x86/unwinder: Handle stack overflows more gracefully

There are at least two unwinder bugs hindering the debugging of
stack-overflow crashes:

- It doesn't deal gracefully with the case where the stack overflows and
  the stack pointer itself isn't on a valid stack but the
  to-be-dereferenced data *is*.

- The ORC oops dump code doesn't know how to print partial pt_regs, for the
  case where if we get an interrupt/exception in *early* entry code
  before the full pt_regs have been saved.

Fix both issues.

http://lkml.kernel.org/r/20171126024031.uxi4numpbjm5rlbr@treble

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bpetkov@suse.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Link: https://lkml.kernel.org/r/20171204150605.071425003@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/kdebug.h

@@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_stack_regs(struct pt_regs *regs);
 extern void __show_regs(struct pt_regs *regs, int all);
+extern void show_iret_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);
 

arch/x86/include/asm/unwind.h

@@ -7,6 +7,9 @@
 #include <asm/ptrace.h>
 #include <asm/stacktrace.h>
 
+#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip))
+#define IRET_FRAME_SIZE   (sizeof(struct pt_regs) - IRET_FRAME_OFFSET)
+
 struct unwind_state {
 	struct stack_info stack_info;
 	unsigned long stack_mask;
@@ -52,6 +55,10 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
 }
 
 #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER)
+/*
+ * WARNING: The entire pt_regs may not be safe to dereference.  In some cases,
+ * only the iret frame registers are accessible.  Use with caution!
+ */
 static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
 {
 	if (unwind_done(state))

arch/x86/kernel/dumpstack.c

@@ -50,6 +50,28 @@ static void printk_stack_address(unsigned long address, int reliable,
 	printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
 }
 
+void show_iret_regs(struct pt_regs *regs)
+{
+	printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip);
+	printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss,
+		regs->sp, regs->flags);
+}
+
+static void show_regs_safe(struct stack_info *info, struct pt_regs *regs)
+{
+	if (on_stack(info, regs, sizeof(*regs)))
+		__show_regs(regs, 0);
+	else if (on_stack(info, (void *)regs + IRET_FRAME_OFFSET,
+			  IRET_FRAME_SIZE)) {
+		/*
+		 * When an interrupt or exception occurs in entry code, the
+		 * full pt_regs might not have been saved yet.  In that case
+		 * just print the iret frame.
+		 */
+		show_iret_regs(regs);
+	}
+}
+
 void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			unsigned long *stack, char *log_lvl)
 {
@@ -94,8 +116,8 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		if (stack_name)
 			printk("%s <%s>\n", log_lvl, stack_name);
 
-		if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
-			__show_regs(regs, 0);
+		if (regs)
+			show_regs_safe(&stack_info, regs);
 
 		/*
 		 * Scan the stack, printing any text addresses we find.  At the
@@ -119,7 +141,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 
 			/*
 			 * Don't print regs->ip again if it was already printed
-			 * by __show_regs() below.
+			 * by show_regs_safe() below.
 			 */
 			if (regs && stack == &regs->ip)
 				goto next;
@@ -155,8 +177,8 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 
 			/* if the frame has entry regs, print them */
 			regs = unwind_get_entry_regs(&state);
-			if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
-				__show_regs(regs, 0);
+			if (regs)
+				show_regs_safe(&stack_info, regs);
 		}
 
 		if (stack_name)

arch/x86/kernel/process_64.c

@@ -69,9 +69,8 @@ void __show_regs(struct pt_regs *regs, int all)
 	unsigned int fsindex, gsindex;
 	unsigned int ds, cs, es;
 
-	printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip);
-	printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss,
-		regs->sp, regs->flags);
+	show_iret_regs(regs);
+
 	if (regs->orig_ax != -1)
 		pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax);
 	else
@@ -88,6 +87,9 @@ void __show_regs(struct pt_regs *regs, int all)
 	printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
 	       regs->r13, regs->r14, regs->r15);
 
+	if (!all)
+		return;
+
 	asm("movl %%ds,%0" : "=r" (ds));
 	asm("movl %%cs,%0" : "=r" (cs));
 	asm("movl %%es,%0" : "=r" (es));
@@ -98,9 +100,6 @@ void __show_regs(struct pt_regs *regs, int all)
 	rdmsrl(MSR_GS_BASE, gs);
 	rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
 
-	if (!all)
-		return;
-
 	cr0 = read_cr0();
 	cr2 = read_cr2();
 	cr3 = __read_cr3();

arch/x86/kernel/unwind_orc.c

@@ -253,22 +253,15 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
 	return NULL;
 }
 
-static bool stack_access_ok(struct unwind_state *state, unsigned long addr,
+static bool stack_access_ok(struct unwind_state *state, unsigned long _addr,
 			    size_t len)
 {
 	struct stack_info *info = &state->stack_info;
+	void *addr = (void *)_addr;
 
-	/*
-	 * If the address isn't on the current stack, switch to the next one.
-	 *
-	 * We may have to traverse multiple stacks to deal with the possibility
-	 * that info->next_sp could point to an empty stack and the address
-	 * could be on a subsequent stack.
-	 */
-	while (!on_stack(info, (void *)addr, len))
-		if (get_stack_info(info->next_sp, state->task, info,
-				   &state->stack_mask))
-			return false;
+	if (!on_stack(info, addr, len) &&
+	    (get_stack_info(addr, state->task, info, &state->stack_mask)))
+		return false;
 
 	return true;
 }
@@ -283,42 +276,32 @@ static bool deref_stack_reg(struct unwind_state *state, unsigned long addr,
 	return true;
 }
 
-#define REGS_SIZE (sizeof(struct pt_regs))
-#define SP_OFFSET (offsetof(struct pt_regs, sp))
-#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip))
-#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip))
-
 static bool deref_stack_regs(struct unwind_state *state, unsigned long addr,
-			     unsigned long *ip, unsigned long *sp, bool full)
+			     unsigned long *ip, unsigned long *sp)
 {
-	size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE;
-	size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET;
-	struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE);
+	struct pt_regs *regs = (struct pt_regs *)addr;
 
-	if (IS_ENABLED(CONFIG_X86_64)) {
-		if (!stack_access_ok(state, addr, regs_size))
-			return false;
+	/* x86-32 support will be more complicated due to the &regs->sp hack */
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_32));
 
-		*ip = regs->ip;
-		*sp = regs->sp;
-
-		return true;
-	}
-
-	if (!stack_access_ok(state, addr, sp_offset))
+	if (!stack_access_ok(state, addr, sizeof(struct pt_regs)))
 		return false;
 
 	*ip = regs->ip;
+	*sp = regs->sp;
+	return true;
+}
 
-	if (user_mode(regs)) {
-		if (!stack_access_ok(state, addr + sp_offset,
-				     REGS_SIZE - SP_OFFSET))
-			return false;
+static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr,
+				  unsigned long *ip, unsigned long *sp)
+{
+	struct pt_regs *regs = (void *)addr - IRET_FRAME_OFFSET;
 
-		*sp = regs->sp;
-	} else
-		*sp = (unsigned long)&regs->sp;
+	if (!stack_access_ok(state, addr, IRET_FRAME_SIZE))
+		return false;
 
+	*ip = regs->ip;
+	*sp = regs->sp;
 	return true;
 }
 
@@ -327,7 +310,6 @@ bool unwind_next_frame(struct unwind_state *state)
 	unsigned long ip_p, sp, orig_ip, prev_sp = state->sp;
 	enum stack_type prev_type = state->stack_info.type;
 	struct orc_entry *orc;
-	struct pt_regs *ptregs;
 	bool indirect = false;
 
 	if (unwind_done(state))
@@ -435,7 +417,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_TYPE_REGS:
-		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) {
+		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
 			goto done;
@@ -447,20 +429,14 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_TYPE_REGS_IRET:
-		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) {
+		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference iret registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
 			goto done;
 		}
 
-		ptregs = container_of((void *)sp, struct pt_regs, ip);
-		if ((unsigned long)ptregs >= prev_sp &&
-		    on_stack(&state->stack_info, ptregs, REGS_SIZE)) {
-			state->regs = ptregs;
-			state->full_regs = false;
-		} else
-			state->regs = NULL;
-
+		state->regs = (void *)sp - IRET_FRAME_OFFSET;
+		state->full_regs = false;
 		state->signal = true;
 		break;