diff options
Diffstat (limited to 'arch/x86/kernel')
| -rw-r--r-- | arch/x86/kernel/cpu/microcode/amd.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/sgx/ioctl.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/core.c | 32 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/xstate.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/irq.c | 23 | ||||
| -rw-r--r-- | arch/x86/kernel/kvm.c | 19 | ||||
| -rw-r--r-- | arch/x86/kernel/unwind_orc.c | 39 | ||||
| -rw-r--r-- | arch/x86/kernel/x86_init.c | 2 |
8 files changed, 100 insertions, 23 deletions
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 3821a985f4ff..46673530bc6f 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -258,7 +258,7 @@ static bool cpu_has_entrysign(void) if (fam == 0x1a) { if (model <= 0x2f || (0x40 <= model && model <= 0x4f) || - (0x60 <= model && model <= 0x6f)) + (0x60 <= model && model <= 0x7f)) return true; } diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 66f1efa16fbb..9322a9287dc7 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -242,7 +242,7 @@ static int __sgx_encl_add_page(struct sgx_encl *encl, /* * If the caller requires measurement of the page as a proof for the content, * use EEXTEND to add a measurement for 256 bytes of the page. Repeat this - * operation until the entire page is measured." + * operation until the entire page is measured. */ static int __sgx_encl_extend(struct sgx_encl *encl, struct sgx_epc_page *epc_page) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index da233f20ae6f..608983806fd7 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -319,10 +319,29 @@ EXPORT_SYMBOL_FOR_KVM(fpu_enable_guest_xfd_features); #ifdef CONFIG_X86_64 void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { + struct fpstate *fpstate = guest_fpu->fpstate; + fpregs_lock(); - guest_fpu->fpstate->xfd = xfd; - if (guest_fpu->fpstate->in_use) - xfd_update_state(guest_fpu->fpstate); + + /* + * KVM's guest ABI is that setting XFD[i]=1 *can* immediately revert the + * save state to its initial configuration. Likewise, KVM_GET_XSAVE does + * the same as XSAVE and returns XSTATE_BV[i]=0 whenever XFD[i]=1. + * + * If the guest's FPU state is in hardware, just update XFD: the XSAVE + * in fpu_swap_kvm_fpstate will clear XSTATE_BV[i] whenever XFD[i]=1. + * + * If however the guest's FPU state is NOT resident in hardware, clear + * disabled components in XSTATE_BV now, or a subsequent XRSTOR will + * attempt to load disabled components and generate #NM _in the host_. + */ + if (xfd && test_thread_flag(TIF_NEED_FPU_LOAD)) + fpstate->regs.xsave.header.xfeatures &= ~xfd; + + fpstate->xfd = xfd; + if (fpstate->in_use) + xfd_update_state(fpstate); + fpregs_unlock(); } EXPORT_SYMBOL_FOR_KVM(fpu_update_guest_xfd); @@ -431,6 +450,13 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, return -EINVAL; /* + * Disabled features must be in their initial state, otherwise XRSTOR + * causes an exception. + */ + if (WARN_ON_ONCE(ustate->xsave.header.xfeatures & kstate->xfd)) + return -EINVAL; + + /* * Nullify @vpkru to preserve its current value if PKRU's bit isn't set * in the header. KVM's odd ABI is to leave PKRU untouched in this * case (all other components are eventually re-initialized). diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 48113c5193aa..76153dfb58c9 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1946,7 +1946,7 @@ static int dump_xsave_layout_desc(struct coredump_params *cprm) }; if (!dump_emit(cprm, &xc, sizeof(xc))) - return 0; + return -1; num_records++; } @@ -1984,7 +1984,7 @@ int elf_coredump_extra_notes_write(struct coredump_params *cprm) return 1; num_records = dump_xsave_layout_desc(cprm); - if (!num_records) + if (num_records < 0) return 1; /* Total size should be equal to the number of records */ diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 86f4e574de02..b2fe6181960c 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -397,6 +397,7 @@ DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_nested_ipi) /* Posted Interrupt Descriptors for coalesced MSIs to be posted */ DEFINE_PER_CPU_ALIGNED(struct pi_desc, posted_msi_pi_desc); +static DEFINE_PER_CPU_CACHE_HOT(bool, posted_msi_handler_active); void intel_posted_msi_init(void) { @@ -414,6 +415,25 @@ void intel_posted_msi_init(void) this_cpu_write(posted_msi_pi_desc.ndst, destination); } +void intel_ack_posted_msi_irq(struct irq_data *irqd) +{ + irq_move_irq(irqd); + + /* + * Handle the rare case that irq_retrigger() raised the actual + * assigned vector on the target CPU, which means that it was not + * invoked via the posted MSI handler below. In that case APIC EOI + * is required as otherwise the ISR entry becomes stale and lower + * priority interrupts are never going to be delivered after that. + * + * If the posted handler invoked the device interrupt handler then + * the EOI would be premature because it would acknowledge the + * posted vector. + */ + if (unlikely(!__this_cpu_read(posted_msi_handler_active))) + apic_eoi(); +} + static __always_inline bool handle_pending_pir(unsigned long *pir, struct pt_regs *regs) { unsigned long pir_copy[NR_PIR_WORDS]; @@ -446,6 +466,8 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification) pid = this_cpu_ptr(&posted_msi_pi_desc); + /* Mark the handler active for intel_ack_posted_msi_irq() */ + __this_cpu_write(posted_msi_handler_active, true); inc_irq_stat(posted_msi_notification_count); irq_enter(); @@ -474,6 +496,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification) apic_eoi(); irq_exit(); + __this_cpu_write(posted_msi_handler_active, false); set_irq_regs(old_regs); } #endif /* X86_POSTED_MSI */ diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index df78ddee0abb..37dc8465e0f5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -89,6 +89,7 @@ struct kvm_task_sleep_node { struct swait_queue_head wq; u32 token; int cpu; + bool dummy; }; static struct kvm_task_sleep_head { @@ -120,15 +121,26 @@ static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n) raw_spin_lock(&b->lock); e = _find_apf_task(b, token); if (e) { - /* dummy entry exist -> wake up was delivered ahead of PF */ - hlist_del(&e->link); + struct kvm_task_sleep_node *dummy = NULL; + + /* + * The entry can either be a 'dummy' entry (which is put on the + * list when wake-up happens ahead of APF handling completion) + * or a token from another task which should not be touched. + */ + if (e->dummy) { + hlist_del(&e->link); + dummy = e; + } + raw_spin_unlock(&b->lock); - kfree(e); + kfree(dummy); return false; } n->token = token; n->cpu = smp_processor_id(); + n->dummy = false; init_swait_queue_head(&n->wq); hlist_add_head(&n->link, &b->list); raw_spin_unlock(&b->lock); @@ -231,6 +243,7 @@ again: } dummy->token = token; dummy->cpu = smp_processor_id(); + dummy->dummy = true; init_swait_queue_head(&dummy->wq); hlist_add_head(&dummy->link, &b->list); dummy = NULL; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 977ee75e047c..f610fde2d5c4 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -2,6 +2,7 @@ #include <linux/objtool.h> #include <linux/module.h> #include <linux/sort.h> +#include <linux/bpf.h> #include <asm/ptrace.h> #include <asm/stacktrace.h> #include <asm/unwind.h> @@ -172,6 +173,25 @@ static struct orc_entry *orc_ftrace_find(unsigned long ip) } #endif +/* Fake frame pointer entry -- used as a fallback for generated code */ +static struct orc_entry orc_fp_entry = { + .type = ORC_TYPE_CALL, + .sp_reg = ORC_REG_BP, + .sp_offset = 16, + .bp_reg = ORC_REG_PREV_SP, + .bp_offset = -16, +}; + +static struct orc_entry *orc_bpf_find(unsigned long ip) +{ +#ifdef CONFIG_BPF_JIT + if (bpf_has_frame_pointer(ip)) + return &orc_fp_entry; +#endif + + return NULL; +} + /* * If we crash with IP==0, the last successfully executed instruction * was probably an indirect function call with a NULL function pointer, @@ -186,15 +206,6 @@ static struct orc_entry null_orc_entry = { .type = ORC_TYPE_CALL }; -/* Fake frame pointer entry -- used as a fallback for generated code */ -static struct orc_entry orc_fp_entry = { - .type = ORC_TYPE_CALL, - .sp_reg = ORC_REG_BP, - .sp_offset = 16, - .bp_reg = ORC_REG_PREV_SP, - .bp_offset = -16, -}; - static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; @@ -238,6 +249,11 @@ static struct orc_entry *orc_find(unsigned long ip) if (orc) return orc; + /* BPF lookup: */ + orc = orc_bpf_find(ip); + if (orc) + return orc; + return orc_ftrace_find(ip); } @@ -495,9 +511,8 @@ bool unwind_next_frame(struct unwind_state *state) if (!orc) { /* * As a fallback, try to assume this code uses a frame pointer. - * This is useful for generated code, like BPF, which ORC - * doesn't know about. This is just a guess, so the rest of - * the unwind is no longer considered reliable. + * This is just a guess, so the rest of the unwind is no longer + * considered reliable. */ orc = &orc_fp_entry; state->error = true; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 0a2bbd674a6d..ebefb77c37bb 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2009 Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * * For licencing details see kernel-base/COPYING */ |