diff options
128 files changed, 1138 insertions, 515 deletions
diff --git a/Documentation/netlink/specs/conntrack.yaml b/Documentation/netlink/specs/conntrack.yaml index c6832633ab7b..591e22a2ee43 100644 --- a/Documentation/netlink/specs/conntrack.yaml +++ b/Documentation/netlink/specs/conntrack.yaml @@ -575,8 +575,8 @@ operations: - nat-dst - timeout - mark - - counter-orig - - counter-reply + - counters-orig + - counters-reply - use - id - nat-dst @@ -591,7 +591,6 @@ operations: request: value: 0x101 attributes: - - nfgen-family - mark - filter - status @@ -608,8 +607,8 @@ operations: - nat-dst - timeout - mark - - counter-orig - - counter-reply + - counters-orig + - counters-reply - use - id - nat-dst diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml index d15335684ec3..d1b4829b580a 100644 --- a/Documentation/netlink/specs/mptcp_pm.yaml +++ b/Documentation/netlink/specs/mptcp_pm.yaml @@ -28,13 +28,13 @@ definitions: traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent. Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, server-side. + dport, server-side, [flags]. - name: established doc: >- A MPTCP connection is established (can start new subflows). Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, server-side. + dport, server-side, [flags]. - name: closed doc: >- diff --git a/MAINTAINERS b/MAINTAINERS index f6206963efbf..520fb4e379a3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7430,7 +7430,7 @@ S: Supported F: Documentation/devicetree/bindings/dpll/dpll-device.yaml F: Documentation/devicetree/bindings/dpll/dpll-pin.yaml F: Documentation/driver-api/dpll.rst -F: drivers/dpll/* +F: drivers/dpll/ F: include/linux/dpll.h F: include/uapi/linux/dpll.h @@ -16196,6 +16196,7 @@ R: Rik van Riel <riel@surriel.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> R: Vlastimil Babka <vbabka@suse.cz> R: Harry Yoo <harry.yoo@oracle.com> +R: Jann Horn <jannh@google.com> L: linux-mm@kvack.org S: Maintained F: include/linux/rmap.h @@ -16240,6 +16241,7 @@ R: Nico Pache <npache@redhat.com> R: Ryan Roberts <ryan.roberts@arm.com> R: Dev Jain <dev.jain@arm.com> R: Barry Song <baohua@kernel.org> +R: Lance Yang <lance.yang@linux.dev> L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org @@ -22050,6 +22052,7 @@ F: drivers/infiniband/ulp/rtrs/ RUNTIME VERIFICATION (RV) M: Steven Rostedt <rostedt@goodmis.org> +M: Gabriele Monaco <gmonaco@redhat.com> L: linux-trace-kernel@vger.kernel.org S: Maintained F: Documentation/trace/rv/ @@ -24257,7 +24260,7 @@ F: Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml F: drivers/input/keyboard/sun4i-lradc-keys.c SUNDANCE NETWORK DRIVER -M: Denis Kirjanov <dkirjanov@suse.de> +M: Denis Kirjanov <kirjanov@gmail.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/dlink/sundance.c diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 2b07f0a27a7d..0ee4f6fa3a17 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1369,6 +1369,7 @@ static inline bool kvm_system_needs_idmapped_vectors(void) } void kvm_init_host_debug_data(void); +void kvm_debug_init_vhe(void); void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu); void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu); void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 1246216616b5..2888b5d03757 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -355,11 +355,6 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke return pteref; } -static inline kvm_pte_t *kvm_dereference_pteref_raw(kvm_pteref_t pteref) -{ - return pteref; -} - static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) { /* @@ -389,11 +384,6 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED)); } -static inline kvm_pte_t *kvm_dereference_pteref_raw(kvm_pteref_t pteref) -{ - return rcu_dereference_raw(pteref); -} - static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) { if (walker->flags & KVM_PGTABLE_WALK_SHARED) @@ -562,26 +552,6 @@ static inline int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2 void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt); /** - * kvm_pgtable_stage2_destroy_range() - Destroy the unlinked range of addresses. - * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). - * @addr: Intermediate physical address at which to place the mapping. - * @size: Size of the mapping. - * - * The page-table is assumed to be unreachable by any hardware walkers prior - * to freeing and therefore no TLB invalidation is performed. - */ -void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt, - u64 addr, u64 size); - -/** - * kvm_pgtable_stage2_destroy_pgd() - Destroy the PGD of guest stage-2 page-table. - * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). - * - * It is assumed that the rest of the page-table is freed before this operation. - */ -void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt); - -/** * kvm_pgtable_stage2_free_unlinked() - Free an unlinked stage-2 paging structure. * @mm_ops: Memory management callbacks. * @pgtable: Unlinked stage-2 paging structure to be freed. diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h index 35f9d9478004..ea58282f59bb 100644 --- a/arch/arm64/include/asm/kvm_pkvm.h +++ b/arch/arm64/include/asm/kvm_pkvm.h @@ -179,9 +179,7 @@ struct pkvm_mapping { int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops); -void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt, - u64 addr, u64 size); -void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt); +void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt); int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot, void *mc, enum kvm_pgtable_walk_flags flags); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 5bf101c869c9..bd6b6a620a09 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2113,8 +2113,10 @@ static void cpu_hyp_init_features(void) { cpu_set_hyp_vector(); - if (is_kernel_in_hyp_mode()) + if (is_kernel_in_hyp_mode()) { kvm_timer_init_vhe(); + kvm_debug_init_vhe(); + } if (vgic_present) kvm_vgic_init_cpu_hardware(); diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index 381382c19fe4..e027d9c32b0d 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -96,6 +96,13 @@ void kvm_init_host_debug_data(void) } } +void kvm_debug_init_vhe(void) +{ + /* Clear PMSCR_EL1.E{0,1}SPE which reset to UNKNOWN values. */ + if (SYS_FIELD_GET(ID_AA64DFR0_EL1, PMSVer, read_sysreg(id_aa64dfr0_el1))) + write_sysreg_el1(0, SYS_PMSCR); +} + /* * Configures the 'external' MDSCR_EL1 value for the guest, i.e. when the host * has taken over MDSCR_EL1. @@ -138,6 +145,9 @@ void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu) /* Must be called before kvm_vcpu_load_vhe() */ KVM_BUG_ON(vcpu_get_flag(vcpu, SYSREGS_ON_CPU), vcpu->kvm); + if (has_vhe()) + *host_data_ptr(host_debug_state.mdcr_el2) = read_sysreg(mdcr_el2); + /* * Determine which of the possible debug states we're in: * @@ -184,6 +194,9 @@ void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu) void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu) { + if (has_vhe()) + write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); + if (likely(!(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) return; diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 84ec4e100fbb..b6682202edf3 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -431,9 +431,6 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) vcpu_set_flag(vcpu, PMUSERENR_ON_CPU); } - *host_data_ptr(host_debug_state.mdcr_el2) = read_sysreg(mdcr_el2); - write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); - if (cpus_have_final_cap(ARM64_HAS_HCX)) { u64 hcrx = vcpu->arch.hcrx_el2; if (is_nested_ctxt(vcpu)) { @@ -454,8 +451,6 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); - write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); - write_sysreg(0, hstr_el2); if (system_supports_pmuv3()) { write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0); diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index ccd575d5f6de..d3b9ec8a7c28 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -50,6 +50,10 @@ extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc); static void __activate_traps(struct kvm_vcpu *vcpu) { ___activate_traps(vcpu, vcpu->arch.hcr_el2); + + *host_data_ptr(host_debug_state.mdcr_el2) = read_sysreg(mdcr_el2); + write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); + __activate_traps_common(vcpu); __activate_cptr_traps(vcpu); @@ -93,6 +97,8 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) isb(); } + write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); + __deactivate_traps_common(vcpu); write_sysreg_hcr(this_cpu_ptr(&kvm_init_params)->hcr_el2); diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 71d2fc97f004..82da9b03692d 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -253,7 +253,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu) *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); *vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR); - __vcpu_assign_sys_reg(vcpu, read_sysreg_el1(SYS_VBAR), VBAR_EL1); + __vcpu_assign_sys_reg(vcpu, VBAR_EL1, read_sysreg_el1(SYS_VBAR)); kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index c36f282a175d..c351b4abd5db 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -1551,38 +1551,21 @@ static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx, return 0; } -void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt, - u64 addr, u64 size) +void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) { + size_t pgd_sz; struct kvm_pgtable_walker walker = { .cb = stage2_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; - WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker)); -} - -void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt) -{ - size_t pgd_sz; - + WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE; - - /* - * Since the pgtable is unlinked at this point, and not shared with - * other walkers, safely deference pgd with kvm_dereference_pteref_raw() - */ - pgt->mm_ops->free_pages_exact(kvm_dereference_pteref_raw(pgt->pgd), pgd_sz); + pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz); pgt->pgd = NULL; } -void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) -{ - kvm_pgtable_stage2_destroy_range(pgt, 0, BIT(pgt->ia_bits)); - kvm_pgtable_stage2_destroy_pgd(pgt); -} - void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level) { kvm_pteref_t ptep = (kvm_pteref_t)pgtable; diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 86f3d80daf37..736394292503 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -904,38 +904,6 @@ static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type) return 0; } -/* - * Assume that @pgt is valid and unlinked from the KVM MMU to free the - * page-table without taking the kvm_mmu_lock and without performing any - * TLB invalidations. - * - * Also, the range of addresses can be large enough to cause need_resched - * warnings, for instance on CONFIG_PREEMPT_NONE kernels. Hence, invoke - * cond_resched() periodically to prevent hogging the CPU for a long time - * and schedule something else, if required. - */ -static void stage2_destroy_range(struct kvm_pgtable *pgt, phys_addr_t addr, - phys_addr_t end) -{ - u64 next; - - do { - next = stage2_range_addr_end(addr, end); - KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, addr, - next - addr); - if (next != end) - cond_resched(); - } while (addr = next, addr != end); -} - -static void kvm_stage2_destroy(struct kvm_pgtable *pgt) -{ - unsigned int ia_bits = VTCR_EL2_IPA(pgt->mmu->vtcr); - - stage2_destroy_range(pgt, 0, BIT(ia_bits)); - KVM_PGT_FN(kvm_pgtable_stage2_destroy_pgd)(pgt); -} - /** * kvm_init_stage2_mmu - Initialise a S2 MMU structure * @kvm: The pointer to the KVM structure @@ -1012,7 +980,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t return 0; out_destroy_pgtable: - kvm_stage2_destroy(pgt); + KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt); out_free_pgtable: kfree(pgt); return err; @@ -1106,10 +1074,14 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu) mmu->pgt = NULL; free_percpu(mmu->last_vcpu_ran); } + + if (kvm_is_nested_s2_mmu(kvm, mmu)) + kvm_init_nested_s2_mmu(mmu); + write_unlock(&kvm->mmu_lock); if (pgt) { - kvm_stage2_destroy(pgt); + KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt); kfree(pgt); } } @@ -1541,11 +1513,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); - if (fault_is_perm && !write_fault && !exec_fault) { - kvm_err("Unexpected L2 read permission error\n"); - return -EFAULT; - } - if (!is_protected_kvm_enabled()) memcache = &vcpu->arch.mmu_page_cache; else diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 77db81bae86f..50d559248a1f 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -847,7 +847,7 @@ static void kvm_invalidate_vncr_ipa(struct kvm *kvm, u64 start, u64 end) ipa_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift, vt->wr.level)); - ipa_start = vt->wr.pa & (ipa_size - 1); + ipa_start = vt->wr.pa & ~(ipa_size - 1); ipa_end = ipa_start + ipa_size; if (ipa_end <= start || ipa_start >= end) @@ -887,7 +887,7 @@ static void invalidate_vncr_va(struct kvm *kvm, va_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift, vt->wr.level)); - va_start = vt->gva & (va_size - 1); + va_start = vt->gva & ~(va_size - 1); va_end = va_start + va_size; switch (scope->type) { @@ -1276,7 +1276,7 @@ static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu) !(tcr & TCR_ASID16)) asid &= GENMASK(7, 0); - return asid != vt->wr.asid; + return asid == vt->wr.asid; } return true; diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c index 61827cf6fea4..fcd70bfe44fb 100644 --- a/arch/arm64/kvm/pkvm.c +++ b/arch/arm64/kvm/pkvm.c @@ -316,16 +316,9 @@ static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 e return 0; } -void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt, - u64 addr, u64 size) +void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) { - __pkvm_pgtable_stage2_unmap(pgt, addr, addr + size); -} - -void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt) -{ - /* Expected to be called after all pKVM mappings have been released. */ - WARN_ON_ONCE(!RB_EMPTY_ROOT(&pgt->pkvm_mappings.rb_root)); + __pkvm_pgtable_stage2_unmap(pgt, 0, ~(0ULL)); } int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index 2684f273d9e1..4c1209261b65 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -69,7 +69,7 @@ static int iter_mark_lpis(struct kvm *kvm) int nr_lpis = 0; xa_for_each(&dist->lpi_xa, intid, irq) { - if (!vgic_try_get_irq_kref(irq)) + if (!vgic_try_get_irq_ref(irq)) continue; xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 1e680ad6e863..4c3c0d82e476 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -53,7 +53,7 @@ void kvm_vgic_early_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - xa_init_flags(&dist->lpi_xa, XA_FLAGS_LOCK_IRQ); + xa_init(&dist->lpi_xa); } /* CREATION */ @@ -208,7 +208,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) raw_spin_lock_init(&irq->irq_lock); irq->vcpu = NULL; irq->target_vcpu = vcpu0; - kref_init(&irq->refcount); + refcount_set(&irq->refcount, 0); switch (dist->vgic_model) { case KVM_DEV_TYPE_ARM_VGIC_V2: irq->targets = 0; @@ -277,7 +277,7 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type) irq->intid = i; irq->vcpu = NULL; irq->target_vcpu = vcpu; - kref_init(&irq->refcount); + refcount_set(&irq->refcount, 0); if (vgic_irq_is_sgi(i)) { /* SGIs */ irq->enabled = 1; diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 7368c13f16b7..ce3e3ed3f29f 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -78,7 +78,6 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = vgic_get_irq(kvm, intid), *oldirq; - unsigned long flags; int ret; /* In this case there is no put, since we keep the reference. */ @@ -89,7 +88,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, if (!irq) return ERR_PTR(-ENOMEM); - ret = xa_reserve_irq(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT); + ret = xa_reserve(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT); if (ret) { kfree(irq); return ERR_PTR(ret); @@ -99,19 +98,19 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, raw_spin_lock_init(&irq->irq_lock); irq->config = VGIC_CONFIG_EDGE; - kref_init(&irq->refcount); + refcount_set(&irq->refcount, 1); irq->intid = intid; irq->target_vcpu = vcpu; irq->group = 1; - xa_lock_irqsave(&dist->lpi_xa, flags); + xa_lock(&dist->lpi_xa); /* * There could be a race with another vgic_add_lpi(), so we need to * check that we don't add a second list entry with the same LPI. */ oldirq = xa_load(&dist->lpi_xa, intid); - if (vgic_try_get_irq_kref(oldirq)) { + if (vgic_try_get_irq_ref(oldirq)) { /* Someone was faster with adding this LPI, lets use that. */ kfree(irq); irq = oldirq; @@ -126,7 +125,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, } out_unlock: - xa_unlock_irqrestore(&dist->lpi_xa, flags); + xa_unlock(&dist->lpi_xa); if (ret) return ERR_PTR(ret); @@ -547,7 +546,7 @@ static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db, rcu_read_lock(); irq = xa_load(&its->translation_cache, cache_key); - if (!vgic_try_get_irq_kref(irq)) + if (!vgic_try_get_irq_ref(irq)) irq = NULL; rcu_read_unlock(); @@ -571,7 +570,7 @@ static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its, * its_lock, as the ITE (and the reference it holds) cannot be freed. */ lockdep_assert_held(&its->its_lock); - vgic_get_irq_kref(irq); + vgic_get_irq_ref(irq); old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT); diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 4d9343d2b0b1..548aec9d5a72 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -518,7 +518,7 @@ static struct vgic_irq *__vgic_host_irq_get_vlpi(struct kvm *kvm, int host_irq) if (!irq->hw || irq->host_irq != host_irq) continue; - if (!vgic_try_get_irq_kref(irq)) + if (!vgic_try_get_irq_ref(irq)) return NULL; return irq; diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index f5148b38120a..6dd5a10081e2 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -28,8 +28,8 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { * kvm->arch.config_lock (mutex) * its->cmd_lock (mutex) * its->its_lock (mutex) - * vgic_cpu->ap_list_lock must be taken with IRQs disabled - * vgic_dist->lpi_xa.xa_lock must be taken with IRQs disabled + * vgic_dist->lpi_xa.xa_lock + * vgic_cpu->ap_list_lock must be taken with IRQs disabled * vgic_irq->irq_lock must be taken with IRQs disabled * * As the ap_list_lock might be taken from the timer interrupt handler, @@ -71,7 +71,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) rcu_read_lock(); irq = xa_load(&dist->lpi_xa, intid); - if (!vgic_try_get_irq_kref(irq)) + if (!vgic_try_get_irq_ref(irq)) irq = NULL; rcu_read_unlock(); @@ -114,37 +114,66 @@ struct vgic_irq *vgic_get_vcpu_irq(struct kvm_vcpu *vcpu, u32 intid) return vgic_get_irq(vcpu->kvm, intid); } -/* - * We can't do anything in here, because we lack the kvm pointer to - * lock and remove the item from the lpi_list. So we keep this function - * empty and use the return value of kref_put() to trigger the freeing. - */ -static void vgic_irq_release(struct kref *ref) +static void vgic_release_lpi_locked(struct vgic_dist *dist, struct vgic_irq *irq) +{ + lockdep_assert_held(&dist->lpi_xa.xa_lock); + __xa_erase(&dist->lpi_xa, irq->intid); + kfree_rcu(irq, rcu); +} + +static __must_check bool __vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) +{ + if (irq->intid < VGIC_MIN_LPI) + return false; + + return refcount_dec_and_test(&irq->refcount); +} + +static __must_check bool vgic_put_irq_norelease(struct kvm *kvm, struct vgic_irq *irq) { + if (!__vgic_put_irq(kvm, irq)) + return false; + + irq->pending_release = true; + return true; } void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { struct vgic_dist *dist = &kvm->arch.vgic; - unsigned long flags; - if (irq->intid < VGIC_MIN_LPI) - return; + if (irq->intid >= VGIC_MIN_LPI) + might_lock(&dist->lpi_xa.xa_lock); - if (!kref_put(&irq->refcount, vgic_irq_release)) + if (!__vgic_put_irq(kvm, irq)) return; - xa_lock_irqsave(&dist->lpi_xa, flags); - __xa_erase(&dist->lpi_xa, irq->intid); - xa_unlock_irqrestore(&dist->lpi_xa, flags); + xa_lock(&dist->lpi_xa); + vgic_release_lpi_locked(dist, irq); + xa_unlock(&dist->lpi_xa); +} - kfree_rcu(irq, rcu); +static void vgic_release_deleted_lpis(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long intid; + struct vgic_irq *irq; + + xa_lock(&dist->lpi_xa); + + xa_for_each(&dist->lpi_xa, intid, irq) { + if (irq->pending_release) + vgic_release_lpi_locked(dist, irq); + } + + xa_unlock(&dist->lpi_xa); } void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq, *tmp; + bool deleted = false; unsigned long flags; raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); @@ -155,11 +184,14 @@ void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) list_del(&irq->ap_list); irq->vcpu = NULL; raw_spin_unlock(&irq->irq_lock); - vgic_put_irq(vcpu->kvm, irq); + deleted |= vgic_put_irq_norelease(vcpu->kvm, irq); } } raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); + + if (deleted) + vgic_release_deleted_lpis(vcpu->kvm); } void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending) @@ -399,7 +431,7 @@ retry: * now in the ap_list. This is safe as the caller must already hold a * reference on the irq. */ - vgic_get_irq_kref(irq); + vgic_get_irq_ref(irq); list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head); irq->vcpu = vcpu; @@ -630,6 +662,7 @@ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq, *tmp; + bool deleted_lpis = false; DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); @@ -657,12 +690,12 @@ retry: /* * This vgic_put_irq call matches the - * vgic_get_irq_kref in vgic_queue_irq_unlock, + * vgic_get_irq_ref in vgic_queue_irq_unlock, * where we added the LPI to the ap_list. As * we remove the irq from the list, we drop * also drop the refcount. */ - vgic_put_irq(vcpu->kvm, irq); + deleted_lpis |= vgic_put_irq_norelease(vcpu->kvm, irq); continue; } @@ -725,6 +758,9 @@ retry: } raw_spin_unlock(&vgic_cpu->ap_list_lock); + + if (unlikely(deleted_lpis)) + vgic_release_deleted_lpis(vcpu->kvm); } static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu) @@ -818,7 +854,7 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) * the AP list has been sorted already. */ if (multi_sgi && irq->priority > prio) { - _raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); break; } diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index de1c1d3261c3..ac5f9c5d2b98 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -267,7 +267,7 @@ void vgic_v2_put(struct kvm_vcpu *vcpu); void vgic_v2_save_state(struct kvm_vcpu *vcpu); void vgic_v2_restore_state(struct kvm_vcpu *vcpu); -static inline bool vgic_try_get_irq_kref(struct vgic_irq *irq) +static inline bool vgic_try_get_irq_ref(struct vgic_irq *irq) { if (!irq) return false; @@ -275,12 +275,12 @@ static inline bool vgic_try_get_irq_kref(struct vgic_irq *irq) if (irq->intid < VGIC_MIN_LPI) return true; - return kref_get_unless_zero(&irq->refcount); + return refcount_inc_not_zero(&irq->refcount); } -static inline void vgic_get_irq_kref(struct vgic_irq *irq) +static inline void vgic_get_irq_ref(struct vgic_irq *irq) { - WARN_ON_ONCE(!vgic_try_get_irq_kref(irq)); + WARN_ON_ONCE(!vgic_try_get_irq_ref(irq)); } void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 2a92a8b9e4c2..9384572ffa7b 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2778,12 +2778,19 @@ static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap) static struct page *get_map_page(struct kvm *kvm, u64 uaddr) { + struct mm_struct *mm = kvm->mm; struct page *page = NULL; + int locked = 1; + + if (mmget_not_zero(mm)) { + mmap_read_lock(mm); + get_user_pages_remote(mm, uaddr, 1, FOLL_WRITE, + &page, &locked); + if (locked) + mmap_read_unlock(mm); + mmput(mm); + } - mmap_read_lock(kvm->mm); - get_user_pages_remote(kvm->mm, uaddr, 1, FOLL_WRITE, - &page, NULL); - mmap_read_unlock(kvm->mm); return page; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index bf6fa8b9ca73..6d51aa5f66be 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4864,12 +4864,12 @@ static void kvm_s390_assert_primary_as(struct kvm_vcpu *vcpu) * @vcpu: the vCPU whose gmap is to be fixed up * @gfn: the guest frame number used for memslots (including fake memslots) * @gaddr: the gmap address, does not have to match @gfn for ucontrol gmaps - * @flags: FOLL_* flags + * @foll: FOLL_* flags * * Return: 0 on success, < 0 in case of error. * Context: The mm lock must not be held before calling. May sleep. */ -int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags) +int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int foll) { struct kvm_memory_slot *slot; unsigned int fault_flags; @@ -4883,13 +4883,13 @@ int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, u if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return vcpu_post_run_addressing_exception(vcpu); - fault_flags = flags & FOLL_WRITE ? FAULT_FLAG_WRITE : 0; + fault_flags = foll & FOLL_WRITE ? FAULT_FLAG_WRITE : 0; if (vcpu->arch.gmap->pfault_enabled) - flags |= FOLL_NOWAIT; + foll |= FOLL_NOWAIT; vmaddr = __gfn_to_hva_memslot(slot, gfn); try_again: - pfn = __kvm_faultin_pfn(slot, gfn, flags, &writable, &page); + pfn = __kvm_faultin_pfn(slot, gfn, foll, &writable, &page); /* Access outside memory, inject addressing exception */ if (is_noslot_pfn(pfn)) @@ -4905,7 +4905,7 @@ try_again: return 0; vcpu->stat.pfault_sync++; /* Could not setup async pfault, try again synchronously */ - flags &= ~FOLL_NOWAIT; + foll &= ~FOLL_NOWAIT; goto try_again; } /* Any other error */ @@ -4925,7 +4925,7 @@ try_again: return rc; } -static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int flags) +static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int foll) { unsigned long gaddr_tmp; gfn_t gfn; @@ -4950,18 +4950,18 @@ static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, un } gfn = gpa_to_gfn(gaddr_tmp); } - return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, flags); + return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, foll); } static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) { - unsigned int flags = 0; + unsigned int foll = 0; unsigned long gaddr; int rc; gaddr = current->thread.gmap_teid.addr * PAGE_SIZE; if (kvm_s390_cur_gmap_fault_is_write()) - flags = FAULT_FLAG_WRITE; + foll = FOLL_WRITE; switch (current->thread.gmap_int_code & PGM_INT_CODE_MASK) { case 0: @@ -5003,7 +5003,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) send_sig(SIGSEGV, current, 0); if (rc != -ENXIO) break; - flags = FAULT_FLAG_WRITE; + foll = FOLL_WRITE; fallthrough; case PGM_PROTECTION: case PGM_SEGMENT_TRANSLATION: @@ -5013,7 +5013,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) case PGM_REGION_SECOND_TRANS: case PGM_REGION_THIRD_TRANS: kvm_s390_assert_primary_as(vcpu); - return vcpu_dat_fault_handler(vcpu, gaddr, flags); + return vcpu_dat_fault_handler(vcpu, gaddr, foll); default: KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx", current->thread.gmap_int_code, current->thread.gmap_teid.val); diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 25ede8354514..6ba5a0305e25 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -624,6 +624,17 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) int cc, ret; u16 dummy; + /* Add the notifier only once. No races because we hold kvm->lock */ + if (kvm->arch.pv.mmu_notifier.ops != &kvm_s390_pv_mmu_notifier_ops) { + /* The notifier will be unregistered when the VM is destroyed */ + kvm->arch.pv.mmu_notifier.ops = &kvm_s390_pv_mmu_notifier_ops; + ret = mmu_notifier_register(&kvm->arch.pv.mmu_notifier, kvm->mm); + if (ret) { + kvm->arch.pv.mmu_notifier.ops = NULL; + return ret; + } + } + ret = kvm_s390_pv_alloc_vm(kvm); if (ret) return ret; @@ -659,11 +670,6 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) return -EIO; } kvm->arch.gmap->guest_handle = uvcb.guest_handle; - /* Add the notifier only once. No races because we hold kvm->lock */ - if (kvm->arch.pv.mmu_notifier.ops != &kvm_s390_pv_mmu_notifier_ops) { - kvm->arch.pv.mmu_notifier.ops = &kvm_s390_pv_mmu_notifier_ops; - mmu_notifier_register(&kvm->arch.pv.mmu_notifier, kvm->mm); - } return 0; } diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index ad8d78fb1d9a..de7867ae220d 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -1250,10 +1250,12 @@ static int virtio_uml_probe(struct platform_device *pdev) device_set_wakeup_capable(&vu_dev->vdev.dev, true); rc = register_virtio_device(&vu_dev->vdev); - if (rc) + if (rc) { put_device(&vu_dev->vdev.dev); + return rc; + } vu_dev->registered = 1; - return rc; + return 0; error_init: os_close_file(vu_dev->sock); diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c index 617886d1fb1e..21f0e50fb1df 100644 --- a/arch/um/os-Linux/file.c +++ b/arch/um/os-Linux/file.c @@ -535,7 +535,7 @@ ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds, cmsg->cmsg_type != SCM_RIGHTS) return n; - memcpy(fds, CMSG_DATA(cmsg), cmsg->cmsg_len); + memcpy(fds, CMSG_DATA(cmsg), cmsg->cmsg_len - CMSG_LEN(0)); return n; } diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c index 4193e04d7e4a..e3ad71a0d13c 100644 --- a/arch/um/os-Linux/util.c +++ b/arch/um/os-Linux/util.c @@ -20,8 +20,7 @@ void stack_protections(unsigned long address) { - if (mprotect((void *) address, UM_THREAD_SIZE, - PROT_READ | PROT_WRITE | PROT_EXEC) < 0) + if (mprotect((void *) address, UM_THREAD_SIZE, PROT_READ | PROT_WRITE) < 0) panic("protecting stack failed, errno = %d", errno); } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d9931c6c4bc6..1bfebe40854f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4046,8 +4046,7 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); u64 cr8; - if (nested_svm_virtualize_tpr(vcpu) || - kvm_vcpu_apicv_active(vcpu)) + if (nested_svm_virtualize_tpr(vcpu)) return; cr8 = kvm_get_cr8(vcpu); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 8acad3cc6e6e..f31652085adc 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1795,6 +1795,7 @@ static int write_same_filled_page(struct zram *zram, unsigned long fill, u32 index) { zram_slot_lock(zram, index); + zram_free_page(zram, index); zram_set_flag(zram, index, ZRAM_SAME); zram_set_handle(zram, index, fill); zram_slot_unlock(zram, index); @@ -1832,6 +1833,7 @@ static int write_incompressible_page(struct zram *zram, struct page *page, kunmap_local(src); zram_slot_lock(zram, index); + zram_free_page(zram, index); zram_set_flag(zram, index, ZRAM_HUGE); zram_set_handle(zram, index, handle); zram_set_obj_size(zram, index, PAGE_SIZE); @@ -1855,11 +1857,6 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index) unsigned long element; bool same_filled; - /* First, free memory allocated to this slot (if any) */ - zram_slot_lock(zram, index); - zram_free_page(zram, index); - zram_slot_unlock(zram, index); - mem = kmap_local_page(page); same_filled = page_same_filled(mem, &element); kunmap_local(mem); @@ -1901,6 +1898,7 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index) zcomp_stream_put(zstrm); zram_slot_lock(zram, index); + zram_free_page(zram, index); zram_set_handle(zram, index, handle); zram_set_obj_size(zram, index, comp_len); zram_slot_unlock(zram, index); diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 036f21cac0a9..0a852011653c 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -211,8 +211,8 @@ static int dpll_msg_add_clock_quality_level(struct sk_buff *msg, struct dpll_device *dpll, struct netlink_ext_ack *extack) { + DECLARE_BITMAP(qls, DPLL_CLOCK_QUALITY_LEVEL_MAX + 1) = { 0 }; const struct dpll_device_ops *ops = dpll_device_ops(dpll); - DECLARE_BITMAP(qls, DPLL_CLOCK_QUALITY_LEVEL_MAX) = { 0 }; enum dpll_clock_quality_level ql; int ret; @@ -221,7 +221,7 @@ dpll_msg_add_clock_quality_level(struct sk_buff *msg, struct dpll_device *dpll, ret = ops->clock_quality_level_get(dpll, dpll_priv(dpll), qls, extack); if (ret) return ret; - for_each_set_bit(ql, qls, DPLL_CLOCK_QUALITY_LEVEL_MAX) + for_each_set_bit(ql, qls, DPLL_CLOCK_QUALITY_LEVEL_MAX + 1) if (nla_put_u32(msg, DPLL_A_CLOCK_QUALITY_LEVEL, ql)) return -EMSGSIZE; diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index efeee0a873c0..ab96b692e5a3 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -133,7 +133,7 @@ struct journal_sector { commit_id_t commit_id; }; -#define MAX_TAG_SIZE (JOURNAL_SECTOR_DATA - JOURNAL_MAC_PER_SECTOR - offsetof(struct journal_entry, last_bytes[MAX_SECTORS_PER_BLOCK])) +#define MAX_TAG_SIZE 255 #define METADATA_PADDING_SECTORS 8 diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 79ea85d18e24..f4b904e24328 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3813,8 +3813,10 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits) struct raid_set *rs = ti->private; unsigned int chunk_size_bytes = to_bytes(rs->md.chunk_sectors); - limits->io_min = chunk_size_bytes; - limits->io_opt = chunk_size_bytes * mddev_data_stripes(rs); + if (chunk_size_bytes) { + limits->io_min = chunk_size_bytes; + limits->io_opt = chunk_size_bytes * mddev_data_stripes(rs); + } } static void raid_presuspend(struct dm_target *ti) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 58902091bf79..1461dc740dae 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -456,11 +456,15 @@ static void stripe_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct stripe_c *sc = ti->private; - unsigned int chunk_size = sc->chunk_size << SECTOR_SHIFT; + unsigned int io_min, io_opt; limits->chunk_sectors = sc->chunk_size; - limits->io_min = chunk_size; - limits->io_opt = chunk_size * sc->stripes; + + if (!check_shl_overflow(sc->chunk_size, SECTOR_SHIFT, &io_min) && + !check_mul_overflow(io_min, sc->stripes, &io_opt)) { + limits->io_min = io_min; + limits->io_opt = io_opt; + } } static struct target_type stripe_target = { diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 257333c88710..57be04f6cb11 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2132,6 +2132,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, memcpy(ss.__data, bond_dev->dev_addr, bond_dev->addr_len); } else if (bond->params.fail_over_mac == BOND_FOM_FOLLOW && BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && + bond_has_slaves(bond) && memcmp(slave_dev->dev_addr, bond_dev->dev_addr, bond_dev->addr_len) == 0) { /* Set slave to random address to avoid duplicate mac * address in later fail over. @@ -3355,7 +3356,6 @@ static void bond_ns_send_all(struct bonding *bond, struct slave *slave) /* Find out through which dev should the packet go */ memset(&fl6, 0, sizeof(struct flowi6)); fl6.daddr = targets[i]; - fl6.flowi6_oif = bond->dev->ifindex; dst = ip6_route_output(dev_net(bond->dev), NULL, &fl6); if (dst->error) { diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index a9040c42d2ff..6e97a5a7daaf 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -4230,8 +4230,7 @@ static void cnic_cm_stop_bnx2x_hw(struct cnic_dev *dev) cnic_bnx2x_delete_wait(dev, 0); - cancel_delayed_work(&cp->delete_task); - flush_workqueue(cnic_wq); + cancel_delayed_work_sync(&cp->delete_task); if (atomic_read(&cp->iscsi_conn) != 0) netdev_warn(dev->netdev, "%d iSCSI connections not destroyed\n", diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c index de8a6ce86ad7..12105ffb5dac 100644 --- a/drivers/net/ethernet/cavium/liquidio/request_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c @@ -126,7 +126,7 @@ int octeon_init_instr_queue(struct octeon_device *oct, oct->io_qmask.iq |= BIT_ULL(iq_no); /* Set the 32B/64B mode for each input queue */ - oct->io_qmask.iq64B |= ((conf->instr_type == 64) << iq_no); + oct->io_qmask.iq64B |= ((u64)(conf->instr_type == 64) << iq_no); iq->iqcmd_64B = (conf->instr_type == 64); oct->fn_list.setup_iq_regs(oct, iq_no); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 4643a3380618..b1e1ad9e4b48 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -2736,7 +2736,7 @@ static int dpaa2_switch_setup_dpbp(struct ethsw_core *ethsw) dev_err(dev, "dpsw_ctrl_if_set_pools() failed\n"); goto err_get_attr; } - ethsw->bpid = dpbp_attrs.id; + ethsw->bpid = dpbp_attrs.bpid; return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 048c33039130..b194eae03208 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -948,9 +948,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, if (!eop_desc) break; - /* prevent any other reads prior to eop_desc */ - smp_rmb(); - i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); /* we have caught up to head, no work left to do */ if (tx_head == tx_desc) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index d2871757ec94..41e7e29879a3 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -894,10 +894,6 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page, rx_buf->page_offset, size); sinfo->xdp_frags_size += size; - /* remember frag count before XDP prog execution; bpf_xdp_adjust_tail() - * can pop off frags but driver has to handle it on its own - */ - rx_ring->nr_frags = sinfo->nr_frags; if (page_is_pfmemalloc(rx_buf->page)) xdp_buff_set_frag_pfmemalloc(xdp); @@ -968,20 +964,20 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, /** * ice_get_pgcnts - grab page_count() for gathered fragments * @rx_ring: Rx descriptor ring to store the page counts on + * @ntc: the next to clean element (not included in this frame!) * * This function is intended to be called right before running XDP * program so that the page recycling mechanism will be able to take * a correct decision regarding underlying pages; this is done in such * way as XDP program can change the refcount of page */ -static void ice_get_pgcnts(struct ice_rx_ring *rx_ring) +static void ice_get_pgcnts(struct ice_rx_ring *rx_ring, unsigned int ntc) { - u32 nr_frags = rx_ring->nr_frags + 1; u32 idx = rx_ring->first_desc; struct ice_rx_buf *rx_buf; u32 cnt = rx_ring->count; - for (int i = 0; i < nr_frags; i++) { + while (idx != ntc) { rx_buf = &rx_ring->rx_buf[idx]; rx_buf->pgcnt = page_count(rx_buf->page); @@ -1154,62 +1150,51 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf) } /** - * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags + * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all buffers in frame * @rx_ring: Rx ring with all the auxiliary data * @xdp: XDP buffer carrying linear + frags part - * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage - * @ntc: a current next_to_clean value to be stored at rx_ring + * @ntc: the next to clean element (not included in this frame!) * @verdict: return code from XDP program execution * - * Walk through gathered fragments and satisfy internal page - * recycle mechanism; we take here an action related to verdict - * returned by XDP program; + * Called after XDP program is completed, or on error with verdict set to + * ICE_XDP_CONSUMED. + * + * Walk through buffers from first_desc to the end of the frame, releasing + * buffers and satisfying internal page recycle mechanism. The action depends + * on verdict from XDP program. */ static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, - u32 *xdp_xmit, u32 ntc, u32 verdict) + u32 ntc, u32 verdict) { - u32 nr_frags = rx_ring->nr_frags + 1; u32 idx = rx_ring->first_desc; u32 cnt = rx_ring->count; - u32 post_xdp_frags = 1; struct ice_rx_buf *buf; - int i; + u32 xdp_frags = 0; + int i = 0; if (unlikely(xdp_buff_has_frags(xdp))) - post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags; + xdp_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags; - for (i = 0; i < post_xdp_frags; i++) { + while (idx != ntc) { buf = &rx_ring->rx_buf[idx]; + if (++idx == cnt) + idx = 0; - if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) { + /* An XDP program could release fragments from the end of the + * buffer. For these, we need to keep the pagecnt_bias as-is. + * To do this, only adjust pagecnt_bias for fragments up to + * the total remaining after the XDP program has run. + */ + if (verdict != ICE_XDP_CONSUMED) ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - *xdp_xmit |= verdict; - } else if (verdict & ICE_XDP_CONSUMED) { + else if (i++ <= xdp_frags) buf->pagecnt_bias++; - } else if (verdict == ICE_XDP_PASS) { - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - } ice_put_rx_buf(rx_ring, buf); - - if (++idx == cnt) - idx = 0; - } - /* handle buffers that represented frags released by XDP prog; - * for these we keep pagecnt_bias as-is; refcount from struct page - * has been decremented within XDP prog and we do not have to increase - * the biased refcnt - */ - for (; i < nr_frags; i++) { - buf = &rx_ring->rx_buf[idx]; - ice_put_rx_buf(rx_ring, buf); - if (++idx == cnt) - idx = 0; } xdp->data = NULL; rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; } /** @@ -1317,6 +1302,10 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) /* retrieve a buffer from the ring */ rx_buf = ice_get_rx_buf(rx_ring, size, ntc); + /* Increment ntc before calls to ice_put_rx_mbuf() */ + if (++ntc == cnt) + ntc = 0; + if (!xdp->data) { void *hard_start; @@ -1325,24 +1314,23 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); xdp_buff_clear_frags_flag(xdp); } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { - ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED); + ice_put_rx_mbuf(rx_ring, xdp, ntc, ICE_XDP_CONSUMED); break; } - if (++ntc == cnt) - ntc = 0; /* skip if it is NOP desc */ if (ice_is_non_eop(rx_ring, rx_desc)) continue; - ice_get_pgcnts(rx_ring); + ice_get_pgcnts(rx_ring, ntc); xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc); if (xdp_verdict == ICE_XDP_PASS) goto construct_skb; total_rx_bytes += xdp_get_buff_len(xdp); total_rx_pkts++; - ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict); + ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict); + xdp_xmit |= xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR); continue; construct_skb: @@ -1355,7 +1343,7 @@ construct_skb: rx_ring->ring_stats->rx_stats.alloc_buf_failed++; xdp_verdict = ICE_XDP_CONSUMED; } - ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict); + ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict); if (!skb) break; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index fef750c5f288..2fd8e78178a2 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -358,7 +358,6 @@ struct ice_rx_ring { struct ice_tx_ring *xdp_ring; struct ice_rx_ring *next; /* pointer to next ring in q_vector */ struct xsk_buff_pool *xsk_pool; - u32 nr_frags; u16 max_frame; u16 rx_buf_len; dma_addr_t dma; /* physical address of ring */ diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 266bfcf2a28f..a427f05814c1 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -345,6 +345,7 @@ struct igc_adapter { /* LEDs */ struct mutex led_mutex; struct igc_led_classdev *leds; + bool leds_available; }; void igc_up(struct igc_adapter *adapter); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index e79b14d50b24..728d7ca5338b 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -7335,8 +7335,14 @@ static int igc_probe(struct pci_dev *pdev, if (IS_ENABLED(CONFIG_IGC_LEDS)) { err = igc_led_setup(adapter); - if (err) - goto err_register; + if (err) { + netdev_warn_once(netdev, + "LED init failed (%d); continuing without LED support\n", + err); + adapter->leds_available = false; + } else { + adapter->leds_available = true; + } } return 0; @@ -7392,7 +7398,7 @@ static void igc_remove(struct pci_dev *pdev) cancel_work_sync(&adapter->watchdog_task); hrtimer_cancel(&adapter->hrtimer); - if (IS_ENABLED(CONFIG_IGC_LEDS)) + if (IS_ENABLED(CONFIG_IGC_LEDS) && adapter->leds_available) igc_led_free(adapter); /* Release control of h/w to f/w. If f/w is AMT enabled, this diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 80e6a2ef1350..6218bdb7f941 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6973,6 +6973,13 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, break; } + /* Make sure the SWFW semaphore is in a valid state */ + if (hw->mac.ops.init_swfw_sync) + hw->mac.ops.init_swfw_sync(hw); + + if (hw->mac.type == ixgbe_mac_e610) + mutex_init(&hw->aci.lock); + #ifdef IXGBE_FCOE /* FCoE support exists, always init the FCoE lock */ spin_lock_init(&adapter->fcoe.lock); @@ -11643,10 +11650,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_sw_init; - /* Make sure the SWFW semaphore is in a valid state */ - if (hw->mac.ops.init_swfw_sync) - hw->mac.ops.init_swfw_sync(hw); - if (ixgbe_check_fw_error(adapter)) return ixgbe_recovery_probe(adapter); @@ -11850,8 +11853,6 @@ skip_sriov: ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); ixgbe_mac_set_default_filter(adapter); - if (hw->mac.type == ixgbe_mac_e610) - mutex_init(&hw->aci.lock); timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); if (ixgbe_removed(hw->hw_addr)) { @@ -12007,9 +12008,9 @@ err_register: devl_unlock(adapter->devlink); ixgbe_release_hw_control(adapter); ixgbe_clear_interrupt_scheme(adapter); +err_sw_init: if (hw->mac.type == ixgbe_mac_e610) mutex_destroy(&adapter->hw.aci.lock); -err_sw_init: ixgbe_disable_sriov(adapter); adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP; iounmap(adapter->io_addr); @@ -12060,10 +12061,8 @@ static void ixgbe_remove(struct pci_dev *pdev) set_bit(__IXGBE_REMOVING, &adapter->state); cancel_work_sync(&adapter->service_task); - if (adapter->hw.mac.type == ixgbe_mac_e610) { + if (adapter->hw.mac.type == ixgbe_mac_e610) ixgbe_disable_link_status_events(adapter); - mutex_destroy(&adapter->hw.aci.lock); - } if (adapter->mii_bus) mdiobus_unregister(adapter->mii_bus); @@ -12123,6 +12122,9 @@ static void ixgbe_remove(struct pci_dev *pdev) disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); + if (adapter->hw.mac.type == ixgbe_mac_e610) + mutex_destroy(&adapter->hw.aci.lock); + if (disable_dev) pci_disable_device(pdev); } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 24499bb36c00..bcea3fc26a8c 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -1124,11 +1124,24 @@ static int octep_set_features(struct net_device *dev, netdev_features_t features return err; } +static bool octep_is_vf_valid(struct octep_device *oct, int vf) +{ + if (vf >= CFG_GET_ACTIVE_VFS(oct->conf)) { + netdev_err(oct->netdev, "Invalid VF ID %d\n", vf); + return false; + } + + return true; +} + static int octep_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi) { struct octep_device *oct = netdev_priv(dev); + if (!octep_is_vf_valid(oct, vf)) + return -EINVAL; + ivi->vf = vf; ether_addr_copy(ivi->mac, oct->vf_info[vf].mac_addr); ivi->spoofchk = true; @@ -1143,6 +1156,9 @@ static int octep_set_vf_mac(struct net_device *dev, int vf, u8 *mac) struct octep_device *oct = netdev_priv(dev); int err; + if (!octep_is_vf_valid(oct, vf)) + return -EINVAL; + if (!is_valid_ether_addr(mac)) { dev_err(&oct->pdev->dev, "Invalid MAC Address %pM\n", mac); return -EADDRNOTAVAIL; diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c index ebecdd29f3bd..0867fab61b19 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c @@ -196,6 +196,7 @@ static void octep_pfvf_get_mac_addr(struct octep_device *oct, u32 vf_id, vf_id); return; } + ether_addr_copy(oct->vf_info[vf_id].mac_addr, rsp->s_set_mac.mac_addr); rsp->s_set_mac.type = OCTEP_PFVF_MBOX_TYPE_RSP_ACK; } @@ -205,6 +206,8 @@ static void octep_pfvf_dev_remove(struct octep_device *oct, u32 vf_id, { int err; + /* Reset VF-specific information maintained by the PF */ + memset(&oct->vf_info[vf_id], 0, sizeof(struct octep_pfvf_info)); err = octep_ctrl_net_dev_remove(oct, vf_id); if (err) { rsp->s.type = OCTEP_PFVF_MBOX_TYPE_RSP_NACK; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c index e52cc6b1a26c..dedd586ed310 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c @@ -491,7 +491,7 @@ void otx2_ptp_destroy(struct otx2_nic *pfvf) if (!ptp) return; - cancel_delayed_work(&pfvf->ptp->synctstamp_work); + cancel_delayed_work_sync(&pfvf->ptp->synctstamp_work); ptp_clock_unregister(ptp->ptp_clock); kfree(ptp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 9560fcba643f..ac65e3191480 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -92,6 +92,7 @@ enum { MLX5E_ACCEL_FS_ESP_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1, MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL, MLX5E_ACCEL_FS_POL_FT_LEVEL, + MLX5E_ACCEL_FS_POL_MISS_FT_LEVEL, MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL, #endif }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index ffcd0cdeb775..23703f28386a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -185,6 +185,7 @@ struct mlx5e_ipsec_rx_create_attr { u32 family; int prio; int pol_level; + int pol_miss_level; int sa_level; int status_level; enum mlx5_flow_namespace_type chains_ns; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 98b6a3a623f9..65dc3529283b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -747,6 +747,7 @@ static void ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, attr->family = family; attr->prio = MLX5E_NIC_PRIO; attr->pol_level = MLX5E_ACCEL_FS_POL_FT_LEVEL; + attr->pol_miss_level = MLX5E_ACCEL_FS_POL_MISS_FT_LEVEL; attr->sa_level = MLX5E_ACCEL_FS_ESP_FT_LEVEL; attr->status_level = MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL; attr->chains_ns = MLX5_FLOW_NAMESPACE_KERNEL; @@ -833,7 +834,7 @@ static int ipsec_rx_chains_create_miss(struct mlx5e_ipsec *ipsec, ft_attr.max_fte = 1; ft_attr.autogroup.max_num_groups = 1; - ft_attr.level = attr->pol_level; + ft_attr.level = attr->pol_miss_level; ft_attr.prio = attr->prio; ft = mlx5_create_auto_grouped_flow_table(attr->ns, &ft_attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e680673ffb72..15eded36b872 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -139,8 +139,6 @@ void mlx5e_update_carrier(struct mlx5e_priv *priv) if (up) { netdev_info(priv->netdev, "Link up\n"); netif_carrier_on(priv->netdev); - mlx5e_port_manual_buffer_config(priv, 0, priv->netdev->mtu, - NULL, NULL, NULL); } else { netdev_info(priv->netdev, "Link down\n"); netif_carrier_off(priv->netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 63a7a788fb0d..cd0242eb008c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1506,12 +1506,21 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = { static int mlx5e_vport_uplink_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) { - struct mlx5e_priv *priv = netdev_priv(mlx5_uplink_netdev_get(dev)); struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); + struct net_device *netdev; + struct mlx5e_priv *priv; + int err; + + netdev = mlx5_uplink_netdev_get(dev); + if (!netdev) + return 0; + priv = netdev_priv(netdev); rpriv->netdev = priv->netdev; - return mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, - rpriv); + err = mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, + rpriv); + mlx5_uplink_netdev_put(dev, netdev); + return err; } static void @@ -1638,8 +1647,16 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) { struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); struct net_device *netdev = rpriv->netdev; - struct mlx5e_priv *priv = netdev_priv(netdev); - void *ppriv = priv->ppriv; + struct mlx5e_priv *priv; + void *ppriv; + + if (!netdev) { + ppriv = rpriv; + goto free_ppriv; + } + + priv = netdev_priv(netdev); + ppriv = priv->ppriv; if (rep->vport == MLX5_VPORT_UPLINK) { mlx5e_vport_uplink_rep_unload(rpriv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 8b4977650183..5f2d6c35f1ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -1515,6 +1515,7 @@ static u32 mlx5_esw_qos_lag_link_speed_get_locked(struct mlx5_core_dev *mdev) speed = lksettings.base.speed; out: + mlx5_uplink_netdev_put(mdev, slave); return speed; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index cb165085a4c1..db552c012b4f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -114,9 +114,9 @@ #define ETHTOOL_NUM_PRIOS 11 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS) /* Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy, - * {IPsec RoCE MPV,Alias table},IPsec RoCE policy + * IPsec policy miss, {IPsec RoCE MPV,Alias table},IPsec RoCE policy */ -#define KERNEL_NIC_PRIO_NUM_LEVELS 10 +#define KERNEL_NIC_PRIO_NUM_LEVELS 11 #define KERNEL_NIC_NUM_PRIOS 1 /* One more level for tc, and one more for promisc */ #define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 2) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index b111ccd03b02..74ea5da58b7e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -47,7 +47,20 @@ int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data); static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *mdev) { - return mdev->mlx5e_res.uplink_netdev; + struct mlx5e_resources *mlx5e_res = &mdev->mlx5e_res; + struct net_device *netdev; + + mutex_lock(&mlx5e_res->uplink_netdev_lock); + netdev = mlx5e_res->uplink_netdev; + netdev_hold(netdev, &mlx5e_res->tracker, GFP_KERNEL); + mutex_unlock(&mlx5e_res->uplink_netdev_lock); + return netdev; +} + +static inline void mlx5_uplink_netdev_put(struct mlx5_core_dev *mdev, + struct net_device *netdev) +{ + netdev_put(netdev, &mdev->mlx5e_res.tracker); } struct mlx5_sd; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 2d7adf7444ba..aa9f2b0a77d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -1170,7 +1170,11 @@ const struct mlx5_link_info *mlx5_port_ptys2info(struct mlx5_core_dev *mdev, mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size, force_legacy); i = find_first_bit(&temp, max_size); - if (i < max_size) + + /* mlx5e_link_info has holes. Check speed + * is not zero as indication of one. + */ + if (i < max_size && table[i].speed) return &table[i]; return NULL; diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c index 56d5464222d9..cdbf82affa7b 100644 --- a/drivers/net/ethernet/natsemi/ns83820.c +++ b/drivers/net/ethernet/natsemi/ns83820.c @@ -820,7 +820,7 @@ static void rx_irq(struct net_device *ndev) struct ns83820 *dev = PRIV(ndev); struct rx_info *info = &dev->rx_info; unsigned next_rx; - int rx_rc, len; + int len; u32 cmdsts; __le32 *desc; unsigned long flags; @@ -881,8 +881,10 @@ static void rx_irq(struct net_device *ndev) if (likely(CMDSTS_OK & cmdsts)) { #endif skb_put(skb, len); - if (unlikely(!skb)) + if (unlikely(!skb)) { + ndev->stats.rx_dropped++; goto netdev_mangle_me_harder_failed; + } if (cmdsts & CMDSTS_DEST_MULTI) ndev->stats.multicast++; ndev->stats.rx_packets++; @@ -901,15 +903,12 @@ static void rx_irq(struct net_device *ndev) __vlan_hwaccel_put_tag(skb, htons(ETH_P_IPV6), tag); } #endif - rx_rc = netif_rx(skb); - if (NET_RX_DROP == rx_rc) { -netdev_mangle_me_harder_failed: - ndev->stats.rx_dropped++; - } + netif_rx(skb); } else { dev_kfree_skb_irq(skb); } +netdev_mangle_me_harder_failed: nr++; next_rx = info->next_rx; desc = info->descs + (DESC_SIZE * next_rx); diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 9c3d3dd2f847..1f0cea3cae92 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -4462,10 +4462,11 @@ static enum dbg_status qed_protection_override_dump(struct qed_hwfn *p_hwfn, goto out; } - /* Add override window info to buffer */ + /* Add override window info to buffer, preventing buffer overflow */ override_window_dwords = - qed_rd(p_hwfn, p_ptt, GRC_REG_NUMBER_VALID_OVERRIDE_WINDOW) * - PROTECTION_OVERRIDE_ELEMENT_DWORDS; + min(qed_rd(p_hwfn, p_ptt, GRC_REG_NUMBER_VALID_OVERRIDE_WINDOW) * + PROTECTION_OVERRIDE_ELEMENT_DWORDS, + PROTECTION_OVERRIDE_DEPTH_DWORDS); if (override_window_dwords) { addr = BYTES_TO_DWORDS(GRC_REG_PROTECTION_OVERRIDE_WINDOW); offset += qed_grc_dump_addr_range(p_hwfn, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c index d912e709a92c..bb03dad4a300 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c @@ -2092,7 +2092,7 @@ static void iwl_txq_gen1_update_byte_cnt_tbl(struct iwl_trans *trans, break; } - if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_9000 && + if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_7000 && trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210) len = DIV_ROUND_UP(len, 4); diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index 18fb44139de2..4d0a38e06f08 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -239,6 +239,14 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_BOARD_NAME, "WUJIE14-GX4HRXL"), } }, + { + .ident = "MECHREVO Yilong15Pro Series GM5HG7A", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MECHREVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "Yilong15Pro Series GM5HG7A"), + } + }, /* https://bugzilla.kernel.org/show_bug.cgi?id=220116 */ { .ident = "PCSpecialist Lafite Pro V 14M", diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index ef988605c4da..bc544a4a5266 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -403,6 +403,7 @@ static const struct acpi_device_id amd_pmf_acpi_ids[] = { {"AMDI0103", 0}, {"AMDI0105", 0}, {"AMDI0107", 0}, + {"AMDI0108", 0}, { } }; MODULE_DEVICE_TABLE(acpi, amd_pmf_acpi_ids); diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 3a488cf9ca06..6a62bc5b02fd 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -673,6 +673,8 @@ static void asus_nb_wmi_key_filter(struct asus_wmi_driver *asus_wmi, int *code, if (atkbd_reports_vol_keys) *code = ASUS_WMI_KEY_IGNORE; break; + case 0x5D: /* Wireless console Toggle */ + case 0x5E: /* Wireless console Enable / Keyboard Attach, Detach */ case 0x5F: /* Wireless console Disable / Special Key */ if (quirks->key_wlan_event) *code = quirks->key_wlan_event; diff --git a/drivers/platform/x86/oxpec.c b/drivers/platform/x86/oxpec.c index eb076bb4099b..54377b282ff8 100644 --- a/drivers/platform/x86/oxpec.c +++ b/drivers/platform/x86/oxpec.c @@ -126,6 +126,13 @@ static const struct dmi_system_id dmi_table[] = { }, { .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AOKZOE"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "AOKZOE A1X"), + }, + .driver_data = (void *)oxp_fly, + }, + { + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "AYANEO"), DMI_MATCH(DMI_BOARD_NAME, "AYANEO 2"), }, @@ -306,6 +313,13 @@ static const struct dmi_system_id dmi_table[] = { }, .driver_data = (void *)oxp_x1, }, + { + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ONE-NETBOOK"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "ONEXPLAYER X1Pro EVA-02"), + }, + .driver_data = (void *)oxp_x1, + }, {}, }; diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 93dcebbe1141..ad2d9ecf32a5 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1919,8 +1919,8 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); - if ((cache.flags & 0xff) == 0xff) - cache.flags = -1; /* read error */ + if (di->chip == BQ27000 && (cache.flags & 0xff) == 0xff) + cache.flags = -ENODEV; /* bq27000 hdq read error */ if (cache.flags >= 0) { cache.capacity = bq27xxx_battery_read_soc(di); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 9bf282d2453c..499a9edf0ca3 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1795,7 +1795,14 @@ static int reclaim_bgs_cmp(void *unused, const struct list_head *a, bg1 = list_entry(a, struct btrfs_block_group, bg_list); bg2 = list_entry(b, struct btrfs_block_group, bg_list); - return bg1->used > bg2->used; + /* + * Some other task may be updating the ->used field concurrently, but it + * is not serious if we get a stale value or load/store tearing issues, + * as sorting the list of block groups to reclaim is not critical and an + * occasional imperfect order is ok. So silence KCSAN and avoid the + * overhead of locking or any other synchronization. + */ + return data_race(bg1->used > bg2->used); } static inline bool btrfs_should_reclaim(const struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 0f8d8e275143..c0c1ddd46b67 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1843,7 +1843,6 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans, int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev) { - struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_delayed_node *delayed_node; struct btrfs_inode_item *inode_item; struct inode *vfs_inode = &inode->vfs_inode; @@ -1864,8 +1863,6 @@ int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev) i_uid_write(vfs_inode, btrfs_stack_inode_uid(inode_item)); i_gid_write(vfs_inode, btrfs_stack_inode_gid(inode_item)); btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item)); - btrfs_inode_set_file_extent_range(inode, 0, - round_up(i_size_read(vfs_inode), fs_info->sectorsize)); vfs_inode->i_mode = btrfs_stack_inode_mode(inode_item); set_nlink(vfs_inode, btrfs_stack_inode_nlink(inode_item)); inode_set_bytes(vfs_inode, btrfs_stack_inode_nbytes(inode_item)); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e7218e78bff4..18db1053cdf0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3885,10 +3885,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path bool filled = false; int first_xattr_slot; - ret = btrfs_init_file_extent_tree(inode); - if (ret) - goto out; - ret = btrfs_fill_inode(inode, &rdev); if (!ret) filled = true; @@ -3920,8 +3916,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path i_uid_write(vfs_inode, btrfs_inode_uid(leaf, inode_item)); i_gid_write(vfs_inode, btrfs_inode_gid(leaf, inode_item)); btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item)); - btrfs_inode_set_file_extent_range(inode, 0, - round_up(i_size_read(vfs_inode), fs_info->sectorsize)); inode_set_atime(vfs_inode, btrfs_timespec_sec(leaf, &inode_item->atime), btrfs_timespec_nsec(leaf, &inode_item->atime)); @@ -3953,6 +3947,11 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path btrfs_set_inode_mapping_order(inode); cache_index: + ret = btrfs_init_file_extent_tree(inode); + if (ret) + goto out; + btrfs_inode_set_file_extent_range(inode, 0, + round_up(i_size_read(vfs_inode), fs_info->sectorsize)); /* * If we were modified in the current generation and evicted from memory * and then re-read we need to do a full sync since we don't have any diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 7d5d90845ca9..7a63afedd01e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1964,7 +1964,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_EXTREF_KEY; - search_key.offset = key->objectid; + search_key.offset = btrfs_extref_hash(key->objectid, name.name, name.len); ret = backref_in_log(root->log_root, &search_key, key->objectid, &name); if (ret < 0) { goto out; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index ea662036f441..efc2a81f50e5 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2582,9 +2582,9 @@ again: spin_lock(&space_info->lock); space_info->total_bytes -= bg->length; space_info->disk_total -= bg->length * factor; + space_info->disk_total -= bg->zone_unusable; /* There is no allocation ever happened. */ ASSERT(bg->used == 0); - ASSERT(bg->zone_unusable == 0); /* No super block in a block group on the zoned setup. */ ASSERT(bg->bytes_super == 0); spin_unlock(&space_info->lock); diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index 14868a3dd592..bc52afbfc5c7 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -1075,7 +1075,7 @@ void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs) ************************************************************************/ static ssize_t nilfs_feature_revision_show(struct kobject *kobj, - struct attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%d.%d\n", NILFS_CURRENT_REV, NILFS_MINOR_REV); @@ -1087,7 +1087,7 @@ static const char features_readme_str[] = "(1) revision\n\tshow current revision of NILFS file system driver.\n"; static ssize_t nilfs_feature_README_show(struct kobject *kobj, - struct attribute *attr, + struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, features_readme_str); diff --git a/fs/nilfs2/sysfs.h b/fs/nilfs2/sysfs.h index 78a87a016928..d370cd5cce3f 100644 --- a/fs/nilfs2/sysfs.h +++ b/fs/nilfs2/sysfs.h @@ -50,16 +50,16 @@ struct nilfs_sysfs_dev_subgroups { struct completion sg_segments_kobj_unregister; }; -#define NILFS_COMMON_ATTR_STRUCT(name) \ +#define NILFS_KOBJ_ATTR_STRUCT(name) \ struct nilfs_##name##_attr { \ struct attribute attr; \ - ssize_t (*show)(struct kobject *, struct attribute *, \ + ssize_t (*show)(struct kobject *, struct kobj_attribute *, \ char *); \ - ssize_t (*store)(struct kobject *, struct attribute *, \ + ssize_t (*store)(struct kobject *, struct kobj_attribute *, \ const char *, size_t); \ } -NILFS_COMMON_ATTR_STRUCT(feature); +NILFS_KOBJ_ATTR_STRUCT(feature); #define NILFS_DEV_ATTR_STRUCT(name) \ struct nilfs_##name##_attr { \ diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 5466aa8c39b1..6550bd9f002c 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -554,7 +554,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) case SMB_DIRECT_MSG_DATA_TRANSFER: { struct smb_direct_data_transfer *data_transfer = (struct smb_direct_data_transfer *)recvmsg->packet; - unsigned int data_length; + u32 remaining_data_length, data_offset, data_length; int avail_recvmsg_count, receive_credits; if (wc->byte_len < @@ -564,15 +564,25 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) return; } + remaining_data_length = le32_to_cpu(data_transfer->remaining_data_length); data_length = le32_to_cpu(data_transfer->data_length); - if (data_length) { - if (wc->byte_len < sizeof(struct smb_direct_data_transfer) + - (u64)data_length) { - put_recvmsg(t, recvmsg); - smb_direct_disconnect_rdma_connection(t); - return; - } + data_offset = le32_to_cpu(data_transfer->data_offset); + if (wc->byte_len < data_offset || + wc->byte_len < (u64)data_offset + data_length) { + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); + return; + } + if (remaining_data_length > t->max_fragmented_recv_size || + data_length > t->max_fragmented_recv_size || + (u64)remaining_data_length + (u64)data_length > + (u64)t->max_fragmented_recv_size) { + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); + return; + } + if (data_length) { if (t->full_packet_received) recvmsg->first_segment = true; @@ -1209,78 +1219,130 @@ static int smb_direct_writev(struct ksmbd_transport *t, bool need_invalidate, unsigned int remote_key) { struct smb_direct_transport *st = smb_trans_direct_transfort(t); - int remaining_data_length; - int start, i, j; - int max_iov_size = st->max_send_size - + size_t remaining_data_length; + size_t iov_idx; + size_t iov_ofs; + size_t max_iov_size = st->max_send_size - sizeof(struct smb_direct_data_transfer); int ret; - struct kvec vec; struct smb_direct_send_ctx send_ctx; + int error = 0; if (st->status != SMB_DIRECT_CS_CONNECTED) return -ENOTCONN; //FIXME: skip RFC1002 header.. + if (WARN_ON_ONCE(niovs <= 1 || iov[0].iov_len != 4)) + return -EINVAL; buflen -= 4; + iov_idx = 1; + iov_ofs = 0; remaining_data_length = buflen; ksmbd_debug(RDMA, "Sending smb (RDMA): smb_len=%u\n", buflen); smb_direct_send_ctx_init(st, &send_ctx, need_invalidate, remote_key); - start = i = 1; - buflen = 0; - while (true) { - buflen += iov[i].iov_len; - if (buflen > max_iov_size) { - if (i > start) { - remaining_data_length -= - (buflen - iov[i].iov_len); - ret = smb_direct_post_send_data(st, &send_ctx, - &iov[start], i - start, - remaining_data_length); - if (ret) + while (remaining_data_length) { + struct kvec vecs[SMB_DIRECT_MAX_SEND_SGES - 1]; /* minus smbdirect hdr */ + size_t possible_bytes = max_iov_size; + size_t possible_vecs; + size_t bytes = 0; + size_t nvecs = 0; + + /* + * For the last message remaining_data_length should be + * have been 0 already! + */ + if (WARN_ON_ONCE(iov_idx >= niovs)) { + error = -EINVAL; + goto done; + } + + /* + * We have 2 factors which limit the arguments we pass + * to smb_direct_post_send_data(): + * + * 1. The number of supported sges for the send, + * while one is reserved for the smbdirect header. + * And we currently need one SGE per page. + * 2. The number of negotiated payload bytes per send. + */ + possible_vecs = min_t(size_t, ARRAY_SIZE(vecs), niovs - iov_idx); + + while (iov_idx < niovs && possible_vecs && possible_bytes) { + struct kvec *v = &vecs[nvecs]; + int page_count; + + v->iov_base = ((u8 *)iov[iov_idx].iov_base) + iov_ofs; + v->iov_len = min_t(size_t, + iov[iov_idx].iov_len - iov_ofs, + possible_bytes); + page_count = get_buf_page_count(v->iov_base, v->iov_len); + if (page_count > possible_vecs) { + /* + * If the number of pages in the buffer + * is to much (because we currently require + * one SGE per page), we need to limit the + * length. + * + * We know possible_vecs is at least 1, + * so we always keep the first page. + * + * We need to calculate the number extra + * pages (epages) we can also keep. + * + * We calculate the number of bytes in the + * first page (fplen), this should never be + * larger than v->iov_len because page_count is + * at least 2, but adding a limitation feels + * better. + * + * Then we calculate the number of bytes (elen) + * we can keep for the extra pages. + */ + size_t epages = possible_vecs - 1; + size_t fpofs = offset_in_page(v->iov_base); + size_t fplen = min_t(size_t, PAGE_SIZE - fpofs, v->iov_len); + size_t elen = min_t(size_t, v->iov_len - fplen, epages*PAGE_SIZE); + + v->iov_len = fplen + elen; + page_count = get_buf_page_count(v->iov_base, v->iov_len); + if (WARN_ON_ONCE(page_count > possible_vecs)) { + /* + * Something went wrong in the above + * logic... + */ + error = -EINVAL; goto done; - } else { - /* iov[start] is too big, break it */ - int nvec = (buflen + max_iov_size - 1) / - max_iov_size; - - for (j = 0; j < nvec; j++) { - vec.iov_base = - (char *)iov[start].iov_base + - j * max_iov_size; - vec.iov_len = - min_t(int, max_iov_size, - buflen - max_iov_size * j); - remaining_data_length -= vec.iov_len; - ret = smb_direct_post_send_data(st, &send_ctx, &vec, 1, - remaining_data_length); - if (ret) - goto done; } - i++; - if (i == niovs) - break; } - start = i; - buflen = 0; - } else { - i++; - if (i == niovs) { - /* send out all remaining vecs */ - remaining_data_length -= buflen; - ret = smb_direct_post_send_data(st, &send_ctx, - &iov[start], i - start, - remaining_data_length); - if (ret) - goto done; - break; + possible_vecs -= page_count; + nvecs += 1; + possible_bytes -= v->iov_len; + bytes += v->iov_len; + + iov_ofs += v->iov_len; + if (iov_ofs >= iov[iov_idx].iov_len) { + iov_idx += 1; + iov_ofs = 0; } } + + remaining_data_length -= bytes; + + ret = smb_direct_post_send_data(st, &send_ctx, + vecs, nvecs, + remaining_data_length); + if (unlikely(ret)) { + error = ret; + goto done; + } } done: ret = smb_direct_flush_send_list(st, &send_ctx, true); + if (unlikely(!ret && error)) + ret = error; /* * As an optimization, we don't wait for individual I/O to finish @@ -1744,6 +1806,11 @@ static int smb_direct_init_params(struct smb_direct_transport *t, return -EINVAL; } + if (device->attrs.max_send_sge < SMB_DIRECT_MAX_SEND_SGES) { + pr_err("warning: device max_send_sge = %d too small\n", + device->attrs.max_send_sge); + return -EINVAL; + } if (device->attrs.max_recv_sge < SMB_DIRECT_MAX_RECV_SGES) { pr_err("warning: device max_recv_sge = %d too small\n", device->attrs.max_recv_sge); @@ -1767,7 +1834,7 @@ static int smb_direct_init_params(struct smb_direct_transport *t, cap->max_send_wr = max_send_wrs; cap->max_recv_wr = t->recv_credit_max; - cap->max_send_sge = max_sge_per_wr; + cap->max_send_sge = SMB_DIRECT_MAX_SEND_SGES; cap->max_recv_sge = SMB_DIRECT_MAX_RECV_SGES; cap->max_inline_data = 0; cap->max_rdma_ctxs = t->max_rw_credits; diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 404883c7af6e..4000ff16f295 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -8,8 +8,8 @@ #include <linux/bits.h> #include <linux/kvm.h> #include <linux/irqreturn.h> -#include <linux/kref.h> #include <linux/mutex.h> +#include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/static_key.h> #include <linux/types.h> @@ -139,10 +139,13 @@ struct vgic_irq { bool pending_latch; /* The pending latch state used to calculate * the pending state for both level * and edge triggered IRQs. */ - bool active; /* not used for LPIs */ + bool active; + bool pending_release; /* Used for LPIs only, unreferenced IRQ + * pending a release */ + bool enabled; bool hw; /* Tied to HW IRQ */ - struct kref refcount; /* Used for LPIs */ + refcount_t refcount; /* Used for LPIs */ u32 hwintid; /* HW INTID number */ unsigned int host_irq; /* linux irq corresponding to hwintid */ union { diff --git a/include/linux/damon.h b/include/linux/damon.h index f13664c62ddd..9e62b2a85538 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -636,6 +636,7 @@ struct damon_operations { * @data: Data that will be passed to @fn. * @repeat: Repeat invocations. * @return_code: Return code from @fn invocation. + * @dealloc_on_cancel: De-allocate when canceled. * * Control damon_call(), which requests specific kdamond to invoke a given * function. Refer to damon_call() for more details. @@ -645,6 +646,7 @@ struct damon_call_control { void *data; bool repeat; int return_code; + bool dealloc_on_cancel; /* private: internal use only */ /* informs if the kdamond finished handling of the request */ struct completion completion; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8c5fbfb85749..10fe492e1fed 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -663,6 +663,7 @@ struct mlx5e_resources { bool tisn_valid; } hw_objs; struct net_device *uplink_netdev; + netdevice_tracker tracker; struct mutex uplink_netdev_lock; struct mlx5_crypto_dek_priv *dek_priv; }; diff --git a/include/linux/rv.h b/include/linux/rv.h index 14410a42faef..9520aab34bcb 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -7,16 +7,14 @@ #ifndef _LINUX_RV_H #define _LINUX_RV_H -#include <linux/types.h> -#include <linux/list.h> - #define MAX_DA_NAME_LEN 32 #define MAX_DA_RETRY_RACING_EVENTS 3 #ifdef CONFIG_RV +#include <linux/array_size.h> #include <linux/bitops.h> +#include <linux/list.h> #include <linux/types.h> -#include <linux/array_size.h> /* * Deterministic automaton per-object variables. diff --git a/include/linux/swap.h b/include/linux/swap.h index 2fe6ed2cc3fd..7012a0f758d8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -385,6 +385,16 @@ void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); +static inline bool folio_may_be_lru_cached(struct folio *folio) +{ + /* + * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting. + * Holding small numbers of low-order mTHP folios in per-CPU LRU cache + * will be sensible, but nobody has implemented and tested that yet. + */ + return !folio_test_large(folio); +} + extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 4160731dcb6e..1fc2fb03ce3f 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -3,6 +3,7 @@ #define __NET_DST_METADATA_H 1 #include <linux/skbuff.h> +#include <net/ip.h> #include <net/ip_tunnels.h> #include <net/macsec.h> #include <net/dst.h> @@ -220,9 +221,15 @@ static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, int md_size) { const struct iphdr *iph = ip_hdr(skb); + struct metadata_dst *tun_dst; + + tun_dst = __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, + 0, flags, tunnel_id, md_size); - return __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl, - 0, flags, tunnel_id, md_size); + if (tun_dst && (iph->frag_off & htons(IP_DF))) + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, + tun_dst->u.tun_info.key.tun_flags); + return tun_dst; } static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr, diff --git a/include/net/sock.h b/include/net/sock.h index fb13322a11fc..2e14283c5be1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2061,6 +2061,9 @@ static inline void sk_set_socket(struct sock *sk, struct socket *sock) if (sock) { WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid); WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino); + } else { + /* Note: sk_uid is unchanged. */ + WRITE_ONCE(sk->sk_ino, 0); } } @@ -2082,8 +2085,6 @@ static inline void sock_orphan(struct sock *sk) sock_set_flag(sk, SOCK_DEAD); sk_set_socket(sk, NULL); sk->sk_wq = NULL; - /* Note: sk_uid is unchanged. */ - WRITE_ONCE(sk->sk_ino, 0); write_unlock_bh(&sk->sk_callback_lock); } diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 67d015df8893..5fd5b4cf75ca 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -31,6 +31,8 @@ #define MPTCP_INFO_FLAG_FALLBACK _BITUL(0) #define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1) +#define MPTCP_PM_EV_FLAG_DENY_JOIN_ID0 _BITUL(0) + #define MPTCP_PM_ADDR_FLAG_SIGNAL (1 << 0) #define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1) #define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2) diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index 6ac84b2f636c..7359d34da446 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -16,10 +16,10 @@ * good time to allocate memory and send ADD_ADDR if needed. Depending on the * traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED * is sent. Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, server-side. + * sport, dport, server-side, [flags]. * @MPTCP_EVENT_ESTABLISHED: A MPTCP connection is established (can start new * subflows). Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, server-side. + * sport, dport, server-side, [flags]. * @MPTCP_EVENT_CLOSED: A MPTCP connection has stopped. Attribute: token. * @MPTCP_EVENT_ANNOUNCED: A new address has been announced by the peer. * Attributes: token, rem_id, family, daddr4 | daddr6 [, dport]. diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 312c6a8b55bb..77d02f87f3f1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -126,8 +126,31 @@ DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem); * of concurrent destructions. Use a separate workqueue so that cgroup * destruction work items don't end up filling up max_active of system_wq * which may lead to deadlock. + * + * A cgroup destruction should enqueue work sequentially to: + * cgroup_offline_wq: use for css offline work + * cgroup_release_wq: use for css release work + * cgroup_free_wq: use for free work + * + * Rationale for using separate workqueues: + * The cgroup root free work may depend on completion of other css offline + * operations. If all tasks were enqueued to a single workqueue, this could + * create a deadlock scenario where: + * - Free work waits for other css offline work to complete. + * - But other css offline work is queued after free work in the same queue. + * + * Example deadlock scenario with single workqueue (cgroup_destroy_wq): + * 1. umount net_prio + * 2. net_prio root destruction enqueues work to cgroup_destroy_wq (CPUx) + * 3. perf_event CSS A offline enqueues work to same cgroup_destroy_wq (CPUx) + * 4. net_prio cgroup_destroy_root->cgroup_lock_and_drain_offline. + * 5. net_prio root destruction blocks waiting for perf_event CSS A offline, + * which can never complete as it's behind in the same queue and + * workqueue's max_active is 1. */ -static struct workqueue_struct *cgroup_destroy_wq; +static struct workqueue_struct *cgroup_offline_wq; +static struct workqueue_struct *cgroup_release_wq; +static struct workqueue_struct *cgroup_free_wq; /* generate an array of cgroup subsystem pointers */ #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, @@ -4159,6 +4182,7 @@ static void cgroup_file_release(struct kernfs_open_file *of) cft->release(of); put_cgroup_ns(ctx->ns); kfree(ctx); + of->priv = NULL; } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, @@ -5558,7 +5582,7 @@ static void css_release_work_fn(struct work_struct *work) cgroup_unlock(); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); - queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); + queue_rcu_work(cgroup_free_wq, &css->destroy_rwork); } static void css_release(struct percpu_ref *ref) @@ -5567,7 +5591,7 @@ static void css_release(struct percpu_ref *ref) container_of(ref, struct cgroup_subsys_state, refcnt); INIT_WORK(&css->destroy_work, css_release_work_fn); - queue_work(cgroup_destroy_wq, &css->destroy_work); + queue_work(cgroup_release_wq, &css->destroy_work); } static void init_and_link_css(struct cgroup_subsys_state *css, @@ -5701,7 +5725,7 @@ err_list_del: list_del_rcu(&css->sibling); err_free_css: INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); - queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); + queue_rcu_work(cgroup_free_wq, &css->destroy_rwork); return ERR_PTR(err); } @@ -5939,7 +5963,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref) if (atomic_dec_and_test(&css->online_cnt)) { INIT_WORK(&css->destroy_work, css_killed_work_fn); - queue_work(cgroup_destroy_wq, &css->destroy_work); + queue_work(cgroup_offline_wq, &css->destroy_work); } } @@ -6325,8 +6349,14 @@ static int __init cgroup_wq_init(void) * We would prefer to do this in cgroup_init() above, but that * is called before init_workqueues(): so leave this until after. */ - cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); - BUG_ON(!cgroup_destroy_wq); + cgroup_offline_wq = alloc_workqueue("cgroup_offline", 0, 1); + BUG_ON(!cgroup_offline_wq); + + cgroup_release_wq = alloc_workqueue("cgroup_release", 0, 1); + BUG_ON(!cgroup_release_wq); + + cgroup_free_wq = alloc_workqueue("cgroup_free", 0, 1); + BUG_ON(!cgroup_free_wq); return 0; } core_initcall(cgroup_wq_init); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index be00629f0ba4..ccba6fc3c3fe 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9551,7 +9551,7 @@ static unsigned long tg_weight(struct task_group *tg) #ifdef CONFIG_FAIR_GROUP_SCHED return scale_load_down(tg->shares); #else - return sched_weight_from_cgroup(tg->scx_weight); + return sched_weight_from_cgroup(tg->scx.weight); #endif } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 4ae32ef179dd..088ceff38c8a 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -6788,12 +6788,8 @@ __bpf_kfunc u32 scx_bpf_reenqueue_local(void) * CPUs disagree, they use %ENQUEUE_RESTORE which is bypassed to * the current local DSQ for running tasks and thus are not * visible to the BPF scheduler. - * - * Also skip re-enqueueing tasks that can only run on this - * CPU, as they would just be re-added to the same local - * DSQ without any benefit. */ - if (p->migration_pending || is_migration_disabled(p) || p->nr_cpus_allowed == 1) + if (p->migration_pending) continue; dispatch_dequeue(rq, p); diff --git a/kernel/trace/rv/monitors/sleep/sleep.c b/kernel/trace/rv/monitors/sleep/sleep.c index eea447b06907..c1347da69e9d 100644 --- a/kernel/trace/rv/monitors/sleep/sleep.c +++ b/kernel/trace/rv/monitors/sleep/sleep.c @@ -127,7 +127,9 @@ static void handle_sys_enter(void *data, struct pt_regs *regs, long id) mon = ltl_get_monitor(current); switch (id) { +#ifdef __NR_clock_nanosleep case __NR_clock_nanosleep: +#endif #ifdef __NR_clock_nanosleep_time64 case __NR_clock_nanosleep_time64: #endif @@ -138,7 +140,9 @@ static void handle_sys_enter(void *data, struct pt_regs *regs, long id) ltl_atom_update(current, LTL_CLOCK_NANOSLEEP, true); break; +#ifdef __NR_futex case __NR_futex: +#endif #ifdef __NR_futex_time64 case __NR_futex_time64: #endif diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 1482e91c39f4..48338520376f 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -495,7 +495,7 @@ static void *available_monitors_next(struct seq_file *m, void *p, loff_t *pos) */ static void *enabled_monitors_next(struct seq_file *m, void *p, loff_t *pos) { - struct rv_monitor *mon = p; + struct rv_monitor *mon = container_of(p, struct rv_monitor, list); (*pos)++; @@ -805,7 +805,7 @@ int rv_register_monitor(struct rv_monitor *monitor, struct rv_monitor *parent) retval = create_monitor_dir(monitor, parent); if (retval) - return retval; + goto out_unlock; /* keep children close to the parent for easier visualisation */ if (parent) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index ccae62d4fb91..fa60362a3f31 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -908,6 +908,8 @@ static int trace_kprobe_create_internal(int argc, const char *argv[], return -EINVAL; } buf = kmemdup(&argv[0][1], len + 1, GFP_KERNEL); + if (!buf) + return -ENOMEM; buf[len] = '\0'; ret = kstrtouint(buf, 0, &maxactive); if (ret || !maxactive) { diff --git a/mm/damon/core.c b/mm/damon/core.c index c2e0b469fd43..08065b363972 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -2479,10 +2479,14 @@ static void kdamond_call(struct damon_ctx *ctx, bool cancel) mutex_lock(&ctx->call_controls_lock); list_del(&control->list); mutex_unlock(&ctx->call_controls_lock); - if (!control->repeat) + if (!control->repeat) { complete(&control->completion); - else + } else if (control->canceled && control->dealloc_on_cancel) { + kfree(control); + continue; + } else { list_add(&control->list, &repeat_controls); + } } control = list_first_entry_or_null(&repeat_controls, struct damon_call_control, list); diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 7b9254cadd5f..c96c2154128f 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1534,14 +1534,10 @@ static int damon_sysfs_repeat_call_fn(void *data) return 0; } -static struct damon_call_control damon_sysfs_repeat_call_control = { - .fn = damon_sysfs_repeat_call_fn, - .repeat = true, -}; - static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond) { struct damon_ctx *ctx; + struct damon_call_control *repeat_call_control; int err; if (damon_sysfs_kdamond_running(kdamond)) @@ -1554,18 +1550,29 @@ static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond) damon_destroy_ctx(kdamond->damon_ctx); kdamond->damon_ctx = NULL; + repeat_call_control = kmalloc(sizeof(*repeat_call_control), + GFP_KERNEL); + if (!repeat_call_control) + return -ENOMEM; + ctx = damon_sysfs_build_ctx(kdamond->contexts->contexts_arr[0]); - if (IS_ERR(ctx)) + if (IS_ERR(ctx)) { + kfree(repeat_call_control); return PTR_ERR(ctx); + } err = damon_start(&ctx, 1, false); if (err) { + kfree(repeat_call_control); damon_destroy_ctx(ctx); return err; } kdamond->damon_ctx = ctx; - damon_sysfs_repeat_call_control.data = kdamond; - damon_call(ctx, &damon_sysfs_repeat_call_control); + repeat_call_control->fn = damon_sysfs_repeat_call_fn; + repeat_call_control->data = kdamond; + repeat_call_control->repeat = true; + repeat_call_control->dealloc_on_cancel = true; + damon_call(ctx, repeat_call_control); return err; } @@ -2287,8 +2287,8 @@ static unsigned long collect_longterm_unpinnable_folios( struct pages_or_folios *pofs) { unsigned long collected = 0; - bool drain_allow = true; struct folio *folio; + int drained = 0; long i = 0; for (folio = pofs_get_folio(pofs, i); folio; @@ -2307,9 +2307,17 @@ static unsigned long collect_longterm_unpinnable_folios( continue; } - if (!folio_test_lru(folio) && drain_allow) { + if (drained == 0 && folio_may_be_lru_cached(folio) && + folio_ref_count(folio) != + folio_expected_ref_count(folio) + 1) { + lru_add_drain(); + drained = 1; + } + if (drained == 1 && folio_may_be_lru_cached(folio) && + folio_ref_count(folio) != + folio_expected_ref_count(folio) + 1) { lru_add_drain_all(); - drain_allow = false; + drained = 2; } if (!folio_isolate_lru(folio)) diff --git a/mm/mlock.c b/mm/mlock.c index a1d93ad33c6d..bb0776f5ef7c 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -255,7 +255,7 @@ void mlock_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -278,7 +278,7 @@ void mlock_new_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -299,7 +299,7 @@ void munlock_folio(struct folio *folio) */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } diff --git a/mm/swap.c b/mm/swap.c index 3632dd061beb..b74ebe865dd9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -164,6 +164,10 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; + /* block memcg migration while the folio moves between lru */ + if (move_fn != lru_add && !folio_test_clear_lru(folio)) + continue; + folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); @@ -176,14 +180,10 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) } static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, - struct folio *folio, move_fn_t move_fn, - bool on_lru, bool disable_irq) + struct folio *folio, move_fn_t move_fn, bool disable_irq) { unsigned long flags; - if (on_lru && !folio_test_clear_lru(folio)) - return; - folio_get(folio); if (disable_irq) @@ -191,8 +191,8 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, else local_lock(&cpu_fbatches.lock); - if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || folio_test_large(folio) || - lru_cache_disabled()) + if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) @@ -201,13 +201,13 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, local_unlock(&cpu_fbatches.lock); } -#define folio_batch_add_and_move(folio, op, on_lru) \ - __folio_batch_add_and_move( \ - &cpu_fbatches.op, \ - folio, \ - op, \ - on_lru, \ - offsetof(struct cpu_fbatches, op) >= offsetof(struct cpu_fbatches, lock_irq) \ +#define folio_batch_add_and_move(folio, op) \ + __folio_batch_add_and_move( \ + &cpu_fbatches.op, \ + folio, \ + op, \ + offsetof(struct cpu_fbatches, op) >= \ + offsetof(struct cpu_fbatches, lock_irq) \ ) static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) @@ -231,10 +231,10 @@ static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) void folio_rotate_reclaimable(struct folio *folio) { if (folio_test_locked(folio) || folio_test_dirty(folio) || - folio_test_unevictable(folio)) + folio_test_unevictable(folio) || !folio_test_lru(folio)) return; - folio_batch_add_and_move(folio, lru_move_tail, true); + folio_batch_add_and_move(folio, lru_move_tail); } void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file, @@ -328,10 +328,11 @@ static void folio_activate_drain(int cpu) void folio_activate(struct folio *folio) { - if (folio_test_active(folio) || folio_test_unevictable(folio)) + if (folio_test_active(folio) || folio_test_unevictable(folio) || + !folio_test_lru(folio)) return; - folio_batch_add_and_move(folio, lru_activate, true); + folio_batch_add_and_move(folio, lru_activate); } #else @@ -507,7 +508,7 @@ void folio_add_lru(struct folio *folio) lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio); - folio_batch_add_and_move(folio, lru_add, false); + folio_batch_add_and_move(folio, lru_add); } EXPORT_SYMBOL(folio_add_lru); @@ -685,13 +686,13 @@ void lru_add_drain_cpu(int cpu) void deactivate_file_folio(struct folio *folio) { /* Deactivating an unevictable folio will not accelerate reclaim */ - if (folio_test_unevictable(folio)) + if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() && lru_gen_clear_refs(folio)) return; - folio_batch_add_and_move(folio, lru_deactivate_file, true); + folio_batch_add_and_move(folio, lru_deactivate_file); } /* @@ -704,13 +705,13 @@ void deactivate_file_folio(struct folio *folio) */ void folio_deactivate(struct folio *folio) { - if (folio_test_unevictable(folio)) + if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio)) return; - folio_batch_add_and_move(folio, lru_deactivate, true); + folio_batch_add_and_move(folio, lru_deactivate); } /** @@ -723,10 +724,11 @@ void folio_deactivate(struct folio *folio) void folio_mark_lazyfree(struct folio *folio) { if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || + !folio_test_lru(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; - folio_batch_add_and_move(folio, lru_lazyfree, true); + folio_batch_add_and_move(folio, lru_lazyfree); } void lru_add_drain(void) diff --git a/mm/vmscan.c b/mm/vmscan.c index a48aec8bfd92..674999999cd0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4507,7 +4507,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c } /* ineligible */ - if (!folio_test_lru(folio) || zone > sc->reclaim_idx) { + if (zone > sc->reclaim_idx) { gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); return true; diff --git a/net/core/dev.c b/net/core/dev.c index 93a25d87b86b..8d49b2198d07 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6965,7 +6965,7 @@ static void napi_stop_kthread(struct napi_struct *napi) * the kthread. */ while (true) { - if (!test_bit(NAPIF_STATE_SCHED_THREADED, &napi->state)) + if (!test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) break; msleep(20); diff --git a/net/devlink/rate.c b/net/devlink/rate.c index 110b3fa8a0b1..264fb82cba19 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -34,7 +34,7 @@ devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info) static struct devlink_rate * devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name) { - static struct devlink_rate *devlink_rate; + struct devlink_rate *devlink_rate; list_for_each_entry(devlink_rate, &devlink->rate_list, list) { if (devlink_rate_is_node(devlink_rate) && @@ -819,8 +819,8 @@ EXPORT_SYMBOL_GPL(devl_rate_leaf_destroy); */ void devl_rate_nodes_destroy(struct devlink *devlink) { - static struct devlink_rate *devlink_rate, *tmp; const struct devlink_ops *ops = devlink->ops; + struct devlink_rate *devlink_rate, *tmp; devl_assert_locked(devlink); diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 4f58648a27ad..92e6a681c797 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -905,7 +905,7 @@ int ethtool_net_get_ts_info_by_phc(struct net_device *dev, int err; if (!ops->get_ts_info) - return -ENODEV; + return -EOPNOTSUPP; /* Does ptp comes from netdev */ ethtool_init_tsinfo(info); @@ -973,7 +973,7 @@ int ethtool_get_ts_info_by_phc(struct net_device *dev, int err; err = ethtool_net_get_ts_info_by_phc(dev, info, hwprov_desc); - if (err == -ENODEV) { + if (err == -ENODEV || err == -EOPNOTSUPP) { struct phy_device *phy; phy = ethtool_phy_get_ts_info_by_phc(dev, info, hwprov_desc); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 71a956fbfc55..ad76556800f2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3327,6 +3327,7 @@ int tcp_disconnect(struct sock *sk, int flags) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; + struct request_sock *req; u32 seq; if (old_state != TCP_CLOSE) @@ -3442,6 +3443,10 @@ int tcp_disconnect(struct sock *sk, int flags) /* Clean up fastopen related fields */ + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); + if (req) + reqsk_fastopen_remove(sk, req, false); tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); tp->fastopen_client_fail = 0; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index bbb8d5f0eae7..3338b6cc85c4 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1178,7 +1178,9 @@ void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb) if (!ao) return; - WRITE_ONCE(ao->risn, tcp_hdr(skb)->seq); + /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */ + if (skb) + WRITE_ONCE(ao->risn, tcp_hdr(skb)->seq); ao->rcv_sne = 0; hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 2a8ea28442b2..1103b3341a70 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -985,13 +985,13 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, return false; } - if (mp_opt->deny_join_id0) - WRITE_ONCE(msk->pm.remote_deny_join_id0, true); - if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); set_fully_established: + if (mp_opt->deny_join_id0) + WRITE_ONCE(msk->pm.remote_deny_join_id0, true); + mptcp_data_lock((struct sock *)msk); __mptcp_subflow_fully_established(msk, subflow, mp_opt); mptcp_data_unlock((struct sock *)msk); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 50aaf259959a..ce7d42d3bd00 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -408,6 +408,7 @@ static int mptcp_event_created(struct sk_buff *skb, const struct sock *ssk) { int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)); + u16 flags = 0; if (err) return err; @@ -415,6 +416,12 @@ static int mptcp_event_created(struct sk_buff *skb, if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, READ_ONCE(msk->pm.server_side))) return -EMSGSIZE; + if (READ_ONCE(msk->pm.remote_deny_join_id0)) + flags |= MPTCP_PM_EV_FLAG_DENY_JOIN_ID0; + + if (flags && nla_put_u16(skb, MPTCP_ATTR_FLAGS, flags)) + return -EMSGSIZE; + return mptcp_event_add_subflow(skb, ssk); } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e6fd97b21e9e..5e497a83e967 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -371,6 +371,20 @@ static void mptcp_close_wake_up(struct sock *sk) sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); } +static void mptcp_shutdown_subflows(struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow; + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; + + slow = lock_sock_fast(ssk); + tcp_shutdown(ssk, SEND_SHUTDOWN); + unlock_sock_fast(ssk, slow); + } +} + /* called under the msk socket lock */ static bool mptcp_pending_data_fin_ack(struct sock *sk) { @@ -395,6 +409,7 @@ static void mptcp_check_data_fin_ack(struct sock *sk) break; case TCP_CLOSING: case TCP_LAST_ACK: + mptcp_shutdown_subflows(msk); mptcp_set_state(sk, TCP_CLOSE); break; } @@ -563,6 +578,7 @@ static bool mptcp_check_data_fin(struct sock *sk) mptcp_set_state(sk, TCP_CLOSING); break; case TCP_FIN_WAIT2: + mptcp_shutdown_subflows(msk); mptcp_set_state(sk, TCP_CLOSE); break; default: diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 3f1b62a9fe88..f31a3a79531a 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -883,6 +883,10 @@ create_child: ctx->subflow_id = 1; owner = mptcp_sk(ctx->conn); + + if (mp_opt.deny_join_id0) + WRITE_ONCE(owner->pm.remote_deny_join_id0, true); + mptcp_pm_new_connection(owner, child, 1); /* with OoO packets we can reach here without ingress diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 28c1b0022178..bd861191157b 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -133,12 +133,15 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len, &off, PAGE_SIZE); - if (unlikely(ret != ibmr->sg_dma_len)) - return ret < 0 ? ret : -EINVAL; + if (unlikely(ret != ibmr->sg_dma_len)) { + ret = ret < 0 ? ret : -EINVAL; + goto out_inc; + } - if (cmpxchg(&frmr->fr_state, - FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE) - return -EBUSY; + if (cmpxchg(&frmr->fr_state, FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE) { + ret = -EBUSY; + goto out_inc; + } atomic_inc(&ibmr->ic->i_fastreg_inuse_count); @@ -166,11 +169,10 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) /* Failure here can be because of -ENOMEM as well */ rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE); - atomic_inc(&ibmr->ic->i_fastreg_wrs); if (printk_ratelimit()) pr_warn("RDS/IB: %s returned error(%d)\n", __func__, ret); - goto out; + goto out_inc; } /* Wait for the registration to complete in order to prevent an invalid @@ -179,8 +181,10 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) */ wait_event(frmr->fr_reg_done, !frmr->fr_reg); -out: + return ret; +out_inc: + atomic_inc(&ibmr->ic->i_fastreg_wrs); return ret; } diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 41e657e97761..cf2dcec6ce5a 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -94,10 +94,10 @@ static const struct dmi_system_id rfkill_gpio_deny_table[] = { static int rfkill_gpio_probe(struct platform_device *pdev) { struct rfkill_gpio_data *rfkill; - struct gpio_desc *gpio; + const char *type_name = NULL; const char *name_property; const char *type_property; - const char *type_name; + struct gpio_desc *gpio; int ret; if (dmi_check_system(rfkill_gpio_deny_table)) diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index 1e19c605bcc8..dce5a3d8a964 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -475,7 +475,7 @@ static int rxgk_verify_packet_integrity(struct rxrpc_call *call, struct krb5_buffer metadata; unsigned int offset = sp->offset, len = sp->len; size_t data_offset = 0, data_len = len; - u32 ac; + u32 ac = 0; int ret = -ENOMEM; _enter(""); @@ -499,9 +499,10 @@ static int rxgk_verify_packet_integrity(struct rxrpc_call *call, ret = rxgk_verify_mic_skb(gk->krb5, gk->rx_Kc, &metadata, skb, &offset, &len, &ac); kfree(hdr); - if (ret == -EPROTO) { - rxrpc_abort_eproto(call, skb, ac, - rxgk_abort_1_verify_mic_eproto); + if (ret < 0) { + if (ret != -ENOMEM) + rxrpc_abort_eproto(call, skb, ac, + rxgk_abort_1_verify_mic_eproto); } else { sp->offset = offset; sp->len = len; @@ -524,15 +525,16 @@ static int rxgk_verify_packet_encrypted(struct rxrpc_call *call, struct rxgk_header hdr; unsigned int offset = sp->offset, len = sp->len; int ret; - u32 ac; + u32 ac = 0; _enter(""); ret = rxgk_decrypt_skb(gk->krb5, gk->rx_enc, skb, &offset, &len, &ac); - if (ret == -EPROTO) - rxrpc_abort_eproto(call, skb, ac, rxgk_abort_2_decrypt_eproto); - if (ret < 0) + if (ret < 0) { + if (ret != -ENOMEM) + rxrpc_abort_eproto(call, skb, ac, rxgk_abort_2_decrypt_eproto); goto error; + } if (len < sizeof(hdr)) { ret = rxrpc_abort_eproto(call, skb, RXGK_PACKETSHORT, diff --git a/net/rxrpc/rxgk_app.c b/net/rxrpc/rxgk_app.c index b94b77a1c317..30275cb5ba3e 100644 --- a/net/rxrpc/rxgk_app.c +++ b/net/rxrpc/rxgk_app.c @@ -54,6 +54,10 @@ int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, _enter(""); + if (ticket_len < 10 * sizeof(__be32)) + return rxrpc_abort_conn(conn, skb, RXGK_INCONSISTENCY, -EPROTO, + rxgk_abort_resp_short_yfs_tkt); + /* Get the session key length */ ret = skb_copy_bits(skb, ticket_offset, tmp, sizeof(tmp)); if (ret < 0) @@ -187,7 +191,7 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, struct key *server_key; unsigned int ticket_offset, ticket_len; u32 kvno, enctype; - int ret, ec; + int ret, ec = 0; struct { __be32 kvno; @@ -195,22 +199,23 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, __be32 token_len; } container; + if (token_len < sizeof(container)) + goto short_packet; + /* Decode the RXGK_TokenContainer object. This tells us which server * key we should be using. We can then fetch the key, get the secret * and set up the crypto to extract the token. */ if (skb_copy_bits(skb, token_offset, &container, sizeof(container)) < 0) - return rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO, - rxgk_abort_resp_tok_short); + goto short_packet; kvno = ntohl(container.kvno); enctype = ntohl(container.enctype); ticket_len = ntohl(container.token_len); ticket_offset = token_offset + sizeof(container); - if (xdr_round_up(ticket_len) > token_len - 3 * 4) - return rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO, - rxgk_abort_resp_tok_short); + if (xdr_round_up(ticket_len) > token_len - sizeof(container)) + goto short_packet; _debug("KVNO %u", kvno); _debug("ENC %u", enctype); @@ -236,9 +241,11 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, &ticket_offset, &ticket_len, &ec); crypto_free_aead(token_enc); token_enc = NULL; - if (ret < 0) - return rxrpc_abort_conn(conn, skb, ec, ret, - rxgk_abort_resp_tok_dec); + if (ret < 0) { + if (ret != -ENOMEM) + return rxrpc_abort_conn(conn, skb, ec, ret, + rxgk_abort_resp_tok_dec); + } ret = conn->security->default_decode_ticket(conn, skb, ticket_offset, ticket_len, _key); @@ -283,4 +290,8 @@ temporary_error: * also come out this way if the ticket decryption fails. */ return ret; + +short_packet: + return rxrpc_abort_conn(conn, skb, RXGK_PACKETSHORT, -EPROTO, + rxgk_abort_resp_tok_short); } diff --git a/net/rxrpc/rxgk_common.h b/net/rxrpc/rxgk_common.h index 7370a5655985..80164d89e19c 100644 --- a/net/rxrpc/rxgk_common.h +++ b/net/rxrpc/rxgk_common.h @@ -88,11 +88,16 @@ int rxgk_decrypt_skb(const struct krb5_enctype *krb5, *_offset += offset; *_len = len; break; + case -EBADMSG: /* Checksum mismatch. */ case -EPROTO: - case -EBADMSG: *_error_code = RXGK_SEALEDINCON; break; + case -EMSGSIZE: + *_error_code = RXGK_PACKETSHORT; + break; + case -ENOPKG: /* Would prefer RXGK_BADETYPE, but not available for YFS. */ default: + *_error_code = RXGK_INCONSISTENCY; break; } @@ -127,11 +132,16 @@ int rxgk_verify_mic_skb(const struct krb5_enctype *krb5, *_offset += offset; *_len = len; break; + case -EBADMSG: /* Checksum mismatch */ case -EPROTO: - case -EBADMSG: *_error_code = RXGK_SEALEDINCON; break; + case -EMSGSIZE: + *_error_code = RXGK_PACKETSHORT; + break; + case -ENOPKG: /* Would prefer RXGK_BADETYPE, but not available for YFS. */ default: + *_error_code = RXGK_INCONSISTENCY; break; } diff --git a/net/tls/tls.h b/net/tls/tls.h index 4e077068e6d9..e4c42731ce39 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -141,6 +141,7 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx); int wait_on_pending_writer(struct sock *sk, long *timeo); void tls_err_abort(struct sock *sk, int err); +void tls_strp_abort_strp(struct tls_strparser *strp, int err); int init_prot_info(struct tls_prot_info *prot, const struct tls_crypto_info *crypto_info, diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index d71643b494a1..98e12f0ff57e 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -13,7 +13,7 @@ static struct workqueue_struct *tls_strp_wq; -static void tls_strp_abort_strp(struct tls_strparser *strp, int err) +void tls_strp_abort_strp(struct tls_strparser *strp, int err) { if (strp->stopped) return; @@ -211,11 +211,17 @@ static int tls_strp_copyin_frag(struct tls_strparser *strp, struct sk_buff *skb, struct sk_buff *in_skb, unsigned int offset, size_t in_len) { + unsigned int nfrag = skb->len / PAGE_SIZE; size_t len, chunk; skb_frag_t *frag; int sz; - frag = &skb_shinfo(skb)->frags[skb->len / PAGE_SIZE]; + if (unlikely(nfrag >= skb_shinfo(skb)->nr_frags)) { + DEBUG_NET_WARN_ON_ONCE(1); + return -EMSGSIZE; + } + + frag = &skb_shinfo(skb)->frags[nfrag]; len = in_len; /* First make sure we got the header */ @@ -520,10 +526,8 @@ static int tls_strp_read_sock(struct tls_strparser *strp) tls_strp_load_anchor_with_queue(strp, inq); if (!strp->stm.full_len) { sz = tls_rx_msg_size(strp, strp->anchor); - if (sz < 0) { - tls_strp_abort_strp(strp, sz); + if (sz < 0) return sz; - } strp->stm.full_len = sz; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index bac65d0d4e3e..daac9fd4be7e 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2474,8 +2474,7 @@ int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb) return data_len + TLS_HEADER_SIZE; read_failure: - tls_err_abort(strp->sk, ret); - + tls_strp_abort_strp(strp, ret); return ret; } diff --git a/samples/damon/mtier.c b/samples/damon/mtier.c index 7ebd352138e4..beaf36657dea 100644 --- a/samples/damon/mtier.c +++ b/samples/damon/mtier.c @@ -208,6 +208,9 @@ static int damon_sample_mtier_enable_store( if (enabled == is_enabled) return 0; + if (!init_called) + return 0; + if (enabled) { err = damon_sample_mtier_start(); if (err) diff --git a/samples/damon/prcl.c b/samples/damon/prcl.c index 1b839c06a612..0226652f94d5 100644 --- a/samples/damon/prcl.c +++ b/samples/damon/prcl.c @@ -137,6 +137,9 @@ static int damon_sample_prcl_enable_store( if (enabled == is_enabled) return 0; + if (!init_called) + return 0; + if (enabled) { err = damon_sample_prcl_start(); if (err) diff --git a/samples/damon/wsse.c b/samples/damon/wsse.c index da052023b099..21eaf15f987d 100644 --- a/samples/damon/wsse.c +++ b/samples/damon/wsse.c @@ -118,6 +118,9 @@ static int damon_sample_wsse_enable_store( return 0; if (enabled) { + if (!init_called) + return 0; + err = damon_sample_wsse_start(); if (err) enabled = false; diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c index 9ef569492560..ddaeb4eb3e24 100644 --- a/tools/lib/subcmd/help.c +++ b/tools/lib/subcmd/help.c @@ -75,6 +75,9 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) size_t ci, cj, ei; int cmp; + if (!excludes->cnt) + return; + ci = cj = ei = 0; while (ci < cmds->cnt && ei < excludes->cnt) { cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index fd49703021fd..078634461df2 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -2009,6 +2009,7 @@ static int __cmd_contention(int argc, const char **argv) .owner = show_lock_owner, .cgroups = RB_ROOT, }; + struct perf_env host_env; lockhash_table = calloc(LOCKHASH_SIZE, sizeof(*lockhash_table)); if (!lockhash_table) @@ -2024,7 +2025,10 @@ static int __cmd_contention(int argc, const char **argv) eops.mmap = perf_event__process_mmap; eops.tracing_data = perf_event__process_tracing_data; - session = perf_session__new(use_bpf ? NULL : &data, &eops); + perf_env__init(&host_env); + session = __perf_session__new(use_bpf ? NULL : &data, &eops, + /*trace_event_repipe=*/false, &host_env); + if (IS_ERR(session)) { pr_err("Initializing perf session failed\n"); err = PTR_ERR(session); @@ -2142,6 +2146,7 @@ out_delete: evlist__delete(con.evlist); lock_contention_finish(&con); perf_session__delete(session); + perf_env__exit(&host_env); zfree(&lockhash_table); return err; } diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 85b2a93a59ac..779f6230130a 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -477,6 +477,7 @@ static int __maps__insert(struct maps *maps, struct map *new) } /* Insert the value at the end. */ maps_by_address[nr_maps] = map__get(new); + map__set_kmap_maps(new, maps); if (maps_by_name) maps_by_name[nr_maps] = map__get(new); @@ -502,8 +503,6 @@ static int __maps__insert(struct maps *maps, struct map *new) if (map__end(new) < map__start(new)) RC_CHK_ACCESS(maps)->ends_broken = true; - map__set_kmap_maps(new, maps); - return 0; } @@ -891,6 +890,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) if (before) { map__put(maps_by_address[i]); maps_by_address[i] = before; + map__set_kmap_maps(before, maps); if (maps_by_name) { map__put(maps_by_name[ni]); @@ -918,6 +918,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ map__put(maps_by_address[i]); maps_by_address[i] = map__get(new); + map__set_kmap_maps(new, maps); if (maps_by_name) { map__put(maps_by_name[ni]); @@ -942,14 +943,13 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ map__put(maps_by_address[i]); maps_by_address[i] = map__get(new); + map__set_kmap_maps(new, maps); if (maps_by_name) { map__put(maps_by_name[ni]); maps_by_name[ni] = map__get(new); } - map__set_kmap_maps(new, maps); - check_invariants(maps); return err; } @@ -1019,6 +1019,7 @@ int maps__copy_from(struct maps *dest, struct maps *parent) err = unwind__prepare_access(dest, new, NULL); if (!err) { dest_maps_by_address[i] = new; + map__set_kmap_maps(new, dest); if (dest_maps_by_name) dest_maps_by_name[i] = map__get(new); RC_CHK_ACCESS(dest)->nr_maps = i + 1; diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index 7bc148889ca7..187b478d0ddf 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -7,6 +7,8 @@ ALL_TESTS=" prio arp_validate num_grat_arp + fail_over_mac + vlan_over_bond " lib_dir=$(dirname "$0") @@ -352,8 +354,8 @@ garp_test() exp_num=$(echo "${param}" | cut -f6 -d ' ') active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") - slowwait_for_counter $((exp_num + 5)) $exp_num \ - tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}" + slowwait_for_counter $((exp_num + 5)) $exp_num tc_rule_handle_stats_get \ + "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}" &> /dev/null # check result real_num=$(tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}") @@ -376,6 +378,197 @@ num_grat_arp() done } +check_all_mac_same() +{ + RET=0 + # all slaves should have same mac address (with the first port's mac) + local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]') + local eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]') + local eth1_mac=$(ip -n "$s_ns" -j link show eth1 | jq -r '.[]["address"]') + local eth2_mac=$(ip -n "$s_ns" -j link show eth2 | jq -r '.[]["address"]') + if [ "$bond_mac" != "${mac[0]}" ] || [ "$eth0_mac" != "$bond_mac" ] || \ + [ "$eth1_mac" != "$bond_mac" ] || [ "$eth2_mac" != "$bond_mac" ]; then + RET=1 + fi +} + +check_bond_mac_same_with_first() +{ + RET=0 + # bond mac address should be same with the first added slave + local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]') + if [ "$bond_mac" != "${mac[0]}" ]; then + RET=1 + fi +} + +check_bond_mac_same_with_active() +{ + RET=0 + # bond mac address should be same with active slave + local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]') + local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + local active_slave_mac=$(ip -n "$s_ns" -j link show "$active_slave" | jq -r '.[]["address"]') + if [ "$bond_mac" != "$active_slave_mac" ]; then + RET=1 + fi +} + +check_backup_slave_mac_not_change() +{ + RET=0 + # backup slave's mac address is not changed + if ip -n "$s_ns" -d -j link show type bond_slave | jq -e '.[] + | select(.linkinfo.info_slave_data.state=="BACKUP") + | select(.address != .linkinfo.info_slave_data.perm_hwaddr)' &> /dev/null; then + RET=1 + fi +} + +check_backup_slave_mac_inherit() +{ + local backup_mac + RET=0 + + # backup slaves should use mac[1] or mac[2] + local backup_macs=$(ip -n "$s_ns" -d -j link show type bond_slave | \ + jq -r '.[] | select(.linkinfo.info_slave_data.state=="BACKUP") | .address') + for backup_mac in $backup_macs; do + if [ "$backup_mac" != "${mac[1]}" ] && [ "$backup_mac" != "${mac[2]}" ]; then + RET=1 + fi + done +} + +check_first_slave_random_mac() +{ + RET=0 + # remove the first added slave and added it back + ip -n "$s_ns" link set eth0 nomaster + ip -n "$s_ns" link set eth0 master bond0 + + # the first slave should use random mac address + eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]') + [ "$eth0_mac" = "${mac[0]}" ] && RET=1 + log_test "bond fail_over_mac follow" "random first slave mac" + + # remove the first slave, the permanent MAC address should be restored back + ip -n "$s_ns" link set eth0 nomaster + eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]') + [ "$eth0_mac" != "${mac[0]}" ] && RET=1 +} + +do_active_backup_failover() +{ + local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + ip -n ${s_ns} link set ${active_slave} down + slowwait 2 active_slave_changed $active_slave + ip -n ${s_ns} link set ${active_slave} up +} + +fail_over_mac() +{ + # Bring down the first interface on the switch to force the bond to + # select another active interface instead of the first one that joined. + ip -n "$g_ns" link set s0 down + + # fail_over_mac none + bond_reset "mode active-backup miimon 100 fail_over_mac 0" + check_all_mac_same + log_test "fail_over_mac 0" "all slaves have same mac" + do_active_backup_failover + check_all_mac_same + log_test "fail_over_mac 0" "failover: all slaves have same mac" + + # fail_over_mac active + bond_reset "mode active-backup miimon 100 fail_over_mac 1" + check_bond_mac_same_with_active + log_test "fail_over_mac 1" "bond mac is same with active slave mac" + check_backup_slave_mac_not_change + log_test "fail_over_mac 1" "backup slave mac is not changed" + do_active_backup_failover + check_bond_mac_same_with_active + log_test "fail_over_mac 1" "failover: bond mac is same with active slave mac" + check_backup_slave_mac_not_change + log_test "fail_over_mac 1" "failover: backup slave mac is not changed" + + # fail_over_mac follow + bond_reset "mode active-backup miimon 100 fail_over_mac 2" + check_bond_mac_same_with_first + log_test "fail_over_mac 2" "bond mac is same with first slave mac" + check_bond_mac_same_with_active + log_test "fail_over_mac 2" "bond mac is same with active slave mac" + check_backup_slave_mac_inherit + log_test "fail_over_mac 2" "backup slave mac inherit" + do_active_backup_failover + check_bond_mac_same_with_first + log_test "fail_over_mac 2" "failover: bond mac is same with first slave mac" + check_bond_mac_same_with_active + log_test "fail_over_mac 2" "failover: bond mac is same with active slave mac" + check_backup_slave_mac_inherit + log_test "fail_over_mac 2" "failover: backup slave mac inherit" + check_first_slave_random_mac + log_test "fail_over_mac 2" "first slave mac random" +} + +vlan_over_bond_arp() +{ + local mode="$1" + RET=0 + + bond_reset "mode $mode arp_interval 100 arp_ip_target 192.0.3.10" + ip -n "${s_ns}" link add bond0.3 link bond0 type vlan id 3 + ip -n "${s_ns}" link set bond0.3 up + ip -n "${s_ns}" addr add 192.0.3.1/24 dev bond0.3 + ip -n "${s_ns}" addr add 2001:db8::3:1/64 dev bond0.3 + + slowwait_for_counter 5 5 tc_rule_handle_stats_get \ + "dev eth0.3 ingress" 101 ".packets" "-n ${c_ns}" &> /dev/null || RET=1 + log_test "vlan over bond arp" "$mode" +} + +vlan_over_bond_ns() +{ + local mode="$1" + RET=0 + + if skip_ns; then + log_test_skip "vlan_over_bond ns" "$mode" + return 0 + fi + + bond_reset "mode $mode arp_interval 100 ns_ip6_target 2001:db8::3:10" + ip -n "${s_ns}" link add bond0.3 link bond0 type vlan id 3 + ip -n "${s_ns}" link set bond0.3 up + ip -n "${s_ns}" addr add 192.0.3.1/24 dev bond0.3 + ip -n "${s_ns}" addr add 2001:db8::3:1/64 dev bond0.3 + + slowwait_for_counter 5 5 tc_rule_handle_stats_get \ + "dev eth0.3 ingress" 102 ".packets" "-n ${c_ns}" &> /dev/null || RET=1 + log_test "vlan over bond ns" "$mode" +} + +vlan_over_bond() +{ + # add vlan 3 for client + ip -n "${c_ns}" link add eth0.3 link eth0 type vlan id 3 + ip -n "${c_ns}" link set eth0.3 up + ip -n "${c_ns}" addr add 192.0.3.10/24 dev eth0.3 + ip -n "${c_ns}" addr add 2001:db8::3:10/64 dev eth0.3 + + # Add tc rule to check the vlan pkts + tc -n "${c_ns}" qdisc add dev eth0.3 clsact + tc -n "${c_ns}" filter add dev eth0.3 ingress protocol arp \ + handle 101 flower skip_hw arp_op request \ + arp_sip 192.0.3.1 arp_tip 192.0.3.10 action pass + tc -n "${c_ns}" filter add dev eth0.3 ingress protocol ipv6 \ + handle 102 flower skip_hw ip_proto icmpv6 \ + type 135 src_ip 2001:db8::3:1 action pass + + vlan_over_bond_arp "active-backup" + vlan_over_bond_ns "active-backup" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh index 195ef83cfbf1..167aa4a4a12a 100644 --- a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh @@ -39,6 +39,8 @@ g_ip4="192.0.2.254" s_ip6="2001:db8::1" c_ip6="2001:db8::10" g_ip6="2001:db8::254" +mac[0]="00:0a:0b:0c:0d:01" +mac[1]="00:0a:0b:0c:0d:02" gateway_create() { @@ -62,6 +64,7 @@ server_create() for i in $(seq 0 1); do ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + ip -n "${s_ns}" link set "eth${i}" addr "${mac[$i]}" ip -n ${g_ns} link set s${i} up ip -n ${g_ns} link set s${i} master br0 diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh index 3a1333d9a85b..23a2932301cc 100644 --- a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh @@ -26,6 +26,7 @@ # +-------------------------------------+ source bond_topo_2d1c.sh +mac[2]="00:0a:0b:0c:0d:03" setup_prepare() { @@ -36,6 +37,7 @@ setup_prepare() # Add the extra device as we use 3 down links for bond0 local i=2 ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + ip -n "${s_ns}" link set "eth${i}" addr "${mac[$i]}" ip -n ${g_ns} link set s${i} up ip -n ${g_ns} link set s${i} master br0 ip -n ${s_ns} link set eth${i} master bond0 diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index 4d16a69ffc65..832fa1caeb66 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -10,3 +10,4 @@ CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_SCH_INGRESS=y CONFIG_NLMON=y CONFIG_VETH=y +CONFIG_VLAN_8021Q=m diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 4f07ac9fa207..b148cadb96d0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1093,6 +1093,7 @@ int main_loop_s(int listensock) struct pollfd polls; socklen_t salen; int remotesock; + int err = 0; int fd = 0; again: @@ -1125,7 +1126,7 @@ again: SOCK_TEST_TCPULP(remotesock, 0); memset(&winfo, 0, sizeof(winfo)); - copyfd_io(fd, remotesock, 1, true, &winfo); + err = copyfd_io(fd, remotesock, 1, true, &winfo); } else { perror("accept"); return 1; @@ -1134,10 +1135,10 @@ again: if (cfg_input) close(fd); - if (--cfg_repeat > 0) + if (!err && --cfg_repeat > 0) goto again; - return 0; + return err; } static void init_rng(void) @@ -1247,7 +1248,7 @@ void xdisconnect(int fd) else xerror("bad family"); - strcpy(cmd, "ss -M | grep -q "); + strcpy(cmd, "ss -Mnt | grep -q "); cmdlen = strlen(cmd); if (!inet_ntop(addr.ss_family, raw_addr, &cmd[cmdlen], sizeof(cmd) - cmdlen)) @@ -1257,7 +1258,7 @@ void xdisconnect(int fd) /* * wait until the pending data is completely flushed and all - * the MPTCP sockets reached the closed status. + * the sockets reached the closed status. * disconnect will bypass/ignore/drop any pending data. */ for (i = 0; ; i += msec_sleep) { diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index c2ab9f7f0d21..47ecb5b3836e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -211,6 +211,11 @@ if $checksum; then done fi +if $capture; then + rndh="${ns1:4}" + mptcp_lib_pr_info "Packet capture files will have this prefix: ${rndh}-" +fi + set_ethtool_flags() { local ns="$1" local dev="$2" @@ -361,7 +366,6 @@ do_transfer() if $capture; then local capuser - local rndh="${connector_ns:4}" if [ -z $SUDO_USER ] ; then capuser="" else diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 09cd24b2ae46..d62e653d48b0 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -384,7 +384,7 @@ mptcp_lib_make_file() { mptcp_lib_print_file_err() { ls -l "${1}" 1>&2 echo "Trailing bytes are: " - tail -c 27 "${1}" + tail -c 32 "${1}" | od -x | head -n2 } # $1: input file ; $2: output file ; $3: what kind of file diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index e934dd26a59d..112c07c4c37a 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -667,22 +667,26 @@ static void process_one_client(int fd, int pipefd) do_getsockopts(&s, fd, ret, ret2); if (s.mptcpi_rcv_delta != (uint64_t)ret + 1) - xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret); + xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64 ", diff %" PRId64, + s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - (ret + 1)); /* be nice when running on top of older kernel */ if (s.pkt_stats_avail) { if (s.last_sample.mptcpi_bytes_sent != ret2) - xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64, + xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, s.last_sample.mptcpi_bytes_sent, ret2, s.last_sample.mptcpi_bytes_sent - ret2); if (s.last_sample.mptcpi_bytes_received != ret) - xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64, + xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, s.last_sample.mptcpi_bytes_received, ret, s.last_sample.mptcpi_bytes_received - ret); if (s.last_sample.mptcpi_bytes_acked != ret) - xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64, - s.last_sample.mptcpi_bytes_acked, ret2, - s.last_sample.mptcpi_bytes_acked - ret2); + xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, + s.last_sample.mptcpi_bytes_acked, ret, + s.last_sample.mptcpi_bytes_acked - ret); } close(fd); diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 994a556f46c1..93fea3442216 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -188,6 +188,13 @@ static int capture_events(int fd, int event_group) fprintf(stderr, ",error:%u", *(__u8 *)RTA_DATA(attrs)); else if (attrs->rta_type == MPTCP_ATTR_SERVER_SIDE) fprintf(stderr, ",server_side:%u", *(__u8 *)RTA_DATA(attrs)); + else if (attrs->rta_type == MPTCP_ATTR_FLAGS) { + __u16 flags = *(__u16 *)RTA_DATA(attrs); + + /* only print when present, easier */ + if (flags & MPTCP_PM_EV_FLAG_DENY_JOIN_ID0) + fprintf(stderr, ",deny_join_id0:1"); + } attrs = RTA_NEXT(attrs, msg_len); } diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 970c329735ff..3d45991f24ed 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -201,6 +201,9 @@ make_connection() is_v6="v4" fi + # set this on the client side only: will not affect the rest + ip netns exec "$ns2" sysctl -q net.mptcp.allow_join_initial_addr_port=0 + :>"$client_evts" :>"$server_evts" @@ -223,23 +226,28 @@ make_connection() local client_token local client_port local client_serverside + local client_nojoin local server_token local server_serverside + local server_nojoin client_token=$(mptcp_lib_evts_get_info token "$client_evts") client_port=$(mptcp_lib_evts_get_info sport "$client_evts") client_serverside=$(mptcp_lib_evts_get_info server_side "$client_evts") + client_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$client_evts") server_token=$(mptcp_lib_evts_get_info token "$server_evts") server_serverside=$(mptcp_lib_evts_get_info server_side "$server_evts") + server_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$server_evts") print_test "Established IP${is_v6} MPTCP Connection ns2 => ns1" - if [ "$client_token" != "" ] && [ "$server_token" != "" ] && [ "$client_serverside" = 0 ] && - [ "$server_serverside" = 1 ] + if [ "${client_token}" != "" ] && [ "${server_token}" != "" ] && + [ "${client_serverside}" = 0 ] && [ "${server_serverside}" = 1 ] && + [ "${client_nojoin:-0}" = 0 ] && [ "${server_nojoin:-0}" = 1 ] then test_pass print_title "Connection info: ${client_addr}:${client_port} -> ${connect_addr}:${app_port}" else - test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})" + test_fail "Expected tokens (c:${client_token} - s:${server_token}), server (c:${client_serverside} - s:${server_serverside}), nojoin (c:${client_nojoin} - s:${server_nojoin})" mptcp_lib_result_print_all_tap exit ${KSFT_FAIL} fi diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index 3c8d3455d8e7..b327d3061ed5 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -25,6 +25,7 @@ tests=" nat_related_v4 ip4-nat-related: ICMP related matches work with SNAT netlink_checks ovsnl: validate netlink attrs and settings upcall_interfaces ovs: test the upcall interfaces + tunnel_metadata ovs: test extraction of tunnel metadata drop_reason drop: test drop reasons are emitted psample psample: Sampling packets with psample" @@ -113,13 +114,13 @@ ovs_add_dp () { } ovs_add_if () { - info "Adding IF to DP: br:$2 if:$3" - if [ "$4" != "-u" ]; then - ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py add-if "$2" "$3" \ - || return 1 + info "Adding IF to DP: br:$3 if:$4 ($2)" + if [ "$5" != "-u" ]; then + ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py add-if \ + -t "$2" "$3" "$4" || return 1 else python3 $ovs_base/ovs-dpctl.py add-if \ - -u "$2" "$3" >$ovs_dir/$3.out 2>$ovs_dir/$3.err & + -u -t "$2" "$3" "$4" >$ovs_dir/$4.out 2>$ovs_dir/$4.err & pid=$! on_exit "ovs_sbx $1 kill -TERM $pid 2>/dev/null" fi @@ -166,9 +167,9 @@ ovs_add_netns_and_veths () { fi if [ "$7" != "-u" ]; then - ovs_add_if "$1" "$2" "$4" || return 1 + ovs_add_if "$1" "netdev" "$2" "$4" || return 1 else - ovs_add_if "$1" "$2" "$4" -u || return 1 + ovs_add_if "$1" "netdev" "$2" "$4" -u || return 1 fi if [ $TRACING -eq 1 ]; then @@ -756,6 +757,79 @@ test_upcall_interfaces() { return 0 } +ovs_add_kernel_tunnel() { + local sbxname=$1; shift + local ns=$1; shift + local tnl_type=$1; shift + local name=$1; shift + local addr=$1; shift + + info "setting up kernel ${tnl_type} tunnel ${name}" + ovs_sbx "${sbxname}" ip -netns ${ns} link add dev ${name} type ${tnl_type} $* || return 1 + on_exit "ovs_sbx ${sbxname} ip -netns ${ns} link del ${name} >/dev/null 2>&1" + ovs_sbx "${sbxname}" ip -netns ${ns} addr add dev ${name} ${addr} || return 1 + ovs_sbx "${sbxname}" ip -netns ${ns} link set dev ${name} mtu 1450 up || return 1 +} + +test_tunnel_metadata() { + which arping >/dev/null 2>&1 || return $ksft_skip + + sbxname="test_tunnel_metadata" + sbx_add "${sbxname}" || return 1 + + info "setting up new DP" + ovs_add_dp "${sbxname}" tdp0 -V 2:1 || return 1 + + ovs_add_netns_and_veths "${sbxname}" tdp0 tns left0 l0 \ + 172.31.110.1/24 || return 1 + + info "removing veth interface from openvswitch and setting IP" + ovs_del_if "${sbxname}" tdp0 left0 || return 1 + ovs_sbx "${sbxname}" ip addr add 172.31.110.2/24 dev left0 || return 1 + ovs_sbx "${sbxname}" ip link set left0 up || return 1 + + info "setting up tunnel port in openvswitch" + ovs_add_if "${sbxname}" "vxlan" tdp0 ovs-vxlan0 -u || return 1 + on_exit "ovs_sbx ${sbxname} ip link del ovs-vxlan0" + ovs_wait ip link show ovs-vxlan0 &>/dev/null || return 1 + ovs_sbx "${sbxname}" ip link set ovs-vxlan0 up || return 1 + + configs=$(echo ' + 1 172.31.221.1/24 1155332 32 set udpcsum flags\(df\|csum\) + 2 172.31.222.1/24 1234567 45 set noudpcsum flags\(df\) + 3 172.31.223.1/24 1020304 23 unset udpcsum flags\(csum\) + 4 172.31.224.1/24 1357986 15 unset noudpcsum' | sed '/^$/d') + + while read -r i addr id ttl df csum flags; do + ovs_add_kernel_tunnel "${sbxname}" tns vxlan vxlan${i} ${addr} \ + remote 172.31.110.2 id ${id} dstport 4789 \ + ttl ${ttl} df ${df} ${csum} || return 1 + done <<< "${configs}" + + ovs_wait grep -q 'listening on upcall packet handler' \ + ${ovs_dir}/ovs-vxlan0.out || return 1 + + info "sending arping" + for i in 1 2 3 4; do + ovs_sbx "${sbxname}" ip netns exec tns \ + arping -I vxlan${i} 172.31.22${i}.2 -c 1 \ + >${ovs_dir}/arping.stdout 2>${ovs_dir}/arping.stderr + done + + info "checking that received decapsulated packets carry correct metadata" + while read -r i addr id ttl df csum flags; do + arp_hdr="arp\\(sip=172.31.22${i}.1,tip=172.31.22${i}.2,op=1,sha=" + addrs="src=172.31.110.1,dst=172.31.110.2" + ports="tp_src=[0-9]*,tp_dst=4789" + tnl_md="tunnel\\(tun_id=${id},${addrs},ttl=${ttl},${ports},${flags}\\)" + + ovs_sbx "${sbxname}" grep -qE "MISS upcall.*${tnl_md}.*${arp_hdr}" \ + ${ovs_dir}/ovs-vxlan0.out || return 1 + done <<< "${configs}" + + return 0 +} + run_test() { ( tname="$1" diff --git a/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-disconnect.pkt b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-disconnect.pkt new file mode 100644 index 000000000000..26794e7ddfd5 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_fastopen_server_reset-after-disconnect.pkt @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +`./defaults.sh + ./set_sysctls.py /proc/sys/net/ipv4/tcp_fastopen=0x602 /proc/sys/net/ipv4/tcp_timestamps=0` + + 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:10(10) win 32792 <mss 1460,nop,nop,sackOK> + +0 > S. 0:0(0) ack 11 win 65535 <mss 1460,nop,nop,sackOK> + +// sk->sk_state is TCP_SYN_RECV + +.1 accept(3, ..., ...) = 4 + +// tcp_disconnect() sets sk->sk_state to TCP_CLOSE + +0 connect(4, AF_UNSPEC, ...) = 0 + +0 > R. 1:1(0) ack 11 win 65535 + +// connect() sets sk->sk_state to TCP_SYN_SENT + +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + +0 connect(4, ..., ...) = -1 EINPROGRESS (Operation is now in progress) + +0 > S 0:0(0) win 65535 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +// tp->fastopen_rsk must be NULL + +1 > S 0:0(0) win 65535 <mss 1460,nop,nop,sackOK,nop,wscale 8> diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 0f5640d8dc7f..dd093f9df6f1 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -2770,6 +2770,22 @@ TEST_F(tls_err, poll_partial_rec_async) } } +/* Use OOB+large send to trigger copy mode due to memory pressure. + * OOB causes a short read. + */ +TEST_F(tls_err, oob_pressure) +{ + char buf[1<<16]; + int i; + + memrnd(buf, sizeof(buf)); + + EXPECT_EQ(send(self->fd2, buf, 5, MSG_OOB), 5); + EXPECT_EQ(send(self->fd2, buf, sizeof(buf), 0), sizeof(buf)); + for (i = 0; i < 64; i++) + EXPECT_EQ(send(self->fd2, buf, 5, MSG_OOB), 5); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; |