diff options
Diffstat (limited to 'arch')
60 files changed, 2160 insertions, 494 deletions
diff --git a/arch/powerpc/include/asm/disassemble.h b/arch/powerpc/include/asm/disassemble.h index 4852e84..c0a5505 100644 --- a/arch/powerpc/include/asm/disassemble.h +++ b/arch/powerpc/include/asm/disassemble.h @@ -87,6 +87,11 @@ static inline unsigned int get_oc(u32 inst) return (inst >> 11) & 0x7fff; } +static inline unsigned int get_tx_or_sx(u32 inst) +{ + return (inst) & 0x1; +} + #define IS_XFORM(inst) (get_op(inst) == 31) #define IS_DSFORM(inst) (get_op(inst) >= 56) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 2c1d507..8a8ce22 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -64,6 +64,11 @@ struct iommu_table_ops { long index, unsigned long *hpa, enum dma_data_direction *direction); + /* Real mode */ + int (*exchange_rm)(struct iommu_table *tbl, + long index, + unsigned long *hpa, + enum dma_data_direction *direction); #endif void (*clear)(struct iommu_table *tbl, long index, long npages); @@ -114,6 +119,7 @@ struct iommu_table { struct list_head it_group_list;/* List of iommu_table_group_link */ unsigned long *it_userspace; /* userspace view of the table */ struct iommu_table_ops *it_ops; + struct kref it_kref; }; #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \ @@ -146,8 +152,8 @@ static inline void *get_iommu_table_base(struct device *dev) extern int dma_iommu_dma_supported(struct device *dev, u64 mask); -/* Frees table for an individual device node */ -extern void iommu_free_table(struct iommu_table *tbl, const char *node_name); +extern struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl); +extern int iommu_tce_table_put(struct iommu_table *tbl); /* Initializes an iommu_table based in values set in the passed-in * structure @@ -208,6 +214,8 @@ extern void iommu_del_device(struct device *dev); extern int __init tce_iommu_bus_notifier_init(void); extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); +extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry, + unsigned long *hpa, enum dma_data_direction *direction); #else static inline void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, @@ -288,11 +296,21 @@ static inline void iommu_restore(void) #endif /* The API to support IOMMU operations for VFIO */ -extern int iommu_tce_clear_param_check(struct iommu_table *tbl, - unsigned long ioba, unsigned long tce_value, - unsigned long npages); -extern int iommu_tce_put_param_check(struct iommu_table *tbl, - unsigned long ioba, unsigned long tce); +extern int iommu_tce_check_ioba(unsigned long page_shift, + unsigned long offset, unsigned long size, + unsigned long ioba, unsigned long npages); +extern int iommu_tce_check_gpa(unsigned long page_shift, + unsigned long gpa); + +#define iommu_tce_clear_param_check(tbl, ioba, tce_value, npages) \ + (iommu_tce_check_ioba((tbl)->it_page_shift, \ + (tbl)->it_offset, (tbl)->it_size, \ + (ioba), (npages)) || (tce_value)) +#define iommu_tce_put_param_check(tbl, ioba, gpa) \ + (iommu_tce_check_ioba((tbl)->it_page_shift, \ + (tbl)->it_offset, (tbl)->it_size, \ + (ioba), 1) || \ + iommu_tce_check_gpa((tbl)->it_page_shift, (gpa))) extern void iommu_flush_tce(struct iommu_table *tbl); extern int iommu_take_ownership(struct iommu_table *tbl); diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 01d05c7..77c6082 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -188,6 +188,13 @@ struct kvmppc_pginfo { atomic_t refcnt; }; +struct kvmppc_spapr_tce_iommu_table { + struct rcu_head rcu; + struct list_head next; + struct iommu_table *tbl; + struct kref kref; +}; + struct kvmppc_spapr_tce_table { struct list_head list; struct kvm *kvm; @@ -196,6 +203,7 @@ struct kvmppc_spapr_tce_table { u32 page_shift; u64 offset; /* in pages */ u64 size; /* window size in pages */ + struct list_head iommu_tables; struct page *pages[0]; }; @@ -342,6 +350,7 @@ struct kvmppc_pte { bool may_read : 1; bool may_write : 1; bool may_execute : 1; + unsigned long wimg; u8 page_size; /* MMU_PAGE_xxx */ }; @@ -438,6 +447,11 @@ struct mmio_hpte_cache { unsigned int index; }; +#define KVMPPC_VSX_COPY_NONE 0 +#define KVMPPC_VSX_COPY_WORD 1 +#define KVMPPC_VSX_COPY_DWORD 2 +#define KVMPPC_VSX_COPY_DWORD_LOAD_DUMP 3 + struct openpic; struct kvm_vcpu_arch { @@ -641,6 +655,21 @@ struct kvm_vcpu_arch { u8 io_gpr; /* GPR used as IO source/target */ u8 mmio_host_swabbed; u8 mmio_sign_extend; + /* conversion between single and double precision */ + u8 mmio_sp64_extend; + /* + * Number of simulations for vsx. + * If we use 2*8bytes to simulate 1*16bytes, + * then the number should be 2 and + * mmio_vsx_copy_type=KVMPPC_VSX_COPY_DWORD. + * If we use 4*4bytes to simulate 1*16bytes, + * the number should be 4 and + * mmio_vsx_copy_type=KVMPPC_VSX_COPY_WORD. + */ + u8 mmio_vsx_copy_nums; + u8 mmio_vsx_offset; + u8 mmio_vsx_copy_type; + u8 mmio_vsx_tx_sx_enabled; u8 osi_needed; u8 osi_enabled; u8 papr_enabled; @@ -729,6 +758,8 @@ struct kvm_vcpu_arch { }; #define VCPU_FPR(vcpu, i) (vcpu)->arch.fp.fpr[i][TS_FPROFFSET] +#define VCPU_VSX_FPR(vcpu, i, j) ((vcpu)->arch.fp.fpr[i][j]) +#define VCPU_VSX_VR(vcpu, i) ((vcpu)->arch.vr.vr[i]) /* Values for vcpu->arch.state */ #define KVMPPC_VCPU_NOTREADY 0 @@ -742,6 +773,7 @@ struct kvm_vcpu_arch { #define KVM_MMIO_REG_FPR 0x0020 #define KVM_MMIO_REG_QPR 0x0040 #define KVM_MMIO_REG_FQPR 0x0060 +#define KVM_MMIO_REG_VSX 0x0080 #define __KVM_HAVE_ARCH_WQP #define __KVM_HAVE_CREATE_DEVICE diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index dd11c4c..5885d32 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -78,9 +78,15 @@ extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, int is_default_endian); +extern int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int rt, unsigned int bytes, + int is_default_endian, int mmio_sign_extend); extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, u64 val, unsigned int bytes, int is_default_endian); +extern int kvmppc_handle_vsx_store(struct kvm_run *run, struct kvm_vcpu *vcpu, + int rs, unsigned int bytes, + int is_default_endian); extern int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type, u32 *inst); @@ -132,6 +138,9 @@ extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu); extern int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu); extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags); +extern void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu); +extern void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu); +extern void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, @@ -164,13 +173,19 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm, extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, unsigned long porder); extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu); +extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, + struct iommu_group *grp); +extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm, + struct iommu_group *grp); extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, struct kvm_create_spapr_tce_64 *args); extern struct kvmppc_spapr_tce_table *kvmppc_find_table( - struct kvm_vcpu *vcpu, unsigned long liobn); -extern long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt, - unsigned long ioba, unsigned long npages); + struct kvm *kvm, unsigned long liobn); +#define kvmppc_ioba_validate(stt, ioba, npages) \ + (iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \ + (stt)->size, (ioba), (npages)) ? \ + H_PARAMETER : H_SUCCESS) extern long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *tt, unsigned long tce); extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa, @@ -240,6 +255,7 @@ union kvmppc_one_reg { u64 dval; vector128 vval; u64 vsxval[2]; + u32 vsx32val[4]; struct { u64 addr; u64 length; diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index b9e3f0a..c70c827 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -29,10 +29,14 @@ extern void mm_iommu_init(struct mm_struct *mm); extern void mm_iommu_cleanup(struct mm_struct *mm); extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm, unsigned long ua, unsigned long size); +extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm( + struct mm_struct *mm, unsigned long ua, unsigned long size); extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, unsigned long ua, unsigned long entries); extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned long *hpa); +extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, + unsigned long ua, unsigned long *hpa); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem); #endif diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index e7d6d86..73f06f4 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -86,32 +86,79 @@ #define OP_TRAP_64 2 #define OP_31_XOP_TRAP 4 +#define OP_31_XOP_LDX 21 #define OP_31_XOP_LWZX 23 +#define OP_31_XOP_LDUX 53 #define OP_31_XOP_DCBST 54 #define OP_31_XOP_LWZUX 55 #define OP_31_XOP_TRAP_64 68 #define OP_31_XOP_DCBF 86 #define OP_31_XOP_LBZX 87 +#define OP_31_XOP_STDX 149 #define OP_31_XOP_STWX 151 +#define OP_31_XOP_STDUX 181 +#define OP_31_XOP_STWUX 183 #define OP_31_XOP_STBX 215 #define OP_31_XOP_LBZUX 119 #define OP_31_XOP_STBUX 247 #define OP_31_XOP_LHZX 279 #define OP_31_XOP_LHZUX 311 #define OP_31_XOP_MFSPR 339 +#define OP_31_XOP_LWAX 341 #define OP_31_XOP_LHAX 343 +#define OP_31_XOP_LWAUX 373 #define OP_31_XOP_LHAUX 375 #define OP_31_XOP_STHX 407 #define OP_31_XOP_STHUX 439 #define OP_31_XOP_MTSPR 467 #define OP_31_XOP_DCBI 470 +#define OP_31_XOP_LDBRX 532 #define OP_31_XOP_LWBRX 534 #define OP_31_XOP_TLBSYNC 566 +#define OP_31_XOP_STDBRX 660 #define OP_31_XOP_STWBRX 662 +#define OP_31_XOP_STFSX 663 +#define OP_31_XOP_STFSUX 695 +#define OP_31_XOP_STFDX 727 +#define OP_31_XOP_STFDUX 759 #define OP_31_XOP_LHBRX 790 +#define OP_31_XOP_LFIWAX 855 +#define OP_31_XOP_LFIWZX 887 #define OP_31_XOP_STHBRX 918 +#define OP_31_XOP_STFIWX 983 + +/* VSX Scalar Load Instructions */ +#define OP_31_XOP_LXSDX 588 +#define OP_31_XOP_LXSSPX 524 +#define OP_31_XOP_LXSIWAX 76 +#define OP_31_XOP_LXSIWZX 12 + +/* VSX Scalar Store Instructions */ +#define OP_31_XOP_STXSDX 716 +#define OP_31_XOP_STXSSPX 652 +#define OP_31_XOP_STXSIWX 140 + +/* VSX Vector Load Instructions */ +#define OP_31_XOP_LXVD2X 844 +#define OP_31_XOP_LXVW4X 780 + +/* VSX Vector Load and Splat Instruction */ +#define OP_31_XOP_LXVDSX 332 + +/* VSX Vector Store Instructions */ +#define OP_31_XOP_STXVD2X 972 +#define OP_31_XOP_STXVW4X 908 + +#define OP_31_XOP_LFSX 535 +#define OP_31_XOP_LFSUX 567 +#define OP_31_XOP_LFDX 599 +#define OP_31_XOP_LFDUX 631 #define OP_LWZ 32 +#define OP_STFS 52 +#define OP_STFSU 53 +#define OP_STFD 54 +#define OP_STFDU 55 #define OP_LD 58 #define OP_LWZU 33 #define OP_LBZ 34 @@ -127,6 +174,17 @@ #define OP_LHAU 43 #define OP_STH 44 #define OP_STHU 45 +#define OP_LMW 46 +#define OP_STMW 47 +#define OP_LFS 48 +#define OP_LFSU 49 +#define OP_LFD 50 +#define OP_LFDU 51 +#define OP_STFS 52 +#define OP_STFSU 53 +#define OP_STFD 54 +#define OP_STFDU 55 +#define OP_LQ 56 /* sorted alphabetically */ #define PPC_INST_BHRBE 0x7c00025c diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 5f202a5..f2b724c 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -711,13 +711,16 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid) return tbl; } -void iommu_free_table(struct iommu_table *tbl, const char *node_name) +static void iommu_table_free(struct kref *kref) { unsigned long bitmap_sz; unsigned int order; + struct iommu_table *tbl; - if (!tbl) - return; + tbl = container_of(kref, struct iommu_table, it_kref); + + if (tbl->it_ops->free) + tbl->it_ops->free(tbl); if (!tbl->it_map) { kfree(tbl); @@ -733,7 +736,7 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name) /* verify that table contains no entries */ if (!bitmap_empty(tbl->it_map, tbl->it_size)) - pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name); + pr_warn("%s: Unexpected TCEs\n", __func__); /* calculate bitmap size in bytes */ bitmap_sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long); @@ -746,6 +749,24 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name) kfree(tbl); } +struct iommu_table *iommu_tce_table_get(struct iommu_table *tbl) +{ + if (kref_get_unless_zero(&tbl->it_kref)) + return tbl; + + return NULL; +} +EXPORT_SYMBOL_GPL(iommu_tce_table_get); + +int iommu_tce_table_put(struct iommu_table *tbl) +{ + if (WARN_ON(!tbl)) + return 0; + + return kref_put(&tbl->it_kref, iommu_table_free); +} +EXPORT_SYMBOL_GPL(iommu_tce_table_put); + /* Creates TCEs for a user provided buffer. The user buffer must be * contiguous real kernel storage (not vmalloc). The address passed here * comprises a page address and offset into that page. The dma_addr_t @@ -942,47 +963,36 @@ void iommu_flush_tce(struct iommu_table *tbl) } EXPORT_SYMBOL_GPL(iommu_flush_tce); -int iommu_tce_clear_param_check(struct iommu_table *tbl, - unsigned long ioba, unsigned long tce_value, - unsigned long npages) +int iommu_tce_check_ioba(unsigned long page_shift, + unsigned long offset, unsigned long size, + unsigned long ioba, unsigned long npages) { - /* tbl->it_ops->clear() does not support any value but 0 */ - if (tce_value) - return -EINVAL; + unsigned long mask = (1UL << page_shift) - 1; - if (ioba & ~IOMMU_PAGE_MASK(tbl)) + if (ioba & mask) return -EINVAL; - ioba >>= tbl->it_page_shift; - if (ioba < tbl->it_offset) + ioba >>= page_shift; + if (ioba < offset) return -EINVAL; - if ((ioba + npages) > (tbl->it_offset + tbl->it_size)) + if ((ioba + 1) > (offset + size)) return -EINVAL; return 0; } -EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check); +EXPORT_SYMBOL_GPL(iommu_tce_check_ioba); -int iommu_tce_put_param_check(struct iommu_table *tbl, - unsigned long ioba, unsigned long tce) +int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa) { - if (tce & ~IOMMU_PAGE_MASK(tbl)) - return -EINVAL; - - if (ioba & ~IOMMU_PAGE_MASK(tbl)) - return -EINVAL; + unsigned long mask = (1UL << page_shift) - 1; - ioba >>= tbl->it_page_shift; - if (ioba < tbl->it_offset) - return -EINVAL; - - if ((ioba + 1) > (tbl->it_offset + tbl->it_size)) + if (gpa & mask) return -EINVAL; return 0; } -EXPORT_SYMBOL_GPL(iommu_tce_put_param_check); +EXPORT_SYMBOL_GPL(iommu_tce_check_gpa); long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction) @@ -1004,6 +1014,31 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, } EXPORT_SYMBOL_GPL(iommu_tce_xchg); +#ifdef CONFIG_PPC_BOOK3S_64 +long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry, + unsigned long *hpa, enum dma_data_direction *direction) +{ + long ret; + + ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); + + if (!ret && ((*direction == DMA_FROM_DEVICE) || + (*direction == DMA_BIDIRECTIONAL))) { + struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT); + + if (likely(pg)) { + SetPageDirty(pg); + } else { + tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); + ret = -EFAULT; + } + } + + return ret; +} +EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm); +#endif + int iommu_take_ownership(struct iommu_table *tbl) { unsigned long flags, i, sz = (tbl->it_size + 7) >> 3; diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 029be26..65a471d 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -67,6 +67,7 @@ config KVM_BOOK3S_64 select KVM_BOOK3S_64_HANDLER select KVM select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE + select SPAPR_TCE_IOMMU if IOMMU_SUPPORT ---help--- Support running unmodified book3s_64 and book3s_32 guest kernels in virtual machines on book3s_64 host processors. diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index b6b5c18..0ff0d07 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -197,6 +197,24 @@ void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags) } EXPORT_SYMBOL_GPL(kvmppc_core_queue_program); +void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu) +{ + /* might as well deliver this straight away */ + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, 0); +} + +void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu) +{ + /* might as well deliver this straight away */ + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_ALTIVEC, 0); +} + +void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu) +{ + /* might as well deliver this straight away */ + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_VSX, 0); +} + void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu) { kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER); diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 7015357..29ebe2f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -319,6 +319,7 @@ do_second: gpte->may_execute = true; gpte->may_read = false; gpte->may_write = false; + gpte->wimg = r & HPTE_R_WIMG; switch (pp) { case 0: diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index a587e8f..145a618 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -145,6 +145,8 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte, else kvmppc_mmu_flush_icache(pfn); + rflags = (rflags & ~HPTE_R_WIMG) | orig_pte->wimg; + /* * Use 64K pages if possible; otherwise, on 64K page kernels, * we need to transfer 4 more bits from guest real to host real addr. @@ -177,12 +179,15 @@ map_again: ret = mmu_hash_ops.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags, hpsize, hpsize, MMU_SEGSIZE_256M); - if (ret < 0) { + if (ret == -1) { /* If we couldn't map a primary PTE, try a secondary */ hash = ~hash; vflags ^= HPTE_V_SECONDARY; attempt++; goto map_again; + } else if (ret < 0) { + r = -EIO; + goto out_unlock; } else { trace_kvm_book3s_64_mmu_map(rflags, hpteg, vpn, hpaddr, orig_pte); diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 3e26cd4..a160c14 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -28,6 +28,8 @@ #include <linux/hugetlb.h> #include <linux/list.h> #include <linux/anon_inodes.h> +#include <linux/iommu.h> +#include <linux/file.h> #include <asm/tlbflush.h> #include <asm/kvm_ppc.h> @@ -40,6 +42,7 @@ #include <asm/udbg.h> #include <asm/iommu.h> #include <asm/tce.h> +#include <asm/mmu_context.h> static unsigned long kvmppc_tce_pages(unsigned long iommu_pages) { @@ -91,6 +94,137 @@ static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc) return ret; } +static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head) +{ + struct kvmppc_spapr_tce_iommu_table *stit = container_of(head, + struct kvmppc_spapr_tce_iommu_table, rcu); + + iommu_tce_table_put(stit->tbl); + + kfree(stit); +} + +static void kvm_spapr_tce_liobn_put(struct kref *kref) +{ + struct kvmppc_spapr_tce_iommu_table *stit = container_of(kref, + struct kvmppc_spapr_tce_iommu_table, kref); + + list_del_rcu(&stit->next); + + call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free); +} + +extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm, + struct iommu_group *grp) +{ + int i; + struct kvmppc_spapr_tce_table *stt; + struct kvmppc_spapr_tce_iommu_table *stit, *tmp; + struct iommu_table_group *table_group = NULL; + + list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) { + + table_group = iommu_group_get_iommudata(grp); + if (WARN_ON(!table_group)) + continue; + + list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) { + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { + if (table_group->tables[i] != stit->tbl) + continue; + + kref_put(&stit->kref, kvm_spapr_tce_liobn_put); + return; + } + } + } +} + +extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, + struct iommu_group *grp) +{ + struct kvmppc_spapr_tce_table *stt = NULL; + bool found = false; + struct iommu_table *tbl = NULL; + struct iommu_table_group *table_group; + long i; + struct kvmppc_spapr_tce_iommu_table *stit; + struct fd f; + + f = fdget(tablefd); + if (!f.file) + return -EBADF; + + list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) { + if (stt == f.file->private_data) { + found = true; + break; + } + } + + fdput(f); + + if (!found) + return -EINVAL; + + table_group = iommu_group_get_iommudata(grp); + if (WARN_ON(!table_group)) + return -EFAULT; + + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { + struct iommu_table *tbltmp = table_group->tables[i]; + + if (!tbltmp) + continue; + /* + * Make sure hardware table parameters are exactly the same; + * this is used in the TCE handlers where boundary checks + * use only the first attached table. + */ + if ((tbltmp->it_page_shift == stt->page_shift) && + (tbltmp->it_offset == stt->offset) && + (tbltmp->it_size == stt->size)) { + /* + * Reference the table to avoid races with + * add/remove DMA windows. + */ + tbl = iommu_tce_table_get(tbltmp); + break; + } + } + if (!tbl) + return -EINVAL; + + list_for_each_entry_rcu(stit, &stt->iommu_tables, next) { + if (tbl != stit->tbl) + continue; + + if (!kref_get_unless_zero(&stit->kref)) { + /* stit is being destroyed */ + iommu_tce_table_put(tbl); + return -ENOTTY; + } + /* + * The table is already known to this KVM, we just increased + * its KVM reference counter and can return. + */ + return 0; + } + + stit = kzalloc(sizeof(*stit), GFP_KERNEL); + if (!stit) { + iommu_tce_table_put(tbl); + return -ENOMEM; + } + + stit->tbl = tbl; + kref_init(&stit->kref); + + list_add_rcu(&stit->next, &stt->iommu_tables); + + return 0; +} + static void release_spapr_tce_table(struct rcu_head *head) { struct kvmppc_spapr_tce_table *stt = container_of(head, @@ -130,9 +264,18 @@ static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma) static int kvm_spapr_tce_release(struct inode *inode, struct file *filp) { struct kvmppc_spapr_tce_table *stt = filp->private_data; + struct kvmppc_spapr_tce_iommu_table *stit, *tmp; list_del_rcu(&stt->list); + list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) { + WARN_ON(!kref_read(&stit->kref)); + while (1) { + if (kref_put(&stit->kref, kvm_spapr_tce_liobn_put)) + break; + } + } + kvm_put_kvm(stt->kvm); kvmppc_account_memlimit( @@ -164,7 +307,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, return -EBUSY; } - size = args->size; + size = _ALIGN_UP(args->size, PAGE_SIZE >> 3); npages = kvmppc_tce_pages(size); ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true); if (ret) { @@ -183,6 +326,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, stt->offset = args->offset; stt->size = size; stt->kvm = kvm; + INIT_LIST_HEAD_RCU(&stt->iommu_tables); for (i = 0; i < npages; i++) { stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO); @@ -211,15 +355,106 @@ fail: return ret; } +static void kvmppc_clear_tce(struct iommu_table *tbl, unsigned long entry) +{ + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE; + + iommu_tce_xchg(tbl, entry, &hpa, &dir); +} + +static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm, + struct iommu_table *tbl, unsigned long entry) +{ + struct mm_iommu_table_group_mem_t *mem = NULL; + const unsigned long pgsize = 1ULL << tbl->it_page_shift; + unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); + + if (!pua) + /* it_userspace allocation might be delayed */ + return H_TOO_HARD; + + mem = mm_iommu_lookup(kvm->mm, *pua, pgsize); + if (!mem) + return H_TOO_HARD; + + mm_iommu_mapped_dec(mem); + + *pua = 0; + + return H_SUCCESS; +} + +static long kvmppc_tce_iommu_unmap(struct kvm *kvm, + struct iommu_table *tbl, unsigned long entry) +{ + enum dma_data_direction dir = DMA_NONE; + unsigned long hpa = 0; + long ret; + + if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir))) + return H_HARDWARE; + + if (dir == DMA_NONE) + return H_SUCCESS; + + ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry); + if (ret != H_SUCCESS) + iommu_tce_xchg(tbl, entry, &hpa, &dir); + + return ret; +} + +long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl, + unsigned long entry, unsigned long ua, + enum dma_data_direction dir) +{ + long ret; + unsigned long hpa, *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); + struct mm_iommu_table_group_mem_t *mem; + + if (!pua) + /* it_userspace allocation might be delayed */ + return H_TOO_HARD; + + mem = mm_iommu_lookup(kvm->mm, ua, 1ULL << tbl->it_page_shift); + if (!mem) + /* This only handles v2 IOMMU type, v1 is handled via ioctl() */ + return H_TOO_HARD; + + if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa))) + return H_HARDWARE; + + if (mm_iommu_mapped_inc(mem)) + return H_CLOSED; + + ret = iommu_tce_xchg(tbl, entry, &hpa, &dir); + if (WARN_ON_ONCE(ret)) { + mm_iommu_mapped_dec(mem); + return H_HARDWARE; + } + + if (dir != DMA_NONE) + kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry); + + *pua = ua; + + return 0; +} + long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba, unsigned long tce) { - struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn); - long ret; + struct kvmppc_spapr_tce_table *stt; + long ret, idx; + struct kvmppc_spapr_tce_iommu_table *stit; + unsigned long entry, ua = 0; + enum dma_data_direction dir; /* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */ /* liobn, ioba, tce); */ + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -231,7 +466,35 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, if (ret != H_SUCCESS) return ret; - kvmppc_tce_put(stt, ioba >> stt->page_shift, tce); + dir = iommu_tce_direction(tce); + if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm, + tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL)) + return H_PARAMETER; + + entry = ioba >> stt->page_shift; + + list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { + if (dir == DMA_NONE) { + ret = kvmppc_tce_iommu_unmap(vcpu->kvm, + stit->tbl, entry); + } else { + idx = srcu_read_lock(&vcpu->kvm->srcu); + 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; + + WARN_ON_ONCE(1); + kvmppc_clear_tce(stit->tbl, entry); + } + + kvmppc_tce_put(stt, entry, tce); return H_SUCCESS; } @@ -246,8 +509,9 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, unsigned long entry, ua = 0; u64 __user *tces; u64 tce; + struct kvmppc_spapr_tce_iommu_table *stit; - stt = kvmppc_find_table(vcpu, liobn); + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -284,6 +548,26 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, if (ret != H_SUCCESS) goto unlock_exit; + if (kvmppc_gpa_to_ua(vcpu->kvm, + tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), + &ua, NULL)) + return H_PARAMETER; + + list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { + ret = kvmppc_tce_iommu_map(vcpu->kvm, + stit->tbl, entry + i, ua, + iommu_tce_direction(tce)); + + if (ret == H_SUCCESS) + continue; + + if (ret == H_TOO_HARD) + goto unlock_exit; + + WARN_ON_ONCE(1); + kvmppc_clear_tce(stit->tbl, entry); + } + kvmppc_tce_put(stt, entry + i, tce); } @@ -300,8 +584,9 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, { struct kvmppc_spapr_tce_table *stt; long i, ret; + struct kvmppc_spapr_tce_iommu_table *stit; - stt = kvmppc_find_table(vcpu, liobn); + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -313,6 +598,24 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ)) return H_PARAMETER; + list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { + unsigned long entry = ioba >> stit->tbl->it_page_shift; + + for (i = 0; i < npages; ++i) { + ret = kvmppc_tce_iommu_unmap(vcpu->kvm, + stit->tbl, entry + i); + + if (ret == H_SUCCESS) + continue; + + if (ret == H_TOO_HARD) + return ret; + + WARN_ON_ONCE(1); + kvmppc_clear_tce(stit->tbl, entry); + } + } + for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value); diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index e4c4ea9..eda0a8f 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -40,6 +40,31 @@ #include <asm/iommu.h> #include <asm/tce.h> +#ifdef CONFIG_BUG + +#define WARN_ON_ONCE_RM(condition) ({ \ + static bool __section(.data.unlikely) __warned; \ + int __ret_warn_once = !!(condition); \ + \ + if (unlikely(__ret_warn_once && !__warned)) { \ + __warned = true; \ + pr_err("WARN_ON_ONCE_RM: (%s) at %s:%u\n", \ + __stringify(condition), \ + __func__, __LINE__); \ + dump_stack(); \ + } \ + unlikely(__ret_warn_once); \ +}) + +#else + +#define WARN_ON_ONCE_RM(condition) ({ \ + int __ret_warn_on = !!(condition); \ + unlikely(__ret_warn_on); \ +}) + +#endif + #define TCES_PER_PAGE (PAGE_SIZE / sizeof(u64)) /* @@ -48,10 +73,9 @@ * WARNING: This will be called in real or virtual mode on HV KVM and virtual * mode on PR KVM */ -struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm_vcpu *vcpu, +struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm, unsigned long liobn) { - struct kvm *kvm = vcpu->kvm; struct kvmppc_spapr_tce_table *stt; list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list) @@ -63,27 +87,6 @@ struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm_vcpu *vcpu, EXPORT_SYMBOL_GPL(kvmppc_find_table); /* - * Validates IO address. - * - * WARNING: This will be called in real-mode on HV KVM and virtual - * mode on PR KVM - */ -long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt, - unsigned long ioba, unsigned long npages) -{ - unsigned long mask = (1ULL << stt->page_shift) - 1; - unsigned long idx = ioba >> stt->page_shift; - - if ((ioba & mask) || (idx < stt->offset) || - (idx - stt->offset + npages > stt->size) || - (idx + npages < idx)) - return H_PARAMETER; - - return H_SUCCESS; -} -EXPORT_SYMBOL_GPL(kvmppc_ioba_validate); - -/* * Validates TCE address. * At the moment flags and page mask are validated. * As the host kernel does not access those addresses (just puts them @@ -96,10 +99,14 @@ EXPORT_SYMBOL_GPL(kvmppc_ioba_validate); */ long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, unsigned long tce) { - unsigned long page_mask = ~((1ULL << stt->page_shift) - 1); - unsigned long mask = ~(page_mask | TCE_PCI_WRITE | TCE_PCI_READ); + unsigned long gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE); + enum dma_data_direction dir = iommu_tce_direction(tce); + + /* Allow userspace to poison TCE table */ + if (dir == DMA_NONE) + return H_SUCCESS; - if (tce & mask) + if (iommu_tce_check_gpa(stt->page_shift, gpa)) return H_PARAMETER; return H_SUCCESS; @@ -179,15 +186,122 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa, EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua); #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry) +{ + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE; + + iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); +} + +static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, + struct iommu_table *tbl, unsigned long entry) +{ + struct mm_iommu_table_group_mem_t *mem = NULL; + const unsigned long pgsize = 1ULL << tbl->it_page_shift; + unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); + + if (!pua) + /* it_userspace allocation might be delayed */ + return H_TOO_HARD; + + pua = (void *) vmalloc_to_phys(pua); + if (WARN_ON_ONCE_RM(!pua)) + return H_HARDWARE; + + mem = mm_iommu_lookup_rm(kvm->mm, *pua, pgsize); + if (!mem) + return H_TOO_HARD; + + mm_iommu_mapped_dec(mem); + + *pua = 0; + + return H_SUCCESS; +} + +static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm, + struct iommu_table *tbl, unsigned long entry) +{ + enum dma_data_direction dir = DMA_NONE; + unsigned long hpa = 0; + long ret; + + if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir)) + /* + * real mode xchg can fail if struct page crosses + * a page boundary + */ + return H_TOO_HARD; + + if (dir == DMA_NONE) + return H_SUCCESS; + + ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry); + if (ret) + iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + + return ret; +} + +static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl, + unsigned long entry, unsigned long ua, + enum dma_data_direction dir) +{ + long ret; + unsigned long hpa = 0; + unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry); + struct mm_iommu_table_group_mem_t *mem; + + if (!pua) + /* it_userspace allocation might be delayed */ + return H_TOO_HARD; + + mem = mm_iommu_lookup_rm(kvm->mm, ua, 1ULL << tbl->it_page_shift); + if (!mem) + return H_TOO_HARD; + + if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa))) + return H_HARDWARE; + + pua = (void *) vmalloc_to_phys(pua); + if (WARN_ON_ONCE_RM(!pua)) + return H_HARDWARE; + + if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem))) + return H_CLOSED; + + ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + if (ret) { + mm_iommu_mapped_dec(mem); + /* + * real mode xchg can fail if struct page crosses + * a page boundary + */ + return H_TOO_HARD; + } + + if (dir != DMA_NONE) + kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry); + + *pua = ua; + + return 0; +} + long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba, unsigned long tce) { - struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn); + struct kvmppc_spapr_tce_table *stt; long ret; + struct kvmppc_spapr_tce_iommu_table *stit; + unsigned long entry, ua = 0; + enum dma_data_direction dir; /* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */ /* liobn, ioba, tce); */ + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -199,7 +313,32 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, if (ret != H_SUCCESS) return ret; - kvmppc_tce_put(stt, ioba >> stt->page_shift, tce); + dir = iommu_tce_direction(tce); + if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm, + tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL)) + return H_PARAMETER; + + entry = ioba >> stt->page_shift; + + list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { + if (dir == DMA_NONE) + ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm, + stit->tbl, entry); + else + ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, + stit->tbl, entry, ua, dir); + + if (ret == H_SUCCESS) + continue; + + if (ret == H_TOO_HARD) + return ret; + + WARN_ON_ONCE_RM(1); + kvmppc_rm_clear_tce(stit->tbl, entry); + } + + kvmppc_tce_put(stt, entry, tce); return H_SUCCESS; } @@ -239,8 +378,10 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, long i, ret = H_SUCCESS; unsigned long tces, entry, ua = 0; unsigned long *rmap = NULL; + bool prereg = false; + struct kvmppc_spapr_tce_iommu_table *stit; - stt = kvmppc_find_table(vcpu, liobn); + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -259,23 +400,49 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, if (ret != H_SUCCESS) return ret; - if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap)) - return H_TOO_HARD; + if (mm_iommu_preregistered(vcpu->kvm->mm)) { + /* + * We get here if guest memory was pre-registered which + * is normally VFIO case and gpa->hpa translation does not + * depend on hpt. + */ + struct mm_iommu_table_group_mem_t *mem; - rmap = (void *) vmalloc_to_phys(rmap); + if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, NULL)) + return H_TOO_HARD; - /* - * Synchronize with the MMU notifier callbacks in - * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.). - * While we have the rmap lock, code running on other CPUs - * cannot finish unmapping the host real page that backs - * this guest real page, so we are OK to access the host - * real page. - */ - lock_rmap(rmap); - if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) { - ret = H_TOO_HARD; - goto unlock_exit; + mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K); + if (mem) + prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0; + } + + if (!prereg) { + /* + * This is usually a case of a guest with emulated devices only + * when TCE list is not in preregistered memory. + * We do not require memory to be preregistered in this case + * so lock rmap and do __find_linux_pte_or_hugepte(). + */ + if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap)) + return H_TOO_HARD; + + rmap = (void *) vmalloc_to_phys(rmap); + if (WARN_ON_ONCE_RM(!rmap)) + return H_HARDWARE; + + /* + * Synchronize with the MMU notifier callbacks in + * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.). + * While we have the rmap lock, code running on other CPUs + * cannot finish unmapping the host real page that backs + * this guest real page, so we are OK to access the host + * real page. + */ + lock_rmap(rmap); + if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) { + ret = H_TOO_HARD; + goto unlock_exit; + } } for (i = 0; i < npages; ++i) { @@ -285,11 +452,33 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, if (ret != H_SUCCESS) goto unlock_exit; + ua = 0; + if (kvmppc_gpa_to_ua(vcpu->kvm, + tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), + &ua, NULL)) + return H_PARAMETER; + + list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { + ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, + stit->tbl, entry + i, ua, + iommu_tce_direction(tce)); + + if (ret == H_SUCCESS) + continue; + + if (ret == H_TOO_HARD) + goto unlock_exit; + + WARN_ON_ONCE_RM(1); + kvmppc_rm_clear_tce(stit->tbl, entry); + } + kvmppc_tce_put(stt, entry + i, tce); } unlock_exit: - unlock_rmap(rmap); + if (rmap) + unlock_rmap(rmap); return ret; } @@ -300,8 +489,9 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, { struct kvmppc_spapr_tce_table *stt; long i, ret; + struct kvmppc_spapr_tce_iommu_table *stit; - stt = kvmppc_find_table(vcpu, liobn); + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; @@ -313,6 +503,24 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ)) return H_PARAMETER; + list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { + unsigned long entry = ioba >> stit->tbl->it_page_shift; + + for (i = 0; i < npages; ++i) { + ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm, + stit->tbl, entry + i); + + if (ret == H_SUCCESS) + continue; + + if (ret == H_TOO_HARD) + return ret; + + WARN_ON_ONCE_RM(1); + kvmppc_rm_clear_tce(stit->tbl, entry); + } + } + for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value); @@ -322,12 +530,13 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba) { - struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn); + struct kvmppc_spapr_tce_table *stt; long ret; unsigned long idx; struct page *page; u64 *tbl; + stt = kvmppc_find_table(vcpu->kvm, liobn); if (!stt) return H_TOO_HARD; diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 8359752..68d6898 100644 --- a/arch/powerpc/kvm/book3s_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -503,10 +503,18 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) break; unprivileged: default: - printk(KERN_INFO "KVM: invalid SPR write: %d\n", sprn); -#ifndef DEBUG_SPR - emulated = EMULATE_FAIL; -#endif + pr_info_ratelimited("KVM: invalid SPR write: %d\n", sprn); + if (sprn & 0x10) { + if (kvmppc_get_msr(vcpu) & MSR_PR) { + kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV); + emulated = EMULATE_AGAIN; + } + } else { + if ((kvmppc_get_msr(vcpu) & MSR_PR) || sprn == 0) { + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + emulated = EMULATE_AGAIN; + } + } break; } @@ -648,10 +656,20 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val break; default: unprivileged: - printk(KERN_INFO "KVM: invalid SPR read: %d\n", sprn); -#ifndef DEBUG_SPR - emulated = EMULATE_FAIL; -#endif + pr_info_ratelimited("KVM: invalid SPR read: %d\n", sprn); + if (sprn & 0x10) { + if (kvmppc_get_msr(vcpu) & MSR_PR) { + kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV); + emulated = EMULATE_AGAIN; + } + } else { + if ((kvmppc_get_msr(vcpu) & MSR_PR) || sprn == 0 || + sprn == 4 || sprn == 5 || sprn == 6) { + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + emulated = EMULATE_AGAIN; + } + } + break; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 1ec86d9..06b7d8a 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3624,11 +3624,9 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) return -EIO; mutex_lock(&kvm->lock); + if (!kvm->arch.pimap) + goto unlock; - if (kvm->arch.pimap == NULL) { - mutex_unlock(&kvm->lock); - return 0; - } pimap = kvm->arch.pimap; for (i = 0; i < pimap->n_mapped; i++) { @@ -3650,7 +3648,7 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi) * We don't free this structure even when the count goes to * zero. The structure is freed when we destroy the VM. */ - + unlock: mutex_unlock(&kvm->lock); return 0; } diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index d4dfc0c..f026b06 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -537,8 +537,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, int r = RESUME_GUEST; int relocated; int page_found = 0; - struct kvmppc_pte pte; - bool is_mmio = false; + struct kvmppc_pte pte = { 0 }; bool dr = (kvmppc_get_msr(vcpu) & MSR_DR) ? true : false; bool ir = (kvmppc_get_msr(vcpu) & MSR_IR) ? true : false; u64 vsid; @@ -616,8 +615,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, /* Page not found in guest SLB */ kvmppc_set_dar(vcpu, kvmppc_get_fault_dar(vcpu)); kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80); - } else if (!is_mmio && - kvmppc_visible_gpa(vcpu, pte.raddr)) { + } else if (kvmppc_visible_gpa(vcpu, pte.raddr)) { if (data && !(vcpu->arch.fault_dsisr & DSISR_NOHPTE)) { /* * There is already a host HPTE there, presumably @@ -627,7 +625,11 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, kvmppc_mmu_unmap_page(vcpu, &pte); } /* The guest's PTE is not mapped yet. Map on the host */ - kvmppc_mmu_map_page(vcpu, &pte, iswrite); + if (kvmppc_mmu_map_page(vcpu, &pte, iswrite) == -EIO) { + /* Exit KVM if mapping failed */ + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + return RESUME_HOST; + } if (data) vcpu->stat.sp_storage++; else if (vcpu->arch.mmu.is_dcbz32(vcpu) && diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 0514cbd..3c296c2 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -300,6 +300,11 @@ void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong esr_flags) kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_PROGRAM); } +void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu) +{ + kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_FP_UNAVAIL); +} + void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu) { kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DECREMENTER); diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 0fda423..77fd043 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -797,9 +797,8 @@ int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500) host_tlb_params[0].sets = host_tlb_params[0].entries / host_tlb_params[0].ways; host_tlb_params[1].sets = 1; - - vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) * - host_tlb_params[1].entries, + vcpu_e500->h2g_tlb1_rmap = kcalloc(host_tlb_params[1].entries, + sizeof(*vcpu_e500->h2g_tlb1_rmap), GFP_KERNEL); if (!vcpu_e500->h2g_tlb1_rmap) return -EINVAL; diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index b379146..c873ffe 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -259,10 +259,18 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu) case OP_31_XOP_MFSPR: emulated = kvmppc_emulate_mfspr(vcpu, sprn, rt); + if (emulated == EMULATE_AGAIN) { + emulated = EMULATE_DONE; + advance = 0; + } break; case OP_31_XOP_MTSPR: emulated = kvmppc_emulate_mtspr(vcpu, sprn, rs); + if (emulated == EMULATE_AGAIN) { + emulated = EMULATE_DONE; + advance = 0; + } break; case OP_31_XOP_TLBSYNC: diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c index 6d3c0ee..af83353 100644 --- a/arch/powerpc/kvm/emulate_loadstore.c +++ b/arch/powerpc/kvm/emulate_loadstore.c @@ -34,18 +34,38 @@ #include "timing.h" #include "trace.h" -/* XXX to do: - * lhax - * lhaux - * lswx - * lswi - * stswx - * stswi - * lha - * lhau - * lmw - * stmw +#ifdef CONFIG_PPC_FPU +static bool kvmppc_check_fp_disabled(struct kvm_vcpu *vcpu) +{ + if (!(kvmppc_get_msr(vcpu) & MSR_FP)) { + kvmppc_core_queue_fpunavail(vcpu); + return true; + } + + return false; +} +#endif /* CONFIG_PPC_FPU */ + +#ifdef CONFIG_VSX +static bool kvmppc_check_vsx_disabled(struct kvm_vcpu *vcpu) +{ + if (!(kvmppc_get_msr(vcpu) & MSR_VSX)) { + kvmppc_core_queue_vsx_unavail(vcpu); + return true; + } + + return false; +} +#endif /* CONFIG_VSX */ + +/* + * XXX to do: + * lfiwax, lfiwzx + * vector loads and stores * + * Instructions that trap when used on cache-inhibited mappings + * are not emulated here: multiple and string instructions, + * lq/stq, and the load-reserve/store-conditional instructions. */ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) { @@ -66,6 +86,19 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) rs = get_rs(inst); rt = get_rt(inst); + /* + * if mmio_vsx_tx_sx_enabled == 0, copy data between + * VSR[0..31] and memory + * if mmio_vsx_tx_sx_enabled == 1, copy data between + * VSR[32..63] and memory + */ + vcpu->arch.mmio_vsx_tx_sx_enabled = get_tx_or_sx(inst); + vcpu->arch.mmio_vsx_copy_nums = 0; + vcpu->arch.mmio_vsx_offset = 0; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_NONE; + vcpu->arch.mmio_sp64_extend = 0; + vcpu->arch.mmio_sign_extend = 0; + switch (get_op(inst)) { case 31: switch (get_xop(inst)) { @@ -73,6 +106,11 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1); break; + case OP_31_XOP_LWZUX: + emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + case OP_31_XOP_LBZX: emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1); break; @@ -82,22 +120,36 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); break; + case OP_31_XOP_STDX: + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 8, 1); + break; + + case OP_31_XOP_STDUX: + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 8, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + case OP_31_XOP_STWX: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 4, 1); + kvmppc_get_gpr(vcpu, rs), 4, 1); + break; + + case OP_31_XOP_STWUX: + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 4, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); break; case OP_31_XOP_STBX: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 1, 1); + kvmppc_get_gpr(vcpu, rs), 1, 1); break; case OP_31_XOP_STBUX: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 1, 1); + kvmppc_get_gpr(vcpu, rs), 1, 1); kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); break; @@ -105,6 +157,11 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1); break; + case OP_31_XOP_LHAUX: + emulated = kvmppc_handle_loads(run, vcpu, rt, 2, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + case OP_31_XOP_LHZX: emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1); break; @@ -116,14 +173,12 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) case OP_31_XOP_STHX: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 2, 1); + kvmppc_get_gpr(vcpu, rs), 2, 1); break; case OP_31_XOP_STHUX: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 2, 1); + kvmppc_get_gpr(vcpu, rs), 2, 1); kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); break; @@ -143,8 +198,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) case OP_31_XOP_STWBRX: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 4, 0); + kvmppc_get_gpr(vcpu, rs), 4, 0); break; case OP_31_XOP_LHBRX: @@ -153,10 +207,258 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) case OP_31_XOP_STHBRX: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 2, 0); + kvmppc_get_gpr(vcpu, rs), 2, 0); + break; + + case OP_31_XOP_LDBRX: + emulated = kvmppc_handle_load(run, vcpu, rt, 8, 0); + break; + + case OP_31_XOP_STDBRX: + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 8, 0); + break; + + case OP_31_XOP_LDX: + emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1); + break; + + case OP_31_XOP_LDUX: + emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + + case OP_31_XOP_LWAX: + emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1); + break; + + case OP_31_XOP_LWAUX: + emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + +#ifdef CONFIG_PPC_FPU + case OP_31_XOP_LFSX: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_sp64_extend = 1; + emulated = kvmppc_handle_load(run, vcpu, + KVM_MMIO_REG_FPR|rt, 4, 1); + break; + + case OP_31_XOP_LFSUX: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_sp64_extend = 1; + emulated = kvmppc_handle_load(run, vcpu, + KVM_MMIO_REG_FPR|rt, 4, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + + case OP_31_XOP_LFDX: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + emulated = kvmppc_handle_load(run, vcpu, + KVM_MMIO_REG_FPR|rt, 8, 1); + break; + + case OP_31_XOP_LFDUX: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + emulated = kvmppc_handle_load(run, vcpu, + KVM_MMIO_REG_FPR|rt, 8, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + + case OP_31_XOP_LFIWAX: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + emulated = kvmppc_handle_loads(run, vcpu, + KVM_MMIO_REG_FPR|rt, 4, 1); + break; + + case OP_31_XOP_LFIWZX: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + emulated = kvmppc_handle_load(run, vcpu, + KVM_MMIO_REG_FPR|rt, 4, 1); + break; + + case OP_31_XOP_STFSX: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_sp64_extend = 1; + emulated = kvmppc_handle_store(run, vcpu, + VCPU_FPR(vcpu, rs), 4, 1); + break; + + case OP_31_XOP_STFSUX: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_sp64_extend = 1; + emulated = kvmppc_handle_store(run, vcpu, + VCPU_FPR(vcpu, rs), 4, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + + case OP_31_XOP_STFDX: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + emulated = kvmppc_handle_store(run, vcpu, + VCPU_FPR(vcpu, rs), 8, 1); + break; + + case OP_31_XOP_STFDUX: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + emulated = kvmppc_handle_store(run, vcpu, + VCPU_FPR(vcpu, rs), 8, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + + case OP_31_XOP_STFIWX: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + emulated = kvmppc_handle_store(run, vcpu, + VCPU_FPR(vcpu, rs), 4, 1); + break; +#endif + +#ifdef CONFIG_VSX + case OP_31_XOP_LXSDX: + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_copy_nums = 1; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD; + emulated = kvmppc_handle_vsx_load(run, vcpu, + KVM_MMIO_REG_VSX|rt, 8, 1, 0); + break; + + case OP_31_XOP_LXSSPX: + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_copy_nums = 1; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD; + vcpu->arch.mmio_sp64_extend = 1; + emulated = kvmppc_handle_vsx_load(run, vcpu, + KVM_MMIO_REG_VSX|rt, 4, 1, 0); + break; + + case OP_31_XOP_LXSIWAX: + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_copy_nums = 1; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD; + emulated = kvmppc_handle_vsx_load(run, vcpu, + KVM_MMIO_REG_VSX|rt, 4, 1, 1); + break; + + case OP_31_XOP_LXSIWZX: + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_copy_nums = 1; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD; + emulated = kvmppc_handle_vsx_load(run, vcpu, + KVM_MMIO_REG_VSX|rt, 4, 1, 0); + break; + + case OP_31_XOP_LXVD2X: + /* + * In this case, the official load/store process is like this: + * Step1, exit from vm by page fault isr, then kvm save vsr. + * Please see guest_exit_cont->store_fp_state->SAVE_32VSRS + * as reference. + * + * Step2, copy data between memory and VCPU + * Notice: for LXVD2X/STXVD2X/LXVW4X/STXVW4X, we use + * 2copies*8bytes or 4copies*4bytes + * to simulate one copy of 16bytes. + * Also there is an endian issue here, we should notice the + * layout of memory. + * Please see MARCO of LXVD2X_ROT/STXVD2X_ROT as more reference. + * If host is little-endian, kvm will call XXSWAPD for + * LXVD2X_ROT/STXVD2X_ROT. + * So, if host is little-endian, + * the postion of memeory should be swapped. + * + * Step3, return to guest, kvm reset register. + * Please see kvmppc_hv_entry->load_fp_state->REST_32VSRS + * as reference. + */ + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_copy_nums = 2; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD; + emulated = kvmppc_handle_vsx_load(run, vcpu, + KVM_MMIO_REG_VSX|rt, 8, 1, 0); + break; + + case OP_31_XOP_LXVW4X: + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_copy_nums = 4; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD; + emulated = kvmppc_handle_vsx_load(run, vcpu, + KVM_MMIO_REG_VSX|rt, 4, 1, 0); + break; + + case OP_31_XOP_LXVDSX: + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_copy_nums = 1; + vcpu->arch.mmio_vsx_copy_type = + KVMPPC_VSX_COPY_DWORD_LOAD_DUMP; + emulated = kvmppc_handle_vsx_load(run, vcpu, + KVM_MMIO_REG_VSX|rt, 8, 1, 0); + break; + + case OP_31_XOP_STXSDX: + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_copy_nums = 1; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD; + emulated = kvmppc_handle_vsx_store(run, vcpu, + rs, 8, 1); break; + case OP_31_XOP_STXSSPX: + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_copy_nums = 1; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD; + vcpu->arch.mmio_sp64_extend = 1; + emulated = kvmppc_handle_vsx_store(run, vcpu, + rs, 4, 1); + break; + + case OP_31_XOP_STXSIWX: + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_offset = 1; + vcpu->arch.mmio_vsx_copy_nums = 1; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD; + emulated = kvmppc_handle_vsx_store(run, vcpu, + rs, 4, 1); + break; + + case OP_31_XOP_STXVD2X: + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_copy_nums = 2; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_DWORD; + emulated = kvmppc_handle_vsx_store(run, vcpu, + rs, 8, 1); + break; + + case OP_31_XOP_STXVW4X: + if (kvmppc_check_vsx_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_vsx_copy_nums = 4; + vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_WORD; + emulated = kvmppc_handle_vsx_store(run, vcpu, + rs, 4, 1); + break; +#endif /* CONFIG_VSX */ default: emulated = EMULATE_FAIL; break; @@ -167,10 +469,60 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1); break; - /* TBD: Add support for other 64 bit load variants like ldu, ldux, ldx etc. */ +#ifdef CONFIG_PPC_FPU + case OP_STFS: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_sp64_extend = 1; + emulated = kvmppc_handle_store(run, vcpu, + VCPU_FPR(vcpu, rs), + 4, 1); + break; + + case OP_STFSU: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_sp64_extend = 1; + emulated = kvmppc_handle_store(run, vcpu, + VCPU_FPR(vcpu, rs), + 4, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + + case OP_STFD: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + emulated = kvmppc_handle_store(run, vcpu, + VCPU_FPR(vcpu, rs), + 8, 1); + break; + + case OP_STFDU: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + emulated = kvmppc_handle_store(run, vcpu, + VCPU_FPR(vcpu, rs), + 8, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; +#endif + case OP_LD: rt = get_rt(inst); - emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1); + switch (inst & 3) { + case 0: /* ld */ + emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1); + break; + case 1: /* ldu */ + emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + case 2: /* lwa */ + emulated = kvmppc_handle_loads(run, vcpu, rt, 4, 1); + break; + default: + emulated = EMULATE_FAIL; + } break; case OP_LWZU: @@ -193,31 +545,37 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) 4, 1); break; - /* TBD: Add support for other 64 bit store variants like stdu, stdux, stdx etc. */ case OP_STD: rs = get_rs(inst); - emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 8, 1); + switch (inst & 3) { + case 0: /* std */ + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 8, 1); + break; + case 1: /* stdu */ + emulated = kvmppc_handle_store(run, vcpu, + kvmppc_get_gpr(vcpu, rs), 8, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + default: + emulated = EMULATE_FAIL; + } break; case OP_STWU: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 4, 1); + kvmppc_get_gpr(vcpu, rs), 4, 1); kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); break; case OP_STB: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 1, 1); + kvmppc_get_gpr(vcpu, rs), 1, 1); break; case OP_STBU: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 1, 1); + kvmppc_get_gpr(vcpu, rs), 1, 1); kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); break; @@ -241,16 +599,48 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) case OP_STH: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 2, 1); + kvmppc_get_gpr(vcpu, rs), 2, 1); break; case OP_STHU: emulated = kvmppc_handle_store(run, vcpu, - kvmppc_get_gpr(vcpu, rs), - 2, 1); + kvmppc_get_gpr(vcpu, rs), 2, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + +#ifdef CONFIG_PPC_FPU + case OP_LFS: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_sp64_extend = 1; + emulated = kvmppc_handle_load(run, vcpu, + KVM_MMIO_REG_FPR|rt, 4, 1); + break; + + case OP_LFSU: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.mmio_sp64_extend = 1; + emulated = kvmppc_handle_load(run, vcpu, + KVM_MMIO_REG_FPR|rt, 4, 1); + kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); + break; + + case OP_LFD: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + emulated = kvmppc_handle_load(run, vcpu, + KVM_MMIO_REG_FPR|rt, 8, 1); + break; + + case OP_LFDU: + if (kvmppc_check_fp_disabled(vcpu)) + return EMULATE_DONE; + emulated = kvmppc_handle_load(run, vcpu, + KVM_MMIO_REG_FPR|rt, 8, 1); kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed); break; +#endif default: emulated = EMULATE_FAIL; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 0e42aa8..cf725c5 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -37,6 +37,7 @@ #include <asm/cputhreads.h> #include <asm/irqflags.h> #include <asm/iommu.h> +#include <asm/switch_to.h> #include "timing.h" #include "irq.h" #include "../mm/mmu_decl.h" @@ -533,6 +534,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CAP_SPAPR_TCE: case KVM_CAP_SPAPR_TCE_64: + /* fallthrough */ + case KVM_CAP_SPAPR_TCE_VFIO: case KVM_CAP_PPC_RTAS: case KVM_CAP_PPC_FIXUP_HCALL: case KVM_CAP_PPC_ENABLE_HCALL: @@ -801,6 +804,129 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, kvm->arch.kvm_ops->irq_bypass_del_producer(cons, prod); } +#ifdef CONFIG_VSX +static inline int kvmppc_get_vsr_dword_offset(int index) +{ + int offset; + + if ((index != 0) && (index != 1)) + return -1; + +#ifdef __BIG_ENDIAN + offset = index; +#else + offset = 1 - index; +#endif + + return offset; +} + +static inline int kvmppc_get_vsr_word_offset(int index) +{ + int offset; + + if ((index > 3) || (index < 0)) + return -1; + +#ifdef __BIG_ENDIAN + offset = index; +#else + offset = 3 - index; +#endif + return offset; +} + +static inline void kvmppc_set_vsr_dword(struct kvm_vcpu *vcpu, + u64 gpr) +{ + union kvmppc_one_reg val; + int offset = kvmppc_get_vsr_dword_offset(vcpu->arch.mmio_vsx_offset); + int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK; + + if (offset == -1) + return; + + if (vcpu->arch.mmio_vsx_tx_sx_enabled) { + val.vval = VCPU_VSX_VR(vcpu, index); + val.vsxval[offset] = gpr; + VCPU_VSX_VR(vcpu, index) = val.vval; + } else { + VCPU_VSX_FPR(vcpu, index, offset) = gpr; + } +} + +static inline void kvmppc_set_vsr_dword_dump(struct kvm_vcpu *vcpu, + u64 gpr) +{ + union kvmppc_one_reg val; + int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK; + + if (vcpu->arch.mmio_vsx_tx_sx_enabled) { + val.vval = VCPU_VSX_VR(vcpu, index); + val.vsxval[0] = gpr; + val.vsxval[1] = gpr; + VCPU_VSX_VR(vcpu, index) = val.vval; + } else { + VCPU_VSX_FPR(vcpu, index, 0) = gpr; + VCPU_VSX_FPR(vcpu, index, 1) = gpr; + } +} + +static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu, + u32 gpr32) +{ + union kvmppc_one_reg val; + int offset = kvmppc_get_vsr_word_offset(vcpu->arch.mmio_vsx_offset); + int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK; + int dword_offset, word_offset; + + if (offset == -1) + return; + + if (vcpu->arch.mmio_vsx_tx_sx_enabled) { + val.vval = VCPU_VSX_VR(vcpu, index); + val.vsx32val[offset] = gpr32; + VCPU_VSX_VR(vcpu, index) = val.vval; + } else { + dword_offset = offset / 2; + word_offset = offset % 2; + val.vsxval[0] = VCPU_VSX_FPR(vcpu, index, dword_offset); + val.vsx32val[word_offset] = gpr32; + VCPU_VSX_FPR(vcpu, index, dword_offset) = val.vsxval[0]; + } +} +#endif /* CONFIG_VSX */ + +#ifdef CONFIG_PPC_FPU +static inline u64 sp_to_dp(u32 fprs) +{ + u64 fprd; + + preempt_disable(); + enable_kernel_fp(); + asm ("lfs%U1%X1 0,%1; stfd%U0%X0 0,%0" : "=m" (fprd) : "m" (fprs) + : "fr0"); + preempt_enable(); + return fprd; +} + +static inline u32 dp_to_sp(u64 fprd) +{ + u32 fprs; + + preempt_disable(); + enable_kernel_fp(); + asm ("lfd%U1%X1 0,%1; stfs%U0%X0 0,%0" : "=m" (fprs) : "m" (fprd) + : "fr0"); + preempt_enable(); + return fprs; +} + +#else +#define sp_to_dp(x) (x) +#define dp_to_sp(x) (x) +#endif /* CONFIG_PPC_FPU */ + static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run) { @@ -827,6 +953,10 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, } } + /* conversion between single and double precision */ + if ((vcpu->arch.mmio_sp64_extend) && (run->mmio.len == 4)) + gpr = sp_to_dp(gpr); + if (vcpu->arch.mmio_sign_extend) { switch (run->mmio.len) { #ifdef CONFIG_PPC64 @@ -843,8 +973,6 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, } } - kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr); - switch (vcpu->arch.io_gpr & KVM_MMIO_REG_EXT_MASK) { case KVM_MMIO_REG_GPR: kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr); @@ -861,6 +989,17 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr; break; #endif +#ifdef CONFIG_VSX + case KVM_MMIO_REG_VSX: + if (vcpu->arch.mmio_vsx_copy_type == KVMPPC_VSX_COPY_DWORD) + kvmppc_set_vsr_dword(vcpu, gpr); + else if (vcpu->arch.mmio_vsx_copy_type == KVMPPC_VSX_COPY_WORD) + kvmppc_set_vsr_word(vcpu, gpr); + else if (vcpu->arch.mmio_vsx_copy_type == + KVMPPC_VSX_COPY_DWORD_LOAD_DUMP) + kvmppc_set_vsr_dword_dump(vcpu, gpr); + break; +#endif default: BUG(); } @@ -927,6 +1066,35 @@ int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, return __kvmppc_handle_load(run, vcpu, rt, bytes, is_default_endian, 1); } +#ifdef CONFIG_VSX +int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int rt, unsigned int bytes, + int is_default_endian, int mmio_sign_extend) +{ + enum emulation_result emulated = EMULATE_DONE; + + /* Currently, mmio_vsx_copy_nums only allowed to be less than 4 */ + if ( (vcpu->arch.mmio_vsx_copy_nums > 4) || + (vcpu->arch.mmio_vsx_copy_nums < 0) ) { + return EMULATE_FAIL; + } + + while (vcpu->arch.mmio_vsx_copy_nums) { + emulated = __kvmppc_handle_load(run, vcpu, rt, bytes, + is_default_endian, mmio_sign_extend); + + if (emulated != EMULATE_DONE) + break; + + vcpu->arch.paddr_accessed += run->mmio.len; + + vcpu->arch.mmio_vsx_copy_nums--; + vcpu->arch.mmio_vsx_offset++; + } + return emulated; +} +#endif /* CONFIG_VSX */ + int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, u64 val, unsigned int bytes, int is_default_endian) { @@ -952,6 +1120,9 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->mmio_needed = 1; vcpu->mmio_is_write = 1; + if ((vcpu->arch.mmio_sp64_extend) && (bytes == 4)) + val = dp_to_sp(val); + /* Store the value at the lowest bytes in 'data'. */ if (!host_swabbed) { switch (bytes) { @@ -985,6 +1156,129 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(kvmppc_handle_store); +#ifdef CONFIG_VSX +static inline int kvmppc_get_vsr_data(struct kvm_vcpu *vcpu, int rs, u64 *val) +{ + u32 dword_offset, word_offset; + union kvmppc_one_reg reg; + int vsx_offset = 0; + int copy_type = vcpu->arch.mmio_vsx_copy_type; + int result = 0; + + switch (copy_type) { + case KVMPPC_VSX_COPY_DWORD: + vsx_offset = + kvmppc_get_vsr_dword_offset(vcpu->arch.mmio_vsx_offset); + + if (vsx_offset == -1) { + result = -1; + break; + } + + if (!vcpu->arch.mmio_vsx_tx_sx_enabled) { + *val = VCPU_VSX_FPR(vcpu, rs, vsx_offset); + } else { + reg.vval = VCPU_VSX_VR(vcpu, rs); + *val = reg.vsxval[vsx_offset]; + } + break; + + case KVMPPC_VSX_COPY_WORD: + vsx_offset = + kvmppc_get_vsr_word_offset(vcpu->arch.mmio_vsx_offset); + + if (vsx_offset == -1) { + result = -1; + break; + } + + if (!vcpu->arch.mmio_vsx_tx_sx_enabled) { + dword_offset = vsx_offset / 2; + word_offset = vsx_offset % 2; + reg.vsxval[0] = VCPU_VSX_FPR(vcpu, rs, dword_offset); + *val = reg.vsx32val[word_offset]; + } else { + reg.vval = VCPU_VSX_VR(vcpu, rs); + *val = reg.vsx32val[vsx_offset]; + } + break; + + default: + result = -1; + break; + } + + return result; +} + +int kvmppc_handle_vsx_store(struct kvm_run *run, struct kvm_vcpu *vcpu, + int rs, unsigned int bytes, int is_default_endian) +{ + u64 val; + enum emulation_result emulated = EMULATE_DONE; + + vcpu->arch.io_gpr = rs; + + /* Currently, mmio_vsx_copy_nums only allowed to be less than 4 */ + if ( (vcpu->arch.mmio_vsx_copy_nums > 4) || + (vcpu->arch.mmio_vsx_copy_nums < 0) ) { + return EMULATE_FAIL; + } + + while (vcpu->arch.mmio_vsx_copy_nums) { + if (kvmppc_get_vsr_data(vcpu, rs, &val) == -1) + return EMULATE_FAIL; + + emulated = kvmppc_handle_store(run, vcpu, + val, bytes, is_default_endian); + + if (emulated != EMULATE_DONE) + break; + + vcpu->arch.paddr_accessed += run->mmio.len; + + vcpu->arch.mmio_vsx_copy_nums--; + vcpu->arch.mmio_vsx_offset++; + } + + return emulated; +} + +static int kvmppc_emulate_mmio_vsx_loadstore(struct kvm_vcpu *vcpu, + struct kvm_run *run) +{ + enum emulation_result emulated = EMULATE_FAIL; + int r; + + vcpu->arch.paddr_accessed += run->mmio.len; + + if (!vcpu->mmio_is_write) { + emulated = kvmppc_handle_vsx_load(run, vcpu, vcpu->arch.io_gpr, + run->mmio.len, 1, vcpu->arch.mmio_sign_extend); + } else { + emulated = kvmppc_handle_vsx_store(run, vcpu, + vcpu->arch.io_gpr, run->mmio.len, 1); + } + + switch (emulated) { + case EMULATE_DO_MMIO: + run->exit_reason = KVM_EXIT_MMIO; + r = RESUME_HOST; + break; + case EMULATE_FAIL: + pr_info("KVM: MMIO emulation failed (VSX repeat)\n"); + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + r = RESUME_HOST; + break; + default: + r = RESUME_GUEST; + break; + } + return r; +} +#endif /* CONFIG_VSX */ + int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) { int r = 0; @@ -1087,13 +1381,24 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) int r; sigset_t sigsaved; - if (vcpu->sigset_active) - sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); - if (vcpu->mmio_needed) { + vcpu->mmio_needed = 0; if (!vcpu->mmio_is_write) kvmppc_complete_mmio_load(vcpu, run); - vcpu->mmio_needed = 0; +#ifdef CONFIG_VSX + if (vcpu->arch.mmio_vsx_copy_nums > 0) { + vcpu->arch.mmio_vsx_copy_nums--; + vcpu->arch.mmio_vsx_offset++; + } + + if (vcpu->arch.mmio_vsx_copy_nums > 0) { + r = kvmppc_emulate_mmio_vsx_loadstore(vcpu, run); + if (r == RESUME_HOST) { + vcpu->mmio_needed = 1; + return r; + } + } +#endif } else if (vcpu->arch.osi_needed) { u64 *gprs = run->osi.gprs; int i; @@ -1115,6 +1420,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) #endif } + if (vcpu->sigset_active) + sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); + if (run->immediate_exit) r = -EINTR; else diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index 497130c..fc67bd7 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -314,6 +314,25 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm, } EXPORT_SYMBOL_GPL(mm_iommu_lookup); +struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm, + unsigned long ua, unsigned long size) +{ + struct mm_iommu_table_group_mem_t *mem, *ret = NULL; + + list_for_each_entry_lockless(mem, &mm->context.iommu_group_mem_list, + next) { + if ((mem->ua <= ua) && + (ua + size <= mem->ua + + (mem->entries << PAGE_SHIFT))) { + ret = mem; + break; + } + } + + return ret; +} +EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm); + struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, unsigned long ua, unsigned long entries) { @@ -345,6 +364,26 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, } EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa); +long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, + unsigned long ua, unsigned long *hpa) +{ + const long entry = (ua - mem->ua) >> PAGE_SHIFT; + void *va = &mem->hpas[entry]; + unsigned long *pa; + + if (entry >= mem->entries) + return -EFAULT; + + pa = (void *) vmalloc_to_phys(va); + if (!pa) + return -EFAULT; + + *hpa = *pa | (ua & ~PAGE_MASK); + + return 0; +} +EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm); + long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem) { if (atomic64_inc_not_zero(&mem->mapped)) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index e367382..ee4cdb5 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1424,8 +1424,7 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe iommu_group_put(pe->table_group.group); BUG_ON(pe->table_group.group); } - pnv_pci_ioda2_table_free_pages(tbl); - iommu_free_table(tbl, of_node_full_name(dev->dev.of_node)); + iommu_tce_table_put(tbl); } static void pnv_ioda_release_vf_PE(struct pci_dev *pdev) @@ -1860,6 +1859,17 @@ static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index, return ret; } + +static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index, + unsigned long *hpa, enum dma_data_direction *direction) +{ + long ret = pnv_tce_xchg(tbl, index, hpa, direction); + + if (!ret) + pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true); + + return ret; +} #endif static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index, @@ -1874,6 +1884,7 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = { .set = pnv_ioda1_tce_build, #ifdef CONFIG_IOMMU_API .exchange = pnv_ioda1_tce_xchg, + .exchange_rm = pnv_ioda1_tce_xchg_rm, #endif .clear = pnv_ioda1_tce_free, .get = pnv_tce_get, @@ -1948,7 +1959,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl, { struct iommu_table_group_link *tgl; - list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) { + list_for_each_entry_lockless(tgl, &tbl->it_group_list, next) { struct pnv_ioda_pe *pe = container_of(tgl->table_group, struct pnv_ioda_pe, table_group); struct pnv_phb *phb = pe->phb; @@ -2004,6 +2015,17 @@ static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index, return ret; } + +static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index, + unsigned long *hpa, enum dma_data_direction *direction) +{ + long ret = pnv_tce_xchg(tbl, index, hpa, direction); + + if (!ret) + pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true); + + return ret; +} #endif static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index, @@ -2017,13 +2039,13 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index, static void pnv_ioda2_table_free(struct iommu_table *tbl) { pnv_pci_ioda2_table_free_pages(tbl); - iommu_free_table(tbl, "pnv"); } static struct iommu_table_ops pnv_ioda2_iommu_ops = { .set = pnv_ioda2_tce_build, #ifdef CONFIG_IOMMU_API .exchange = pnv_ioda2_tce_xchg, + .exchange_rm = pnv_ioda2_tce_xchg_rm, #endif .clear = pnv_ioda2_tce_free, .get = pnv_tce_get, @@ -2203,7 +2225,7 @@ found: __free_pages(tce_mem, get_order(tce32_segsz * segs)); if (tbl) { pnv_pci_unlink_table_and_group(tbl, &pe->table_group); - iommu_free_table(tbl, "pnv"); + iommu_tce_table_put(tbl); } } @@ -2293,16 +2315,16 @@ static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group, if (!tbl) return -ENOMEM; + tbl->it_ops = &pnv_ioda2_iommu_ops; + ret = pnv_pci_ioda2_table_alloc_pages(nid, bus_offset, page_shift, window_size, levels, tbl); if (ret) { - iommu_free_table(tbl, "pnv"); + iommu_tce_table_put(tbl); return ret; } - tbl->it_ops = &pnv_ioda2_iommu_ops; - *ptbl = tbl; return 0; @@ -2343,7 +2365,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe) if (rc) { pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n", rc); - pnv_ioda2_table_free(tbl); + iommu_tce_table_put(tbl); return rc; } @@ -2431,7 +2453,7 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group) pnv_pci_ioda2_unset_window(&pe->table_group, 0); if (pe->pbus) pnv_ioda_setup_bus_dma(pe, pe->pbus, false); - pnv_ioda2_table_free(tbl); + iommu_tce_table_put(tbl); } static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group) @@ -3406,7 +3428,7 @@ static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe) } free_pages(tbl->it_base, get_order(tbl->it_size << 3)); - iommu_free_table(tbl, "pnv"); + iommu_tce_table_put(tbl); } static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe) @@ -3433,7 +3455,7 @@ static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe) } pnv_pci_ioda2_table_free_pages(tbl); - iommu_free_table(tbl, "pnv"); + iommu_tce_table_put(tbl); } static void pnv_ioda_free_pe_seg(struct pnv_ioda_pe *pe, diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index eb835e9..204a829 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -767,6 +767,7 @@ struct iommu_table *pnv_pci_table_alloc(int nid) tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, nid); INIT_LIST_HEAD_RCU(&tbl->it_group_list); + kref_init(&tbl->it_kref); return tbl; } diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 4d757ea..7ce5db2 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -74,6 +74,7 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node) goto fail_exit; INIT_LIST_HEAD_RCU(&tbl->it_group_list); + kref_init(&tbl->it_kref); tgl->table_group = table_group; list_add_rcu(&tgl->next, &tbl->it_group_list); @@ -115,7 +116,7 @@ static void iommu_pseries_free_group(struct iommu_table_group *table_group, BUG_ON(table_group->group); } #endif - iommu_free_table(tbl, node_name); + iommu_tce_table_put(tbl); kfree(table_group); } diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 7204939..28b09fd 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1318,7 +1318,7 @@ static void vio_dev_release(struct device *dev) struct iommu_table *tbl = get_iommu_table_base(dev); if (tbl) - iommu_free_table(tbl, of_node_full_name(dev->of_node)); + iommu_tce_table_put(tbl); of_node_put(dev->of_node); kfree(to_vio_dev(dev)); } diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index de5d572..cd1fa97 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -302,8 +302,8 @@ extern int ignore_sigio_fd(int fd); extern void maybe_sigio_broken(int fd, int read); extern void sigio_broken(int fd, int read); -/* sys-x86_64/prctl.c */ -extern int os_arch_prctl(int pid, int code, unsigned long *addr); +/* prctl.c */ +extern int os_arch_prctl(int pid, int option, unsigned long *arg2); /* tty.c */ extern int get_pty(void); diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 9ba050f..0af59fa 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -390,3 +390,4 @@ 381 i386 pkey_alloc sys_pkey_alloc 382 i386 pkey_free sys_pkey_free 383 i386 statx sys_statx +384 i386 arch_prctl sys_arch_prctl compat_sys_arch_prctl diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index b04bb6d..0fe0044 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -187,6 +187,7 @@ * Reuse free bits when adding new feature flags! */ #define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ #define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d962fa9..f5c942e 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -611,6 +611,8 @@ struct kvm_vcpu_arch { unsigned long dr7; unsigned long eff_db[KVM_NR_DB_REGS]; unsigned long guest_debug_dr7; + u64 msr_platform_info; + u64 msr_misc_features_enables; u64 mcg_cap; u64 mcg_status; @@ -726,6 +728,7 @@ struct kvm_hv { enum kvm_irqchip_mode { KVM_IRQCHIP_NONE, + KVM_IRQCHIP_INIT_IN_PROGRESS, /* temporarily set during creation */ KVM_IRQCHIP_KERNEL, /* created with KVM_CREATE_IRQCHIP */ KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ }; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d8b5f8a..673f9ac 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -45,6 +45,8 @@ #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd #define MSR_PLATFORM_INFO 0x000000ce +#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT 31 +#define MSR_PLATFORM_INFO_CPUID_FAULT BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT) #define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) @@ -127,6 +129,7 @@ /* DEBUGCTLMSR bits (others vary by model): */ #define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ #define DEBUGCTLMSR_TR (1UL << 6) #define DEBUGCTLMSR_BTS (1UL << 7) @@ -552,10 +555,12 @@ #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT) -/* MISC_FEATURE_ENABLES non-architectural features */ -#define MSR_MISC_FEATURE_ENABLES 0x00000140 +/* MISC_FEATURES_ENABLES non-architectural features */ +#define MSR_MISC_FEATURES_ENABLES 0x00000140 -#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT 1 +#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT 0 +#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT) +#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT 1 #define MSR_IA32_TSC_DEADLINE 0x000006E0 diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index f385eca..a80c1b3 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -884,6 +884,8 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, extern int get_tsc_mode(unsigned long adr); extern int set_tsc_mode(unsigned int val); +DECLARE_PER_CPU(u64, msr_misc_features_shadow); + /* Register/unregister a process' MPX related resource */ #define MPX_ENABLE_MANAGEMENT() mpx_enable_management() #define MPX_DISABLE_MANAGEMENT() mpx_disable_management() diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 9b9b30b1..8d3964f 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -9,6 +9,7 @@ void syscall_init(void); #ifdef CONFIG_X86_64 void entry_SYSCALL_64(void); +long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2); #endif #ifdef CONFIG_X86_32 @@ -30,6 +31,7 @@ void x86_report_nx(void); extern int reboot_force; -long do_arch_prctl(struct task_struct *task, int code, unsigned long addr); +long do_arch_prctl_common(struct task_struct *task, int option, + unsigned long cpuid_enabled); #endif /* _ASM_X86_PROTO_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index ad6f5eb0..9fc44b9 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -87,6 +87,7 @@ struct thread_info { #define TIF_SECCOMP 8 /* secure computing */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ +#define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ #define TIF_NOHZ 19 /* in adaptive nohz mode */ @@ -110,6 +111,7 @@ struct thread_info { #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) +#define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_NOHZ (1 << TIF_NOHZ) @@ -138,7 +140,7 @@ struct thread_info { /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP) + (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP) #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) @@ -239,6 +241,8 @@ static inline int arch_within_stack_frames(const void * const stack, extern void arch_task_cache_init(void); extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); extern void arch_release_task_struct(struct task_struct *tsk); +extern void arch_setup_new_exec(void); +#define arch_setup_new_exec arch_setup_new_exec #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_THREAD_INFO_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index fc5abff..75d002b 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -110,6 +110,16 @@ static inline void cr4_clear_bits(unsigned long mask) } } +static inline void cr4_toggle_bits(unsigned long mask) +{ + unsigned long cr4; + + cr4 = this_cpu_read(cpu_tlbstate.cr4); + cr4 ^= mask; + this_cpu_write(cpu_tlbstate.cr4, cr4); + __write_cr4(cr4); +} + /* Read the CR4 shadow. */ static inline unsigned long cr4_read_shadow(void) { diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index 835aa51..c457655 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -1,10 +1,13 @@ #ifndef _ASM_X86_PRCTL_H #define _ASM_X86_PRCTL_H -#define ARCH_SET_GS 0x1001 -#define ARCH_SET_FS 0x1002 -#define ARCH_GET_FS 0x1003 -#define ARCH_GET_GS 0x1004 +#define ARCH_SET_GS 0x1001 +#define ARCH_SET_FS 0x1002 +#define ARCH_GET_FS 0x1003 +#define ARCH_GET_GS 0x1004 + +#define ARCH_GET_CPUID 0x1011 +#define ARCH_SET_CPUID 0x1012 #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 0631977..dfa90a3 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -90,16 +90,12 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) return; } - if (ring3mwait_disabled) { - msr_clear_bit(MSR_MISC_FEATURE_ENABLES, - MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); + if (ring3mwait_disabled) return; - } - - msr_set_bit(MSR_MISC_FEATURE_ENABLES, - MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); set_cpu_cap(c, X86_FEATURE_RING3MWAIT); + this_cpu_or(msr_misc_features_shadow, + 1UL << MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT); if (c == &boot_cpu_data) ELF_HWCAP2 |= HWCAP2_RING3MWAIT; @@ -488,6 +484,34 @@ static void intel_bsp_resume(struct cpuinfo_x86 *c) init_intel_energy_perf(c); } +static void init_cpuid_fault(struct cpuinfo_x86 *c) +{ + u64 msr; + + if (!rdmsrl_safe(MSR_PLATFORM_INFO, &msr)) { + if (msr & MSR_PLATFORM_INFO_CPUID_FAULT) + set_cpu_cap(c, X86_FEATURE_CPUID_FAULT); + } +} + +static void init_intel_misc_features(struct cpuinfo_x86 *c) +{ + u64 msr; + + if (rdmsrl_safe(MSR_MISC_FEATURES_ENABLES, &msr)) + return; + + /* Clear all MISC features */ + this_cpu_write(msr_misc_features_shadow, 0); + + /* Check features and update capabilities and shadow control bits */ + init_cpuid_fault(c); + probe_xeon_phi_r3mwait(c); + + msr = this_cpu_read(msr_misc_features_shadow); + wrmsrl(MSR_MISC_FEATURES_ENABLES, msr); +} + static void init_intel(struct cpuinfo_x86 *c) { unsigned int l2 = 0; @@ -602,7 +626,7 @@ static void init_intel(struct cpuinfo_x86 *c) init_intel_energy_perf(c); - probe_xeon_phi_r3mwait(c); + init_intel_misc_features(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 14f65a5..da5c097 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -396,9 +396,9 @@ static u64 kvm_steal_clock(int cpu) src = &per_cpu(steal_time, cpu); do { version = src->version; - rmb(); + virt_rmb(); steal = src->steal; - rmb(); + virt_rmb(); } while ((version & 1) || (version != src->version)); return steal; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f675915..0bb8842 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -37,6 +37,7 @@ #include <asm/vm86.h> #include <asm/switch_to.h> #include <asm/desc.h> +#include <asm/prctl.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -124,11 +125,6 @@ void flush_thread(void) fpu__clear(&tsk->thread.fpu); } -static void hard_disable_TSC(void) -{ - cr4_set_bits(X86_CR4_TSD); -} - void disable_TSC(void) { preempt_disable(); @@ -137,15 +133,10 @@ void disable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_disable_TSC(); + cr4_set_bits(X86_CR4_TSD); preempt_enable(); } -static void hard_enable_TSC(void) -{ - cr4_clear_bits(X86_CR4_TSD); -} - static void enable_TSC(void) { preempt_disable(); @@ -154,7 +145,7 @@ static void enable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_enable_TSC(); + cr4_clear_bits(X86_CR4_TSD); preempt_enable(); } @@ -182,54 +173,129 @@ int set_tsc_mode(unsigned int val) return 0; } -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss) -{ - struct thread_struct *prev, *next; - - prev = &prev_p->thread; - next = &next_p->thread; +DEFINE_PER_CPU(u64, msr_misc_features_shadow); - if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^ - test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); +static void set_cpuid_faulting(bool on) +{ + u64 msrval; - debugctl &= ~DEBUGCTLMSR_BTF; - if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) - debugctl |= DEBUGCTLMSR_BTF; + msrval = this_cpu_read(msr_misc_features_shadow); + msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT; + msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT); + this_cpu_write(msr_misc_features_shadow, msrval); + wrmsrl(MSR_MISC_FEATURES_ENABLES, msrval); +} - update_debugctlmsr(debugctl); +static void disable_cpuid(void) +{ + preempt_disable(); + if (!test_and_set_thread_flag(TIF_NOCPUID)) { + /* + * Must flip the CPU state synchronously with + * TIF_NOCPUID in the current running context. + */ + set_cpuid_faulting(true); } + preempt_enable(); +} - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) - hard_disable_TSC(); - else - hard_enable_TSC(); +static void enable_cpuid(void) +{ + preempt_disable(); + if (test_and_clear_thread_flag(TIF_NOCPUID)) { + /* + * Must flip the CPU state synchronously with + * TIF_NOCPUID in the current running context. + */ + set_cpuid_faulting(false); } + preempt_enable(); +} + +static int get_cpuid_mode(void) +{ + return !test_thread_flag(TIF_NOCPUID); +} + +static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled) +{ + if (!static_cpu_has(X86_FEATURE_CPUID_FAULT)) + return -ENODEV; + + if (cpuid_enabled) + enable_cpuid(); + else + disable_cpuid(); + + return 0; +} + +/* + * Called immediately after a successful exec. + */ +void arch_setup_new_exec(void) +{ + /* If cpuid was previously disabled for this task, re-enable it. */ + if (test_thread_flag(TIF_NOCPUID)) + enable_cpuid(); +} - if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { +static inline void switch_to_bitmap(struct tss_struct *tss, + struct thread_struct *prev, + struct thread_struct *next, + unsigned long tifp, unsigned long tifn) +{ + if (tifn & _TIF_IO_BITMAP) { /* * Copy the relevant range of the IO bitmap. * Normally this is 128 bytes or less: */ memcpy(tss->io_bitmap, next->io_bitmap_ptr, max(prev->io_bitmap_max, next->io_bitmap_max)); - /* * Make sure that the TSS limit is correct for the CPU * to notice the IO bitmap. */ refresh_tss_limit(); - } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { + } else if (tifp & _TIF_IO_BITMAP) { /* * Clear any possible leftover bits: */ memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } +} + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss) +{ + struct thread_struct *prev, *next; + unsigned long tifp, tifn; + + prev = &prev_p->thread; + next = &next_p->thread; + + tifn = READ_ONCE(task_thread_info(next_p)->flags); + tifp = READ_ONCE(task_thread_info(prev_p)->flags); + switch_to_bitmap(tss, prev, next, tifp, tifn); + propagate_user_return_notify(prev_p, next_p); + + if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) && + arch_has_block_step()) { + unsigned long debugctl, msk; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl &= ~DEBUGCTLMSR_BTF; + msk = tifn & _TIF_BLOCKSTEP; + debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT; + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + } + + if ((tifp ^ tifn) & _TIF_NOTSC) + cr4_toggle_bits(X86_CR4_TSD); + + if ((tifp ^ tifn) & _TIF_NOCPUID) + set_cpuid_faulting(!!(tifn & _TIF_NOCPUID)); } /* @@ -550,3 +616,16 @@ out: put_task_stack(p); return ret; } + +long do_arch_prctl_common(struct task_struct *task, int option, + unsigned long cpuid_enabled) +{ + switch (option) { + case ARCH_GET_CPUID: + return get_cpuid_mode(); + case ARCH_SET_CPUID: + return set_cpuid_mode(task, cpuid_enabled); + } + + return -EINVAL; +} diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 4c818f8..ff40e74 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/kdebug.h> +#include <linux/syscalls.h> #include <asm/pgtable.h> #include <asm/ldt.h> @@ -56,6 +57,7 @@ #include <asm/switch_to.h> #include <asm/vm86.h> #include <asm/intel_rdt.h> +#include <asm/proto.h> void __show_regs(struct pt_regs *regs, int all) { @@ -304,3 +306,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } + +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + return do_arch_prctl_common(current, option, arg2); +} diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index d6b784a..ea1a618 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/ftrace.h> +#include <linux/syscalls.h> #include <asm/pgtable.h> #include <asm/processor.h> @@ -204,7 +205,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, (struct user_desc __user *)tls, 0); else #endif - err = do_arch_prctl(p, ARCH_SET_FS, tls); + err = do_arch_prctl_64(p, ARCH_SET_FS, tls); if (err) goto out; } @@ -547,70 +548,72 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr) } #endif -long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) +long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) { int ret = 0; int doit = task == current; int cpu; - switch (code) { + switch (option) { case ARCH_SET_GS: - if (addr >= TASK_SIZE_MAX) + if (arg2 >= TASK_SIZE_MAX) return -EPERM; cpu = get_cpu(); task->thread.gsindex = 0; - task->thread.gsbase = addr; + task->thread.gsbase = arg2; if (doit) { load_gs_index(0); - ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); + ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, arg2); } put_cpu(); break; case ARCH_SET_FS: /* Not strictly needed for fs, but do it for symmetry with gs */ - if (addr >= TASK_SIZE_MAX) + if (arg2 >= TASK_SIZE_MAX) return -EPERM; cpu = get_cpu(); task->thread.fsindex = 0; - task->thread.fsbase = addr; + task->thread.fsbase = arg2; if (doit) { /* set the selector to 0 to not confuse __switch_to */ loadsegment(fs, 0); - ret = wrmsrl_safe(MSR_FS_BASE, addr); + ret = wrmsrl_safe(MSR_FS_BASE, arg2); } put_cpu(); break; case ARCH_GET_FS: { unsigned long base; + if (doit) rdmsrl(MSR_FS_BASE, base); else base = task->thread.fsbase; - ret = put_user(base, (unsigned long __user *)addr); + ret = put_user(base, (unsigned long __user *)arg2); break; } case ARCH_GET_GS: { unsigned long base; + if (doit) rdmsrl(MSR_KERNEL_GS_BASE, base); else base = task->thread.gsbase; - ret = put_user(base, (unsigned long __user *)addr); + ret = put_user(base, (unsigned long __user *)arg2); break; } #ifdef CONFIG_CHECKPOINT_RESTORE # ifdef CONFIG_X86_X32_ABI case ARCH_MAP_VDSO_X32: - return prctl_map_vdso(&vdso_image_x32, addr); + return prctl_map_vdso(&vdso_image_x32, arg2); # endif # if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION case ARCH_MAP_VDSO_32: - return prctl_map_vdso(&vdso_image_32, addr); + return prctl_map_vdso(&vdso_image_32, arg2); # endif case ARCH_MAP_VDSO_64: - return prctl_map_vdso(&vdso_image_64, addr); + return prctl_map_vdso(&vdso_image_64, arg2); #endif default: @@ -621,10 +624,23 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) return ret; } -long sys_arch_prctl(int code, unsigned long addr) +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + long ret; + + ret = do_arch_prctl_64(current, option, arg2); + if (ret == -EINVAL) + ret = do_arch_prctl_common(current, option, arg2); + + return ret; +} + +#ifdef CONFIG_IA32_EMULATION +COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return do_arch_prctl(current, code, addr); + return do_arch_prctl_common(current, option, arg2); } +#endif unsigned long KSTK_ESP(struct task_struct *task) { diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 2364b23..f37d181 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -396,12 +396,12 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; /* - * When changing the segment base, use do_arch_prctl + * When changing the segment base, use do_arch_prctl_64 * to set either thread.fs or thread.fsindex and the * corresponding GDT slot. */ if (child->thread.fsbase != value) - return do_arch_prctl(child, ARCH_SET_FS, value); + return do_arch_prctl_64(child, ARCH_SET_FS, value); return 0; case offsetof(struct user_regs_struct,gs_base): /* @@ -410,7 +410,7 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; if (child->thread.gsbase != value) - return do_arch_prctl(child, ARCH_SET_GS, value); + return do_arch_prctl_64(child, ARCH_SET_GS, value); return 0; #endif } @@ -869,7 +869,7 @@ long arch_ptrace(struct task_struct *child, long request, Works just like arch_prctl, except that the arguments are reversed. */ case PTRACE_ARCH_PRCTL: - ret = do_arch_prctl(child, data, addr); + ret = do_arch_prctl_64(child, data, addr); break; #endif diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index efde6cc..a181ae7 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -876,6 +876,9 @@ int kvm_emulate_cpuid(struct kvm_vcpu *vcpu) { u32 eax, ebx, ecx, edx; + if (cpuid_fault_enabled(vcpu) && !kvm_require_cpl(vcpu, 0)) + return 1; + eax = kvm_register_read(vcpu, VCPU_REGS_RAX); ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 35058c2..a6fd40a 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -205,4 +205,15 @@ static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu) return x86_stepping(best->eax); } +static inline bool supports_cpuid_fault(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.msr_platform_info & MSR_PLATFORM_INFO_CPUID_FAULT; +} + +static inline bool cpuid_fault_enabled(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.msr_misc_features_enables & + MSR_MISC_FEATURES_ENABLES_CPUID_FAULT; +} + #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 45c7306..6a2ea94 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3854,6 +3854,13 @@ static int em_sti(struct x86_emulate_ctxt *ctxt) static int em_cpuid(struct x86_emulate_ctxt *ctxt) { u32 eax, ebx, ecx, edx; + u64 msr = 0; + + ctxt->ops->get_msr(ctxt, MSR_MISC_FEATURES_ENABLES, &msr); + if (msr & MSR_MISC_FEATURES_ENABLES_CPUID_FAULT && + ctxt->ops->cpl(ctxt)) { + return emulate_gp(ctxt, 0); + } eax = reg_read(ctxt, VCPU_REGS_RAX); ecx = reg_read(ctxt, VCPU_REGS_RCX); diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 047b17a..bdcd413 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -49,7 +49,7 @@ static void pic_unlock(struct kvm_pic *s) __releases(&s->lock) { bool wakeup = s->wakeup_needed; - struct kvm_vcpu *vcpu, *found = NULL; + struct kvm_vcpu *vcpu; int i; s->wakeup_needed = false; @@ -59,16 +59,11 @@ static void pic_unlock(struct kvm_pic *s) if (wakeup) { kvm_for_each_vcpu(i, vcpu, s->kvm) { if (kvm_apic_accept_pic_intr(vcpu)) { - found = vcpu; - break; + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + return; } } - - if (!found) - return; - - kvm_make_request(KVM_REQ_EVENT, found); - kvm_vcpu_kick(found); } } @@ -239,7 +234,7 @@ static inline void pic_intack(struct kvm_kpic_state *s, int irq) int kvm_pic_read_irq(struct kvm *kvm) { int irq, irq2, intno; - struct kvm_pic *s = pic_irqchip(kvm); + struct kvm_pic *s = kvm->arch.vpic; s->output = 0; @@ -273,7 +268,7 @@ int kvm_pic_read_irq(struct kvm *kvm) return intno; } -void kvm_pic_reset(struct kvm_kpic_state *s) +static void kvm_pic_reset(struct kvm_kpic_state *s) { int irq, i; struct kvm_vcpu *vcpu; @@ -422,19 +417,16 @@ static u32 pic_poll_read(struct kvm_kpic_state *s, u32 addr1) return ret; } -static u32 pic_ioport_read(void *opaque, u32 addr1) +static u32 pic_ioport_read(void *opaque, u32 addr) { struct kvm_kpic_state *s = opaque; - unsigned int addr; int ret; - addr = addr1; - addr &= 1; if (s->poll) { - ret = pic_poll_read(s, addr1); + ret = pic_poll_read(s, addr); s->poll = 0; } else - if (addr == 0) + if ((addr & 1) == 0) if (s->read_reg_select) ret = s->isr; else @@ -456,76 +448,64 @@ static u32 elcr_ioport_read(void *opaque, u32 addr1) return s->elcr; } -static int picdev_in_range(gpa_t addr) -{ - switch (addr) { - case 0x20: - case 0x21: - case 0xa0: - case 0xa1: - case 0x4d0: - case 0x4d1: - return 1; - default: - return 0; - } -} - static int picdev_write(struct kvm_pic *s, gpa_t addr, int len, const void *val) { unsigned char data = *(unsigned char *)val; - if (!picdev_in_range(addr)) - return -EOPNOTSUPP; if (len != 1) { pr_pic_unimpl("non byte write\n"); return 0; } - pic_lock(s); switch (addr) { case 0x20: case 0x21: case 0xa0: case 0xa1: + pic_lock(s); pic_ioport_write(&s->pics[addr >> 7], addr, data); + pic_unlock(s); break; case 0x4d0: case 0x4d1: + pic_lock(s); elcr_ioport_write(&s->pics[addr & 1], addr, data); + pic_unlock(s); break; + default: + return -EOPNOTSUPP; } - pic_unlock(s); return 0; } static int picdev_read(struct kvm_pic *s, gpa_t addr, int len, void *val) { - unsigned char data = 0; - if (!picdev_in_range(addr)) - return -EOPNOTSUPP; + unsigned char *data = (unsigned char *)val; if (len != 1) { memset(val, 0, len); pr_pic_unimpl("non byte read\n"); return 0; } - pic_lock(s); switch (addr) { case 0x20: case 0x21: case 0xa0: case 0xa1: - data = pic_ioport_read(&s->pics[addr >> 7], addr); + pic_lock(s); + *data = pic_ioport_read(&s->pics[addr >> 7], addr); + pic_unlock(s); break; case 0x4d0: case 0x4d1: - data = elcr_ioport_read(&s->pics[addr & 1], addr); + pic_lock(s); + *data = elcr_ioport_read(&s->pics[addr & 1], addr); + pic_unlock(s); break; + default: + return -EOPNOTSUPP; } - *(unsigned char *)val = data; - pic_unlock(s); return 0; } @@ -576,7 +556,7 @@ static int picdev_eclr_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, */ static void pic_irq_request(struct kvm *kvm, int level) { - struct kvm_pic *s = pic_irqchip(kvm); + struct kvm_pic *s = kvm->arch.vpic; if (!s->output) s->wakeup_needed = true; @@ -660,9 +640,11 @@ void kvm_pic_destroy(struct kvm *kvm) if (!vpic) return; + mutex_lock(&kvm->slots_lock); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr); + mutex_unlock(&kvm->slots_lock); kvm->arch.vpic = NULL; kfree(vpic); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 289270a..bdff437 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -266,11 +266,9 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors) spin_unlock(&ioapic->lock); } -void kvm_vcpu_request_scan_ioapic(struct kvm *kvm) +void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm) { - struct kvm_ioapic *ioapic = kvm->arch.vioapic; - - if (!ioapic) + if (!ioapic_in_kernel(kvm)) return; kvm_make_scan_ioapic_request(kvm); } @@ -315,7 +313,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG && ioapic->irr & (1 << index)) ioapic_service(ioapic, index, false); - kvm_vcpu_request_scan_ioapic(ioapic->kvm); + kvm_make_scan_ioapic_request(ioapic->kvm); break; } } @@ -624,10 +622,8 @@ int kvm_ioapic_init(struct kvm *kvm) if (ret < 0) { kvm->arch.vioapic = NULL; kfree(ioapic); - return ret; } - kvm_vcpu_request_scan_ioapic(kvm); return ret; } @@ -639,36 +635,32 @@ void kvm_ioapic_destroy(struct kvm *kvm) return; cancel_delayed_work_sync(&ioapic->eoi_inject); + mutex_lock(&kvm->slots_lock); kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); + mutex_unlock(&kvm->slots_lock); kvm->arch.vioapic = NULL; kfree(ioapic); } -int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) +void kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) { - struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); - if (!ioapic) - return -EINVAL; + struct kvm_ioapic *ioapic = kvm->arch.vioapic; spin_lock(&ioapic->lock); memcpy(state, ioapic, sizeof(struct kvm_ioapic_state)); state->irr &= ~ioapic->irr_delivered; spin_unlock(&ioapic->lock); - return 0; } -int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) +void kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) { - struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); - if (!ioapic) - return -EINVAL; + struct kvm_ioapic *ioapic = kvm->arch.vioapic; spin_lock(&ioapic->lock); memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); ioapic->irr = 0; ioapic->irr_delivered = 0; - kvm_vcpu_request_scan_ioapic(kvm); + kvm_make_scan_ioapic_request(kvm); kvm_ioapic_inject_all(ioapic, state->irr); spin_unlock(&ioapic->lock); - return 0; } diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 1cc6e54..29ce197 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -105,17 +105,13 @@ do { \ #define ASSERT(x) do { } while (0) #endif -static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) -{ - return kvm->arch.vioapic; -} - static inline int ioapic_in_kernel(struct kvm *kvm) { - int ret; + int mode = kvm->arch.irqchip_mode; - ret = (ioapic_irqchip(kvm) != NULL); - return ret; + /* Matches smp_wmb() when setting irqchip_mode */ + smp_rmb(); + return mode == KVM_IRQCHIP_KERNEL; } void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); @@ -132,8 +128,8 @@ void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id); int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, struct dest_map *dest_map); -int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); -int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); +void kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); +void kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors); void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 60d91c9..5c24811 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -60,7 +60,7 @@ static int kvm_cpu_has_extint(struct kvm_vcpu *v) if (irqchip_split(v->kvm)) return pending_userspace_extint(v); else - return pic_irqchip(v->kvm)->output; + return v->kvm->arch.vpic->output; } else return 0; } diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 40d5b2c..0edd22c 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -78,40 +78,42 @@ void kvm_pic_destroy(struct kvm *kvm); int kvm_pic_read_irq(struct kvm *kvm); void kvm_pic_update_irq(struct kvm_pic *s); -static inline struct kvm_pic *pic_irqchip(struct kvm *kvm) -{ - return kvm->arch.vpic; -} - static inline int pic_in_kernel(struct kvm *kvm) { - int ret; + int mode = kvm->arch.irqchip_mode; - ret = (pic_irqchip(kvm) != NULL); - return ret; + /* Matches smp_wmb() when setting irqchip_mode */ + smp_rmb(); + return mode == KVM_IRQCHIP_KERNEL; } static inline int irqchip_split(struct kvm *kvm) { - return kvm->arch.irqchip_mode == KVM_IRQCHIP_SPLIT; + int mode = kvm->arch.irqchip_mode; + + /* Matches smp_wmb() when setting irqchip_mode */ + smp_rmb(); + return mode == KVM_IRQCHIP_SPLIT; } static inline int irqchip_kernel(struct kvm *kvm) { - return kvm->arch.irqchip_mode == KVM_IRQCHIP_KERNEL; + int mode = kvm->arch.irqchip_mode; + + /* Matches smp_wmb() when setting irqchip_mode */ + smp_rmb(); + return mode == KVM_IRQCHIP_KERNEL; } static inline int irqchip_in_kernel(struct kvm *kvm) { - bool ret = kvm->arch.irqchip_mode != KVM_IRQCHIP_NONE; + int mode = kvm->arch.irqchip_mode; - /* Matches with wmb after initializing kvm->irq_routing. */ + /* Matches smp_wmb() when setting irqchip_mode */ smp_rmb(); - return ret; + return mode > KVM_IRQCHIP_INIT_IN_PROGRESS; } -void kvm_pic_reset(struct kvm_kpic_state *s); - void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu); void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 6825cd3..4517a4c 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -42,7 +42,7 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { - struct kvm_pic *pic = pic_irqchip(kvm); + struct kvm_pic *pic = kvm->arch.vpic; return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level); } @@ -232,11 +232,11 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) goto unlock; } clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); - if (!ioapic_in_kernel(kvm)) + if (!irqchip_kernel(kvm)) goto unlock; kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id); - kvm_pic_clear_all(pic_irqchip(kvm), irq_source_id); + kvm_pic_clear_all(kvm->arch.vpic, irq_source_id); unlock: mutex_unlock(&kvm->irq_lock); } @@ -278,38 +278,35 @@ int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { - int r = -EINVAL; - int delta; - unsigned max_pin; + /* also allow creation of routes during KVM_IRQCHIP_INIT_IN_PROGRESS */ + if (kvm->arch.irqchip_mode == KVM_IRQCHIP_NONE) + return -EINVAL; + /* Matches smp_wmb() when setting irqchip_mode */ + smp_rmb(); switch (ue->type) { case KVM_IRQ_ROUTING_IRQCHIP: - delta = 0; + if (irqchip_split(kvm)) + return -EINVAL; + e->irqchip.pin = ue->u.irqchip.pin; switch (ue->u.irqchip.irqchip) { case KVM_IRQCHIP_PIC_SLAVE: - delta = 8; + e->irqchip.pin += PIC_NUM_PINS / 2; /* fall through */ case KVM_IRQCHIP_PIC_MASTER: - if (!pic_in_kernel(kvm)) - goto out; - + if (ue->u.irqchip.pin >= PIC_NUM_PINS / 2) + return -EINVAL; e->set = kvm_set_pic_irq; - max_pin = PIC_NUM_PINS; break; case KVM_IRQCHIP_IOAPIC: - if (!ioapic_in_kernel(kvm)) - goto out; - - max_pin = KVM_IOAPIC_NUM_PINS; + if (ue->u.irqchip.pin >= KVM_IOAPIC_NUM_PINS) + return -EINVAL; e->set = kvm_set_ioapic_irq; break; default: - goto out; + return -EINVAL; } e->irqchip.irqchip = ue->u.irqchip.irqchip; - e->irqchip.pin = ue->u.irqchip.pin + delta; - if (e->irqchip.pin >= max_pin) - goto out; break; case KVM_IRQ_ROUTING_MSI: e->set = kvm_set_msi; @@ -318,7 +315,7 @@ int kvm_set_routing_entry(struct kvm *kvm, e->msi.data = ue->u.msi.data; if (kvm_msi_route_invalid(kvm, e)) - goto out; + return -EINVAL; break; case KVM_IRQ_ROUTING_HV_SINT: e->set = kvm_hv_set_sint; @@ -326,12 +323,10 @@ int kvm_set_routing_entry(struct kvm *kvm, e->hv_sint.sint = ue->u.hv_sint.sint; break; default: - goto out; + return -EINVAL; } - r = 0; -out: - return r; + return 0; } bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1b203ab..c41f03e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1198,10 +1198,13 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_CLGI); set_intercept(svm, INTERCEPT_SKINIT); set_intercept(svm, INTERCEPT_WBINVD); - set_intercept(svm, INTERCEPT_MONITOR); - set_intercept(svm, INTERCEPT_MWAIT); set_intercept(svm, INTERCEPT_XSETBV); + if (!kvm_mwait_in_guest()) { + set_intercept(svm, INTERCEPT_MONITOR); + set_intercept(svm, INTERCEPT_MWAIT); + } + control->iopm_base_pa = iopm_base; control->msrpm_base_pa = __pa(svm->msrpm); control->int_ctl = V_INTR_MASKING_MASK; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index cfdb0d9..a4ef637 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -84,9 +84,6 @@ module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO); static bool __read_mostly emulate_invalid_guest_state = true; module_param(emulate_invalid_guest_state, bool, S_IRUGO); -static bool __read_mostly vmm_exclusive = 1; -module_param(vmm_exclusive, bool, S_IRUGO); - static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); @@ -910,8 +907,6 @@ static void nested_release_page_clean(struct page *page) static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu); static u64 construct_eptp(unsigned long root_hpa); -static void kvm_cpu_vmxon(u64 addr); -static void kvm_cpu_vmxoff(void); static bool vmx_xsaves_supported(void); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static void vmx_set_segment(struct kvm_vcpu *vcpu, @@ -2231,15 +2226,10 @@ static void decache_tsc_multiplier(struct vcpu_vmx *vmx) static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); bool already_loaded = vmx->loaded_vmcs->cpu == cpu; - if (!vmm_exclusive) - kvm_cpu_vmxon(phys_addr); - else if (!already_loaded) - loaded_vmcs_clear(vmx->loaded_vmcs); - if (!already_loaded) { + loaded_vmcs_clear(vmx->loaded_vmcs); local_irq_disable(); crash_disable_local_vmclear(cpu); @@ -2317,11 +2307,6 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) vmx_vcpu_pi_put(vcpu); __vmx_load_host_state(to_vmx(vcpu)); - if (!vmm_exclusive) { - __loaded_vmcs_clear(to_vmx(vcpu)->loaded_vmcs); - vcpu->cpu = -1; - kvm_cpu_vmxoff(); - } } static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu); @@ -3416,6 +3401,7 @@ static __init int vmx_disabled_by_bios(void) static void kvm_cpu_vmxon(u64 addr) { + cr4_set_bits(X86_CR4_VMXE); intel_pt_handle_vmx(1); asm volatile (ASM_VMX_VMXON_RAX @@ -3458,12 +3444,8 @@ static int hardware_enable(void) /* enable and lock */ wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits); } - cr4_set_bits(X86_CR4_VMXE); - - if (vmm_exclusive) { - kvm_cpu_vmxon(phys_addr); - ept_sync_global(); - } + kvm_cpu_vmxon(phys_addr); + ept_sync_global(); native_store_gdt(this_cpu_ptr(&host_gdt)); @@ -3489,15 +3471,13 @@ static void kvm_cpu_vmxoff(void) asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc"); intel_pt_handle_vmx(0); + cr4_clear_bits(X86_CR4_VMXE); } static void hardware_disable(void) { - if (vmm_exclusive) { - vmclear_local_loaded_vmcss(); - kvm_cpu_vmxoff(); - } - cr4_clear_bits(X86_CR4_VMXE); + vmclear_local_loaded_vmcss(); + kvm_cpu_vmxoff(); } static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, @@ -3547,11 +3527,13 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MOV_DR_EXITING | CPU_BASED_USE_TSC_OFFSETING | - CPU_BASED_MWAIT_EXITING | - CPU_BASED_MONITOR_EXITING | CPU_BASED_INVLPG_EXITING | CPU_BASED_RDPMC_EXITING; + if (!kvm_mwait_in_guest()) + min |= CPU_BASED_MWAIT_EXITING | + CPU_BASED_MONITOR_EXITING; + opt = CPU_BASED_TPR_SHADOW | CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; @@ -6221,7 +6203,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) * page table accesses are reads or writes. */ u64 eptp = nested_ept_get_cr3(vcpu); - if (eptp & VMX_EPT_AD_ENABLE_BIT) + if (!(eptp & VMX_EPT_AD_ENABLE_BIT)) exit_qualification &= ~EPT_VIOLATION_ACC_WRITE; } @@ -9170,11 +9152,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->loaded_vmcs->shadow_vmcs = NULL; if (!vmx->loaded_vmcs->vmcs) goto free_msrs; - if (!vmm_exclusive) - kvm_cpu_vmxon(__pa(per_cpu(vmxarea, raw_smp_processor_id()))); loaded_vmcs_init(vmx->loaded_vmcs); - if (!vmm_exclusive) - kvm_cpu_vmxoff(); cpu = get_cpu(); vmx_vcpu_load(&vmx->vcpu, cpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6bc47e2..f68c5b2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1007,6 +1007,8 @@ static u32 emulated_msrs[] = { MSR_IA32_MCG_CTL, MSR_IA32_MCG_EXT_CTL, MSR_IA32_SMBASE, + MSR_PLATFORM_INFO, + MSR_MISC_FEATURES_ENABLES, }; static unsigned num_emulated_msrs; @@ -1443,10 +1445,10 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; - s64 usdiff; bool matched; bool already_matched; u64 data = msr->data; + bool synchronizing = false; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); offset = kvm_compute_tsc_offset(vcpu, data); @@ -1454,51 +1456,34 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) elapsed = ns - kvm->arch.last_tsc_nsec; if (vcpu->arch.virtual_tsc_khz) { - int faulted = 0; - - /* n.b - signed multiplication and division required */ - usdiff = data - kvm->arch.last_tsc_write; -#ifdef CONFIG_X86_64 - usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz; -#else - /* do_div() only does unsigned */ - asm("1: idivl %[divisor]\n" - "2: xor %%edx, %%edx\n" - " movl $0, %[faulted]\n" - "3:\n" - ".section .fixup,\"ax\"\n" - "4: movl $1, %[faulted]\n" - " jmp 3b\n" - ".previous\n" - - _ASM_EXTABLE(1b, 4b) - - : "=A"(usdiff), [faulted] "=r" (faulted) - : "A"(usdiff * 1000), [divisor] "rm"(vcpu->arch.virtual_tsc_khz)); - -#endif - do_div(elapsed, 1000); - usdiff -= elapsed; - if (usdiff < 0) - usdiff = -usdiff; - - /* idivl overflow => difference is larger than USEC_PER_SEC */ - if (faulted) - usdiff = USEC_PER_SEC; - } else - usdiff = USEC_PER_SEC; /* disable TSC match window below */ + if (data == 0 && msr->host_initiated) { + /* + * detection of vcpu initialization -- need to sync + * with other vCPUs. This particularly helps to keep + * kvm_clock stable after CPU hotplug + */ + synchronizing = true; + } else { + u64 tsc_exp = kvm->arch.last_tsc_write + + nsec_to_cycles(vcpu, elapsed); + u64 tsc_hz = vcpu->arch.virtual_tsc_khz * 1000LL; + /* + * Special case: TSC write with a small delta (1 second) + * of virtual cycle time against real time is + * interpreted as an attempt to synchronize the CPU. + */ + synchronizing = data < tsc_exp + tsc_hz && + data + tsc_hz > tsc_exp; + } + } /* - * Special case: TSC write with a small delta (1 second) of virtual - * cycle time against real time is interpreted as an attempt to - * synchronize the CPU. - * * For a reliable TSC, we can match TSC offsets, and for an unstable * TSC, we add elapsed time in this computation. We could let the * compensation code attempt to catch up if we fall behind, but * it's better to try to match offsets from the beginning. */ - if (usdiff < USEC_PER_SEC && + if (synchronizing && vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) { if (!check_tsc_unstable()) { offset = kvm->arch.cur_tsc_offset; @@ -1774,7 +1759,7 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) #endif } -static u64 __get_kvmclock_ns(struct kvm *kvm) +u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; @@ -1795,18 +1780,6 @@ static u64 __get_kvmclock_ns(struct kvm *kvm) return __pvclock_read_cycles(&hv_clock, rdtsc()); } -u64 get_kvmclock_ns(struct kvm *kvm) -{ - unsigned long flags; - s64 ns; - - local_irq_save(flags); - ns = __get_kvmclock_ns(kvm); - local_irq_restore(flags); - - return ns; -} - static void kvm_setup_pvclock_page(struct kvm_vcpu *v) { struct kvm_vcpu_arch *vcpu = &v->arch; @@ -2154,6 +2127,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_VM_HSAVE_PA: case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: + case MSR_AMD64_DC_CFG: break; case MSR_EFER: @@ -2330,6 +2304,21 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.osvw.status = data; break; + case MSR_PLATFORM_INFO: + if (!msr_info->host_initiated || + data & ~MSR_PLATFORM_INFO_CPUID_FAULT || + (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) && + cpuid_fault_enabled(vcpu))) + return 1; + vcpu->arch.msr_platform_info = data; + break; + case MSR_MISC_FEATURES_ENABLES: + if (data & ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT || + (data & MSR_MISC_FEATURES_ENABLES_CPUID_FAULT && + !supports_cpuid_fault(vcpu))) + return 1; + vcpu->arch.msr_misc_features_enables = data; + break; default: if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); @@ -2416,6 +2405,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_FAM10H_MMIO_CONF_BASE: case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: + case MSR_AMD64_DC_CFG: msr_info->data = 0; break; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: @@ -2544,6 +2534,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; msr_info->data = vcpu->arch.osvw.status; break; + case MSR_PLATFORM_INFO: + msr_info->data = vcpu->arch.msr_platform_info; + break; + case MSR_MISC_FEATURES_ENABLES: + msr_info->data = vcpu->arch.msr_misc_features_enables; + break; default: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); @@ -2679,6 +2675,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ADJUST_CLOCK: r = KVM_CLOCK_TSC_STABLE; break; + case KVM_CAP_X86_GUEST_MWAIT: + r = kvm_mwait_in_guest(); + break; case KVM_CAP_X86_SMM: /* SMBASE is usually relocated above 1M on modern chipsets, * and SMM handlers might indeed rely on 4G segment limits, @@ -3715,22 +3714,21 @@ static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) { + struct kvm_pic *pic = kvm->arch.vpic; int r; r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_PIC_MASTER: - memcpy(&chip->chip.pic, - &pic_irqchip(kvm)->pics[0], + memcpy(&chip->chip.pic, &pic->pics[0], sizeof(struct kvm_pic_state)); break; case KVM_IRQCHIP_PIC_SLAVE: - memcpy(&chip->chip.pic, - &pic_irqchip(kvm)->pics[1], + memcpy(&chip->chip.pic, &pic->pics[1], sizeof(struct kvm_pic_state)); break; case KVM_IRQCHIP_IOAPIC: - r = kvm_get_ioapic(kvm, &chip->chip.ioapic); + kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -3741,32 +3739,31 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) { + struct kvm_pic *pic = kvm->arch.vpic; int r; r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_PIC_MASTER: - spin_lock(&pic_irqchip(kvm)->lock); - memcpy(&pic_irqchip(kvm)->pics[0], - &chip->chip.pic, + spin_lock(&pic->lock); + memcpy(&pic->pics[0], &chip->chip.pic, sizeof(struct kvm_pic_state)); - spin_unlock(&pic_irqchip(kvm)->lock); + spin_unlock(&pic->lock); break; case KVM_IRQCHIP_PIC_SLAVE: - spin_lock(&pic_irqchip(kvm)->lock); - memcpy(&pic_irqchip(kvm)->pics[1], - &chip->chip.pic, + spin_lock(&pic->lock); + memcpy(&pic->pics[1], &chip->chip.pic, sizeof(struct kvm_pic_state)); - spin_unlock(&pic_irqchip(kvm)->lock); + spin_unlock(&pic->lock); break; case KVM_IRQCHIP_IOAPIC: - r = kvm_set_ioapic(kvm, &chip->chip.ioapic); + kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; break; } - kvm_pic_update_irq(pic_irqchip(kvm)); + kvm_pic_update_irq(pic); return r; } @@ -3928,9 +3925,14 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, goto split_irqchip_unlock; if (kvm->created_vcpus) goto split_irqchip_unlock; + kvm->arch.irqchip_mode = KVM_IRQCHIP_INIT_IN_PROGRESS; r = kvm_setup_empty_irq_routing(kvm); - if (r) + if (r) { + kvm->arch.irqchip_mode = KVM_IRQCHIP_NONE; + /* Pairs with smp_rmb() when reading irqchip_mode */ + smp_wmb(); goto split_irqchip_unlock; + } /* Pairs with irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; @@ -4012,20 +4014,18 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_ioapic_init(kvm); if (r) { - mutex_lock(&kvm->slots_lock); kvm_pic_destroy(kvm); - mutex_unlock(&kvm->slots_lock); goto create_irqchip_unlock; } + kvm->arch.irqchip_mode = KVM_IRQCHIP_INIT_IN_PROGRESS; r = kvm_setup_default_irq_routing(kvm); if (r) { - mutex_lock(&kvm->slots_lock); - mutex_lock(&kvm->irq_lock); + kvm->arch.irqchip_mode = KVM_IRQCHIP_NONE; + /* Pairs with smp_rmb() when reading irqchip_mode */ + smp_wmb(); kvm_ioapic_destroy(kvm); kvm_pic_destroy(kvm); - mutex_unlock(&kvm->irq_lock); - mutex_unlock(&kvm->slots_lock); goto create_irqchip_unlock; } /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ @@ -4190,10 +4190,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; r = 0; - local_irq_disable(); - now_ns = __get_kvmclock_ns(kvm); + now_ns = get_kvmclock_ns(kvm); kvm->arch.kvmclock_offset += user_ns.clock - now_ns; - local_irq_enable(); kvm_gen_update_masterclock(kvm); break; } @@ -4201,11 +4199,9 @@ long kvm_arch_vm_ioctl(struct file *filp, struct kvm_clock_data user_ns; u64 now_ns; - local_irq_disable(); - now_ns = __get_kvmclock_ns(kvm); + now_ns = get_kvmclock_ns(kvm); user_ns.clock = now_ns; user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0; - local_irq_enable(); memset(&user_ns.pad, 0, sizeof(user_ns.pad)); r = -EFAULT; @@ -7724,6 +7720,9 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) if (!init_event) { kvm_pmu_reset(vcpu); vcpu->arch.smbase = 0x30000; + + vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; + vcpu->arch.msr_misc_features_enables = 0; } memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index e8ff3e4..6120670 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -1,6 +1,8 @@ #ifndef ARCH_X86_KVM_X86_H #define ARCH_X86_KVM_X86_H +#include <asm/processor.h> +#include <asm/mwait.h> #include <linux/kvm_host.h> #include <asm/pvclock.h> #include "kvm_cache_regs.h" @@ -212,4 +214,38 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) __rem; \ }) +static inline bool kvm_mwait_in_guest(void) +{ + unsigned int eax, ebx, ecx, edx; + + if (!cpu_has(&boot_cpu_data, X86_FEATURE_MWAIT)) + return false; + + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + /* All AMD CPUs have a working MWAIT implementation */ + return true; + case X86_VENDOR_INTEL: + /* Handle Intel below */ + break; + default: + return false; + } + + /* + * Intel CPUs without CPUID5_ECX_INTERRUPT_BREAK are problematic as + * they would allow guest to stop the CPU completely by disabling + * interrupts then invoking MWAIT. + */ + if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF) + return false; + + cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); + + if (!(ecx & CPUID5_ECX_INTERRUPT_BREAK)) + return false; + + return true; +} + #endif diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index e7e7055..69f0827 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -16,7 +16,7 @@ obj-y = bug.o bugs_$(BITS).o delay.o fault.o ldt.o \ ifeq ($(CONFIG_X86_32),y) -obj-y += checksum_32.o +obj-y += checksum_32.o syscalls_32.o obj-$(CONFIG_ELF_CORE) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h index e59eef2..b291ca5 100644 --- a/arch/x86/um/asm/ptrace.h +++ b/arch/x86/um/asm/ptrace.h @@ -78,7 +78,7 @@ static inline int ptrace_set_thread_area(struct task_struct *child, int idx, return -ENOSYS; } -extern long arch_prctl(struct task_struct *task, int code, +extern long arch_prctl(struct task_struct *task, int option, unsigned long __user *addr); #endif diff --git a/arch/x86/um/os-Linux/prctl.c b/arch/x86/um/os-Linux/prctl.c index 96eb2bd..8431e87 100644 --- a/arch/x86/um/os-Linux/prctl.c +++ b/arch/x86/um/os-Linux/prctl.c @@ -6,7 +6,7 @@ #include <sys/ptrace.h> #include <asm/ptrace.h> -int os_arch_prctl(int pid, int code, unsigned long *addr) +int os_arch_prctl(int pid, int option, unsigned long *arg2) { - return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) addr, code); + return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) arg2, option); } diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c new file mode 100644 index 0000000..627d688 --- /dev/null +++ b/arch/x86/um/syscalls_32.c @@ -0,0 +1,7 @@ +#include <linux/syscalls.h> +#include <os.h> + +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) +{ + return -EINVAL; +} diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c index 10d9070..58f5166 100644 --- a/arch/x86/um/syscalls_64.c +++ b/arch/x86/um/syscalls_64.c @@ -7,13 +7,15 @@ #include <linux/sched.h> #include <linux/sched/mm.h> +#include <linux/syscalls.h> #include <linux/uaccess.h> #include <asm/prctl.h> /* XXX This should get the constants from libc */ #include <os.h> -long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) +long arch_prctl(struct task_struct *task, int option, + unsigned long __user *arg2) { - unsigned long *ptr = addr, tmp; + unsigned long *ptr = arg2, tmp; long ret; int pid = task->mm->context.id.u.pid; @@ -30,7 +32,7 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) * arch_prctl is run on the host, then the registers are read * back. */ - switch (code) { + switch (option) { case ARCH_SET_FS: case ARCH_SET_GS: ret = restore_registers(pid, ¤t->thread.regs.regs); @@ -50,11 +52,11 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) ptr = &tmp; } - ret = os_arch_prctl(pid, code, ptr); + ret = os_arch_prctl(pid, option, ptr); if (ret) return ret; - switch (code) { + switch (option) { case ARCH_SET_FS: current->thread.arch.fs = (unsigned long) ptr; ret = save_registers(pid, ¤t->thread.regs.regs); @@ -63,19 +65,19 @@ long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr) ret = save_registers(pid, ¤t->thread.regs.regs); break; case ARCH_GET_FS: - ret = put_user(tmp, addr); + ret = put_user(tmp, arg2); break; case ARCH_GET_GS: - ret = put_user(tmp, addr); + ret = put_user(tmp, arg2); break; } return ret; } -long sys_arch_prctl(int code, unsigned long addr) +SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return arch_prctl(current, code, (unsigned long __user *) addr); + return arch_prctl(current, option, (unsigned long __user *) arg2); } void arch_switch_to(struct task_struct *to) |
