diff options
Diffstat (limited to 'arch/x86/kernel/traps.c')
| -rw-r--r-- | arch/x86/kernel/traps.c | 1209 |
1 files changed, 867 insertions, 342 deletions
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 6ef00eb6fbb9..d3fdec706f1d 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -15,6 +15,7 @@ #include <linux/context_tracking.h> #include <linux/interrupt.h> #include <linux/kallsyms.h> +#include <linux/kmsan.h> #include <linux/spinlock.h> #include <linux/kprobes.h> #include <linux/uaccess.h> @@ -37,15 +38,20 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/io.h> +#include <linux/hardirq.h> +#include <linux/atomic.h> +#include <linux/ioasid.h> + #include <asm/stacktrace.h> #include <asm/processor.h> #include <asm/debugreg.h> -#include <linux/atomic.h> +#include <asm/realmode.h> #include <asm/text-patching.h> #include <asm/ftrace.h> #include <asm/traps.h> #include <asm/desc.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> +#include <asm/cpu.h> #include <asm/cpu_entry_area.h> #include <asm/mce.h> #include <asm/fixmap.h> @@ -56,10 +62,12 @@ #include <asm/umip.h> #include <asm/insn.h> #include <asm/insn-eval.h> +#include <asm/vdso.h> +#include <asm/tdx.h> +#include <asm/cfi.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> -#include <asm/pgalloc.h> #include <asm/proto.h> #else #include <asm/processor-flags.h> @@ -81,107 +89,16 @@ static inline void cond_local_irq_disable(struct pt_regs *regs) local_irq_disable(); } -/* - * In IST context, we explicitly disable preemption. This serves two - * purposes: it makes it much less likely that we would accidentally - * schedule in IST context and it will force a warning if we somehow - * manage to schedule by accident. - */ -void ist_enter(struct pt_regs *regs) -{ - if (user_mode(regs)) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - } else { - /* - * We might have interrupted pretty much anything. In - * fact, if we're a machine check, we can even interrupt - * NMI processing. We don't want in_nmi() to return true, - * but we need to notify RCU. - */ - rcu_nmi_enter(); - } - - preempt_disable(); - - /* This code is a bit fragile. Test it. */ - RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work"); -} -NOKPROBE_SYMBOL(ist_enter); - -void ist_exit(struct pt_regs *regs) -{ - preempt_enable_no_resched(); - - if (!user_mode(regs)) - rcu_nmi_exit(); -} - -/** - * ist_begin_non_atomic() - begin a non-atomic section in an IST exception - * @regs: regs passed to the IST exception handler - * - * IST exception handlers normally cannot schedule. As a special - * exception, if the exception interrupted userspace code (i.e. - * user_mode(regs) would return true) and the exception was not - * a double fault, it can be safe to schedule. ist_begin_non_atomic() - * begins a non-atomic section within an ist_enter()/ist_exit() region. - * Callers are responsible for enabling interrupts themselves inside - * the non-atomic section, and callers must call ist_end_non_atomic() - * before ist_exit(). - */ -void ist_begin_non_atomic(struct pt_regs *regs) -{ - BUG_ON(!user_mode(regs)); - - /* - * Sanity check: we need to be on the normal thread stack. This - * will catch asm bugs and any attempt to use ist_preempt_enable - * from double_fault. - */ - BUG_ON(!on_thread_stack()); - - preempt_enable_no_resched(); -} - -/** - * ist_end_non_atomic() - begin a non-atomic section in an IST exception - * - * Ends a non-atomic section started with ist_begin_non_atomic(). - */ -void ist_end_non_atomic(void) +__always_inline int is_valid_bugaddr(unsigned long addr) { - preempt_disable(); -} - -int is_valid_bugaddr(unsigned long addr) -{ - unsigned short ud; - if (addr < TASK_SIZE_MAX) return 0; - if (probe_kernel_address((unsigned short *)addr, ud)) - return 0; - - return ud == INSN_UD0 || ud == INSN_UD2; -} - -int fixup_bug(struct pt_regs *regs, int trapnr) -{ - if (trapnr != X86_TRAP_UD) - return 0; - - switch (report_bug(regs->ip, regs)) { - case BUG_TRAP_TYPE_NONE: - case BUG_TRAP_TYPE_BUG: - break; - - case BUG_TRAP_TYPE_WARN: - regs->ip += LEN_UD2; - return 1; - } - - return 0; + /* + * We got #UD, if the text isn't readable we'd have gotten + * a different exception. + */ + return *(unsigned short *)addr == INSN_UD2; } static nokprobe_inline int @@ -205,6 +122,9 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str, tsk->thread.error_code = error_code; tsk->thread.trap_nr = trapnr; die(str, regs, error_code); + } else { + if (fixup_vdso_exception(regs, trapnr, error_code, 0)) + return 0; } /* @@ -214,7 +134,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str, * process no chance to handle the signal and notice the * kernel fault information, so that won't result in polluting * the information about previously queued, but not yet - * delivered, faults. See also do_general_protection below. + * delivered, faults. See also exc_general_protection below. */ tsk->thread.error_code = error_code; tsk->thread.trap_nr = trapnr; @@ -242,7 +162,6 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, { struct task_struct *tsk = current; - if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code)) return; @@ -260,53 +179,242 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str, { RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - /* - * WARN*()s end up here; fix them up before we call the - * notifier chain. - */ - if (!user_mode(regs) && fixup_bug(regs, trapnr)) - return; - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) != NOTIFY_STOP) { cond_local_irq_enable(regs); do_trap(trapnr, signr, str, regs, error_code, sicode, addr); + cond_local_irq_disable(regs); } } -#define IP ((void __user *)uprobe_get_trap_addr(regs)) -#define DO_ERROR(trapnr, signr, sicode, addr, str, name) \ -dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ -{ \ - do_error_trap(regs, error_code, str, trapnr, signr, sicode, addr); \ +/* + * Posix requires to provide the address of the faulting instruction for + * SIGILL (#UD) and SIGFPE (#DE) in the si_addr member of siginfo_t. + * + * This address is usually regs->ip, but when an uprobe moved the code out + * of line then regs->ip points to the XOL code which would confuse + * anything which analyzes the fault address vs. the unmodified binary. If + * a trap happened in XOL code then uprobe maps regs->ip back to the + * original instruction address. + */ +static __always_inline void __user *error_get_trap_addr(struct pt_regs *regs) +{ + return (void __user *)uprobe_get_trap_addr(regs); +} + +DEFINE_IDTENTRY(exc_divide_error) +{ + do_error_trap(regs, 0, "divide error", X86_TRAP_DE, SIGFPE, + FPE_INTDIV, error_get_trap_addr(regs)); +} + +DEFINE_IDTENTRY(exc_overflow) +{ + do_error_trap(regs, 0, "overflow", X86_TRAP_OF, SIGSEGV, 0, NULL); +} + +#ifdef CONFIG_X86_KERNEL_IBT + +static __ro_after_init bool ibt_fatal = true; + +extern void ibt_selftest_ip(void); /* code label defined in asm below */ + +enum cp_error_code { + CP_EC = (1 << 15) - 1, + + CP_RET = 1, + CP_IRET = 2, + CP_ENDBR = 3, + CP_RSTRORSSP = 4, + CP_SETSSBSY = 5, + + CP_ENCL = 1 << 15, +}; + +DEFINE_IDTENTRY_ERRORCODE(exc_control_protection) +{ + if (!cpu_feature_enabled(X86_FEATURE_IBT)) { + pr_err("Unexpected #CP\n"); + BUG(); + } + + if (WARN_ON_ONCE(user_mode(regs) || (error_code & CP_EC) != CP_ENDBR)) + return; + + if (unlikely(regs->ip == (unsigned long)&ibt_selftest_ip)) { + regs->ax = 0; + return; + } + + pr_err("Missing ENDBR: %pS\n", (void *)instruction_pointer(regs)); + if (!ibt_fatal) { + printk(KERN_DEFAULT CUT_HERE); + __warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL); + return; + } + BUG(); +} + +/* Must be noinline to ensure uniqueness of ibt_selftest_ip. */ +noinline bool ibt_selftest(void) +{ + unsigned long ret; + + asm (" lea ibt_selftest_ip(%%rip), %%rax\n\t" + ANNOTATE_RETPOLINE_SAFE + " jmp *%%rax\n\t" + "ibt_selftest_ip:\n\t" + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + " nop\n\t" + + : "=a" (ret) : : "memory"); + + return !ret; +} + +static int __init ibt_setup(char *str) +{ + if (!strcmp(str, "off")) + setup_clear_cpu_cap(X86_FEATURE_IBT); + + if (!strcmp(str, "warn")) + ibt_fatal = false; + + return 1; +} + +__setup("ibt=", ibt_setup); + +#endif /* CONFIG_X86_KERNEL_IBT */ + +#ifdef CONFIG_X86_F00F_BUG +void handle_invalid_op(struct pt_regs *regs) +#else +static inline void handle_invalid_op(struct pt_regs *regs) +#endif +{ + do_error_trap(regs, 0, "invalid opcode", X86_TRAP_UD, SIGILL, + ILL_ILLOPN, error_get_trap_addr(regs)); +} + +static noinstr bool handle_bug(struct pt_regs *regs) +{ + bool handled = false; + + /* + * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug() + * is a rare case that uses @regs without passing them to + * irqentry_enter(). + */ + kmsan_unpoison_entry_regs(regs); + if (!is_valid_bugaddr(regs->ip)) + return handled; + + /* + * All lies, just get the WARN/BUG out. + */ + instrumentation_begin(); + /* + * Since we're emulating a CALL with exceptions, restore the interrupt + * state to what it was at the exception site. + */ + if (regs->flags & X86_EFLAGS_IF) + raw_local_irq_enable(); + if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN || + handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) { + regs->ip += LEN_UD2; + handled = true; + } + if (regs->flags & X86_EFLAGS_IF) + raw_local_irq_disable(); + instrumentation_end(); + + return handled; +} + +DEFINE_IDTENTRY_RAW(exc_invalid_op) +{ + irqentry_state_t state; + + /* + * We use UD2 as a short encoding for 'CALL __WARN', as such + * handle it before exception entry to avoid recursive WARN + * in case exception entry is the one triggering WARNs. + */ + if (!user_mode(regs) && handle_bug(regs)) + return; + + state = irqentry_enter(regs); + instrumentation_begin(); + handle_invalid_op(regs); + instrumentation_end(); + irqentry_exit(regs, state); +} + +DEFINE_IDTENTRY(exc_coproc_segment_overrun) +{ + do_error_trap(regs, 0, "coprocessor segment overrun", + X86_TRAP_OLD_MF, SIGFPE, 0, NULL); +} + +DEFINE_IDTENTRY_ERRORCODE(exc_invalid_tss) +{ + do_error_trap(regs, error_code, "invalid TSS", X86_TRAP_TS, SIGSEGV, + 0, NULL); } -DO_ERROR(X86_TRAP_DE, SIGFPE, FPE_INTDIV, IP, "divide error", divide_error) -DO_ERROR(X86_TRAP_OF, SIGSEGV, 0, NULL, "overflow", overflow) -DO_ERROR(X86_TRAP_UD, SIGILL, ILL_ILLOPN, IP, "invalid opcode", invalid_op) -DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, 0, NULL, "coprocessor segment overrun", coprocessor_segment_overrun) -DO_ERROR(X86_TRAP_TS, SIGSEGV, 0, NULL, "invalid TSS", invalid_TSS) -DO_ERROR(X86_TRAP_NP, SIGBUS, 0, NULL, "segment not present", segment_not_present) -DO_ERROR(X86_TRAP_SS, SIGBUS, 0, NULL, "stack segment", stack_segment) -DO_ERROR(X86_TRAP_AC, SIGBUS, BUS_ADRALN, NULL, "alignment check", alignment_check) -#undef IP +DEFINE_IDTENTRY_ERRORCODE(exc_segment_not_present) +{ + do_error_trap(regs, error_code, "segment not present", X86_TRAP_NP, + SIGBUS, 0, NULL); +} + +DEFINE_IDTENTRY_ERRORCODE(exc_stack_segment) +{ + do_error_trap(regs, error_code, "stack segment", X86_TRAP_SS, SIGBUS, + 0, NULL); +} + +DEFINE_IDTENTRY_ERRORCODE(exc_alignment_check) +{ + char *str = "alignment check"; + + if (notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_AC, SIGBUS) == NOTIFY_STOP) + return; + + if (!user_mode(regs)) + die("Split lock detected\n", regs, error_code); + + local_irq_enable(); + + if (handle_user_split_lock(regs, error_code)) + goto out; + + do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs, + error_code, BUS_ADRALN, NULL); + +out: + local_irq_disable(); +} #ifdef CONFIG_VMAP_STACK -__visible void __noreturn handle_stack_overflow(const char *message, - struct pt_regs *regs, - unsigned long fault_address) +__visible void __noreturn handle_stack_overflow(struct pt_regs *regs, + unsigned long fault_address, + struct stack_info *info) { - printk(KERN_EMERG "BUG: stack guard page was hit at %p (stack is %p..%p)\n", - (void *)fault_address, current->stack, - (char *)current->stack + THREAD_SIZE - 1); - die(message, regs, 0); + const char *name = stack_type_name(info->type); + + printk(KERN_EMERG "BUG: %s stack guard page was hit at %p (stack is %p..%p)\n", + name, (void *)fault_address, info->begin, info->end); + + die("stack guard page", regs, 0); /* Be absolutely certain we don't return. */ - panic("%s", message); + panic("%s stack guard hit", name); } #endif -#if defined(CONFIG_X86_64) || defined(CONFIG_DOUBLEFAULT) /* * Runs on an IST stack for x86_64 and on a special task stack for x86_32. * @@ -322,12 +430,20 @@ __visible void __noreturn handle_stack_overflow(const char *message, * from the TSS. Returning is, in principle, okay, but changes to regs will * be lost. If, for some reason, we need to return to a context with modified * regs, the shim code could be adjusted to synchronize the registers. + * + * The 32bit #DF shim provides CR2 already as an argument. On 64bit it needs + * to be read before doing anything else. */ -dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long cr2) +DEFINE_IDTENTRY_DF(exc_double_fault) { static const char str[] = "double fault"; struct task_struct *tsk = current; +#ifdef CONFIG_VMAP_STACK + unsigned long address = read_cr2(); + struct stack_info info; +#endif + #ifdef CONFIG_X86_ESPFIX64 extern unsigned char native_irq_return_iret[]; @@ -343,13 +459,14 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign * The net result is that our #GP handler will think that we * entered from usermode with the bad user context. * - * No need for ist_enter here because we don't use RCU. + * No need for nmi_enter() here because we don't use RCU. */ if (((long)regs->sp >> P4D_SHIFT) == ESPFIX_PGD_ENTRY && regs->cs == __KERNEL_CS && regs->ip == (unsigned long)native_irq_return_iret) { struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; + unsigned long *p = (unsigned long *)regs->sp; /* * regs->sp points to the failing IRET frame on the @@ -357,13 +474,17 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign * in gpregs->ss through gpregs->ip. * */ - memmove(&gpregs->ip, (void *)regs->sp, 5*8); + gpregs->ip = p[0]; + gpregs->cs = p[1]; + gpregs->flags = p[2]; + gpregs->sp = p[3]; + gpregs->ss = p[4]; gpregs->orig_ax = 0; /* Missing (lost) #GP error code */ /* * Adjust our frame so that we return straight to the #GP * vector with the expected RSP value. This is safe because - * we won't enable interupts or schedule before we invoke + * we won't enable interrupts or schedule before we invoke * general_protection, so nothing will clobber the stack * frame we just set up. * @@ -371,14 +492,15 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign * which is what the stub expects, given that the faulting * RIP will be the IRET instruction. */ - regs->ip = (unsigned long)general_protection; + regs->ip = (unsigned long)asm_exc_general_protection; regs->sp = (unsigned long)&gpregs->orig_ax; return; } #endif - ist_enter(regs); + irqentry_nmi_enter(regs); + instrumentation_begin(); notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); tsk->thread.error_code = error_code; @@ -422,28 +544,29 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign * stack even if the actual trigger for the double fault was * something else. */ - if ((unsigned long)task_stack_page(tsk) - 1 - cr2 < PAGE_SIZE) - handle_stack_overflow("kernel stack overflow (double-fault)", regs, cr2); + if (get_stack_guard_info((void *)address, &info)) + handle_stack_overflow(regs, address, &info); #endif pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code); die("double fault", regs, error_code); panic("Machine halted."); + instrumentation_end(); } -#endif -dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY(exc_bounds) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - if (notify_die(DIE_TRAP, "bounds", regs, error_code, + if (notify_die(DIE_TRAP, "bounds", regs, 0, X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP) return; cond_local_irq_enable(regs); if (!user_mode(regs)) - die("bounds", regs, error_code); + die("bounds", regs, 0); + + do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, 0, 0, NULL); - do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, 0, NULL); + cond_local_irq_disable(regs); } enum kernel_gp_hint { @@ -462,13 +585,15 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs, { u8 insn_buf[MAX_INSN_SIZE]; struct insn insn; + int ret; - if (probe_kernel_read(insn_buf, (void *)regs->ip, MAX_INSN_SIZE)) + if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip, + MAX_INSN_SIZE)) return GP_NO_HINT; - kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE); - insn_get_modrm(&insn); - insn_get_sib(&insn); + ret = insn_decode_kernel(&insn, insn_buf); + if (ret < 0) + return GP_NO_HINT; *addr = (unsigned long)insn_get_addr_ref(&insn, regs); if (*addr == -1UL) @@ -490,58 +615,152 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs, #define GPFSTR "general protection fault" -dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) +static bool fixup_iopl_exception(struct pt_regs *regs) +{ + struct thread_struct *t = ¤t->thread; + unsigned char byte; + unsigned long ip; + + if (!IS_ENABLED(CONFIG_X86_IOPL_IOPERM) || t->iopl_emul != 3) + return false; + + if (insn_get_effective_ip(regs, &ip)) + return false; + + if (get_user(byte, (const char __user *)ip)) + return false; + + if (byte != 0xfa && byte != 0xfb) + return false; + + if (!t->iopl_warn && printk_ratelimit()) { + pr_err("%s[%d] attempts to use CLI/STI, pretending it's a NOP, ip:%lx", + current->comm, task_pid_nr(current), ip); + print_vma_addr(KERN_CONT " in ", ip); + pr_cont("\n"); + t->iopl_warn = 1; + } + + regs->ip += 1; + return true; +} + +/* + * The unprivileged ENQCMD instruction generates #GPs if the + * IA32_PASID MSR has not been populated. If possible, populate + * the MSR from a PASID previously allocated to the mm. + */ +static bool try_fixup_enqcmd_gp(void) +{ +#ifdef CONFIG_IOMMU_SVA + u32 pasid; + + /* + * MSR_IA32_PASID is managed using XSAVE. Directly + * writing to the MSR is only possible when fpregs + * are valid and the fpstate is not. This is + * guaranteed when handling a userspace exception + * in *before* interrupts are re-enabled. + */ + lockdep_assert_irqs_disabled(); + + /* + * Hardware without ENQCMD will not generate + * #GPs that can be fixed up here. + */ + if (!cpu_feature_enabled(X86_FEATURE_ENQCMD)) + return false; + + pasid = current->mm->pasid; + + /* + * If the mm has not been allocated a + * PASID, the #GP can not be fixed up. + */ + if (!pasid_valid(pasid)) + return false; + + /* + * Did this thread already have its PASID activated? + * If so, the #GP must be from something else. + */ + if (current->pasid_activated) + return false; + + wrmsrl(MSR_IA32_PASID, pasid | MSR_IA32_PASID_VALID); + current->pasid_activated = 1; + + return true; +#else + return false; +#endif +} + +static bool gp_try_fixup_and_notify(struct pt_regs *regs, int trapnr, + unsigned long error_code, const char *str) +{ + if (fixup_exception(regs, trapnr, error_code, 0)) + return true; + + current->thread.error_code = error_code; + current->thread.trap_nr = trapnr; + + /* + * To be potentially processing a kprobe fault and to trust the result + * from kprobe_running(), we have to be non-preemptible. + */ + if (!preemptible() && kprobe_running() && + kprobe_fault_handler(regs, trapnr)) + return true; + + return notify_die(DIE_GPF, str, regs, error_code, trapnr, SIGSEGV) == NOTIFY_STOP; +} + +static void gp_user_force_sig_segv(struct pt_regs *regs, int trapnr, + unsigned long error_code, const char *str) +{ + current->thread.error_code = error_code; + current->thread.trap_nr = trapnr; + show_signal(current, SIGSEGV, "", str, regs, error_code); + force_sig(SIGSEGV); +} + +DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) { char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR; enum kernel_gp_hint hint = GP_NO_HINT; - struct task_struct *tsk; unsigned long gp_addr; - int ret; - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + if (user_mode(regs) && try_fixup_enqcmd_gp()) + return; + cond_local_irq_enable(regs); if (static_cpu_has(X86_FEATURE_UMIP)) { if (user_mode(regs) && fixup_umip_exception(regs)) - return; + goto exit; } if (v8086_mode(regs)) { local_irq_enable(); handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); + local_irq_disable(); return; } - tsk = current; - if (user_mode(regs)) { - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; + if (fixup_iopl_exception(regs)) + goto exit; - show_signal(tsk, SIGSEGV, "", desc, regs, error_code); - force_sig(SIGSEGV); + if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0)) + goto exit; - return; + gp_user_force_sig_segv(regs, X86_TRAP_GP, error_code, desc); + goto exit; } - if (fixup_exception(regs, X86_TRAP_GP, error_code, 0)) - return; - - tsk->thread.error_code = error_code; - tsk->thread.trap_nr = X86_TRAP_GP; - - /* - * To be potentially processing a kprobe fault and to trust the result - * from kprobe_running(), we have to be non-preemptible. - */ - if (!preemptible() && - kprobe_running() && - kprobe_fault_handler(regs, X86_TRAP_GP)) - return; - - ret = notify_die(DIE_GPF, desc, regs, error_code, X86_TRAP_GP, SIGSEGV); - if (ret == NOTIFY_STOP) - return; + if (gp_try_fixup_and_notify(regs, X86_TRAP_GP, error_code, desc)) + goto exit; if (error_code) snprintf(desc, sizeof(desc), "segment-related " GPFSTR); @@ -563,46 +782,73 @@ dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) die_addr(desc, regs, error_code, gp_addr); +exit: + cond_local_irq_disable(regs); } -NOKPROBE_SYMBOL(do_general_protection); -dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) +static bool do_int3(struct pt_regs *regs) { - if (poke_int3_handler(regs)) - return; + int res; - /* - * Use ist_enter despite the fact that we don't use an IST stack. - * We can be called from a kprobe in non-CONTEXT_KERNEL kernel - * mode or even during context tracking state changes. - * - * This means that we can't schedule. That's okay. - */ - ist_enter(regs); - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP - if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, - SIGTRAP) == NOTIFY_STOP) - goto exit; + if (kgdb_ll_trap(DIE_INT3, "int3", regs, 0, X86_TRAP_BP, + SIGTRAP) == NOTIFY_STOP) + return true; #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */ #ifdef CONFIG_KPROBES if (kprobe_int3_handler(regs)) - goto exit; + return true; #endif + res = notify_die(DIE_INT3, "int3", regs, 0, X86_TRAP_BP, SIGTRAP); - if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, - SIGTRAP) == NOTIFY_STOP) - goto exit; + return res == NOTIFY_STOP; +} +NOKPROBE_SYMBOL(do_int3); + +static void do_int3_user(struct pt_regs *regs) +{ + if (do_int3(regs)) + return; cond_local_irq_enable(regs); - do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, 0, NULL); + do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, 0, 0, NULL); cond_local_irq_disable(regs); +} -exit: - ist_exit(regs); +DEFINE_IDTENTRY_RAW(exc_int3) +{ + /* + * poke_int3_handler() is completely self contained code; it does (and + * must) *NOT* call out to anything, lest it hits upon yet another + * INT3. + */ + if (poke_int3_handler(regs)) + return; + + /* + * irqentry_enter_from_user_mode() uses static_branch_{,un}likely() + * and therefore can trigger INT3, hence poke_int3_handler() must + * be done before. If the entry came from kernel mode, then use + * nmi_enter() because the INT3 could have been hit in any context + * including NMI. + */ + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + instrumentation_begin(); + do_int3_user(regs); + instrumentation_end(); + irqentry_exit_to_user_mode(regs); + } else { + irqentry_state_t irq_state = irqentry_nmi_enter(regs); + + instrumentation_begin(); + if (!do_int3(regs)) + die("int3", regs, 0); + instrumentation_end(); + irqentry_nmi_exit(regs, irq_state); + } } -NOKPROBE_SYMBOL(do_int3); #ifdef CONFIG_X86_64 /* @@ -610,23 +856,61 @@ NOKPROBE_SYMBOL(do_int3); * to switch to the normal thread stack if the interrupted code was in * user mode. The actual stack switch is done in entry_64.S */ -asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs) +asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs) { struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1; if (regs != eregs) *regs = *eregs; return regs; } -NOKPROBE_SYMBOL(sync_regs); -struct bad_iret_stack { - void *error_entry_ret; - struct pt_regs regs; -}; +#ifdef CONFIG_AMD_MEM_ENCRYPT +asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *regs) +{ + unsigned long sp, *stack; + struct stack_info info; + struct pt_regs *regs_ret; + + /* + * In the SYSCALL entry path the RSP value comes from user-space - don't + * trust it and switch to the current kernel stack + */ + if (ip_within_syscall_gap(regs)) { + sp = this_cpu_read(cpu_current_top_of_stack); + goto sync; + } -asmlinkage __visible notrace -struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) + /* + * From here on the RSP value is trusted. Now check whether entry + * happened from a safe stack. Not safe are the entry or unknown stacks, + * use the fall-back stack instead in this case. + */ + sp = regs->sp; + stack = (unsigned long *)sp; + + if (!get_stack_info_noinstr(stack, current, &info) || info.type == STACK_TYPE_ENTRY || + info.type > STACK_TYPE_EXCEPTION_LAST) + sp = __this_cpu_ist_top_va(VC2); + +sync: + /* + * Found a safe stack - switch to it as if the entry didn't happen via + * IST stack. The code below only copies pt_regs, the real switch happens + * in assembly code. + */ + sp = ALIGN_DOWN(sp, 8) - sizeof(*regs_ret); + + regs_ret = (struct pt_regs *)sp; + *regs_ret = *regs; + + return regs_ret; +} +#endif + +asmlinkage __visible noinstr struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs) { + struct pt_regs tmp, *new_stack; + /* * This is called from entry_64.S early in handling a fault * caused by a bad iret to user mode. To handle the fault @@ -635,19 +919,20 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) * just below the IRET frame) and we want to pretend that the * exception came from the IRET target. */ - struct bad_iret_stack *new_stack = - (struct bad_iret_stack *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; + new_stack = (struct pt_regs *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; - /* Copy the IRET target to the new stack. */ - memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); + /* Copy the IRET target to the temporary storage. */ + __memcpy(&tmp.ip, (void *)bad_regs->sp, 5*8); /* Copy the remainder of the stack from the current stack. */ - memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip)); + __memcpy(&tmp, bad_regs, offsetof(struct pt_regs, ip)); - BUG_ON(!user_mode(&new_stack->regs)); + /* Update the entry stack */ + __memcpy(new_stack, &tmp, sizeof(tmp)); + + BUG_ON(!user_mode(new_stack)); return new_stack; } -NOKPROBE_SYMBOL(fixup_bad_iret); #endif static bool is_sysenter_singlestep(struct pt_regs *regs) @@ -673,6 +958,28 @@ static bool is_sysenter_singlestep(struct pt_regs *regs) #endif } +static __always_inline unsigned long debug_read_clear_dr6(void) +{ + unsigned long dr6; + + /* + * The Intel SDM says: + * + * Certain debug exceptions may clear bits 0-3. The remaining + * contents of the DR6 register are never cleared by the + * processor. To avoid confusion in identifying debug + * exceptions, debug handlers should clear the register before + * returning to the interrupted task. + * + * Keep it simple: clear DR6 immediately. + */ + get_debugreg(dr6, 6); + set_debugreg(DR6_RESERVED, 6); + dr6 ^= DR6_RESERVED; /* Flip to positive polarity */ + + return dr6; +} + /* * Our handling of the processor debug registers is non-trivial. * We do not clear them on entry and exit from the kernel. Therefore @@ -697,116 +1004,200 @@ static bool is_sysenter_singlestep(struct pt_regs *regs) * * May run on IST stack. */ -dotraplinkage void do_debug(struct pt_regs *regs, long error_code) + +static bool notify_debug(struct pt_regs *regs, unsigned long *dr6) { - struct task_struct *tsk = current; - int user_icebp = 0; - unsigned long dr6; - int si_code; + /* + * Notifiers will clear bits in @dr6 to indicate the event has been + * consumed - hw_breakpoint_handler(), single_stop_cont(). + * + * Notifiers will set bits in @virtual_dr6 to indicate the desire + * for signals - ptrace_triggered(), kgdb_hw_overflow_handler(). + */ + if (notify_die(DIE_DEBUG, "debug", regs, (long)dr6, 0, SIGTRAP) == NOTIFY_STOP) + return true; - ist_enter(regs); + return false; +} - get_debugreg(dr6, 6); +static __always_inline void exc_debug_kernel(struct pt_regs *regs, + unsigned long dr6) +{ /* - * The Intel SDM says: + * Disable breakpoints during exception handling; recursive exceptions + * are exceedingly 'fun'. * - * Certain debug exceptions may clear bits 0-3. The remaining - * contents of the DR6 register are never cleared by the - * processor. To avoid confusion in identifying debug - * exceptions, debug handlers should clear the register before - * returning to the interrupted task. + * Since this function is NOKPROBE, and that also applies to + * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a + * HW_BREAKPOINT_W on our stack) * - * Keep it simple: clear DR6 immediately. + * Entry text is excluded for HW_BP_X and cpu_entry_area, which + * includes the entry stack is excluded for everything. */ - set_debugreg(0, 6); - - /* Filter out all the reserved bits which are preset to 1 */ - dr6 &= ~DR6_RESERVED; + unsigned long dr7 = local_db_save(); + irqentry_state_t irq_state = irqentry_nmi_enter(regs); + instrumentation_begin(); /* - * The SDM says "The processor clears the BTF flag when it - * generates a debug exception." Clear TIF_BLOCKSTEP to keep - * TIF_BLOCKSTEP in sync with the hardware BTF flag. + * If something gets miswired and we end up here for a user mode + * #DB, we will malfunction. */ - clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP); + WARN_ON_ONCE(user_mode(regs)); - if (unlikely(!user_mode(regs) && (dr6 & DR_STEP) && - is_sysenter_singlestep(regs))) { - dr6 &= ~DR_STEP; - if (!dr6) - goto exit; + if (test_thread_flag(TIF_BLOCKSTEP)) { /* - * else we might have gotten a single-step trap and hit a - * watchpoint at the same time, in which case we should fall - * through and handle the watchpoint. + * The SDM says "The processor clears the BTF flag when it + * generates a debug exception." but PTRACE_BLOCKSTEP requested + * it for userspace, but we just took a kernel #DB, so re-set + * BTF. */ + unsigned long debugctl; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl |= DEBUGCTLMSR_BTF; + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); } /* - * If dr6 has no reason to give us about the origin of this trap, - * then it's very likely the result of an icebp/int01 trap. - * User wants a sigtrap for that. + * Catch SYSENTER with TF set and clear DR_STEP. If this hit a + * watchpoint at the same time then that will still be handled. + */ + if ((dr6 & DR_STEP) && is_sysenter_singlestep(regs)) + dr6 &= ~DR_STEP; + + /* + * The kernel doesn't use INT1 */ - if (!dr6 && user_mode(regs)) - user_icebp = 1; + if (!dr6) + goto out; - /* Store the virtualized DR6 value */ - tsk->thread.debugreg6 = dr6; + if (notify_debug(regs, &dr6)) + goto out; -#ifdef CONFIG_KPROBES - if (kprobe_debug_handler(regs)) - goto exit; -#endif + /* + * The kernel doesn't use TF single-step outside of: + * + * - Kprobes, consumed through kprobe_debug_handler() + * - KGDB, consumed through notify_debug() + * + * So if we get here with DR_STEP set, something is wonky. + * + * A known way to trigger this is through QEMU's GDB stub, + * which leaks #DB into the guest and causes IST recursion. + */ + if (WARN_ON_ONCE(dr6 & DR_STEP)) + regs->flags &= ~X86_EFLAGS_TF; +out: + instrumentation_end(); + irqentry_nmi_exit(regs, irq_state); - if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, error_code, - SIGTRAP) == NOTIFY_STOP) - goto exit; + local_db_restore(dr7); +} + +static __always_inline void exc_debug_user(struct pt_regs *regs, + unsigned long dr6) +{ + bool icebp; + + /* + * If something gets miswired and we end up here for a kernel mode + * #DB, we will malfunction. + */ + WARN_ON_ONCE(!user_mode(regs)); + + /* + * NB: We can't easily clear DR7 here because + * irqentry_exit_to_usermode() can invoke ptrace, schedule, access + * user memory, etc. This means that a recursive #DB is possible. If + * this happens, that #DB will hit exc_debug_kernel() and clear DR7. + * Since we're not on the IST stack right now, everything will be + * fine. + */ + + irqentry_enter_from_user_mode(regs); + instrumentation_begin(); /* - * Let others (NMI) know that the debug stack is in use - * as we may switch to the interrupt stack. + * Start the virtual/ptrace DR6 value with just the DR_STEP mask + * of the real DR6. ptrace_triggered() will set the DR_TRAPn bits. + * + * Userspace expects DR_STEP to be visible in ptrace_get_debugreg(6) + * even if it is not the result of PTRACE_SINGLESTEP. + */ + current->thread.virtual_dr6 = (dr6 & DR_STEP); + + /* + * The SDM says "The processor clears the BTF flag when it + * generates a debug exception." Clear TIF_BLOCKSTEP to keep + * TIF_BLOCKSTEP in sync with the hardware BTF flag. */ - debug_stack_usage_inc(); + clear_thread_flag(TIF_BLOCKSTEP); + + /* + * If dr6 has no reason to give us about the origin of this trap, + * then it's very likely the result of an icebp/int01 trap. + * User wants a sigtrap for that. + */ + icebp = !dr6; + + if (notify_debug(regs, &dr6)) + goto out; /* It's safe to allow irq's after DR6 has been saved */ - cond_local_irq_enable(regs); + local_irq_enable(); if (v8086_mode(regs)) { - handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, - X86_TRAP_DB); - cond_local_irq_disable(regs); - debug_stack_usage_dec(); - goto exit; + handle_vm86_trap((struct kernel_vm86_regs *)regs, 0, X86_TRAP_DB); + goto out_irq; } - if (WARN_ON_ONCE((dr6 & DR_STEP) && !user_mode(regs))) { - /* - * Historical junk that used to handle SYSENTER single-stepping. - * This should be unreachable now. If we survive for a while - * without anyone hitting this warning, we'll turn this into - * an oops. - */ - tsk->thread.debugreg6 &= ~DR_STEP; - set_tsk_thread_flag(tsk, TIF_SINGLESTEP); - regs->flags &= ~X86_EFLAGS_TF; - } - si_code = get_si_code(tsk->thread.debugreg6); - if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) - send_sigtrap(regs, error_code, si_code); - cond_local_irq_disable(regs); - debug_stack_usage_dec(); + /* #DB for bus lock can only be triggered from userspace. */ + if (dr6 & DR_BUS_LOCK) + handle_bus_lock(regs); -exit: - ist_exit(regs); + /* Add the virtual_dr6 bits for signals. */ + dr6 |= current->thread.virtual_dr6; + if (dr6 & (DR_STEP | DR_TRAP_BITS) || icebp) + send_sigtrap(regs, 0, get_si_code(dr6)); + +out_irq: + local_irq_disable(); +out: + instrumentation_end(); + irqentry_exit_to_user_mode(regs); +} + +#ifdef CONFIG_X86_64 +/* IST stack entry */ +DEFINE_IDTENTRY_DEBUG(exc_debug) +{ + exc_debug_kernel(regs, debug_read_clear_dr6()); +} + +/* User entry, runs on regular task stack */ +DEFINE_IDTENTRY_DEBUG_USER(exc_debug) +{ + exc_debug_user(regs, debug_read_clear_dr6()); +} +#else +/* 32 bit does not have separate entry points. */ +DEFINE_IDTENTRY_RAW(exc_debug) +{ + unsigned long dr6 = debug_read_clear_dr6(); + + if (user_mode(regs)) + exc_debug_user(regs, dr6); + else + exc_debug_kernel(regs, dr6); } -NOKPROBE_SYMBOL(do_debug); +#endif /* * Note that we play around with the 'TS' bit in an attempt to get * the correct behaviour even in the presence of the asynchronous * IRQ13 behaviour */ -static void math_error(struct pt_regs *regs, int error_code, int trapnr) +static void math_error(struct pt_regs *regs, int trapnr) { struct task_struct *task = current; struct fpu *fpu = &task->thread.fpu; @@ -817,60 +1208,122 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) cond_local_irq_enable(regs); if (!user_mode(regs)) { - if (fixup_exception(regs, trapnr, error_code, 0)) - return; + if (fixup_exception(regs, trapnr, 0, 0)) + goto exit; - task->thread.error_code = error_code; + task->thread.error_code = 0; task->thread.trap_nr = trapnr; - if (notify_die(DIE_TRAP, str, regs, error_code, - trapnr, SIGFPE) != NOTIFY_STOP) - die(str, regs, error_code); - return; + if (notify_die(DIE_TRAP, str, regs, 0, trapnr, + SIGFPE) != NOTIFY_STOP) + die(str, regs, 0); + goto exit; } /* - * Save the info for the exception handler and clear the error. + * Synchronize the FPU register state to the memory register state + * if necessary. This allows the exception handler to inspect it. */ - fpu__save(fpu); + fpu_sync_fpstate(fpu); task->thread.trap_nr = trapnr; - task->thread.error_code = error_code; + task->thread.error_code = 0; si_code = fpu__exception_code(fpu, trapnr); /* Retry when we get spurious exceptions: */ if (!si_code) - return; + goto exit; + + if (fixup_vdso_exception(regs, trapnr, 0, 0)) + goto exit; force_sig_fault(SIGFPE, si_code, (void __user *)uprobe_get_trap_addr(regs)); +exit: + cond_local_irq_disable(regs); } -dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY(exc_coprocessor_error) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - math_error(regs, error_code, X86_TRAP_MF); + math_error(regs, X86_TRAP_MF); } -dotraplinkage void -do_simd_coprocessor_error(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY(exc_simd_coprocessor_error) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - math_error(regs, error_code, X86_TRAP_XF); + if (IS_ENABLED(CONFIG_X86_INVD_BUG)) { + /* AMD 486 bug: INVD in CPL 0 raises #XF instead of #GP */ + if (!static_cpu_has(X86_FEATURE_XMM)) { + __exc_general_protection(regs, 0); + return; + } + } + math_error(regs, X86_TRAP_XF); } -dotraplinkage void -do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY(exc_spurious_interrupt_bug) { - cond_local_irq_enable(regs); + /* + * This addresses a Pentium Pro Erratum: + * + * PROBLEM: If the APIC subsystem is configured in mixed mode with + * Virtual Wire mode implemented through the local APIC, an + * interrupt vector of 0Fh (Intel reserved encoding) may be + * generated by the local APIC (Int 15). This vector may be + * generated upon receipt of a spurious interrupt (an interrupt + * which is removed before the system receives the INTA sequence) + * instead of the programmed 8259 spurious interrupt vector. + * + * IMPLICATION: The spurious interrupt vector programmed in the + * 8259 is normally handled by an operating system's spurious + * interrupt handler. However, a vector of 0Fh is unknown to some + * operating systems, which would crash if this erratum occurred. + * + * In theory this could be limited to 32bit, but the handler is not + * hurting and who knows which other CPUs suffer from this. + */ +} + +static bool handle_xfd_event(struct pt_regs *regs) +{ + u64 xfd_err; + int err; + + if (!IS_ENABLED(CONFIG_X86_64) || !cpu_feature_enabled(X86_FEATURE_XFD)) + return false; + + rdmsrl(MSR_IA32_XFD_ERR, xfd_err); + if (!xfd_err) + return false; + + wrmsrl(MSR_IA32_XFD_ERR, 0); + + /* Die if that happens in kernel space */ + if (WARN_ON(!user_mode(regs))) + return false; + + local_irq_enable(); + + err = xfd_enable_feature(xfd_err); + + switch (err) { + case -EPERM: + force_sig_fault(SIGILL, ILL_ILLOPC, error_get_trap_addr(regs)); + break; + case -EFAULT: + force_sig(SIGSEGV); + break; + } + + local_irq_disable(); + return true; } -dotraplinkage void -do_device_not_available(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY(exc_device_not_available) { unsigned long cr0 = read_cr0(); - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + if (handle_xfd_event(regs)) + return; #ifdef CONFIG_MATH_EMULATION if (!boot_cpu_has(X86_FEATURE_FPU) && (cr0 & X86_CR0_EM)) { @@ -880,6 +1333,8 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); + + cond_local_irq_disable(regs); return; } #endif @@ -894,22 +1349,105 @@ do_device_not_available(struct pt_regs *regs, long error_code) * to kill the task than getting stuck in a never-ending * loop of #NM faults. */ - die("unexpected #NM exception", regs, error_code); + die("unexpected #NM exception", regs, 0); + } +} + +#ifdef CONFIG_INTEL_TDX_GUEST + +#define VE_FAULT_STR "VE fault" + +static void ve_raise_fault(struct pt_regs *regs, long error_code) +{ + if (user_mode(regs)) { + gp_user_force_sig_segv(regs, X86_TRAP_VE, error_code, VE_FAULT_STR); + return; } + + if (gp_try_fixup_and_notify(regs, X86_TRAP_VE, error_code, VE_FAULT_STR)) + return; + + die_addr(VE_FAULT_STR, regs, error_code, 0); +} + +/* + * Virtualization Exceptions (#VE) are delivered to TDX guests due to + * specific guest actions which may happen in either user space or the + * kernel: + * + * * Specific instructions (WBINVD, for example) + * * Specific MSR accesses + * * Specific CPUID leaf accesses + * * Access to specific guest physical addresses + * + * In the settings that Linux will run in, virtualization exceptions are + * never generated on accesses to normal, TD-private memory that has been + * accepted (by BIOS or with tdx_enc_status_changed()). + * + * Syscall entry code has a critical window where the kernel stack is not + * yet set up. Any exception in this window leads to hard to debug issues + * and can be exploited for privilege escalation. Exceptions in the NMI + * entry code also cause issues. Returning from the exception handler with + * IRET will re-enable NMIs and nested NMI will corrupt the NMI stack. + * + * For these reasons, the kernel avoids #VEs during the syscall gap and + * the NMI entry code. Entry code paths do not access TD-shared memory, + * MMIO regions, use #VE triggering MSRs, instructions, or CPUID leaves + * that might generate #VE. VMM can remove memory from TD at any point, + * but access to unaccepted (or missing) private memory leads to VM + * termination, not to #VE. + * + * Similarly to page faults and breakpoints, #VEs are allowed in NMI + * handlers once the kernel is ready to deal with nested NMIs. + * + * During #VE delivery, all interrupts, including NMIs, are blocked until + * TDGETVEINFO is called. It prevents #VE nesting until the kernel reads + * the VE info. + * + * If a guest kernel action which would normally cause a #VE occurs in + * the interrupt-disabled region before TDGETVEINFO, a #DF (fault + * exception) is delivered to the guest which will result in an oops. + * + * The entry code has been audited carefully for following these expectations. + * Changes in the entry code have to be audited for correctness vs. this + * aspect. Similarly to #PF, #VE in these places will expose kernel to + * privilege escalation or may lead to random crashes. + */ +DEFINE_IDTENTRY(exc_virtualization_exception) +{ + struct ve_info ve; + + /* + * NMIs/Machine-checks/Interrupts will be in a disabled state + * till TDGETVEINFO TDCALL is executed. This ensures that VE + * info cannot be overwritten by a nested #VE. + */ + tdx_get_ve_info(&ve); + + cond_local_irq_enable(regs); + + /* + * If tdx_handle_virt_exception() could not process + * it successfully, treat it as #GP(0) and handle it. + */ + if (!tdx_handle_virt_exception(regs, &ve)) + ve_raise_fault(regs, 0); + + cond_local_irq_disable(regs); } -NOKPROBE_SYMBOL(do_device_not_available); + +#endif #ifdef CONFIG_X86_32 -dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY_SW(iret_error) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); local_irq_enable(); - - if (notify_die(DIE_TRAP, "iret exception", regs, error_code, + if (notify_die(DIE_TRAP, "iret exception", regs, 0, X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) { - do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, + do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, 0, ILL_BADSTK, (void __user *)NULL); } + local_irq_disable(); } #endif @@ -918,25 +1456,12 @@ void __init trap_init(void) /* Init cpu_entry_area before IST entries are set up */ setup_cpu_entry_areas(); - idt_setup_traps(); + /* Init GHCB memory pages when running as an SEV-ES guest */ + sev_es_init_vc_handling(); - /* - * Set the IDT descriptor to a fixed read-only location, so that the - * "sidt" instruction will not leak the location of the kernel, and - * to defend the IDT against arbitrary memory write vulnerabilities. - * It will be reloaded in cpu_init() */ - cea_set_pte(CPU_ENTRY_AREA_RO_IDT_VADDR, __pa_symbol(idt_table), - PAGE_KERNEL_RO); - idt_descr.address = CPU_ENTRY_AREA_RO_IDT; - - /* - * Should be a barrier for any external CPU state: - */ + /* Initialize TSS before setting up traps so ISTs work */ + cpu_init_exception_handling(); + /* Setup traps as cpu_init() might #GP */ + idt_setup_traps(); cpu_init(); - - idt_setup_ist_traps(); - - x86_init.irqs.trap_init(); - - idt_setup_debugidt_traps(); } |