1 files changed, 265 insertions, 39 deletions

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c9d566dcf89a..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>
@@ -39,6 +40,7 @@
 #include <linux/io.h>
 #include <linux/hardirq.h>
 #include <linux/atomic.h>
+#include <linux/ioasid.h>
 
 #include <asm/stacktrace.h>
 #include <asm/processor.h>
@@ -61,6 +63,8 @@
 #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>
@@ -209,6 +213,81 @@ 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
@@ -223,6 +302,12 @@ 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;
 
@@ -236,7 +321,8 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	 */
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_enable();
-	if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
+	if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN ||
+	    handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
 		regs->ip += LEN_UD2;
 		handled = true;
 	}
@@ -559,13 +645,94 @@ static bool fixup_iopl_exception(struct pt_regs *regs)
 	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;
+
+	if (user_mode(regs) && try_fixup_enqcmd_gp())
+		return;
 
 	cond_local_irq_enable(regs);
 
@@ -581,40 +748,18 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection)
 		return;
 	}
 
-	tsk = current;
-
 	if (user_mode(regs)) {
 		if (fixup_iopl_exception(regs))
 			goto exit;
 
-		tsk->thread.error_code = error_code;
-		tsk->thread.trap_nr = X86_TRAP_GP;
-
 		if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0))
 			goto exit;
 
-		show_signal(tsk, SIGSEGV, "", desc, regs, error_code);
-		force_sig(SIGSEGV);
+		gp_user_force_sig_segv(regs, X86_TRAP_GP, error_code, desc);
 		goto exit;
 	}
 
-	if (fixup_exception(regs, X86_TRAP_GP, error_code, 0))
-		goto exit;
-
-	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))
-		goto exit;
-
-	ret = notify_die(DIE_GPF, desc, regs, error_code, X86_TRAP_GP, SIGSEGV);
-	if (ret == NOTIFY_STOP)
+	if (gp_try_fixup_and_notify(regs, X86_TRAP_GP, error_code, desc))
 		goto exit;
 
 	if (error_code)
@@ -659,6 +804,7 @@ static bool do_int3(struct pt_regs *regs)
 
 	return res == NOTIFY_STOP;
 }
+NOKPROBE_SYMBOL(do_int3);
 
 static void do_int3_user(struct pt_regs *regs)
 {
@@ -761,14 +907,10 @@ sync:
 }
 #endif
 
-struct bad_iret_stack {
-	void *error_entry_ret;
-	struct pt_regs regs;
-};
-
-asmlinkage __visible noinstr
-struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
+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
@@ -777,19 +919,18 @@ 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 tmp, *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 temporary storage. */
-	__memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
+	__memcpy(&tmp.ip, (void *)bad_regs->sp, 5*8);
 
 	/* Copy the remainder of the stack from the current stack. */
-	__memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
+	__memcpy(&tmp, bad_regs, offsetof(struct pt_regs, ip));
 
 	/* Update the entry stack */
 	__memcpy(new_stack, &tmp, sizeof(tmp));
 
-	BUG_ON(!user_mode(&new_stack->regs));
+	BUG_ON(!user_mode(new_stack));
 	return new_stack;
 }
 #endif
@@ -1212,6 +1353,91 @@ DEFINE_IDTENTRY(exc_device_not_available)
 	}
 }
 
+#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);
+}
+
+#endif
+
 #ifdef CONFIG_X86_32
 DEFINE_IDTENTRY_SW(iret_error)
 {