Merge tag 'objtool-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull objtool updates from Ingo Molar:
 "Build footprint & performance improvements:

   - Reduce memory usage with CONFIG_DEBUG_INFO=y

     In the worst case of an allyesconfig+CONFIG_DEBUG_INFO=y kernel,
     DWARF creates almost 200 million relocations, ballooning objtool's
     peak heap usage to 53GB. These patches reduce that to 25GB.

     On a distro-type kernel with kernel IBT enabled, they reduce
     objtool's peak heap usage from 4.2GB to 2.8GB.

     These changes also improve the runtime significantly.

  Debuggability improvements:

   - Add the unwind_debug command-line option, for more extend unwinding
     debugging output
   - Limit unreachable warnings to once per function
   - Add verbose option for disassembling affected functions
   - Include backtrace in verbose mode
   - Detect missing __noreturn annotations
   - Ignore exc_double_fault() __noreturn warnings
   - Remove superfluous global_noreturns entries
   - Move noreturn function list to separate file
   - Add __kunit_abort() to noreturns

  Unwinder improvements:

   - Allow stack operations in UNWIND_HINT_UNDEFINED regions
   - drm/vmwgfx: Add unwind hints around RBP clobber

  Cleanups:

   - Move the x86 entry thunk restore code into thunk functions
   - x86/unwind/orc: Use swap() instead of open coding it
   - Remove unnecessary/unused variables

  Fixes for modern stack canary handling"

* tag 'objtool-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (42 commits)
  x86/orc: Make the is_callthunk() definition depend on CONFIG_BPF_JIT=y
  objtool: Skip reading DWARF section data
  objtool: Free insns when done
  objtool: Get rid of reloc->rel[a]
  objtool: Shrink elf hash nodes
  objtool: Shrink reloc->sym_reloc_entry
  objtool: Get rid of reloc->jump_table_start
  objtool: Get rid of reloc->addend
  objtool: Get rid of reloc->type
  objtool: Get rid of reloc->offset
  objtool: Get rid of reloc->idx
  objtool: Get rid of reloc->list
  objtool: Allocate relocs in advance for new rela sections
  objtool: Add for_each_reloc()
  objtool: Don't free memory in elf_close()
  objtool: Keep GElf_Rel[a] structs synced
  objtool: Add elf_create_section_pair()
  objtool: Add mark_sec_changed()
  objtool: Fix reloc_hash size
  objtool: Consolidate rel/rela handling
  ...

5 files changed, 69 insertions, 44 deletions

diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index 5e37f41e5f14..27b5da2111ac 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -26,17 +26,7 @@ SYM_FUNC_START(\name)
 	pushq %r11
 
 	call \func
-	jmp  __thunk_restore
-SYM_FUNC_END(\name)
-	_ASM_NOKPROBE(\name)
-	.endm
-
-	THUNK preempt_schedule_thunk, preempt_schedule
-	THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
-	EXPORT_SYMBOL(preempt_schedule_thunk)
-	EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
 
-SYM_CODE_START_LOCAL(__thunk_restore)
 	popq %r11
 	popq %r10
 	popq %r9
@@ -48,5 +38,11 @@ SYM_CODE_START_LOCAL(__thunk_restore)
 	popq %rdi
 	popq %rbp
 	RET
-	_ASM_NOKPROBE(__thunk_restore)
-SYM_CODE_END(__thunk_restore)
+SYM_FUNC_END(\name)
+	_ASM_NOKPROBE(\name)
+	.endm
+
+THUNK preempt_schedule_thunk, preempt_schedule
+THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
+EXPORT_SYMBOL(preempt_schedule_thunk)
+EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index d7da28fada87..6c15a622ad60 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -113,7 +113,6 @@ extern void callthunks_patch_builtin_calls(void);
 extern void callthunks_patch_module_calls(struct callthunk_sites *sites,
 					  struct module *mod);
 extern void *callthunks_translate_call_dest(void *dest);
-extern bool is_callthunk(void *addr);
 extern int x86_call_depth_emit_accounting(u8 **pprog, void *func);
 #else
 static __always_inline void callthunks_patch_builtin_calls(void) {}
@@ -124,10 +123,6 @@ static __always_inline void *callthunks_translate_call_dest(void *dest)
 {
 	return dest;
 }
-static __always_inline bool is_callthunk(void *addr)
-{
-	return false;
-}
 static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
 							  void *func)
 {
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index 01cb9692b160..85cc57cb6539 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -76,9 +76,18 @@
 
 #else
 
+#define UNWIND_HINT_UNDEFINED \
+	UNWIND_HINT(UNWIND_HINT_TYPE_UNDEFINED, 0, 0, 0)
+
 #define UNWIND_HINT_FUNC \
 	UNWIND_HINT(UNWIND_HINT_TYPE_FUNC, ORC_REG_SP, 8, 0)
 
+#define UNWIND_HINT_SAVE \
+	UNWIND_HINT(UNWIND_HINT_TYPE_SAVE, 0, 0, 0)
+
+#define UNWIND_HINT_RESTORE \
+	UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0)
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_UNWIND_HINTS_H */
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 8bb937331acb..c06bfc086565 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -293,7 +293,8 @@ void *callthunks_translate_call_dest(void *dest)
 	return target ? : dest;
 }
 
-bool is_callthunk(void *addr)
+#ifdef CONFIG_BPF_JIT
+static bool is_callthunk(void *addr)
 {
 	unsigned int tmpl_size = SKL_TMPL_SIZE;
 	void *tmpl = skl_call_thunk_template;
@@ -306,7 +307,6 @@ bool is_callthunk(void *addr)
 	return !bcmp((void *)(dest - tmpl_size), tmpl, tmpl_size);
 }
 
-#ifdef CONFIG_BPF_JIT
 int x86_call_depth_emit_accounting(u8 **pprog, void *func)
 {
 	unsigned int tmpl_size = SKL_TMPL_SIZE;
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 4d8e518365f4..7e574cf3bf8a 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -16,8 +16,14 @@ ORC_HEADER;
 
 #define orc_warn_current(args...)					\
 ({									\
-	if (state->task == current && !state->error)			\
+	static bool dumped_before;					\
+	if (state->task == current && !state->error) {			\
 		orc_warn(args);						\
+		if (unwind_debug && !dumped_before) {			\
+			dumped_before = true;				\
+			unwind_dump(state);				\
+		}							\
+	}								\
 })
 
 extern int __start_orc_unwind_ip[];
@@ -26,8 +32,49 @@ extern struct orc_entry __start_orc_unwind[];
 extern struct orc_entry __stop_orc_unwind[];
 
 static bool orc_init __ro_after_init;
+static bool unwind_debug __ro_after_init;
 static unsigned int lookup_num_blocks __ro_after_init;
 
+static int __init unwind_debug_cmdline(char *str)
+{
+	unwind_debug = true;
+
+	return 0;
+}
+early_param("unwind_debug", unwind_debug_cmdline);
+
+static void unwind_dump(struct unwind_state *state)
+{
+	static bool dumped_before;
+	unsigned long word, *sp;
+	struct stack_info stack_info = {0};
+	unsigned long visit_mask = 0;
+
+	if (dumped_before)
+		return;
+
+	dumped_before = true;
+
+	printk_deferred("unwind stack type:%d next_sp:%p mask:0x%lx graph_idx:%d\n",
+			state->stack_info.type, state->stack_info.next_sp,
+			state->stack_mask, state->graph_idx);
+
+	for (sp = __builtin_frame_address(0); sp;
+	     sp = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
+		if (get_stack_info(sp, state->task, &stack_info, &visit_mask))
+			break;
+
+		for (; sp < stack_info.end; sp++) {
+
+			word = READ_ONCE_NOCHECK(*sp);
+
+			printk_deferred("%0*lx: %0*lx (%pB)\n", BITS_PER_LONG/4,
+					(unsigned long)sp, BITS_PER_LONG/4,
+					word, (void *)word);
+		}
+	}
+}
+
 static inline unsigned long orc_ip(const int *ip)
 {
 	return (unsigned long)ip + *ip;
@@ -139,21 +186,6 @@ static struct orc_entry null_orc_entry = {
 	.type = ORC_TYPE_CALL
 };
 
-#ifdef CONFIG_CALL_THUNKS
-static struct orc_entry *orc_callthunk_find(unsigned long ip)
-{
-	if (!is_callthunk((void *)ip))
-		return NULL;
-
-	return &null_orc_entry;
-}
-#else
-static struct orc_entry *orc_callthunk_find(unsigned long ip)
-{
-	return NULL;
-}
-#endif
-
 /* Fake frame pointer entry -- used as a fallback for generated code */
 static struct orc_entry orc_fp_entry = {
 	.type		= ORC_TYPE_CALL,
@@ -206,11 +238,7 @@ static struct orc_entry *orc_find(unsigned long ip)
 	if (orc)
 		return orc;
 
-	orc =  orc_ftrace_find(ip);
-	if (orc)
-		return orc;
-
-	return orc_callthunk_find(ip);
+	return orc_ftrace_find(ip);
 }
 
 #ifdef CONFIG_MODULES
@@ -222,7 +250,6 @@ static struct orc_entry *cur_orc_table = __start_orc_unwind;
 static void orc_sort_swap(void *_a, void *_b, int size)
 {
 	struct orc_entry *orc_a, *orc_b;
-	struct orc_entry orc_tmp;
 	int *a = _a, *b = _b, tmp;
 	int delta = _b - _a;
 
@@ -234,9 +261,7 @@ static void orc_sort_swap(void *_a, void *_b, int size)
 	/* Swap the corresponding .orc_unwind entries: */
 	orc_a = cur_orc_table + (a - cur_orc_ip_table);
 	orc_b = cur_orc_table + (b - cur_orc_ip_table);
-	orc_tmp = *orc_a;
-	*orc_a = *orc_b;
-	*orc_b = orc_tmp;
+	swap(*orc_a, *orc_b);
 }
 
 static int orc_sort_cmp(const void *_a, const void *_b)