diff options
Diffstat (limited to 'arch')
32 files changed, 291 insertions, 126 deletions
diff --git a/arch/arc/Makefile b/arch/arc/Makefile index d4df6be66d58..85814e74677d 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -66,8 +66,6 @@ endif endif -cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables - # By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok ifeq ($(atleast_gcc48),y) cflags-$(CONFIG_ARC_DW2_UNWIND) += -gdwarf-2 diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index e0efff15a5ae..b9192a653b7e 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -142,7 +142,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, * prelogue is setup (callee regs saved and then fp set and not other * way around */ - pr_warn("CONFIG_ARC_DW2_UNWIND needs to be enabled\n"); + pr_warn_once("CONFIG_ARC_DW2_UNWIND needs to be enabled\n"); return 0; #endif diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 893941ec98dc..f1bde7c4e736 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -263,6 +263,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) kvm_timer_vcpu_terminate(vcpu); kvm_vgic_vcpu_destroy(vcpu); kvm_pmu_vcpu_destroy(vcpu); + kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vcpu); } diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 87e1985f3be8..9d9fd4b9a72e 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -80,12 +80,14 @@ #define APM_CPU_PART_POTENZA 0x000 #define CAVIUM_CPU_PART_THUNDERX 0x0A1 +#define CAVIUM_CPU_PART_THUNDERX_81XX 0x0A2 #define BRCM_CPU_PART_VULCAN 0x516 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) +#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index a307eb6e7fa8..7f94755089e2 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -117,6 +117,8 @@ struct pt_regs { }; u64 orig_x0; u64 syscallno; + u64 orig_addr_limit; + u64 unused; // maintain 16 byte alignment }; #define arch_has_single_step() (1) diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index f8e5d47f0880..2f4ba774488a 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -60,6 +60,7 @@ int main(void) DEFINE(S_PC, offsetof(struct pt_regs, pc)); DEFINE(S_ORIG_X0, offsetof(struct pt_regs, orig_x0)); DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno)); + DEFINE(S_ORIG_ADDR_LIMIT, offsetof(struct pt_regs, orig_addr_limit)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); BLANK(); DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index d42789499f17..af716b65110d 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -98,6 +98,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = { MIDR_RANGE(MIDR_THUNDERX, 0x00, (1 << MIDR_VARIANT_SHIFT) | 1), }, + { + /* Cavium ThunderX, T81 pass 1.0 */ + .desc = "Cavium erratum 27456", + .capability = ARM64_WORKAROUND_CAVIUM_27456, + MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00), + }, #endif { } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 12e8d2bcb3f9..6c3b7345a6c4 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -28,6 +28,7 @@ #include <asm/errno.h> #include <asm/esr.h> #include <asm/irq.h> +#include <asm/memory.h> #include <asm/thread_info.h> #include <asm/unistd.h> @@ -97,7 +98,14 @@ mov x29, xzr // fp pointed to user-space .else add x21, sp, #S_FRAME_SIZE - .endif + get_thread_info tsk + /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */ + ldr x20, [tsk, #TI_ADDR_LIMIT] + str x20, [sp, #S_ORIG_ADDR_LIMIT] + mov x20, #TASK_SIZE_64 + str x20, [tsk, #TI_ADDR_LIMIT] + ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO) + .endif /* \el == 0 */ mrs x22, elr_el1 mrs x23, spsr_el1 stp lr, x21, [sp, #S_LR] @@ -128,6 +136,14 @@ .endm .macro kernel_exit, el + .if \el != 0 + /* Restore the task's original addr_limit. */ + ldr x20, [sp, #S_ORIG_ADDR_LIMIT] + str x20, [tsk, #TI_ADDR_LIMIT] + + /* No need to restore UAO, it will be restored from SPSR_EL1 */ + .endif + ldp x21, x22, [sp, #S_PC] // load ELR, SPSR .if \el == 0 ct_user_enter @@ -406,7 +422,6 @@ el1_irq: bl trace_hardirqs_off #endif - get_thread_info tsk irq_handler #ifdef CONFIG_PREEMPT diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 013e2cbe7924..b1166d1e5955 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -280,7 +280,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, } if (permission_fault(esr) && (addr < USER_DS)) { - if (get_fs() == KERNEL_DS) + /* regs->orig_addr_limit may be 0 if we entered from EL0 */ + if (regs->orig_addr_limit == KERNEL_DS) die("Accessing user space memory with fs=KERNEL_DS", regs, esr); if (!search_exception_tables(regs->pc)) diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index a6b611f1da43..f53816744d60 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -24,7 +24,7 @@ struct mm_struct; struct vm_area_struct; #define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_NO_READ | \ - _CACHE_CACHABLE_NONCOHERENT) + _page_cachable_default) #define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_WRITE | \ _page_cachable_default) #define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_NO_EXEC | \ @@ -476,7 +476,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) pte.pte_low &= (_PAGE_MODIFIED | _PAGE_ACCESSED | _PFNX_MASK); pte.pte_high &= (_PFN_MASK | _CACHE_MASK); pte.pte_low |= pgprot_val(newprot) & ~_PFNX_MASK; - pte.pte_high |= pgprot_val(newprot) & ~_PFN_MASK; + pte.pte_high |= pgprot_val(newprot) & ~(_PFN_MASK | _CACHE_MASK); return pte; } #elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) @@ -491,7 +491,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #else static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { - return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | + (pgprot_val(newprot) & ~_PAGE_CHG_MASK)); } #endif @@ -632,7 +633,8 @@ static inline struct page *pmd_page(pmd_t pmd) static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmd_val(pmd) = (pmd_val(pmd) & _PAGE_CHG_MASK) | pgprot_val(newprot); + pmd_val(pmd) = (pmd_val(pmd) & _PAGE_CHG_MASK) | + (pgprot_val(newprot) & ~_PAGE_CHG_MASK); return pmd; } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 88a5ecaa157b..ab84c89c9e98 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -230,6 +230,7 @@ extern unsigned long __kernel_virt_size; #define KERN_VIRT_SIZE __kernel_virt_size extern struct page *vmemmap; extern unsigned long ioremap_bot; +extern unsigned long pci_io_base; #endif /* __ASSEMBLY__ */ #include <asm/book3s/64/hash.h> diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index b5f73cb5eeb6..d70101e1e25c 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -647,7 +647,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, pci_unlock_rescan_remove(); } } else if (frozen_bus) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data); + eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data); } /* diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 3759df52bd67..a5ae49a2dcc4 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -47,7 +47,6 @@ static int __init pcibios_init(void) printk(KERN_INFO "PCI: Probing PCI hardware\n"); - pci_io_base = ISA_IO_BASE; /* For now, override phys_mem_access_prot. If we need it,g * later, we may move that initialization to each ppc_md */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index e2f12cbcade9..0b93893424f5 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1505,6 +1505,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.regs = regs - 1; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * Clear any transactional state, we're exec()ing. The cause is + * not important as there will never be a recheckpoint so it's not + * user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); +#endif + memset(regs->gpr, 0, sizeof(regs->gpr)); regs->ctr = 0; regs->link = 0; diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index bf8f34a58670..b7019b559ddb 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim) std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) - /* We need to setup MSR for VSX register save instructions. Here we - * also clear the MSR RI since when we do the treclaim, we won't have a - * valid kernel pointer for a while. We clear RI here as it avoids - * adding another mtmsr closer to the treclaim. This makes the region - * maked as non-recoverable wider than it needs to be but it saves on - * inserting another mtmsrd later. - */ + /* We need to setup MSR for VSX register save instructions. */ mfmsr r14 mr r15, r14 ori r15, r15, MSR_FP - li r16, MSR_RI + li r16, 0 ori r16, r16, MSR_EE /* IRQs hard off */ andc r15, r15, r16 oris r15, r15, MSR_VEC@h @@ -176,7 +170,17 @@ dont_backup_fp: 1: tdeqi r6, 0 EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 - /* The moment we treclaim, ALL of our GPRs will switch + /* Clear MSR RI since we are about to change r1, EE is already off. */ + li r4, 0 + mtmsrd r4, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + * + * The moment we treclaim, ALL of our GPRs will switch * to user register state. (FPRs, CCR etc. also!) * Use an sprg and a tm_scratch in the PACA to shuffle. */ @@ -197,6 +201,11 @@ dont_backup_fp: /* Store the PPR in r11 and reset to decent value */ std r11, GPR11(r1) /* Temporary stash */ + + /* Reset MSR RI so we can take SLB faults again */ + li r11, MSR_RI + mtmsrd r11, 1 + mfspr r11, SPRN_PPR HMT_MEDIUM @@ -397,11 +406,6 @@ restore_gprs: ld r5, THREAD_TM_DSCR(r3) ld r6, THREAD_TM_PPR(r3) - /* Clear the MSR RI since we are about to change R1. EE is already off - */ - li r4, 0 - mtmsrd r4, 1 - REST_GPR(0, r7) /* GPR0 */ REST_2GPRS(2, r7) /* GPR2-3 */ REST_GPR(4, r7) /* GPR4 */ @@ -439,10 +443,33 @@ restore_gprs: ld r6, _CCR(r7) mtcr r6 - REST_GPR(1, r7) /* GPR1 */ - REST_GPR(5, r7) /* GPR5-7 */ REST_GPR(6, r7) - ld r7, GPR7(r7) + + /* + * Store r1 and r5 on the stack so that we can access them + * after we clear MSR RI. + */ + + REST_GPR(5, r7) + std r5, -8(r1) + ld r5, GPR1(r7) + std r5, -16(r1) + + REST_GPR(7, r7) + + /* Clear MSR RI since we are about to change r1. EE is already off */ + li r5, 0 + mtmsrd r5, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + */ + + ld r5, -8(r1) + ld r1, -16(r1) /* Commit register state as checkpointed state: */ TRECHKPT diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 5b22ba0b58bc..2971ea18c768 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -922,6 +922,10 @@ void __init hash__early_init_mmu(void) vmemmap = (struct page *)H_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; +#ifdef CONFIG_PCI + pci_io_base = ISA_IO_BASE; +#endif + /* Initialize the MMU Hash table and create the linear mapping * of memory. Has to be done before SLB initialization as this is * currently where the page size encoding is obtained. diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index e58707deef5c..7931e1496f0d 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -328,6 +328,11 @@ void __init radix__early_init_mmu(void) __vmalloc_end = RADIX_VMALLOC_END; vmemmap = (struct page *)RADIX_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; + +#ifdef CONFIG_PCI + pci_io_base = ISA_IO_BASE; +#endif + /* * For now radix also use the same frag size */ diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h index 5e04f3cbd320..8ae236b0f80b 100644 --- a/arch/s390/include/asm/fpu/api.h +++ b/arch/s390/include/asm/fpu/api.h @@ -22,7 +22,7 @@ static inline int test_fp_ctl(u32 fpc) " la %0,0\n" "1:\n" EX_TABLE(0b,1b) - : "=d" (rc), "=d" (orig_fpc) + : "=d" (rc), "=&d" (orig_fpc) : "d" (fpc), "0" (-EINVAL)); return rc; } diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index f20abdb5630a..d14069d4b88d 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2064,12 +2064,5 @@ void s390_reset_system(void) S390_lowcore.program_new_psw.addr = (unsigned long) s390_base_pgm_handler; - /* - * Clear subchannel ID and number to signal new kernel that no CCW or - * SCSI IPL has been done (for kexec and kdump) - */ - S390_lowcore.subchannel_id = 0; - S390_lowcore.subchannel_nr = 0; - do_reset_calls(); } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 33787ee817f0..26ced536005a 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2319,7 +2319,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct stack_frame frame; - const void __user *fp; + const unsigned long __user *fp; if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ @@ -2332,7 +2332,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) return; - fp = (void __user *)regs->bp; + fp = (unsigned long __user *)regs->bp; perf_callchain_store(entry, regs->ip); @@ -2345,16 +2345,17 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs pagefault_disable(); while (entry->nr < entry->max_stack) { unsigned long bytes; + frame.next_frame = NULL; frame.return_address = 0; - if (!access_ok(VERIFY_READ, fp, 16)) + if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2)) break; - bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8); + bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp)); if (bytes != 0) break; - bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8); + bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp)); if (bytes != 0) break; diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile index 3660b2cf245a..06c2baa51814 100644 --- a/arch/x86/events/intel/Makefile +++ b/arch/x86/events/intel/Makefile @@ -1,8 +1,8 @@ obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o cqm.o obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o -obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl.o -intel-rapl-objs := rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl-perf.o +intel-rapl-perf-objs := rapl.o obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel-uncore.o intel-uncore-objs := uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE) += intel-cstate.o diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7c666958a625..9b4f9d3ce465 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -115,6 +115,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -139,6 +143,10 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -182,6 +190,16 @@ struct event_constraint intel_skl_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ + + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc6, 0xf), /* FRONTEND_RETIRED.* */ + EVENT_CONSTRAINT_END }; @@ -250,6 +268,10 @@ static struct event_constraint intel_hsw_event_constraints[] = { /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -264,6 +286,13 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ EVENT_CONSTRAINT_END }; diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index fdcc04020636..7c1c89598688 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -69,29 +69,22 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) } static __always_inline -u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) -{ - u64 delta = rdtsc_ordered() - src->tsc_timestamp; - return pvclock_scale_delta(delta, src->tsc_to_system_mul, - src->tsc_shift); -} - -static __always_inline unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, cycle_t *cycles, u8 *flags) { unsigned version; - cycle_t ret, offset; - u8 ret_flags; + cycle_t offset; + u64 delta; version = src->version; + /* Make the latest version visible */ + smp_rmb(); - offset = pvclock_get_nsec_offset(src); - ret = src->system_time + offset; - ret_flags = src->flags; - - *cycles = ret; - *flags = ret_flags; + delta = rdtsc_ordered() - src->tsc_timestamp; + offset = pvclock_scale_delta(delta, src->tsc_to_system_mul, + src->tsc_shift); + *cycles = src->system_time + offset; + *flags = src->flags; return version; } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index a147e676fc7b..e991d5c8bb3a 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -71,8 +71,8 @@ int amd_cache_northbridges(void) while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL) i++; - if (i == 0) - return 0; + if (!i) + return -ENODEV; nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL); if (!nb) diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 99bfc025111d..06c58ce46762 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -61,11 +61,16 @@ void pvclock_resume(void) u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) { unsigned version; - cycle_t ret; u8 flags; do { - version = __pvclock_read_cycles(src, &ret, &flags); + version = src->version; + /* Make the latest version visible */ + smp_rmb(); + + flags = src->flags; + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); return flags & valid_flags; @@ -80,6 +85,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) do { version = __pvclock_read_cycles(src, &ret, &flags); + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index bbb5b283ff63..a397200281c1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1310,7 +1310,8 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ if (guest_tsc < tsc_deadline) - __delay(tsc_deadline - guest_tsc); + __delay(min(tsc_deadline - guest_tsc, + nsec_to_cycles(vcpu, lapic_timer_advance_ns))); } static void start_apic_timer(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 003618e324ce..64a79f271276 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -6671,7 +6671,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Checks for #GP/#SS exceptions. */ exn = false; - if (is_protmode(vcpu)) { + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is the only check on the memory + * destination for long mode! + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { /* Protected mode: apply checks for segment validity in the * following order: * - segment type check (#GP(0) may be thrown) @@ -6688,17 +6694,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, * execute-only code segment */ exn = ((s.type & 0xa) == 8); - } - if (exn) { - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - if (is_long_mode(vcpu)) { - /* Long mode: #GP(0)/#SS(0) if the memory address is in a - * non-canonical form. This is an only check for long mode. - */ - exn = is_noncanonical_address(*ret); - } else if (is_protmode(vcpu)) { + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. */ exn = (s.unusable != 0); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 902d9da12392..7da5dd2057a9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1244,12 +1244,6 @@ static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); static unsigned long max_tsc_khz; -static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) -{ - return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, - vcpu->arch.virtual_tsc_shift); -} - static u32 adjust_tsc_khz(u32 khz, s32 ppm) { u64 v = (u64)khz * (1000000 + ppm); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 7ce3634ab5fe..a82ca466b62e 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -2,6 +2,7 @@ #define ARCH_X86_KVM_X86_H #include <linux/kvm_host.h> +#include <asm/pvclock.h> #include "kvm_cache_regs.h" #define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL @@ -195,6 +196,12 @@ extern unsigned int lapic_timer_advance_ns; extern struct static_key kvm_no_apic_vcpu; +static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) +{ + return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); +} + /* Same "calling convention" as do_div: * - divide (n << 32) by base * - put result in n diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index b2a4e2a61f6b..3cd69832d7f4 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -396,6 +396,7 @@ int __init pci_acpi_init(void) return -ENODEV; printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n"); + acpi_irq_penalty_init(); pcibios_enable_irq = acpi_pci_irq_enable; pcibios_disable_irq = acpi_pci_irq_disable; x86_init.pci.init_irq = x86_init_noop; diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 009947d419a6..f2b5e6a5cf95 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -19,6 +19,7 @@ #include <asm/mtrr.h> #include <asm/sections.h> #include <asm/suspend.h> +#include <asm/tlbflush.h> /* Defined in hibernate_asm_64.S */ extern asmlinkage __visible int restore_image(void); @@ -28,6 +29,7 @@ extern asmlinkage __visible int restore_image(void); * kernel's text (this value is passed in the image header). */ unsigned long restore_jump_address __visible; +unsigned long jump_address_phys; /* * Value of the cr3 register from before the hibernation (this value is passed @@ -37,7 +39,43 @@ unsigned long restore_cr3 __visible; pgd_t *temp_level4_pgt __visible; -void *relocated_restore_code __visible; +unsigned long relocated_restore_code __visible; + +static int set_up_temporary_text_mapping(void) +{ + pmd_t *pmd; + pud_t *pud; + + /* + * The new mapping only has to cover the page containing the image + * kernel's entry point (jump_address_phys), because the switch over to + * it is carried out by relocated code running from a page allocated + * specifically for this purpose and covered by the identity mapping, so + * the temporary kernel text mapping is only needed for the final jump. + * Moreover, in that mapping the virtual address of the image kernel's + * entry point must be the same as its virtual address in the image + * kernel (restore_jump_address), so the image kernel's + * restore_registers() code doesn't find itself in a different area of + * the virtual address space after switching over to the original page + * tables used by the image kernel. + */ + pud = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!pud) + return -ENOMEM; + + pmd = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!pmd) + return -ENOMEM; + + set_pmd(pmd + pmd_index(restore_jump_address), + __pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC)); + set_pud(pud + pud_index(restore_jump_address), + __pud(__pa(pmd) | _KERNPG_TABLE)); + set_pgd(temp_level4_pgt + pgd_index(restore_jump_address), + __pgd(__pa(pud) | _KERNPG_TABLE)); + + return 0; +} static void *alloc_pgt_page(void *context) { @@ -59,9 +97,10 @@ static int set_up_temporary_mappings(void) if (!temp_level4_pgt) return -ENOMEM; - /* It is safe to reuse the original kernel mapping */ - set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map), - init_level4_pgt[pgd_index(__START_KERNEL_map)]); + /* Prepare a temporary mapping for the kernel text */ + result = set_up_temporary_text_mapping(); + if (result) + return result; /* Set up the direct mapping from scratch */ for (i = 0; i < nr_pfn_mapped; i++) { @@ -78,19 +117,50 @@ static int set_up_temporary_mappings(void) return 0; } +static int relocate_restore_code(void) +{ + pgd_t *pgd; + pud_t *pud; + + relocated_restore_code = get_safe_page(GFP_ATOMIC); + if (!relocated_restore_code) + return -ENOMEM; + + memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE); + + /* Make the page containing the relocated code executable */ + pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code); + pud = pud_offset(pgd, relocated_restore_code); + if (pud_large(*pud)) { + set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); + } else { + pmd_t *pmd = pmd_offset(pud, relocated_restore_code); + + if (pmd_large(*pmd)) { + set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); + } else { + pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code); + + set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); + } + } + __flush_tlb_all(); + + return 0; +} + int swsusp_arch_resume(void) { int error; /* We have got enough memory and from now on we cannot recover */ - if ((error = set_up_temporary_mappings())) + error = set_up_temporary_mappings(); + if (error) return error; - relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC); - if (!relocated_restore_code) - return -ENOMEM; - memcpy(relocated_restore_code, &core_restore_code, - &restore_registers - &core_restore_code); + error = relocate_restore_code(); + if (error) + return error; restore_image(); return 0; @@ -109,11 +179,12 @@ int pfn_is_nosave(unsigned long pfn) struct restore_data_record { unsigned long jump_address; + unsigned long jump_address_phys; unsigned long cr3; unsigned long magic; }; -#define RESTORE_MAGIC 0x0123456789ABCDEFUL +#define RESTORE_MAGIC 0x123456789ABCDEF0UL /** * arch_hibernation_header_save - populate the architecture specific part @@ -126,7 +197,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) if (max_size < sizeof(struct restore_data_record)) return -EOVERFLOW; - rdr->jump_address = restore_jump_address; + rdr->jump_address = (unsigned long)&restore_registers; + rdr->jump_address_phys = __pa_symbol(&restore_registers); rdr->cr3 = restore_cr3; rdr->magic = RESTORE_MAGIC; return 0; @@ -142,6 +214,7 @@ int arch_hibernation_header_restore(void *addr) struct restore_data_record *rdr = addr; restore_jump_address = rdr->jump_address; + jump_address_phys = rdr->jump_address_phys; restore_cr3 = rdr->cr3; return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL; } diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 4400a43b9e28..3177c2bc26f6 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -44,9 +44,6 @@ ENTRY(swsusp_arch_suspend) pushfq popq pt_regs_flags(%rax) - /* save the address of restore_registers */ - movq $restore_registers, %rax - movq %rax, restore_jump_address(%rip) /* save cr3 */ movq %cr3, %rax movq %rax, restore_cr3(%rip) @@ -57,31 +54,34 @@ ENTRY(swsusp_arch_suspend) ENDPROC(swsusp_arch_suspend) ENTRY(restore_image) - /* switch to temporary page tables */ - movq $__PAGE_OFFSET, %rdx - movq temp_level4_pgt(%rip), %rax - subq %rdx, %rax - movq %rax, %cr3 - /* Flush TLB */ - movq mmu_cr4_features(%rip), %rax - movq %rax, %rdx - andq $~(X86_CR4_PGE), %rdx - movq %rdx, %cr4; # turn off PGE - movq %cr3, %rcx; # flush TLB - movq %rcx, %cr3; - movq %rax, %cr4; # turn PGE back on - /* prepare to jump to the image kernel */ - movq restore_jump_address(%rip), %rax - movq restore_cr3(%rip), %rbx + movq restore_jump_address(%rip), %r8 + movq restore_cr3(%rip), %r9 + + /* prepare to switch to temporary page tables */ + movq temp_level4_pgt(%rip), %rax + movq mmu_cr4_features(%rip), %rbx /* prepare to copy image data to their original locations */ movq restore_pblist(%rip), %rdx + + /* jump to relocated restore code */ movq relocated_restore_code(%rip), %rcx jmpq *%rcx /* code below has been relocated to a safe page */ ENTRY(core_restore_code) + /* switch to temporary page tables */ + movq $__PAGE_OFFSET, %rcx + subq %rcx, %rax + movq %rax, %cr3 + /* flush TLB */ + movq %rbx, %rcx + andq $~(X86_CR4_PGE), %rcx + movq %rcx, %cr4; # turn off PGE + movq %cr3, %rcx; # flush TLB + movq %rcx, %cr3; + movq %rbx, %cr4; # turn PGE back on .Lloop: testq %rdx, %rdx jz .Ldone @@ -96,24 +96,17 @@ ENTRY(core_restore_code) /* progress to the next pbe */ movq pbe_next(%rdx), %rdx jmp .Lloop + .Ldone: /* jump to the restore_registers address from the image header */ - jmpq *%rax - /* - * NOTE: This assumes that the boot kernel's text mapping covers the - * image kernel's page containing restore_registers and the address of - * this page is the same as in the image kernel's text mapping (it - * should always be true, because the text mapping is linear, starting - * from 0, and is supposed to cover the entire kernel text for every - * kernel). - * - * code below belongs to the image kernel - */ + jmpq *%r8 + /* code below belongs to the image kernel */ + .align PAGE_SIZE ENTRY(restore_registers) FRAME_BEGIN /* go back to the original page tables */ - movq %rbx, %cr3 + movq %r9, %cr3 /* Flush TLB, including "global" things (vmalloc) */ movq mmu_cr4_features(%rip), %rax |