diff options
Diffstat (limited to 'arch')
42 files changed, 463 insertions, 190 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 1aafb4efbb51..d789a89cb32c 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -937,9 +937,6 @@ config STRICT_MODULE_RWX and non-text memory will be made non-executable. This provides protection against certain security exploits (e.g. writing to text) -config ARCH_WANT_RELAX_ORDER - bool - config ARCH_HAS_REFCOUNT bool help diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index 903f3bf48419..7e25c5cc353a 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -155,14 +155,16 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, return __cmpxchg_small(ptr, old, new, size); case 4: - return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, old, new); + return __cmpxchg_asm("ll", "sc", (volatile u32 *)ptr, + (u32)old, new); case 8: /* lld/scd are only available for MIPS64 */ if (!IS_ENABLED(CONFIG_64BIT)) return __cmpxchg_called_with_bad_pointer(); - return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, old, new); + return __cmpxchg_asm("lld", "scd", (volatile u64 *)ptr, + (u64)old, new); default: return __cmpxchg_called_with_bad_pointer(); diff --git a/arch/mips/loongson32/common/platform.c b/arch/mips/loongson32/common/platform.c index 100f23dfa438..ac584c5823d0 100644 --- a/arch/mips/loongson32/common/platform.c +++ b/arch/mips/loongson32/common/platform.c @@ -183,18 +183,20 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv) } static struct plat_stmmacenet_data ls1x_eth0_pdata = { - .bus_id = 0, - .phy_addr = -1, + .bus_id = 0, + .phy_addr = -1, #if defined(CONFIG_LOONGSON1_LS1B) - .interface = PHY_INTERFACE_MODE_MII, + .interface = PHY_INTERFACE_MODE_MII, #elif defined(CONFIG_LOONGSON1_LS1C) - .interface = PHY_INTERFACE_MODE_RMII, + .interface = PHY_INTERFACE_MODE_RMII, #endif - .mdio_bus_data = &ls1x_mdio_bus_data, - .dma_cfg = &ls1x_eth_dma_cfg, - .has_gmac = 1, - .tx_coe = 1, - .init = ls1x_eth_mux_init, + .mdio_bus_data = &ls1x_mdio_bus_data, + .dma_cfg = &ls1x_eth_dma_cfg, + .has_gmac = 1, + .tx_coe = 1, + .rx_queues_to_use = 1, + .tx_queues_to_use = 1, + .init = ls1x_eth_mux_init, }; static struct resource ls1x_eth0_resources[] = { @@ -222,14 +224,16 @@ struct platform_device ls1x_eth0_pdev = { #ifdef CONFIG_LOONGSON1_LS1B static struct plat_stmmacenet_data ls1x_eth1_pdata = { - .bus_id = 1, - .phy_addr = -1, - .interface = PHY_INTERFACE_MODE_MII, - .mdio_bus_data = &ls1x_mdio_bus_data, - .dma_cfg = &ls1x_eth_dma_cfg, - .has_gmac = 1, - .tx_coe = 1, - .init = ls1x_eth_mux_init, + .bus_id = 1, + .phy_addr = -1, + .interface = PHY_INTERFACE_MODE_MII, + .mdio_bus_data = &ls1x_mdio_bus_data, + .dma_cfg = &ls1x_eth_dma_cfg, + .has_gmac = 1, + .tx_coe = 1, + .rx_queues_to_use = 1, + .tx_queues_to_use = 1, + .init = ls1x_eth_mux_init, }; static struct resource ls1x_eth1_resources[] = { diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 192542dbd972..16d9ef5a78c5 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -2558,7 +2558,6 @@ dcopuop: break; default: /* Reserved R6 ops */ - pr_err("Reserved MIPS R6 CMP.condn.S operation\n"); return SIGILL; } } @@ -2719,7 +2718,6 @@ dcopuop: break; default: /* Reserved R6 ops */ - pr_err("Reserved MIPS R6 CMP.condn.D operation\n"); return SIGILL; } } diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 7646891c4e9b..01b7a87ea678 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -667,7 +667,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, { int src, dst, r, td, ts, mem_off, b_off; bool need_swap, did_move, cmp_eq; - unsigned int target; + unsigned int target = 0; u64 t64; s64 t64s; int bpf_op = BPF_OP(insn->code); diff --git a/arch/mips/tools/generic-board-config.sh b/arch/mips/tools/generic-board-config.sh index 5c4f93687039..654d652d7fa1 100755 --- a/arch/mips/tools/generic-board-config.sh +++ b/arch/mips/tools/generic-board-config.sh @@ -30,8 +30,6 @@ cfg="$4" boards_origin="$5" shift 5 -cd "${srctree}" - # Only print Skipping... lines if the user explicitly specified BOARDS=. In the # general case it only serves to obscure the useful output about what actually # was included. @@ -48,7 +46,7 @@ environment*) esac for board in $@; do - board_cfg="arch/mips/configs/generic/board-${board}.config" + board_cfg="${srctree}/arch/mips/configs/generic/board-${board}.config" if [ ! -f "${board_cfg}" ]; then echo "WARNING: Board config '${board_cfg}' not found" continue @@ -84,7 +82,7 @@ for board in $@; do done || continue # Merge this board config fragment into our final config file - ./scripts/kconfig/merge_config.sh \ + ${srctree}/scripts/kconfig/merge_config.sh \ -m -O ${objtree} ${cfg} ${board_cfg} \ | grep -Ev '^(#|Using)' done diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 48da0f5d2f7f..b82586c53560 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -734,7 +734,29 @@ EXC_REAL(program_check, 0x700, 0x100) EXC_VIRT(program_check, 0x4700, 0x100, 0x700) TRAMP_KVM(PACA_EXGEN, 0x700) EXC_COMMON_BEGIN(program_check_common) - EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) + /* + * It's possible to receive a TM Bad Thing type program check with + * userspace register values (in particular r1), but with SRR1 reporting + * that we came from the kernel. Normally that would confuse the bad + * stack logic, and we would report a bad kernel stack pointer. Instead + * we switch to the emergency stack if we're taking a TM Bad Thing from + * the kernel. + */ + li r10,MSR_PR /* Build a mask of MSR_PR .. */ + oris r10,r10,0x200000@h /* .. and SRR1_PROGTM */ + and r10,r10,r12 /* Mask SRR1 with that. */ + srdi r10,r10,8 /* Shift it so we can compare */ + cmpldi r10,(0x200000 >> 8) /* .. with an immediate. */ + bne 1f /* If != go to normal path. */ + + /* SRR1 had PR=0 and SRR1_PROGTM=1, so use the emergency stack */ + andi. r10,r12,MSR_PR; /* Set CR0 correctly for label */ + /* 3 in EXCEPTION_PROLOG_COMMON */ + mr r10,r1 /* Save r1 */ + ld r1,PACAEMERGSP(r13) /* Use emergency stack */ + subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ + b 3f /* Jump into the macro !! */ +1: EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) addi r3,r1,STACK_FRAME_OVERHEAD diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index c83c115858c1..b2c002993d78 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -452,9 +452,20 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, if (MSR_TM_RESV(msr)) return -EINVAL; - /* pull in MSR TM from user context */ + /* pull in MSR TS bits from user context */ regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); + /* + * Ensure that TM is enabled in regs->msr before we leave the signal + * handler. It could be the case that (a) user disabled the TM bit + * through the manipulation of the MSR bits in uc_mcontext or (b) the + * TM bit was disabled because a sufficient number of context switches + * happened whilst in the signal handler and load_tm overflowed, + * disabling the TM bit. In either case we can end up with an illegal + * TM state leading to a TM Bad Thing when we return to userspace. + */ + regs->msr |= MSR_TM; + /* pull in MSR LE from user context */ regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S index c98e90b4ea7b..b4e2b7165f79 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S @@ -181,34 +181,25 @@ _GLOBAL(ftrace_stub) * - we have no stack frame and can not allocate one * - LR points back to the original caller (in A) * - CTR holds the new NIP in C - * - r0 & r12 are free - * - * r0 can't be used as the base register for a DS-form load or store, so - * we temporarily shuffle r1 (stack pointer) into r0 and then put it back. + * - r0, r11 & r12 are free */ livepatch_handler: CURRENT_THREAD_INFO(r12, r1) - /* Save stack pointer into r0 */ - mr r0, r1 - /* Allocate 3 x 8 bytes */ - ld r1, TI_livepatch_sp(r12) - addi r1, r1, 24 - std r1, TI_livepatch_sp(r12) + ld r11, TI_livepatch_sp(r12) + addi r11, r11, 24 + std r11, TI_livepatch_sp(r12) /* Save toc & real LR on livepatch stack */ - std r2, -24(r1) + std r2, -24(r11) mflr r12 - std r12, -16(r1) + std r12, -16(r11) /* Store stack end marker */ lis r12, STACK_END_MAGIC@h ori r12, r12, STACK_END_MAGIC@l - std r12, -8(r1) - - /* Restore real stack pointer */ - mr r1, r0 + std r12, -8(r11) /* Put ctr in r12 for global entry and branch there */ mfctr r12 @@ -216,36 +207,30 @@ livepatch_handler: /* * Now we are returning from the patched function to the original - * caller A. We are free to use r0 and r12, and we can use r2 until we + * caller A. We are free to use r11, r12 and we can use r2 until we * restore it. */ CURRENT_THREAD_INFO(r12, r1) - /* Save stack pointer into r0 */ - mr r0, r1 - - ld r1, TI_livepatch_sp(r12) + ld r11, TI_livepatch_sp(r12) /* Check stack marker hasn't been trashed */ lis r2, STACK_END_MAGIC@h ori r2, r2, STACK_END_MAGIC@l - ld r12, -8(r1) + ld r12, -8(r11) 1: tdne r12, r2 EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0 /* Restore LR & toc from livepatch stack */ - ld r12, -16(r1) + ld r12, -16(r11) mtlr r12 - ld r2, -24(r1) + ld r2, -24(r11) /* Pop livepatch stack frame */ - CURRENT_THREAD_INFO(r12, r0) - subi r1, r1, 24 - std r1, TI_livepatch_sp(r12) - - /* Restore real stack pointer */ - mr r1, r0 + CURRENT_THREAD_INFO(r12, r1) + subi r11, r11, 24 + std r11, TI_livepatch_sp(r12) /* Return to original caller of live patched function */ blr diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 8f2da8bba737..4dffa611376d 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -478,28 +478,30 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, return ret; dir = iommu_tce_direction(tce); + + idx = srcu_read_lock(&vcpu->kvm->srcu); + if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm, - tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL)) - return H_PARAMETER; + tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL)) { + ret = H_PARAMETER; + goto unlock_exit; + } entry = ioba >> stt->page_shift; list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { - if (dir == DMA_NONE) { + if (dir == DMA_NONE) ret = kvmppc_tce_iommu_unmap(vcpu->kvm, stit->tbl, entry); - } else { - idx = srcu_read_lock(&vcpu->kvm->srcu); + else ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl, entry, ua, dir); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - } if (ret == H_SUCCESS) continue; if (ret == H_TOO_HARD) - return ret; + goto unlock_exit; WARN_ON_ONCE(1); kvmppc_clear_tce(stit->tbl, entry); @@ -507,7 +509,10 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, kvmppc_tce_put(stt, entry, tce); - return H_SUCCESS; +unlock_exit: + srcu_read_unlock(&vcpu->kvm->srcu, idx); + + return ret; } EXPORT_SYMBOL_GPL(kvmppc_h_put_tce); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index ec69fa45d5a2..42639fba89e8 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -989,13 +989,14 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) beq no_xive ld r11, VCPU_XIVE_SAVED_STATE(r4) li r9, TM_QW1_OS - stdcix r11,r9,r10 eieio + stdcix r11,r9,r10 lwz r11, VCPU_XIVE_CAM_WORD(r4) li r9, TM_QW1_OS + TM_WORD2 stwcix r11,r9,r10 li r9, 1 stw r9, VCPU_XIVE_PUSHED(r4) + eieio no_xive: #endif /* CONFIG_KVM_XICS */ @@ -1310,6 +1311,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) bne 3f BEGIN_FTR_SECTION PPC_MSGSYNC + lwsync END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) lbz r0, HSTATE_HOST_IPI(r13) cmpwi r0, 0 @@ -1400,8 +1402,8 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ cmpldi cr0, r10, 0 beq 1f /* First load to pull the context, we ignore the value */ - lwzx r11, r7, r10 eieio + lwzx r11, r7, r10 /* Second load to recover the context state (Words 0 and 1) */ ldx r11, r6, r10 b 3f @@ -1409,8 +1411,8 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ cmpldi cr0, r10, 0 beq 1f /* First load to pull the context, we ignore the value */ - lwzcix r11, r7, r10 eieio + lwzcix r11, r7, r10 /* Second load to recover the context state (Words 0 and 1) */ ldcix r11, r6, r10 3: std r11, VCPU_XIVE_SAVED_STATE(r9) @@ -1420,6 +1422,7 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ stw r10, VCPU_XIVE_PUSHED(r9) stb r10, (VCPU_XIVE_SAVED_STATE+3)(r9) stb r0, (VCPU_XIVE_SAVED_STATE+4)(r9) + eieio 1: #endif /* CONFIG_KVM_XICS */ /* Save more register state */ @@ -2788,6 +2791,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) PPC_MSGCLR(6) /* see if it's a host IPI */ li r3, 1 +BEGIN_FTR_SECTION + PPC_MSGSYNC + lwsync +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) lbz r0, HSTATE_HOST_IPI(r13) cmpwi r0, 0 bnelr diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 3480faaf1ef8..ee279c7f4802 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -644,8 +644,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; #endif case KVM_CAP_PPC_HTM: - r = cpu_has_feature(CPU_FTR_TM_COMP) && - is_kvmppc_hv_enabled(kvm); + r = cpu_has_feature(CPU_FTR_TM_COMP) && hv_enabled; break; default: r = 0; diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 5e8418c28bd8..f208f560aecd 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -1684,11 +1684,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, * Logical instructions */ case 26: /* cntlzw */ - op->val = __builtin_clz((unsigned int) regs->gpr[rd]); + val = (unsigned int) regs->gpr[rd]; + op->val = ( val ? __builtin_clz(val) : 32 ); goto logical_done; #ifdef __powerpc64__ case 58: /* cntlzd */ - op->val = __builtin_clzl(regs->gpr[rd]); + val = regs->gpr[rd]; + op->val = ( val ? __builtin_clzl(val) : 64 ); goto logical_done; #endif case 28: /* and */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b95c584ce19d..a51df9ef529d 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1438,7 +1438,6 @@ out: int arch_update_cpu_topology(void) { - lockdep_assert_cpus_held(); return numa_update_cpu_topology(true); } diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 9ccac86f3463..88126245881b 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -399,6 +399,20 @@ static void nest_imc_counters_release(struct perf_event *event) /* Take the mutex lock for this node and then decrement the reference count */ mutex_lock(&ref->lock); + if (ref->refc == 0) { + /* + * The scenario where this is true is, when perf session is + * started, followed by offlining of all cpus in a given node. + * + * In the cpuhotplug offline path, ppc_nest_imc_cpu_offline() + * function set the ref->count to zero, if the cpu which is + * about to offline is the last cpu in a given node and make + * an OPAL call to disable the engine in that node. + * + */ + mutex_unlock(&ref->lock); + return; + } ref->refc--; if (ref->refc == 0) { rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, @@ -523,8 +537,8 @@ static int core_imc_mem_init(int cpu, int size) /* We need only vbase for core counters */ mem_info->vbase = page_address(alloc_pages_node(phys_id, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - get_order(size))); + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | + __GFP_NOWARN, get_order(size))); if (!mem_info->vbase) return -ENOMEM; @@ -646,6 +660,20 @@ static void core_imc_counters_release(struct perf_event *event) return; mutex_lock(&ref->lock); + if (ref->refc == 0) { + /* + * The scenario where this is true is, when perf session is + * started, followed by offlining of all cpus in a given core. + * + * In the cpuhotplug offline path, ppc_core_imc_cpu_offline() + * function set the ref->count to zero, if the cpu which is + * about to offline is the last cpu in a given core and make + * an OPAL call to disable the engine in that core. + * + */ + mutex_unlock(&ref->lock); + return; + } ref->refc--; if (ref->refc == 0) { rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, @@ -763,8 +791,8 @@ static int thread_imc_mem_alloc(int cpu_id, int size) * free the memory in cpu offline path. */ local_mem = page_address(alloc_pages_node(phys_id, - GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, - get_order(size))); + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE | + __GFP_NOWARN, get_order(size))); if (!local_mem) return -ENOMEM; @@ -1148,7 +1176,8 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) } /* Only free the attr_groups which are dynamically allocated */ - kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs); + if (pmu_ptr->attr_groups[IMC_EVENT_ATTR]) + kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs); kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]); kfree(pmu_ptr); return; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 0be3828752e5..4e83f950713e 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -44,7 +44,6 @@ config SPARC select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS select LOCKDEP_SMALL if LOCKDEP - select ARCH_WANT_RELAX_ORDER config SPARC32 def_bool !64BIT diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 8a13d468635a..50e0d2bc4528 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -176,7 +176,7 @@ /* * This is a sneaky trick to help the unwinder find pt_regs on the stack. The * frame pointer is replaced with an encoded pointer to pt_regs. The encoding - * is just setting the LSB, which makes it an invalid stack address and is also + * is just clearing the MSB, which makes it an invalid stack address and is also * a signal to the unwinder that it's a pt_regs pointer in disguise. * * NOTE: This macro must be used *after* SAVE_ALL because it corrupts the @@ -185,7 +185,7 @@ .macro ENCODE_FRAME_POINTER #ifdef CONFIG_FRAME_POINTER mov %esp, %ebp - orl $0x1, %ebp + andl $0x7fffffff, %ebp #endif .endm diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 1c5390f1cf09..d45e06346f14 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -822,7 +822,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) pmus[i].type = type; pmus[i].boxes = kzalloc(size, GFP_KERNEL); if (!pmus[i].boxes) - return -ENOMEM; + goto err; } type->pmus = pmus; @@ -836,7 +836,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) + sizeof(*attr_group), GFP_KERNEL); if (!attr_group) - return -ENOMEM; + goto err; attrs = (struct attribute **)(attr_group + 1); attr_group->name = "events"; @@ -849,7 +849,15 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) } type->pmu_group = &uncore_pmu_attr_group; + return 0; + +err: + for (i = 0; i < type->num_boxes; i++) + kfree(pmus[i].boxes); + kfree(pmus); + + return -ENOMEM; } static int __init diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 1a8eb550c40f..a5db63f728a2 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -85,6 +85,8 @@ EXPORT_SYMBOL_GPL(hyperv_cs); u32 *hv_vp_index; EXPORT_SYMBOL_GPL(hv_vp_index); +u32 hv_max_vp_index; + static int hv_cpu_init(unsigned int cpu) { u64 msr_vp_index; @@ -93,6 +95,9 @@ static int hv_cpu_init(unsigned int cpu) hv_vp_index[smp_processor_id()] = msr_vp_index; + if (msr_vp_index > hv_max_vp_index) + hv_max_vp_index = msr_vp_index; + return 0; } diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 39e7f6e50919..9cc9e1c1e2db 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -36,9 +36,9 @@ struct hv_flush_pcpu_ex { /* Each gva in gva_list encodes up to 4096 pages to flush */ #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE) -static struct hv_flush_pcpu __percpu *pcpu_flush; +static struct hv_flush_pcpu __percpu **pcpu_flush; -static struct hv_flush_pcpu_ex __percpu *pcpu_flush_ex; +static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex; /* * Fills in gva_list starting from offset. Returns the number of items added. @@ -76,6 +76,18 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, { int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; + /* valid_bank_mask can represent up to 64 banks */ + if (hv_max_vp_index / 64 >= 64) + return 0; + + /* + * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex + * structs are not cleared between calls, we risk flushing unneeded + * vCPUs otherwise. + */ + for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++) + flush->hv_vp_set.bank_contents[vcpu_bank] = 0; + /* * Some banks may end up being empty but this is acceptable. */ @@ -83,11 +95,6 @@ static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, vcpu = hv_cpu_number_to_vp_number(cpu); vcpu_bank = vcpu / 64; vcpu_offset = vcpu % 64; - - /* valid_bank_mask can represent up to 64 banks */ - if (vcpu_bank >= 64) - return 0; - __set_bit(vcpu_offset, (unsigned long *) &flush->hv_vp_set.bank_contents[vcpu_bank]); if (vcpu_bank >= nr_bank) @@ -102,6 +109,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, const struct flush_tlb_info *info) { int cpu, vcpu, gva_n, max_gvas; + struct hv_flush_pcpu **flush_pcpu; struct hv_flush_pcpu *flush; u64 status = U64_MAX; unsigned long flags; @@ -116,7 +124,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, local_irq_save(flags); - flush = this_cpu_ptr(pcpu_flush); + flush_pcpu = this_cpu_ptr(pcpu_flush); + + if (unlikely(!*flush_pcpu)) + *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + + flush = *flush_pcpu; + + if (unlikely(!flush)) { + local_irq_restore(flags); + goto do_native; + } if (info->mm) { flush->address_space = virt_to_phys(info->mm->pgd); @@ -173,6 +191,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, const struct flush_tlb_info *info) { int nr_bank = 0, max_gvas, gva_n; + struct hv_flush_pcpu_ex **flush_pcpu; struct hv_flush_pcpu_ex *flush; u64 status = U64_MAX; unsigned long flags; @@ -187,7 +206,17 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, local_irq_save(flags); - flush = this_cpu_ptr(pcpu_flush_ex); + flush_pcpu = this_cpu_ptr(pcpu_flush_ex); + + if (unlikely(!*flush_pcpu)) + *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + + flush = *flush_pcpu; + + if (unlikely(!flush)) { + local_irq_restore(flags); + goto do_native; + } if (info->mm) { flush->address_space = virt_to_phys(info->mm->pgd); @@ -222,18 +251,18 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY; status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, - 0, nr_bank + 2, flush, NULL); + 0, nr_bank, flush, NULL); } else if (info->end && ((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) { status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX, - 0, nr_bank + 2, flush, NULL); + 0, nr_bank, flush, NULL); } else { gva_n = fill_gva_list(flush->gva_list, nr_bank, info->start, info->end); status = hv_do_rep_hypercall( HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX, - gva_n, nr_bank + 2, flush, NULL); + gva_n, nr_bank, flush, NULL); } local_irq_restore(flags); @@ -266,7 +295,7 @@ void hyper_alloc_mmu(void) return; if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - pcpu_flush = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); + pcpu_flush = alloc_percpu(struct hv_flush_pcpu *); else - pcpu_flush_ex = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); + pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *); } diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index e7636bac7372..6c98821fef5e 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -62,8 +62,10 @@ #define new_len2 145f-144f /* - * max without conditionals. Idea adapted from: + * gas compatible max based on the idea from: * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax + * + * The additional "-" is needed because gas uses a "true" value of -1. */ #define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index c096624137ae..ccbe24e697c4 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -103,12 +103,12 @@ static inline int alternatives_text_reserved(void *start, void *end) alt_end_marker ":\n" /* - * max without conditionals. Idea adapted from: + * gas compatible max based on the idea from: * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax * - * The additional "-" is needed because gas works with s32s. + * The additional "-" is needed because gas uses a "true" value of -1. */ -#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") - (" b ")))))" +#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))" /* * Pad the second replacement alternative with additional NOPs if it is diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 181264989db5..8edac1de2e35 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -187,7 +187,6 @@ struct mca_msr_regs { extern struct mce_vendor_flags mce_flags; -extern struct mca_config mca_cfg; extern struct mca_msr_regs msr_ops; enum mce_notifier_prios { diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index c120b5db178a..3c856a15b98e 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -126,13 +126,7 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) DEBUG_LOCKS_WARN_ON(preemptible()); } -static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ - int cpu = smp_processor_id(); - - if (cpumask_test_cpu(cpu, mm_cpumask(mm))) - cpumask_clear_cpu(cpu, mm_cpumask(mm)); -} +void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 738503e1f80c..530f448fddaf 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -289,6 +289,7 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, * to this information. */ extern u32 *hv_vp_index; +extern u32 hv_max_vp_index; /** * hv_cpu_number_to_vp_number() - Map CPU to VP. diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 4893abf7f74f..d362161d3291 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -83,6 +83,13 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) #endif /* + * If tlb_use_lazy_mode is true, then we try to avoid switching CR3 to point + * to init_mm when we switch to a kernel thread (e.g. the idle thread). If + * it's false, then we immediately switch CR3 when entering a kernel thread. + */ +DECLARE_STATIC_KEY_TRUE(tlb_use_lazy_mode); + +/* * 6 because 6 should be plenty and struct tlb_state will fit in * two cache lines. */ @@ -105,6 +112,23 @@ struct tlb_state { u16 next_asid; /* + * We can be in one of several states: + * + * - Actively using an mm. Our CPU's bit will be set in + * mm_cpumask(loaded_mm) and is_lazy == false; + * + * - Not using a real mm. loaded_mm == &init_mm. Our CPU's bit + * will not be set in mm_cpumask(&init_mm) and is_lazy == false. + * + * - Lazily using a real mm. loaded_mm != &init_mm, our bit + * is set in mm_cpumask(loaded_mm), but is_lazy == true. + * We're heuristically guessing that the CR3 load we + * skipped more than makes up for the overhead added by + * lazy mode. + */ + bool is_lazy; + + /* * Access to this CR4 shadow and to H/W CR4 is protected by * disabling interrupts when modifying either one. */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index d705c769f77d..ff891772c9f8 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -573,11 +573,21 @@ static u32 bdx_deadline_rev(void) return ~0U; } +static u32 skx_deadline_rev(void) +{ + switch (boot_cpu_data.x86_mask) { + case 0x03: return 0x01000136; + case 0x04: return 0x02000014; + } + + return ~0U; +} + static const struct x86_cpu_id deadline_match[] = { DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev), - DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_X, 0x02000014), + DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X, skx_deadline_rev), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE, 0x22), DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT, 0x20), @@ -600,7 +610,8 @@ static void apic_check_deadline_errata(void) const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || + boot_cpu_has(X86_FEATURE_HYPERVISOR)) return; m = x86_match_cpu(deadline_match); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 098530a93bb7..debb974fd17d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -1,3 +1,6 @@ +#ifndef __X86_MCE_INTERNAL_H__ +#define __X86_MCE_INTERNAL_H__ + #include <linux/device.h> #include <asm/mce.h> @@ -108,3 +111,7 @@ static inline void mce_work_trigger(void) { } static inline void mce_register_injector_chain(struct notifier_block *nb) { } static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } #endif + +extern struct mca_config mca_cfg; + +#endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 40e28ed77fbf..486f640b02ef 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -28,6 +28,8 @@ #include <asm/msr.h> #include <asm/trace/irq_vectors.h> +#include "mce-internal.h" + #define NR_BLOCKS 5 #define THRESHOLD_MAX 0xFFF #define INT_TYPE_APIC 0x00020000 diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 86e8f0b2537b..c4fa4a85d4cb 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -122,9 +122,6 @@ static bool __init check_loader_disabled_bsp(void) bool *res = &dis_ucode_ldr; #endif - if (!have_cpuid_p()) - return *res; - /* * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not * completely accurate as xen pv guests don't see that CPUID bit set but @@ -166,24 +163,36 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name) void __init load_ucode_bsp(void) { unsigned int cpuid_1_eax; + bool intel = true; - if (check_loader_disabled_bsp()) + if (!have_cpuid_p()) return; cpuid_1_eax = native_cpuid_eax(1); switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (x86_family(cpuid_1_eax) >= 6) - load_ucode_intel_bsp(); + if (x86_family(cpuid_1_eax) < 6) + return; break; + case X86_VENDOR_AMD: - if (x86_family(cpuid_1_eax) >= 0x10) - load_ucode_amd_bsp(cpuid_1_eax); + if (x86_family(cpuid_1_eax) < 0x10) + return; + intel = false; break; + default: - break; + return; } + + if (check_loader_disabled_bsp()) + return; + + if (intel) + load_ucode_intel_bsp(); + else + load_ucode_amd_bsp(cpuid_1_eax); } static bool check_loader_disabled_ap(void) diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index db2182d63ed0..3fc0f9a794cb 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -3,6 +3,15 @@ /* Kprobes and Optprobes common header */ +#include <asm/asm.h> + +#ifdef CONFIG_FRAME_POINTER +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" \ + " mov %" _ASM_SP ", %" _ASM_BP "\n" +#else +# define SAVE_RBP_STRING " push %" _ASM_BP "\n" +#endif + #ifdef CONFIG_X86_64 #define SAVE_REGS_STRING \ /* Skip cs, ip, orig_ax. */ \ @@ -17,7 +26,7 @@ " pushq %r10\n" \ " pushq %r11\n" \ " pushq %rbx\n" \ - " pushq %rbp\n" \ + SAVE_RBP_STRING \ " pushq %r12\n" \ " pushq %r13\n" \ " pushq %r14\n" \ @@ -48,7 +57,7 @@ " pushl %es\n" \ " pushl %ds\n" \ " pushl %eax\n" \ - " pushl %ebp\n" \ + SAVE_RBP_STRING \ " pushl %edi\n" \ " pushl %esi\n" \ " pushl %edx\n" \ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index f0153714ddac..0742491cbb73 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1080,8 +1080,6 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) * raw stack chunk with redzones: */ __memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr)); - regs->flags &= ~X86_EFLAGS_IF; - trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); /* diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d88967659098..5b609e28ce3f 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -79,7 +79,7 @@ static void kvm_get_wallclock(struct timespec *now) static int kvm_set_wallclock(const struct timespec *now) { - return -1; + return -ENODEV; } static u64 kvm_clock_read(void) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 54180fa6f66f..add33f600531 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -105,6 +105,10 @@ void __noreturn machine_real_restart(unsigned int type) load_cr3(initial_page_table); #else write_cr3(real_mode_header->trampoline_pgd); + + /* Exiting long mode will fail if CR4.PCIDE is set. */ + if (static_cpu_has(X86_FEATURE_PCID)) + cr4_clear_bits(X86_CR4_PCIDE); #endif /* Jump to the identity-mapped low memory code */ diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index d145a0b1f529..3dc26f95d46e 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -44,7 +44,8 @@ static void unwind_dump(struct unwind_state *state) state->stack_info.type, state->stack_info.next_sp, state->stack_mask, state->graph_idx); - for (sp = state->orig_sp; sp; sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + for (sp = PTR_ALIGN(state->orig_sp, sizeof(long)); sp; + sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { if (get_stack_info(sp, state->task, &stack_info, &visit_mask)) break; @@ -174,6 +175,7 @@ static bool is_last_task_frame(struct unwind_state *state) * This determines if the frame pointer actually contains an encoded pointer to * pt_regs on the stack. See ENCODE_FRAME_POINTER. */ +#ifdef CONFIG_X86_64 static struct pt_regs *decode_frame_pointer(unsigned long *bp) { unsigned long regs = (unsigned long)bp; @@ -183,6 +185,23 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp) return (struct pt_regs *)(regs & ~0x1); } +#else +static struct pt_regs *decode_frame_pointer(unsigned long *bp) +{ + unsigned long regs = (unsigned long)bp; + + if (regs & 0x80000000) + return NULL; + + return (struct pt_regs *)(regs | 0x80000000); +} +#endif + +#ifdef CONFIG_X86_32 +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs) - 2*sizeof(long)) +#else +#define KERNEL_REGS_SIZE (sizeof(struct pt_regs)) +#endif static bool update_stack_state(struct unwind_state *state, unsigned long *next_bp) @@ -202,7 +221,7 @@ static bool update_stack_state(struct unwind_state *state, regs = decode_frame_pointer(next_bp); if (regs) { frame = (unsigned long *)regs; - len = regs_size(regs); + len = KERNEL_REGS_SIZE; state->got_irq = true; } else { frame = next_bp; @@ -226,6 +245,14 @@ static bool update_stack_state(struct unwind_state *state, frame < prev_frame_end) return false; + /* + * On 32-bit with user mode regs, make sure the last two regs are safe + * to access: + */ + if (IS_ENABLED(CONFIG_X86_32) && regs && user_mode(regs) && + !on_stack(info, frame, len + 2*sizeof(long))) + return false; + /* Move state to the next frame: */ if (regs) { state->regs = regs; @@ -328,6 +355,13 @@ bad_address: state->regs->sp < (unsigned long)task_pt_regs(state->task)) goto the_end; + /* + * There are some known frame pointer issues on 32-bit. Disable + * unwinder warnings on 32-bit until it gets objtool support. + */ + if (IS_ENABLED(CONFIG_X86_32)) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 69c5612be786..36c90d631096 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1992,6 +1992,11 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.apic_base | MSR_IA32_APICBASE_BSP); vcpu->arch.pv_eoi.msr_val = 0; apic_update_ppr(apic); + if (vcpu->arch.apicv_active) { + kvm_x86_ops->apicv_post_state_restore(vcpu); + kvm_x86_ops->hwapic_irr_update(vcpu, -1); + kvm_x86_ops->hwapic_isr_update(vcpu, -1); + } vcpu->arch.apic_arb_prio = 0; vcpu->arch.apic_attention = 0; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 106d4a029a8a..7a69cf053711 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3974,19 +3974,19 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte) { /* - * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set - * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means - * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then. - */ - gpte |= level - PT_PAGE_TABLE_LEVEL - 1; - - /* * The RHS has bit 7 set iff level < mmu->last_nonleaf_level. * If it is clear, there are no large pages at this level, so clear * PT_PAGE_SIZE_MASK in gpte if that is the case. */ gpte &= level - mmu->last_nonleaf_level; + /* + * PT_PAGE_TABLE_LEVEL always terminates. The RHS has bit 7 set + * iff level <= PT_PAGE_TABLE_LEVEL, which for our purpose means + * level == PT_PAGE_TABLE_LEVEL; set PT_PAGE_SIZE_MASK in gpte then. + */ + gpte |= level - PT_PAGE_TABLE_LEVEL - 1; + return gpte & PT_PAGE_SIZE_MASK; } @@ -4555,6 +4555,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, update_permission_bitmask(vcpu, context, true); update_pkru_bitmask(vcpu, context, true); + update_last_nonleaf_level(vcpu, context); reset_rsvds_bits_mask_ept(vcpu, context, execonly); reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 86b68dc5a649..f18d1f8d332b 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -334,10 +334,11 @@ retry_walk: --walker->level; index = PT_INDEX(addr, walker->level); - table_gfn = gpte_to_gfn(pte); offset = index * sizeof(pt_element_t); pte_gpa = gfn_to_gpa(table_gfn) + offset; + + BUG_ON(walker->level < 1); walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a2b804e10c95..a6f4f095f8f4 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5619,9 +5619,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - if (kvm_vcpu_apicv_active(vcpu)) - memset(&vmx->pi_desc, 0, sizeof(struct pi_desc)); - if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); @@ -11297,7 +11294,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, /* Same as above - no reason to call set_cr4_guest_host_mask(). */ vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); - kvm_set_cr4(vcpu, vmcs12->host_cr4); + vmx_set_cr4(vcpu, vmcs12->host_cr4); nested_ept_uninit_mmu_context(vcpu); diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 72bf8c01c6e3..e1f095884386 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,5 +1,12 @@ -# Kernel does not boot with instrumentation of tlb.c. -KCOV_INSTRUMENT_tlb.o := n +# Kernel does not boot with instrumentation of tlb.c and mem_encrypt.c +KCOV_INSTRUMENT_tlb.o := n +KCOV_INSTRUMENT_mem_encrypt.o := n + +KASAN_SANITIZE_mem_encrypt.o := n + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_mem_encrypt.o = -pg +endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o physaddr.o setup_nx.o tlb.o diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 49d9778376d7..658bf0090565 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -30,6 +30,8 @@ atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1); +DEFINE_STATIC_KEY_TRUE(tlb_use_lazy_mode); + static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, u16 *new_asid, bool *need_flush) { @@ -80,7 +82,7 @@ void leave_mm(int cpu) return; /* Warn if we're not lazy. */ - WARN_ON(cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))); + WARN_ON(!this_cpu_read(cpu_tlbstate.is_lazy)); switch_mm(NULL, &init_mm, NULL); } @@ -142,45 +144,24 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, __flush_tlb_all(); } #endif + this_cpu_write(cpu_tlbstate.is_lazy, false); if (real_prev == next) { VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != next->context.ctx_id); - if (cpumask_test_cpu(cpu, mm_cpumask(next))) { - /* - * There's nothing to do: we weren't lazy, and we - * aren't changing our mm. We don't need to flush - * anything, nor do we need to update CR3, CR4, or - * LDTR. - */ - return; - } - - /* Resume remote flushes and then read tlb_gen. */ - cpumask_set_cpu(cpu, mm_cpumask(next)); - next_tlb_gen = atomic64_read(&next->context.tlb_gen); - - if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) < - next_tlb_gen) { - /* - * Ideally, we'd have a flush_tlb() variant that - * takes the known CR3 value as input. This would - * be faster on Xen PV and on hypothetical CPUs - * on which INVPCID is fast. - */ - this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen, - next_tlb_gen); - write_cr3(build_cr3(next, prev_asid)); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, - TLB_FLUSH_ALL); - } - /* - * We just exited lazy mode, which means that CR4 and/or LDTR - * may be stale. (Changes to the required CR4 and LDTR states - * are not reflected in tlb_gen.) + * We don't currently support having a real mm loaded without + * our cpu set in mm_cpumask(). We have all the bookkeeping + * in place to figure out whether we would need to flush + * if our cpu were cleared in mm_cpumask(), but we don't + * currently use it. */ + if (WARN_ON_ONCE(real_prev != &init_mm && + !cpumask_test_cpu(cpu, mm_cpumask(next)))) + cpumask_set_cpu(cpu, mm_cpumask(next)); + + return; } else { u16 new_asid; bool need_flush; @@ -199,10 +180,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } /* Stop remote flushes for the previous mm */ - if (cpumask_test_cpu(cpu, mm_cpumask(real_prev))) - cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); - - VM_WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); + VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && + real_prev != &init_mm); + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); /* * Start remote flushes and then read tlb_gen. @@ -233,6 +213,37 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } /* + * enter_lazy_tlb() is a hint from the scheduler that we are entering a + * kernel thread or other context without an mm. Acceptable implementations + * include doing nothing whatsoever, switching to init_mm, or various clever + * lazy tricks to try to minimize TLB flushes. + * + * The scheduler reserves the right to call enter_lazy_tlb() several times + * in a row. It will notify us that we're going back to a real mm by + * calling switch_mm_irqs_off(). + */ +void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ + if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) + return; + + if (static_branch_unlikely(&tlb_use_lazy_mode)) { + /* + * There's a significant optimization that may be possible + * here. We have accurate enough TLB flush tracking that we + * don't need to maintain coherence of TLB per se when we're + * lazy. We do, however, need to maintain coherence of + * paging-structure caches. We could, in principle, leave our + * old mm loaded and only switch to init_mm when + * tlb_remove_page() happens. + */ + this_cpu_write(cpu_tlbstate.is_lazy, true); + } else { + switch_mm(NULL, &init_mm, NULL); + } +} + +/* * Call this when reinitializing a CPU. It fixes the following potential * problems: * @@ -303,16 +314,20 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, /* This code cannot presently handle being reentered. */ VM_WARN_ON(!irqs_disabled()); + if (unlikely(loaded_mm == &init_mm)) + return; + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) != loaded_mm->context.ctx_id); - if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(loaded_mm))) { + if (this_cpu_read(cpu_tlbstate.is_lazy)) { /* - * We're in lazy mode -- don't flush. We can get here on - * remote flushes due to races and on local flushes if a - * kernel thread coincidentally flushes the mm it's lazily - * still using. + * We're in lazy mode. We need to at least flush our + * paging-structure cache to avoid speculatively reading + * garbage into our TLB. Since switching to init_mm is barely + * slower than a minimal flush, just switch to init_mm. */ + switch_mm_irqs_off(NULL, &init_mm, NULL); return; } @@ -611,3 +626,57 @@ static int __init create_tlb_single_page_flush_ceiling(void) return 0; } late_initcall(create_tlb_single_page_flush_ceiling); + +static ssize_t tlblazy_read_file(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + char buf[2]; + + buf[0] = static_branch_likely(&tlb_use_lazy_mode) ? '1' : '0'; + buf[1] = '\n'; + + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t tlblazy_write_file(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + bool val; + + if (kstrtobool_from_user(user_buf, count, &val)) + return -EINVAL; + + if (val) + static_branch_enable(&tlb_use_lazy_mode); + else + static_branch_disable(&tlb_use_lazy_mode); + + return count; +} + +static const struct file_operations fops_tlblazy = { + .read = tlblazy_read_file, + .write = tlblazy_write_file, + .llseek = default_llseek, +}; + +static int __init init_tlb_use_lazy_mode(void) +{ + if (boot_cpu_has(X86_FEATURE_PCID)) { + /* + * Heuristic: with PCID on, switching to and from + * init_mm is reasonably fast, but remote flush IPIs + * as expensive as ever, so turn off lazy TLB mode. + * + * We can't do this in setup_pcid() because static keys + * haven't been initialized yet, and it would blow up + * badly. + */ + static_branch_disable(&tlb_use_lazy_mode); + } + + debugfs_create_file("tlb_use_lazy_mode", S_IRUSR | S_IWUSR, + arch_debugfs_dir, NULL, &fops_tlblazy); + return 0; +} +late_initcall(init_tlb_use_lazy_mode); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 0e7ef69e8531..d669e9d89001 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -93,11 +93,11 @@ int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int), int rc; rc = cpuhp_setup_state_nocalls(CPUHP_XEN_PREPARE, - "x86/xen/hvm_guest:prepare", + "x86/xen/guest:prepare", cpu_up_prepare_cb, cpu_dead_cb); if (rc >= 0) { rc = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, - "x86/xen/hvm_guest:online", + "x86/xen/guest:online", xen_cpu_up_online, NULL); if (rc < 0) cpuhp_remove_state_nocalls(CPUHP_XEN_PREPARE); |