diff options
45 files changed, 764 insertions, 405 deletions
diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt index 2f6c6ff7161d..d8880ca30af4 100644 --- a/Documentation/block/null_blk.txt +++ b/Documentation/block/null_blk.txt @@ -70,3 +70,6 @@ use_per_node_hctx=[0/1]: Default: 0 parameter. 1: The multi-queue block layer is instantiated with a hardware dispatch queue for each CPU node in the system. + +use_lightnvm=[0/1]: Default: 0 + Register device with LightNVM. Requires blk-mq to be used. diff --git a/MAINTAINERS b/MAINTAINERS index 050d0e77a2cf..3f92804f5dac 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6366,6 +6366,7 @@ F: arch/*/include/asm/pmem.h LIGHTNVM PLATFORM SUPPORT M: Matias Bjorling <mb@lightnvm.io> W: http://github/OpenChannelSSD +L: linux-block@vger.kernel.org S: Maintained F: drivers/lightnvm/ F: include/linux/lightnvm.h diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index eab83b2435b8..e06fd299de08 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -564,17 +564,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) vcpu_sleep(vcpu); /* - * Disarming the background timer must be done in a - * preemptible context, as this call may sleep. - */ - kvm_timer_flush_hwstate(vcpu); - - /* * Preparing the interrupts to be injected also * involves poking the GIC, which must be done in a * non-preemptible context. */ preempt_disable(); + kvm_timer_flush_hwstate(vcpu); kvm_vgic_flush_hwstate(vcpu); local_irq_disable(); diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 6984342da13d..7dace909d5cf 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -98,6 +98,11 @@ static void kvm_flush_dcache_pud(pud_t pud) __kvm_flush_dcache_pud(pud); } +static bool kvm_is_device_pfn(unsigned long pfn) +{ + return !pfn_valid(pfn); +} + /** * stage2_dissolve_pmd() - clear and flush huge PMD entry * @kvm: pointer to kvm structure. @@ -213,7 +218,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd, kvm_tlb_flush_vmid_ipa(kvm, addr); /* No need to invalidate the cache for device mappings */ - if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + if (!kvm_is_device_pfn(__phys_to_pfn(addr))) kvm_flush_dcache_pte(old_pte); put_page(virt_to_page(pte)); @@ -305,8 +310,7 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, pte = pte_offset_kernel(pmd, addr); do { - if (!pte_none(*pte) && - (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE) + if (!pte_none(*pte) && !kvm_is_device_pfn(__phys_to_pfn(addr))) kvm_flush_dcache_pte(*pte); } while (pte++, addr += PAGE_SIZE, addr != end); } @@ -1037,11 +1041,6 @@ static bool kvm_is_write_fault(struct kvm_vcpu *vcpu) return kvm_vcpu_dabt_iswrite(vcpu); } -static bool kvm_is_device_pfn(unsigned long pfn) -{ - return !pfn_valid(pfn); -} - /** * stage2_wp_ptes - write protect PMD range * @pmd: pointer to pmd entry diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 9ac16a482ff1..e55848c1edf4 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -316,6 +316,27 @@ config ARM64_ERRATUM_832075 If unsure, say Y. +config ARM64_ERRATUM_834220 + bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault" + depends on KVM + default y + help + This option adds an alternative code sequence to work around ARM + erratum 834220 on Cortex-A57 parts up to r1p2. + + Affected Cortex-A57 parts might report a Stage 2 translation + fault as the result of a Stage 1 fault for load crossing a + page boundary when there is a permission or device memory + alignment fault at Stage 1 and a translation fault at Stage 2. + + The workaround is to verify that the Stage 1 translation + doesn't generate a fault before handling the Stage 2 fault. + Please note that this does not necessarily enable the workaround, + as it depends on the alternative framework, which will only patch + the kernel if an affected CPU is detected. + + If unsure, say Y. + config ARM64_ERRATUM_845719 bool "Cortex-A53: 845719: a load might read incorrect data" depends on COMPAT diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 11d5bb0fdd54..52722ee73dba 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -29,8 +29,9 @@ #define ARM64_HAS_PAN 4 #define ARM64_HAS_LSE_ATOMICS 5 #define ARM64_WORKAROUND_CAVIUM_23154 6 +#define ARM64_WORKAROUND_834220 7 -#define ARM64_NCAPS 7 +#define ARM64_NCAPS 8 #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 17e92f05b1fe..3ca894ecf699 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -99,11 +99,13 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) *vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT; } +/* + * vcpu_reg should always be passed a register number coming from a + * read of ESR_EL2. Otherwise, it may give the wrong result on AArch32 + * with banked registers. + */ static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num) { - if (vcpu_mode_is_32bit(vcpu)) - return vcpu_reg32(vcpu, reg_num); - return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num]; } diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 24926f2504f7..feb6b4efa641 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -75,6 +75,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { (1 << MIDR_VARIANT_SHIFT) | 2), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_834220 + { + /* Cortex-A57 r0p0 - r1p2 */ + .desc = "ARM erratum 834220", + .capability = ARM64_WORKAROUND_834220, + MIDR_RANGE(MIDR_CORTEX_A57, 0x00, + (1 << MIDR_VARIANT_SHIFT) | 2), + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_845719 { /* Cortex-A53 r0p[01234] */ diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 1599701ef044..86c289832272 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -864,6 +864,10 @@ ENTRY(__kvm_flush_vm_context) ENDPROC(__kvm_flush_vm_context) __kvm_hyp_panic: + // Stash PAR_EL1 before corrupting it in __restore_sysregs + mrs x0, par_el1 + push x0, xzr + // Guess the context by looking at VTTBR: // If zero, then we're already a host. // Otherwise restore a minimal host context before panicing. @@ -898,7 +902,7 @@ __kvm_hyp_panic: mrs x3, esr_el2 mrs x4, far_el2 mrs x5, hpfar_el2 - mrs x6, par_el1 + pop x6, xzr // active context PAR_EL1 mrs x7, tpidr_el2 mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ @@ -914,7 +918,7 @@ __kvm_hyp_panic: ENDPROC(__kvm_hyp_panic) __hyp_panic_str: - .ascii "HYP panic:\nPS:%08x PC:%p ESR:%p\nFAR:%p HPFAR:%p PAR:%p\nVCPU:%p\n\0" + .ascii "HYP panic:\nPS:%08x PC:%016x ESR:%08x\nFAR:%016x HPFAR:%016x PAR:%016x\nVCPU:%p\n\0" .align 2 @@ -1015,9 +1019,15 @@ el1_trap: b.ne 1f // Not an abort we care about /* This is an abort. Check for permission fault */ +alternative_if_not ARM64_WORKAROUND_834220 and x2, x1, #ESR_ELx_FSC_TYPE cmp x2, #FSC_PERM b.ne 1f // Not a permission fault +alternative_else + nop // Use the permission fault path to + nop // check for a valid S1 translation, + nop // regardless of the ESR value. +alternative_endif /* * Check for Stage-1 page table walk, which is guaranteed diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 85c57158dcd9..648112e90ed5 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -48,7 +48,7 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) /* Note: These now point to the banked copies */ *vcpu_spsr(vcpu) = new_spsr_value; - *vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; + *vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; /* Branch to exception vector */ if (sctlr & (1 << 13)) diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index d5fa3eaf39a1..41b1b090f56f 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1581,7 +1581,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, base = (inst >> 21) & 0x1f; op_inst = (inst >> 16) & 0x1f; - offset = inst & 0xffff; + offset = (int16_t)inst; cache = (inst >> 16) & 0x3; op = (inst >> 18) & 0x7; diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S index 7bab3a4e8f7d..7e2210846b8b 100644 --- a/arch/mips/kvm/locore.S +++ b/arch/mips/kvm/locore.S @@ -157,9 +157,11 @@ FEXPORT(__kvm_mips_vcpu_run) FEXPORT(__kvm_mips_load_asid) /* Set the ASID for the Guest Kernel */ - INT_SLL t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */ - /* addresses shift to 0x80000000 */ - bltz t0, 1f /* If kernel */ + PTR_L t0, VCPU_COP0(k1) + LONG_L t0, COP0_STATUS(t0) + andi t0, KSU_USER | ST0_ERL | ST0_EXL + xori t0, KSU_USER + bnez t0, 1f /* If kernel */ INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */ INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID /* else user */ 1: @@ -474,9 +476,11 @@ __kvm_mips_return_to_guest: mtc0 t0, CP0_EPC /* Set the ASID for the Guest Kernel */ - INT_SLL t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */ - /* addresses shift to 0x80000000 */ - bltz t0, 1f /* If kernel */ + PTR_L t0, VCPU_COP0(k1) + LONG_L t0, COP0_STATUS(t0) + andi t0, KSU_USER | ST0_ERL | ST0_EXL + xori t0, KSU_USER + bnez t0, 1f /* If kernel */ INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */ INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID /* else user */ 1: diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 49ff3bfc007e..b9b803facdbf 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -279,7 +279,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) if (!gebase) { err = -ENOMEM; - goto out_free_cpu; + goto out_uninit_cpu; } kvm_debug("Allocated %d bytes for KVM Exception Handlers @ %p\n", ALIGN(size, PAGE_SIZE), gebase); @@ -343,6 +343,9 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) out_free_gebase: kfree(gebase); +out_uninit_cpu: + kvm_vcpu_uninit(vcpu); + out_free_cpu: kfree(vcpu); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 373e32346d68..6a75352f453c 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1030,8 +1030,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) src_id, 0); /* sending vcpu invalid */ - if (src_id >= KVM_MAX_VCPUS || - kvm_get_vcpu(vcpu->kvm, src_id) == NULL) + if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL) return -EINVAL; if (sclp.has_sigpif) @@ -1110,6 +1109,10 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu, trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY, irq->u.emerg.code, 0); + /* sending vcpu invalid */ + if (kvm_get_vcpu_by_id(vcpu->kvm, irq->u.emerg.code) == NULL) + return -EINVAL; + set_bit(irq->u.emerg.code, li->sigp_emerg_pending); set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs); atomic_or(CPUSTAT_EXT_INT, li->cpuflags); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 8fe2f1c722dc..846589281b04 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -342,12 +342,16 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) r = 0; break; case KVM_CAP_S390_VECTOR_REGISTERS: - if (MACHINE_HAS_VX) { + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus)) { + r = -EBUSY; + } else if (MACHINE_HAS_VX) { set_kvm_facility(kvm->arch.model.fac->mask, 129); set_kvm_facility(kvm->arch.model.fac->list, 129); r = 0; } else r = -EINVAL; + mutex_unlock(&kvm->lock); VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s", r ? "(not available)" : "(success)"); break; diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 77191b85ea7a..d76b51cb4b62 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -660,7 +660,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) kvm_s390_get_regs_rre(vcpu, ®1, ®2); - if (!MACHINE_HAS_PFMF) + if (!test_kvm_facility(vcpu->kvm, 8)) return kvm_s390_inject_program_int(vcpu, PGM_OPERATION); if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index da690b69f9fe..77c22d685c7a 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -291,12 +291,8 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code, u16 cpu_addr, u32 parameter, u64 *status_reg) { int rc; - struct kvm_vcpu *dst_vcpu; + struct kvm_vcpu *dst_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr); - if (cpu_addr >= KVM_MAX_VCPUS) - return SIGP_CC_NOT_OPERATIONAL; - - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); if (!dst_vcpu) return SIGP_CC_NOT_OPERATIONAL; @@ -478,7 +474,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu) trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr); if (order_code == SIGP_EXTERNAL_CALL) { - dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); + dest_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr); BUG_ON(dest_vcpu == NULL); kvm_s390_vcpu_wakeup(dest_vcpu); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 87acc5221740..af823a388c19 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -7394,11 +7394,6 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) switch (type) { case VMX_VPID_EXTENT_ALL_CONTEXT: - if (get_vmcs12(vcpu)->virtual_processor_id == 0) { - nested_vmx_failValid(vcpu, - VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); - return 1; - } __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); nested_vmx_succeed(vcpu); break; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 00462bd63129..eed32283d22c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2763,6 +2763,26 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, return 0; } +static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) +{ + return (!lapic_in_kernel(vcpu) || + kvm_apic_accept_pic_intr(vcpu)); +} + +/* + * if userspace requested an interrupt window, check that the + * interrupt window is open. + * + * No need to exit to userspace if we already have an interrupt queued. + */ +static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) +{ + return kvm_arch_interrupt_allowed(vcpu) && + !kvm_cpu_has_interrupt(vcpu) && + !kvm_event_needs_reinjection(vcpu) && + kvm_cpu_accept_dm_intr(vcpu); +} + static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { @@ -2786,6 +2806,7 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, return -EEXIST; vcpu->arch.pending_external_vector = irq->irq; + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } @@ -5910,23 +5931,10 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); } -/* - * Check if userspace requested an interrupt window, and that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { - if (!vcpu->run->request_interrupt_window || pic_in_kernel(vcpu->kvm)) - return false; - - if (kvm_cpu_has_interrupt(vcpu)) - return false; - - return (irqchip_split(vcpu->kvm) - ? kvm_apic_accept_pic_intr(vcpu) - : kvm_arch_interrupt_allowed(vcpu)); + return vcpu->run->request_interrupt_window && + likely(!pic_in_kernel(vcpu->kvm)); } static void post_kvm_run_save(struct kvm_vcpu *vcpu) @@ -5937,17 +5945,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); - if (!irqchip_in_kernel(vcpu->kvm)) - kvm_run->ready_for_interrupt_injection = - kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu); - else if (!pic_in_kernel(vcpu->kvm)) - kvm_run->ready_for_interrupt_injection = - kvm_apic_accept_pic_intr(vcpu) && - !kvm_cpu_has_interrupt(vcpu); - else - kvm_run->ready_for_interrupt_injection = 1; + kvm_run->ready_for_interrupt_injection = + pic_in_kernel(vcpu->kvm) || + kvm_vcpu_ready_for_interrupt_injection(vcpu); } static void update_cr8_intercept(struct kvm_vcpu *vcpu) @@ -6360,8 +6360,10 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; - bool req_int_win = !lapic_in_kernel(vcpu) && - vcpu->run->request_interrupt_window; + bool req_int_win = + dm_request_for_irq_injection(vcpu) && + kvm_cpu_accept_dm_intr(vcpu); + bool req_immediate_exit = false; if (vcpu->requests) { @@ -6663,7 +6665,8 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); - if (dm_request_for_irq_injection(vcpu)) { + if (dm_request_for_irq_injection(vcpu) && + kvm_vcpu_ready_for_interrupt_injection(vcpu)) { r = 0; vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; ++vcpu->stat.request_irq_exits; diff --git a/block/blk-merge.c b/block/blk-merge.c index de5716d8e525..41a55ba0d78e 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -76,6 +76,9 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio_vec bv, bvprv, *bvprvp = NULL; struct bvec_iter iter; unsigned seg_size = 0, nsegs = 0, sectors = 0; + unsigned front_seg_size = bio->bi_seg_front_size; + bool do_split = true; + struct bio *new = NULL; bio_for_each_segment(bv, bio, iter) { if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q)) @@ -98,7 +101,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, seg_size += bv.bv_len; bvprv = bv; - bvprvp = &bv; + bvprvp = &bvprv; sectors += bv.bv_len >> 9; continue; } @@ -108,16 +111,29 @@ new_segment: nsegs++; bvprv = bv; - bvprvp = &bv; + bvprvp = &bvprv; seg_size = bv.bv_len; sectors += bv.bv_len >> 9; + + if (nsegs == 1 && seg_size > front_seg_size) + front_seg_size = seg_size; } - *segs = nsegs; - return NULL; + do_split = false; split: *segs = nsegs; - return bio_split(bio, sectors, GFP_NOIO, bs); + + if (do_split) { + new = bio_split(bio, sectors, GFP_NOIO, bs); + if (new) + bio = new; + } + + bio->bi_seg_front_size = front_seg_size; + if (seg_size > bio->bi_seg_back_size) + bio->bi_seg_back_size = seg_size; + + return do_split ? new : NULL; } void blk_queue_split(struct request_queue *q, struct bio **bio, @@ -412,6 +428,12 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, if (sg) sg_mark_end(sg); + /* + * Something must have been wrong if the figured number of + * segment is bigger than number of req's physical segments + */ + WARN_ON(nsegs > rq->nr_phys_segments); + return nsegs; } EXPORT_SYMBOL(blk_rq_map_sg); diff --git a/block/blk-mq.c b/block/blk-mq.c index 3ae09de62f19..6d6f8feb48c0 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1291,15 +1291,16 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_mq_bio_to_request(rq, bio); /* - * we do limited pluging. If bio can be merged, do merge. + * We do limited pluging. If the bio can be merged, do that. * Otherwise the existing request in the plug list will be * issued. So the plug list will have one request at most */ if (plug) { /* * The plug list might get flushed before this. If that - * happens, same_queue_rq is invalid and plug list is empty - **/ + * happens, same_queue_rq is invalid and plug list is + * empty + */ if (same_queue_rq && !list_empty(&plug->mq_list)) { old_rq = same_queue_rq; list_del_init(&old_rq->queuelist); @@ -1380,12 +1381,15 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) blk_mq_bio_to_request(rq, bio); if (!request_count) trace_block_plug(q); - else if (request_count >= BLK_MAX_REQUEST_COUNT) { + + blk_mq_put_ctx(data.ctx); + + if (request_count >= BLK_MAX_REQUEST_COUNT) { blk_flush_plug_list(plug, false); trace_block_plug(q); } + list_add_tail(&rq->queuelist, &plug->mq_list); - blk_mq_put_ctx(data.ctx); return cookie; } diff --git a/block/blk-timeout.c b/block/blk-timeout.c index 246dfb16c3d9..aa40aa93381b 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -158,11 +158,13 @@ void blk_abort_request(struct request *req) { if (blk_mark_rq_complete(req)) return; - blk_delete_timer(req); - if (req->q->mq_ops) + + if (req->q->mq_ops) { blk_mq_rq_timed_out(req, false); - else + } else { + blk_delete_timer(req); blk_rq_timed_out(req); + } } EXPORT_SYMBOL_GPL(blk_abort_request); diff --git a/block/noop-iosched.c b/block/noop-iosched.c index 3de89d4690f3..a163c487cf38 100644 --- a/block/noop-iosched.c +++ b/block/noop-iosched.c @@ -21,10 +21,10 @@ static void noop_merged_requests(struct request_queue *q, struct request *rq, static int noop_dispatch(struct request_queue *q, int force) { struct noop_data *nd = q->elevator->elevator_data; + struct request *rq; - if (!list_empty(&nd->queue)) { - struct request *rq; - rq = list_entry(nd->queue.next, struct request, queuelist); + rq = list_first_entry_or_null(&nd->queue, struct request, queuelist); + if (rq) { list_del_init(&rq->queuelist); elv_dispatch_sort(q, rq); return 1; @@ -46,7 +46,7 @@ noop_former_request(struct request_queue *q, struct request *rq) if (rq->queuelist.prev == &nd->queue) return NULL; - return list_entry(rq->queuelist.prev, struct request, queuelist); + return list_prev_entry(rq, queuelist); } static struct request * @@ -56,7 +56,7 @@ noop_latter_request(struct request_queue *q, struct request *rq) if (rq->queuelist.next == &nd->queue) return NULL; - return list_entry(rq->queuelist.next, struct request, queuelist); + return list_next_entry(rq, queuelist); } static int noop_init_queue(struct request_queue *q, struct elevator_type *e) diff --git a/block/partitions/mac.c b/block/partitions/mac.c index c2c48ec64b27..621317ac4d59 100644 --- a/block/partitions/mac.c +++ b/block/partitions/mac.c @@ -32,7 +32,7 @@ int mac_partition(struct parsed_partitions *state) Sector sect; unsigned char *data; int slot, blocks_in_map; - unsigned secsize; + unsigned secsize, datasize, partoffset; #ifdef CONFIG_PPC_PMAC int found_root = 0; int found_root_goodness = 0; @@ -50,10 +50,14 @@ int mac_partition(struct parsed_partitions *state) } secsize = be16_to_cpu(md->block_size); put_dev_sector(sect); - data = read_part_sector(state, secsize/512, §); + datasize = round_down(secsize, 512); + data = read_part_sector(state, datasize / 512, §); if (!data) return -1; - part = (struct mac_partition *) (data + secsize%512); + partoffset = secsize % 512; + if (partoffset + sizeof(*part) > datasize) + return -1; + part = (struct mac_partition *) (data + partoffset); if (be16_to_cpu(part->signature) != MAC_PARTITION_MAGIC) { put_dev_sector(sect); return 0; /* not a MacOS disk */ diff --git a/drivers/Makefile b/drivers/Makefile index 73d039156ea7..795d0ca714bf 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -63,6 +63,7 @@ obj-$(CONFIG_FB_I810) += video/fbdev/i810/ obj-$(CONFIG_FB_INTEL) += video/fbdev/intelfb/ obj-$(CONFIG_PARPORT) += parport/ +obj-$(CONFIG_NVM) += lightnvm/ obj-y += base/ block/ misc/ mfd/ nfc/ obj-$(CONFIG_LIBNVDIMM) += nvdimm/ obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/ @@ -70,7 +71,6 @@ obj-$(CONFIG_NUBUS) += nubus/ obj-y += macintosh/ obj-$(CONFIG_IDE) += ide/ obj-$(CONFIG_SCSI) += scsi/ -obj-$(CONFIG_NVM) += lightnvm/ obj-y += nvme/ obj-$(CONFIG_ATA) += ata/ obj-$(CONFIG_TARGET_CORE) += target/ diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index a28a562f7b7f..3457ac8c03e2 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -3810,7 +3810,6 @@ static int mtip_block_initialize(struct driver_data *dd) sector_t capacity; unsigned int index = 0; struct kobject *kobj; - unsigned char thd_name[16]; if (dd->disk) goto skip_create_disk; /* hw init done, before rebuild */ @@ -3958,10 +3957,9 @@ skip_create_disk: } start_service_thread: - sprintf(thd_name, "mtip_svc_thd_%02d", index); dd->mtip_svc_handler = kthread_create_on_node(mtip_service_thread, - dd, dd->numa_node, "%s", - thd_name); + dd, dd->numa_node, + "mtip_svc_thd_%02d", index); if (IS_ERR(dd->mtip_svc_handler)) { dev_err(&dd->pdev->dev, "service thread failed to start\n"); diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index 6255d1c4bba4..5c8ba5484d86 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -8,6 +8,7 @@ #include <linux/slab.h> #include <linux/blk-mq.h> #include <linux/hrtimer.h> +#include <linux/lightnvm.h> struct nullb_cmd { struct list_head list; @@ -39,12 +40,14 @@ struct nullb { struct nullb_queue *queues; unsigned int nr_queues; + char disk_name[DISK_NAME_LEN]; }; static LIST_HEAD(nullb_list); static struct mutex lock; static int null_major; static int nullb_indexes; +static struct kmem_cache *ppa_cache; struct completion_queue { struct llist_head list; @@ -119,6 +122,10 @@ static int nr_devices = 2; module_param(nr_devices, int, S_IRUGO); MODULE_PARM_DESC(nr_devices, "Number of devices to register"); +static bool use_lightnvm; +module_param(use_lightnvm, bool, S_IRUGO); +MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device"); + static int irqmode = NULL_IRQ_SOFTIRQ; static int null_set_irqmode(const char *str, const struct kernel_param *kp) @@ -427,15 +434,156 @@ static void null_del_dev(struct nullb *nullb) { list_del_init(&nullb->list); - del_gendisk(nullb->disk); + if (use_lightnvm) + nvm_unregister(nullb->disk_name); + else + del_gendisk(nullb->disk); blk_cleanup_queue(nullb->q); if (queue_mode == NULL_Q_MQ) blk_mq_free_tag_set(&nullb->tag_set); - put_disk(nullb->disk); + if (!use_lightnvm) + put_disk(nullb->disk); cleanup_queues(nullb); kfree(nullb); } +#ifdef CONFIG_NVM + +static void null_lnvm_end_io(struct request *rq, int error) +{ + struct nvm_rq *rqd = rq->end_io_data; + struct nvm_dev *dev = rqd->dev; + + dev->mt->end_io(rqd, error); + + blk_put_request(rq); +} + +static int null_lnvm_submit_io(struct request_queue *q, struct nvm_rq *rqd) +{ + struct request *rq; + struct bio *bio = rqd->bio; + + rq = blk_mq_alloc_request(q, bio_rw(bio), GFP_KERNEL, 0); + if (IS_ERR(rq)) + return -ENOMEM; + + rq->cmd_type = REQ_TYPE_DRV_PRIV; + rq->__sector = bio->bi_iter.bi_sector; + rq->ioprio = bio_prio(bio); + + if (bio_has_data(bio)) + rq->nr_phys_segments = bio_phys_segments(q, bio); + + rq->__data_len = bio->bi_iter.bi_size; + rq->bio = rq->biotail = bio; + + rq->end_io_data = rqd; + + blk_execute_rq_nowait(q, NULL, rq, 0, null_lnvm_end_io); + + return 0; +} + +static int null_lnvm_id(struct request_queue *q, struct nvm_id *id) +{ + sector_t size = gb * 1024 * 1024 * 1024ULL; + sector_t blksize; + struct nvm_id_group *grp; + + id->ver_id = 0x1; + id->vmnt = 0; + id->cgrps = 1; + id->cap = 0x3; + id->dom = 0x1; + + id->ppaf.blk_offset = 0; + id->ppaf.blk_len = 16; + id->ppaf.pg_offset = 16; + id->ppaf.pg_len = 16; + id->ppaf.sect_offset = 32; + id->ppaf.sect_len = 8; + id->ppaf.pln_offset = 40; + id->ppaf.pln_len = 8; + id->ppaf.lun_offset = 48; + id->ppaf.lun_len = 8; + id->ppaf.ch_offset = 56; + id->ppaf.ch_len = 8; + + do_div(size, bs); /* convert size to pages */ + do_div(size, 256); /* concert size to pgs pr blk */ + grp = &id->groups[0]; + grp->mtype = 0; + grp->fmtype = 0; + grp->num_ch = 1; + grp->num_pg = 256; + blksize = size; + do_div(size, (1 << 16)); + grp->num_lun = size + 1; + do_div(blksize, grp->num_lun); + grp->num_blk = blksize; + grp->num_pln = 1; + + grp->fpg_sz = bs; + grp->csecs = bs; + grp->trdt = 25000; + grp->trdm = 25000; + grp->tprt = 500000; + grp->tprm = 500000; + grp->tbet = 1500000; + grp->tbem = 1500000; + grp->mpos = 0x010101; /* single plane rwe */ + grp->cpar = hw_queue_depth; + + return 0; +} + +static void *null_lnvm_create_dma_pool(struct request_queue *q, char *name) +{ + mempool_t *virtmem_pool; + + virtmem_pool = mempool_create_slab_pool(64, ppa_cache); + if (!virtmem_pool) { + pr_err("null_blk: Unable to create virtual memory pool\n"); + return NULL; + } + + return virtmem_pool; +} + +static void null_lnvm_destroy_dma_pool(void *pool) +{ + mempool_destroy(pool); +} + +static void *null_lnvm_dev_dma_alloc(struct request_queue *q, void *pool, + gfp_t mem_flags, dma_addr_t *dma_handler) +{ + return mempool_alloc(pool, mem_flags); +} + +static void null_lnvm_dev_dma_free(void *pool, void *entry, + dma_addr_t dma_handler) +{ + mempool_free(entry, pool); +} + +static struct nvm_dev_ops null_lnvm_dev_ops = { + .identity = null_lnvm_id, + .submit_io = null_lnvm_submit_io, + + .create_dma_pool = null_lnvm_create_dma_pool, + .destroy_dma_pool = null_lnvm_destroy_dma_pool, + .dev_dma_alloc = null_lnvm_dev_dma_alloc, + .dev_dma_free = null_lnvm_dev_dma_free, + + /* Simulate nvme protocol restriction */ + .max_phys_sect = 64, +}; +#else +static struct nvm_dev_ops null_lnvm_dev_ops; +#endif /* CONFIG_NVM */ + static int null_open(struct block_device *bdev, fmode_t mode) { return 0; @@ -575,11 +723,6 @@ static int null_add_dev(void) queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q); queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q); - disk = nullb->disk = alloc_disk_node(1, home_node); - if (!disk) { - rv = -ENOMEM; - goto out_cleanup_blk_queue; - } mutex_lock(&lock); list_add_tail(&nullb->list, &nullb_list); @@ -589,6 +732,21 @@ static int null_add_dev(void) blk_queue_logical_block_size(nullb->q, bs); blk_queue_physical_block_size(nullb->q, bs); + sprintf(nullb->disk_name, "nullb%d", nullb->index); + + if (use_lightnvm) { + rv = nvm_register(nullb->q, nullb->disk_name, + &null_lnvm_dev_ops); + if (rv) + goto out_cleanup_blk_queue; + goto done; + } + + disk = nullb->disk = alloc_disk_node(1, home_node); + if (!disk) { + rv = -ENOMEM; + goto out_cleanup_lightnvm; + } size = gb * 1024 * 1024 * 1024ULL; set_capacity(disk, size >> 9); @@ -598,10 +756,15 @@ static int null_add_dev(void) disk->fops = &null_fops; disk->private_data = nullb; disk->queue = nullb->q; - sprintf(disk->disk_name, "nullb%d", nullb->index); + strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); + add_disk(disk); +done: return 0; +out_cleanup_lightnvm: + if (use_lightnvm) + nvm_unregister(nullb->disk_name); out_cleanup_blk_queue: blk_cleanup_queue(nullb->q); out_cleanup_tags: @@ -625,6 +788,18 @@ static int __init null_init(void) bs = PAGE_SIZE; } + if (use_lightnvm && bs != 4096) { + pr_warn("null_blk: LightNVM only supports 4k block size\n"); + pr_warn("null_blk: defaults block size to 4k\n"); + bs = 4096; + } + + if (use_lightnvm && queue_mode != NULL_Q_MQ) { + pr_warn("null_blk: LightNVM only supported for blk-mq\n"); + pr_warn("null_blk: defaults queue mode to blk-mq\n"); + queue_mode = NULL_Q_MQ; + } + if (queue_mode == NULL_Q_MQ && use_per_node_hctx) { if (submit_queues < nr_online_nodes) { pr_warn("null_blk: submit_queues param is set to %u.", @@ -655,15 +830,27 @@ static int __init null_init(void) if (null_major < 0) return null_major; + if (use_lightnvm) { + ppa_cache = kmem_cache_create("ppa_cache", 64 * sizeof(u64), + 0, 0, NULL); + if (!ppa_cache) { + pr_err("null_blk: unable to create ppa cache\n"); + return -ENOMEM; + } + } + for (i = 0; i < nr_devices; i++) { if (null_add_dev()) { unregister_blkdev(null_major, "nullb"); - return -EINVAL; + goto err_ppa; } } pr_info("null: module loaded\n"); return 0; +err_ppa: + kmem_cache_destroy(ppa_cache); + return -EINVAL; } static void __exit null_exit(void) @@ -678,6 +865,8 @@ static void __exit null_exit(void) null_del_dev(nullb); } mutex_unlock(&lock); + + kmem_cache_destroy(ppa_cache); } module_init(null_init); diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index f659e605a406..5178645ac42b 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -160,11 +160,6 @@ int nvm_erase_blk(struct nvm_dev *dev, struct nvm_block *blk) } EXPORT_SYMBOL(nvm_erase_blk); -static void nvm_core_free(struct nvm_dev *dev) -{ - kfree(dev); -} - static int nvm_core_init(struct nvm_dev *dev) { struct nvm_id *id = &dev->identity; @@ -179,12 +174,21 @@ static int nvm_core_init(struct nvm_dev *dev) dev->sec_size = grp->csecs; dev->oob_size = grp->sos; dev->sec_per_pg = grp->fpg_sz / grp->csecs; - dev->addr_mode = id->ppat; - dev->addr_format = id->ppaf; + memcpy(&dev->ppaf, &id->ppaf, sizeof(struct nvm_addr_format)); dev->plane_mode = NVM_PLANE_SINGLE; dev->max_rq_size = dev->ops->max_phys_sect * dev->sec_size; + if (grp->mtype != 0) { + pr_err("nvm: memory type not supported\n"); + return -EINVAL; + } + + if (grp->fmtype != 0 && grp->fmtype != 1) { + pr_err("nvm: flash type not supported\n"); + return -EINVAL; + } + if (grp->mpos & 0x020202) dev->plane_mode = NVM_PLANE_DOUBLE; if (grp->mpos & 0x040404) @@ -213,21 +217,18 @@ static void nvm_free(struct nvm_dev *dev) if (dev->mt) dev->mt->unregister_mgr(dev); - - nvm_core_free(dev); } static int nvm_init(struct nvm_dev *dev) { struct nvmm_type *mt; - int ret = 0; + int ret = -EINVAL; if (!dev->q || !dev->ops) - return -EINVAL; + return ret; if (dev->ops->identity(dev->q, &dev->identity)) { pr_err("nvm: device could not be identified\n"); - ret = -EINVAL; goto err; } @@ -273,7 +274,6 @@ static int nvm_init(struct nvm_dev *dev) dev->nr_chnls); return 0; err: - nvm_free(dev); pr_err("nvm: failed to initialize nvm\n"); return ret; } @@ -308,22 +308,24 @@ int nvm_register(struct request_queue *q, char *disk_name, if (ret) goto err_init; - down_write(&nvm_lock); - list_add(&dev->devices, &nvm_devices); - up_write(&nvm_lock); - if (dev->ops->max_phys_sect > 1) { dev->ppalist_pool = dev->ops->create_dma_pool(dev->q, "ppalist"); if (!dev->ppalist_pool) { pr_err("nvm: could not create ppa pool\n"); - return -ENOMEM; + ret = -ENOMEM; + goto err_init; } } else if (dev->ops->max_phys_sect > 256) { pr_info("nvm: max sectors supported is 256.\n"); - return -EINVAL; + ret = -EINVAL; + goto err_init; } + down_write(&nvm_lock); + list_add(&dev->devices, &nvm_devices); + up_write(&nvm_lock); + return 0; err_init: kfree(dev); @@ -341,11 +343,12 @@ void nvm_unregister(char *disk_name) return; } - nvm_exit(dev); - down_write(&nvm_lock); list_del(&dev->devices); up_write(&nvm_lock); + + nvm_exit(dev); + kfree(dev); } EXPORT_SYMBOL(nvm_unregister); @@ -457,11 +460,11 @@ static void nvm_remove_target(struct nvm_target *t) lockdep_assert_held(&nvm_lock); del_gendisk(tdisk); + blk_cleanup_queue(q); + if (tt->exit) tt->exit(tdisk->private_data); - blk_cleanup_queue(q); - put_disk(tdisk); list_del(&t->list); @@ -541,7 +544,7 @@ static int nvm_configure_show(const char *val) if (!dev->mt) return 0; - dev->mt->free_blocks_print(dev); + dev->mt->lun_info_print(dev); return 0; } diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c index ae1fb2bdc5f4..e20e74ec6b91 100644 --- a/drivers/lightnvm/gennvm.c +++ b/drivers/lightnvm/gennvm.c @@ -60,23 +60,28 @@ static int gennvm_luns_init(struct nvm_dev *dev, struct gen_nvm *gn) lun->vlun.lun_id = i % dev->luns_per_chnl; lun->vlun.chnl_id = i / dev->luns_per_chnl; lun->vlun.nr_free_blocks = dev->blks_per_lun; + lun->vlun.nr_inuse_blocks = 0; + lun->vlun.nr_bad_blocks = 0; } return 0; } -static int gennvm_block_bb(u32 lun_id, void *bb_bitmap, unsigned int nr_blocks, +static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks, void *private) { struct gen_nvm *gn = private; - struct gen_lun *lun = &gn->luns[lun_id]; + struct nvm_dev *dev = gn->dev; + struct gen_lun *lun; struct nvm_block *blk; int i; - if (unlikely(bitmap_empty(bb_bitmap, nr_blocks))) - return 0; + ppa = dev_to_generic_addr(gn->dev, ppa); + lun = &gn->luns[(dev->nr_luns * ppa.g.ch) + ppa.g.lun]; + + for (i = 0; i < nr_blocks; i++) { + if (blks[i] == 0) + continue; - i = -1; - while ((i = find_next_bit(bb_bitmap, nr_blocks, i + 1)) < nr_blocks) { blk = &lun->vlun.blocks[i]; if (!blk) { pr_err("gennvm: BB data is out of bounds.\n"); @@ -84,6 +89,7 @@ static int gennvm_block_bb(u32 lun_id, void *bb_bitmap, unsigned int nr_blocks, } list_move_tail(&blk->list, &lun->bb_list); + lun->vlun.nr_bad_blocks++; } return 0; @@ -136,6 +142,7 @@ static int gennvm_block_map(u64 slba, u32 nlb, __le64 *entries, void *private) list_move_tail(&blk->list, &lun->used_list); blk->type = 1; lun->vlun.nr_free_blocks--; + lun->vlun.nr_inuse_blocks++; } } @@ -164,15 +171,25 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn) block->id = cur_block_id++; /* First block is reserved for device */ - if (unlikely(lun_iter == 0 && blk_iter == 0)) + if (unlikely(lun_iter == 0 && blk_iter == 0)) { + lun->vlun.nr_free_blocks--; continue; + } list_add_tail(&block->list, &lun->free_list); } if (dev->ops->get_bb_tbl) { - ret = dev->ops->get_bb_tbl(dev->q, lun->vlun.id, - dev->blks_per_lun, gennvm_block_bb, gn); + struct ppa_addr ppa; + + ppa.ppa = 0; + ppa.g.ch = lun->vlun.chnl_id; + ppa.g.lun = lun->vlun.id; + ppa = generic_to_dev_addr(dev, ppa); + + ret = dev->ops->get_bb_tbl(dev->q, ppa, + dev->blks_per_lun, + gennvm_block_bb, gn); if (ret) pr_err("gennvm: could not read BB table\n"); } @@ -199,6 +216,7 @@ static int gennvm_register(struct nvm_dev *dev) if (!gn) return -ENOMEM; + gn->dev = dev; gn->nr_luns = dev->nr_luns; dev->mp = gn; @@ -254,6 +272,7 @@ static struct nvm_block *gennvm_get_blk(struct nvm_dev *dev, blk->type = 1; lun->vlun.nr_free_blocks--; + lun->vlun.nr_inuse_blocks++; spin_unlock(&vlun->lock); out: @@ -271,16 +290,21 @@ static void gennvm_put_blk(struct nvm_dev *dev, struct nvm_block *blk) case 1: list_move_tail(&blk->list, &lun->free_list); lun->vlun.nr_free_blocks++; + lun->vlun.nr_inuse_blocks--; blk->type = 0; break; case 2: list_move_tail(&blk->list, &lun->bb_list); + lun->vlun.nr_bad_blocks++; + lun->vlun.nr_inuse_blocks--; break; default: WARN_ON_ONCE(1); pr_err("gennvm: erroneous block type (%lu -> %u)\n", blk->id, blk->type); list_move_tail(&blk->list, &lun->bb_list); + lun->vlun.nr_bad_blocks++; + lun->vlun.nr_inuse_blocks--; } spin_unlock(&vlun->lock); @@ -292,10 +316,10 @@ static void gennvm_addr_to_generic_mode(struct nvm_dev *dev, struct nvm_rq *rqd) if (rqd->nr_pages > 1) { for (i = 0; i < rqd->nr_pages; i++) - rqd->ppa_list[i] = addr_to_generic_mode(dev, + rqd->ppa_list[i] = dev_to_generic_addr(dev, rqd->ppa_list[i]); } else { - rqd->ppa_addr = addr_to_generic_mode(dev, rqd->ppa_addr); + rqd->ppa_addr = dev_to_generic_addr(dev, rqd->ppa_addr); } } @@ -305,10 +329,10 @@ static void gennvm_generic_to_addr_mode(struct nvm_dev *dev, struct nvm_rq *rqd) if (rqd->nr_pages > 1) { for (i = 0; i < rqd->nr_pages; i++) - rqd->ppa_list[i] = generic_to_addr_mode(dev, + rqd->ppa_list[i] = generic_to_dev_addr(dev, rqd->ppa_list[i]); } else { - rqd->ppa_addr = generic_to_addr_mode(dev, rqd->ppa_addr); + rqd->ppa_addr = generic_to_dev_addr(dev, rqd->ppa_addr); } } @@ -354,10 +378,10 @@ static void gennvm_mark_blk_bad(struct nvm_dev *dev, struct nvm_rq *rqd) { int i; - if (!dev->ops->set_bb) + if (!dev->ops->set_bb_tbl) return; - if (dev->ops->set_bb(dev->q, rqd, 1)) + if (dev->ops->set_bb_tbl(dev->q, rqd, 1)) return; gennvm_addr_to_generic_mode(dev, rqd); @@ -440,15 +464,24 @@ static struct nvm_lun *gennvm_get_lun(struct nvm_dev *dev, int lunid) return &gn->luns[lunid].vlun; } -static void gennvm_free_blocks_print(struct nvm_dev *dev) +static void gennvm_lun_info_print(struct nvm_dev *dev) { struct gen_nvm *gn = dev->mp; struct gen_lun *lun; unsigned int i; - gennvm_for_each_lun(gn, lun, i) - pr_info("%s: lun%8u\t%u\n", - dev->name, i, lun->vlun.nr_free_blocks); + + gennvm_for_each_lun(gn, lun, i) { + spin_lock(&lun->vlun.lock); + + pr_info("%s: lun%8u\t%u\t%u\t%u\n", + dev->name, i, + lun->vlun.nr_free_blocks, + lun->vlun.nr_inuse_blocks, + lun->vlun.nr_bad_blocks); + + spin_unlock(&lun->vlun.lock); + } } static struct nvmm_type gennvm = { @@ -466,7 +499,7 @@ static struct nvmm_type gennvm = { .erase_blk = gennvm_erase_blk, .get_lun = gennvm_get_lun, - .free_blocks_print = gennvm_free_blocks_print, + .lun_info_print = gennvm_lun_info_print, }; static int __init gennvm_module_init(void) diff --git a/drivers/lightnvm/gennvm.h b/drivers/lightnvm/gennvm.h index d23bd3501ddc..9c24b5b32dac 100644 --- a/drivers/lightnvm/gennvm.h +++ b/drivers/lightnvm/gennvm.h @@ -35,6 +35,8 @@ struct gen_lun { }; struct gen_nvm { + struct nvm_dev *dev; + int nr_luns; struct gen_lun *luns; }; diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c index 7ba64c87ba1c..75e59c3a3f96 100644 --- a/drivers/lightnvm/rrpc.c +++ b/drivers/lightnvm/rrpc.c @@ -123,12 +123,42 @@ static u64 block_to_addr(struct rrpc *rrpc, struct rrpc_block *rblk) return blk->id * rrpc->dev->pgs_per_blk; } +static struct ppa_addr linear_to_generic_addr(struct nvm_dev *dev, + struct ppa_addr r) +{ + struct ppa_addr l; + int secs, pgs, blks, luns; + sector_t ppa = r.ppa; + + l.ppa = 0; + + div_u64_rem(ppa, dev->sec_per_pg, &secs); + l.g.sec = secs; + + sector_div(ppa, dev->sec_per_pg); + div_u64_rem(ppa, dev->sec_per_blk, &pgs); + l.g.pg = pgs; + + sector_div(ppa, dev->pgs_per_blk); + div_u64_rem(ppa, dev->blks_per_lun, &blks); + l.g.blk = blks; + + sector_div(ppa, dev->blks_per_lun); + div_u64_rem(ppa, dev->luns_per_chnl, &luns); + l.g.lun = luns; + + sector_div(ppa, dev->luns_per_chnl); + l.g.ch = ppa; + + return l; +} + static struct ppa_addr rrpc_ppa_to_gaddr(struct nvm_dev *dev, u64 addr) { struct ppa_addr paddr; paddr.ppa = addr; - return __linear_to_generic_addr(dev, paddr); + return linear_to_generic_addr(dev, paddr); } /* requires lun->lock taken */ diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 917d47e290ae..3147c8d09ea8 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -112,7 +112,8 @@ struct iv_tcw_private { * and encrypts / decrypts at the same time. */ enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID, - DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD }; + DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD, + DM_CRYPT_EXIT_THREAD}; /* * The fields in here must be read only after initialization. @@ -1203,20 +1204,18 @@ continue_locked: if (!RB_EMPTY_ROOT(&cc->write_tree)) goto pop_from_list; + if (unlikely(test_bit(DM_CRYPT_EXIT_THREAD, &cc->flags))) { + spin_unlock_irq(&cc->write_thread_wait.lock); + break; + } + __set_current_state(TASK_INTERRUPTIBLE); __add_wait_queue(&cc->write_thread_wait, &wait); spin_unlock_irq(&cc->write_thread_wait.lock); - if (unlikely(kthread_should_stop())) { - set_task_state(current, TASK_RUNNING); - remove_wait_queue(&cc->write_thread_wait, &wait); - break; - } - schedule(); - set_task_state(current, TASK_RUNNING); spin_lock_irq(&cc->write_thread_wait.lock); __remove_wait_queue(&cc->write_thread_wait, &wait); goto continue_locked; @@ -1531,8 +1530,13 @@ static void crypt_dtr(struct dm_target *ti) if (!cc) return; - if (cc->write_thread) + if (cc->write_thread) { + spin_lock_irq(&cc->write_thread_wait.lock); + set_bit(DM_CRYPT_EXIT_THREAD, &cc->flags); + wake_up_locked(&cc->write_thread_wait); + spin_unlock_irq(&cc->write_thread_wait.lock); kthread_stop(cc->write_thread); + } if (cc->io_queue) destroy_workqueue(cc->io_queue); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index aaa6caa46a9f..cfa29f574c2a 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1537,32 +1537,34 @@ static int multipath_prepare_ioctl(struct dm_target *ti, struct block_device **bdev, fmode_t *mode) { struct multipath *m = ti->private; - struct pgpath *pgpath; unsigned long flags; int r; - r = 0; - spin_lock_irqsave(&m->lock, flags); if (!m->current_pgpath) __choose_pgpath(m, 0); - pgpath = m->current_pgpath; - - if (pgpath) { - *bdev = pgpath->path.dev->bdev; - *mode = pgpath->path.dev->mode; + if (m->current_pgpath) { + if (!m->queue_io) { + *bdev = m->current_pgpath->path.dev->bdev; + *mode = m->current_pgpath->path.dev->mode; + r = 0; + } else { + /* pg_init has not started or completed */ + r = -ENOTCONN; + } + } else { + /* No path is available */ + if (m->queue_if_no_path) + r = -ENOTCONN; + else + r = -EIO; } - if ((pgpath && m->queue_io) || (!pgpath && m->queue_if_no_path)) - r = -ENOTCONN; - else if (!*bdev) - r = -EIO; - spin_unlock_irqrestore(&m->lock, flags); - if (r == -ENOTCONN && !fatal_signal_pending(current)) { + if (r == -ENOTCONN) { spin_lock_irqsave(&m->lock, flags); if (!m->current_pg) { /* Path status changed, redo selection */ diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 3897b90bd462..63903a5a5d9e 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2432,6 +2432,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) case PM_WRITE: if (old_mode != new_mode) notify_of_pool_mode_change(pool, "write"); + pool->pf.error_if_no_space = pt->requested_pf.error_if_no_space; dm_pool_metadata_read_write(pool->pmd); pool->process_bio = process_bio; pool->process_discard = process_discard_bio; @@ -4249,10 +4250,9 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct thin_c *tc = ti->private; struct pool *pool = tc->pool; - struct queue_limits *pool_limits = dm_get_queue_limits(pool->pool_md); - if (!pool_limits->discard_granularity) - return; /* pool's discard support is disabled */ + if (!pool->pf.discard_enabled) + return; limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT; limits->max_discard_sectors = 2048 * 1024 * 16; /* 16G */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 6e15f3565892..5df40480228b 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -591,7 +591,7 @@ retry: out: dm_put_live_table(md, *srcu_idx); - if (r == -ENOTCONN) { + if (r == -ENOTCONN && !fatal_signal_pending(current)) { msleep(10); goto retry; } @@ -603,9 +603,10 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, { struct mapped_device *md = bdev->bd_disk->private_data; struct dm_target *tgt; + struct block_device *tgt_bdev = NULL; int srcu_idx, r; - r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + r = dm_get_live_table_for_ioctl(md, &tgt, &tgt_bdev, &mode, &srcu_idx); if (r < 0) return r; @@ -620,7 +621,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, goto out; } - r = __blkdev_driver_ioctl(bdev, mode, cmd, arg); + r = __blkdev_driver_ioctl(tgt_bdev, mode, cmd, arg); out: dm_put_live_table(md, srcu_idx); return r; diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c index e0b7b95813bc..9202d1a468d0 100644 --- a/drivers/nvme/host/lightnvm.c +++ b/drivers/nvme/host/lightnvm.c @@ -93,7 +93,7 @@ struct nvme_nvm_l2ptbl { __le16 cdw14[6]; }; -struct nvme_nvm_bbtbl { +struct nvme_nvm_getbbtbl { __u8 opcode; __u8 flags; __u16 command_id; @@ -101,10 +101,23 @@ struct nvme_nvm_bbtbl { __u64 rsvd[2]; __le64 prp1; __le64 prp2; - __le32 prp1_len; - __le32 prp2_len; - __le32 lbb; - __u32 rsvd11[3]; + __le64 spba; + __u32 rsvd4[4]; +}; + +struct nvme_nvm_setbbtbl { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __le64 rsvd[2]; + __le64 prp1; + __le64 prp2; + __le64 spba; + __le16 nlb; + __u8 value; + __u8 rsvd3; + __u32 rsvd4[3]; }; struct nvme_nvm_erase_blk { @@ -129,8 +142,8 @@ struct nvme_nvm_command { struct nvme_nvm_hb_rw hb_rw; struct nvme_nvm_ph_rw ph_rw; struct nvme_nvm_l2ptbl l2p; - struct nvme_nvm_bbtbl get_bb; - struct nvme_nvm_bbtbl set_bb; + struct nvme_nvm_getbbtbl get_bb; + struct nvme_nvm_setbbtbl set_bb; struct nvme_nvm_erase_blk erase; }; }; @@ -142,11 +155,13 @@ struct nvme_nvm_id_group { __u8 num_ch; __u8 num_lun; __u8 num_pln; + __u8 rsvd1; __le16 num_blk; __le16 num_pg; __le16 fpg_sz; __le16 csecs; __le16 sos; + __le16 rsvd2; __le32 trdt; __le32 trdm; __le32 tprt; @@ -154,8 +169,9 @@ struct nvme_nvm_id_group { __le32 tbet; __le32 tbem; __le32 mpos; + __le32 mccap; __le16 cpar; - __u8 reserved[913]; + __u8 reserved[906]; } __packed; struct nvme_nvm_addr_format { @@ -178,15 +194,28 @@ struct nvme_nvm_id { __u8 ver_id; __u8 vmnt; __u8 cgrps; - __u8 res[5]; + __u8 res; __le32 cap; __le32 dom; struct nvme_nvm_addr_format ppaf; - __u8 ppat; - __u8 resv[223]; + __u8 resv[228]; struct nvme_nvm_id_group groups[4]; } __packed; +struct nvme_nvm_bb_tbl { + __u8 tblid[4]; + __le16 verid; + __le16 revid; + __le32 rvsd1; + __le32 tblks; + __le32 tfact; + __le32 tgrown; + __le32 tdresv; + __le32 thresv; + __le32 rsvd2[8]; + __u8 blk[0]; +}; + /* * Check we didn't inadvertently grow the command struct */ @@ -195,12 +224,14 @@ static inline void _nvme_nvm_check_size(void) BUILD_BUG_ON(sizeof(struct nvme_nvm_identity) != 64); BUILD_BUG_ON(sizeof(struct nvme_nvm_hb_rw) != 64); BUILD_BUG_ON(sizeof(struct nvme_nvm_ph_rw) != 64); - BUILD_BUG_ON(sizeof(struct nvme_nvm_bbtbl) != 64); + BUILD_BUG_ON(sizeof(struct nvme_nvm_getbbtbl) != 64); + BUILD_BUG_ON(sizeof(struct nvme_nvm_setbbtbl) != 64); BUILD_BUG_ON(sizeof(struct nvme_nvm_l2ptbl) != 64); BUILD_BUG_ON(sizeof(struct nvme_nvm_erase_blk) != 64); BUILD_BUG_ON(sizeof(struct nvme_nvm_id_group) != 960); BUILD_BUG_ON(sizeof(struct nvme_nvm_addr_format) != 128); BUILD_BUG_ON(sizeof(struct nvme_nvm_id) != 4096); + BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 512); } static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id) @@ -234,6 +265,7 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id) dst->tbet = le32_to_cpu(src->tbet); dst->tbem = le32_to_cpu(src->tbem); dst->mpos = le32_to_cpu(src->mpos); + dst->mccap = le32_to_cpu(src->mccap); dst->cpar = le16_to_cpu(src->cpar); } @@ -244,6 +276,7 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id) static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id) { struct nvme_ns *ns = q->queuedata; + struct nvme_dev *dev = ns->dev; struct nvme_nvm_id *nvme_nvm_id; struct nvme_nvm_command c = {}; int ret; @@ -256,8 +289,8 @@ static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id) if (!nvme_nvm_id) return -ENOMEM; - ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c, nvme_nvm_id, - sizeof(struct nvme_nvm_id)); + ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c, + nvme_nvm_id, sizeof(struct nvme_nvm_id)); if (ret) { ret = -EIO; goto out; @@ -268,6 +301,8 @@ static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id) nvm_id->cgrps = nvme_nvm_id->cgrps; nvm_id->cap = le32_to_cpu(nvme_nvm_id->cap); nvm_id->dom = le32_to_cpu(nvme_nvm_id->dom); + memcpy(&nvm_id->ppaf, &nvme_nvm_id->ppaf, + sizeof(struct nvme_nvm_addr_format)); ret = init_grps(nvm_id, nvme_nvm_id); out: @@ -281,7 +316,7 @@ static int nvme_nvm_get_l2p_tbl(struct request_queue *q, u64 slba, u32 nlb, struct nvme_ns *ns = q->queuedata; struct nvme_dev *dev = ns->dev; struct nvme_nvm_command c = {}; - u32 len = queue_max_hw_sectors(q) << 9; + u32 len = queue_max_hw_sectors(dev->admin_q) << 9; u32 nlb_pr_rq = len / sizeof(u64); u64 cmd_slba = slba; void *entries; @@ -299,8 +334,8 @@ static int nvme_nvm_get_l2p_tbl(struct request_queue *q, u64 slba, u32 nlb, c.l2p.slba = cpu_to_le64(cmd_slba); c.l2p.nlb = cpu_to_le32(cmd_nlb); - ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c, - entries, len); + ret = nvme_submit_sync_cmd(dev->admin_q, + (struct nvme_command *)&c, entries, len); if (ret) { dev_err(dev->dev, "L2P table transfer failed (%d)\n", ret); @@ -322,43 +357,82 @@ out: return ret; } -static int nvme_nvm_get_bb_tbl(struct request_queue *q, int lunid, - unsigned int nr_blocks, - nvm_bb_update_fn *update_bbtbl, void *priv) +static int nvme_nvm_get_bb_tbl(struct request_queue *q, struct ppa_addr ppa, + int nr_blocks, nvm_bb_update_fn *update_bbtbl, + void *priv) { struct nvme_ns *ns = q->queuedata; struct nvme_dev *dev = ns->dev; struct nvme_nvm_command c = {}; - void *bb_bitmap; - u16 bb_bitmap_size; + struct nvme_nvm_bb_tbl *bb_tbl; + int tblsz = sizeof(struct nvme_nvm_bb_tbl) + nr_blocks; int ret = 0; c.get_bb.opcode = nvme_nvm_admin_get_bb_tbl; c.get_bb.nsid = cpu_to_le32(ns->ns_id); - c.get_bb.lbb = cpu_to_le32(lunid); - bb_bitmap_size = ((nr_blocks >> 15) + 1) * PAGE_SIZE; - bb_bitmap = kmalloc(bb_bitmap_size, GFP_KERNEL); - if (!bb_bitmap) - return -ENOMEM; + c.get_bb.spba = cpu_to_le64(ppa.ppa); - bitmap_zero(bb_bitmap, nr_blocks); + bb_tbl = kzalloc(tblsz, GFP_KERNEL); + if (!bb_tbl) + return -ENOMEM; - ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c, bb_bitmap, - bb_bitmap_size); + ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c, + bb_tbl, tblsz); if (ret) { dev_err(dev->dev, "get bad block table failed (%d)\n", ret); ret = -EIO; goto out; } - ret = update_bbtbl(lunid, bb_bitmap, nr_blocks, priv); + if (bb_tbl->tblid[0] != 'B' || bb_tbl->tblid[1] != 'B' || + bb_tbl->tblid[2] != 'L' || bb_tbl->tblid[3] != 'T') { + dev_err(dev->dev, "bbt format mismatch\n"); + ret = -EINVAL; + goto out; + } + + if (le16_to_cpu(bb_tbl->verid) != 1) { + ret = -EINVAL; + dev_err(dev->dev, "bbt version not supported\n"); + goto out; + } + + if (le32_to_cpu(bb_tbl->tblks) != nr_blocks) { + ret = -EINVAL; + dev_err(dev->dev, "bbt unsuspected blocks returned (%u!=%u)", + le32_to_cpu(bb_tbl->tblks), nr_blocks); + goto out; + } + + ret = update_bbtbl(ppa, nr_blocks, bb_tbl->blk, priv); if (ret) { ret = -EINTR; goto out; } out: - kfree(bb_bitmap); + kfree(bb_tbl); + return ret; +} + +static int nvme_nvm_set_bb_tbl(struct request_queue *q, struct nvm_rq *rqd, + int type) +{ + struct nvme_ns *ns = q->queuedata; + struct nvme_dev *dev = ns->dev; + struct nvme_nvm_command c = {}; + int ret = 0; + + c.set_bb.opcode = nvme_nvm_admin_set_bb_tbl; + c.set_bb.nsid = cpu_to_le32(ns->ns_id); + c.set_bb.spba = cpu_to_le64(rqd->ppa_addr.ppa); + c.set_bb.nlb = cpu_to_le16(rqd->nr_pages - 1); + c.set_bb.value = type; + + ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c, + NULL, 0); + if (ret) + dev_err(dev->dev, "set bad block table failed (%d)\n", ret); return ret; } @@ -474,6 +548,7 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = { .get_l2p_tbl = nvme_nvm_get_l2p_tbl, .get_bb_tbl = nvme_nvm_get_bb_tbl, + .set_bb_tbl = nvme_nvm_set_bb_tbl, .submit_io = nvme_nvm_submit_io, .erase_block = nvme_nvm_erase_block, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 8187df204695..f3b53af789ef 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -896,19 +896,28 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, goto retry_cmd; } if (blk_integrity_rq(req)) { - if (blk_rq_count_integrity_sg(req->q, req->bio) != 1) + if (blk_rq_count_integrity_sg(req->q, req->bio) != 1) { + dma_unmap_sg(dev->dev, iod->sg, iod->nents, + dma_dir); goto error_cmd; + } sg_init_table(iod->meta_sg, 1); if (blk_rq_map_integrity_sg( - req->q, req->bio, iod->meta_sg) != 1) + req->q, req->bio, iod->meta_sg) != 1) { + dma_unmap_sg(dev->dev, iod->sg, iod->nents, + dma_dir); goto error_cmd; + } if (rq_data_dir(req)) nvme_dif_remap(req, nvme_dif_prep); - if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir)) + if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir)) { + dma_unmap_sg(dev->dev, iod->sg, iod->nents, + dma_dir); goto error_cmd; + } } } @@ -968,7 +977,8 @@ static void __nvme_process_cq(struct nvme_queue *nvmeq, unsigned int *tag) if (head == nvmeq->cq_head && phase == nvmeq->cq_phase) return; - writel(head, nvmeq->q_db + nvmeq->dev->db_stride); + if (likely(nvmeq->cq_vector >= 0)) + writel(head, nvmeq->q_db + nvmeq->dev->db_stride); nvmeq->cq_head = head; nvmeq->cq_phase = phase; @@ -1727,9 +1737,13 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) u32 aqa; u64 cap = lo_hi_readq(&dev->bar->cap); struct nvme_queue *nvmeq; - unsigned page_shift = PAGE_SHIFT; + /* + * default to a 4K page size, with the intention to update this + * path in the future to accomodate architectures with differing + * kernel and IO page sizes. + */ + unsigned page_shift = 12; unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12; - unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12; if (page_shift < dev_page_min) { dev_err(dev->dev, @@ -1738,13 +1752,6 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) 1 << page_shift); return -ENODEV; } - if (page_shift > dev_page_max) { - dev_info(dev->dev, - "Device maximum page size (%u) smaller than " - "host (%u); enabling work-around\n", - 1 << dev_page_max, 1 << page_shift); - page_shift = dev_page_max; - } dev->subsystem = readl(&dev->bar->vs) >= NVME_VS(1, 1) ? NVME_CAP_NSSRC(cap) : 0; @@ -2268,7 +2275,7 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid) if (dev->max_hw_sectors) { blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors); blk_queue_max_segments(ns->queue, - ((dev->max_hw_sectors << 9) / dev->page_size) + 1); + (dev->max_hw_sectors / (dev->page_size >> 9)) + 1); } if (dev->stripe_size) blk_queue_chunk_sectors(ns->queue, dev->stripe_size >> 9); @@ -2787,6 +2794,10 @@ static void nvme_del_queue_end(struct nvme_queue *nvmeq) { struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx; nvme_put_dq(dq); + + spin_lock_irq(&nvmeq->q_lock); + nvme_process_cq(nvmeq); + spin_unlock_irq(&nvmeq->q_lock); } static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8 opcode, diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 9c747cb14ad8..d2f41477f8ae 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -342,10 +342,10 @@ int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, struct irq_phys_map *map, bool level); void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg); int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); -int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu); struct irq_phys_map *kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, int virt_irq, int irq); int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map); +bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, struct irq_phys_map *map); #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) #define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5706a2108f0a..c923350ca20a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -460,6 +460,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ idx++) +static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) +{ + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) + if (vcpu->vcpu_id == id) + return vcpu; + return NULL; +} + #define kvm_for_each_memslot(memslot, slots) \ for (memslot = &slots->memslots[0]; \ memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\ diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 69c9057e1ab8..3db5552b17d5 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -58,7 +58,6 @@ enum { struct nvm_id_group { u8 mtype; u8 fmtype; - u16 res16; u8 num_ch; u8 num_lun; u8 num_pln; @@ -74,9 +73,9 @@ struct nvm_id_group { u32 tbet; u32 tbem; u32 mpos; + u32 mccap; u16 cpar; - u8 res[913]; -} __packed; +}; struct nvm_addr_format { u8 ch_offset; @@ -91,19 +90,15 @@ struct nvm_addr_format { u8 pg_len; u8 sect_offset; u8 sect_len; - u8 res[4]; }; struct nvm_id { u8 ver_id; u8 vmnt; u8 cgrps; - u8 res[5]; u32 cap; u32 dom; struct nvm_addr_format ppaf; - u8 ppat; - u8 resv[224]; struct nvm_id_group groups[4]; } __packed; @@ -123,39 +118,28 @@ struct nvm_tgt_instance { #define NVM_VERSION_MINOR 0 #define NVM_VERSION_PATCH 0 -#define NVM_SEC_BITS (8) -#define NVM_PL_BITS (6) -#define NVM_PG_BITS (16) #define NVM_BLK_BITS (16) -#define NVM_LUN_BITS (10) +#define NVM_PG_BITS (16) +#define NVM_SEC_BITS (8) +#define NVM_PL_BITS (8) +#define NVM_LUN_BITS (8) #define NVM_CH_BITS (8) struct ppa_addr { + /* Generic structure for all addresses */ union { - /* Channel-based PPA format in nand 4x2x2x2x8x10 */ - struct { - u64 ch : 4; - u64 sec : 2; /* 4 sectors per page */ - u64 pl : 2; /* 4 planes per LUN */ - u64 lun : 2; /* 4 LUNs per channel */ - u64 pg : 8; /* 256 pages per block */ - u64 blk : 10;/* 1024 blocks per plane */ - u64 resved : 36; - } chnl; - - /* Generic structure for all addresses */ struct { + u64 blk : NVM_BLK_BITS; + u64 pg : NVM_PG_BITS; u64 sec : NVM_SEC_BITS; u64 pl : NVM_PL_BITS; - u64 pg : NVM_PG_BITS; - u64 blk : NVM_BLK_BITS; u64 lun : NVM_LUN_BITS; u64 ch : NVM_CH_BITS; } g; u64 ppa; }; -} __packed; +}; struct nvm_rq { struct nvm_tgt_instance *ins; @@ -191,11 +175,11 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata) struct nvm_block; typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *); -typedef int (nvm_bb_update_fn)(u32, void *, unsigned int, void *); +typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *); typedef int (nvm_id_fn)(struct request_queue *, struct nvm_id *); typedef int (nvm_get_l2p_tbl_fn)(struct request_queue *, u64, u32, nvm_l2p_update_fn *, void *); -typedef int (nvm_op_bb_tbl_fn)(struct request_queue *, int, unsigned int, +typedef int (nvm_op_bb_tbl_fn)(struct request_queue *, struct ppa_addr, int, nvm_bb_update_fn *, void *); typedef int (nvm_op_set_bb_fn)(struct request_queue *, struct nvm_rq *, int); typedef int (nvm_submit_io_fn)(struct request_queue *, struct nvm_rq *); @@ -210,7 +194,7 @@ struct nvm_dev_ops { nvm_id_fn *identity; nvm_get_l2p_tbl_fn *get_l2p_tbl; nvm_op_bb_tbl_fn *get_bb_tbl; - nvm_op_set_bb_fn *set_bb; + nvm_op_set_bb_fn *set_bb_tbl; nvm_submit_io_fn *submit_io; nvm_erase_blk_fn *erase_block; @@ -220,7 +204,7 @@ struct nvm_dev_ops { nvm_dev_dma_alloc_fn *dev_dma_alloc; nvm_dev_dma_free_fn *dev_dma_free; - uint8_t max_phys_sect; + unsigned int max_phys_sect; }; struct nvm_lun { @@ -229,7 +213,9 @@ struct nvm_lun { int lun_id; int chnl_id; + unsigned int nr_inuse_blocks; /* Number of used blocks */ unsigned int nr_free_blocks; /* Number of unused blocks */ + unsigned int nr_bad_blocks; /* Number of bad blocks */ struct nvm_block *blocks; spinlock_t lock; @@ -263,8 +249,7 @@ struct nvm_dev { int blks_per_lun; int sec_size; int oob_size; - int addr_mode; - struct nvm_addr_format addr_format; + struct nvm_addr_format ppaf; /* Calculated/Cached values. These do not reflect the actual usable * blocks at run-time. @@ -290,118 +275,45 @@ struct nvm_dev { char name[DISK_NAME_LEN]; }; -/* fallback conversion */ -static struct ppa_addr __generic_to_linear_addr(struct nvm_dev *dev, - struct ppa_addr r) -{ - struct ppa_addr l; - - l.ppa = r.g.sec + - r.g.pg * dev->sec_per_pg + - r.g.blk * (dev->pgs_per_blk * - dev->sec_per_pg) + - r.g.lun * (dev->blks_per_lun * - dev->pgs_per_blk * - dev->sec_per_pg) + - r.g.ch * (dev->blks_per_lun * - dev->pgs_per_blk * - dev->luns_per_chnl * - dev->sec_per_pg); - - return l; -} - -/* fallback conversion */ -static struct ppa_addr __linear_to_generic_addr(struct nvm_dev *dev, - struct ppa_addr r) +static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev, + struct ppa_addr r) { struct ppa_addr l; - int secs, pgs, blks, luns; - sector_t ppa = r.ppa; - l.ppa = 0; - - div_u64_rem(ppa, dev->sec_per_pg, &secs); - l.g.sec = secs; - - sector_div(ppa, dev->sec_per_pg); - div_u64_rem(ppa, dev->sec_per_blk, &pgs); - l.g.pg = pgs; - - sector_div(ppa, dev->pgs_per_blk); - div_u64_rem(ppa, dev->blks_per_lun, &blks); - l.g.blk = blks; - - sector_div(ppa, dev->blks_per_lun); - div_u64_rem(ppa, dev->luns_per_chnl, &luns); - l.g.lun = luns; - - sector_div(ppa, dev->luns_per_chnl); - l.g.ch = ppa; + l.ppa = ((u64)r.g.blk) << dev->ppaf.blk_offset; + l.ppa |= ((u64)r.g.pg) << dev->ppaf.pg_offset; + l.ppa |= ((u64)r.g.sec) << dev->ppaf.sect_offset; + l.ppa |= ((u64)r.g.pl) << dev->ppaf.pln_offset; + l.ppa |= ((u64)r.g.lun) << dev->ppaf.lun_offset; + l.ppa |= ((u64)r.g.ch) << dev->ppaf.ch_offset; return l; } -static struct ppa_addr __generic_to_chnl_addr(struct ppa_addr r) +static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev, + struct ppa_addr r) { struct ppa_addr l; - l.ppa = 0; - - l.chnl.sec = r.g.sec; - l.chnl.pl = r.g.pl; - l.chnl.pg = r.g.pg; - l.chnl.blk = r.g.blk; - l.chnl.lun = r.g.lun; - l.chnl.ch = r.g.ch; - - return l; -} - -static struct ppa_addr __chnl_to_generic_addr(struct ppa_addr r) -{ - struct ppa_addr l; - - l.ppa = 0; - - l.g.sec = r.chnl.sec; - l.g.pl = r.chnl.pl; - l.g.pg = r.chnl.pg; - l.g.blk = r.chnl.blk; - l.g.lun = r.chnl.lun; - l.g.ch = r.chnl.ch; + /* + * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc. + */ + l.g.blk = (r.ppa >> dev->ppaf.blk_offset) & + (((1 << dev->ppaf.blk_len) - 1)); + l.g.pg |= (r.ppa >> dev->ppaf.pg_offset) & + (((1 << dev->ppaf.pg_len) - 1)); + l.g.sec |= (r.ppa >> dev->ppaf.sect_offset) & + (((1 << dev->ppaf.sect_len) - 1)); + l.g.pl |= (r.ppa >> dev->ppaf.pln_offset) & + (((1 << dev->ppaf.pln_len) - 1)); + l.g.lun |= (r.ppa >> dev->ppaf.lun_offset) & + (((1 << dev->ppaf.lun_len) - 1)); + l.g.ch |= (r.ppa >> dev->ppaf.ch_offset) & + (((1 << dev->ppaf.ch_len) - 1)); return l; } -static inline struct ppa_addr addr_to_generic_mode(struct nvm_dev *dev, - struct ppa_addr gppa) -{ - switch (dev->addr_mode) { - case NVM_ADDRMODE_LINEAR: - return __linear_to_generic_addr(dev, gppa); - case NVM_ADDRMODE_CHANNEL: - return __chnl_to_generic_addr(gppa); - default: - BUG(); - } - return gppa; -} - -static inline struct ppa_addr generic_to_addr_mode(struct nvm_dev *dev, - struct ppa_addr gppa) -{ - switch (dev->addr_mode) { - case NVM_ADDRMODE_LINEAR: - return __generic_to_linear_addr(dev, gppa); - case NVM_ADDRMODE_CHANNEL: - return __generic_to_chnl_addr(gppa); - default: - BUG(); - } - return gppa; -} - static inline int ppa_empty(struct ppa_addr ppa_addr) { return (ppa_addr.ppa == ADDR_EMPTY); @@ -468,7 +380,7 @@ typedef int (nvmm_end_io_fn)(struct nvm_rq *, int); typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, unsigned long); typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int); -typedef void (nvmm_free_blocks_print_fn)(struct nvm_dev *); +typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *); struct nvmm_type { const char *name; @@ -492,7 +404,7 @@ struct nvmm_type { nvmm_get_lun_fn *get_lun; /* Statistics */ - nvmm_free_blocks_print_fn *free_blocks_print; + nvmm_lun_info_print_fn *lun_info_print; struct list_head list; }; diff --git a/kernel/pid.c b/kernel/pid.c index ca368793808e..78b3d9f80d44 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -467,7 +467,7 @@ struct pid *get_task_pid(struct task_struct *task, enum pid_type type) rcu_read_lock(); if (type != PIDTYPE_PID) task = task->group_leader; - pid = get_pid(task->pids[type].pid); + pid = get_pid(rcu_dereference(task->pids[type].pid)); rcu_read_unlock(); return pid; } @@ -528,7 +528,7 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, if (likely(pid_alive(task))) { if (type != PIDTYPE_PID) task = task->group_leader; - nr = pid_nr_ns(task->pids[type].pid, ns); + nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns); } rcu_read_unlock(); diff --git a/tools/testing/selftests/futex/README b/tools/testing/selftests/futex/README index 3224a049b196..0558bb9ce0a6 100644 --- a/tools/testing/selftests/futex/README +++ b/tools/testing/selftests/futex/README @@ -27,7 +27,7 @@ o The build system shall remain as simple as possible, avoiding any archive or o Where possible, any helper functions or other package-wide code shall be implemented in header files, avoiding the need to compile intermediate object files. -o External dependendencies shall remain as minimal as possible. Currently gcc +o External dependencies shall remain as minimal as possible. Currently gcc and glibc are the only dependencies. o Tests return 0 for success and < 0 for failure. diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index e38cc54942db..882fe83a3554 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -492,6 +492,9 @@ TEST_SIGNAL(KILL_one_arg_six, SIGSYS) pid_t parent = getppid(); int fd; void *map1, *map2; + int page_size = sysconf(_SC_PAGESIZE); + + ASSERT_LT(0, page_size); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); ASSERT_EQ(0, ret); @@ -504,16 +507,16 @@ TEST_SIGNAL(KILL_one_arg_six, SIGSYS) EXPECT_EQ(parent, syscall(__NR_getppid)); map1 = (void *)syscall(sysno, - NULL, PAGE_SIZE, PROT_READ, MAP_PRIVATE, fd, PAGE_SIZE); + NULL, page_size, PROT_READ, MAP_PRIVATE, fd, page_size); EXPECT_NE(MAP_FAILED, map1); /* mmap2() should never return. */ map2 = (void *)syscall(sysno, - NULL, PAGE_SIZE, PROT_READ, MAP_PRIVATE, fd, 0x0C0FFEE); + NULL, page_size, PROT_READ, MAP_PRIVATE, fd, 0x0C0FFEE); EXPECT_EQ(MAP_FAILED, map2); /* The test failed, so clean up the resources. */ - munmap(map1, PAGE_SIZE); - munmap(map2, PAGE_SIZE); + munmap(map1, page_size); + munmap(map2, page_size); close(fd); } diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 21a0ab2d8919..69bca185c471 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -221,17 +221,23 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) kvm_timer_update_state(vcpu); /* - * If we enter the guest with the virtual input level to the VGIC - * asserted, then we have already told the VGIC what we need to, and - * we don't need to exit from the guest until the guest deactivates - * the already injected interrupt, so therefore we should set the - * hardware active state to prevent unnecessary exits from the guest. - * - * Conversely, if the virtual input level is deasserted, then always - * clear the hardware active state to ensure that hardware interrupts - * from the timer triggers a guest exit. - */ - if (timer->irq.level) + * If we enter the guest with the virtual input level to the VGIC + * asserted, then we have already told the VGIC what we need to, and + * we don't need to exit from the guest until the guest deactivates + * the already injected interrupt, so therefore we should set the + * hardware active state to prevent unnecessary exits from the guest. + * + * Also, if we enter the guest with the virtual timer interrupt active, + * then it must be active on the physical distributor, because we set + * the HW bit and the guest must be able to deactivate the virtual and + * physical interrupt at the same time. + * + * Conversely, if the virtual input level is deasserted and the virtual + * interrupt is not active, then always clear the hardware active state + * to ensure that hardware interrupts from the timer triggers a guest + * exit. + */ + if (timer->irq.level || kvm_vgic_map_is_active(vcpu, timer->map)) phys_active = true; else phys_active = false; diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 533538385d5d..65461f821a75 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -1096,6 +1096,27 @@ static void vgic_retire_lr(int lr_nr, struct kvm_vcpu *vcpu) vgic_set_lr(vcpu, lr_nr, vlr); } +static bool dist_active_irq(struct kvm_vcpu *vcpu) +{ + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + + return test_bit(vcpu->vcpu_id, dist->irq_active_on_cpu); +} + +bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, struct irq_phys_map *map) +{ + int i; + + for (i = 0; i < vcpu->arch.vgic_cpu.nr_lr; i++) { + struct vgic_lr vlr = vgic_get_lr(vcpu, i); + + if (vlr.irq == map->virt_irq && vlr.state & LR_STATE_ACTIVE) + return true; + } + + return dist_active_irq(vcpu); +} + /* * An interrupt may have been disabled after being made pending on the * CPU interface (the classic case is a timer running while we're @@ -1248,7 +1269,7 @@ static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) * may have been serviced from another vcpu. In all cases, * move along. */ - if (!kvm_vgic_vcpu_pending_irq(vcpu) && !kvm_vgic_vcpu_active_irq(vcpu)) + if (!kvm_vgic_vcpu_pending_irq(vcpu) && !dist_active_irq(vcpu)) goto epilog; /* SGIs */ @@ -1396,25 +1417,13 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu) static bool vgic_sync_hwirq(struct kvm_vcpu *vcpu, int lr, struct vgic_lr vlr) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - struct irq_phys_map *map; - bool phys_active; bool level_pending; - int ret; if (!(vlr.state & LR_HW)) return false; - map = vgic_irq_map_search(vcpu, vlr.irq); - BUG_ON(!map); - - ret = irq_get_irqchip_state(map->irq, - IRQCHIP_STATE_ACTIVE, - &phys_active); - - WARN_ON(ret); - - if (phys_active) - return 0; + if (vlr.state & LR_STATE_ACTIVE) + return false; spin_lock(&dist->lock); level_pending = process_queued_irq(vcpu, lr, vlr); @@ -1479,17 +1488,6 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu); } -int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - if (!irqchip_in_kernel(vcpu->kvm)) - return 0; - - return test_bit(vcpu->vcpu_id, dist->irq_active_on_cpu); -} - - void vgic_kick_vcpus(struct kvm *kvm) { struct kvm_vcpu *vcpu; |