- A couple of SEV-ES fixes and robustifications: verify usermode stack

pointer in NMI is not coming from the syscall gap, correctly track IRQ
 states in the #VC handler and access user insn bytes atomically in same
 handler as latter cannot sleep.
 
 - Balance 32-bit fast syscall exit path to do the proper work on exit
 and thus not confuse audit and ptrace frameworks.
 
 - Two fixes for the ORC unwinder going "off the rails" into KASAN
 redzones and when ORC data is missing.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmBN+ksACgkQEsHwGGHe
 VUpYtBAAj199n50ipP2x+jjgCueIytMqwCCRozrgZ8JF0Al83piVfjhuAYQpfvD8
 cKCxN/jSEF0YoUg/grBTPLG6f0J4B2GoekSlSc3ljnuhBby4iJ9B4YgE7qym6tuT
 G/mBOuAo2HBzvB70i1BYPN6mrA+6SG1d4tIhRLGKHCz+hQm8yYnJYVbiOkLBECeP
 0QOOpX6hR5ytOOCRqwD/O5YIdZD8NvlA4sQE522Mrw/4PWz9XcS2kwpOQFHoRsFL
 if3t2yLMiGMfV0dyUCMoGZl0NqpnIZynoNdVPq/bllTW5obnmh6z8Eir44PzJmVJ
 ftVZTcReRqm5ObgwZh0g1H7CRjKe0xU9FyJHRmQl3Xb5g3wRAm3OkMJ2hQcOUPy9
 VOB4vp7kbDg3MmGJe2xOtsEeAyVHGzTaWlmZ0moxjJXiLTjUy69eelmvLepypO3P
 Bo/xpjn9hN7L9ptKv1exsSatQRN7KWTCxtz+NBJgC4pEpkdtDBkaWunIKeauPTZ2
 CAJJrp2sn7i5/CKPOuhjbQ+nSTMptpuZQxTDrjVUO0/6qs4ffQT3O+WXRV1bQ07v
 ObRqi0hIYgm4vSiBfVRfxOU+Zrx0j3kny4/xUs6CIjMjrjIp4RgBbqvZ95ZMooMi
 yeyZdVfzQ7PRaam5J2V3IHxKz7554hvMl5Zf4zAdl0qcQw3YZ0o=
 =rw8S
 -----END PGP SIGNATURE-----

Merge tag 'x86_urgent_for_v5.12_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

 - A couple of SEV-ES fixes and robustifications: verify usermode stack
   pointer in NMI is not coming from the syscall gap, correctly track
   IRQ states in the #VC handler and access user insn bytes atomically
   in same handler as latter cannot sleep.

 - Balance 32-bit fast syscall exit path to do the proper work on exit
   and thus not confuse audit and ptrace frameworks.

 - Two fixes for the ORC unwinder going "off the rails" into KASAN
   redzones and when ORC data is missing.

* tag 'x86_urgent_for_v5.12_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/sev-es: Use __copy_from_user_inatomic()
  x86/sev-es: Correctly track IRQ states in runtime #VC handler
  x86/sev-es: Check regs->sp is trusted before adjusting #VC IST stack
  x86/sev-es: Introduce ip_within_syscall_gap() helper
  x86/entry: Fix entry/exit mismatch on failed fast 32-bit syscalls
  x86/unwind/orc: Silence warnings caused by missing ORC data
  x86/unwind/orc: Disable KASAN checking in the ORC unwinder, part 2

arch/x86/entry/common.c

@@ -128,7 +128,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 		regs->ax = -EFAULT;
 
 		instrumentation_end();
-		syscall_exit_to_user_mode(regs);
+		local_irq_disable();
+		irqentry_exit_to_user_mode(regs);
 		return false;
 	}
 

arch/x86/entry/entry_64_compat.S

@@ -210,6 +210,8 @@ SYM_CODE_START(entry_SYSCALL_compat)
 	/* Switch to the kernel stack */
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
+SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL)
+
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER32_DS		/* pt_regs->ss */
 	pushq	%r8			/* pt_regs->sp */

arch/x86/include/asm/insn-eval.h

@@ -23,6 +23,8 @@ unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx);
 int insn_get_code_seg_params(struct pt_regs *regs);
 int insn_fetch_from_user(struct pt_regs *regs,
 			 unsigned char buf[MAX_INSN_SIZE]);
+int insn_fetch_from_user_inatomic(struct pt_regs *regs,
+				  unsigned char buf[MAX_INSN_SIZE]);
 bool insn_decode(struct insn *insn, struct pt_regs *regs,
 		 unsigned char buf[MAX_INSN_SIZE], int buf_size);
 

arch/x86/include/asm/proto.h

@@ -25,6 +25,7 @@ void __end_SYSENTER_singlestep_region(void);
 void entry_SYSENTER_compat(void);
 void __end_entry_SYSENTER_compat(void);
 void entry_SYSCALL_compat(void);
+void entry_SYSCALL_compat_safe_stack(void);
 void entry_INT80_compat(void);
 #ifdef CONFIG_XEN_PV
 void xen_entry_INT80_compat(void);

arch/x86/include/asm/ptrace.h

@@ -94,6 +94,8 @@ struct pt_regs {
 #include <asm/paravirt_types.h>
 #endif
 
+#include <asm/proto.h>
+
 struct cpuinfo_x86;
 struct task_struct;
 
@@ -175,6 +177,19 @@ static inline bool any_64bit_mode(struct pt_regs *regs)
 #ifdef CONFIG_X86_64
 #define current_user_stack_pointer()	current_pt_regs()->sp
 #define compat_user_stack_pointer()	current_pt_regs()->sp
+
+static inline bool ip_within_syscall_gap(struct pt_regs *regs)
+{
+	bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
+		    regs->ip <  (unsigned long)entry_SYSCALL_64_safe_stack);
+
+#ifdef CONFIG_IA32_EMULATION
+	ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat &&
+		      regs->ip <  (unsigned long)entry_SYSCALL_compat_safe_stack);
+#endif
+
+	return ret;
+}
 #endif
 
 static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)

arch/x86/kernel/sev-es.c

@@ -121,8 +121,18 @@ static void __init setup_vc_stacks(int cpu)
 	cea_set_pte((void *)vaddr, pa, PAGE_KERNEL);
 }
 
-static __always_inline bool on_vc_stack(unsigned long sp)
+static __always_inline bool on_vc_stack(struct pt_regs *regs)
 {
+	unsigned long sp = regs->sp;
+
+	/* User-mode RSP is not trusted */
+	if (user_mode(regs))
+		return false;
+
+	/* SYSCALL gap still has user-mode RSP */
+	if (ip_within_syscall_gap(regs))
+		return false;
+
 	return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
 }
 
@@ -144,7 +154,7 @@ void noinstr __sev_es_ist_enter(struct pt_regs *regs)
 	old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
 
 	/* Make room on the IST stack */
-	if (on_vc_stack(regs->sp))
+	if (on_vc_stack(regs))
 		new_ist = ALIGN_DOWN(regs->sp, 8) - sizeof(old_ist);
 	else
 		new_ist = old_ist - sizeof(old_ist);
@@ -248,7 +258,7 @@ static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
 	int res;
 
 	if (user_mode(ctxt->regs)) {
-		res = insn_fetch_from_user(ctxt->regs, buffer);
+		res = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
 		if (!res) {
 			ctxt->fi.vector     = X86_TRAP_PF;
 			ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
@@ -1248,13 +1258,12 @@ static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs)
 DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
 {
 	struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
+	irqentry_state_t irq_state;
 	struct ghcb_state state;
 	struct es_em_ctxt ctxt;
 	enum es_result result;
 	struct ghcb *ghcb;
 
-	lockdep_assert_irqs_disabled();
-
 	/*
 	 * Handle #DB before calling into !noinstr code to avoid recursive #DB.
 	 */
@@ -1263,6 +1272,8 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
 		return;
 	}
 
+	irq_state = irqentry_nmi_enter(regs);
+	lockdep_assert_irqs_disabled();
 	instrumentation_begin();
 
 	/*
@@ -1325,6 +1336,7 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
 
 out:
 	instrumentation_end();
+	irqentry_nmi_exit(regs, irq_state);
 
 	return;
 

arch/x86/kernel/traps.c

@@ -694,8 +694,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r
 	 * In the SYSCALL entry path the RSP value comes from user-space - don't
 	 * trust it and switch to the current kernel stack
 	 */
-	if (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
-	    regs->ip <  (unsigned long)entry_SYSCALL_64_safe_stack) {
+	if (ip_within_syscall_gap(regs)) {
 		sp = this_cpu_read(cpu_current_top_of_stack);
 		goto sync;
 	}

arch/x86/kernel/unwind_orc.c

@@ -13,7 +13,7 @@
 
 #define orc_warn_current(args...)					\
 ({									\
-	if (state->task == current)					\
+	if (state->task == current && !state->error)			\
 		orc_warn(args);						\
 })
 
@@ -367,8 +367,8 @@ static bool deref_stack_regs(struct unwind_state *state, unsigned long addr,
 	if (!stack_access_ok(state, addr, sizeof(struct pt_regs)))
 		return false;
 
-	*ip = regs->ip;
-	*sp = regs->sp;
+	*ip = READ_ONCE_NOCHECK(regs->ip);
+	*sp = READ_ONCE_NOCHECK(regs->sp);
 	return true;
 }
 
@@ -380,8 +380,8 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr
 	if (!stack_access_ok(state, addr, IRET_FRAME_SIZE))
 		return false;
 
-	*ip = regs->ip;
-	*sp = regs->sp;
+	*ip = READ_ONCE_NOCHECK(regs->ip);
+	*sp = READ_ONCE_NOCHECK(regs->sp);
 	return true;
 }
 
@@ -402,12 +402,12 @@ static bool get_reg(struct unwind_state *state, unsigned int reg_off,
 		return false;
 
 	if (state->full_regs) {
-		*val = ((unsigned long *)state->regs)[reg];
+		*val = READ_ONCE_NOCHECK(((unsigned long *)state->regs)[reg]);
 		return true;
 	}
 
 	if (state->prev_regs) {
-		*val = ((unsigned long *)state->prev_regs)[reg];
+		*val = READ_ONCE_NOCHECK(((unsigned long *)state->prev_regs)[reg]);
 		return true;
 	}
 

arch/x86/lib/insn-eval.c

@@ -1415,6 +1415,25 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
 	}
 }
 
+static unsigned long insn_get_effective_ip(struct pt_regs *regs)
+{
+	unsigned long seg_base = 0;
+
+	/*
+	 * If not in user-space long mode, a custom code segment could be in
+	 * use. This is true in protected mode (if the process defined a local
+	 * descriptor table), or virtual-8086 mode. In most of the cases
+	 * seg_base will be zero as in USER_CS.
+	 */
+	if (!user_64bit_mode(regs)) {
+		seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS);
+		if (seg_base == -1L)
+			return 0;
+	}
+
+	return seg_base + regs->ip;
+}
+
 /**
  * insn_fetch_from_user() - Copy instruction bytes from user-space memory
  * @regs:	Structure with register values as seen when entering kernel mode
@@ -1431,24 +1450,43 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
  */
 int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE])
 {
-	unsigned long seg_base = 0;
+	unsigned long ip;
 	int not_copied;
 
-	/*
-	 * If not in user-space long mode, a custom code segment could be in
-	 * use. This is true in protected mode (if the process defined a local
-	 * descriptor table), or virtual-8086 mode. In most of the cases
-	 * seg_base will be zero as in USER_CS.
-	 */
-	if (!user_64bit_mode(regs)) {
-		seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS);
-		if (seg_base == -1L)
-			return 0;
-	}
+	ip = insn_get_effective_ip(regs);
+	if (!ip)
+		return 0;
 
+	not_copied = copy_from_user(buf, (void __user *)ip, MAX_INSN_SIZE);
 
-	not_copied = copy_from_user(buf, (void __user *)(seg_base + regs->ip),
-				    MAX_INSN_SIZE);
+	return MAX_INSN_SIZE - not_copied;
+}
+
+/**
+ * insn_fetch_from_user_inatomic() - Copy instruction bytes from user-space memory
+ *                                   while in atomic code
+ * @regs:	Structure with register values as seen when entering kernel mode
+ * @buf:	Array to store the fetched instruction
+ *
+ * Gets the linear address of the instruction and copies the instruction bytes
+ * to the buf. This function must be used in atomic context.
+ *
+ * Returns:
+ *
+ * Number of instruction bytes copied.
+ *
+ * 0 if nothing was copied.
+ */
+int insn_fetch_from_user_inatomic(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE])
+{
+	unsigned long ip;
+	int not_copied;
+
+	ip = insn_get_effective_ip(regs);
+	if (!ip)
+		return 0;
+
+	not_copied = __copy_from_user_inatomic(buf, (void __user *)ip, MAX_INSN_SIZE);
 
 	return MAX_INSN_SIZE - not_copied;
 }