Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm updates from Thomas Gleixner:
 "The lowlevel and ASM code updates for x86:

   - Make stack trace unwinding more reliable

   - ASM instruction updates for better code generation

   - Various cleanups"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/entry/64: Add two more instruction suffixes
  x86/asm/64: Use 32-bit XOR to zero registers
  x86/build/vdso: Simplify 'cmd_vdso2c'
  x86/build/vdso: Remove unused vdso-syms.lds
  x86/stacktrace: Enable HAVE_RELIABLE_STACKTRACE for the ORC unwinder
  x86/unwind/orc: Detect the end of the stack
  x86/stacktrace: Do not fail for ORC with regs on stack
  x86/stacktrace: Clarify the reliable success paths
  x86/stacktrace: Remove STACKTRACE_DUMP_ONCE
  x86/stacktrace: Do not unwind after user regs
  x86/asm: Use CC_SET/CC_OUT in percpu_cmpxchg8b_double() to micro-optimize code generation

4 files changed, 47 insertions, 51 deletions

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 8344dd2f310a..15ebc2fc166e 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -235,7 +235,7 @@ ENTRY(secondary_startup_64)
 	 *		address given in m16:64.
 	 */
 	pushq	$.Lafter_lret	# put return address on stack for unwinder
-	xorq	%rbp, %rbp	# clear frame pointer
+	xorl	%ebp, %ebp	# clear frame pointer
 	movq	initial_code(%rip), %rax
 	pushq	$__KERNEL_CS	# set correct cs
 	pushq	%rax		# target address in negative space
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 9edadabf04f6..9cb98f7b07c9 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -20,7 +20,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax");
 
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
 DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
-DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
 #endif
 
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 093f2ea5dd56..7627455047c2 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -81,16 +81,6 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 #ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
 
-#define STACKTRACE_DUMP_ONCE(task) ({				\
-	static bool __section(.data.unlikely) __dumped;		\
-								\
-	if (!__dumped) {					\
-		__dumped = true;				\
-		WARN_ON(1);					\
-		show_stack(task, NULL);				\
-	}							\
-})
-
 static int __always_inline
 __save_stack_trace_reliable(struct stack_trace *trace,
 			    struct task_struct *task)
@@ -99,30 +89,25 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 	struct pt_regs *regs;
 	unsigned long addr;
 
-	for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
+	for (unwind_start(&state, task, NULL, NULL);
+	     !unwind_done(&state) && !unwind_error(&state);
 	     unwind_next_frame(&state)) {
 
 		regs = unwind_get_entry_regs(&state, NULL);
 		if (regs) {
+			/* Success path for user tasks */
+			if (user_mode(regs))
+				goto success;
+
 			/*
 			 * Kernel mode registers on the stack indicate an
 			 * in-kernel interrupt or exception (e.g., preemption
 			 * or a page fault), which can make frame pointers
 			 * unreliable.
 			 */
-			if (!user_mode(regs))
-				return -EINVAL;
 
-			/*
-			 * The last frame contains the user mode syscall
-			 * pt_regs.  Skip it and finish the unwind.
-			 */
-			unwind_next_frame(&state);
-			if (!unwind_done(&state)) {
-				STACKTRACE_DUMP_ONCE(task);
+			if (IS_ENABLED(CONFIG_FRAME_POINTER))
 				return -EINVAL;
-			}
-			break;
 		}
 
 		addr = unwind_get_return_address(&state);
@@ -132,21 +117,22 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 		 * generated code which __kernel_text_address() doesn't know
 		 * about.
 		 */
-		if (!addr) {
-			STACKTRACE_DUMP_ONCE(task);
+		if (!addr)
 			return -EINVAL;
-		}
 
 		if (save_stack_address(trace, addr, false))
 			return -EINVAL;
 	}
 
 	/* Check for stack corruption */
-	if (unwind_error(&state)) {
-		STACKTRACE_DUMP_ONCE(task);
+	if (unwind_error(&state))
+		return -EINVAL;
+
+	/* Success path for non-user tasks, i.e. kthreads and idle tasks */
+	if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
 		return -EINVAL;
-	}
 
+success:
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index feb28fee6cea..26038eacf74a 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -198,7 +198,7 @@ static int orc_sort_cmp(const void *_a, const void *_b)
 	 * whitelisted .o files which didn't get objtool generation.
 	 */
 	orc_a = cur_orc_table + (a - cur_orc_ip_table);
-	return orc_a->sp_reg == ORC_REG_UNDEFINED ? -1 : 1;
+	return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1;
 }
 
 #ifdef CONFIG_MODULES
@@ -352,7 +352,7 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr
 
 bool unwind_next_frame(struct unwind_state *state)
 {
-	unsigned long ip_p, sp, orig_ip, prev_sp = state->sp;
+	unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp;
 	enum stack_type prev_type = state->stack_info.type;
 	struct orc_entry *orc;
 	bool indirect = false;
@@ -363,9 +363,9 @@ bool unwind_next_frame(struct unwind_state *state)
 	/* Don't let modules unload while we're reading their ORC data. */
 	preempt_disable();
 
-	/* Have we reached the end? */
+	/* End-of-stack check for user tasks: */
 	if (state->regs && user_mode(state->regs))
-		goto done;
+		goto the_end;
 
 	/*
 	 * Find the orc_entry associated with the text address.
@@ -374,9 +374,16 @@ bool unwind_next_frame(struct unwind_state *state)
 	 * calls and calls to noreturn functions.
 	 */
 	orc = orc_find(state->signal ? state->ip : state->ip - 1);
-	if (!orc || orc->sp_reg == ORC_REG_UNDEFINED)
-		goto done;
-	orig_ip = state->ip;
+	if (!orc)
+		goto err;
+
+	/* End-of-stack check for kernel threads: */
+	if (orc->sp_reg == ORC_REG_UNDEFINED) {
+		if (!orc->end)
+			goto err;
+
+		goto the_end;
+	}
 
 	/* Find the previous frame's stack: */
 	switch (orc->sp_reg) {
@@ -402,7 +409,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg R10 at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->r10;
 		break;
@@ -411,7 +418,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg R13 at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->r13;
 		break;
@@ -420,7 +427,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg DI at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->di;
 		break;
@@ -429,7 +436,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg DX at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->dx;
 		break;
@@ -437,12 +444,12 @@ bool unwind_next_frame(struct unwind_state *state)
 	default:
 		orc_warn("unknown SP base reg %d for ip %pB\n",
 			 orc->sp_reg, (void *)state->ip);
-		goto done;
+		goto err;
 	}
 
 	if (indirect) {
 		if (!deref_stack_reg(state, sp, &sp))
-			goto done;
+			goto err;
 	}
 
 	/* Find IP, SP and possibly regs: */
@@ -451,7 +458,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		ip_p = sp - sizeof(long);
 
 		if (!deref_stack_reg(state, ip_p, &state->ip))
-			goto done;
+			goto err;
 
 		state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
 						  state->ip, (void *)ip_p);
@@ -465,7 +472,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		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;
+			goto err;
 		}
 
 		state->regs = (struct pt_regs *)sp;
@@ -477,7 +484,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		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;
+			goto err;
 		}
 
 		state->regs = (void *)sp - IRET_FRAME_OFFSET;
@@ -500,18 +507,18 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	case ORC_REG_PREV_SP:
 		if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp))
-			goto done;
+			goto err;
 		break;
 
 	case ORC_REG_BP:
 		if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp))
-			goto done;
+			goto err;
 		break;
 
 	default:
 		orc_warn("unknown BP base reg %d for ip %pB\n",
 			 orc->bp_reg, (void *)orig_ip);
-		goto done;
+		goto err;
 	}
 
 	/* Prevent a recursive loop due to bad ORC data: */
@@ -520,13 +527,16 @@ bool unwind_next_frame(struct unwind_state *state)
 	    state->sp <= prev_sp) {
 		orc_warn("stack going in the wrong direction? ip=%pB\n",
 			 (void *)orig_ip);
-		goto done;
+		goto err;
 	}
 
 	preempt_enable();
 	return true;
 
-done:
+err:
+	state->error = true;
+
+the_end:
 	preempt_enable();
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
 	return false;