diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2026-05-21 15:02:54 -0700 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2026-05-28 14:02:21 -0700 |
| commit | d44646fc9eeb423ad50f3043f11f66f491d908a7 (patch) | |
| tree | 18e6b3eda2c313c246ba18b88b4e06b2e18432c2 /arch | |
| parent | 0cf905cb9a12dbfb5d14896729b74508f83f73df (diff) | |
| parent | 3e20009988e2470063824c58b19d1c80816cc46d (diff) | |
| download | linux-next-history-d44646fc9eeb423ad50f3043f11f66f491d908a7.tar.gz | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR (net-7.1-rc6).
Conflicts:
drivers/net/phy/air_en8811h.c
d895767c33781 ("net: phy: air_en8811h: add AN8811HB MCU assert/deassert support")
dddfadd75197e ("net: phy: Add Airoha phy library for shared code")
5226bb6634cdf ("net: phy: air_phy_lib: Factorize BuckPBus register accessors")
e08f0ea6daf2e ("net: phy: Rename Airoha common BuckPBus register accessors")
net/sched/sch_netem.c
a2f6ed7b4873 ("net/sched: netem: add per-impairment extended statistics")
9552b11e3eda ("net/sched: fix packet loop on netem when duplicate is on")
Adjacent changes:
drivers/dpll/zl3073x/core.c
c1224569cef0 ("dpll: zl3073x: make frequency monitor a per-device attribute")
54e65df8cf18 ("dpll: zl3073x: report FFO as DPLL vs input reference offset")
net/iucv/af_iucv.c
347fdd4df85f ("af_iucv: convert to getsockopt_iter")
3589d20a666c ("net/iucv: fix locking in .getsockopt")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'arch')
39 files changed, 345 insertions, 129 deletions
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index f463a654a2bbd..cc0702fa64a79 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -409,7 +409,7 @@ __AARCH64_INSN_FUNCS(cbz, 0x7F000000, 0x34000000) __AARCH64_INSN_FUNCS(cbnz, 0x7F000000, 0x35000000) __AARCH64_INSN_FUNCS(tbz, 0x7F000000, 0x36000000) __AARCH64_INSN_FUNCS(tbnz, 0x7F000000, 0x37000000) -__AARCH64_INSN_FUNCS(bcond, 0xFF000010, 0x54000000) +__AARCH64_INSN_FUNCS(bcond, 0xFF000000, 0x54000000) __AARCH64_INSN_FUNCS(svc, 0xFFE0001F, 0xD4000001) __AARCH64_INSN_FUNCS(hvc, 0xFFE0001F, 0xD4000002) __AARCH64_INSN_FUNCS(smc, 0xFFE0001F, 0xD4000003) diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index 10869d7731b83..751bd57bc3bac 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -53,7 +53,8 @@ static inline int tlb_get_level(struct mmu_gather *tlb) static inline void tlb_flush(struct mmu_gather *tlb) { struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); - tlbf_t flags = tlb->freed_tables ? TLBF_NONE : TLBF_NOWALKCACHE; + tlbf_t flags = (tlb->freed_tables || tlb->unshared_tables) ? + TLBF_NONE : TLBF_NOWALKCACHE; unsigned long stride = tlb_get_unmap_size(tlb); int tlb_level = tlb_get_level(tlb); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 34c9950884d5e..9453321ef8c67 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -555,8 +555,10 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_destroy_mpidr_data(vcpu->kvm); err = kvm_vgic_vcpu_init(vcpu); - if (err) + if (err) { + kvm_vgic_vcpu_destroy(vcpu); return err; + } err = kvm_share_hyp(vcpu, vcpu + 1); if (err) diff --git a/arch/arm64/kvm/hyp/nvhe/trace.c b/arch/arm64/kvm/hyp/nvhe/trace.c index a6ca27b18e154..e7e150ab265ff 100644 --- a/arch/arm64/kvm/hyp/nvhe/trace.c +++ b/arch/arm64/kvm/hyp/nvhe/trace.c @@ -164,13 +164,16 @@ static int hyp_trace_buffer_load(struct hyp_trace_buffer *trace_buffer, return ret; } -static bool hyp_trace_desc_validate(struct hyp_trace_desc *desc, size_t desc_size) +static bool hyp_trace_desc_is_valid(struct hyp_trace_desc *desc, size_t desc_size) { struct ring_buffer_desc *rb_desc; unsigned int cpu; size_t nr_bpages; void *desc_end; + if (!is_protected_kvm_enabled()) + return true; + /* * Both desc_size and bpages_backing_size are untrusted host-provided * values. We rely on __pkvm_host_donate_hyp() to enforce their validity. @@ -212,8 +215,10 @@ int __tracing_load(unsigned long desc_hva, size_t desc_size) if (ret) return ret; - if (!hyp_trace_desc_validate(desc, desc_size)) + if (!hyp_trace_desc_is_valid(desc, desc_size)) { + ret = -EINVAL; goto err_release_desc; + } hyp_spin_lock(&trace_buffer.lock); diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 2ea9f1c7ebcd0..1d7e5d560af4c 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2307,6 +2307,10 @@ static int vgic_its_restore_dte(struct vgic_its *its, u32 id, /* dte entry is valid */ offset = (entry & KVM_ITS_DTE_NEXT_MASK) >> KVM_ITS_DTE_NEXT_SHIFT; + /* Mimic the MAPD behaviour and reject invalid EID bits. */ + if (num_eventid_bits > VITS_TYPER_IDBITS) + return -EINVAL; + if (!vgic_its_check_id(its, baser, id, NULL)) return -EINVAL; diff --git a/arch/loongarch/include/asm/efi.h b/arch/loongarch/include/asm/efi.h index eddc8e79b3fae..1ad764b18c3e8 100644 --- a/arch/loongarch/include/asm/efi.h +++ b/arch/loongarch/include/asm/efi.h @@ -30,6 +30,8 @@ static inline unsigned long efi_get_kimg_min_align(void) return SZ_2M; } -#define EFI_KIMG_PREFERRED_ADDRESS PHYSADDR(VMLINUX_LOAD_ADDRESS) +unsigned long efi_get_kimg_kaslr_address(void); + +#define EFI_KIMG_PREFERRED_ADDRESS efi_get_kimg_kaslr_address() #endif /* _ASM_LOONGARCH_EFI_H */ diff --git a/arch/loongarch/include/asm/paravirt.h b/arch/loongarch/include/asm/paravirt.h index 0111f0ad5f733..acae1c5e5f882 100644 --- a/arch/loongarch/include/asm/paravirt.h +++ b/arch/loongarch/include/asm/paravirt.h @@ -4,6 +4,12 @@ #ifdef CONFIG_PARAVIRT +#include <linux/jump_label.h> + +DECLARE_STATIC_KEY_FALSE(virt_preempt_key); +DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key); +DECLARE_PER_CPU(struct kvm_steal_time, steal_time); + int __init pv_ipi_init(void); int __init pv_time_init(void); int __init pv_spinlock_init(void); diff --git a/arch/loongarch/include/asm/qspinlock.h b/arch/loongarch/include/asm/qspinlock.h index 0ee15b3b39372..fbfc6be82f26b 100644 --- a/arch/loongarch/include/asm/qspinlock.h +++ b/arch/loongarch/include/asm/qspinlock.h @@ -3,12 +3,9 @@ #define _ASM_LOONGARCH_QSPINLOCK_H #include <asm/kvm_para.h> -#include <linux/jump_label.h> +#include <asm/paravirt.h> #ifdef CONFIG_PARAVIRT -DECLARE_STATIC_KEY_FALSE(virt_preempt_key); -DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key); -DECLARE_PER_CPU(struct kvm_steal_time, steal_time); #define virt_spin_lock virt_spin_lock diff --git a/arch/loongarch/kernel/kprobes.c b/arch/loongarch/kernel/kprobes.c index 8ba391cfabb00..1985ed30dd16f 100644 --- a/arch/loongarch/kernel/kprobes.c +++ b/arch/loongarch/kernel/kprobes.c @@ -60,16 +60,18 @@ NOKPROBE_SYMBOL(arch_prepare_kprobe); /* Install breakpoint in text */ void arch_arm_kprobe(struct kprobe *p) { - *p->addr = KPROBE_BP_INSN; - flush_insn_slot(p); + u32 insn = KPROBE_BP_INSN; + + larch_insn_text_copy(p->addr, &insn, LOONGARCH_INSN_SIZE); } NOKPROBE_SYMBOL(arch_arm_kprobe); /* Remove breakpoint from text */ void arch_disarm_kprobe(struct kprobe *p) { - *p->addr = p->opcode; - flush_insn_slot(p); + u32 insn = p->opcode; + + larch_insn_text_copy(p->addr, &insn, LOONGARCH_INSN_SIZE); } NOKPROBE_SYMBOL(arch_disarm_kprobe); @@ -184,16 +186,16 @@ static bool reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { switch (kcb->kprobe_status) { - case KPROBE_HIT_SS: case KPROBE_HIT_SSDONE: case KPROBE_HIT_ACTIVE: kprobes_inc_nmissed_count(p); setup_singlestep(p, regs, kcb, 1); break; + case KPROBE_HIT_SS: case KPROBE_REENTER: pr_warn("Failed to recover from reentered kprobes.\n"); dump_kprobe(p); - WARN_ON_ONCE(1); + BUG(); break; default: WARN_ON(1); diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index 16f6a9b39659f..4b61a9632a980 100644 --- a/arch/loongarch/kernel/relocate.c +++ b/arch/loongarch/kernel/relocate.c @@ -134,11 +134,23 @@ early_param("nokaslr", nokaslr); #define KASLR_DISABLED_MESSAGE "KASLR is disabled by %s in %s cmdline.\n" +/* + * Note: strictly-defined KASLR means the kernel's final runtime address + * has a random offset from the kernel's load address, which is implemented + * in relocate.c; broadly-defined KALSR means the kernel's final runtime + * address has a random offset from the kernel's link address (a.k.a. + * VMLINUX_LOAD_ADDRESS), which also include the efistlub implementation, + * kexec_file implementation and QEMU direct kernel boot. kaslr_disabled() + * return true only means strictly-defined KASLR is disabled. + */ static inline __init bool kaslr_disabled(void) { char *str; const char *builtin_cmdline = CONFIG_CMDLINE; + if (kaslr_offset()) + return true; /* KASLR is performed during early boot. */ + str = strstr(builtin_cmdline, "nokaslr"); if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' ')) { pr_info(KASLR_DISABLED_MESSAGE, "\'nokaslr\'", "built-in"); @@ -210,14 +222,52 @@ static inline void __init *determine_relocation_address(void) return RELOCATED_KASLR(destination); } +static unsigned long __init determine_initrd_address(unsigned long *size) +{ + unsigned long start = 0; + unsigned long key_length; + char *p, *endp, *key = "initrd="; + + key_length = strlen(key); + p = strstr(boot_command_line, key); + + if (!p) { + key = "initrdmem="; + key_length = strlen(key); + p = strstr(boot_command_line, key); + } + + if (p == boot_command_line || (p > boot_command_line && *(p - 1) == ' ')) { + p += key_length; + start = memparse(p, &endp); + if (*endp == ',') + *size = memparse(endp + 1, NULL); + } + + return start; +} + static inline int __init relocation_addr_valid(void *location_new) { + unsigned long kernel_start, kernel_size; + unsigned long initrd_start, initrd_size = 0; + if ((unsigned long)location_new & 0x00000ffff) return 0; /* Inappropriately aligned new location */ if ((unsigned long)location_new < (unsigned long)_end) return 0; /* New location overlaps original kernel */ + initrd_start = determine_initrd_address(&initrd_size); + if (initrd_start && initrd_size) { + kernel_start = PHYSADDR(location_new); + kernel_size = (unsigned long)_end - (unsigned long)_text; + + if (kernel_start < (initrd_start + initrd_size) && + initrd_start < (kernel_start + kernel_size)) + return 0; /* initrd/initramfs overlaps kernel */ + } + return 1; } #endif diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index 3f9ab54114c51..031b39eb081c5 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -123,11 +123,7 @@ void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn); - /* With altmap the first mapped page is offset from @start */ - if (altmap) - page += vmem_altmap_offset(altmap); __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/nios2/include/asm/linkage.h b/arch/nios2/include/asm/linkage.h index 211302301a8a5..c4073235852bb 100644 --- a/arch/nios2/include/asm/linkage.h +++ b/arch/nios2/include/asm/linkage.h @@ -12,4 +12,6 @@ #define __ALIGN .align 4 #define __ALIGN_STR ".align 4" +#define _THIS_IP_ ({ unsigned long __ip; asm volatile("nextpc %0" : "=r" (__ip)); __ip; }) + #endif diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c index 4d89b94128aea..f09f9251d1f0a 100644 --- a/arch/riscv/kvm/vcpu_insn.c +++ b/arch/riscv/kvm/vcpu_insn.c @@ -415,7 +415,6 @@ int kvm_riscv_vcpu_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run, shift = 8 * (sizeof(ulong) - len); } else if ((insn & INSN_MASK_LBU) == INSN_MATCH_LBU) { len = 1; - shift = 8 * (sizeof(ulong) - len); #ifdef CONFIG_64BIT } else if ((insn & INSN_MASK_LD) == INSN_MATCH_LD) { len = 8; @@ -649,22 +648,22 @@ int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) case 1: data8 = *((u8 *)run->mmio.data); SET_RD(insn, &vcpu->arch.guest_context, - (ulong)data8 << shift >> shift); + (long)((ulong)data8 << shift) >> shift); break; case 2: data16 = *((u16 *)run->mmio.data); SET_RD(insn, &vcpu->arch.guest_context, - (ulong)data16 << shift >> shift); + (long)((ulong)data16 << shift) >> shift); break; case 4: data32 = *((u32 *)run->mmio.data); SET_RD(insn, &vcpu->arch.guest_context, - (ulong)data32 << shift >> shift); + (long)((ulong)data32 << shift) >> shift); break; case 8: data64 = *((u64 *)run->mmio.data); SET_RD(insn, &vcpu->arch.guest_context, - (ulong)data64 << shift >> shift); + (long)((ulong)data64 << shift) >> shift); break; default: return -EOPNOTSUPP; diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c index a935ed96bc176..bb46dcbfb24da 100644 --- a/arch/riscv/kvm/vcpu_pmu.c +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -453,8 +453,10 @@ int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long s } kvpmu->sdata = kzalloc(snapshot_area_size, GFP_ATOMIC); - if (!kvpmu->sdata) - return -ENOMEM; + if (!kvpmu->sdata) { + sbiret = SBI_ERR_FAILURE; + goto out; + } /* No need to check writable slot explicitly as kvm_vcpu_write_guest does it internally */ if (kvm_vcpu_write_guest(vcpu, saddr, kvpmu->sdata, snapshot_area_size)) { @@ -499,8 +501,10 @@ int kvm_riscv_vcpu_pmu_event_info(struct kvm_vcpu *vcpu, unsigned long saddr_low } einfo = kzalloc(shmem_size, GFP_KERNEL); - if (!einfo) - return -ENOMEM; + if (!einfo) { + ret = SBI_ERR_FAILURE; + goto out; + } ret = kvm_vcpu_read_guest(vcpu, shmem, einfo, shmem_size); if (ret) { diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c index 3b834709b429f..60e50296a0085 100644 --- a/arch/riscv/kvm/vcpu_sbi_sta.c +++ b/arch/riscv/kvm/vcpu_sbi_sta.c @@ -46,7 +46,7 @@ void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu) gfn = shmem >> PAGE_SHIFT; hva = kvm_vcpu_gfn_to_hva(vcpu, gfn); - if (WARN_ON(kvm_is_error_hva(hva))) { + if (kvm_is_error_hva(hva)) { vcpu->arch.sta.shmem = INVALID_GPA; return; } diff --git a/arch/riscv/kvm/vcpu_sbi_v01.c b/arch/riscv/kvm/vcpu_sbi_v01.c index 188d5ea5b3b85..c9c323d4577a9 100644 --- a/arch/riscv/kvm/vcpu_sbi_v01.c +++ b/arch/riscv/kvm/vcpu_sbi_v01.c @@ -55,6 +55,8 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, for_each_set_bit(i, &hmask, BITS_PER_LONG) { rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i); + if (!rvcpu) + continue; ret = kvm_riscv_vcpu_set_interrupt(rvcpu, IRQ_VS_SOFT); if (ret < 0) break; diff --git a/arch/s390/kernel/perf_pai.c b/arch/s390/kernel/perf_pai.c index 86f71a3d1ef2d..cdb8006220ca0 100644 --- a/arch/s390/kernel/perf_pai.c +++ b/arch/s390/kernel/perf_pai.c @@ -186,6 +186,13 @@ static u64 pai_getctr(unsigned long *page, int nr, unsigned long offset) return page[nr]; } +static void pai_setctr(unsigned long *page, int nr, unsigned long offset, u64 v) +{ + if (offset) + nr += offset / sizeof(*page); + page[nr] = v; +} + /* Read the counter values. Return value from location in CMP. For base * event xxx_ALL sum up all events. Returns counter value. */ @@ -551,6 +558,8 @@ static void paicrypt_del(struct perf_event *event, int flags) /* Create raw data and save it in buffer. Calculate the delta for each * counter between this invocation and the last invocation. * Returns number of bytes copied. + * After reading from PAI counter page, save the read value to the old + * page to calculate PAI counter deltas. * Saves only entries with positive counter difference of the form * 2 bytes: Number of counter * 8 bytes: Value of counter @@ -562,16 +571,22 @@ static size_t pai_copy(struct pai_userdata *userdata, unsigned long *page, int i, outidx = 0; for (i = 1; i <= pp->num_avail; i++) { - u64 val = 0, val_old = 0; + u64 val = 0, val_old = 0, val_k = 0, val_old_k = 0; if (!exclude_kernel) { - val += pai_getctr(page, i, pp->kernel_offset); - val_old += pai_getctr(page_old, i, pp->kernel_offset); + val_k = pai_getctr(page, i, pp->kernel_offset); + val_old_k = pai_getctr(page_old, i, pp->kernel_offset); + if (val_k != val_old_k) + pai_setctr(page_old, i, pp->kernel_offset, val_k); } if (!exclude_user) { - val += pai_getctr(page, i, 0); - val_old += pai_getctr(page_old, i, 0); + val = pai_getctr(page, i, 0); + val_old = pai_getctr(page_old, i, 0); + if (val != val_old) + pai_setctr(page_old, i, 0, val); } + val += val_k; + val_old += val_old_k; if (val >= val_old) val -= val_old; else @@ -602,8 +617,6 @@ static size_t pai_copy(struct pai_userdata *userdata, unsigned long *page, static int pai_push_sample(size_t rawsize, struct pai_map *cpump, struct perf_event *event) { - int idx = PAI_PMU_IDX(event); - struct pai_pmu *pp = &pai_pmu[idx]; struct perf_sample_data data; struct perf_raw_record raw; struct pt_regs regs; @@ -634,8 +647,6 @@ static int pai_push_sample(size_t rawsize, struct pai_map *cpump, overflow = perf_event_overflow(event, &data, ®s); perf_event_update_userpage(event); - /* Save crypto counter lowcore page after reading event data. */ - memcpy((void *)PAI_SAVE_AREA(event), cpump->area, pp->area_size); return overflow; } @@ -651,7 +662,7 @@ static void pai_have_sample(struct perf_event *event, struct pai_map *cpump) rawsize = pai_copy(cpump->save, cpump->area, pp, (unsigned long *)PAI_SAVE_AREA(event), event->attr.exclude_user, - event->attr.exclude_kernel); + !pp->kernel_offset ? true : event->attr.exclude_kernel); if (rawsize) /* No incremented counters */ pai_push_sample(rawsize, cpump, event); } diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 1913a5566ac2b..1377c6f3f6709 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -192,17 +192,21 @@ static void tl_to_masks(struct sysinfo_15_1_x *info) end = (union topology_entry *)((unsigned long)info + info->length); while (tle < end) { switch (tle->nl) { + /* + * Adjust drawer_id, book_id, and socked_id so they match the + * numbering scheme of e.g. the hardware management console. + */ case 3: drawer = drawer->next; - drawer->id = tle->container.id; + drawer->id = tle->container.id - 1; break; case 2: book = book->next; - book->id = tle->container.id; + book->id = tle->container.id - 1; break; case 1: socket = socket->next; - socket->id = tle->container.id; + socket->id = tle->container.id - 1; break; case 0: add_cpus_to_mask(&tle->cpu, drawer, book, socket); diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index 7b8d70fe406de..4a41c0247ffa2 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -267,6 +267,7 @@ static int dat_split_ste(struct kvm_s390_mmu_cache *mc, union pmd *pmdp, gfn_t g /* No need to take locks as the page table is not installed yet. */ pgste_init.prefix_notif = old.s.fc1.prefix_notif; pgste_init.vsie_notif = old.s.fc1.vsie_notif; + pgste_init.vsie_gmem = old.s.fc1.vsie_notif; pgste_init.pcl = uses_skeys && init.h.i; dat_init_pgstes(pt, pgste_init.val); } else { diff --git a/arch/s390/kvm/dat.h b/arch/s390/kvm/dat.h index 8f8278c448794..873e13ac5a27f 100644 --- a/arch/s390/kvm/dat.h +++ b/arch/s390/kvm/dat.h @@ -145,7 +145,8 @@ union pgste { unsigned long cmma_d : 1; /* Dirty flag for CMMA bits */ unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */ unsigned long vsie_notif : 1; /* Referenced in a shadow table */ - unsigned long : 5; + unsigned long vsie_gmem : 1; /* Contains nested guest memory */ + unsigned long : 4; unsigned long : 8; }; struct { diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index b07accd196182..4f8d5592c9a92 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -1445,6 +1445,7 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union } else { pgste = _gmap_ptep_xchg(sg->parent, ptep_h, newpte, pgste, f->gfn, false); pgste.vsie_notif = 1; + pgste.vsie_gmem = 1; } pgste_set_unlock(ptep_h, pgste); if (rc) diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c index 3c26e35af0ef7..957126ab991ca 100644 --- a/arch/s390/kvm/gmap.c +++ b/arch/s390/kvm/gmap.c @@ -125,7 +125,7 @@ struct gmap *gmap_new_child(struct gmap *parent, gfn_t limit) int gmap_set_limit(struct gmap *gmap, gfn_t limit) { - struct kvm_s390_mmu_cache *mc; + struct kvm_s390_mmu_cache *mc __free(kvm_s390_mmu_cache) = NULL; int rc, type; type = gmap_limit_to_type(limit); @@ -142,7 +142,6 @@ int gmap_set_limit(struct gmap *gmap, gfn_t limit) rc = dat_set_asce_limit(mc, &gmap->asce, type); } while (rc == -ENOMEM); - kvm_s390_free_mmu_cache(mc); return 0; } @@ -822,8 +821,8 @@ int gmap_ucas_translate(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, gpa_t int gmap_ucas_map(struct gmap *gmap, gfn_t p_gfn, gfn_t c_gfn, unsigned long count) { - struct kvm_s390_mmu_cache *mc; - int rc; + struct kvm_s390_mmu_cache *mc __free(kvm_s390_mmu_cache) = NULL; + int rc = 0; mc = kvm_s390_new_mmu_cache(); if (!mc) @@ -1026,13 +1025,15 @@ int gmap_insert_rmap(struct gmap *sg, gfn_t p_gfn, gfn_t r_gfn, int level) int gmap_protect_rmap(struct kvm_s390_mmu_cache *mc, struct gmap *sg, gfn_t p_gfn, gfn_t r_gfn, kvm_pfn_t pfn, int level, bool wr) { + unsigned long bitmask; union crste *crstep; union pgste pgste; union pte *ptep; union pte pte; int flags, rc; - KVM_BUG_ON(!is_shadow(sg), sg->kvm); + if (KVM_BUG_ON(!is_shadow(sg) || level <= TABLE_TYPE_PAGE_TABLE, sg->kvm)) + return -EINVAL; lockdep_assert_held(&sg->parent->children_lock); flags = DAT_WALK_SPLIT_ALLOC | (uses_skeys(sg->parent) ? DAT_WALK_USES_SKEYS : 0); @@ -1041,8 +1042,9 @@ int gmap_protect_rmap(struct kvm_s390_mmu_cache *mc, struct gmap *sg, gfn_t p_gf if (rc) return rc; if (level <= TABLE_TYPE_REGION1) { + bitmask = -1UL << (8 + 11 * level); scoped_guard(spinlock, &sg->host_to_rmap_lock) - rc = gmap_insert_rmap(sg, p_gfn, r_gfn, level); + rc = gmap_insert_rmap(sg, p_gfn, r_gfn & bitmask, level); } if (rc) return rc; @@ -1143,8 +1145,10 @@ void _gmap_handle_vsie_unshadow_event(struct gmap *parent, gfn_t gfn) } scoped_guard(spinlock, &sg->host_to_rmap_lock) head = radix_tree_delete(&sg->host_to_rmap, gfn); - gmap_for_each_rmap_safe(rmap, rnext, head) + gmap_for_each_rmap_safe(rmap, rnext, head) { gmap_unshadow_level(sg, rmap->r_gfn, rmap->level); + kfree(rmap); + } } } diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h index 96ee1395a5925..742e42a317445 100644 --- a/arch/s390/kvm/gmap.h +++ b/arch/s390/kvm/gmap.h @@ -167,6 +167,36 @@ static inline bool gmap_unmap_prefix(struct gmap *gmap, gfn_t gfn, gfn_t end) return _gmap_unmap_prefix(gmap, gfn, end, false); } +/** + * pte_needs_unshadow() -- Check if the pte operations triggers unshadowing. + * @oldpte: the previous value for the guest pte. + * @newpte: the new pte being set. + * @pgste: the pgste for the pte entry. + * + * If the pgste.vsie_notif bit is not set, return false: the page is not + * involved in vsie and thus should not trigger an unshadow operation. + * + * If the pgste.vsie_gmem bit is set, this pte represents shadowed guest + * memory. The access rights on g3's memory should be synchronized with g1's + * and g2's. Therefore unshadowing is triggered if the new and old pte + * differ in protection, or if the new pte is invalid. + * + * If the pgste.vsie_gmem bit is not set, this pte maps the g2 dat tables + * for g3. If the entry becomes writable or absent, it becomes impossible to + * guarantee that the shadow mapping will match g2's mapping. In that case, + * trigger an unshadow event. + * + * Return: true if an unshadow event should be triggered, otherwise false. + */ +static inline bool pte_needs_unshadow(union pte oldpte, union pte newpte, union pgste pgste) +{ + if (!pgste.vsie_notif) + return false; + if (pgste.vsie_gmem) + return (oldpte.h.p != newpte.h.p) || newpte.h.i; + return !newpte.h.p || !newpte.s.pr; +} + static inline union pgste _gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, union pte newpte, union pgste pgste, gfn_t gfn, bool needs_lock) { @@ -180,8 +210,9 @@ static inline union pgste _gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, un pgste.prefix_notif = 0; gmap_unmap_prefix(gmap, gfn, gfn + 1); } - if (pgste.vsie_notif && (ptep->h.p != newpte.h.p || newpte.h.i)) { + if (pte_needs_unshadow(*ptep, newpte, pgste)) { pgste.vsie_notif = 0; + pgste.vsie_gmem = 0; if (needs_lock) gmap_handle_vsie_unshadow_event(gmap, gfn); else @@ -189,6 +220,7 @@ static inline union pgste _gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, un } if (!ptep->s.d && newpte.s.d && !newpte.s.s) SetPageDirty(pfn_to_page(newpte.h.pfra)); + pgste.zero = 0; return __dat_ptep_xchg(ptep, pgste, newpte, gfn, gmap->asce, uses_skeys(gmap)); } @@ -198,6 +230,30 @@ static inline union pgste gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, uni return _gmap_ptep_xchg(gmap, ptep, newpte, pgste, gfn, true); } +/** + * crste_needs_unshadow() -- Check if the crste operations triggers unshadowing. + * @oldcrste: the previous value for the crste. + * @newcrste: the new value for the crste. + * + * If the old crste did not have the vsie_notif bit set, return false: the + * page is not involved in vsie and thus should not trigger an unshadow + * operation. Conversely, if the bit is set, it can only be g3 memory, since + * dat tables are never mapped using large pages. + * + * Similar to the pgste.vsie_gmem case of pte_needs_unshadow(), if the + * protection bit is changing or the new page is invalid, trigger an + * unshadow event. Also trigger an unshadow event if the new crste does not + * have the vsie_notif bit set. + * + * Return: true if an unshadow event should be triggered, otherwise false. + */ +static inline bool crste_needs_unshadow(union crste oldcrste, union crste newcrste) +{ + if (!oldcrste.s.fc1.vsie_notif) + return false; + return (newcrste.h.p != oldcrste.h.p) || newcrste.h.i || !newcrste.s.fc1.vsie_notif; +} + static inline bool __must_check _gmap_crstep_xchg_atomic(struct gmap *gmap, union crste *crstep, union crste oldcrste, union crste newcrste, gfn_t gfn, bool needs_lock) @@ -216,8 +272,7 @@ static inline bool __must_check _gmap_crstep_xchg_atomic(struct gmap *gmap, unio newcrste.s.fc1.prefix_notif = 0; gmap_unmap_prefix(gmap, gfn, gfn + align); } - if (crste_leaf(oldcrste) && oldcrste.s.fc1.vsie_notif && - (newcrste.h.p || newcrste.h.i || !newcrste.s.fc1.vsie_notif)) { + if (crste_leaf(oldcrste) && crste_needs_unshadow(oldcrste, newcrste)) { newcrste.s.fc1.vsie_notif = 0; if (needs_lock) gmap_handle_vsie_unshadow_event(gmap, gfn); diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 72cae8e0ce856..83b4762d6ecba 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -13,7 +13,7 @@ CFLAGS_REMOVE_syscall_64.o = $(CC_FLAGS_FTRACE) CFLAGS_syscall_32.o += -fno-stack-protector CFLAGS_syscall_64.o += -fno-stack-protector -obj-y := entry.o entry_$(BITS).o syscall_$(BITS).o +obj-y := entry.o entry_$(BITS).o syscall_$(BITS).o common.o obj-y += vdso/ obj-y += vsyscall/ diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c new file mode 100644 index 0000000000000..06c7c6ebd6f94 --- /dev/null +++ b/arch/x86/entry/common.c @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/entry-common.h> +#include <linux/kvm_types.h> +#include <linux/hrtimer_rearm.h> +#include <asm/fred.h> +#include <asm/desc.h> + +#if IS_ENABLED(CONFIG_KVM_INTEL) +/* + * On VMX, NMIs and IRQs (as configured by KVM) are acknowledged by hardware as + * part of the VM-Exit, i.e. the event itself is consumed as part the VM-Exit. + * x86_entry_from_kvm() is invoked by KVM to effectively forward NMIs and IRQs + * to the kernel for servicing. On SVM, a.k.a. AMD, the NMI/IRQ VM-Exit is + * purely a signal that an NMI/IRQ is pending, i.e. the event that triggered + * the VM-Exit is held pending until it's unblocked in the host. + */ +noinstr void x86_entry_from_kvm(unsigned int event_type, unsigned int vector) +{ + if (event_type == EVENT_TYPE_EXTINT) { +#ifdef CONFIG_X86_64 + /* + * Use FRED dispatch, even when running IDT. The dispatch + * tables are kept in sync between FRED and IDT, and the FRED + * dispatch works well with CFI. + */ + fred_entry_from_kvm(event_type, vector); +#else + idt_entry_from_kvm(vector); +#endif + /* + * Strictly speaking, only the NMI path requires noinstr. + */ + instrumentation_begin(); + /* + * KVM/VMX will dispatch from IRQ-disabled but for a context + * that will have IRQs-enabled. This confuses the entry code + * and it will not have reprogrammed the timer. Do so now. + */ + hrtimer_rearm_deferred(); + instrumentation_end(); + + return; + } + + WARN_ON_ONCE(event_type != EVENT_TYPE_NMI); + +#ifdef CONFIG_X86_64 + if (cpu_feature_enabled(X86_FEATURE_FRED)) + return fred_entry_from_kvm(event_type, vector); +#endif + + /* + * Notably, we must use IDT dispatch for NMI when running in IDT mode. + * The FRED NMI context is significantly different and will not work + * right (specifically FRED fixed the NMI recursion issue). + */ + idt_entry_from_kvm(vector); +} +EXPORT_SYMBOL_FOR_KVM(x86_entry_from_kvm); +#endif diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index 6ba2b3adcef0f..a56e043b266dc 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -75,3 +75,49 @@ THUNK warn_thunk_thunk, __warn_thunk #if defined(CONFIG_STACKPROTECTOR) && defined(CONFIG_SMP) EXPORT_SYMBOL(__ref_stack_chk_guard); #endif + +#if IS_ENABLED(CONFIG_KVM_INTEL) +.macro IDT_DO_EVENT_IRQOFF call_insn call_target + /* + * Unconditionally create a stack frame, getting the correct RSP on the + * stack (for x86-64) would take two instructions anyways, and RBP can + * be used to restore RSP to make objtool happy (see below). + */ + push %_ASM_BP + mov %_ASM_SP, %_ASM_BP + +#ifdef CONFIG_X86_64 + /* + * Align RSP to a 16-byte boundary (to emulate CPU behavior) before + * creating the synthetic interrupt stack frame for the IRQ/NMI. + */ + and $-16, %rsp + push $__KERNEL_DS + push %rbp +#endif + pushf + push $__KERNEL_CS + \call_insn \call_target + + /* + * "Restore" RSP from RBP, even though IRET has already unwound RSP to + * the correct value. objtool doesn't know the callee will IRET and, + * without the explicit restore, thinks the stack is getting walloped. + * Using an unwind hint is problematic due to x86-64's dynamic alignment. + */ + leave + RET +.endm + +.pushsection .text, "ax" +SYM_FUNC_START(idt_do_interrupt_irqoff) + IDT_DO_EVENT_IRQOFF CALL_NOSPEC _ASM_ARG1 +SYM_FUNC_END(idt_do_interrupt_irqoff) +.popsection + +.pushsection .noinstr.text, "ax" +SYM_FUNC_START(idt_do_nmi_irqoff) + IDT_DO_EVENT_IRQOFF call asm_exc_nmi_kvm_vmx +SYM_FUNC_END(idt_do_nmi_irqoff) +.popsection +#endif diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S index 894f7f16eb80a..0d2768ab836c4 100644 --- a/arch/x86/entry/entry_64_fred.S +++ b/arch/x86/entry/entry_64_fred.S @@ -147,5 +147,4 @@ SYM_FUNC_START(asm_fred_entry_from_kvm) RET SYM_FUNC_END(asm_fred_entry_from_kvm) -EXPORT_SYMBOL_FOR_KVM(asm_fred_entry_from_kvm); #endif diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index a6bfcc8243cd9..d903bce24f15d 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -178,7 +178,7 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr) if (IS_ERR(vma)) { ret = PTR_ERR(vma); do_munmap(mm, text_start, image->size, NULL); - do_munmap(mm, addr, image->size, NULL); + do_munmap(mm, addr, VDSO_NR_PAGES * PAGE_SIZE, NULL); goto up_fail; } diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index ec95fe44fa3a0..00aeae8435297 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -438,6 +438,10 @@ extern void idt_setup_traps(void); extern void idt_setup_apic_and_irq_gates(void); extern bool idt_is_f00f_address(unsigned long address); +extern void idt_do_interrupt_irqoff(unsigned long address); +extern void idt_do_nmi_irqoff(void); +extern void idt_entry_from_kvm(unsigned int vector); + #ifdef CONFIG_X86_64 extern void idt_setup_early_pf(void); #else diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h index 7e6b9314758a1..2f2ce8aadf076 100644 --- a/arch/x86/include/asm/desc_defs.h +++ b/arch/x86/include/asm/desc_defs.h @@ -145,7 +145,7 @@ struct gate_struct { typedef struct gate_struct gate_desc; #ifndef _SETUP -static inline unsigned long gate_offset(const gate_desc *g) +static __always_inline unsigned long gate_offset(const gate_desc *g) { #ifdef CONFIG_X86_64 return g->offset_low | ((unsigned long)g->offset_middle << 16) | diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 7535131c711bb..eca24b5e07f4c 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -97,4 +97,6 @@ static __always_inline void arch_exit_to_user_mode(void) } #define arch_exit_to_user_mode arch_exit_to_user_mode +extern void x86_entry_from_kvm(unsigned int entry_type, unsigned int vector); + #endif diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h index 2bb65677c079b..18a2f811c3580 100644 --- a/arch/x86/include/asm/fred.h +++ b/arch/x86/include/asm/fred.h @@ -110,7 +110,6 @@ static __always_inline unsigned long fred_event_data(struct pt_regs *regs) { ret static inline void cpu_init_fred_exceptions(void) { } static inline void cpu_init_fred_rsps(void) { } static inline void fred_complete_exception_setup(void) { } -static inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { } static inline void fred_sync_rsp0(unsigned long rsp0) { } static inline void fred_update_rsp0(void) { } #endif /* CONFIG_X86_FRED */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index 146f6f8b0650b..99801e844b305 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -92,6 +92,7 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_FRED, X86_FEATURE_LKGS }, { X86_FEATURE_SPEC_CTRL_SSBD, X86_FEATURE_SPEC_CTRL }, { X86_FEATURE_LASS, X86_FEATURE_SMAP }, + { X86_FEATURE_INVLPGB, X86_FEATURE_PCID }, {} }; diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 2604565887564..7bcf1decc0349 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -268,6 +268,21 @@ void __init idt_setup_early_pf(void) } #endif +#if IS_ENABLED(CONFIG_KVM_INTEL) +noinstr void idt_entry_from_kvm(unsigned int vector) +{ + if (vector == NMI_VECTOR) + return idt_do_nmi_irqoff(); + + /* + * Only the NMI path requires noinstr. + */ + instrumentation_begin(); + idt_do_interrupt_irqoff(gate_offset(idt_table + vector)); + instrumentation_end(); +} +#endif + static void __init idt_map_in_cea(void) { /* diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 3d239ed127441..52a3afb1b79e9 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -614,7 +614,6 @@ DEFINE_IDTENTRY_RAW(exc_nmi_kvm_vmx) { exc_nmi(regs); } -EXPORT_SYMBOL_FOR_KVM(asm_exc_nmi_kvm_vmx); #endif #ifdef CONFIG_NMI_CHECK_CPU diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index adf211860949a..993b551180fe9 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -1300,12 +1300,14 @@ bool __init avic_hardware_setup(void) } /* - * Disable IPI virtualization for AMD Family 17h CPUs (Zen1 and Zen2) - * due to erratum 1235, which results in missed VM-Exits on the sender - * and thus missed wake events for blocking vCPUs due to the CPU - * failing to see a software update to clear IsRunning. + * Disable IPI virtualization for AMD Family 17h (Zen1 and Zen2) and + * Hygon Family 18h (derived from AMD Zen1) CPUs due to erratum 1235, + * which results in missed VM-Exits on the sender and thus missed wake + * events for blocking vCPUs due to the CPU failing to see a software + * update to clear IsRunning. */ - enable_ipiv = enable_ipiv && boot_cpu_data.x86 != 0x17; + if (boot_cpu_data.x86 == 0x17 || boot_cpu_data.x86 == 0x18) + enable_ipiv = false; amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 8a481dae9cae2..ff1f254a0ef4e 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -31,38 +31,6 @@ #define VCPU_R15 __VCPU_REGS_R15 * WORD_SIZE #endif -.macro VMX_DO_EVENT_IRQOFF call_insn call_target - /* - * Unconditionally create a stack frame, getting the correct RSP on the - * stack (for x86-64) would take two instructions anyways, and RBP can - * be used to restore RSP to make objtool happy (see below). - */ - push %_ASM_BP - mov %_ASM_SP, %_ASM_BP - -#ifdef CONFIG_X86_64 - /* - * Align RSP to a 16-byte boundary (to emulate CPU behavior) before - * creating the synthetic interrupt stack frame for the IRQ/NMI. - */ - and $-16, %rsp - push $__KERNEL_DS - push %rbp -#endif - pushf - push $__KERNEL_CS - \call_insn \call_target - - /* - * "Restore" RSP from RBP, even though IRET has already unwound RSP to - * the correct value. objtool doesn't know the callee will IRET and, - * without the explicit restore, thinks the stack is getting walloped. - * Using an unwind hint is problematic due to x86-64's dynamic alignment. - */ - leave - RET -.endm - .section .noinstr.text, "ax" /** @@ -320,10 +288,6 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL) SYM_FUNC_END(__vmx_vcpu_run) -SYM_FUNC_START(vmx_do_nmi_irqoff) - VMX_DO_EVENT_IRQOFF call asm_exc_nmi_kvm_vmx -SYM_FUNC_END(vmx_do_nmi_irqoff) - #ifndef CONFIG_CC_HAS_ASM_GOTO_OUTPUT /** @@ -375,13 +339,3 @@ SYM_FUNC_START(vmread_error_trampoline) RET SYM_FUNC_END(vmread_error_trampoline) #endif - -.section .text, "ax" - -#ifndef CONFIG_X86_FRED - -SYM_FUNC_START(vmx_do_interrupt_irqoff) - VMX_DO_EVENT_IRQOFF CALL_NOSPEC _ASM_ARG1 -SYM_FUNC_END(vmx_do_interrupt_irqoff) - -#endif diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 49feecb286b23..b9103de01428e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7117,9 +7117,6 @@ void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } -void vmx_do_interrupt_irqoff(unsigned long entry); -void vmx_do_nmi_irqoff(void); - static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) { /* @@ -7161,17 +7158,8 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu, "unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; - /* - * Invoke the kernel's IRQ handler for the vector. Use the FRED path - * when it's available even if FRED isn't fully enabled, e.g. even if - * FRED isn't supported in hardware, in order to avoid the indirect - * CALL in the non-FRED path. - */ kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); - if (IS_ENABLED(CONFIG_X86_FRED)) - fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector); - else - vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector)); + x86_entry_from_kvm(EVENT_TYPE_EXTINT, vector); kvm_after_interrupt(vcpu); vcpu->arch.at_instruction_boundary = true; @@ -7481,10 +7469,7 @@ noinstr void vmx_handle_nmi(struct kvm_vcpu *vcpu) return; kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); - if (cpu_feature_enabled(X86_FEATURE_FRED)) - fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR); - else - vmx_do_nmi_irqoff(); + x86_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR); kvm_after_interrupt(vcpu); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0a1b63c63d1a9..c1a72d749084f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4876,7 +4876,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = tdp_enabled; break; case KVM_CAP_X86_APIC_BUS_CYCLES_NS: - r = APIC_BUS_CYCLE_NS_DEFAULT; + r = kvm ? kvm->arch.apic_bus_cycle_ns : APIC_BUS_CYCLE_NS_DEFAULT; break; case KVM_CAP_EXIT_HYPERCALL: r = KVM_EXIT_HYPERCALL_VALID_MASK; |