f4b8f 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -370,7 +370,7 @@ static void map_all_vpes(struct kvm *kvm) dist->its_vm.vpes[i]->irq)); } -/** +/* * vgic_v3_save_pending_tables - Save the pending tables into guest RAM * kvm lock and all vcpu lock must be held */ diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index f07b3ddff7d4..974849ea7101 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -313,7 +313,7 @@ static bool vgic_validate_injection(struct vgic_irq *irq, bool level, void *owne * with all locks dropped. */ bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, - unsigned long flags) + unsigned long flags) __releases(&irq->irq_lock) { struct kvm_vcpu *vcpu; diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 03d356a12377..ba8f790431bd 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -186,7 +186,7 @@ bool vgic_get_phys_line_level(struct vgic_irq *irq); void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending); void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active); bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, - unsigned long flags); + unsigned long flags) __releases(&irq->irq_lock); void vgic_kick_vcpus(struct kvm *kvm); void vgic_irq_handle_resampling(struct vgic_irq *irq, bool lr_deactivated, bool lr_pending); diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 0b5f8f3e84f1..153d93468b77 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -441,7 +441,10 @@ static inline int share(unsigned long addr, u16 cmd) if (!uv_call(0, (u64)&uvcb)) return 0; - return -EINVAL; + pr_err("%s UVC failed (rc: 0x%x, rrc: 0x%x), possible hypervisor bug.\n", + uvcb.header.cmd == UVC_CMD_SET_SHARED_ACCESS ? "Share" : "Unshare", + uvcb.header.rc, uvcb.header.rrc); + panic("System security cannot be guaranteed unless the system panics now.\n"); } /* diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index bf8534218af3..e680c6bf0c9d 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -267,7 +267,12 @@ static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots) static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm) { - u32 gd = virt_to_phys(kvm->arch.gisa_int.origin); + u32 gd; + + if (!kvm->arch.gisa_int.origin) + return 0; + + gd = virt_to_phys(kvm->arch.gisa_int.origin); if (gd && sclp.has_gisaf) gd |= GISA_FORMAT1; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 94e7b5a4fafe..4a68cb3eba78 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2192,6 +2192,8 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, #define kvm_arch_has_private_mem(kvm) false #endif +#define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state) + static inline u16 kvm_read_ldt(void) { u16 ldt; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 923e64903da9..913bfc96959c 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -286,7 +286,6 @@ static inline int kvm_hv_hypercall(struct kvm_vcpu *vcpu) return HV_STATUS_ACCESS_DENIED; } static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) {} -static inline void kvm_hv_free_pa_page(struct kvm *kvm) {} static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector) { return false; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4915acdbfcd8..5bb481aefcbc 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -351,10 +351,8 @@ static void kvm_recalculate_logical_map(struct kvm_apic_map *new, * reversing the LDR calculation to get cluster of APICs, i.e. no * additional work is required. */ - if (apic_x2apic_mode(apic)) { - WARN_ON_ONCE(ldr != kvm_apic_calc_x2apic_ldr(kvm_x2apic_id(apic))); + if (apic_x2apic_mode(apic)) return; - } if (WARN_ON_ONCE(!kvm_apic_map_get_logical_dest(new, ldr, &cluster, &mask))) { @@ -2966,18 +2964,28 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s, bool set) { if (apic_x2apic_mode(vcpu->arch.apic)) { + u32 x2apic_id = kvm_x2apic_id(vcpu->arch.apic); u32 *id = (u32 *)(s->regs + APIC_ID); u32 *ldr = (u32 *)(s->regs + APIC_LDR); u64 icr; if (vcpu->kvm->arch.x2apic_format) { - if (*id != vcpu->vcpu_id) + if (*id != x2apic_id) return -EINVAL; } else { + /* + * Ignore the userspace value when setting APIC state. + * KVM's model is that the x2APIC ID is readonly, e.g. + * KVM only supports delivering interrupts to KVM's + * version of the x2APIC ID. However, for backwards + * compatibility, don't reject attempts to set a + * mismatched ID for userspace that hasn't opted into + * x2apic_format. + */ if (set) - *id >>= 24; + *id = x2apic_id; else - *id <<= 24; + *id = x2apic_id << 24; } /* @@ -2986,7 +2994,7 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, * split to ICR+ICR2 in userspace for backwards compatibility. */ if (set) { - *ldr = kvm_apic_calc_x2apic_ldr(*id); + *ldr = kvm_apic_calc_x2apic_ldr(x2apic_id); icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) | (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 532df12b43c5..714c517dd4b7 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2276,7 +2276,7 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pf for (gfn = gfn_start, i = 0; gfn < gfn_start + npages; gfn++, i++) { struct sev_data_snp_launch_update fw_args = {0}; - bool assigned; + bool assigned = false; int level; ret = snp_lookup_rmpentry((u64)pfn + i, &assigned, &level); @@ -2290,9 +2290,10 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pf if (src) { void *vaddr = kmap_local_pfn(pfn + i); - ret = copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE); - if (ret) + if (copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE)) { + ret = -EFAULT; goto err; + } kunmap_local(vaddr); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ef3d3511e4af..70219e406987 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -427,8 +427,7 @@ static void kvm_user_return_msr_cpu_online(void) int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) { - unsigned int cpu = smp_processor_id(); - struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); int err; value = (value & mask) | (msrs->values[slot].host & ~mask); @@ -450,8 +449,7 @@ EXPORT_SYMBOL_GPL(kvm_set_user_return_msr); static void drop_user_return_notifiers(void) { - unsigned int cpu = smp_processor_id(); - struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); if (msrs->registered) kvm_on_user_return(&msrs->urn); diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index d6f5e25e1ed8..473e00a58a8b 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -951,8 +951,19 @@ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc) &sense_key, &asc, &ascq); ata_scsi_set_sense(qc->dev, cmd, sense_key, asc, ascq); } else { - /* ATA PASS-THROUGH INFORMATION AVAILABLE */ - ata_scsi_set_sense(qc->dev, cmd, RECOVERED_ERROR, 0, 0x1D); + /* + * ATA PASS-THROUGH INFORMATION AVAILABLE + * + * Note: we are supposed to call ata_scsi_set_sense(), which + * respects the D_SENSE bit, instead of unconditionally + * generating the sense data in descriptor format. However, + * because hdparm, hddtemp, and udisks incorrectly assume sense + * data in descriptor format, without even looking at the + * RESPONSE CODE field in the returned sense data (to see which + * format the returned sense data is in), we are stuck with + * being bug compatible with older kernels. + */ + scsi_build_sense(cmd, 1, RECOVERED_ERROR, 0, 0x1D); } } diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index e7f713cd70d3..a876024d8a05 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) rpp->len += skb->len; if (stat & SAR_RSQE_EPDU) { + unsigned int len, truesize; unsigned char *l1l2; - unsigned int len; l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6); @@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) ATM_SKB(skb)->vcc = vcc; __net_timestamp(skb); + truesize = skb->truesize; vcc->push(vcc, skb); atomic_inc(&vcc->stats->rx); - if (skb->truesize > SAR_FB_SIZE_3) + if (truesize > SAR_FB_SIZE_3) add_rx_skb(card, 3, SAR_FB_SIZE_3, 1); - else if (skb->truesize > SAR_FB_SIZE_2) + else if (truesize > SAR_FB_SIZE_2) add_rx_skb(card, 2, SAR_FB_SIZE_2, 1); - else if (skb->truesize > SAR_FB_SIZE_1) + else if (truesize > SAR_FB_SIZE_1) add_rx_skb(card, 1, SAR_FB_SIZE_1, 1); else add_rx_skb(card, 0, SAR_FB_SIZE_0, 1); diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c index 22d83ac18eb7..fbf58012becd 100644 --- a/drivers/media/usb/dvb-usb/dvb-usb-init.c +++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c @@ -23,40 +23,11 @@ static int dvb_usb_force_pid_filter_usage; module_param_named(force_pid_filter_usage, dvb_usb_force_pid_filter_usage, int, 0444); MODULE_PARM_DESC(force_pid_filter_usage, "force all dvb-usb-devices to use a PID filter, if any (default: 0)."); -static int dvb_usb_check_bulk_endpoint(struct dvb_usb_device *d, u8 endpoint) -{ - if (endpoint) { - int ret; - - ret = usb_pipe_type_check(d->udev, usb_sndbulkpipe(d->udev, endpoint)); - if (ret) - return ret; - ret = usb_pipe_type_check(d->udev, usb_rcvbulkpipe(d->udev, endpoint)); - if (ret) - return ret; - } - return 0; -} - -static void dvb_usb_clear_halt(struct dvb_usb_device *d, u8 endpoint) -{ - if (endpoint) { - usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, endpoint)); - usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, endpoint)); - } -} - static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs) { struct dvb_usb_adapter *adap; int ret, n, o; - ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint); - if (ret) - return ret; - ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint_response); - if (ret) - return ret; for (n = 0; n < d->props.num_adapters; n++) { adap = &d->adapter[n]; adap->dev = d; @@ -132,8 +103,10 @@ static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs) * when reloading the driver w/o replugging the device * sometimes a timeout occurs, this helps */ - dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint); - dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint_response); + if (d->props.generic_bulk_ctrl_endpoint != 0) { + usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint)); + usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint)); + } return 0; diff --git a/drivers/misc/lkdtm/refcount.c b/drivers/misc/lkdtm/refcount.c index 5cd488f54cfa..8f744bee6fbd 100644 --- a/drivers/misc/lkdtm/refcount.c +++ b/drivers/misc/lkdtm/refcount.c @@ -182,6 +182,21 @@ static void lkdtm_REFCOUNT_SUB_AND_TEST_NEGATIVE(void) check_negative(&neg, 3); } +/* + * A refcount_sub_and_test() by zero when the counter is at zero should act like + * refcount_sub_and_test() above when going negative. + */ +static void lkdtm_REFCOUNT_SUB_AND_TEST_ZERO(void) +{ + refcount_t neg = REFCOUNT_INIT(0); + + pr_info("attempting bad refcount_sub_and_test() at zero\n"); + if (refcount_sub_and_test(0, &neg)) + pr_warn("Weird: refcount_sub_and_test() reported zero\n"); + + check_negative(&neg, 0); +} + static void check_from_zero(refcount_t *ref) { switch (refcount_read(ref)) { @@ -400,6 +415,7 @@ static struct crashtype crashtypes[] = { CRASHTYPE(REFCOUNT_DEC_NEGATIVE), CRASHTYPE(REFCOUNT_DEC_AND_TEST_NEGATIVE), CRASHTYPE(REFCOUNT_SUB_AND_TEST_NEGATIVE), + CRASHTYPE(REFCOUNT_SUB_AND_TEST_ZERO), CRASHTYPE(REFCOUNT_INC_ZERO), CRASHTYPE(REFCOUNT_ADD_ZERO), CRASHTYPE(REFCOUNT_INC_SATURATED), diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index d9d3e30fd47a..e3f95d2cc2c1 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -40,6 +40,10 @@ #define VSC73XX_BLOCK_ARBITER 0x5 /* Only subblock 0 */ #define VSC73XX_BLOCK_SYSTEM 0x7 /* Only subblock 0 */ +/* MII Block subblock */ +#define VSC73XX_BLOCK_MII_INTERNAL 0x0 /* Internal MDIO subblock */ +#define VSC73XX_BLOCK_MII_EXTERNAL 0x1 /* External MDIO subblock */ + #define CPU_PORT 6 /* CPU port */ /* MAC Block registers */ @@ -225,6 +229,8 @@ #define VSC73XX_MII_CMD 0x1 #define VSC73XX_MII_DATA 0x2 +#define VSC73XX_MII_STAT_BUSY BIT(3) + /* Arbiter block 5 registers */ #define VSC73XX_ARBEMPTY 0x0c #define VSC73XX_ARBDISC 0x0e @@ -299,6 +305,7 @@ #define IS_739X(a) (IS_7395(a) || IS_7398(a)) #define VSC73XX_POLL_SLEEP_US 1000 +#define VSC73XX_MDIO_POLL_SLEEP_US 5 #define VSC73XX_POLL_TIMEOUT_US 10000 struct vsc73xx_counter { @@ -527,6 +534,22 @@ static int vsc73xx_detect(struct vsc73xx *vsc) return 0; } +static int vsc73xx_mdio_busy_check(struct vsc73xx *vsc) +{ + int ret, err; + u32 val; + + ret = read_poll_timeout(vsc73xx_read, err, + err < 0 || !(val & VSC73XX_MII_STAT_BUSY), + VSC73XX_MDIO_POLL_SLEEP_US, + VSC73XX_POLL_TIMEOUT_US, false, vsc, + VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_STAT, &val); + if (ret) + return ret; + return err; +} + static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum) { struct vsc73xx *vsc = ds->priv; @@ -534,12 +557,20 @@ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum) u32 val; int ret; + ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; + /* Setting bit 26 means "read" */ cmd = BIT(26) | (phy << 21) | (regnum << 16); ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); if (ret) return ret; - msleep(2); + + ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; + ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val); if (ret) return ret; @@ -563,18 +594,11 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum, u32 cmd; int ret; - /* It was found through tedious experiments that this router - * chip really hates to have it's PHYs reset. They - * never recover if that happens: autonegotiation stops - * working after a reset. Just filter out this command. - * (Resetting the whole chip is OK.) - */ - if (regnum == 0 && (val & BIT(15))) { - dev_info(vsc->dev, "reset PHY - disallowed\n"); - return 0; - } + ret = vsc73xx_mdio_busy_check(vsc); + if (ret) + return ret; - cmd = (phy << 21) | (regnum << 16); + cmd = (phy << 21) | (regnum << 16) | val; ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); if (ret) return ret; @@ -957,6 +981,11 @@ static void vsc73xx_mac_link_up(struct phylink_config *config, if (duplex == DUPLEX_FULL) val |= VSC73XX_MAC_CFG_FDX; + else + /* In datasheet description ("Port Mode Procedure" in 5.6.2) + * this bit is configured only for half duplex. + */ + val |= VSC73XX_MAC_CFG_WEXC_DIS; /* This routine is described in the datasheet (below ARBDISC register * description) @@ -967,7 +996,6 @@ static void vsc73xx_mac_link_up(struct phylink_config *config, get_random_bytes(&seed, 1); val |= seed << VSC73XX_MAC_CFG_SEED_OFFSET; val |= VSC73XX_MAC_CFG_SEED_LOAD; - val |= VSC73XX_MAC_CFG_WEXC_DIS; /* Those bits are responsible for MTU only. Kernel takes care about MTU, * let's enable +8 bytes frame length unconditionally. diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 11665be3a22c..dcd3f54ed0cf 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5250,8 +5250,8 @@ static int __maybe_unused macb_suspend(struct device *dev) if (bp->wol & MACB_WOL_ENABLED) { /* Check for IP address in WOL ARP mode */ idev = __in_dev_get_rcu(bp->dev); - if (idev && idev->ifa_list) - ifa = rcu_access_pointer(idev->ifa_list); + if (idev) + ifa = rcu_dereference(idev->ifa_list); if ((bp->wolopts & WAKE_ARP) && !ifa) { netdev_err(netdev, "IP address not assigned as required by WoL walk ARP\n"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index a40c266c37f2..608cc6af5af1 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1054,18 +1054,12 @@ static int phy_interface_mode(u8 lmac_type) static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid) { - struct lmac *lmac, **priv; + struct lmac *lmac; u64 cfg; lmac = &bgx->lmac[lmacid]; lmac->bgx = bgx; - lmac->netdev = alloc_netdev_dummy(sizeof(struct lmac *)); - if (!lmac->netdev) - return -ENOMEM; - priv = netdev_priv(lmac->netdev); - *priv = lmac; - if ((lmac->lmac_type == BGX_MODE_SGMII) || (lmac->lmac_type == BGX_MODE_QSGMII) || (lmac->lmac_type == BGX_MODE_RGMII)) { @@ -1191,7 +1185,6 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid) (lmac->lmac_type != BGX_MODE_10G_KR) && lmac->phydev) phy_disconnect(lmac->phydev); - free_netdev(lmac->netdev); lmac->phydev = NULL; } @@ -1653,6 +1646,23 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) bgx_get_qlm_mode(bgx); + for (lmac = 0; lmac < bgx->lmac_count; lmac++) { + struct lmac *lmacp, **priv; + + lmacp = &bgx->lmac[lmac]; + lmacp->netdev = alloc_netdev_dummy(sizeof(struct lmac *)); + + if (!lmacp->netdev) { + for (int i = 0; i < lmac; i++) + free_netdev(bgx->lmac[i].netdev); + err = -ENOMEM; + goto err_enable; + } + + priv = netdev_priv(lmacp->netdev); + *priv = lmacp; + } + err = bgx_init_phy(bgx); if (err) goto err_enable; @@ -1692,8 +1702,10 @@ static void bgx_remove(struct pci_dev *pdev) u8 lmac; /* Disable all LMACs */ - for (lmac = 0; lmac < bgx->lmac_count; lmac++) + for (lmac = 0; lmac < bgx->lmac_count; lmac++) { bgx_lmac_disable(bgx, lmac); + free_netdev(bgx->lmac[lmac].netdev); + } pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index a5fc0209d628..4cbc4d069a1f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5724,6 +5724,9 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) struct net_device *netdev = handle->kinfo.netdev; struct hns3_nic_priv *priv = netdev_priv(netdev); + if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + hns3_nic_net_stop(netdev); + if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) { netdev_warn(netdev, "already uninitialized\n"); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index e132c2f09560..cc7f46c0b35f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -1598,8 +1598,7 @@ static void hclge_query_reg_info_of_ssu(struct hclge_dev *hdev) { u32 loop_para[HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE] = {0}; struct hclge_mod_reg_common_msg msg; - u8 i, j, num; - u32 loop_time; + u8 i, j, num, loop_time; num = ARRAY_SIZE(hclge_ssu_reg_common_msg); for (i = 0; i < num; i++) { @@ -1609,7 +1608,8 @@ static void hclge_query_reg_info_of_ssu(struct hclge_dev *hdev) loop_time = 1; loop_para[0] = 0; if (msg.need_para) { - loop_time = hdev->ae_dev->dev_specs.tnl_num; + loop_time = min(hdev->ae_dev->dev_specs.tnl_num, + HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE); for (j = 0; j < loop_time; j++) loop_para[j] = j + 1; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 82574ce0194f..6c33195a1168 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2653,8 +2653,17 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed, { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; + int ret; + + ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num); + + if (ret) + return ret; - return hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num); + hdev->hw.mac.req_speed = speed; + hdev->hw.mac.req_duplex = duplex; + + return 0; } static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable) @@ -2956,17 +2965,20 @@ static int hclge_mac_init(struct hclge_dev *hdev) if (!test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) hdev->hw.mac.duplex = HCLGE_MAC_FULL; - ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, - hdev->hw.mac.duplex, hdev->hw.mac.lane_num); - if (ret) - return ret; - if (hdev->hw.mac.support_autoneg) { ret = hclge_set_autoneg_en(hdev, hdev->hw.mac.autoneg); if (ret) return ret; } + if (!hdev->hw.mac.autoneg) { + ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.req_speed, + hdev->hw.mac.req_duplex, + hdev->hw.mac.lane_num); + if (ret) + return ret; + } + mac->link = 0; if (mac->user_fec_mode & BIT(HNAE3_FEC_USER_DEF)) { @@ -11444,7 +11456,7 @@ static void hclge_pci_uninit(struct hclge_dev *hdev) pcim_iounmap(pdev, hdev->hw.hw.io_base); pci_free_irq_vectors(pdev); - pci_release_mem_regions(pdev); + pci_release_regions(pdev); pci_disable_device(pdev); } @@ -11516,8 +11528,8 @@ static void hclge_reset_done(struct hnae3_ae_dev *ae_dev) dev_err(&hdev->pdev->dev, "fail to rebuild, ret=%d\n", ret); hdev->reset_type = HNAE3_NONE_RESET; - clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state); - up(&hdev->reset_sem); + if (test_and_clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + up(&hdev->reset_sem); } static void hclge_clear_resetting_state(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 85fb11de43a1..80079657afeb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -191,6 +191,9 @@ static void hclge_mac_adjust_link(struct net_device *netdev) if (ret) netdev_err(netdev, "failed to adjust link.\n"); + hdev->hw.mac.req_speed = (u32)speed; + hdev->hw.mac.req_duplex = (u8)duplex; + ret = hclge_cfg_flowctrl(hdev); if (ret) netdev_err(netdev, "failed to configure flow control.\n"); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 3735d2fed11f..094a7c7b5592 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1747,8 +1747,8 @@ static void hclgevf_reset_done(struct hnae3_ae_dev *ae_dev) ret); hdev->reset_type = HNAE3_NONE_RESET; - clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state); - up(&hdev->reset_sem); + if (test_and_clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) + up(&hdev->reset_sem); } static u32 hclgevf_get_fw_version(struct hnae3_handle *handle) diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 5f92b3c7c3d4..511384f3ec5c 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -404,6 +404,12 @@ #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ +/* Retry Buffer Control */ +#define IGC_RETX_CTL 0x041C +#define IGC_RETX_CTL_WATERMARK_MASK 0xF +#define IGC_RETX_CTL_QBVFULLTH_SHIFT 8 /* QBV Retry Buffer Full Threshold */ +#define IGC_RETX_CTL_QBVFULLEN 0x1000 /* Enable QBV Retry Buffer Full Threshold */ + /* Transmit Scheduling Latency */ /* Latency between transmission scheduling (LaunchTime) and the time * the packet is transmitted to the network in nanosecond. diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 8daf938afc36..dfd6c00b4205 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6315,12 +6315,16 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, if (!validate_schedule(adapter, qopt)) return -EINVAL; + igc_ptp_read(adapter, &now); + + if (igc_tsn_is_taprio_activated_by_user(adapter) && + is_base_time_past(qopt->base_time, &now)) + adapter->qbv_config_change_errors++; + adapter->cycle_time = qopt->cycle_time; adapter->base_time = qopt->base_time; adapter->taprio_offload_enable = true; - igc_ptp_read(adapter, &now); - for (n = 0; n < qopt->num_entries; n++) { struct tc_taprio_sched_entry *e = &qopt->entries[n]; diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 22cefb1eeedf..d68fa7f3d5f0 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -49,12 +49,19 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter) return new_flags; } +static bool igc_tsn_is_tx_mode_in_tsn(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return !!(rd32(IGC_TQAVCTRL) & IGC_TQAVCTRL_TRANSMIT_MODE_TSN); +} + void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; u16 txoffset; - if (!is_any_launchtime(adapter)) + if (!igc_tsn_is_tx_mode_in_tsn(adapter)) return; switch (adapter->link_speed) { @@ -78,6 +85,23 @@ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) wr32(IGC_GTXOFFSET, txoffset); } +static void igc_tsn_restore_retx_default(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl; + + retxctl = rd32(IGC_RETX_CTL) & IGC_RETX_CTL_WATERMARK_MASK; + wr32(IGC_RETX_CTL, retxctl); +} + +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return (rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && + adapter->taprio_offload_enable; +} + /* Returns the TSN specific registers to their default values after * the adapter is reset. */ @@ -91,6 +115,9 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT); + if (igc_is_device_id_i226(hw)) + igc_tsn_restore_retx_default(adapter); + tqavctrl = rd32(IGC_TQAVCTRL); tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS); @@ -111,6 +138,25 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) return 0; } +/* To partially fix i226 HW errata, reduce MAC internal buffering from 192 Bytes + * to 88 Bytes by setting RETX_CTL register using the recommendation from: + * a) Ethernet Controller I225/I226 Specification Update Rev 2.1 + * Item 9: TSN: Packet Transmission Might Cross the Qbv Window + * b) I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control + */ +static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl, watermark; + + retxctl = rd32(IGC_RETX_CTL); + watermark = retxctl & IGC_RETX_CTL_WATERMARK_MASK; + /* Set QBVFULLTH value using watermark and set QBVFULLEN */ + retxctl |= (watermark << IGC_RETX_CTL_QBVFULLTH_SHIFT) | + IGC_RETX_CTL_QBVFULLEN; + wr32(IGC_RETX_CTL, retxctl); +} + static int igc_tsn_enable_offload(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; @@ -123,6 +169,9 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN); wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN); + if (igc_is_device_id_i226(hw)) + igc_tsn_set_retx_qbvfullthreshold(adapter); + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; u32 txqctl = 0; @@ -262,14 +311,6 @@ skip_cbs: s64 n = div64_s64(ktime_sub_ns(systim, base_time), cycle); base_time = ktime_add_ns(base_time, (n + 1) * cycle); - - /* Increase the counter if scheduling into the past while - * Gate Control List (GCL) is running. - */ - if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && - (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) && - (adapter->qbv_count > 1)) - adapter->qbv_config_change_errors++; } else { if (igc_is_device_id_i226(hw)) { ktime_t adjust_time, expires_time; @@ -331,15 +372,22 @@ int igc_tsn_reset(struct igc_adapter *adapter) return err; } -int igc_tsn_offload_apply(struct igc_adapter *adapter) +static bool igc_tsn_will_tx_mode_change(struct igc_adapter *adapter) { - struct igc_hw *hw = &adapter->hw; + bool any_tsn_enabled = !!(igc_tsn_new_flags(adapter) & + IGC_FLAG_TSN_ANY_ENABLED); - /* Per I225/6 HW Design Section 7.5.2.1, transmit mode - * cannot be changed dynamically. Require reset the adapter. + return (any_tsn_enabled && !igc_tsn_is_tx_mode_in_tsn(adapter)) || + (!any_tsn_enabled && igc_tsn_is_tx_mode_in_tsn(adapter)); +} + +int igc_tsn_offload_apply(struct igc_adapter *adapter) +{ + /* Per I225/6 HW Design Section 7.5.2.1 guideline, if tx mode change + * from legacy->tsn or tsn->legacy, then reset adapter is needed. */ if (netif_running(adapter->netdev) && - (igc_is_device_id_i225(hw) || !adapter->qbv_count)) { + igc_tsn_will_tx_mode_change(adapter)) { schedule_work(&adapter->reset_task); return 0; } diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h index b53e6af560b7..98ec845a86bf 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.h +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -7,5 +7,6 @@ int igc_tsn_offload_apply(struct igc_adapter *adapter); int igc_tsn_reset(struct igc_adapter *adapter); void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter); +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter); #endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index b06e24562973..d8be0e4dcb07 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -946,15 +946,13 @@ jme_udpsum(struct sk_buff *skb) if (skb->protocol != htons(ETH_P_IP)) return csum; skb_set_network_header(skb, ETH_HLEN); - if ((ip_hdr(skb)->protocol != IPPROTO_UDP) || - (skb->len < (ETH_HLEN + - (ip_hdr(skb)->ihl << 2) + - sizeof(struct udphdr)))) { + + if (ip_hdr(skb)->protocol != IPPROTO_UDP || + skb->len < (ETH_HLEN + ip_hdrlen(skb) + sizeof(struct udphdr))) { skb_reset_network_header(skb); return csum; } - skb_set_transport_header(skb, - ETH_HLEN + (ip_hdr(skb)->ihl << 2)); + skb_set_transport_header(skb, ETH_HLEN + ip_hdrlen(skb)); csum = udp_hdr(skb)->check; skb_reset_transport_header(skb); skb_reset_network_header(skb); diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 61334a71058c..e212a4ba9275 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -2666,14 +2666,15 @@ mtk_wed_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_pri { struct mtk_wed_flow_block_priv *priv = cb_priv; struct flow_cls_offload *cls = type_data; - struct mtk_wed_hw *hw = priv->hw; + struct mtk_wed_hw *hw = NULL; - if (!tc_can_offload(priv->dev)) + if (!priv || !tc_can_offload(priv->dev)) return -EOPNOTSUPP; if (type != TC_SETUP_CLSFLOWER) return -EOPNOTSUPP; + hw = priv->hw; return mtk_flow_offload_cmd(hw->eth, cls, hw->index); } @@ -2729,6 +2730,7 @@ mtk_wed_setup_tc_block(struct mtk_wed_hw *hw, struct net_device *dev, flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); kfree(block_cb->cb_priv); + block_cb->cb_priv = NULL; } return 0; default: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 5fd82c67b6ab..bb5da42edc23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -130,7 +130,7 @@ struct page_pool; #define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW 0x2 #define MLX5E_DEFAULT_LRO_TIMEOUT 32 -#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4 +#define MLX5E_DEFAULT_SHAMPO_TIMEOUT 1024 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC 0x10 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE 0x3 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 6c9ccccca81e..64b62ed17b07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -928,7 +928,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, log_headers_entry_size, mlx5e_shampo_get_log_hd_entry_size(mdev, params)); MLX5_SET(rqc, rqc, reservation_timeout, - params->packet_merge.timeout); + mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_SHAMPO_TIMEOUT)); MLX5_SET(rqc, rqc, shampo_match_criteria_type, params->packet_merge.shampo.match_criteria_type); MLX5_SET(rqc, rqc, shampo_no_match_alignment_granularity, @@ -1087,6 +1087,20 @@ static u32 mlx5e_shampo_icosq_sz(struct mlx5_core_dev *mdev, return wqebbs; } +#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4 + +u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) +{ + int i; + + /* The supported periods are organized in ascending order */ + for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++) + if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout) + break; + + return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); +} + static u32 mlx5e_mpwrq_total_umr_wqebbs(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 749b2ec0436e..3f8986f9d862 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -108,6 +108,7 @@ u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev, u32 mlx5e_shampo_hd_per_wq(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_rq_param *rq_param); +u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout); u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 22918b2ef7f1..09433b91be17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -146,7 +146,9 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) return err; } + mutex_lock(&priv->state_lock); err = mlx5e_safe_reopen_channels(priv); + mutex_unlock(&priv->state_lock); if (!err) { to_ctx->status = 1; /* all channels recovered */ return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 3eccdadc0357..773624bb2c5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -734,7 +734,7 @@ mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv, if (num_tuples <= 0) { netdev_warn(priv->netdev, "%s: flow is not valid %d\n", __func__, num_tuples); - return num_tuples; + return num_tuples < 0 ? num_tuples : -EINVAL; } eth_ft = get_flow_table(priv, fs, num_tuples); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 6f686fabed44..5df904639b0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5167,18 +5167,6 @@ const struct net_device_ops mlx5e_netdev_ops = { #endif }; -static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) -{ - int i; - - /* The supported periods are organized in ascending order */ - for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++) - if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout) - break; - - return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); -} - void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 mtu) { struct mlx5e_params *params = &priv->channels.params; @@ -5308,7 +5296,7 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i, struct mlx5e_rq_stats *rq_stats; ASSERT_RTNL(); - if (mlx5e_is_uplink_rep(priv)) + if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch) return; channel_stats = priv->channel_stats[i]; @@ -5328,6 +5316,9 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i, struct mlx5e_sq_stats *sq_stats; ASSERT_RTNL(); + if (!priv->stats_nch) + return; + /* no special case needed for ptp htb etc since txq2sq_stats is kept up * to date for active sq_stats, otherwise get_base_stats takes care of * inactive sqs. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index f6deb5a3f820..eeb0b7ea05f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -126,7 +126,7 @@ static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses) } static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, - u8 *host_buses, u8 *sd_group) + u8 *host_buses) { u32 out[MLX5_ST_SZ_DW(mpir_reg)]; int err; @@ -135,10 +135,6 @@ static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, if (err) return err; - err = mlx5_query_nic_vport_sd_group(dev, sd_group); - if (err) - return err; - *sdm = MLX5_GET(mpir_reg, out, sdm); *host_buses = MLX5_GET(mpir_reg, out, host_buses); @@ -166,19 +162,23 @@ static int sd_init(struct mlx5_core_dev *dev) if (mlx5_core_is_ecpf(dev)) return 0; + err = mlx5_query_nic_vport_sd_group(dev, &sd_group); + if (err) + return err; + + if (!sd_group) + return 0; + if (!MLX5_CAP_MCAM_REG(dev, mpir)) return 0; - err = mlx5_query_sd(dev, &sdm, &host_buses, &sd_group); + err = mlx5_query_sd(dev, &sdm, &host_buses); if (err) return err; if (!sdm) return 0; - if (!sd_group) - return 0; - group_id = mlx5_sd_group_id(dev, sd_group); if (!mlx5_sd_is_supported(dev, host_buses)) { diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h index bc94e75a7aeb..e7777700ee18 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h @@ -40,6 +40,7 @@ */ #define MLXBF_GIGE_BCAST_MAC_FILTER_IDX 0 #define MLXBF_GIGE_LOCAL_MAC_FILTER_IDX 1 +#define MLXBF_GIGE_MAX_FILTER_IDX 3 /* Define for broadcast MAC literal */ #define BCAST_MAC_ADDR 0xFFFFFFFFFFFF @@ -175,6 +176,13 @@ enum mlxbf_gige_res { int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv); void mlxbf_gige_mdio_remove(struct mlxbf_gige *priv); + +void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv); +void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv); +void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index); +void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index); void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, unsigned int index, u64 dmac); void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index b157f0f1c5a8..385a56ac7348 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -168,6 +168,10 @@ static int mlxbf_gige_open(struct net_device *netdev) if (err) goto napi_deinit; + mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_BCAST_MAC_FILTER_IDX); + mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_LOCAL_MAC_FILTER_IDX); + mlxbf_gige_enable_multicast_rx(priv); + /* Set bits in INT_EN that we care about */ int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR | MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS | @@ -379,6 +383,7 @@ static int mlxbf_gige_probe(struct platform_device *pdev) void __iomem *plu_base; void __iomem *base; int addr, phy_irq; + unsigned int i; int err; base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC); @@ -423,6 +428,11 @@ static int mlxbf_gige_probe(struct platform_device *pdev) priv->rx_q_entries = MLXBF_GIGE_DEFAULT_RXQ_SZ; priv->tx_q_entries = MLXBF_GIGE_DEFAULT_TXQ_SZ; + for (i = 0; i <= MLXBF_GIGE_MAX_FILTER_IDX; i++) + mlxbf_gige_disable_mac_rx_filter(priv, i); + mlxbf_gige_disable_multicast_rx(priv); + mlxbf_gige_disable_promisc(priv); + /* Write initial MAC address to hardware */ mlxbf_gige_initial_mac(priv); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h index 98a8681c21b9..4d14cb13fd64 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h @@ -62,6 +62,8 @@ #define MLXBF_GIGE_TX_STATUS_DATA_FIFO_FULL BIT(1) #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_START 0x0520 #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_END 0x0528 +#define MLXBF_GIGE_RX_MAC_FILTER_GENERAL 0x0530 +#define MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST BIT(1) #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC 0x0540 #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC_EN BIT(0) #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS 0x0548 diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c index 699984358493..eb62620b63c7 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -11,15 +11,31 @@ #include "mlxbf_gige.h" #include "mlxbf_gige_regs.h" -void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, - unsigned int index, u64 dmac) +void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv) { void __iomem *base = priv->base; - u64 control; + u64 data; - /* Write destination MAC to specified MAC RX filter */ - writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER + - (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); + data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); + data |= MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST; + writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); +} + +void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv) +{ + void __iomem *base = priv->base; + u64 data; + + data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); + data &= ~MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST; + writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL); +} + +void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index) +{ + void __iomem *base = priv->base; + u64 control; /* Enable MAC receive filter mask for specified index */ control = readq(base + MLXBF_GIGE_CONTROL); @@ -27,6 +43,28 @@ void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, writeq(control, base + MLXBF_GIGE_CONTROL); } +void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index) +{ + void __iomem *base = priv->base; + u64 control; + + /* Disable MAC receive filter mask for specified index */ + control = readq(base + MLXBF_GIGE_CONTROL); + control &= ~(MLXBF_GIGE_CONTROL_EN_SPECIFIC_MAC << index); + writeq(control, base + MLXBF_GIGE_CONTROL); +} + +void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index, u64 dmac) +{ + void __iomem *base = priv->base; + + /* Write destination MAC to specified MAC RX filter */ + writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER + + (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); +} + void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, unsigned int index, u64 *dmac) { diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index d2f07e179e86..39f56973746d 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -599,7 +599,11 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size, else *headroom = XDP_PACKET_HEADROOM; - *alloc_size = mtu + MANA_RXBUF_PAD + *headroom; + *alloc_size = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + *headroom); + + /* Using page pool in this case, so alloc_size is PAGE_SIZE */ + if (*alloc_size < PAGE_SIZE) + *alloc_size = PAGE_SIZE; *datasize = mtu + ETH_HLEN; } @@ -1788,7 +1792,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) { struct mana_cq *cq = context; - u8 arm_bit; int w; WARN_ON_ONCE(cq->gdma_cq != gdma_queue); @@ -1799,16 +1802,23 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) mana_poll_tx_cq(cq); w = cq->work_done; - - if (w < cq->budget && - napi_complete_done(&cq->napi, w)) { - arm_bit = SET_ARM_BIT; - } else { - arm_bit = 0; + cq->work_done_since_doorbell += w; + + if (w < cq->budget) { + mana_gd_ring_cq(gdma_queue, SET_ARM_BIT); + cq->work_done_since_doorbell = 0; + napi_complete_done(&cq->napi, w); + } else if (cq->work_done_since_doorbell > + cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) { + /* MANA hardware requires at least one doorbell ring every 8 + * wraparounds of CQ even if there is no need to arm the CQ. + * This driver rings the doorbell as soon as we have exceeded + * 4 wraparounds. + */ + mana_gd_ring_cq(gdma_queue, 0); + cq->work_done_since_doorbell = 0; } - mana_gd_ring_cq(gdma_queue, arm_bit); - return w; } diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index fa5500decc96..c7d9221fafdc 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -160,16 +160,16 @@ #define XAE_RCW1_OFFSET 0x00000404 /* Rx Configuration Word 1 */ #define XAE_TC_OFFSET 0x00000408 /* Tx Configuration */ #define XAE_FCC_OFFSET 0x0000040C /* Flow Control Configuration */ -#define XAE_EMMC_OFFSET 0x00000410 /* EMAC mode configuration */ -#define XAE_PHYC_OFFSET 0x00000414 /* RGMII/SGMII configuration */ +#define XAE_EMMC_OFFSET 0x00000410 /* MAC speed configuration */ +#define XAE_PHYC_OFFSET 0x00000414 /* RX Max Frame Configuration */ #define XAE_ID_OFFSET 0x000004F8 /* Identification register */ -#define XAE_MDIO_MC_OFFSET 0x00000500 /* MII Management Config */ -#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MII Management Control */ -#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MII Management Write Data */ -#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MII Management Read Data */ +#define XAE_MDIO_MC_OFFSET 0x00000500 /* MDIO Setup */ +#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MDIO Control */ +#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MDIO Write Data */ +#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MDIO Read Data */ #define XAE_UAW0_OFFSET 0x00000700 /* Unicast address word 0 */ #define XAE_UAW1_OFFSET 0x00000704 /* Unicast address word 1 */ -#define XAE_FMI_OFFSET 0x00000708 /* Filter Mask Index */ +#define XAE_FMI_OFFSET 0x00000708 /* Frame Filter Control */ #define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */ #define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */ @@ -308,7 +308,7 @@ */ #define XAE_UAW1_UNICASTADDR_MASK 0x0000FFFF -/* Bit masks for Axi Ethernet FMI register */ +/* Bit masks for Axi Ethernet FMC register */ #define XAE_FMI_PM_MASK 0x80000000 /* Promis. mode enable */ #define XAE_FMI_IND_MASK 0x00000003 /* Index Mask */ diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 427b91aca50d..0696faf60013 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1269,6 +1269,9 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev) if (skb_cow_head(skb, dev->needed_headroom)) goto tx_err; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + skb_reset_inner_headers(skb); /* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */ diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 897b979ec03c..3b5fcaf0dd36 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -237,16 +237,6 @@ static int vsc739x_config_init(struct phy_device *phydev) return 0; } -static int vsc73xx_config_aneg(struct phy_device *phydev) -{ - /* The VSC73xx switches does not like to be instructed to - * do autonegotiation in any way, it prefers that you just go - * with the power-on/reset defaults. Writing some registers will - * just make autonegotiation permanently fail. - */ - return 0; -} - /* This adds a skew for both TX and RX clocks, so the skew should only be * applied to "rgmii-id" interfaces. It may not work as expected * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. @@ -444,7 +434,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc738x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { @@ -453,7 +442,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc738x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { @@ -462,7 +450,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc739x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { @@ -471,7 +458,6 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc739x_config_init, - .config_aneg = vsc73xx_config_aneg, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, }, { diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c index ec20953e0f82..4f032b16a8a0 100644 --- a/drivers/net/pse-pd/pse_core.c +++ b/drivers/net/pse-pd/pse_core.c @@ -401,9 +401,14 @@ devm_pse_pi_regulator_register(struct pse_controller_dev *pcdev, rdesc->ops = &pse_pi_ops; rdesc->owner = pcdev->owner; - rinit_data->constraints.valid_ops_mask = REGULATOR_CHANGE_STATUS | - REGULATOR_CHANGE_CURRENT; - rinit_data->constraints.max_uA = MAX_PI_CURRENT; + rinit_data->constraints.valid_ops_mask = REGULATOR_CHANGE_STATUS; + + if (pcdev->ops->pi_set_current_limit) { + rinit_data->constraints.valid_ops_mask |= + REGULATOR_CHANGE_CURRENT; + rinit_data->constraints.max_uA = MAX_PI_CURRENT; + } + rinit_data->supply_regulator = "vpwr"; rconfig.dev = pcdev->dev; diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index 687d70cfc556..46afb95ffabe 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -286,10 +286,11 @@ static void ipheth_rcvbulk_callback(struct urb *urb) return; } - if (urb->actual_length <= IPHETH_IP_ALIGN) { - dev->net->stats.rx_length_errors++; - return; - } + /* iPhone may periodically send URBs with no payload + * on the "bulk in" endpoint. It is safe to ignore them. + */ + if (urb->actual_length == 0) + goto rx_submit; /* RX URBs starting with 0x00 0x01 do not encapsulate Ethernet frames, * but rather are control frames. Their purpose is not documented, and @@ -298,7 +299,8 @@ static void ipheth_rcvbulk_callback(struct urb *urb) * URB received from the bulk IN endpoint. */ if (unlikely - (((char *)urb->transfer_buffer)[0] == 0 && + (urb->actual_length == 4 && + ((char *)urb->transfer_buffer)[0] == 0 && ((char *)urb->transfer_buffer)[1] == 1)) goto rx_submit; @@ -306,7 +308,6 @@ static void ipheth_rcvbulk_callback(struct urb *urb) if (retval != 0) { dev_err(&dev->intf->dev, "%s: callback retval: %d\n", __func__, retval); - return; } rx_submit: @@ -354,13 +355,14 @@ static int ipheth_carrier_set(struct ipheth_device *dev) 0x02, /* index */ dev->ctrl_buf, IPHETH_CTRL_BUF_SIZE, IPHETH_CTRL_TIMEOUT); - if (retval < 0) { + if (retval <= 0) { dev_err(&dev->intf->dev, "%s: usb_control_msg: %d\n", __func__, retval); return retval; } - if (dev->ctrl_buf[0] == IPHETH_CARRIER_ON) { + if ((retval == 1 && dev->ctrl_buf[0] == IPHETH_CARRIER_ON) || + (retval >= 2 && dev->ctrl_buf[1] == IPHETH_CARRIER_ON)) { netif_carrier_on(dev->net); if (dev->tx_urb->status != -EINPROGRESS) netif_wake_queue(dev->net); @@ -475,8 +477,8 @@ static int ipheth_close(struct net_device *net) { struct ipheth_device *dev = netdev_priv(net); - cancel_delayed_work_sync(&dev->carrier_work); netif_stop_queue(net); + cancel_delayed_work_sync(&dev->carrier_work); return 0; } diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c index d08c04343e90..44406e0b4a34 100644 --- a/drivers/net/wireless/ath/ath12k/dp_tx.c +++ b/drivers/net/wireless/ath/ath12k/dp_tx.c @@ -162,6 +162,60 @@ static int ath12k_dp_prepare_htt_metadata(struct sk_buff *skb) return 0; } +static void ath12k_dp_tx_move_payload(struct sk_buff *skb, + unsigned long delta, + bool head) +{ + unsigned long len = skb->len; + + if (head) { + skb_push(skb, delta); + memmove(skb->data, skb->data + delta, len); + skb_trim(skb, len); + } else { + skb_put(skb, delta); + memmove(skb->data + delta, skb->data, len); + skb_pull(skb, delta); + } +} + +static int ath12k_dp_tx_align_payload(struct ath12k_base *ab, + struct sk_buff **pskb) +{ + u32 iova_mask = ab->hw_params->iova_mask; + unsigned long offset, delta1, delta2; + struct sk_buff *skb2, *skb = *pskb; + unsigned int headroom = skb_headroom(skb); + int tailroom = skb_tailroom(skb); + int ret = 0; + + offset = (unsigned long)skb->data & iova_mask; + delta1 = offset; + delta2 = iova_mask - offset + 1; + + if (headroom >= delta1) { + ath12k_dp_tx_move_payload(skb, delta1, true); + } else if (tailroom >= delta2) { + ath12k_dp_tx_move_payload(skb, delta2, false); + } else { + skb2 = skb_realloc_headroom(skb, iova_mask); + if (!skb2) { + ret = -ENOMEM; + goto out; + } + + dev_kfree_skb_any(skb); + + offset = (unsigned long)skb2->data & iova_mask; + if (offset) + ath12k_dp_tx_move_payload(skb2, offset, true); + *pskb = skb2; + } + +out: + return ret; +} + int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif, struct sk_buff *skb) { @@ -184,6 +238,7 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif, bool tcl_ring_retry; bool msdu_ext_desc = false; bool add_htt_metadata = false; + u32 iova_mask = ab->hw_params->iova_mask; if (test_bit(ATH12K_FLAG_CRASH_FLUSH, &ar->ab->dev_flags)) return -ESHUTDOWN; @@ -279,6 +334,23 @@ tcl_ring_sel: goto fail_remove_tx_buf; } + if (iova_mask && + (unsigned long)skb->data & iova_mask) { + ret = ath12k_dp_tx_align_payload(ab, &skb); + if (ret) { + ath12k_warn(ab, "failed to align TX buffer %d\n", ret); + /* don't bail out, give original buffer + * a chance even unaligned. + */ + goto map; + } + + /* hdr is pointing to a wrong place after alignment, + * so refresh it for later use. + */ + hdr = (void *)skb->data; + } +map: ti.paddr = dma_map_single(ab->dev, skb->data, skb->len, DMA_TO_DEVICE); if (dma_mapping_error(ab->dev, ti.paddr)) { atomic_inc(&ab->soc_stats.tx_err.misc_fail); diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c index 2e11ea763574..7b0b6a7f4701 100644 --- a/drivers/net/wireless/ath/ath12k/hw.c +++ b/drivers/net/wireless/ath/ath12k/hw.c @@ -924,6 +924,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = { .acpi_guid = NULL, .supports_dynamic_smps_6ghz = true, + + .iova_mask = 0, }, { .name = "wcn7850 hw2.0", @@ -1000,6 +1002,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = { .acpi_guid = &wcn7850_uuid, .supports_dynamic_smps_6ghz = false, + + .iova_mask = ATH12K_PCIE_MAX_PAYLOAD_SIZE - 1, }, { .name = "qcn9274 hw2.0", @@ -1072,6 +1076,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = { .acpi_guid = NULL, .supports_dynamic_smps_6ghz = true, + + .iova_mask = 0, }, }; diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h index e792eb6b249b..b1d302c48326 100644 --- a/drivers/net/wireless/ath/ath12k/hw.h +++ b/drivers/net/wireless/ath/ath12k/hw.h @@ -96,6 +96,8 @@ #define ATH12K_M3_FILE "m3.bin" #define ATH12K_REGDB_FILE_NAME "regdb.bin" +#define ATH12K_PCIE_MAX_PAYLOAD_SIZE 128 + enum ath12k_hw_rate_cck { ATH12K_HW_RATE_CCK_LP_11M = 0, ATH12K_HW_RATE_CCK_LP_5_5M, @@ -215,6 +217,8 @@ struct ath12k_hw_params { const guid_t *acpi_guid; bool supports_dynamic_smps_6ghz; + + u32 iova_mask; }; struct ath12k_hw_ops { diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index 8106297f0bc1..ce41c8153080 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -9193,6 +9193,7 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah) hw->vif_data_size = sizeof(struct ath12k_vif); hw->sta_data_size = sizeof(struct ath12k_sta); + hw->extra_tx_headroom = ab->hw_params->iova_mask; wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_STA_TX_PWR); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 1585a5653ee4..d4cc5fa92341 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -4320,9 +4320,16 @@ brcmf_pmksa_v3_op(struct brcmf_if *ifp, struct cfg80211_pmksa *pmksa, /* Single PMK operation */ pmk_op->count = cpu_to_le16(1); length += sizeof(struct brcmf_pmksa_v3); - memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN); - memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN); - pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN; + if (pmksa->bssid) + memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN); + if (pmksa->pmkid) { + memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN); + pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN; + } + if (pmksa->ssid && pmksa->ssid_len) { + memcpy(pmk_op->pmk[0].ssid.SSID, pmksa->ssid, pmksa->ssid_len); + pmk_op->pmk[0].ssid.SSID_len = pmksa->ssid_len; + } pmk_op->pmk[0].time_left = cpu_to_le32(alive ? BRCMF_PMKSA_NO_EXPIRY : 0); } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index b59de4f80b4b..27a7e0b5b3d5 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -639,7 +639,8 @@ void iwl_trans_pcie_tx_reset(struct iwl_trans *trans); int iwl_pcie_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num, bool cmd_queue); -dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, void *addr); +dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset, + unsigned int len); struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb, struct iwl_cmd_meta *cmd_meta, u8 **hdr, unsigned int hdr_room); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index 2e780fb2da42..b1846abb99b7 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -168,6 +168,7 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans, struct ieee80211_hdr *hdr = (void *)skb->data; unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room; unsigned int mss = skb_shinfo(skb)->gso_size; + unsigned int data_offset = 0; dma_addr_t start_hdr_phys; u16 length, amsdu_pad; u8 *start_hdr; @@ -260,7 +261,8 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans, int ret; tb_len = min_t(unsigned int, tso.size, data_left); - tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, tso.data); + tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, data_offset, + tb_len); /* Not a real mapping error, use direct comparison */ if (unlikely(tb_phys == DMA_MAPPING_ERROR)) goto out_err; @@ -272,6 +274,7 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans, goto out_err; data_left -= tb_len; + data_offset += tb_len; tso_build_data(skb, &tso, tb_len); } } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index 22d482ae53d9..9fe050f0ddc1 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -1814,23 +1814,31 @@ out: /** * iwl_pcie_get_sgt_tb_phys - Find TB address in mapped SG list * @sgt: scatter gather table - * @addr: Virtual address + * @offset: Offset into the mapped memory (i.e. SKB payload data) + * @len: Length of the area * - * Find the entry that includes the address for the given address and return - * correct physical address for the TB entry. + * Find the DMA address that corresponds to the SKB payload data at the + * position given by @offset. * * Returns: Address for TB entry */ -dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, void *addr) +dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset, + unsigned int len) { struct scatterlist *sg; + unsigned int sg_offset = 0; int i; + /* + * Search the mapped DMA areas in the SG for the area that contains the + * data at offset with the given length. + */ for_each_sgtable_dma_sg(sgt, sg, i) { - if (addr >= sg_virt(sg) && - (u8 *)addr < (u8 *)sg_virt(sg) + sg_dma_len(sg)) - return sg_dma_address(sg) + - ((unsigned long)addr - (unsigned long)sg_virt(sg)); + if (offset >= sg_offset && + offset + len <= sg_offset + sg_dma_len(sg)) + return sg_dma_address(sg) + offset - sg_offset; + + sg_offset += sg_dma_len(sg); } WARN_ON_ONCE(1); @@ -1875,7 +1883,9 @@ struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb, sg_init_table(sgt->sgl, skb_shinfo(skb)->nr_frags + 1); - sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, 0, skb->len); + /* Only map the data, not the header (it is copied to the TSO page) */ + sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, skb_headlen(skb), + skb->data_len); if (WARN_ON_ONCE(sgt->orig_nents <= 0)) return NULL; @@ -1900,6 +1910,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, struct ieee80211_hdr *hdr = (void *)skb->data; unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room; unsigned int mss = skb_shinfo(skb)->gso_size; + unsigned int data_offset = 0; u16 length, iv_len, amsdu_pad; dma_addr_t start_hdr_phys; u8 *start_hdr, *pos_hdr; @@ -2000,7 +2011,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, data_left); dma_addr_t tb_phys; - tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, tso.data); + tb_phys = iwl_pcie_get_sgt_tb_phys(sgt, data_offset, size); /* Not a real mapping error, use direct comparison */ if (unlikely(tb_phys == DMA_MAPPING_ERROR)) return -EINVAL; @@ -2011,6 +2022,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, tb_phys, size); data_left -= size; + data_offset += size; tso_build_data(skb, &tso, size); } } diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 1bab93d049df..23b228804289 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -1183,7 +1183,7 @@ static void mt7921_ipv6_addr_change(struct ieee80211_hw *hw, struct inet6_dev *idev) { struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; - struct mt792x_dev *dev = mvif->phy->dev; + struct mt792x_dev *dev = mt792x_hw_dev(hw); struct inet6_ifaddr *ifa; struct in6_addr ns_addrs[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; struct sk_buff *skb; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c index 700c6e2bcad1..ff458fb8514d 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/hw.c @@ -181,11 +181,11 @@ static void _rtl92du_init_queue_reserved_page(struct ieee80211_hw *hw, struct rtl_hal *rtlhal = rtl_hal(rtlpriv); u32 txqpagenum, txqpageunit; u32 txqremainingpage; + u32 value32 = 0; u32 numhq = 0; u32 numlq = 0; u32 numnq = 0; u32 numpubq; - u32 value32; if (rtlhal->macphymode != SINGLEMAC_SINGLEPHY) { numpubq = NORMAL_PAGE_NUM_PUBQ_92D_DUAL_MAC; diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 665fa9524986..ddfccc226751 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -477,6 +477,7 @@ config LENOVO_YMC tristate "Lenovo Yoga Tablet Mode Control" depends on ACPI_WMI depends on INPUT + depends on IDEAPAD_LAPTOP select INPUT_SPARSEKMAP help This driver maps the Tablet Mode Control switch to SW_TABLET_MODE input diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c index a3dec14c3004..3c153fb1425e 100644 --- a/drivers/platform/x86/amd/pmf/spc.c +++ b/drivers/platform/x86/amd/pmf/spc.c @@ -150,36 +150,26 @@ static int amd_pmf_get_slider_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_ return 0; } -static int amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) +static void amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) { struct amd_sfh_info sfh_info; - int ret; + + /* Get the latest information from SFH */ + in->ev_info.user_present = false; /* Get ALS data */ - ret = amd_get_sfh_info(&sfh_info, MT_ALS); - if (!ret) + if (!amd_get_sfh_info(&sfh_info, MT_ALS)) in->ev_info.ambient_light = sfh_info.ambient_light; else - return ret; + dev_dbg(dev->dev, "ALS is not enabled/detected\n"); /* get HPD data */ - ret = amd_get_sfh_info(&sfh_info, MT_HPD); - if (ret) - return ret; - - switch (sfh_info.user_present) { - case SFH_NOT_DETECTED: - in->ev_info.user_present = 0xff; /* assume no sensors connected */ - break; - case SFH_USER_PRESENT: - in->ev_info.user_present = 1; - break; - case SFH_USER_AWAY: - in->ev_info.user_present = 0; - break; + if (!amd_get_sfh_info(&sfh_info, MT_HPD)) { + if (sfh_info.user_present == SFH_USER_PRESENT) + in->ev_info.user_present = true; + } else { + dev_dbg(dev->dev, "HPD is not enabled/detected\n"); } - - return 0; } void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 1ace711f7442..98ec30fce9fd 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -126,6 +126,7 @@ struct ideapad_rfk_priv { struct ideapad_private { struct acpi_device *adev; + struct mutex vpc_mutex; /* protects the VPC calls */ struct rfkill *rfk[IDEAPAD_RFKILL_DEV_NUM]; struct ideapad_rfk_priv rfk_priv[IDEAPAD_RFKILL_DEV_NUM]; struct platform_device *platform_device; @@ -146,6 +147,7 @@ struct ideapad_private { bool touchpad_ctrl_via_ec : 1; bool ctrl_ps2_aux_port : 1; bool usb_charging : 1; + bool ymc_ec_trigger : 1; } features; struct { bool initialized; @@ -194,6 +196,12 @@ MODULE_PARM_DESC(touchpad_ctrl_via_ec, "Enable registering a 'touchpad' sysfs-attribute which can be used to manually " "tell the EC to enable/disable the touchpad. This may not work on all models."); +static bool ymc_ec_trigger __read_mostly; +module_param(ymc_ec_trigger, bool, 0444); +MODULE_PARM_DESC(ymc_ec_trigger, + "Enable EC triggering work-around to force emitting tablet mode events. " + "If you need this please report this to: platform-driver-x86@vger.kernel.org"); + /* * shared data */ @@ -294,6 +302,8 @@ static int debugfs_status_show(struct seq_file *s, void *data) struct ideapad_private *priv = s->private; unsigned long value; + guard(mutex)(&priv->vpc_mutex); + if (!read_ec_data(priv->adev->handle, VPCCMD_R_BL_MAX, &value)) seq_printf(s, "Backlight max: %lu\n", value); if (!read_ec_data(priv->adev->handle, VPCCMD_R_BL, &value)) @@ -412,7 +422,8 @@ static ssize_t camera_power_show(struct device *dev, unsigned long result; int err; - err = read_ec_data(priv->adev->handle, VPCCMD_R_CAMERA, &result); + scoped_guard(mutex, &priv->vpc_mutex) + err = read_ec_data(priv->adev->handle, VPCCMD_R_CAMERA, &result); if (err) return err; @@ -431,7 +442,8 @@ static ssize_t camera_power_store(struct device *dev, if (err) return err; - err = write_ec_cmd(priv->adev->handle, VPCCMD_W_CAMERA, state); + scoped_guard(mutex, &priv->vpc_mutex) + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_CAMERA, state); if (err) return err; @@ -484,7 +496,8 @@ static ssize_t fan_mode_show(struct device *dev, unsigned long result; int err; - err = read_ec_data(priv->adev->handle, VPCCMD_R_FAN, &result); + scoped_guard(mutex, &priv->vpc_mutex) + err = read_ec_data(priv->adev->handle, VPCCMD_R_FAN, &result); if (err) return err; @@ -506,7 +519,8 @@ static ssize_t fan_mode_store(struct device *dev, if (state > 4 || state == 3) return -EINVAL; - err = write_ec_cmd(priv->adev->handle, VPCCMD_W_FAN, state); + scoped_guard(mutex, &priv->vpc_mutex) + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_FAN, state); if (err) return err; @@ -591,7 +605,8 @@ static ssize_t touchpad_show(struct device *dev, unsigned long result; int err; - err = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &result); + scoped_guard(mutex, &priv->vpc_mutex) + err = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &result); if (err) return err; @@ -612,7 +627,8 @@ static ssize_t touchpad_store(struct device *dev, if (err) return err; - err = write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, state); + scoped_guard(mutex, &priv->vpc_mutex) + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, state); if (err) return err; @@ -1005,6 +1021,8 @@ static int ideapad_rfk_set(void *data, bool blocked) struct ideapad_rfk_priv *priv = data; int opcode = ideapad_rfk_data[priv->dev].opcode; + guard(mutex)(&priv->priv->vpc_mutex); + return write_ec_cmd(priv->priv->adev->handle, opcode, !blocked); } @@ -1018,6 +1036,8 @@ static void ideapad_sync_rfk_state(struct ideapad_private *priv) int i; if (priv->features.hw_rfkill_switch) { + guard(mutex)(&priv->vpc_mutex); + if (read_ec_data(priv->adev->handle, VPCCMD_R_RF, &hw_blocked)) return; hw_blocked = !hw_blocked; @@ -1191,8 +1211,9 @@ static void ideapad_input_novokey(struct ideapad_private *priv) { unsigned long long_pressed; - if (read_ec_data(priv->adev->handle, VPCCMD_R_NOVO, &long_pressed)) - return; + scoped_guard(mutex, &priv->vpc_mutex) + if (read_ec_data(priv->adev->handle, VPCCMD_R_NOVO, &long_pressed)) + return; if (long_pressed) ideapad_input_report(priv, 17); @@ -1204,8 +1225,9 @@ static void ideapad_check_special_buttons(struct ideapad_private *priv) { unsigned long bit, value; - if (read_ec_data(priv->adev->handle, VPCCMD_R_SPECIAL_BUTTONS, &value)) - return; + scoped_guard(mutex, &priv->vpc_mutex) + if (read_ec_data(priv->adev->handle, VPCCMD_R_SPECIAL_BUTTONS, &value)) + return; for_each_set_bit (bit, &value, 16) { switch (bit) { @@ -1238,6 +1260,8 @@ static int ideapad_backlight_get_brightness(struct backlight_device *blightdev) unsigned long now; int err; + guard(mutex)(&priv->vpc_mutex); + err = read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now); if (err) return err; @@ -1250,6 +1274,8 @@ static int ideapad_backlight_update_status(struct backlight_device *blightdev) struct ideapad_private *priv = bl_get_data(blightdev); int err; + guard(mutex)(&priv->vpc_mutex); + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_BL, blightdev->props.brightness); if (err) @@ -1327,6 +1353,8 @@ static void ideapad_backlight_notify_power(struct ideapad_private *priv) if (!blightdev) return; + guard(mutex)(&priv->vpc_mutex); + if (read_ec_data(priv->adev->handle, VPCCMD_R_BL_POWER, &power)) return; @@ -1339,7 +1367,8 @@ static void ideapad_backlight_notify_brightness(struct ideapad_private *priv) /* if we control brightness via acpi video driver */ if (!priv->blightdev) - read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now); + scoped_guard(mutex, &priv->vpc_mutex) + read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now); else backlight_force_update(priv->blightdev, BACKLIGHT_UPDATE_HOTKEY); } @@ -1564,7 +1593,8 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv, bool send_ int ret; /* Without reading from EC touchpad LED doesn't switch state */ - ret = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &value); + scoped_guard(mutex, &priv->vpc_mutex) + ret = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &value); if (ret) return; @@ -1592,16 +1622,92 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv, bool send_ priv->r_touchpad_val = value; } +static const struct dmi_system_id ymc_ec_trigger_quirk_dmi_table[] = { + { + /* Lenovo Yoga 7 14ARB7 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82QF"), + }, + }, + { + /* Lenovo Yoga 7 14ACN6 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82N7"), + }, + }, + { } +}; + +static void ideapad_laptop_trigger_ec(void) +{ + struct ideapad_private *priv; + int ret; + + guard(mutex)(&ideapad_shared_mutex); + + priv = ideapad_shared; + if (!priv) + return; + + if (!priv->features.ymc_ec_trigger) + return; + + scoped_guard(mutex, &priv->vpc_mutex) + ret = write_ec_cmd(priv->adev->handle, VPCCMD_W_YMC, 1); + if (ret) + dev_warn(&priv->platform_device->dev, "Could not write YMC: %d\n", ret); +} + +static int ideapad_laptop_nb_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + switch (action) { + case IDEAPAD_LAPTOP_YMC_EVENT: + ideapad_laptop_trigger_ec(); + break; + } + + return 0; +} + +static struct notifier_block ideapad_laptop_notifier = { + .notifier_call = ideapad_laptop_nb_notify, +}; + +static BLOCKING_NOTIFIER_HEAD(ideapad_laptop_chain_head); + +int ideapad_laptop_register_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&ideapad_laptop_chain_head, nb); +} +EXPORT_SYMBOL_NS_GPL(ideapad_laptop_register_notifier, IDEAPAD_LAPTOP); + +int ideapad_laptop_unregister_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&ideapad_laptop_chain_head, nb); +} +EXPORT_SYMBOL_NS_GPL(ideapad_laptop_unregister_notifier, IDEAPAD_LAPTOP); + +void ideapad_laptop_call_notifier(unsigned long action, void *data) +{ + blocking_notifier_call_chain(&ideapad_laptop_chain_head, action, data); +} +EXPORT_SYMBOL_NS_GPL(ideapad_laptop_call_notifier, IDEAPAD_LAPTOP); + static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data) { struct ideapad_private *priv = data; unsigned long vpc1, vpc2, bit; - if (read_ec_data(handle, VPCCMD_R_VPC1, &vpc1)) - return; + scoped_guard(mutex, &priv->vpc_mutex) { + if (read_ec_data(handle, VPCCMD_R_VPC1, &vpc1)) + return; - if (read_ec_data(handle, VPCCMD_R_VPC2, &vpc2)) - return; + if (read_ec_data(handle, VPCCMD_R_VPC2, &vpc2)) + return; + } vpc1 = (vpc2 << 8) | vpc1; @@ -1728,6 +1834,8 @@ static void ideapad_check_features(struct ideapad_private *priv) priv->features.ctrl_ps2_aux_port = ctrl_ps2_aux_port || dmi_check_system(ctrl_ps2_aux_port_list); priv->features.touchpad_ctrl_via_ec = touchpad_ctrl_via_ec; + priv->features.ymc_ec_trigger = + ymc_ec_trigger || dmi_check_system(ymc_ec_trigger_quirk_dmi_table); if (!read_ec_data(handle, VPCCMD_R_FAN, &val)) priv->features.fan_mode = true; @@ -1906,6 +2014,10 @@ static int ideapad_acpi_add(struct platform_device *pdev) priv->adev = adev; priv->platform_device = pdev; + err = devm_mutex_init(&pdev->dev, &priv->vpc_mutex); + if (err) + return err; + ideapad_check_features(priv); err = ideapad_sysfs_init(priv); @@ -1974,6 +2086,8 @@ static int ideapad_acpi_add(struct platform_device *pdev) if (err) goto shared_init_failed; + ideapad_laptop_register_notifier(&ideapad_laptop_notifier); + return 0; shared_init_failed: @@ -2006,6 +2120,8 @@ static void ideapad_acpi_remove(struct platform_device *pdev) struct ideapad_private *priv = dev_get_drvdata(&pdev->dev); int i; + ideapad_laptop_unregister_notifier(&ideapad_laptop_notifier); + ideapad_shared_exit(priv); acpi_remove_notify_handler(priv->adev->handle, diff --git a/drivers/platform/x86/ideapad-laptop.h b/drivers/platform/x86/ideapad-laptop.h index 4498a96de597..948cc61800a9 100644 --- a/drivers/platform/x86/ideapad-laptop.h +++ b/drivers/platform/x86/ideapad-laptop.h @@ -12,6 +12,15 @@ #include <linux/acpi.h> #include <linux/jiffies.h> #include <linux/errno.h> +#include <linux/notifier.h> + +enum ideapad_laptop_notifier_actions { + IDEAPAD_LAPTOP_YMC_EVENT, +}; + +int ideapad_laptop_register_notifier(struct notifier_block *nb); +int ideapad_laptop_unregister_notifier(struct notifier_block *nb); +void ideapad_laptop_call_notifier(unsigned long action, void *data); enum { VPCCMD_R_VPC1 = 0x10, diff --git a/drivers/platform/x86/lenovo-ymc.c b/drivers/platform/x86/lenovo-ymc.c index e1fbc35504d4..e0bbd6a14a89 100644 --- a/drivers/platform/x86/lenovo-ymc.c +++ b/drivers/platform/x86/lenovo-ymc.c @@ -20,32 +20,10 @@ #define LENOVO_YMC_QUERY_INSTANCE 0 #define LENOVO_YMC_QUERY_METHOD 0x01 -static bool ec_trigger __read_mostly; -module_param(ec_trigger, bool, 0444); -MODULE_PARM_DESC(ec_trigger, "Enable EC triggering work-around to force emitting tablet mode events"); - static bool force; module_param(force, bool, 0444); MODULE_PARM_DESC(force, "Force loading on boards without a convertible DMI chassis-type"); -static const struct dmi_system_id ec_trigger_quirk_dmi_table[] = { - { - /* Lenovo Yoga 7 14ARB7 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "82QF"), - }, - }, - { - /* Lenovo Yoga 7 14ACN6 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "82N7"), - }, - }, - { } -}; - static const struct dmi_system_id allowed_chasis_types_dmi_table[] = { { .matches = { @@ -62,21 +40,8 @@ static const struct dmi_system_id allowed_chasis_types_dmi_table[] = { struct lenovo_ymc_private { struct input_dev *input_dev; - struct acpi_device *ec_acpi_dev; }; -static void lenovo_ymc_trigger_ec(struct wmi_device *wdev, struct lenovo_ymc_private *priv) -{ - int err; - - if (!priv->ec_acpi_dev) - return; - - err = write_ec_cmd(priv->ec_acpi_dev->handle, VPCCMD_W_YMC, 1); - if (err) - dev_warn(&wdev->dev, "Could not write YMC: %d\n", err); -} - static const struct key_entry lenovo_ymc_keymap[] = { /* Laptop */ { KE_SW, 0x01, { .sw = { SW_TABLET_MODE, 0 } } }, @@ -125,11 +90,9 @@ static void lenovo_ymc_notify(struct wmi_device *wdev, union acpi_object *data) free_obj: kfree(obj); - lenovo_ymc_trigger_ec(wdev, priv); + ideapad_laptop_call_notifier(IDEAPAD_LAPTOP_YMC_EVENT, &code); } -static void acpi_dev_put_helper(void *p) { acpi_dev_put(p); } - static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx) { struct lenovo_ymc_private *priv; @@ -143,29 +106,10 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx) return -ENODEV; } - ec_trigger |= dmi_check_system(ec_trigger_quirk_dmi_table); - priv = devm_kzalloc(&wdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; - if (ec_trigger) { - pr_debug("Lenovo YMC enable EC triggering.\n"); - priv->ec_acpi_dev = acpi_dev_get_first_match_dev("VPC2004", NULL, -1); - - if (!priv->ec_acpi_dev) { - dev_err(&wdev->dev, "Could not find EC ACPI device.\n"); - return -ENODEV; - } - err = devm_add_action_or_reset(&wdev->dev, - acpi_dev_put_helper, priv->ec_acpi_dev); - if (err) { - dev_err(&wdev->dev, - "Could not clean up EC ACPI device: %d\n", err); - return err; - } - } - input_dev = devm_input_allocate_device(&wdev->dev); if (!input_dev) return -ENOMEM; @@ -192,7 +136,6 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx) dev_set_drvdata(&wdev->dev, priv); /* Report the state for the first time on probe */ - lenovo_ymc_trigger_ec(wdev, priv); lenovo_ymc_notify(wdev, NULL); return 0; } @@ -217,3 +160,4 @@ module_wmi_driver(lenovo_ymc_driver); MODULE_AUTHOR("Gergo Koteles <soyer@irl.hu>"); MODULE_DESCRIPTION("Lenovo Yoga Mode Control driver"); MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(IDEAPAD_LAPTOP); diff --git a/drivers/staging/media/atomisp/pci/ia_css_stream_public.h b/drivers/staging/media/atomisp/pci/ia_css_stream_public.h index 961c61288083..aad860e54d3a 100644 --- a/drivers/staging/media/atomisp/pci/ia_css_stream_public.h +++ b/drivers/staging/media/atomisp/pci/ia_css_stream_public.h @@ -27,12 +27,16 @@ #include "ia_css_prbs.h" #include "ia_css_input_port.h" -/* Input modes, these enumerate all supported input modes. - * Note that not all ISP modes support all input modes. +/* + * Input modes, these enumerate all supported input modes. + * This enum is part of the atomisp firmware ABI and must + * NOT be changed! + * Note that not all ISP modes support all input modes. */ enum ia_css_input_mode { IA_CSS_INPUT_MODE_SENSOR, /** data from sensor */ IA_CSS_INPUT_MODE_FIFO, /** data from input-fifo */ + IA_CSS_INPUT_MODE_TPG, /** data from test-pattern generator */ IA_CSS_INPUT_MODE_PRBS, /** data from pseudo-random bit stream */ IA_CSS_INPUT_MODE_MEMORY, /** data from a frame in memory */ IA_CSS_INPUT_MODE_BUFFERED_SENSOR /** data is sent through mipi buffer */ diff --git a/drivers/staging/media/atomisp/pci/sh_css_internal.h b/drivers/staging/media/atomisp/pci/sh_css_internal.h index a2d972ea3fa0..959e7f549641 100644 --- a/drivers/staging/media/atomisp/pci/sh_css_internal.h +++ b/drivers/staging/media/atomisp/pci/sh_css_internal.h @@ -344,7 +344,14 @@ struct sh_css_sp_input_formatter_set { #define IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT (3) -/* SP configuration information */ +/* + * SP configuration information + * + * This struct is part of the atomisp firmware ABI and is directly copied + * to ISP DRAM by sh_css_store_sp_group_to_ddr() + * + * Do NOT change this struct's layout or remove seemingly unused fields! + */ struct sh_css_sp_config { u8 no_isp_sync; /* Signal host immediately after start */ u8 enable_raw_pool_locking; /** Enable Raw Buffer Locking for HALv3 Support */ @@ -354,6 +361,10 @@ struct sh_css_sp_config { host (true) or when they are passed to the preview/video pipe (false). */ + /* + * Note the fields below are only used on the ISP2400 not on the ISP2401, + * sh_css_store_sp_group_to_ddr() skip copying these when run on the ISP2401. + */ struct { u8 a_changed; u8 b_changed; @@ -363,11 +374,13 @@ struct sh_css_sp_config { } input_formatter; sync_generator_cfg_t sync_gen; + tpg_cfg_t tpg; prbs_cfg_t prbs; input_system_cfg_t input_circuit; u8 input_circuit_cfg_changed; - u32 mipi_sizes_for_check[N_CSI_PORTS][IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT]; - u8 enable_isys_event_queue; + u32 mipi_sizes_for_check[N_CSI_PORTS][IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT]; + /* These last 2 fields are used on both the ISP2400 and the ISP2401 */ + u8 enable_isys_event_queue; u8 disable_cont_vf; }; diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index a97ceb105cd8..24fdc74caeba 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -75,7 +75,8 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) /* if we just extended the file size, any portion not in * cache won't be on server and is zeroes */ - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (subreq->rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); netfs_subreq_terminated(subreq, err ?: total, false); } diff --git a/fs/afs/file.c b/fs/afs/file.c index c3f0c45ae9a9..ec1be0091fdb 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -242,7 +242,8 @@ static void afs_fetch_data_notify(struct afs_operation *op) req->error = error; if (subreq) { - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (subreq->rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); netfs_subreq_terminated(subreq, error ?: req->actual_len, false); req->subreq = NULL; } else if (req->done) { diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index c26545d71d39..cd6d5bbb4b9d 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -72,8 +72,10 @@ #ifdef CONFIG_BINFMT_FLAT_NO_DATA_START_OFFSET #define DATA_START_OFFSET_WORDS (0) +#define MAX_SHARED_LIBS_UPDATE (0) #else #define DATA_START_OFFSET_WORDS (MAX_SHARED_LIBS) +#define MAX_SHARED_LIBS_UPDATE (MAX_SHARED_LIBS) #endif struct lib_info { @@ -880,7 +882,7 @@ static int load_flat_binary(struct linux_binprm *bprm) return res; /* Update data segment pointers for all libraries */ - for (i = 0; i < MAX_SHARED_LIBS; i++) { + for (i = 0; i < MAX_SHARED_LIBS_UPDATE; i++) { if (!libinfo.lib_list[i].loaded) continue; for (j = 0; j < MAX_SHARED_LIBS; j++) { diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 2ac9296edccb..06a9e0542d70 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -1134,6 +1134,73 @@ btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 byt return find_ref_head(delayed_refs, bytenr, false); } +static int find_comp(struct btrfs_delayed_ref_node *entry, u64 root, u64 parent) +{ + int type = parent ? BTRFS_SHARED_BLOCK_REF_KEY : BTRFS_TREE_BLOCK_REF_KEY; + + if (type < entry->type) + return -1; + if (type > entry->type) + return 1; + + if (type == BTRFS_TREE_BLOCK_REF_KEY) { + if (root < entry->ref_root) + return -1; + if (root > entry->ref_root) + return 1; + } else { + if (parent < entry->parent) + return -1; + if (parent > entry->parent) + return 1; + } + return 0; +} + +/* + * Check to see if a given root/parent reference is attached to the head. This + * only checks for BTRFS_ADD_DELAYED_REF references that match, as that + * indicates the reference exists for the given root or parent. This is for + * tree blocks only. + * + * @head: the head of the bytenr we're searching. + * @root: the root objectid of the reference if it is a normal reference. + * @parent: the parent if this is a shared backref. + */ +bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head, + u64 root, u64 parent) +{ + struct rb_node *node; + bool found = false; + + lockdep_assert_held(&head->mutex); + + spin_lock(&head->lock); + node = head->ref_tree.rb_root.rb_node; + while (node) { + struct btrfs_delayed_ref_node *entry; + int ret; + + entry = rb_entry(node, struct btrfs_delayed_ref_node, ref_node); + ret = find_comp(entry, root, parent); + if (ret < 0) { + node = node->rb_left; + } else if (ret > 0) { + node = node->rb_right; + } else { + /* + * We only want to count ADD actions, as drops mean the + * ref doesn't exist. + */ + if (entry->action == BTRFS_ADD_DELAYED_REF) + found = true; + break; + } + } + spin_unlock(&head->lock); + return found; +} + void __cold btrfs_delayed_ref_exit(void) { kmem_cache_destroy(btrfs_delayed_ref_head_cachep); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index ef15e998be03..05f634eb472d 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -389,6 +389,8 @@ void btrfs_dec_delayed_refs_rsv_bg_updates(struct btrfs_fs_info *fs_info); int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info, enum btrfs_reserve_flush_enum flush); bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info); +bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head, + u64 root, u64 parent); static inline u64 btrfs_delayed_ref_owner(struct btrfs_delayed_ref_node *node) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index ff9f0d41987e..feec49e6f9c8 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5472,23 +5472,62 @@ static int check_ref_exists(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 parent, int level) { + struct btrfs_delayed_ref_root *delayed_refs; + struct btrfs_delayed_ref_head *head; struct btrfs_path *path; struct btrfs_extent_inline_ref *iref; int ret; + bool exists = false; path = btrfs_alloc_path(); if (!path) return -ENOMEM; - +again: ret = lookup_extent_backref(trans, path, &iref, bytenr, root->fs_info->nodesize, parent, btrfs_root_id(root), level, 0); + if (ret != -ENOENT) { + /* + * If we get 0 then we found our reference, return 1, else + * return the error if it's not -ENOENT; + */ + btrfs_free_path(path); + return (ret < 0 ) ? ret : 1; + } + + /* + * We could have a delayed ref with this reference, so look it up while + * we're holding the path open to make sure we don't race with the + * delayed ref running. + */ + delayed_refs = &trans->transaction->delayed_refs; + spin_lock(&delayed_refs->lock); + head = btrfs_find_delayed_ref_head(delayed_refs, bytenr); + if (!head) + goto out; + if (!mutex_trylock(&head->mutex)) { + /* + * We're contended, means that the delayed ref is running, get a + * reference and wait for the ref head to be complete and then + * try again. + */ + refcount_inc(&head->refs); + spin_unlock(&delayed_refs->lock); + + btrfs_release_path(path); + + mutex_lock(&head->mutex); + mutex_unlock(&head->mutex); + btrfs_put_delayed_ref_head(head); + goto again; + } + + exists = btrfs_find_delayed_tree_ref(head, root->root_key.objectid, parent); + mutex_unlock(&head->mutex); +out: + spin_unlock(&delayed_refs->lock); btrfs_free_path(path); - if (ret == -ENOENT) - return 0; - if (ret < 0) - return ret; - return 1; + return exists ? 1 : 0; } /* diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index aa7f8148cd0d..c73cd4f89015 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1496,6 +1496,13 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, free_extent_map(em); em = NULL; + /* + * Although the PageDirty bit might be cleared before entering + * this function, subpage dirty bit is not cleared. + * So clear subpage dirty bit here so next time we won't submit + * page for range already written to disk. + */ + btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize); btrfs_set_range_writeback(inode, cur, cur + iosize - 1); if (!PageWriteback(page)) { btrfs_err(inode->root->fs_info, @@ -1503,13 +1510,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, page->index, cur, end); } - /* - * Although the PageDirty bit is cleared before entering this - * function, subpage dirty bit is not cleared. - * So clear subpage dirty bit here so next time we won't submit - * page for range already written to disk. - */ - btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize); submit_extent_page(bio_ctrl, disk_bytenr, page, iosize, cur - page_offset(page)); diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 23b65dc73c00..10ac5f657e38 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -1147,8 +1147,7 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c return 0; /* - * We want to be fast because we can be called from any path trying to - * allocate memory, so if the lock is busy we don't want to spend time + * We want to be fast so if the lock is busy we don't want to spend time * waiting for it - either some task is about to do IO for the inode or * we may have another task shrinking extent maps, here in this code, so * skip this inode. @@ -1191,9 +1190,7 @@ next: /* * Stop if we need to reschedule or there's contention on the * lock. This is to avoid slowing other tasks trying to take the - * lock and because the shrinker might be called during a memory - * allocation path and we want to avoid taking a very long time - * and slowing down all sorts of tasks. + * lock. */ if (need_resched() || rwlock_needbreak(&tree->lock)) break; @@ -1222,12 +1219,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx if (ctx->scanned >= ctx->nr_to_scan) break; - /* - * We may be called from memory allocation paths, so we don't - * want to take too much time and slowdown tasks. - */ - if (need_resched()) - break; + cond_resched(); inode = btrfs_find_first_inode(root, min_ino); } @@ -1285,14 +1277,12 @@ long btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan) ctx.last_ino); } - /* - * We may be called from memory allocation paths, so we don't want to - * take too much time and slowdown tasks, so stop if we need reschedule. - */ - while (ctx.scanned < ctx.nr_to_scan && !need_resched()) { + while (ctx.scanned < ctx.nr_to_scan) { struct btrfs_root *root; unsigned long count; + cond_resched(); + spin_lock(&fs_info->fs_roots_radix_lock); count = radix_tree_gang_lookup(&fs_info->fs_roots_radix, (void **)&root, diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 4ca711a773ef..7fc692fc76e1 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6157,25 +6157,51 @@ static int send_write_or_clone(struct send_ctx *sctx, u64 offset = key->offset; u64 end; u64 bs = sctx->send_root->fs_info->sectorsize; + struct btrfs_file_extent_item *ei; + u64 disk_byte; + u64 data_offset; + u64 num_bytes; + struct btrfs_inode_info info = { 0 }; end = min_t(u64, btrfs_file_extent_end(path), sctx->cur_inode_size); if (offset >= end) return 0; - if (clone_root && IS_ALIGNED(end, bs)) { - struct btrfs_file_extent_item *ei; - u64 disk_byte; - u64 data_offset; + num_bytes = end - offset; - ei = btrfs_item_ptr(path->nodes[0], path->slots[0], - struct btrfs_file_extent_item); - disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei); - data_offset = btrfs_file_extent_offset(path->nodes[0], ei); - ret = clone_range(sctx, path, clone_root, disk_byte, - data_offset, offset, end - offset); - } else { - ret = send_extent_data(sctx, path, offset, end - offset); - } + if (!clone_root) + goto write_data; + + if (IS_ALIGNED(end, bs)) + goto clone_data; + + /* + * If the extent end is not aligned, we can clone if the extent ends at + * the i_size of the inode and the clone range ends at the i_size of the + * source inode, otherwise the clone operation fails with -EINVAL. + */ + if (end != sctx->cur_inode_size) + goto write_data; + + ret = get_inode_info(clone_root->root, clone_root->ino, &info); + if (ret < 0) + return ret; + + if (clone_root->offset + num_bytes == info.size) + goto clone_data; + +write_data: + ret = send_extent_data(sctx, path, offset, num_bytes); + sctx->cur_inode_next_write_offset = end; + return ret; + +clone_data: + ei = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei); + data_offset = btrfs_file_extent_offset(path->nodes[0], ei); + ret = clone_range(sctx, path, clone_root, disk_byte, data_offset, offset, + num_bytes); sctx->cur_inode_next_write_offset = end; return ret; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 83478deada3b..11044e9e2cb1 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -28,6 +28,7 @@ #include <linux/btrfs.h> #include <linux/security.h> #include <linux/fs_parser.h> +#include <linux/swap.h> #include "messages.h" #include "delayed-inode.h" #include "ctree.h" @@ -2409,6 +2410,15 @@ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_cont const long nr_to_scan = min_t(unsigned long, LONG_MAX, sc->nr_to_scan); struct btrfs_fs_info *fs_info = btrfs_sb(sb); + /* + * We may be called from any task trying to allocate memory and we don't + * want to slow it down with scanning and dropping extent maps. It would + * also cause heavy lock contention if many tasks concurrently enter + * here. Therefore only allow kswapd tasks to scan and drop extent maps. + */ + if (!current_is_kswapd()) + return 0; + return btrfs_free_extent_maps(fs_info, nr_to_scan); } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index a825fa598e3c..6f1e2f2215d9 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -569,9 +569,10 @@ static int check_dir_item(struct extent_buffer *leaf, /* dir type check */ dir_type = btrfs_dir_ftype(leaf, di); - if (unlikely(dir_type >= BTRFS_FT_MAX)) { + if (unlikely(dir_type <= BTRFS_FT_UNKNOWN || + dir_type >= BTRFS_FT_MAX)) { dir_item_err(leaf, slot, - "invalid dir item type, have %u expect [0, %u)", + "invalid dir item type, have %u expect (0, %u)", dir_type, BTRFS_FT_MAX); return -EUCLEAN; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8c16bc5250ef..c4744a02db75 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -246,7 +246,8 @@ static void finish_netfs_read(struct ceph_osd_request *req) if (err >= 0) { if (sparse && err > 0) err = ceph_sparse_ext_map_end(op); - if (err < subreq->len) + if (err < subreq->len && + subreq->rreq->origin != NETFS_DIO_READ) __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); if (IS_ENCRYPTED(inode) && err > 0) { err = ceph_fscrypt_decrypt_extents(inode, @@ -282,7 +283,8 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) size_t len; int mode; - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); if (subreq->start >= inode->i_size) @@ -424,6 +426,9 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) struct ceph_netfs_request_data *priv; int ret = 0; + /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ + __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); + if (rreq->origin != NETFS_READAHEAD) return 0; @@ -498,6 +503,11 @@ const struct netfs_request_ops ceph_netfs_ops = { }; #ifdef CONFIG_CEPH_FSCACHE +static void ceph_set_page_fscache(struct page *page) +{ + folio_start_private_2(page_folio(page)); /* [DEPRECATED] */ +} + static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async) { struct inode *inode = priv; @@ -515,6 +525,10 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b ceph_fscache_write_terminated, inode, true, caching); } #else +static inline void ceph_set_page_fscache(struct page *page) +{ +} + static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching) { } @@ -706,6 +720,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) len = wlen; set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); ceph_fscache_write_to_cache(inode, page_off, len, caching); if (IS_ENCRYPTED(inode)) { @@ -789,6 +805,8 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc) return AOP_WRITEPAGE_ACTIVATE; } + folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */ + err = writepage_nounlock(page, wbc); if (err == -ERESTARTSYS) { /* direct memory reclaimer was killed by SIGKILL. return 0 @@ -1062,7 +1080,8 @@ get_more_pages: unlock_page(page); break; } - if (PageWriteback(page)) { + if (PageWriteback(page) || + PagePrivate2(page) /* [DEPRECATED] */) { if (wbc->sync_mode == WB_SYNC_NONE) { doutc(cl, "%p under writeback\n", page); unlock_page(page); @@ -1070,6 +1089,7 @@ get_more_pages: } doutc(cl, "waiting on writeback %p\n", page); wait_on_page_writeback(page); + folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */ } if (!clear_page_dirty_for_io(page)) { @@ -1254,6 +1274,8 @@ new_request: } set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); len += thp_size(page); } ceph_fscache_write_to_cache(inode, offset, len, caching); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 8f8de8f33abb..71cd70514efa 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -577,8 +577,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb) /* Set parameters for the netfs library */ netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false); - /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ - __set_bit(NETFS_ICTX_USE_PGPRIV2, &ci->netfs.flags); spin_lock_init(&ci->i_ceph_lock); diff --git a/fs/exec.c b/fs/exec.c index a126e3d1cacb..50e76cc633c4 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1692,6 +1692,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) unsigned int mode; vfsuid_t vfsuid; vfsgid_t vfsgid; + int err; if (!mnt_may_suid(file->f_path.mnt)) return; @@ -1708,12 +1709,17 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) /* Be careful if suid/sgid is set */ inode_lock(inode); - /* reload atomically mode/uid/gid now that lock held */ + /* Atomically reload and check mode/uid/gid now that lock held. */ mode = inode->i_mode; vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid = i_gid_into_vfsgid(idmap, inode); + err = inode_permission(idmap, inode, MAY_EXEC); inode_unlock(inode); + /* Did the exec bit vanish out from under us? Give up. */ + if (err) + return; + /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) || !vfsgid_has_mapping(bprm->cred->user_ns, vfsgid)) diff --git a/fs/file.c b/fs/file.c index a11e59b5d602..655338effe9c 100644 --- a/fs/file.c +++ b/fs/file.c @@ -46,27 +46,23 @@ static void free_fdtable_rcu(struct rcu_head *rcu) #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) +#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ -static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, - unsigned int count) +static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, + unsigned int copy_words) { - unsigned int cpy, set; - - cpy = count / BITS_PER_BYTE; - set = (nfdt->max_fds - count) / BITS_PER_BYTE; - memcpy(nfdt->open_fds, ofdt->open_fds, cpy); - memset((char *)nfdt->open_fds + cpy, 0, set); - memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); - memset((char *)nfdt->close_on_exec + cpy, 0, set); - - cpy = BITBIT_SIZE(count); - set = BITBIT_SIZE(nfdt->max_fds) - cpy; - memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); - memset((char *)nfdt->full_fds_bits + cpy, 0, set); + unsigned int nwords = fdt_words(nfdt); + + bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, + copy_words, nwords); } /* @@ -84,7 +80,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); - copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); + copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* @@ -379,7 +375,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int open_files = sane_fdtable_size(old_fdt, max_fds); } - copy_fd_bitmaps(new_fdt, old_fdt, open_files); + copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; diff --git a/fs/inode.c b/fs/inode.c index 86670941884b..10c4619faeef 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -488,6 +488,39 @@ static void inode_lru_list_del(struct inode *inode) this_cpu_dec(nr_unused); } +static void inode_pin_lru_isolating(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); + inode->i_state |= I_LRU_ISOLATING; +} + +static void inode_unpin_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); + inode->i_state &= ~I_LRU_ISOLATING; + smp_mb(); + wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); +} + +static void inode_wait_for_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + if (inode->i_state & I_LRU_ISOLATING) { + DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); + __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); + spin_lock(&inode->i_lock); + WARN_ON(inode->i_state & I_LRU_ISOLATING); + } + spin_unlock(&inode->i_lock); +} + /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add @@ -657,6 +690,8 @@ static void evict(struct inode *inode) inode_sb_list_del(inode); + inode_wait_for_lru_isolating(inode); + /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since @@ -855,7 +890,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, * be under pressure before the cache inside the highmem zone. */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { - __iget(inode); + inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { @@ -867,7 +902,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); } - iput(inode); + inode_unpin_lru_isolating(inode); spin_lock(lru_lock); return LRU_RETRY; } diff --git a/fs/libfs.c b/fs/libfs.c index 8aa34870449f..02602d00939e 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -450,6 +450,14 @@ void simple_offset_destroy(struct offset_ctx *octx) mtree_destroy(&octx->mt); } +static int offset_dir_open(struct inode *inode, struct file *file) +{ + struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); + + file->private_data = (void *)ctx->next_offset; + return 0; +} + /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated @@ -463,6 +471,9 @@ void simple_offset_destroy(struct offset_ctx *octx) */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { + struct inode *inode = file->f_inode; + struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); + switch (whence) { case SEEK_CUR: offset += file->f_pos; @@ -476,7 +487,8 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) } /* In this case, ->private_data is protected by f_pos_lock */ - file->private_data = NULL; + if (!offset) + file->private_data = (void *)ctx->next_offset; return vfs_setpos(file, offset, LONG_MAX); } @@ -507,7 +519,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } -static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) +static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index) { struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *dentry; @@ -515,17 +527,21 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) while (true) { dentry = offset_find_next(octx, ctx->pos); if (!dentry) - return ERR_PTR(-ENOENT); + return; + + if (dentry2offset(dentry) >= last_index) { + dput(dentry); + return; + } if (!offset_dir_emit(ctx, dentry)) { dput(dentry); - break; + return; } ctx->pos = dentry2offset(dentry) + 1; dput(dentry); } - return NULL; } /** @@ -552,22 +568,19 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; + long last_index = (long)file->private_data; lockdep_assert_held(&d_inode(dir)->i_rwsem); if (!dir_emit_dots(file, ctx)) return 0; - /* In this case, ->private_data is protected by f_pos_lock */ - if (ctx->pos == DIR_OFFSET_MIN) - file->private_data = NULL; - else if (file->private_data == ERR_PTR(-ENOENT)) - return 0; - file->private_data = offset_iterate_dir(d_inode(dir), ctx); + offset_iterate_dir(d_inode(dir), ctx, last_index); return 0; } const struct file_operations simple_offset_dir_operations = { + .open = offset_dir_open, .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, diff --git a/fs/locks.c b/fs/locks.c index 9afb16e0683f..e45cad40f8b6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2984,7 +2984,7 @@ static int __init filelock_init(void) filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); - filelease_cache = kmem_cache_create("file_lock_cache", + filelease_cache = kmem_cache_create("file_lease_cache", sizeof(struct file_lease), 0, SLAB_PANIC, NULL); for_each_possible_cpu(i) { diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig index 1b78e8b65ebc..7701c037c328 100644 --- a/fs/netfs/Kconfig +++ b/fs/netfs/Kconfig @@ -24,7 +24,7 @@ config NETFS_STATS config NETFS_DEBUG bool "Enable dynamic debugging netfslib and FS-Cache" - depends on NETFS + depends on NETFS_SUPPORT help This permits debugging to be dynamically enabled in the local caching management module. If this is set, the debugging output may be diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index a688d4c75d99..27c750d39476 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -10,6 +10,97 @@ #include "internal.h" /* + * [DEPRECATED] Unlock the folios in a read operation for when the filesystem + * is using PG_private_2 and direct writing to the cache from here rather than + * marking the page for writeback. + * + * Note that we don't touch folio->private in this code. + */ +static void netfs_rreq_unlock_folios_pgpriv2(struct netfs_io_request *rreq, + size_t *account) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + bool subreq_failed = false; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + /* Walk through the pagecache and the I/O request lists simultaneously. + * We may have a mixture of cached and uncached sections and we only + * really want to write out the uncached sections. This is slightly + * complicated by the possibility that we might have huge pages with a + * mixture inside. + */ + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + subreq_failed = (subreq->error < 0); + + trace_netfs_rreq(rreq, netfs_rreq_trace_unlock_pgpriv2); + + rcu_read_lock(); + xas_for_each(&xas, folio, last_page) { + loff_t pg_end; + bool pg_failed = false; + bool folio_started = false; + + if (xas_retry(&xas, folio)) + continue; + + pg_end = folio_pos(folio) + folio_size(folio) - 1; + + for (;;) { + loff_t sreq_end; + + if (!subreq) { + pg_failed = true; + break; + } + + if (!folio_started && + test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags) && + fscache_operation_valid(&rreq->cache_resources)) { + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); + folio_start_private_2(folio); + folio_started = true; + } + + pg_failed |= subreq_failed; + sreq_end = subreq->start + subreq->len - 1; + if (pg_end < sreq_end) + break; + + *account += subreq->transferred; + if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + + if (pg_end == sreq_end) + break; + } + + if (!pg_failed) { + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio->index == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) + _debug("no unlock"); + else + folio_unlock(folio); + } + } + rcu_read_unlock(); +} + +/* * Unlock the folios in a read operation. We need to set PG_writeback on any * folios we're going to write back before we unlock them. * @@ -35,6 +126,12 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) } } + /* Handle deprecated PG_private_2 case. */ + if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + netfs_rreq_unlock_folios_pgpriv2(rreq, &account); + goto out; + } + /* Walk through the pagecache and the I/O request lists simultaneously. * We may have a mixture of cached and uncached sections and we only * really want to write out the uncached sections. This is slightly @@ -52,7 +149,6 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) loff_t pg_end; bool pg_failed = false; bool wback_to_cache = false; - bool folio_started = false; if (xas_retry(&xas, folio)) continue; @@ -66,17 +162,8 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) pg_failed = true; break; } - if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { - if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE, - &subreq->flags)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); - folio_started = true; - } - } else { - wback_to_cache |= - test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); - } + + wback_to_cache |= test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); pg_failed |= subreq_failed; sreq_end = subreq->start + subreq->len - 1; if (pg_end < sreq_end) @@ -124,6 +211,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) } rcu_read_unlock(); +out: task_io_account_read(account); if (rreq->netfs_ops->done) rreq->netfs_ops->done(rreq); @@ -395,7 +483,7 @@ zero_out: } /** - * netfs_write_begin - Helper to prepare for writing + * netfs_write_begin - Helper to prepare for writing [DEPRECATED] * @ctx: The netfs context * @file: The file to read from * @mapping: The mapping to read from @@ -426,6 +514,9 @@ zero_out: * inode before calling this. * * This is usable whether or not caching is enabled. + * + * Note that this should be considered deprecated and netfs_perform_write() + * used instead. */ int netfs_write_begin(struct netfs_inode *ctx, struct file *file, struct address_space *mapping, @@ -466,7 +557,7 @@ retry: if (!netfs_is_cache_enabled(ctx) && netfs_skip_folio_read(folio, pos, len, false)) { netfs_stat(&netfs_n_rh_write_zskip); - goto have_folio; + goto have_folio_no_wait; } rreq = netfs_alloc_request(mapping, file, @@ -507,6 +598,10 @@ retry: netfs_put_request(rreq, false, netfs_rreq_trace_put_return); have_folio: + ret = folio_wait_private_2_killable(folio); + if (ret < 0) + goto error; +have_folio_no_wait: *_folio = folio; _leave(" = 0"); return 0; diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 4726c315453c..ca53c5d1622e 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -184,7 +184,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0; ssize_t written = 0, ret, ret2; loff_t i_size, pos = iocb->ki_pos, from, to; - size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; + size_t max_chunk = mapping_max_folio_size(mapping); bool maybe_trouble = false; if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) || diff --git a/fs/netfs/fscache_cookie.c b/fs/netfs/fscache_cookie.c index bce2492186d0..d4d4b3a8b106 100644 --- a/fs/netfs/fscache_cookie.c +++ b/fs/netfs/fscache_cookie.c @@ -741,6 +741,10 @@ again_locked: spin_lock(&cookie->lock); } if (test_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) { + if (atomic_read(&cookie->n_accesses) != 0) + /* still being accessed: postpone it */ + break; + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_LRU_DISCARDING); wake = true; diff --git a/fs/netfs/io.c b/fs/netfs/io.c index c93851b98368..5367caf3fa28 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -99,6 +99,146 @@ static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async) } /* + * [DEPRECATED] Deal with the completion of writing the data to the cache. We + * have to clear the PG_fscache bits on the folios involved and release the + * caller's ref. + * + * May be called in softirq mode and we inherit a ref from the caller. + */ +static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, + bool was_async) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t unlocked = 0; + bool have_unlocked = false; + + rcu_read_lock(); + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); + + xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { + if (xas_retry(&xas, folio)) + continue; + + /* We might have multiple writes from the same huge + * folio, but we mustn't unlock a folio more than once. + */ + if (have_unlocked && folio->index <= unlocked) + continue; + unlocked = folio_next_index(folio) - 1; + trace_netfs_folio(folio, netfs_folio_trace_end_copy); + folio_end_private_2(folio); + have_unlocked = true; + } + } + + rcu_read_unlock(); + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) /* [DEPRECATED] */ +{ + struct netfs_io_subrequest *subreq = priv; + struct netfs_io_request *rreq = subreq->rreq; + + if (IS_ERR_VALUE(transferred_or_error)) { + netfs_stat(&netfs_n_rh_write_failed); + trace_netfs_failure(rreq, subreq, transferred_or_error, + netfs_fail_copy_to_cache); + } else { + netfs_stat(&netfs_n_rh_write_done); + } + + trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); + + /* If we decrement nr_copy_ops to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, was_async); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); +} + +/* + * [DEPRECATED] Perform any outstanding writes to the cache. We inherit a ref + * from the caller. + */ +static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct netfs_io_subrequest *subreq, *next, *p; + struct iov_iter iter; + int ret; + + trace_netfs_rreq(rreq, netfs_rreq_trace_copy); + + /* We don't want terminating writes trying to wake us up whilst we're + * still going through the list. + */ + atomic_inc(&rreq->nr_copy_ops); + + list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { + if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + list_del_init(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_no_copy); + } + } + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + /* Amalgamate adjacent writes */ + while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + next = list_next_entry(subreq, rreq_link); + if (next->start != subreq->start + subreq->len) + break; + subreq->len += next->len; + list_del_init(&next->rreq_link); + netfs_put_subrequest(next, false, + netfs_sreq_trace_put_merged); + } + + ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, + subreq->len, rreq->i_size, true); + if (ret < 0) { + trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); + trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); + continue; + } + + iov_iter_xarray(&iter, ITER_SOURCE, &rreq->mapping->i_pages, + subreq->start, subreq->len); + + atomic_inc(&rreq->nr_copy_ops); + netfs_stat(&netfs_n_rh_write); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache); + trace_netfs_sreq(subreq, netfs_sreq_trace_write); + cres->ops->write(cres, subreq->start, &iter, + netfs_rreq_copy_terminated, subreq); + } + + /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, false); +} + +static void netfs_rreq_write_to_cache_work(struct work_struct *work) /* [DEPRECATED] */ +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + + netfs_rreq_do_write_to_cache(rreq); +} + +static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) /* [DEPRECATED] */ +{ + rreq->work.func = netfs_rreq_write_to_cache_work; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); +} + +/* * Handle a short read. */ static void netfs_rreq_short_read(struct netfs_io_request *rreq, @@ -275,6 +415,10 @@ again: clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags) && + test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) + return netfs_rreq_write_to_cache(rreq); + netfs_rreq_completed(rreq, was_async); } @@ -386,7 +530,8 @@ incomplete: if (transferred_or_error == 0) { if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { - subreq->error = -ENODATA; + if (rreq->origin != NETFS_DIO_READ) + subreq->error = -ENODATA; goto failed; } } else { @@ -457,9 +602,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq, } if (subreq->len > ictx->zero_point - subreq->start) subreq->len = ictx->zero_point - subreq->start; + + /* We limit buffered reads to the EOF, but let the + * server deal with larger-than-EOF DIO/unbuffered + * reads. + */ + if (subreq->len > rreq->i_size - subreq->start) + subreq->len = rreq->i_size - subreq->start; } - if (subreq->len > rreq->i_size - subreq->start) - subreq->len = rreq->i_size - subreq->start; if (rreq->rsize && subreq->len > rreq->rsize) subreq->len = rreq->rsize; @@ -595,11 +745,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync) do { _debug("submit %llx + %llx >= %llx", rreq->start, rreq->submitted, rreq->i_size); - if (rreq->origin == NETFS_DIO_READ && - rreq->start + rreq->submitted >= rreq->i_size) - break; if (!netfs_rreq_submit_slice(rreq, &io_iter)) break; + if (test_bit(NETFS_SREQ_NO_PROGRESS, &rreq->flags)) + break; if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) && test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags)) break; diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index f4a642727479..0294df70c3ff 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -24,10 +24,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, struct netfs_io_request *rreq; mempool_t *mempool = ctx->ops->request_pool ?: &netfs_request_pool; struct kmem_cache *cache = mempool->pool_data; - bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE || - origin == NETFS_DIO_READ || - origin == NETFS_DIO_WRITE); - bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx); int ret; for (;;) { @@ -56,12 +52,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, refcount_set(&rreq->ref, 1); __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - if (cached) { - __set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); - if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) - /* Filesystem uses deprecated PG_private_2 marking. */ - __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); - } if (file && file->f_flags & O_NONBLOCK) __set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags); if (rreq->netfs_ops->init_request) { diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 9258d30cffe3..3f7e37e50c7d 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -94,6 +94,8 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, { struct netfs_io_request *wreq; struct netfs_inode *ictx; + bool is_buffered = (origin == NETFS_WRITEBACK || + origin == NETFS_WRITETHROUGH); wreq = netfs_alloc_request(mapping, file, start, 0, origin); if (IS_ERR(wreq)) @@ -102,7 +104,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, _enter("R=%x", wreq->debug_id); ictx = netfs_inode(wreq->inode); - if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags)) + if (is_buffered && netfs_is_cache_enabled(ictx)) fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx)); wreq->contiguity = wreq->start; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 7202ce84d0eb..7a558dea75c4 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -265,6 +265,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi { rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); + /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ + __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); return 0; } @@ -361,7 +363,8 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr) return; sreq = netfs->sreq; - if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) + if (test_bit(NFS_IOHDR_EOF, &hdr->flags) && + sreq->rreq->origin != NETFS_DIO_READ) __set_bit(NETFS_SREQ_CLEAR_TAIL, &sreq->flags); if (hdr->error) diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index fbed0027996f..e8adae1bc260 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -81,8 +81,6 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) { netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false); - /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ - __set_bit(NETFS_ICTX_USE_PGPRIV2, &nfsi->netfs.flags); } extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr); extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr); diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index b2405dd4d4d4..3f3842e7b44a 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -217,7 +217,8 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq) goto out; } - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (subreq->rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); rc = rdata->server->ops->async_readv(rdata); out: diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index e0a6b758094f..d8d03070ae44 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -15,6 +15,7 @@ #include "share_config.h" #include "user_config.h" #include "user_session.h" +#include "../connection.h" #include "../transport_ipc.h" #include "../misc.h" @@ -120,12 +121,13 @@ static int parse_veto_list(struct ksmbd_share_config *share, return 0; } -static struct ksmbd_share_config *share_config_request(struct unicode_map *um, +static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work, const char *name) { struct ksmbd_share_config_response *resp; struct ksmbd_share_config *share = NULL; struct ksmbd_share_config *lookup; + struct unicode_map *um = work->conn->um; int ret; resp = ksmbd_ipc_share_config_request(name); @@ -181,7 +183,14 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um, KSMBD_SHARE_CONFIG_VETO_LIST(resp), resp->veto_list_sz); if (!ret && share->path) { + if (__ksmbd_override_fsids(work, share)) { + kill_share(share); + share = NULL; + goto out; + } + ret = kern_path(share->path, 0, &share->vfs_path); + ksmbd_revert_fsids(work); if (ret) { ksmbd_debug(SMB, "failed to access '%s'\n", share->path); @@ -214,7 +223,7 @@ out: return share; } -struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um, +struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work, const char *name) { struct ksmbd_share_config *share; @@ -227,7 +236,7 @@ struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um, if (share) return share; - return share_config_request(um, name); + return share_config_request(work, name); } bool ksmbd_share_veto_filename(struct ksmbd_share_config *share, diff --git a/fs/smb/server/mgmt/share_config.h b/fs/smb/server/mgmt/share_config.h index 5f591751b923..d4ac2dd4de20 100644 --- a/fs/smb/server/mgmt/share_config.h +++ b/fs/smb/server/mgmt/share_config.h @@ -11,6 +11,8 @@ #include <linux/path.h> #include <linux/unicode.h> +struct ksmbd_work; + struct ksmbd_share_config { char *name; char *path; @@ -68,7 +70,7 @@ static inline void ksmbd_share_config_put(struct ksmbd_share_config *share) __ksmbd_share_config_put(share); } -struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um, +struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work, const char *name); bool ksmbd_share_veto_filename(struct ksmbd_share_config *share, const char *filename); diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index d2c81a8a11dd..94a52a75014a 100644 --- a/fs/smb/server/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c @@ -16,17 +16,18 @@ #include "user_session.h" struct ksmbd_tree_conn_status -ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, - const char *share_name) +ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name) { struct ksmbd_tree_conn_status status = {-ENOENT, NULL}; struct ksmbd_tree_connect_response *resp = NULL; struct ksmbd_share_config *sc; struct ksmbd_tree_connect *tree_conn = NULL; struct sockaddr *peer_addr; + struct ksmbd_conn *conn = work->conn; + struct ksmbd_session *sess = work->sess; int ret; - sc = ksmbd_share_config_get(conn->um, share_name); + sc = ksmbd_share_config_get(work, share_name); if (!sc) return status; @@ -61,7 +62,7 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, struct ksmbd_share_config *new_sc; ksmbd_share_config_del(sc); - new_sc = ksmbd_share_config_get(conn->um, share_name); + new_sc = ksmbd_share_config_get(work, share_name); if (!new_sc) { pr_err("Failed to update stale share config\n"); status.ret = -ESTALE; diff --git a/fs/smb/server/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h index 6377a70b811c..a42cdd051041 100644 --- a/fs/smb/server/mgmt/tree_connect.h +++ b/fs/smb/server/mgmt/tree_connect.h @@ -13,6 +13,7 @@ struct ksmbd_share_config; struct ksmbd_user; struct ksmbd_conn; +struct ksmbd_work; enum { TREE_NEW = 0, @@ -50,8 +51,7 @@ static inline int test_tree_conn_flag(struct ksmbd_tree_connect *tree_conn, struct ksmbd_session; struct ksmbd_tree_conn_status -ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, - const char *share_name); +ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name); void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon); int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 37a39ab4ee65..2df1354288e6 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1955,7 +1955,7 @@ int smb2_tree_connect(struct ksmbd_work *work) ksmbd_debug(SMB, "tree connect request for tree %s treename %s\n", name, treename); - status = ksmbd_tree_conn_connect(conn, sess, name); + status = ksmbd_tree_conn_connect(work, name); if (status.ret == KSMBD_TREE_CONN_STATUS_OK) rsp->hdr.Id.SyncId.TreeId = cpu_to_le32(status.tree_conn->id); else @@ -5596,6 +5596,11 @@ int smb2_query_info(struct ksmbd_work *work) ksmbd_debug(SMB, "GOT query info request\n"); + if (ksmbd_override_fsids(work)) { + rc = -ENOMEM; + goto err_out; + } + switch (req->InfoType) { case SMB2_O_INFO_FILE: ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n"); @@ -5614,6 +5619,7 @@ int smb2_query_info(struct ksmbd_work *work) req->InfoType); rc = -EOPNOTSUPP; } + ksmbd_revert_fsids(work); if (!rc) { rsp->StructureSize = cpu_to_le16(9); @@ -5623,6 +5629,7 @@ int smb2_query_info(struct ksmbd_work *work) le32_to_cpu(rsp->OutputBufferLength)); } +err_out: if (rc < 0) { if (rc == -EACCES) rsp->hdr.Status = STATUS_ACCESS_DENIED; diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index 474dadf6b7b8..13818ecb6e1b 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -732,10 +732,10 @@ bool is_asterisk(char *p) return p && p[0] == '*'; } -int ksmbd_override_fsids(struct ksmbd_work *work) +int __ksmbd_override_fsids(struct ksmbd_work *work, + struct ksmbd_share_config *share) { struct ksmbd_session *sess = work->sess; - struct ksmbd_share_config *share = work->tcon->share_conf; struct cred *cred; struct group_info *gi; unsigned int uid; @@ -775,6 +775,11 @@ int ksmbd_override_fsids(struct ksmbd_work *work) return 0; } +int ksmbd_override_fsids(struct ksmbd_work *work) +{ + return __ksmbd_override_fsids(work, work->tcon->share_conf); +} + void ksmbd_revert_fsids(struct ksmbd_work *work) { const struct cred *cred; diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h index f1092519c0c2..4a3148b0167f 100644 --- a/fs/smb/server/smb_common.h +++ b/fs/smb/server/smb_common.h @@ -447,6 +447,8 @@ int ksmbd_extract_shortname(struct ksmbd_conn *conn, int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command); int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp); +int __ksmbd_override_fsids(struct ksmbd_work *work, + struct ksmbd_share_config *share); int ksmbd_override_fsids(struct ksmbd_work *work); void ksmbd_revert_fsids(struct ksmbd_work *work); diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index 16bd693d0b3a..d5918eba27e3 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -279,8 +279,13 @@ int squashfs_read_inode(struct inode *inode, long long ino) if (err < 0) goto failed_read; - set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le32_to_cpu(sqsh_ino->symlink_size); + if (inode->i_size > PAGE_SIZE) { + ERROR("Corrupted symlink\n"); + return -EINVAL; + } + + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_op = &squashfs_symlink_inode_ops; inode_nohighmem(inode); inode->i_data.a_ops = &squashfs_symlink_aops; diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 8c4768c44a01..d3b66d77df7a 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -270,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); } +static inline void bitmap_copy_and_extend(unsigned long *to, + const unsigned long *from, + unsigned int count, unsigned int size) +{ + unsigned int copy = BITS_TO_LONGS(count); + + memcpy(to, from, copy * sizeof(long)); + if (count % BITS_PER_LONG) + to[copy - 1] &= BITMAP_LAST_WORD_MASK(count); + memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long)); +} + /* * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 * machines the order of hi and lo parts of numbers match the bitmap structure. diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 6503c85b10a3..7b776dae36e5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -856,8 +856,8 @@ static inline u32 type_flag(u32 type) /* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) { - return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ? - prog->aux->dst_prog->type : prog->type; + return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ? + prog->aux->saved_dst_prog_type : prog->type; } static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) diff --git a/include/linux/file.h b/include/linux/file.h index 237931f20739..59b146a14dca 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -110,7 +110,7 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), * * f = dentry_open(&path, O_RDONLY, current_cred()); * if (IS_ERR(f)) - * return PTR_ERR(fd); + * return PTR_ERR(f); * * fd_install(fd, f); * return take_fd(fd); diff --git a/include/linux/fs.h b/include/linux/fs.h index fd34b5755c0b..fb0426f349fc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2392,6 +2392,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2415,6 +2418,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define I_PINNING_NETFS_WB (1 << 18) +#define __I_LRU_ISOLATING 19 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 79a6b1a63027..b23c6d48392f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -715,6 +715,13 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm) } #endif +#ifndef kvm_arch_has_readonly_mem +static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) +{ + return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); +} +#endif + struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5d0288938cc2..983816608f15 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -73,8 +73,6 @@ struct netfs_inode { #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ -#define NETFS_ICTX_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark - * write to cache on read */ }; /* @@ -269,7 +267,6 @@ struct netfs_io_request { #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ -#define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */ #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ #define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ #define NETFS_RREQ_BLOCKED 10 /* We blocked */ diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 59b3b752394d..35f039ecb272 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -266,12 +266,12 @@ bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) if (oldp) *oldp = old; - if (old == i) { + if (old > 0 && old == i) { smp_acquire__after_ctrl_dep(); return true; } - if (unlikely(old < 0 || old - i < 0)) + if (unlikely(old <= 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 535701efc1e5..24d970f7a4fa 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -230,8 +230,12 @@ struct vsock_tap { int vsock_add_tap(struct vsock_tap *vt); int vsock_remove_tap(struct vsock_tap *vt); void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque); +int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags); int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 6439fd8b437b..7caa334f4888 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -275,6 +275,7 @@ struct mana_cq { /* NAPI data */ struct napi_struct napi; int work_done; + int work_done_since_doorbell; int budget; }; diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index da23484268df..606b4a0f92da 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -51,6 +51,7 @@ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ EM(netfs_rreq_trace_set_pause, "PAUSE ") \ EM(netfs_rreq_trace_unlock, "UNLOCK ") \ + EM(netfs_rreq_trace_unlock_pgpriv2, "UNLCK-2") \ EM(netfs_rreq_trace_unmark, "UNMARK ") \ EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ EM(netfs_rreq_trace_wait_pause, "WT-PAUS") \ @@ -145,6 +146,7 @@ EM(netfs_folio_trace_clear_g, "clear-g") \ EM(netfs_folio_trace_clear_s, "clear-s") \ EM(netfs_folio_trace_copy_to_cache, "mark-copy") \ + EM(netfs_folio_trace_end_copy, "end-copy") \ EM(netfs_folio_trace_filled_gaps, "filled-gaps") \ EM(netfs_folio_trace_kill, "kill") \ EM(netfs_folio_trace_kill_cc, "kill-cc") \ diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index b133211331f6..5fad3d0fcd70 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -3,6 +3,7 @@ #define __LINUX_NSFS_H #include <linux/ioctl.h> +#include <linux/types.h> #define NSIO 0xb7 @@ -16,7 +17,7 @@ /* Get owner UID (in the caller's user namespace) for a user namespace */ #define NS_GET_OWNER_UID _IO(NSIO, 0x4) /* Get the id for a mount namespace */ -#define NS_GET_MNTNS_ID _IO(NSIO, 0x5) +#define NS_GET_MNTNS_ID _IOR(NSIO, 0x5, __u64) /* Translate pid from target pid namespace into the caller's pid namespace. */ #define NS_GET_PID_FROM_PIDNS _IOR(NSIO, 0x6, int) /* Return thread-group leader id of pid in the callers pid namespace. */ diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 2289b7c76c59..832c15d9155b 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -51,6 +51,7 @@ typedef enum { SEV_RET_INVALID_PLATFORM_STATE, SEV_RET_INVALID_GUEST_STATE, SEV_RET_INAVLID_CONFIG, + SEV_RET_INVALID_CONFIG = SEV_RET_INAVLID_CONFIG, SEV_RET_INVALID_LEN, SEV_RET_ALREADY_OWNED, SEV_RET_INVALID_CERTIFICATE, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4cb5441ad75f..d8520095ca03 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -16884,8 +16884,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, spi = i / BPF_REG_SIZE; if (exact != NOT_EXACT && - old->stack[spi].slot_type[i % BPF_REG_SIZE] != - cur->stack[spi].slot_type[i % BPF_REG_SIZE]) + (i >= cur->allocated_stack || + old->stack[spi].slot_type[i % BPF_REG_SIZE] != + cur->stack[spi].slot_type[i % BPF_REG_SIZE])) return false; if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ) diff --git a/kernel/events/core.c b/kernel/events/core.c index aa3450bdc227..c973e3c11e03 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9706,7 +9706,8 @@ static int __perf_event_overflow(struct perf_event *event, ret = __perf_event_account_interrupt(event, throttle); - if (event->prog && !bpf_overflow_handler(event, data, regs)) + if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT && + !bpf_overflow_handler(event, data, regs)) return ret; /* diff --git a/kernel/fork.c b/kernel/fork.c index cc760491f201..18bdc87209d0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2053,11 +2053,24 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { - bool thread = flags & PIDFD_THREAD; - - if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID)) + if (!pid) return -EINVAL; + scoped_guard(rcu) { + struct task_struct *tsk; + + if (flags & PIDFD_THREAD) + tsk = pid_task(pid, PIDTYPE_PID); + else + tsk = pid_task(pid, PIDTYPE_TGID); + if (!tsk) + return -EINVAL; + + /* Don't create pidfds for kernel threads for now. */ + if (tsk->flags & PF_KTHREAD) + return -EINVAL; + } + return __pidfd_prepare(pid, flags, ret); } @@ -2403,6 +2416,12 @@ __latent_entropy struct task_struct *copy_process( if (clone_flags & CLONE_PIDFD) { int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; + /* Don't create pidfds for kernel threads for now. */ + if (args->kthread) { + retval = -EINVAL; + goto bad_fork_free_pid; + } + /* Note that no task has been attached to @pid yet. */ retval = __pidfd_prepare(pid, flags, &pidfile); if (retval < 0) diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index fb2c77368d18..a9a0ca605d4a 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -160,38 +160,6 @@ unsigned long kallsyms_sym_address(int idx) return kallsyms_relative_base - 1 - kallsyms_offsets[idx]; } -static void cleanup_symbol_name(char *s) -{ - char *res; - - if (!IS_ENABLED(CONFIG_LTO_CLANG)) - return; - - /* - * LLVM appends various suffixes for local functions and variables that - * must be promoted to global scope as part of LTO. This can break - * hooking of static functions with kprobes. '.' is not a valid - * character in an identifier in C. Suffixes only in LLVM LTO observed: - * - foo.llvm.[0-9a-f]+ - */ - res = strstr(s, ".llvm."); - if (res) - *res = '\0'; - - return; -} - -static int compare_symbol_name(const char *name, char *namebuf) -{ - /* The kallsyms_seqs_of_names is sorted based on names after - * cleanup_symbol_name() (see scripts/kallsyms.c) if clang lto is enabled. - * To ensure correct bisection in kallsyms_lookup_names(), do - * cleanup_symbol_name(namebuf) before comparing name and namebuf. - */ - cleanup_symbol_name(namebuf); - return strcmp(name, namebuf); -} - static unsigned int get_symbol_seq(int index) { unsigned int i, seq = 0; @@ -219,7 +187,7 @@ static int kallsyms_lookup_names(const char *name, seq = get_symbol_seq(mid); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - ret = compare_symbol_name(name, namebuf); + ret = strcmp(name, namebuf); if (ret > 0) low = mid + 1; else if (ret < 0) @@ -236,7 +204,7 @@ static int kallsyms_lookup_names(const char *name, seq = get_symbol_seq(low - 1); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - if (compare_symbol_name(name, namebuf)) + if (strcmp(name, namebuf)) break; low--; } @@ -248,7 +216,7 @@ static int kallsyms_lookup_names(const char *name, seq = get_symbol_seq(high + 1); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - if (compare_symbol_name(name, namebuf)) + if (strcmp(name, namebuf)) break; high++; } @@ -407,8 +375,7 @@ static int kallsyms_lookup_buildid(unsigned long addr, if (modbuildid) *modbuildid = NULL; - ret = strlen(namebuf); - goto found; + return strlen(namebuf); } /* See if it's in a module or a BPF JITed image. */ @@ -422,8 +389,6 @@ static int kallsyms_lookup_buildid(unsigned long addr, ret = ftrace_mod_address_lookup(addr, symbolsize, offset, modname, namebuf); -found: - cleanup_symbol_name(namebuf); return ret; } @@ -450,8 +415,6 @@ const char *kallsyms_lookup(unsigned long addr, int lookup_symbol_name(unsigned long addr, char *symname) { - int res; - symname[0] = '\0'; symname[KSYM_NAME_LEN - 1] = '\0'; @@ -462,16 +425,10 @@ int lookup_symbol_name(unsigned long addr, char *symname) /* Grab name */ kallsyms_expand_symbol(get_symbol_offset(pos), symname, KSYM_NAME_LEN); - goto found; + return 0; } /* See if it's in a module. */ - res = lookup_module_symbol_name(addr, symname); - if (res) - return res; - -found: - cleanup_symbol_name(symname); - return 0; + return lookup_module_symbol_name(addr, symname); } /* Look up a kernel symbol and return it in a text buffer. */ diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c index 2f84896a7bcb..873f7c445488 100644 --- a/kernel/kallsyms_selftest.c +++ b/kernel/kallsyms_selftest.c @@ -187,31 +187,11 @@ static void test_perf_kallsyms_lookup_name(void) stat.min, stat.max, div_u64(stat.sum, stat.real_cnt)); } -static bool match_cleanup_name(const char *s, const char *name) -{ - char *p; - int len; - - if (!IS_ENABLED(CONFIG_LTO_CLANG)) - return false; - - p = strstr(s, ".llvm."); - if (!p) - return false; - - len = strlen(name); - if (p - s != len) - return false; - - return !strncmp(s, name, len); -} - static int find_symbol(void *data, const char *name, unsigned long addr) { struct test_stat *stat = (struct test_stat *)data; - if (strcmp(name, stat->name) == 0 || - (!stat->perf && match_cleanup_name(name, stat->name))) { + if (!strcmp(name, stat->name)) { stat->real_cnt++; stat->addr = addr; diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c index f314a0c15a6d..2abc78367dd1 100644 --- a/lib/overflow_kunit.c +++ b/lib/overflow_kunit.c @@ -668,7 +668,6 @@ DEFINE_TEST_ALLOC(devm_kzalloc, devm_kfree, 1, 1, 0); static void overflow_allocation_test(struct kunit *test) { - const char device_name[] = "overflow-test"; struct device *dev; int count = 0; @@ -678,7 +677,7 @@ static void overflow_allocation_test(struct kunit *test) } while (0) /* Create dummy device for devm_kmalloc()-family tests. */ - dev = kunit_device_register(test, device_name); + dev = kunit_device_register(test, "overflow-test"); KUNIT_ASSERT_FALSE_MSG(test, IS_ERR(dev), "Cannot register test device\n"); diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 09f6a773a708..8f9c19d992ac 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -622,8 +622,12 @@ static unsigned int br_nf_local_in(void *priv, if (likely(nf_ct_is_confirmed(ct))) return NF_ACCEPT; + if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + WARN_ON_ONCE(skb_shared(skb)); - WARN_ON_ONCE(refcount_read(&nfct->use) != 1); /* We can't call nf_confirm here, it would create a dependency * on nf_conntrack module. diff --git a/net/core/dev.c b/net/core/dev.c index 751d9b70e6ad..f66e61407883 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9912,6 +9912,15 @@ static void netdev_sync_lower_features(struct net_device *upper, } } +static bool netdev_has_ip_or_hw_csum(netdev_features_t features) +{ + netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + bool ip_csum = (features & ip_csum_mask) == ip_csum_mask; + bool hw_csum = features & NETIF_F_HW_CSUM; + + return ip_csum || hw_csum; +} + static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { @@ -9993,15 +10002,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~NETIF_F_LRO; } - if (features & NETIF_F_HW_TLS_TX) { - bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) == - (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - bool hw_csum = features & NETIF_F_HW_CSUM; - - if (!ip_csum && !hw_csum) { - netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); - features &= ~NETIF_F_HW_TLS_TX; - } + if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) { + netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); + features &= ~NETIF_F_HW_TLS_TX; } if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { @@ -10009,6 +10012,11 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~NETIF_F_HW_TLS_RX; } + if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) { + netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n"); + features &= ~NETIF_F_GSO_UDP_L4; + } + return features; } diff --git a/net/ethtool/cmis_fw_update.c b/net/ethtool/cmis_fw_update.c index ae4b4b28a601..655ff5224ffa 100644 --- a/net/ethtool/cmis_fw_update.c +++ b/net/ethtool/cmis_fw_update.c @@ -35,7 +35,10 @@ struct cmis_cdb_fw_mng_features_rpl { __be16 resv7; }; -#define CMIS_CDB_FW_WRITE_MECHANISM_LPL 0x01 +enum cmis_cdb_fw_write_mechanism { + CMIS_CDB_FW_WRITE_MECHANISM_LPL = 0x01, + CMIS_CDB_FW_WRITE_MECHANISM_BOTH = 0x11, +}; static int cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb, @@ -64,7 +67,8 @@ cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb, } rpl = (struct cmis_cdb_fw_mng_features_rpl *)args.req.payload; - if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL)) { + if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL || + rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_BOTH)) { ethnl_module_fw_flash_ntf_err(dev, ntf_params, "Write LPL is not supported", NULL); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e2b9583ed96a..e37488d3453f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -238,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) */ if (unlikely(len != icsk->icsk_ack.rcv_mss)) { u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE; + u8 old_ratio = tcp_sk(sk)->scaling_ratio; do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; + + if (old_ratio != tcp_sk(sk)->scaling_ratio) + WRITE_ONCE(tcp_sk(sk)->window_clamp, + tcp_win_from_space(sk, sk->sk_rcvbuf)); } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); @@ -754,7 +759,8 @@ void tcp_rcv_space_adjust(struct sock *sk) * <prev RTT . ><current RTT .. ><next RTT .... > */ - if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) { + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && + !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { u64 rcvwin, grow; int rcvbuf; @@ -770,22 +776,12 @@ void tcp_rcv_space_adjust(struct sock *sk) rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin), READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); - if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - if (rcvbuf > sk->sk_rcvbuf) { - WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); - - /* Make the window clamp follow along. */ - WRITE_ONCE(tp->window_clamp, - tcp_win_from_space(sk, rcvbuf)); - } - } else { - /* Make the window clamp follow along while being bounded - * by SO_RCVBUF. - */ - int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf)); + if (rcvbuf > sk->sk_rcvbuf) { + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); - if (clamp > tp->window_clamp) - WRITE_ONCE(tp->window_clamp, clamp); + /* Make the window clamp follow along. */ + WRITE_ONCE(tp->window_clamp, + tcp_win_from_space(sk, rcvbuf)); } } tp->rcvq_space.space = copied; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index bc8a9da750fe..b254a5dadfcf 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -282,6 +282,12 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, skb_transport_header(gso_skb))) return ERR_PTR(-EINVAL); + /* We don't know if egress device can segment and checksum the packet + * when IPv6 extension headers are present. Fall back to software GSO. + */ + if (gso_skb->ip_summed != CHECKSUM_PARTIAL) + features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 6f0844c9315d..4120e67a8ce6 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -154,6 +154,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, }; struct inet_frag_queue *q; + if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST | + IPV6_ADDR_LINKLOCAL))) + key.iif = 0; + q = inet_frag_find(nf_frag->fqdir, &key); if (!q) return NULL; diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index 3ae46b545d2c..2d3efb405437 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk) nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */ nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */ - nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ + nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */ nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */ diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index ff1a4e36c2b5..e06bc36f49fe 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -841,8 +841,8 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable, struct list_head *block_cb_list) { struct flow_cls_offload cls_flow = {}; + struct netlink_ext_ack extack = {}; struct flow_block_cb *block_cb; - struct netlink_ext_ack extack; __be16 proto = ETH_P_ALL; int err, i = 0; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 481ee78e77bc..0a2f79346958 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8020,6 +8020,19 @@ cont: return skb->len; } +static int nf_tables_dumpreset_obj(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); + int ret; + + mutex_lock(&nft_net->commit_mutex); + ret = nf_tables_dump_obj(skb, cb); + mutex_unlock(&nft_net->commit_mutex); + + return ret; +} + static int nf_tables_dump_obj_start(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -8036,12 +8049,18 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb) if (nla[NFTA_OBJ_TYPE]) ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - ctx->reset = true; - return 0; } +static int nf_tables_dumpreset_obj_start(struct netlink_callback *cb) +{ + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; + + ctx->reset = true; + + return nf_tables_dump_obj_start(cb); +} + static int nf_tables_dump_obj_done(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -8052,8 +8071,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, - const struct nlattr * const nla[]) +static struct sk_buff * +nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, + const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); @@ -8062,72 +8082,109 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_object *obj; struct sk_buff *skb2; - bool reset = false; u32 objtype; int err; - if (info->nlh->nlmsg_flags & NLM_F_DUMP) { - struct netlink_dump_control c = { - .start = nf_tables_dump_obj_start, - .dump = nf_tables_dump_obj, - .done = nf_tables_dump_obj_done, - .module = THIS_MODULE, - .data = (void *)nla, - }; - - return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); - } - if (!nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_TYPE]) - return -EINVAL; + return ERR_PTR(-EINVAL); table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); - return PTR_ERR(table); + return ERR_CAST(table); } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); - return PTR_ERR(obj); + return ERR_CAST(obj); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) - return -ENOMEM; + return ERR_PTR(-ENOMEM); - if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - reset = true; + err = nf_tables_fill_obj_info(skb2, net, portid, + info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, + family, table, obj, reset); + if (err < 0) { + kfree_skb(skb2); + return ERR_PTR(err); + } - if (reset) { - const struct nftables_pernet *nft_net; - char *buf; + return skb2; +} - nft_net = nft_pernet(net); - buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq); +static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + u32 portid = NETLINK_CB(skb).portid; + struct sk_buff *skb2; - audit_log_nfcfg(buf, - family, - 1, - AUDIT_NFT_OP_OBJ_RESET, - GFP_ATOMIC); - kfree(buf); + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dump_obj_start, + .dump = nf_tables_dump_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } - err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, - info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, - family, table, obj, reset); - if (err < 0) - goto err_fill_obj_info; + skb2 = nf_tables_getobj_single(portid, info, nla, false); + if (IS_ERR(skb2)) + return PTR_ERR(skb2); - return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, info->net, portid); +} -err_fill_obj_info: - kfree_skb(skb2); - return err; +static int nf_tables_getobj_reset(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; + char *buf; + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dumpreset_obj_start, + .dump = nf_tables_dumpreset_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + if (!try_module_get(THIS_MODULE)) + return -EINVAL; + rcu_read_unlock(); + mutex_lock(&nft_net->commit_mutex); + skb2 = nf_tables_getobj_single(portid, info, nla, true); + mutex_unlock(&nft_net->commit_mutex); + rcu_read_lock(); + module_put(THIS_MODULE); + + if (IS_ERR(skb2)) + return PTR_ERR(skb2); + + buf = kasprintf(GFP_ATOMIC, "%.*s:%u", + nla_len(nla[NFTA_OBJ_TABLE]), + (char *)nla_data(nla[NFTA_OBJ_TABLE]), + nft_net->base_seq); + audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, + AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); + kfree(buf); + + return nfnetlink_unicast(skb2, net, portid); } static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) @@ -9410,7 +9467,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { - .call = nf_tables_getobj, + .call = nf_tables_getobj_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 4abf660c7baf..932b3ddb34f1 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -427,8 +427,10 @@ replay_abort: nfnl_unlock(subsys_id); - if (nlh->nlmsg_flags & NLM_F_ACK) + if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); nfnl_err_add(&err_list, nlh, 0, &extack); + } while (skb->len >= nlmsg_total_size(0)) { int msglen, type; @@ -577,6 +579,7 @@ done: ss->abort(net, oskb, NFNL_ABORT_NONE); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } else if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); nfnl_err_add(&err_list, nlh, 0, &extack); } } else { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 55e28e1da66e..e0716da256bf 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -820,10 +820,41 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) static const unsigned long flags = IPS_CONFIRMED | IPS_DYING; - const struct nf_conn *ct = (void *)skb_nfct(entry->skb); + struct nf_conn *ct = (void *)skb_nfct(entry->skb); + unsigned long status; + unsigned int use; - if (ct && ((ct->status & flags) == IPS_DYING)) + if (!ct) + return false; + + status = READ_ONCE(ct->status); + if ((status & flags) == IPS_DYING) return true; + + if (status & IPS_CONFIRMED) + return false; + + /* in some cases skb_clone() can occur after initial conntrack + * pickup, but conntrack assumes exclusive skb->_nfct ownership for + * unconfirmed entries. + * + * This happens for br_netfilter and with ip multicast routing. + * We can't be solved with serialization here because one clone could + * have been queued for local delivery. + */ + use = refcount_read(&ct->ct_general.use); + if (likely(use == 1)) + return false; + + /* Can't decrement further? Exclusive ownership. */ + if (!refcount_dec_not_one(&ct->ct_general.use)) + return false; + + skb_set_nfct(entry->skb, 0); + /* No nf_ct_put(): we already decremented .use and it cannot + * drop down to 0. + */ + return true; #endif return false; } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4b040285aa78..0ff9b2dd86ba 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1270,25 +1270,28 @@ out: return err; } +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk = vsock_sk(sk); + + return vsk->transport->dgram_dequeue(vsk, msg, len, flags); +} + int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; const struct proto *prot; -#endif - struct vsock_sock *vsk; - struct sock *sk; - sk = sock->sk; - vsk = vsock_sk(sk); - -#ifdef CONFIG_BPF_SYSCALL prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags, NULL); #endif - return vsk->transport->dgram_dequeue(vsk, msg, len, flags); + return __vsock_dgram_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg); @@ -2174,15 +2177,12 @@ out: } int -vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; -#ifdef CONFIG_BPF_SYSCALL - const struct proto *prot; -#endif int err; sk = sock->sk; @@ -2233,14 +2233,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; } -#ifdef CONFIG_BPF_SYSCALL - prot = READ_ONCE(sk->sk_prot); - if (prot != &vsock_proto) { - release_sock(sk); - return prot->recvmsg(sk, msg, len, flags, NULL); - } -#endif - if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else @@ -2250,6 +2242,22 @@ out: release_sock(sk); return err; } + +int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ +#ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; + const struct proto *prot; + + prot = READ_ONCE(sk->sk_prot); + if (prot != &vsock_proto) + return prot->recvmsg(sk, msg, len, flags, NULL); +#endif + + return __vsock_connectible_recvmsg(sock, msg, len, flags); +} EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg); static int vsock_set_rcvlowat(struct sock *sk, int val) diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index a3c97546ab84..c42c5cc18f32 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int int err; if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) - err = vsock_connectible_recvmsg(sock, msg, len, flags); + err = __vsock_connectible_recvmsg(sock, msg, len, flags); else if (sk->sk_type == SOCK_DGRAM) - err = vsock_dgram_recvmsg(sock, msg, len, flags); + err = __vsock_dgram_recvmsg(sock, msg, len, flags); else err = -EPROTOTYPE; diff --git a/scripts/gcc-plugins/randomize_layout_plugin.c b/scripts/gcc-plugins/randomize_layout_plugin.c index 746ff2d272f2..5694df3da2e9 100644 --- a/scripts/gcc-plugins/randomize_layout_plugin.c +++ b/scripts/gcc-plugins/randomize_layout_plugin.c @@ -19,10 +19,6 @@ #include "gcc-common.h" #include "randomize_layout_seed.h" -#if BUILDING_GCC_MAJOR < 4 || (BUILDING_GCC_MAJOR == 4 && BUILDING_GCC_MINOR < 7) -#error "The RANDSTRUCT plugin requires GCC 4.7 or newer." -#endif - #define ORIG_TYPE_NAME(node) \ (TYPE_NAME(TYPE_MAIN_VARIANT(node)) != NULL_TREE ? ((const unsigned char *)IDENTIFIER_POINTER(TYPE_NAME(TYPE_MAIN_VARIANT(node)))) : (const unsigned char *)"anonymous") diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 0ed873491bf5..123dab0572f8 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -5,8 +5,7 @@ * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. * - * Usage: kallsyms [--all-symbols] [--absolute-percpu] - * [--lto-clang] in.map > out.S + * Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S * * Table compression uses all the unused char codes on the symbols and * maps these to the most used substrings (tokens). For instance, it might @@ -62,7 +61,6 @@ static struct sym_entry **table; static unsigned int table_size, table_cnt; static int all_symbols; static int absolute_percpu; -static int lto_clang; static int token_profit[0x10000]; @@ -73,8 +71,7 @@ static unsigned char best_table_len[256]; static void usage(void) { - fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] " - "[--lto-clang] in.map > out.S\n"); + fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S\n"); exit(1); } @@ -344,25 +341,6 @@ static bool symbol_absolute(const struct sym_entry *s) return s->percpu_absolute; } -static void cleanup_symbol_name(char *s) -{ - char *p; - - /* - * ASCII[.] = 2e - * ASCII[0-9] = 30,39 - * ASCII[A-Z] = 41,5a - * ASCII[_] = 5f - * ASCII[a-z] = 61,7a - * - * As above, replacing the first '.' in ".llvm." with '\0' does not - * affect the main sorting, but it helps us with subsorting. - */ - p = strstr(s, ".llvm."); - if (p) - *p = '\0'; -} - static int compare_names(const void *a, const void *b) { int ret; @@ -526,10 +504,6 @@ static void write_src(void) output_address(relative_base); printf("\n"); - if (lto_clang) - for (i = 0; i < table_cnt; i++) - cleanup_symbol_name((char *)table[i]->sym); - sort_symbols_by_name(); output_label("kallsyms_seqs_of_names"); for (i = 0; i < table_cnt; i++) @@ -807,7 +781,6 @@ int main(int argc, char **argv) static const struct option long_options[] = { {"all-symbols", no_argument, &all_symbols, 1}, {"absolute-percpu", no_argument, &absolute_percpu, 1}, - {"lto-clang", no_argument, <o_clang, 1}, {}, }; diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index f7b2503cdba9..22d0bc843986 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -156,10 +156,6 @@ kallsyms() kallsymopt="${kallsymopt} --absolute-percpu" fi - if is_enabled CONFIG_LTO_CLANG; then - kallsymopt="${kallsymopt} --lto-clang" - fi - info KSYMS "${2}.S" scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S" diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 32eb67fb3e42..b49c44869dc4 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -330,12 +330,12 @@ static int avc_add_xperms_decision(struct avc_node *node, { struct avc_xperms_decision_node *dest_xpd; - node->ae.xp_node->xp.len++; dest_xpd = avc_xperms_decision_alloc(src->used); if (!dest_xpd) return -ENOMEM; avc_copy_xperms_decision(&dest_xpd->xpd, src); list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head); + node->ae.xp_node->xp.len++; return 0; } @@ -907,7 +907,11 @@ static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, node->ae.avd.auditdeny &= ~perms; break; case AVC_CALLBACK_ADD_XPERMS: - avc_add_xperms_decision(node, xpd); + rc = avc_add_xperms_decision(node, xpd); + if (rc) { + avc_node_kill(node); + goto out_unlock; + } break; } avc_node_replace(node, orig); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 55c78c318ccd..bfa61e005aac 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3852,7 +3852,17 @@ static int selinux_file_mprotect(struct vm_area_struct *vma, if (default_noexec && (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) { int rc = 0; - if (vma_is_initial_heap(vma)) { + /* + * We don't use the vma_is_initial_heap() helper as it has + * a history of problems and is currently broken on systems + * where there is no heap, e.g. brk == start_brk. Before + * replacing the conditional below with vma_is_initial_heap(), + * or something similar, please ensure that the logic is the + * same as what we have below or you have tested every possible + * corner case you can think to test. + */ + if (vma->vm_start >= vma->vm_mm->start_brk && + vma->vm_end <= vma->vm_mm->brk) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECHEAP, NULL); } else if (!vma->vm_file && (vma_is_initial_stack(vma) || diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 7b32b99023a2..5fd7caea4419 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -86,9 +86,14 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_CORTEX_X1C 0xD4C +#define ARM_CPU_PART_CORTEX_X3 0xD4E #define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_A720 0xD81 #define ARM_CPU_PART_CORTEX_X4 0xD82 #define ARM_CPU_PART_NEOVERSE_V3 0xD84 +#define ARM_CPU_PART_CORTEX_X925 0xD85 +#define ARM_CPU_PART_CORTEX_A725 0xD87 #define APM_CPU_PART_XGENE 0x000 #define APM_CPU_VAR_POTENZA 0x00 @@ -162,9 +167,14 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C) +#define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) +#define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) +#define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 1691297a766a..eaeda001784e 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -645,6 +645,9 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_SIER3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3) #define KVM_REG_PPC_DAWR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc4) #define KVM_REG_PPC_DAWRX1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc5) +#define KVM_REG_PPC_DEXCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc6) +#define KVM_REG_PPC_HASHKEYR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc7) +#define KVM_REG_PPC_HASHPKEYR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc8) /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 3c7434329661..dd4682857c12 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -18,170 +18,170 @@ /* * Note: If the comment begins with a quoted string, that string is used - * in /proc/cpuinfo instead of the macro name. If the string is "", - * this feature bit is not displayed in /proc/cpuinfo at all. + * in /proc/cpuinfo instead of the macro name. Otherwise, this feature + * bit is not displayed in /proc/cpuinfo at all. * * When adding new features here that depend on other features, * please update the table in kernel/cpu/cpuid-deps.c as well. */ /* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */ -#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ -#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ -#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ -#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ -#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ -#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ -#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ -#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ -#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ -#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ -#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ -#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ -#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ -#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ -#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */ -#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ -#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ -#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ -#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ +#define X86_FEATURE_FPU ( 0*32+ 0) /* "fpu" Onboard FPU */ +#define X86_FEATURE_VME ( 0*32+ 1) /* "vme" Virtual Mode Extensions */ +#define X86_FEATURE_DE ( 0*32+ 2) /* "de" Debugging Extensions */ +#define X86_FEATURE_PSE ( 0*32+ 3) /* "pse" Page Size Extensions */ +#define X86_FEATURE_TSC ( 0*32+ 4) /* "tsc" Time Stamp Counter */ +#define X86_FEATURE_MSR ( 0*32+ 5) /* "msr" Model-Specific Registers */ +#define X86_FEATURE_PAE ( 0*32+ 6) /* "pae" Physical Address Extensions */ +#define X86_FEATURE_MCE ( 0*32+ 7) /* "mce" Machine Check Exception */ +#define X86_FEATURE_CX8 ( 0*32+ 8) /* "cx8" CMPXCHG8 instruction */ +#define X86_FEATURE_APIC ( 0*32+ 9) /* "apic" Onboard APIC */ +#define X86_FEATURE_SEP ( 0*32+11) /* "sep" SYSENTER/SYSEXIT */ +#define X86_FEATURE_MTRR ( 0*32+12) /* "mtrr" Memory Type Range Registers */ +#define X86_FEATURE_PGE ( 0*32+13) /* "pge" Page Global Enable */ +#define X86_FEATURE_MCA ( 0*32+14) /* "mca" Machine Check Architecture */ +#define X86_FEATURE_CMOV ( 0*32+15) /* "cmov" CMOV instructions (plus FCMOVcc, FCOMI with FPU) */ +#define X86_FEATURE_PAT ( 0*32+16) /* "pat" Page Attribute Table */ +#define X86_FEATURE_PSE36 ( 0*32+17) /* "pse36" 36-bit PSEs */ +#define X86_FEATURE_PN ( 0*32+18) /* "pn" Processor serial number */ +#define X86_FEATURE_CLFLUSH ( 0*32+19) /* "clflush" CLFLUSH instruction */ #define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ -#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ -#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ -#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ +#define X86_FEATURE_ACPI ( 0*32+22) /* "acpi" ACPI via MSR */ +#define X86_FEATURE_MMX ( 0*32+23) /* "mmx" Multimedia Extensions */ +#define X86_FEATURE_FXSR ( 0*32+24) /* "fxsr" FXSAVE/FXRSTOR, CR4.OSFXSR */ #define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ #define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ #define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ -#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ +#define X86_FEATURE_HT ( 0*32+28) /* "ht" Hyper-Threading */ #define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ -#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ -#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ +#define X86_FEATURE_IA64 ( 0*32+30) /* "ia64" IA-64 processor */ +#define X86_FEATURE_PBE ( 0*32+31) /* "pbe" Pending Break Enable */ /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */ /* Don't duplicate feature flags which are redundant with Intel! */ -#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ -#define X86_FEATURE_MP ( 1*32+19) /* MP Capable */ -#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ -#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ -#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ +#define X86_FEATURE_SYSCALL ( 1*32+11) /* "syscall" SYSCALL/SYSRET */ +#define X86_FEATURE_MP ( 1*32+19) /* "mp" MP Capable */ +#define X86_FEATURE_NX ( 1*32+20) /* "nx" Execute Disable */ +#define X86_FEATURE_MMXEXT ( 1*32+22) /* "mmxext" AMD MMX extensions */ +#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* "fxsr_opt" FXSAVE/FXRSTOR optimizations */ #define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ -#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ -#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64, 64-bit support) */ -#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow extensions */ -#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow */ +#define X86_FEATURE_RDTSCP ( 1*32+27) /* "rdtscp" RDTSCP */ +#define X86_FEATURE_LM ( 1*32+29) /* "lm" Long Mode (x86-64, 64-bit support) */ +#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* "3dnowext" AMD 3DNow extensions */ +#define X86_FEATURE_3DNOW ( 1*32+31) /* "3dnow" 3DNow */ /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */ -#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ -#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ -#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ +#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* "recovery" CPU in recovery mode */ +#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* "longrun" Longrun power control */ +#define X86_FEATURE_LRTI ( 2*32+ 3) /* "lrti" LongRun table interface */ /* Other features, Linux-defined mapping, word 3 */ /* This range is used for feature bits which conflict or are synthesized */ -#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ -#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ -#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ -#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ -#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */ -#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ -#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ -#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ -#define X86_FEATURE_UP ( 3*32+ 9) /* SMP kernel running on UP */ -#define X86_FEATURE_ART ( 3*32+10) /* Always running timer (ART) */ -#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ -#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ -#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ -#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */ -#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ -#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ -#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */ -#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ -#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ -#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ -#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* CPU topology enum extensions */ -#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ -#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ -#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ -#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* Extended APICID (8 bits) */ -#define X86_FEATURE_AMD_DCM ( 3*32+27) /* AMD multi-node processor */ -#define X86_FEATURE_APERFMPERF ( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */ -#define X86_FEATURE_RAPL ( 3*32+29) /* AMD/Hygon RAPL interface */ -#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ -#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */ +#define X86_FEATURE_CXMMX ( 3*32+ 0) /* "cxmmx" Cyrix MMX extensions */ +#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* "k6_mtrr" AMD K6 nonstandard MTRRs */ +#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* "cyrix_arr" Cyrix ARRs (= MTRRs) */ +#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */ +#define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */ +#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */ +#define X86_FEATURE_P3 ( 3*32+ 6) /* P3 */ +#define X86_FEATURE_P4 ( 3*32+ 7) /* P4 */ +#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */ +#define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */ +#define X86_FEATURE_ART ( 3*32+10) /* "art" Always running timer (ART) */ +#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* "arch_perfmon" Intel Architectural PerfMon */ +#define X86_FEATURE_PEBS ( 3*32+12) /* "pebs" Precise-Event Based Sampling */ +#define X86_FEATURE_BTS ( 3*32+13) /* "bts" Branch Trace Store */ +#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* syscall in IA32 userspace */ +#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* sysenter in IA32 userspace */ +#define X86_FEATURE_REP_GOOD ( 3*32+16) /* "rep_good" REP microcode works well */ +#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* Clear CPU buffers using VERW */ +#define X86_FEATURE_ACC_POWER ( 3*32+19) /* "acc_power" AMD Accumulated Power Mechanism */ +#define X86_FEATURE_NOPL ( 3*32+20) /* "nopl" The NOPL (0F 1F) instructions */ +#define X86_FEATURE_ALWAYS ( 3*32+21) /* Always-present feature */ +#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* "xtopology" CPU topology enum extensions */ +#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* "tsc_reliable" TSC is known to be reliable */ +#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* "nonstop_tsc" TSC does not stop in C states */ +#define X86_FEATURE_CPUID ( 3*32+25) /* "cpuid" CPU has CPUID instruction itself */ +#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* "extd_apicid" Extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM ( 3*32+27) /* "amd_dcm" AMD multi-node processor */ +#define X86_FEATURE_APERFMPERF ( 3*32+28) /* "aperfmperf" P-State hardware coordination feedback capability (APERF/MPERF MSRs) */ +#define X86_FEATURE_RAPL ( 3*32+29) /* "rapl" AMD/Hygon RAPL interface */ +#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* "nonstop_tsc_s3" TSC doesn't stop in S3 state */ +#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* "tsc_known_freq" TSC has known frequency */ /* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */ #define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ -#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ -#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ +#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* "pclmulqdq" PCLMULQDQ instruction */ +#define X86_FEATURE_DTES64 ( 4*32+ 2) /* "dtes64" 64-bit Debug Store */ #define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */ #define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */ -#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ -#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer Mode eXtensions */ -#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ -#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ -#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ -#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ -#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ -#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ -#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B instruction */ -#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ -#define X86_FEATURE_PDCM ( 4*32+15) /* Perf/Debug Capabilities MSR */ -#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */ -#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */ +#define X86_FEATURE_VMX ( 4*32+ 5) /* "vmx" Hardware virtualization */ +#define X86_FEATURE_SMX ( 4*32+ 6) /* "smx" Safer Mode eXtensions */ +#define X86_FEATURE_EST ( 4*32+ 7) /* "est" Enhanced SpeedStep */ +#define X86_FEATURE_TM2 ( 4*32+ 8) /* "tm2" Thermal Monitor 2 */ +#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* "ssse3" Supplemental SSE-3 */ +#define X86_FEATURE_CID ( 4*32+10) /* "cid" Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* "sdbg" Silicon Debug */ +#define X86_FEATURE_FMA ( 4*32+12) /* "fma" Fused multiply-add */ +#define X86_FEATURE_CX16 ( 4*32+13) /* "cx16" CMPXCHG16B instruction */ +#define X86_FEATURE_XTPR ( 4*32+14) /* "xtpr" Send Task Priority Messages */ +#define X86_FEATURE_PDCM ( 4*32+15) /* "pdcm" Perf/Debug Capabilities MSR */ +#define X86_FEATURE_PCID ( 4*32+17) /* "pcid" Process Context Identifiers */ +#define X86_FEATURE_DCA ( 4*32+18) /* "dca" Direct Cache Access */ #define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ #define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ -#define X86_FEATURE_X2APIC ( 4*32+21) /* X2APIC */ -#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */ -#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */ -#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* TSC deadline timer */ -#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */ -#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */ -#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE instruction enabled in the OS */ -#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ -#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit FP conversions */ -#define X86_FEATURE_RDRAND ( 4*32+30) /* RDRAND instruction */ -#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ +#define X86_FEATURE_X2APIC ( 4*32+21) /* "x2apic" X2APIC */ +#define X86_FEATURE_MOVBE ( 4*32+22) /* "movbe" MOVBE instruction */ +#define X86_FEATURE_POPCNT ( 4*32+23) /* "popcnt" POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* "tsc_deadline_timer" TSC deadline timer */ +#define X86_FEATURE_AES ( 4*32+25) /* "aes" AES instructions */ +#define X86_FEATURE_XSAVE ( 4*32+26) /* "xsave" XSAVE/XRSTOR/XSETBV/XGETBV instructions */ +#define X86_FEATURE_OSXSAVE ( 4*32+27) /* XSAVE instruction enabled in the OS */ +#define X86_FEATURE_AVX ( 4*32+28) /* "avx" Advanced Vector Extensions */ +#define X86_FEATURE_F16C ( 4*32+29) /* "f16c" 16-bit FP conversions */ +#define X86_FEATURE_RDRAND ( 4*32+30) /* "rdrand" RDRAND instruction */ +#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* "hypervisor" Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ #define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ #define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ #define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ #define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ -#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ -#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ -#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ -#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ -#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ -#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ +#define X86_FEATURE_ACE2 ( 5*32+ 8) /* "ace2" Advanced Cryptography Engine v2 */ +#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* "ace2_en" ACE v2 enabled */ +#define X86_FEATURE_PHE ( 5*32+10) /* "phe" PadLock Hash Engine */ +#define X86_FEATURE_PHE_EN ( 5*32+11) /* "phe_en" PHE enabled */ +#define X86_FEATURE_PMM ( 5*32+12) /* "pmm" PadLock Montgomery Multiplier */ +#define X86_FEATURE_PMM_EN ( 5*32+13) /* "pmm_en" PMM enabled */ /* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */ -#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ -#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ -#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure Virtual Machine */ -#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ -#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ -#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ -#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ -#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ -#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ -#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ -#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ -#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ -#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ -#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ -#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ -#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ -#define X86_FEATURE_TCE ( 6*32+17) /* Translation Cache Extension */ -#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ -#define X86_FEATURE_TBM ( 6*32+21) /* Trailing Bit Manipulations */ -#define X86_FEATURE_TOPOEXT ( 6*32+22) /* Topology extensions CPUID leafs */ -#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* Core performance counter extensions */ -#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ -#define X86_FEATURE_BPEXT ( 6*32+26) /* Data breakpoint extension */ -#define X86_FEATURE_PTSC ( 6*32+27) /* Performance time-stamp counter */ -#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* Last Level Cache performance counter extensions */ -#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */ +#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* "lahf_lm" LAHF/SAHF in long mode */ +#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* "cmp_legacy" If yes HyperThreading not valid */ +#define X86_FEATURE_SVM ( 6*32+ 2) /* "svm" Secure Virtual Machine */ +#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* "extapic" Extended APIC space */ +#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* "cr8_legacy" CR8 in 32-bit mode */ +#define X86_FEATURE_ABM ( 6*32+ 5) /* "abm" Advanced bit manipulation */ +#define X86_FEATURE_SSE4A ( 6*32+ 6) /* "sse4a" SSE-4A */ +#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* "misalignsse" Misaligned SSE mode */ +#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* "3dnowprefetch" 3DNow prefetch instructions */ +#define X86_FEATURE_OSVW ( 6*32+ 9) /* "osvw" OS Visible Workaround */ +#define X86_FEATURE_IBS ( 6*32+10) /* "ibs" Instruction Based Sampling */ +#define X86_FEATURE_XOP ( 6*32+11) /* "xop" Extended AVX instructions */ +#define X86_FEATURE_SKINIT ( 6*32+12) /* "skinit" SKINIT/STGI instructions */ +#define X86_FEATURE_WDT ( 6*32+13) /* "wdt" Watchdog timer */ +#define X86_FEATURE_LWP ( 6*32+15) /* "lwp" Light Weight Profiling */ +#define X86_FEATURE_FMA4 ( 6*32+16) /* "fma4" 4 operands MAC instructions */ +#define X86_FEATURE_TCE ( 6*32+17) /* "tce" Translation Cache Extension */ +#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* "nodeid_msr" NodeId MSR */ +#define X86_FEATURE_TBM ( 6*32+21) /* "tbm" Trailing Bit Manipulations */ +#define X86_FEATURE_TOPOEXT ( 6*32+22) /* "topoext" Topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* "perfctr_core" Core performance counter extensions */ +#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* "perfctr_nb" NB performance counter extensions */ +#define X86_FEATURE_BPEXT ( 6*32+26) /* "bpext" Data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* "ptsc" Performance time-stamp counter */ +#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* "perfctr_llc" Last Level Cache performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* "mwaitx" MWAIT extension (MONITORX/MWAITX instructions) */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -189,93 +189,93 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */ -#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ -#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ -#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ -#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ -#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ -#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ -#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* Platform supports being a TDX host */ -#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ -#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ -#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ -#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ -#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ -#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ -#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ -#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ -#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* AMD Performance Monitoring Version 2 */ -#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ -#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ -#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ -#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */ -#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ -#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ -#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_ZEN ( 7*32+28) /* "" Generic flag for all Zen and newer */ -#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ -#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ -#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* "ring3mwait" Ring 3 MONITOR/MWAIT instructions */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* "cpuid_fault" Intel CPUID faulting */ +#define X86_FEATURE_CPB ( 7*32+ 2) /* "cpb" AMD Core Performance Boost */ +#define X86_FEATURE_EPB ( 7*32+ 3) /* "epb" IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* "cat_l3" Cache Allocation Technology L3 */ +#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* "cat_l2" Cache Allocation Technology L2 */ +#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* "cdp_l3" Code and Data Prioritization L3 */ +#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* "tdx_host_platform" Platform supports being a TDX host */ +#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* "hw_pstate" AMD HW-PState */ +#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* "proc_feedback" AMD ProcFeedbackInterface */ +#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* Use compacted XSTATE (XSAVES or XSAVEC) */ +#define X86_FEATURE_PTI ( 7*32+11) /* "pti" Kernel Page Table Isolation enabled */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* Set/clear IBRS on kernel entry/exit */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* Fill RSB on VM-Exit */ +#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* "intel_ppin" Intel Processor Inventory Number */ +#define X86_FEATURE_CDP_L2 ( 7*32+15) /* "cdp_l2" Code and Data Prioritization L2 */ +#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* MSR SPEC_CTRL is implemented */ +#define X86_FEATURE_SSBD ( 7*32+17) /* "ssbd" Speculative Store Bypass Disable */ +#define X86_FEATURE_MBA ( 7*32+18) /* "mba" Memory Bandwidth Allocation */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ +#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* "perfmon_v2" AMD Performance Monitoring Version 2 */ +#define X86_FEATURE_USE_IBPB ( 7*32+21) /* Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* Use IBRS during runtime firmware calls */ +#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */ +#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */ +#define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */ +#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */ +#define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ZEN ( 7*32+28) /* Generic flag for all Zen and newer */ +#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* L1TF workaround PTE inversion */ +#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* "ibrs_enhanced" Enhanced IBRS */ +#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* MSR IA32_FEAT_CTL configured */ /* Virtualization flags: Linux defined, word 8 */ -#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */ +#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* "tpr_shadow" Intel TPR Shadow */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */ -#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ -#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ -#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ -#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ -#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ -#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ -#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ -#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */ +#define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */ +#define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */ +#define X86_FEATURE_EPT_AD ( 8*32+17) /* "ept_ad" Intel Extended Page Table access-dirty bit */ +#define X86_FEATURE_VMCALL ( 8*32+18) /* Hypervisor supports the VMCALL instruction */ +#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* VMware prefers VMMCALL hypercall instruction */ +#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* PV unlock function */ +#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* PV vcpu_is_preempted function */ +#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* "tdx_guest" Intel Trust Domain Extensions Guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ -#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ -#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3B */ -#define X86_FEATURE_SGX ( 9*32+ 2) /* Software Guard Extensions */ -#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ -#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ -#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ -#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */ -#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ -#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ -#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */ -#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ -#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ -#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ -#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */ -#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ -#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ -#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ -#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ -#define X86_FEATURE_RDSEED ( 9*32+18) /* RDSEED instruction */ -#define X86_FEATURE_ADX ( 9*32+19) /* ADCX and ADOX instructions */ -#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ -#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ -#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ -#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */ -#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ -#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ -#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ -#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ -#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */ -#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */ +#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* "fsgsbase" RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ +#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* "tsc_adjust" TSC adjustment MSR 0x3B */ +#define X86_FEATURE_SGX ( 9*32+ 2) /* "sgx" Software Guard Extensions */ +#define X86_FEATURE_BMI1 ( 9*32+ 3) /* "bmi1" 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE ( 9*32+ 4) /* "hle" Hardware Lock Elision */ +#define X86_FEATURE_AVX2 ( 9*32+ 5) /* "avx2" AVX2 instructions */ +#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* FPU data pointer updated only on x87 exceptions */ +#define X86_FEATURE_SMEP ( 9*32+ 7) /* "smep" Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 ( 9*32+ 8) /* "bmi2" 2nd group bit manipulation extensions */ +#define X86_FEATURE_ERMS ( 9*32+ 9) /* "erms" Enhanced REP MOVSB/STOSB instructions */ +#define X86_FEATURE_INVPCID ( 9*32+10) /* "invpcid" Invalidate Processor Context ID */ +#define X86_FEATURE_RTM ( 9*32+11) /* "rtm" Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* "cqm" Cache QoS Monitoring */ +#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* Zero out FPU CS and FPU DS */ +#define X86_FEATURE_MPX ( 9*32+14) /* "mpx" Memory Protection Extension */ +#define X86_FEATURE_RDT_A ( 9*32+15) /* "rdt_a" Resource Director Technology Allocation */ +#define X86_FEATURE_AVX512F ( 9*32+16) /* "avx512f" AVX-512 Foundation */ +#define X86_FEATURE_AVX512DQ ( 9*32+17) /* "avx512dq" AVX-512 DQ (Double/Quad granular) Instructions */ +#define X86_FEATURE_RDSEED ( 9*32+18) /* "rdseed" RDSEED instruction */ +#define X86_FEATURE_ADX ( 9*32+19) /* "adx" ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP ( 9*32+20) /* "smap" Supervisor Mode Access Prevention */ +#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* "avx512ifma" AVX-512 Integer Fused Multiply-Add instructions */ +#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* "clflushopt" CLFLUSHOPT instruction */ +#define X86_FEATURE_CLWB ( 9*32+24) /* "clwb" CLWB instruction */ +#define X86_FEATURE_INTEL_PT ( 9*32+25) /* "intel_pt" Intel Processor Trace */ +#define X86_FEATURE_AVX512PF ( 9*32+26) /* "avx512pf" AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER ( 9*32+27) /* "avx512er" AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD ( 9*32+28) /* "avx512cd" AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* "sha_ni" SHA1/SHA256 Instruction Extensions */ +#define X86_FEATURE_AVX512BW ( 9*32+30) /* "avx512bw" AVX-512 BW (Byte/Word granular) Instructions */ +#define X86_FEATURE_AVX512VL ( 9*32+31) /* "avx512vl" AVX-512 VL (128/256 Vector Length) Extensions */ /* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */ -#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT instruction */ -#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */ -#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */ -#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */ -#define X86_FEATURE_XFD (10*32+ 4) /* "" eXtended Feature Disabling */ +#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* "xsaveopt" XSAVEOPT instruction */ +#define X86_FEATURE_XSAVEC (10*32+ 1) /* "xsavec" XSAVEC instruction */ +#define X86_FEATURE_XGETBV1 (10*32+ 2) /* "xgetbv1" XGETBV with ECX = 1 instruction */ +#define X86_FEATURE_XSAVES (10*32+ 3) /* "xsaves" XSAVES/XRSTORS instructions */ +#define X86_FEATURE_XFD (10*32+ 4) /* eXtended Feature Disabling */ /* * Extended auxiliary flags: Linux defined - for features scattered in various @@ -283,181 +283,183 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */ -#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */ -#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */ -#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ -#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ -#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ -#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ -#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ -#define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ -#define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ -#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */ -#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */ -#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ -#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ -#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ -#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ -#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ -#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ -#define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ -#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ -#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ -#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ -#define X86_FEATURE_USER_SHSTK (11*32+23) /* Shadow stack support for user mode applications */ -#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ -#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ -#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ -#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ -#define X86_FEATURE_ZEN2 (11*32+28) /* "" CPU based on Zen2 microarchitecture */ -#define X86_FEATURE_ZEN3 (11*32+29) /* "" CPU based on Zen3 microarchitecture */ -#define X86_FEATURE_ZEN4 (11*32+30) /* "" CPU based on Zen4 microarchitecture */ -#define X86_FEATURE_ZEN1 (11*32+31) /* "" CPU based on Zen1 microarchitecture */ +#define X86_FEATURE_CQM_LLC (11*32+ 0) /* "cqm_llc" LLC QoS if 1 */ +#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* "cqm_occup_llc" LLC occupancy monitoring */ +#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* "cqm_mbm_total" LLC Total MBM monitoring */ +#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* "cqm_mbm_local" LLC Local MBM monitoring */ +#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* LFENCE in user entry SWAPGS path */ +#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* "split_lock_detect" #AC for split lock */ +#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* Per-thread Memory Bandwidth Allocation */ +#define X86_FEATURE_SGX1 (11*32+ 8) /* Basic SGX */ +#define X86_FEATURE_SGX2 (11*32+ 9) /* SGX Enclave Dynamic Memory Management (EDMM) */ +#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* Issue an IBPB on kernel entry */ +#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* RET prediction control */ +#define X86_FEATURE_RETPOLINE (11*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_RETHUNK (11*32+14) /* Use REturn THUNK */ +#define X86_FEATURE_UNRET (11*32+15) /* AMD BTB untrain return */ +#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* Use IBPB during runtime firmware calls */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* Fill RSB on VM exit when EIBRS is enabled */ +#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* SGX EDECCSSA user leaf function */ +#define X86_FEATURE_CALL_DEPTH (11*32+19) /* Call depth tracking for RSB stuffing */ +#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* Bandwidth Monitoring Event Configuration */ +#define X86_FEATURE_USER_SHSTK (11*32+23) /* "user_shstk" Shadow stack support for user mode applications */ +#define X86_FEATURE_SRSO (11*32+24) /* AMD BTB untrain RETs */ +#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* AMD BTB untrain RETs through aliasing */ +#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* Issue an IBPB only on VMEXIT */ +#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ +#define X86_FEATURE_ZEN2 (11*32+28) /* CPU based on Zen2 microarchitecture */ +#define X86_FEATURE_ZEN3 (11*32+29) /* CPU based on Zen3 microarchitecture */ +#define X86_FEATURE_ZEN4 (11*32+30) /* CPU based on Zen4 microarchitecture */ +#define X86_FEATURE_ZEN1 (11*32+31) /* CPU based on Zen1 microarchitecture */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ -#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ -#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ -#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ -#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ -#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ -#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ -#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ -#define X86_FEATURE_FRED (12*32+17) /* Flexible Return and Event Delivery */ -#define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ -#define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */ -#define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ -#define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ -#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ +#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* "avx_vnni" AVX VNNI instructions */ +#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* "avx512_bf16" AVX512 BFLOAT16 instructions */ +#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* Fast short REP {CMPSB,SCASB} */ +#define X86_FEATURE_FRED (12*32+17) /* "fred" Flexible Return and Event Delivery */ +#define X86_FEATURE_LKGS (12*32+18) /* Load "kernel" (userspace) GS */ +#define X86_FEATURE_WRMSRNS (12*32+19) /* Non-serializing WRMSR */ +#define X86_FEATURE_AMX_FP16 (12*32+21) /* AMX fp16 Support */ +#define X86_FEATURE_AVX_IFMA (12*32+23) /* Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* "lam" Linear Address Masking */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ -#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ -#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ -#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ -#define X86_FEATURE_RDPRU (13*32+ 4) /* Read processor register at user level */ -#define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */ -#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ -#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ -#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */ -#define X86_FEATURE_AMD_PPIN (13*32+23) /* Protected Processor Inventory Number */ -#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ -#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ -#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ -#define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ -#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ -#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ -#define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ +#define X86_FEATURE_CLZERO (13*32+ 0) /* "clzero" CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+ 1) /* "irperf" Instructions Retired Count */ +#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */ +#define X86_FEATURE_RDPRU (13*32+ 4) /* "rdpru" Read processor register at user level */ +#define X86_FEATURE_WBNOINVD (13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */ +#define X86_FEATURE_AMD_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */ +#define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */ +#define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */ +#define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */ +#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* Speculative Store Bypass is fixed in hardware. */ +#define X86_FEATURE_CPPC (13*32+27) /* "cppc" Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ +#define X86_FEATURE_BTC_NO (13*32+29) /* Not vulnerable to Branch Type Confusion */ +#define X86_FEATURE_BRS (13*32+31) /* "brs" Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ -#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ -#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ -#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ -#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ -#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ -#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ -#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ -#define X86_FEATURE_HFI (14*32+19) /* Hardware Feedback Interface */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* "dtherm" Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* "ida" Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* "arat" Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* "pln" Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* "pts" Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* "hwp" Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* "hwp_notify" HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* "hwp_act_window" HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* "hwp_epp" HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* "hwp_pkg_req" HWP Package Level Request */ +#define X86_FEATURE_HWP_HIGHEST_PERF_CHANGE (14*32+15) /* HWP Highest perf change */ +#define X86_FEATURE_HFI (14*32+19) /* "hfi" Hardware Feedback Interface */ /* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */ -#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ -#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_NPT (15*32+ 0) /* "npt" Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* "lbrv" LBR Virtualization support */ #define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ #define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ #define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ #define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ -#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ -#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ -#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ -#define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */ -#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ -#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ -#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* "flushbyasid" Flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* "decodeassists" Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* "pausefilter" Filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* "pfthreshold" Pause filter threshold */ +#define X86_FEATURE_AVIC (15*32+13) /* "avic" Virtual Interrupt Controller */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* "v_vmsave_vmload" Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* "vgif" Virtual GIF */ +#define X86_FEATURE_X2AVIC (15*32+18) /* "x2avic" Virtual x2apic */ +#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */ +#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ -#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ -#define X86_FEATURE_UMIP (16*32+ 2) /* User Mode Instruction Protection */ -#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ -#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ -#define X86_FEATURE_WAITPKG (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */ -#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */ -#define X86_FEATURE_SHSTK (16*32+ 7) /* "" Shadow stack */ -#define X86_FEATURE_GFNI (16*32+ 8) /* Galois Field New Instructions */ -#define X86_FEATURE_VAES (16*32+ 9) /* Vector AES */ -#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */ -#define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */ -#define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ -#define X86_FEATURE_TME (16*32+13) /* Intel Total Memory Encryption */ -#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ -#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ -#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ -#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* Bus Lock detect */ -#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ -#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ -#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ -#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */ -#define X86_FEATURE_SGX_LC (16*32+30) /* Software Guard Extensions Launch Control */ +#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* "avx512vbmi" AVX512 Vector Bit Manipulation instructions*/ +#define X86_FEATURE_UMIP (16*32+ 2) /* "umip" User Mode Instruction Protection */ +#define X86_FEATURE_PKU (16*32+ 3) /* "pku" Protection Keys for Userspace */ +#define X86_FEATURE_OSPKE (16*32+ 4) /* "ospke" OS Protection Keys Enable */ +#define X86_FEATURE_WAITPKG (16*32+ 5) /* "waitpkg" UMONITOR/UMWAIT/TPAUSE Instructions */ +#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* "avx512_vbmi2" Additional AVX512 Vector Bit Manipulation Instructions */ +#define X86_FEATURE_SHSTK (16*32+ 7) /* Shadow stack */ +#define X86_FEATURE_GFNI (16*32+ 8) /* "gfni" Galois Field New Instructions */ +#define X86_FEATURE_VAES (16*32+ 9) /* "vaes" Vector AES */ +#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* "vpclmulqdq" Carry-Less Multiplication Double Quadword */ +#define X86_FEATURE_AVX512_VNNI (16*32+11) /* "avx512_vnni" Vector Neural Network Instructions */ +#define X86_FEATURE_AVX512_BITALG (16*32+12) /* "avx512_bitalg" Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ +#define X86_FEATURE_TME (16*32+13) /* "tme" Intel Total Memory Encryption */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* "avx512_vpopcntdq" POPCNT for vectors of DW/QW */ +#define X86_FEATURE_LA57 (16*32+16) /* "la57" 5-level page tables */ +#define X86_FEATURE_RDPID (16*32+22) /* "rdpid" RDPID instruction */ +#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* "bus_lock_detect" Bus Lock detect */ +#define X86_FEATURE_CLDEMOTE (16*32+25) /* "cldemote" CLDEMOTE instruction */ +#define X86_FEATURE_MOVDIRI (16*32+27) /* "movdiri" MOVDIRI instruction */ +#define X86_FEATURE_MOVDIR64B (16*32+28) /* "movdir64b" MOVDIR64B instruction */ +#define X86_FEATURE_ENQCMD (16*32+29) /* "enqcmd" ENQCMD and ENQCMDS instructions */ +#define X86_FEATURE_SGX_LC (16*32+30) /* "sgx_lc" Software Guard Extensions Launch Control */ /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ -#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ -#define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */ -#define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* "overflow_recov" MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+ 1) /* "succor" Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+ 3) /* "smca" Scalable MCA */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ -#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ -#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */ -#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */ -#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */ -#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ -#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* "" RTM transaction always aborts */ -#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ -#define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */ -#define X86_FEATURE_HYBRID_CPU (18*32+15) /* "" This part has CPUs of more than one type */ -#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ -#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ -#define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ -#define X86_FEATURE_IBT (18*32+20) /* Indirect Branch Tracking */ -#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */ -#define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */ -#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ -#define X86_FEATURE_AMX_INT8 (18*32+25) /* AMX int8 Support */ -#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ -#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ -#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ -#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */ -#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ +#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* "avx512_4vnniw" AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* "avx512_4fmaps" AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_FSRM (18*32+ 4) /* "fsrm" Fast Short Rep Mov */ +#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* "avx512_vp2intersect" AVX-512 Intersect for D/Q */ +#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* SRBDS mitigation MSR available */ +#define X86_FEATURE_MD_CLEAR (18*32+10) /* "md_clear" VERW clears CPU buffers */ +#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* RTM transaction always aborts */ +#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* TSX_FORCE_ABORT */ +#define X86_FEATURE_SERIALIZE (18*32+14) /* "serialize" SERIALIZE instruction */ +#define X86_FEATURE_HYBRID_CPU (18*32+15) /* This part has CPUs of more than one type */ +#define X86_FEATURE_TSXLDTRK (18*32+16) /* "tsxldtrk" TSX Suspend Load Address Tracking */ +#define X86_FEATURE_PCONFIG (18*32+18) /* "pconfig" Intel PCONFIG */ +#define X86_FEATURE_ARCH_LBR (18*32+19) /* "arch_lbr" Intel ARCH LBR */ +#define X86_FEATURE_IBT (18*32+20) /* "ibt" Indirect Branch Tracking */ +#define X86_FEATURE_AMX_BF16 (18*32+22) /* "amx_bf16" AMX bf16 Support */ +#define X86_FEATURE_AVX512_FP16 (18*32+23) /* "avx512_fp16" AVX512 FP16 */ +#define X86_FEATURE_AMX_TILE (18*32+24) /* "amx_tile" AMX tile Support */ +#define X86_FEATURE_AMX_INT8 (18*32+25) /* "amx_int8" AMX int8 Support */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_INTEL_STIBP (18*32+27) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_FLUSH_L1D (18*32+28) /* "flush_l1d" Flush L1D cache */ +#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* "arch_capabilities" IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* IA32_CORE_CAPABILITIES MSR */ +#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */ /* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ -#define X86_FEATURE_SME (19*32+ 0) /* AMD Secure Memory Encryption */ -#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ -#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ -#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ -#define X86_FEATURE_SEV_SNP (19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */ -#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ -#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ -#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */ +#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */ +#define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */ +#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ -#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ -#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* "" WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ -#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ -#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ -#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ -#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ +#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* Null Selector Clears Base */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */ -#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ -#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ -#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ +#define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ +#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ +#define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ /* * Extended auxiliary flags: Linux defined - for features scattered in various @@ -465,59 +467,60 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ -#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ -#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ -#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ -#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* "amd_lbr_pmc_freeze" AMD LBR and PMC Freeze */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */ +#define X86_FEATURE_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */ /* * BUG word(s) */ #define X86_BUG(x) (NCAPINTS*32 + (x)) -#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ -#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ -#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ +#define X86_BUG_F00F X86_BUG(0) /* "f00f" Intel F00F */ +#define X86_BUG_FDIV X86_BUG(1) /* "fdiv" FPU FDIV */ +#define X86_BUG_COMA X86_BUG(2) /* "coma" Cyrix 6x86 coma */ #define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ #define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ -#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ -#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ -#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ -#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ +#define X86_BUG_11AP X86_BUG(5) /* "11ap" Bad local APIC aka 11AP */ +#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* "fxsave_leak" FXSAVE leaks FOP/FIP/FOP */ +#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* "clflush_monitor" AAI65, CLFLUSH required before MONITOR */ +#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* "sysret_ss_attrs" SYSRET doesn't fix up SS attrs */ #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional * to avoid confusion. */ -#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ +#define X86_BUG_ESPFIX X86_BUG(9) /* IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif -#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ -#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ -#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ -#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ -#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ -#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ -#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ -#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ -#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ -#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ -#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ -#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ -#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ -#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ -#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ -#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ -#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ -#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ -#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ -#define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ -#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */ +#define X86_BUG_NULL_SEG X86_BUG(10) /* "null_seg" Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* "swapgs_fence" SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* "monitor" IPI required to wake up remote CPU */ +#define X86_BUG_AMD_E400 X86_BUG(13) /* "amd_e400" CPU is among the affected by Erratum 400 */ +#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* "cpu_meltdown" CPU is affected by meltdown attack and needs kernel page table isolation */ +#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* "spectre_v1" CPU is affected by Spectre variant 1 attack with conditional branches */ +#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* "spectre_v2" CPU is affected by Spectre variant 2 attack with indirect branches */ +#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* "spec_store_bypass" CPU is affected by speculative store bypass attack */ +#define X86_BUG_L1TF X86_BUG(18) /* "l1tf" CPU is affected by L1 Terminal Fault */ +#define X86_BUG_MDS X86_BUG(19) /* "mds" CPU is affected by Microarchitectural data sampling */ +#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* "msbds_only" CPU is only affected by the MSDBS variant of BUG_MDS */ +#define X86_BUG_SWAPGS X86_BUG(21) /* "swapgs" CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* "taa" CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* "itlb_multihit" CPU may incur MCE during certain page attribute changes */ +#define X86_BUG_SRBDS X86_BUG(24) /* "srbds" CPU may leak RNG bits if not mitigated */ +#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* "mmio_stale_data" CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */ +#define X86_BUG_RETBLEED X86_BUG(27) /* "retbleed" CPU is affected by RETBleed */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* "eibrs_pbrsb" EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* "smt_rsb" CPU is vulnerable to Cross-Thread Return Address Predictions */ +#define X86_BUG_GDS X86_BUG(30) /* "gds" CPU is affected by Gather Data Sampling */ +#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* "tdx_pw_mce" CPU may incur #MC if non-TD software does partial write to TDX private memory */ /* BUG word 2 */ -#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ -#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ -#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ -#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ +#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* "srso" AMD SRSO bug */ +#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index e022e6eb766c..82c6a4d350e0 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -566,6 +566,12 @@ #define MSR_RELOAD_PMC0 0x000014c1 #define MSR_RELOAD_FIXED_CTR0 0x00001309 +/* V6 PMON MSR range */ +#define MSR_IA32_PMC_V6_GP0_CTR 0x1900 +#define MSR_IA32_PMC_V6_GP0_CFG_A 0x1901 +#define MSR_IA32_PMC_V6_FX0_CTR 0x1980 +#define MSR_IA32_PMC_V6_STEP 4 + /* KeyID partitioning between MKTME and TDX */ #define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087 @@ -660,6 +666,8 @@ #define MSR_AMD64_RMP_BASE 0xc0010132 #define MSR_AMD64_RMP_END 0xc0010133 +#define MSR_SVSM_CAA 0xc001f000 + /* AMD Collaborative Processor Performance Control MSRs */ #define MSR_AMD_CPPC_CAP1 0xc00102b0 #define MSR_AMD_CPPC_ENABLE 0xc00102b1 @@ -781,6 +789,8 @@ #define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 +#define MSR_K7_HWCR_CPB_DIS_BIT 25 +#define MSR_K7_HWCR_CPB_DIS BIT_ULL(MSR_K7_HWCR_CPB_DIS_BIT) /* K6 MSRs */ #define MSR_K6_WHCR 0xc0000082 @@ -1164,6 +1174,7 @@ #define MSR_IA32_QM_CTR 0xc8e #define MSR_IA32_PQR_ASSOC 0xc8f #define MSR_IA32_L3_CBM_BASE 0xc90 +#define MSR_RMID_SNC_CONFIG 0xca0 #define MSR_IA32_L2_CBM_BASE 0xd10 #define MSR_IA32_MBA_THRTL_BASE 0xd50 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 9fae1b73b529..bf57a824f722 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -106,6 +106,7 @@ struct kvm_ioapic_state { #define KVM_RUN_X86_SMM (1 << 0) #define KVM_RUN_X86_BUS_LOCK (1 << 1) +#define KVM_RUN_X86_GUEST_MODE (1 << 2) /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { @@ -697,6 +698,11 @@ enum sev_cmd_id { /* Second time is the charm; improved versions of the above ioctls. */ KVM_SEV_INIT2, + /* SNP-specific commands */ + KVM_SEV_SNP_LAUNCH_START = 100, + KVM_SEV_SNP_LAUNCH_UPDATE, + KVM_SEV_SNP_LAUNCH_FINISH, + KVM_SEV_NR_MAX, }; @@ -824,6 +830,48 @@ struct kvm_sev_receive_update_data { __u32 pad2; }; +struct kvm_sev_snp_launch_start { + __u64 policy; + __u8 gosvw[16]; + __u16 flags; + __u8 pad0[6]; + __u64 pad1[4]; +}; + +/* Kept in sync with firmware values for simplicity. */ +#define KVM_SEV_SNP_PAGE_TYPE_NORMAL 0x1 +#define KVM_SEV_SNP_PAGE_TYPE_ZERO 0x3 +#define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED 0x4 +#define KVM_SEV_SNP_PAGE_TYPE_SECRETS 0x5 +#define KVM_SEV_SNP_PAGE_TYPE_CPUID 0x6 + +struct kvm_sev_snp_launch_update { + __u64 gfn_start; + __u64 uaddr; + __u64 len; + __u8 type; + __u8 pad0; + __u16 flags; + __u32 pad1; + __u64 pad2[4]; +}; + +#define KVM_SEV_SNP_ID_BLOCK_SIZE 96 +#define KVM_SEV_SNP_ID_AUTH_SIZE 4096 +#define KVM_SEV_SNP_FINISH_DATA_SIZE 32 + +struct kvm_sev_snp_launch_finish { + __u64 id_block_uaddr; + __u64 id_auth_uaddr; + __u8 id_block_en; + __u8 auth_key_en; + __u8 vcek_disabled; + __u8 host_data[KVM_SEV_SNP_FINISH_DATA_SIZE]; + __u8 pad0[3]; + __u16 flags; + __u64 pad1[4]; +}; + #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) @@ -874,5 +922,6 @@ struct kvm_hyperv_eventfd { #define KVM_X86_SW_PROTECTED_VM 1 #define KVM_X86_SEV_VM 2 #define KVM_X86_SEV_ES_VM 3 +#define KVM_X86_SNP_VM 4 #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index 80e1df482337..1814b413fd57 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -115,6 +115,7 @@ #define SVM_VMGEXIT_AP_CREATE_ON_INIT 0 #define SVM_VMGEXIT_AP_CREATE 1 #define SVM_VMGEXIT_AP_DESTROY 2 +#define SVM_VMGEXIT_SNP_RUN_VMPL 0x80000018 #define SVM_VMGEXIT_HV_FEATURES 0x8000fffd #define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe #define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \ diff --git a/tools/include/uapi/README b/tools/include/uapi/README new file mode 100644 index 000000000000..7147b1b2cb28 --- /dev/null +++ b/tools/include/uapi/README @@ -0,0 +1,73 @@ +Why we want a copy of kernel headers in tools? +============================================== + +There used to be no copies, with tools/ code using kernel headers +directly. From time to time tools/perf/ broke due to legitimate kernel +hacking. At some point Linus complained about such direct usage. Then we +adopted the current model. + +The way these headers are used in perf are not restricted to just +including them to compile something. + +There are sometimes used in scripts that convert defines into string +tables, etc, so some change may break one of these scripts, or new MSRs +may use some different #define pattern, etc. + +E.g.: + + $ ls -1 tools/perf/trace/beauty/*.sh | head -5 + tools/perf/trace/beauty/arch_errno_names.sh + tools/perf/trace/beauty/drm_ioctl.sh + tools/perf/trace/beauty/fadvise.sh + tools/perf/trace/beauty/fsconfig.sh + tools/perf/trace/beauty/fsmount.sh + $ + $ tools/perf/trace/beauty/fadvise.sh + static const char *fadvise_advices[] = { + [0] = "NORMAL", + [1] = "RANDOM", + [2] = "SEQUENTIAL", + [3] = "WILLNEED", + [4] = "DONTNEED", + [5] = "NOREUSE", + }; + $ + +The tools/perf/check-headers.sh script, part of the tools/ build +process, points out changes in the original files. + +So its important not to touch the copies in tools/ when doing changes in +the original kernel headers, that will be done later, when +check-headers.sh inform about the change to the perf tools hackers. + +Another explanation from Ingo Molnar: +It's better than all the alternatives we tried so far: + + - Symbolic links and direct #includes: this was the original approach but + was pushed back on from the kernel side, when tooling modified the + headers and broke them accidentally for kernel builds. + + - Duplicate self-defined ABI headers like glibc: double the maintenance + burden, double the chance for mistakes, plus there's no tech-driven + notification mechanism to look at new kernel side changes. + +What we are doing now is a third option: + + - A software-enforced copy-on-write mechanism of kernel headers to + tooling, driven by non-fatal warnings on the tooling side build when + kernel headers get modified: + + Warning: Kernel ABI header differences: + diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h + diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h + diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h + ... + + The tooling policy is to always pick up the kernel side headers as-is, + and integate them into the tooling build. The warnings above serve as a + notification to tooling maintainers that there's changes on the kernel + side. + +We've been using this for many years now, and it might seem hacky, but +works surprisingly well. + diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index a00d53d02723..5bf6148cac2b 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -737,7 +737,7 @@ __SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64) #define __NR_ppoll_time64 414 __SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64) #define __NR_io_pgetevents_time64 416 -__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +__SC_COMP(__NR_io_pgetevents_time64, sys_io_pgetevents, compat_sys_io_pgetevents_time64) #define __NR_recvmmsg_time64 417 __SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64) #define __NR_mq_timedsend_time64 418 diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index d4d86e566e07..535cb68fdb5c 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2163,6 +2163,15 @@ struct drm_i915_gem_context_param { * supports this per context flag. */ #define I915_CONTEXT_PARAM_LOW_LATENCY 0xe + +/* + * I915_CONTEXT_PARAM_CONTEXT_IMAGE: + * + * Allows userspace to provide own context images. + * + * Note that this is a debug API not available on production kernel builds. + */ +#define I915_CONTEXT_PARAM_CONTEXT_IMAGE 0xf /* Must be kept compact -- no holes and well documented */ /** @value: Context parameter value to be set or queried */ @@ -2564,6 +2573,24 @@ struct i915_context_param_engines { struct i915_engine_class_instance engines[N__]; \ } __attribute__((packed)) name__ +struct i915_gem_context_param_context_image { + /** @engine: Engine class & instance to be configured. */ + struct i915_engine_class_instance engine; + + /** @flags: One of the supported flags or zero. */ + __u32 flags; +#define I915_CONTEXT_IMAGE_FLAG_ENGINE_INDEX (1u << 0) + + /** @size: Size of the image blob pointed to by @image. */ + __u32 size; + + /** @mbz: Must be zero. */ + __u32 mbz; + + /** @image: Userspace memory containing the context image. */ + __u64 image; +} __attribute__((packed)); + /** * struct drm_i915_gem_context_create_ext_setparam - Context parameter * to set or query during context creation. diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index e682ab628dfa..d358add1611c 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -81,6 +81,8 @@ enum { #define IPPROTO_ETHERNET IPPROTO_ETHERNET IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW + IPPROTO_SMC = 256, /* Shared Memory Communications */ +#define IPPROTO_SMC IPPROTO_SMC IPPROTO_MPTCP = 262, /* Multipath TCP connection */ #define IPPROTO_MPTCP IPPROTO_MPTCP IPPROTO_MAX diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index e5af8c692dc0..637efc055145 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -192,11 +192,24 @@ struct kvm_xen_exit { /* Flags that describe what fields in emulation_failure hold valid data. */ #define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) +/* + * struct kvm_run can be modified by userspace at any time, so KVM must be + * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM() + * renames fields in struct kvm_run from <symbol> to <symbol>__unsafe when + * compiled into the kernel, ensuring that any use within KVM is obvious and + * gets extra scrutiny. + */ +#ifdef __KERNEL__ +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe +#else +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol +#endif + /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { /* in */ __u8 request_interrupt_window; - __u8 immediate_exit; + __u8 HINT_UNSAFE_IN_KVM(immediate_exit); __u8 padding1[6]; /* out */ @@ -918,6 +931,8 @@ struct kvm_enable_cap { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 #define KVM_CAP_PRE_FAULT_MEMORY 236 +#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 +#define KVM_CAP_X86_GUEST_MODE 238 struct kvm_irq_routing_irqchip { __u32 irqchip; diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 3a64499b0f5d..4842c36fdf80 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1349,12 +1349,14 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -/* 5-0x7 available */ +#define PERF_MEM_LVLNUM_L2_MHB 0x05 /* L2 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_MSC 0x06 /* Memory-side Cache */ +/* 0x7 available */ #define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ #define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ -#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ +#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB / L1 Miss Handling Buffer */ #define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ #define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ #define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 67626d535316..887a25286441 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -126,9 +126,15 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[11]; /* Spare space for future expansion */ + __u64 stx_subvol; /* Subvolume identifier */ + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */ + /* 0xb0 */ + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */ + __u32 __spare1[1]; + /* 0xb8 */ + __u64 __spare3[9]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -157,6 +163,7 @@ struct statx { #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -192,6 +199,7 @@ struct statx { #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 3656f1ca7a21..ebae8415dfbb 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -230,8 +230,10 @@ 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 179 64 pread64 sys_pread64 +179 spu pread64 sys_pread64 180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 180 64 pwrite64 sys_pwrite64 +180 spu pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -246,6 +248,7 @@ 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit 191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead 191 64 readahead sys_readahead +191 spu readahead sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 @@ -293,6 +296,7 @@ 232 nospu set_tid_address sys_set_tid_address 233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 233 64 fadvise64 sys_fadvise64 +233 spu fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_ni_syscall 236 common epoll_create sys_epoll_create @@ -502,7 +506,7 @@ 412 32 utimensat_time64 sys_utimensat sys_utimensat 413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index bd0fee24ad10..01071182763e 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -418,7 +418,7 @@ 412 32 utimensat_time64 - sys_utimensat 413 32 pselect6_time64 - compat_sys_pselect6_time64 414 32 ppoll_time64 - compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 - sys_io_pgetevents +416 32 io_pgetevents_time64 - compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 - sys_mq_timedsend 419 32 mq_timedreceive_time64 - sys_mq_timedreceive diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index a396f6e6ab5b..7093ee21c0d1 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -1,8 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note # # 64-bit system call numbers and entry vectors # # The format is: -# <number> <abi> <name> <entry point> +# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]] # # The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls # @@ -68,7 +69,7 @@ 57 common fork sys_fork 58 common vfork sys_vfork 59 64 execve sys_execve -60 common exit sys_exit +60 common exit sys_exit - noreturn 61 common wait4 sys_wait4 62 common kill sys_kill 63 common uname sys_newuname @@ -239,7 +240,7 @@ 228 common clock_gettime sys_clock_gettime 229 common clock_getres sys_clock_getres 230 common clock_nanosleep sys_clock_nanosleep -231 common exit_group sys_exit_group +231 common exit_group sys_exit_group - noreturn 232 common epoll_wait sys_epoll_wait 233 common epoll_ctl sys_epoll_ctl 234 common tgkill sys_tgkill @@ -343,6 +344,7 @@ 332 common statx sys_statx 333 common io_pgetevents sys_io_pgetevents 334 common rseq sys_rseq +335 common uretprobe sys_uretprobe # don't use numbers 387 through 423, add new calls after the last # 'common' entry 424 common pidfd_send_signal sys_pidfd_send_signal diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index de76bbc50bfb..5c9335fff2d3 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <internal/lib.h> +#include <inttypes.h> #include <subcmd/parse-options.h> #include <api/fd/array.h> #include <api/fs/fs.h> @@ -688,7 +689,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) /* lock */ csv_sep, daemon->base, "lock"); - fprintf(out, "%c%lu", + fprintf(out, "%c%" PRIu64, /* session up time */ csv_sep, (curr - daemon->start) / 60); @@ -700,7 +701,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) daemon->base, SESSION_OUTPUT); fprintf(out, " lock: %s/lock\n", daemon->base); - fprintf(out, " up: %lu minutes\n", + fprintf(out, " up: %" PRIu64 " minutes\n", (curr - daemon->start) / 60); } } @@ -727,7 +728,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) /* session ack */ csv_sep, session->base, SESSION_ACK); - fprintf(out, "%c%lu", + fprintf(out, "%c%" PRIu64, /* session up time */ csv_sep, (curr - session->start) / 60); @@ -745,7 +746,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) session->base, SESSION_CONTROL); fprintf(out, " ack: %s/%s\n", session->base, SESSION_ACK); - fprintf(out, " up: %lu minutes\n", + fprintf(out, " up: %" PRIu64 " minutes\n", (curr - session->start) / 60); } } diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 89d16b90370b..df9cdb8bbfb8 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -76,7 +76,7 @@ struct msghdr { __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ struct ubuf_info *msg_ubuf; - int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb, + int (*sg_from_iter)(struct sk_buff *skb, struct iov_iter *from, size_t length); }; @@ -442,11 +442,14 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, extern int __sys_socket(int family, int type, int protocol); extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); +extern int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address, + int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen); extern int __sys_listen(int fd, int backlog); +extern int __sys_listen_socket(struct socket *sock, int backlog); extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h index 45e4e64fd664..753971770733 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fs.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h @@ -329,12 +329,17 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO negation of O_APPEND */ #define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) +/* Atomic Write */ +#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND | RWF_NOAPPEND) + RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC) + +#define PROCFS_IOCTL_MAGIC 'f' /* Pagemap ioctl */ -#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) +#define PAGEMAP_SCAN _IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg) /* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */ #define PAGE_IS_WPALLOWED (1 << 0) @@ -393,4 +398,158 @@ struct pm_scan_arg { __u64 return_mask; }; +/* /proc/<pid>/maps ioctl */ +#define PROCMAP_QUERY _IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query) + +enum procmap_query_flags { + /* + * VMA permission flags. + * + * Can be used as part of procmap_query.query_flags field to look up + * only VMAs satisfying specified subset of permissions. E.g., specifying + * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs, + * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only + * return read/write VMAs, though both executable/non-executable and + * private/shared will be ignored. + * + * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags + * field to specify actual VMA permissions. + */ + PROCMAP_QUERY_VMA_READABLE = 0x01, + PROCMAP_QUERY_VMA_WRITABLE = 0x02, + PROCMAP_QUERY_VMA_EXECUTABLE = 0x04, + PROCMAP_QUERY_VMA_SHARED = 0x08, + /* + * Query modifier flags. + * + * By default VMA that covers provided address is returned, or -ENOENT + * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest + * VMA with vma_start > addr will be returned if no covering VMA is + * found. + * + * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that + * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA + * to iterate all VMAs with file backing. + */ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA = 0x10, + PROCMAP_QUERY_FILE_BACKED_VMA = 0x20, +}; + +/* + * Input/output argument structured passed into ioctl() call. It can be used + * to query a set of VMAs (Virtual Memory Areas) of a process. + * + * Each field can be one of three kinds, marked in a short comment to the + * right of the field: + * - "in", input argument, user has to provide this value, kernel doesn't modify it; + * - "out", output argument, kernel sets this field with VMA data; + * - "in/out", input and output argument; user provides initial value (used + * to specify maximum allowable buffer size), and kernel sets it to actual + * amount of data written (or zero, if there is no data). + * + * If matching VMA is found (according to criterias specified by + * query_addr/query_flags, all the out fields are filled out, and ioctl() + * returns 0. If there is no matching VMA, -ENOENT will be returned. + * In case of any other error, negative error code other than -ENOENT is + * returned. + * + * Most of the data is similar to the one returned as text in /proc/<pid>/maps + * file, but procmap_query provides more querying flexibility. There are no + * consistency guarantees between subsequent ioctl() calls, but data returned + * for matched VMA is self-consistent. + */ +struct procmap_query { + /* Query struct size, for backwards/forward compatibility */ + __u64 size; + /* + * Query flags, a combination of enum procmap_query_flags values. + * Defines query filtering and behavior, see enum procmap_query_flags. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_flags; /* in */ + /* + * Query address. By default, VMA that covers this address will + * be looked up. PROCMAP_QUERY_* flags above modify this default + * behavior further. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_addr; /* in */ + /* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */ + __u64 vma_start; /* out */ + __u64 vma_end; /* out */ + /* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */ + __u64 vma_flags; /* out */ + /* VMA backing page size granularity. */ + __u64 vma_page_size; /* out */ + /* + * VMA file offset. If VMA has file backing, this specifies offset + * within the file that VMA's start address corresponds to. + * Is set to zero if VMA has no backing file. + */ + __u64 vma_offset; /* out */ + /* Backing file's inode number, or zero, if VMA has no backing file. */ + __u64 inode; /* out */ + /* Backing file's device major/minor number, or zero, if VMA has no backing file. */ + __u32 dev_major; /* out */ + __u32 dev_minor; /* out */ + /* + * If set to non-zero value, signals the request to return VMA name + * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix + * appended, if file was unlinked from FS) for matched VMA. VMA name + * can also be some special name (e.g., "[heap]", "[stack]") or could + * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME). + * + * Kernel will set this field to zero, if VMA has no associated name. + * Otherwise kernel will return actual amount of bytes filled in + * user-supplied buffer (see vma_name_addr field below), including the + * terminating zero. + * + * If VMA name is longer that user-supplied maximum buffer size, + * -E2BIG error is returned. + * + * If this field is set to non-zero value, vma_name_addr should point + * to valid user space memory buffer of at least vma_name_size bytes. + * If set to zero, vma_name_addr should be set to zero as well + */ + __u32 vma_name_size; /* in/out */ + /* + * If set to non-zero value, signals the request to extract and return + * VMA's backing file's build ID, if the backing file is an ELF file + * and it contains embedded build ID. + * + * Kernel will set this field to zero, if VMA has no backing file, + * backing file is not an ELF file, or ELF file has no build ID + * embedded. + * + * Build ID is a binary value (not a string). Kernel will set + * build_id_size field to exact number of bytes used for build ID. + * If build ID is requested and present, but needs more bytes than + * user-supplied maximum buffer size (see build_id_addr field below), + * -E2BIG error will be returned. + * + * If this field is set to non-zero value, build_id_addr should point + * to valid user space memory buffer of at least build_id_size bytes. + * If set to zero, build_id_addr should be set to zero as well + */ + __u32 build_id_size; /* in/out */ + /* + * User-supplied address of a buffer of at least vma_name_size bytes + * for kernel to fill with matched VMA's name (see vma_name_size field + * description above for details). + * + * Should be set to zero if VMA name should not be returned. + */ + __u64 vma_name_addr; /* in */ + /* + * User-supplied address of a buffer of at least build_id_size bytes + * for kernel to fill with matched VMA's ELF build ID, if available + * (see build_id_size field description above for details). + * + * Should be set to zero if build ID should not be returned. + */ + __u64 build_id_addr; /* in */ +}; + #endif /* _UAPI_LINUX_FS_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h index ad5478dbad00..225bc366ffcb 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/mount.h +++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h @@ -154,7 +154,7 @@ struct mount_attr { */ struct statmount { __u32 size; /* Total size, including strings */ - __u32 __spare1; + __u32 mnt_opts; /* [str] Mount options of the mount */ __u64 mask; /* What results were written */ __u32 sb_dev_major; /* Device ID */ __u32 sb_dev_minor; @@ -172,7 +172,8 @@ struct statmount { __u64 propagate_from; /* Propagation from in current namespace */ __u32 mnt_root; /* [str] Root of mount relative to root of fs */ __u32 mnt_point; /* [str] Mountpoint relative to current root */ - __u64 __spare2[50]; + __u64 mnt_ns_id; /* ID of the mount namespace */ + __u64 __spare2[49]; char str[]; /* Variable size part containing strings */ }; @@ -188,10 +189,12 @@ struct mnt_id_req { __u32 spare; __u64 mnt_id; __u64 param; + __u64 mnt_ns_id; }; /* List of all mnt_id_req versions. */ #define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */ +#define MNT_ID_REQ_SIZE_VER1 32 /* sizeof second published struct */ /* * @mask bits for statmount(2) @@ -202,10 +205,13 @@ struct mnt_id_req { #define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */ #define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ #define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ +#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ +#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */ /* * Special @mnt_id values that can be passed to listmount */ #define LSMT_ROOT 0xffffffffffffffff /* root mount */ +#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ #endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h index 67626d535316..887a25286441 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/stat.h +++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h @@ -126,9 +126,15 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[11]; /* Spare space for future expansion */ + __u64 stx_subvol; /* Subvolume identifier */ + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */ + /* 0xb0 */ + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */ + __u32 __spare1[1]; + /* 0xb8 */ + __u64 __spare3[9]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -157,6 +163,7 @@ struct statx { #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -192,6 +199,7 @@ struct statx { #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/perf/trace/beauty/include/uapi/sound/asound.h b/tools/perf/trace/beauty/include/uapi/sound/asound.h index 628d46a0da92..8bf7e8a0eb6f 100644 --- a/tools/perf/trace/beauty/include/uapi/sound/asound.h +++ b/tools/perf/trace/beauty/include/uapi/sound/asound.h @@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image { * * *****************************************************************************/ -#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17) +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 18) typedef unsigned long snd_pcm_uframes_t; typedef signed long snd_pcm_sframes_t; @@ -334,7 +334,7 @@ union snd_pcm_sync_id { unsigned char id[16]; unsigned short id16[8]; unsigned int id32[4]; -}; +} __attribute__((deprecated)); struct snd_pcm_info { unsigned int device; /* RO/WR (control): device number */ @@ -348,7 +348,7 @@ struct snd_pcm_info { int dev_subclass; /* SNDRV_PCM_SUBCLASS_* */ unsigned int subdevices_count; unsigned int subdevices_avail; - union snd_pcm_sync_id sync; /* hardware synchronization ID */ + unsigned char pad1[16]; /* was: hardware synchronization ID */ unsigned char reserved[64]; /* reserved for future... */ }; @@ -420,7 +420,8 @@ struct snd_pcm_hw_params { unsigned int rate_num; /* R: rate numerator */ unsigned int rate_den; /* R: rate denominator */ snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */ - unsigned char reserved[64]; /* reserved for future */ + unsigned char sync[16]; /* R: synchronization ID (perfect sync - one clock source) */ + unsigned char reserved[48]; /* reserved for future */ }; enum { diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 16bdc3e25591..ef70b88bccb2 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -1432,4 +1432,58 @@ int iter_arr_with_actual_elem_count(const void *ctx) return sum; } +__u32 upper, select_n, result; +__u64 global; + +static __noinline bool nest_2(char *str) +{ + /* some insns (including branch insns) to ensure stacksafe() is triggered + * in nest_2(). This way, stacksafe() can compare frame associated with nest_1(). + */ + if (str[0] == 't') + return true; + if (str[1] == 'e') + return true; + if (str[2] == 's') + return true; + if (str[3] == 't') + return true; + return false; +} + +static __noinline bool nest_1(int n) +{ + /* case 0: allocate stack, case 1: no allocate stack */ + switch (n) { + case 0: { + char comm[16]; + + if (bpf_get_current_comm(comm, 16)) + return false; + return nest_2(comm); + } + case 1: + return nest_2((char *)&global); + default: + return false; + } +} + +SEC("raw_tp") +__success +int iter_subprog_check_stacksafe(const void *ctx) +{ + long i; + + bpf_for(i, 0, upper) { + if (!nest_1(select_n)) { + result = 1; + return 0; + } + } + + result = 2; + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index 991c473e3859..12b4eb9d0434 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -589,4 +589,39 @@ TEST(close_range_cloexec_unshare_syzbot) EXPECT_EQ(close(fd3), 0); } +TEST(close_range_bitmap_corruption) +{ + pid_t pid; + int status; + struct __clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + /* get the first 128 descriptors open */ + for (int i = 2; i < 128; i++) + EXPECT_GE(dup2(0, i), 0); + + /* get descriptor table shared */ + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + /* unshare and truncate descriptor table down to 64 */ + if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE)) + exit(EXIT_FAILURE); + + ASSERT_EQ(fcntl(64, F_GETFD), -1); + /* ... and verify that the range 64..127 is not + stuck "fully used" according to secondary bitmap */ + EXPECT_EQ(dup(0), 64) + exit(EXIT_FAILURE); + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index 709d7d721760..4abebde78187 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -32,13 +32,13 @@ static struct feature_id_reg feat_id_regs[] = { { ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ - 4, + 8, 1 }, { ARM64_SYS_REG(3, 0, 10, 2, 3), /* PIR_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ - 4, + 8, 1 } }; diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index 69849acd95b0..618cd2442390 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -184,6 +184,33 @@ static void test_apic_id(void) kvm_vm_free(vm); } +static void test_x2apic_id(void) +{ + struct kvm_lapic_state lapic = {}; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int i; + + vm = vm_create_with_one_vcpu(&vcpu, NULL); + vcpu_set_msr(vcpu, MSR_IA32_APICBASE, MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); + + /* + * Try stuffing a modified x2APIC ID, KVM should ignore the value and + * always return the vCPU's default/readonly x2APIC ID. + */ + for (i = 0; i <= 0xff; i++) { + *(u32 *)(lapic.regs + APIC_ID) = i << 24; + *(u32 *)(lapic.regs + APIC_SPIV) = APIC_SPIV_APIC_ENABLED; + vcpu_ioctl(vcpu, KVM_SET_LAPIC, &lapic); + + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &lapic); + TEST_ASSERT(*((u32 *)&lapic.regs[APIC_ID]) == vcpu->id << 24, + "x2APIC ID should be fully readonly"); + } + + kvm_vm_free(vm); +} + int main(int argc, char *argv[]) { struct xapic_vcpu x = { @@ -211,4 +238,5 @@ int main(int argc, char *argv[]) kvm_vm_free(vm); test_apic_id(); + test_x2apic_id(); } diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c index 16d0c172eaeb..535eb2c3d7d1 100644 --- a/tools/testing/selftests/net/af_unix/msg_oob.c +++ b/tools/testing/selftests/net/af_unix/msg_oob.c @@ -209,7 +209,7 @@ static void __sendpair(struct __test_metadata *_metadata, static void __recvpair(struct __test_metadata *_metadata, FIXTURE_DATA(msg_oob) *self, - const void *expected_buf, int expected_len, + const char *expected_buf, int expected_len, int buf_len, int flags) { int i, ret[2], recv_errno[2], expected_errno = 0; diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index d0219032f773..8ee4489238ca 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -146,6 +146,7 @@ cleanup_ns() for ns in "$@"; do [ -z "${ns}" ] && continue + ip netns pids "${ns}" 2> /dev/null | xargs -r kill || true ip netns delete "${ns}" &> /dev/null || true if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then echo "Warn: Failed to remove namespace $ns" diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile index 47945b2b3f92..d13fb5ea3e89 100644 --- a/tools/testing/selftests/net/netfilter/Makefile +++ b/tools/testing/selftests/net/netfilter/Makefile @@ -7,6 +7,7 @@ MNL_CFLAGS := $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null) MNL_LDLIBS := $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) TEST_PROGS := br_netfilter.sh bridge_brouter.sh +TEST_PROGS += br_netfilter_queue.sh TEST_PROGS += conntrack_icmp_related.sh TEST_PROGS += conntrack_ipip_mtu.sh TEST_PROGS += conntrack_tcp_unreplied.sh diff --git a/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh new file mode 100755 index 000000000000..6a764d70ab06 --- /dev/null +++ b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh @@ -0,0 +1,78 @@ +#!/bin/bash + +source lib.sh + +checktool "nft --version" "run test without nft tool" + +cleanup() { + cleanup_all_ns +} + +setup_ns c1 c2 c3 sender + +trap cleanup EXIT + +nf_queue_wait() +{ + grep -q "^ *$1 " "/proc/self/net/netfilter/nfnetlink_queue" +} + +port_add() { + ns="$1" + dev="$2" + a="$3" + + ip link add name "$dev" type veth peer name "$dev" netns "$ns" + + ip -net "$ns" addr add 192.168.1."$a"/24 dev "$dev" + ip -net "$ns" link set "$dev" up + + ip link set "$dev" master br0 + ip link set "$dev" up +} + +[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; } + +ip link add br0 type bridge +ip addr add 192.168.1.254/24 dev br0 + +port_add "$c1" "c1" 1 +port_add "$c2" "c2" 2 +port_add "$c3" "c3" 3 +port_add "$sender" "sender" 253 + +ip link set br0 up + +modprobe -q br_netfilter + +sysctl net.bridge.bridge-nf-call-iptables=1 || exit 1 + +ip netns exec "$sender" ping -I sender -c1 192.168.1.1 || exit 1 +ip netns exec "$sender" ping -I sender -c1 192.168.1.2 || exit 2 +ip netns exec "$sender" ping -I sender -c1 192.168.1.3 || exit 3 + +nft -f /dev/stdin <<EOF +table ip filter { + chain forward { + type filter hook forward priority 0; policy accept; + ct state new counter + ip protocol icmp counter queue num 0 bypass + } +} +EOF +./nf_queue -t 5 > /dev/null & + +busywait 5000 nf_queue_wait + +for i in $(seq 1 5); do conntrack -F > /dev/null 2> /dev/null; sleep 0.1 ; done & +ip netns exec "$sender" ping -I sender -f -c 50 -b 192.168.1.255 + +read t < /proc/sys/kernel/tainted +if [ "$t" -eq 0 ];then + echo PASS: kernel not tainted +else + echo ERROR: kernel is tainted + exit 1 +fi + +exit 0 diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 3e74cfa1a2bf..3f2fca02fec5 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -67,6 +67,7 @@ struct testcase { int gso_len; /* mss after applying gso */ int r_num_mss; /* recv(): number of calls of full mss */ int r_len_last; /* recv(): size of last non-mss dgram, if any */ + bool v6_ext_hdr; /* send() dgrams with IPv6 extension headers */ }; const struct in6_addr addr6 = { @@ -77,6 +78,8 @@ const struct in_addr addr4 = { __constant_htonl(0x0a000001), /* 10.0.0.1 */ }; +static const char ipv6_hopopts_pad1[8] = { 0 }; + struct testcase testcases_v4[] = { { /* no GSO: send a single byte */ @@ -256,6 +259,13 @@ struct testcase testcases_v6[] = { .r_num_mss = 2, }, { + /* send 2 1B segments with extension headers */ + .tlen = 2, + .gso_len = 1, + .r_num_mss = 2, + .v6_ext_hdr = true, + }, + { /* send 2B + 2B + 1B segments */ .tlen = 5, .gso_len = 2, @@ -396,11 +406,18 @@ static void run_one(struct testcase *test, int fdt, int fdr, int i, ret, val, mss; bool sent; - fprintf(stderr, "ipv%d tx:%d gso:%d %s\n", + fprintf(stderr, "ipv%d tx:%d gso:%d %s%s\n", addr->sa_family == AF_INET ? 4 : 6, test->tlen, test->gso_len, + test->v6_ext_hdr ? "ext-hdr " : "", test->tfail ? "(fail)" : ""); + if (test->v6_ext_hdr) { + if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS, + ipv6_hopopts_pad1, sizeof(ipv6_hopopts_pad1))) + error(1, errno, "setsockopt ipv6 hopopts"); + } + val = test->gso_len; if (cfg_do_setsockopt) { if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val))) @@ -412,6 +429,12 @@ static void run_one(struct testcase *test, int fdt, int fdr, error(1, 0, "send succeeded while expecting failure"); if (!sent && !test->tfail) error(1, 0, "send failed while expecting success"); + + if (test->v6_ext_hdr) { + if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS, NULL, 0)) + error(1, errno, "setsockopt ipv6 hopopts clear"); + } + if (!sent) return; diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 229570059a1b..992f9beb3e7d 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -97,18 +97,19 @@ irqfd_resampler_shutdown(struct kvm_kernel_irqfd *irqfd) mutex_lock(&kvm->irqfds.resampler_lock); list_del_rcu(&irqfd->resampler_link); - synchronize_srcu(&kvm->irq_srcu); if (list_empty(&resampler->list)) { list_del_rcu(&resampler->link); kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier); /* - * synchronize_srcu(&kvm->irq_srcu) already called + * synchronize_srcu_expedited(&kvm->irq_srcu) already called * in kvm_unregister_irq_ack_notifier(). */ kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, resampler->notifier.gsi, 0, false); kfree(resampler); + } else { + synchronize_srcu_expedited(&kvm->irq_srcu); } mutex_unlock(&kvm->irqfds.resampler_lock); @@ -126,7 +127,7 @@ irqfd_shutdown(struct work_struct *work) u64 cnt; /* Make sure irqfd has been initialized in assign path. */ - synchronize_srcu(&kvm->irq_srcu); + synchronize_srcu_expedited(&kvm->irq_srcu); /* * Synchronize with the wait-queue and unhook ourselves to prevent @@ -384,7 +385,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) } list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list); - synchronize_srcu(&kvm->irq_srcu); + synchronize_srcu_expedited(&kvm->irq_srcu); mutex_unlock(&kvm->irqfds.resampler_lock); } @@ -523,7 +524,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm, mutex_lock(&kvm->irq_lock); hlist_del_init_rcu(&kian->link); mutex_unlock(&kvm->irq_lock); - synchronize_srcu(&kvm->irq_srcu); + synchronize_srcu_expedited(&kvm->irq_srcu); kvm_arch_post_irq_ack_notifier_list_update(kvm); } @@ -608,7 +609,7 @@ kvm_irqfd_release(struct kvm *kvm) /* * Take note of a change in irq routing. - * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards. + * Caller must invoke synchronize_srcu_expedited(&kvm->irq_srcu) afterwards. */ void kvm_irq_routing_update(struct kvm *kvm) { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 92901656a0d4..cb2b78e92910 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1578,15 +1578,14 @@ static int check_memory_region_flags(struct kvm *kvm, if (mem->flags & KVM_MEM_GUEST_MEMFD) valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES; -#ifdef CONFIG_HAVE_KVM_READONLY_MEM /* * GUEST_MEMFD is incompatible with read-only memslots, as writes to * read-only memslots have emulated MMIO, not page fault, semantics, * and KVM doesn't allow emulated MMIO for private memory. */ - if (!(mem->flags & KVM_MEM_GUEST_MEMFD)) + if (kvm_arch_has_readonly_mem(kvm) && + !(mem->flags & KVM_MEM_GUEST_MEMFD)) valid_flags |= KVM_MEM_READONLY; -#endif if (mem->flags & ~valid_flags) return -EINVAL; |