Merge tag 'objtool-core-2020-10-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull objtool updates from Ingo Molnar:
 "Most of the changes are cleanups and reorganization to make the
  objtool code more arch-agnostic. This is in preparation for non-x86
  support.

  Other changes:

   - KASAN fixes

   - Handle unreachable trap after call to noreturn functions better

   - Ignore unreachable fake jumps

   - Misc smaller fixes & cleanups"

* tag 'objtool-core-2020-10-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  perf build: Allow nested externs to enable BUILD_BUG() usage
  objtool: Allow nested externs to enable BUILD_BUG()
  objtool: Permit __kasan_check_{read,write} under UACCESS
  objtool: Ignore unreachable trap after call to noreturn functions
  objtool: Handle calling non-function symbols in other sections
  objtool: Ignore unreachable fake jumps
  objtool: Remove useless tests before save_reg()
  objtool: Decode unwind hint register depending on architecture
  objtool: Make unwind hint definitions available to other architectures
  objtool: Only include valid definitions depending on source file type
  objtool: Rename frame.h -> objtool.h
  objtool: Refactor jump table code to support other architectures
  objtool: Make relocation in alternative handling arch dependent
  objtool: Abstract alternative special case handling
  objtool: Move macros describing structures to arch-dependent code
  objtool: Make sync-check consider the target architecture
  objtool: Group headers to check in a single list
  objtool: Define 'struct orc_entry' only when needed
  objtool: Skip ORC entry creation for non-text sections
  objtool: Move ORC logic out of check()
  ...

MAINTAINERS

@@ -12515,6 +12515,7 @@ M:	Josh Poimboeuf <jpoimboe@redhat.com>
 M:	Peter Zijlstra <peterz@infradead.org>
 S:	Supported
 F:	tools/objtool/
+F:	include/linux/objtool.h
 
 OCELOT ETHERNET SWITCH DRIVER
 M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>

arch/x86/include/asm/nospec-branch.h

@@ -4,7 +4,7 @@
 #define _ASM_X86_NOSPEC_BRANCH_H_
 
 #include <linux/static_key.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 
 #include <asm/alternative.h>
 #include <asm/alternative-asm.h>

arch/x86/include/asm/orc_types.h

@@ -39,27 +39,6 @@
 #define ORC_REG_SP_INDIRECT		9
 #define ORC_REG_MAX			15
 
-/*
- * ORC_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP (the
- * caller's SP right before it made the call).  Used for all callable
- * functions, i.e. all C code and all callable asm functions.
- *
- * ORC_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset points
- * to a fully populated pt_regs from a syscall, interrupt, or exception.
- *
- * ORC_TYPE_REGS_IRET: Used in entry code to indicate that sp_reg+sp_offset
- * points to the iret return frame.
- *
- * The UNWIND_HINT macros are used only for the unwind_hint struct.  They
- * aren't used in struct orc_entry due to size and complexity constraints.
- * Objtool converts them to real types when it converts the hints to orc
- * entries.
- */
-#define ORC_TYPE_CALL			0
-#define ORC_TYPE_REGS			1
-#define ORC_TYPE_REGS_IRET		2
-#define UNWIND_HINT_TYPE_RET_OFFSET	3
-
 #ifndef __ASSEMBLY__
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
@@ -78,19 +57,6 @@ struct orc_entry {
 	unsigned	end:1;
 } __packed;
 
-/*
- * This struct is used by asm and inline asm code to manually annotate the
- * location of registers on the stack for the ORC unwinder.
- *
- * Type can be either ORC_TYPE_* or UNWIND_HINT_TYPE_*.
- */
-struct unwind_hint {
-	u32		ip;
-	s16		sp_offset;
-	u8		sp_reg;
-	u8		type;
-	u8		end;
-};
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ORC_TYPES_H */

arch/x86/include/asm/unwind_hints.h

 #ifndef _ASM_X86_UNWIND_HINTS_H
 #define _ASM_X86_UNWIND_HINTS_H
 
+#include <linux/objtool.h>
+
 #include "orc_types.h"
 
 #ifdef __ASSEMBLY__
 
-/*
- * In asm, there are two kinds of code: normal C-type callable functions and
- * the rest.  The normal callable functions can be called by other code, and
- * don't do anything unusual with the stack.  Such normal callable functions
- * are annotated with the ENTRY/ENDPROC macros.  Most asm code falls in this
- * category.  In this case, no special debugging annotations are needed because
- * objtool can automatically generate the ORC data for the ORC unwinder to read
- * at runtime.
- *
- * Anything which doesn't fall into the above category, such as syscall and
- * interrupt handlers, tends to not be called directly by other functions, and
- * often does unusual non-C-function-type things with the stack pointer.  Such
- * code needs to be annotated such that objtool can understand it.  The
- * following CFI hint macros are for this type of code.
- *
- * These macros provide hints to objtool about the state of the stack at each
- * instruction.  Objtool starts from the hints and follows the code flow,
- * making automatic CFI adjustments when it sees pushes and pops, filling out
- * the debuginfo as necessary.  It will also warn if it sees any
- * inconsistencies.
- */
-.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL end=0
-#ifdef CONFIG_STACK_VALIDATION
-.Lunwind_hint_ip_\@:
-	.pushsection .discard.unwind_hints
-		/* struct unwind_hint */
-		.long .Lunwind_hint_ip_\@ - .
-		.short \sp_offset
-		.byte \sp_reg
-		.byte \type
-		.byte \end
-		.balign 4
-	.popsection
-#endif
-.endm
-
 .macro UNWIND_HINT_EMPTY
-	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED end=1
+	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_CALL end=1
 .endm
 
-.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0
+.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0
 	.if \base == %rsp
 		.if \indirect
 			.set sp_reg, ORC_REG_SP_INDIRECT
@@ -66,24 +32,24 @@
 
 	.set sp_offset, \offset
 
-	.if \iret
-		.set type, ORC_TYPE_REGS_IRET
+	.if \partial
+		.set type, UNWIND_HINT_TYPE_REGS_PARTIAL
 	.elseif \extra == 0
-		.set type, ORC_TYPE_REGS_IRET
+		.set type, UNWIND_HINT_TYPE_REGS_PARTIAL
 		.set sp_offset, \offset + (16*8)
 	.else
-		.set type, ORC_TYPE_REGS
+		.set type, UNWIND_HINT_TYPE_REGS
 	.endif
 
 	UNWIND_HINT sp_reg=sp_reg sp_offset=sp_offset type=type
 .endm
 
 .macro UNWIND_HINT_IRET_REGS base=%rsp offset=0
-	UNWIND_HINT_REGS base=\base offset=\offset iret=1
+	UNWIND_HINT_REGS base=\base offset=\offset partial=1
 .endm
 
 .macro UNWIND_HINT_FUNC sp_offset=8
-	UNWIND_HINT sp_offset=\sp_offset
+	UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=\sp_offset type=UNWIND_HINT_TYPE_CALL
 .endm
 
 /*
@@ -92,7 +58,7 @@
  * initial_func_cfi.
  */
 .macro UNWIND_HINT_RET_OFFSET sp_offset=8
-	UNWIND_HINT type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset
+	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_RET_OFFSET sp_offset=\sp_offset
 .endm
 
 #endif /* __ASSEMBLY__ */

arch/x86/kernel/kprobes/core.c

@@ -38,9 +38,9 @@
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
-#include <linux/frame.h>
 #include <linux/kasan.h>
 #include <linux/moduleloader.h>
+#include <linux/objtool.h>
 #include <linux/vmalloc.h>
 #include <linux/pgtable.h>
 

arch/x86/kernel/kprobes/opt.c

@@ -16,7 +16,7 @@
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/pgtable.h>
 #include <linux/static_call.h>
 

arch/x86/kernel/reboot.c

@@ -10,7 +10,7 @@
 #include <linux/sched.h>
 #include <linux/tboot.h>
 #include <linux/delay.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/pgtable.h>
 #include <acpi/reboot.h>
 #include <asm/io.h>

arch/x86/kernel/unwind_orc.c

 // SPDX-License-Identifier: GPL-2.0-only
+#include <linux/objtool.h>
 #include <linux/module.h>
 #include <linux/sort.h>
 #include <asm/ptrace.h>
@@ -127,12 +128,12 @@ static struct orc_entry null_orc_entry = {
 	.sp_offset = sizeof(long),
 	.sp_reg = ORC_REG_SP,
 	.bp_reg = ORC_REG_UNDEFINED,
-	.type = ORC_TYPE_CALL
+	.type = UNWIND_HINT_TYPE_CALL
 };
 
 /* Fake frame pointer entry -- used as a fallback for generated code */
 static struct orc_entry orc_fp_entry = {
-	.type		= ORC_TYPE_CALL,
+	.type		= UNWIND_HINT_TYPE_CALL,
 	.sp_reg		= ORC_REG_BP,
 	.sp_offset	= 16,
 	.bp_reg		= ORC_REG_PREV_SP,
@@ -531,7 +532,7 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	/* Find IP, SP and possibly regs: */
 	switch (orc->type) {
-	case ORC_TYPE_CALL:
+	case UNWIND_HINT_TYPE_CALL:
 		ip_p = sp - sizeof(long);
 
 		if (!deref_stack_reg(state, ip_p, &state->ip))
@@ -546,7 +547,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		state->signal = false;
 		break;
 
-	case ORC_TYPE_REGS:
+	case UNWIND_HINT_TYPE_REGS:
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn_current("can't access registers at %pB\n",
 					 (void *)orig_ip);
@@ -559,7 +560,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		state->signal = true;
 		break;
 
-	case ORC_TYPE_REGS_IRET:
+	case UNWIND_HINT_TYPE_REGS_PARTIAL:
 		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn_current("can't access iret registers at %pB\n",
 					 (void *)orig_ip);

arch/x86/kvm/svm/svm.c

@@ -19,7 +19,7 @@
 #include <linux/trace_events.h>
 #include <linux/slab.h>
 #include <linux/hashtable.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/psp-sev.h>
 #include <linux/file.h>
 #include <linux/pagemap.h>

arch/x86/kvm/vmx/nested.c

 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/percpu.h>
 
 #include <asm/debugreg.h>

arch/x86/kvm/vmx/vmx.c

@@ -13,7 +13,6 @@
  *   Yaniv Kamay  <yaniv@qumranet.com>
  */
 
-#include <linux/frame.h>
 #include <linux/highmem.h>
 #include <linux/hrtimer.h>
 #include <linux/kernel.h>
@@ -22,6 +21,7 @@
 #include <linux/moduleparam.h>
 #include <linux/mod_devicetable.h>
 #include <linux/mm.h>
+#include <linux/objtool.h>
 #include <linux/sched.h>
 #include <linux/sched/smt.h>
 #include <linux/slab.h>

arch/x86/xen/enlighten_pv.c

@@ -32,7 +32,7 @@
 #include <linux/pci.h>
 #include <linux/gfp.h>
 #include <linux/edd.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 
 #include <xen/xen.h>
 #include <xen/events.h>

drivers/gpu/drm/vmwgfx/vmwgfx_msg.c

@@ -24,7 +24,7 @@
  *
  */
 
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -599,4 +599,3 @@ int vmw_msg_ioctl(struct drm_device *dev, void *data,
 
 	return -EINVAL;
 }
-

include/linux/frame.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_FRAME_H
-#define _LINUX_FRAME_H
-
-#ifdef CONFIG_STACK_VALIDATION
-/*
- * This macro marks the given function's stack frame as "non-standard", which
- * tells objtool to ignore the function when doing stack metadata validation.
- * It should only be used in special cases where you're 100% sure it won't
- * affect the reliability of frame pointers and kernel stack traces.
- *
- * For more information, see tools/objtool/Documentation/stack-validation.txt.
- */
-#define STACK_FRAME_NON_STANDARD(func) \
-	static void __used __section(.discard.func_stack_frame_non_standard) \
-		*__func_stack_frame_non_standard_##func = func
-
-/*
- * This macro indicates that the following intra-function call is valid.
- * Any non-annotated intra-function call will cause objtool to issue a warning.
- */
-#define ANNOTATE_INTRA_FUNCTION_CALL				\
-	999:							\
-	.pushsection .discard.intra_function_calls;		\
-	.long 999b;						\
-	.popsection;
-
-#else /* !CONFIG_STACK_VALIDATION */
-
-#define STACK_FRAME_NON_STANDARD(func)
-#define ANNOTATE_INTRA_FUNCTION_CALL
-
-#endif /* CONFIG_STACK_VALIDATION */
-
-#endif /* _LINUX_FRAME_H */

include/linux/objtool.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_OBJTOOL_H
+#define _LINUX_OBJTOOL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * This struct is used by asm and inline asm code to manually annotate the
+ * location of registers on the stack.
+ */
+struct unwind_hint {
+	u32		ip;
+	s16		sp_offset;
+	u8		sp_reg;
+	u8		type;
+	u8		end;
+};
+#endif
+
+/*
+ * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP
+ * (the caller's SP right before it made the call).  Used for all callable
+ * functions, i.e. all C code and all callable asm functions.
+ *
+ * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset
+ * points to a fully populated pt_regs from a syscall, interrupt, or exception.
+ *
+ * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that
+ * sp_reg+sp_offset points to the iret return frame.
+ */
+#define UNWIND_HINT_TYPE_CALL		0
+#define UNWIND_HINT_TYPE_REGS		1
+#define UNWIND_HINT_TYPE_REGS_PARTIAL	2
+#define UNWIND_HINT_TYPE_RET_OFFSET	3
+
+#ifdef CONFIG_STACK_VALIDATION
+
+#ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
+	"987: \n\t"						\
+	".pushsection .discard.unwind_hints\n\t"		\
+	/* struct unwind_hint */				\
+	".long 987b - .\n\t"					\
+	".short " __stringify(sp_offset) "\n\t"			\
+	".byte " __stringify(sp_reg) "\n\t"			\
+	".byte " __stringify(type) "\n\t"			\
+	".byte " __stringify(end) "\n\t"			\
+	".balign 4 \n\t"					\
+	".popsection\n\t"
+
+/*
+ * This macro marks the given function's stack frame as "non-standard", which
+ * tells objtool to ignore the function when doing stack metadata validation.
+ * It should only be used in special cases where you're 100% sure it won't
+ * affect the reliability of frame pointers and kernel stack traces.
+ *
+ * For more information, see tools/objtool/Documentation/stack-validation.txt.
+ */
+#define STACK_FRAME_NON_STANDARD(func) \
+	static void __used __section(.discard.func_stack_frame_non_standard) \
+		*__func_stack_frame_non_standard_##func = func
+
+#else /* __ASSEMBLY__ */
+
+/*
+ * This macro indicates that the following intra-function call is valid.
+ * Any non-annotated intra-function call will cause objtool to issue a warning.
+ */
+#define ANNOTATE_INTRA_FUNCTION_CALL				\
+	999:							\
+	.pushsection .discard.intra_function_calls;		\
+	.long 999b;						\
+	.popsection;
+
+/*
+ * In asm, there are two kinds of code: normal C-type callable functions and
+ * the rest.  The normal callable functions can be called by other code, and
+ * don't do anything unusual with the stack.  Such normal callable functions
+ * are annotated with the ENTRY/ENDPROC macros.  Most asm code falls in this
+ * category.  In this case, no special debugging annotations are needed because
+ * objtool can automatically generate the ORC data for the ORC unwinder to read
+ * at runtime.
+ *
+ * Anything which doesn't fall into the above category, such as syscall and
+ * interrupt handlers, tends to not be called directly by other functions, and
+ * often does unusual non-C-function-type things with the stack pointer.  Such
+ * code needs to be annotated such that objtool can understand it.  The
+ * following CFI hint macros are for this type of code.
+ *
+ * These macros provide hints to objtool about the state of the stack at each
+ * instruction.  Objtool starts from the hints and follows the code flow,
+ * making automatic CFI adjustments when it sees pushes and pops, filling out
+ * the debuginfo as necessary.  It will also warn if it sees any
+ * inconsistencies.
+ */
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.Lunwind_hint_ip_\@:
+	.pushsection .discard.unwind_hints
+		/* struct unwind_hint */
+		.long .Lunwind_hint_ip_\@ - .
+		.short \sp_offset
+		.byte \sp_reg
+		.byte \type
+		.byte \end
+		.balign 4
+	.popsection
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#else /* !CONFIG_STACK_VALIDATION */
+
+#ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)	\
+	"\n\t"
+#define STACK_FRAME_NON_STANDARD(func)
+#else
+#define ANNOTATE_INTRA_FUNCTION_CALL
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.endm
+#endif
+
+#endif /* CONFIG_STACK_VALIDATION */
+
+#endif /* _LINUX_OBJTOOL_H */

kernel/bpf/core.c

@@ -25,7 +25,7 @@
 #include <linux/moduleloader.h>
 #include <linux/bpf.h>
 #include <linux/btf.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 #include <linux/rbtree_latch.h>
 #include <linux/kallsyms.h>
 #include <linux/rcupdate.h>

kernel/kexec_core.c

@@ -36,7 +36,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/compiler.h>
 #include <linux/hugetlb.h>
-#include <linux/frame.h>
+#include <linux/objtool.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>

tools/arch/x86/include/asm/orc_types.h

@@ -39,27 +39,6 @@
 #define ORC_REG_SP_INDIRECT		9
 #define ORC_REG_MAX			15
 
-/*
- * ORC_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP (the
- * caller's SP right before it made the call).  Used for all callable
- * functions, i.e. all C code and all callable asm functions.
- *
- * ORC_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset points
- * to a fully populated pt_regs from a syscall, interrupt, or exception.
- *
- * ORC_TYPE_REGS_IRET: Used in entry code to indicate that sp_reg+sp_offset
- * points to the iret return frame.
- *
- * The UNWIND_HINT macros are used only for the unwind_hint struct.  They
- * aren't used in struct orc_entry due to size and complexity constraints.
- * Objtool converts them to real types when it converts the hints to orc
- * entries.
- */
-#define ORC_TYPE_CALL			0
-#define ORC_TYPE_REGS			1
-#define ORC_TYPE_REGS_IRET		2
-#define UNWIND_HINT_TYPE_RET_OFFSET	3
-
 #ifndef __ASSEMBLY__
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
@@ -78,19 +57,6 @@ struct orc_entry {
 	unsigned	end:1;
 } __packed;
 
-/*
- * This struct is used by asm and inline asm code to manually annotate the
- * location of registers on the stack for the ORC unwinder.
- *
- * Type can be either ORC_TYPE_* or UNWIND_HINT_TYPE_*.
- */
-struct unwind_hint {
-	u32		ip;
-	s16		sp_offset;
-	u8		sp_reg;
-	u8		type;
-	u8		end;
-};
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ORC_TYPES_H */

tools/include/linux/objtool.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_OBJTOOL_H
+#define _LINUX_OBJTOOL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * This struct is used by asm and inline asm code to manually annotate the
+ * location of registers on the stack.
+ */
+struct unwind_hint {
+	u32		ip;
+	s16		sp_offset;
+	u8		sp_reg;
+	u8		type;
+	u8		end;
+};
+#endif
+
+/*
+ * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP
+ * (the caller's SP right before it made the call).  Used for all callable
+ * functions, i.e. all C code and all callable asm functions.
+ *
+ * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset
+ * points to a fully populated pt_regs from a syscall, interrupt, or exception.
+ *
+ * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that
+ * sp_reg+sp_offset points to the iret return frame.
+ */
+#define UNWIND_HINT_TYPE_CALL		0
+#define UNWIND_HINT_TYPE_REGS		1
+#define UNWIND_HINT_TYPE_REGS_PARTIAL	2
+#define UNWIND_HINT_TYPE_RET_OFFSET	3
+
+#ifdef CONFIG_STACK_VALIDATION
+
+#ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
+	"987: \n\t"						\
+	".pushsection .discard.unwind_hints\n\t"		\
+	/* struct unwind_hint */				\
+	".long 987b - .\n\t"					\
+	".short " __stringify(sp_offset) "\n\t"			\
+	".byte " __stringify(sp_reg) "\n\t"			\
+	".byte " __stringify(type) "\n\t"			\
+	".byte " __stringify(end) "\n\t"			\
+	".balign 4 \n\t"					\
+	".popsection\n\t"
+
+/*
+ * This macro marks the given function's stack frame as "non-standard", which
+ * tells objtool to ignore the function when doing stack metadata validation.
+ * It should only be used in special cases where you're 100% sure it won't
+ * affect the reliability of frame pointers and kernel stack traces.
+ *
+ * For more information, see tools/objtool/Documentation/stack-validation.txt.
+ */
+#define STACK_FRAME_NON_STANDARD(func) \
+	static void __used __section(.discard.func_stack_frame_non_standard) \
+		*__func_stack_frame_non_standard_##func = func
+
+#else /* __ASSEMBLY__ */
+
+/*
+ * This macro indicates that the following intra-function call is valid.
+ * Any non-annotated intra-function call will cause objtool to issue a warning.
+ */
+#define ANNOTATE_INTRA_FUNCTION_CALL				\
+	999:							\
+	.pushsection .discard.intra_function_calls;		\
+	.long 999b;						\
+	.popsection;
+
+/*
+ * In asm, there are two kinds of code: normal C-type callable functions and
+ * the rest.  The normal callable functions can be called by other code, and
+ * don't do anything unusual with the stack.  Such normal callable functions
+ * are annotated with the ENTRY/ENDPROC macros.  Most asm code falls in this
+ * category.  In this case, no special debugging annotations are needed because
+ * objtool can automatically generate the ORC data for the ORC unwinder to read
+ * at runtime.
+ *
+ * Anything which doesn't fall into the above category, such as syscall and
+ * interrupt handlers, tends to not be called directly by other functions, and
+ * often does unusual non-C-function-type things with the stack pointer.  Such
+ * code needs to be annotated such that objtool can understand it.  The
+ * following CFI hint macros are for this type of code.
+ *
+ * These macros provide hints to objtool about the state of the stack at each
+ * instruction.  Objtool starts from the hints and follows the code flow,
+ * making automatic CFI adjustments when it sees pushes and pops, filling out
+ * the debuginfo as necessary.  It will also warn if it sees any
+ * inconsistencies.
+ */
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.Lunwind_hint_ip_\@:
+	.pushsection .discard.unwind_hints
+		/* struct unwind_hint */
+		.long .Lunwind_hint_ip_\@ - .
+		.short \sp_offset
+		.byte \sp_reg
+		.byte \type
+		.byte \end
+		.balign 4
+	.popsection
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#else /* !CONFIG_STACK_VALIDATION */
+
+#ifndef __ASSEMBLY__
+
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)	\
+	"\n\t"
+#define STACK_FRAME_NON_STANDARD(func)
+#else
+#define ANNOTATE_INTRA_FUNCTION_CALL
+.macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0
+.endm
+#endif
+
+#endif /* CONFIG_STACK_VALIDATION */
+
+#endif /* _LINUX_OBJTOOL_H */

tools/objtool/Makefile

@@ -37,7 +37,7 @@ INCLUDES := -I$(srctree)/tools/include \
 	    -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
 	    -I$(srctree)/tools/arch/$(SRCARCH)/include	\
 	    -I$(srctree)/tools/objtool/arch/$(SRCARCH)/include
-WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
+WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed -Wno-nested-externs
 CFLAGS   := -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS)
 LDFLAGS  += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
 
@@ -55,6 +55,10 @@ ifeq ($(SRCARCH),x86)
 	SUBCMD_ORC := y
 endif
 
+ifeq ($(SUBCMD_ORC),y)
+	CFLAGS += -DINSN_USE_ORC
+endif
+
 export SUBCMD_CHECK SUBCMD_ORC
 export srctree OUTPUT CFLAGS SRCARCH AWK
 include $(srctree)/tools/build/Makefile.include

tools/objtool/arch.h

@@ -11,7 +11,9 @@
 #include "objtool.h"
 #include "cfi.h"
 
+#ifdef INSN_USE_ORC
 #include <asm/orc_types.h>
+#endif
 
 enum insn_type {
 	INSN_JUMP_CONDITIONAL,
@@ -86,4 +88,6 @@ unsigned long arch_dest_reloc_offset(int addend);
 
 const char *arch_nop_insn(int len);
 
+int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg);
+
 #endif /* _ARCH_H */

tools/objtool/arch/x86/Build

+objtool-y += special.o
 objtool-y += decode.o
 
 inat_tables_script = ../arch/x86/tools/gen-insn-attr-x86.awk

tools/objtool/arch/x86/decode.c

@@ -15,6 +15,7 @@
 #include "../../elf.h"
 #include "../../arch.h"
 #include "../../warn.h"
+#include <asm/orc_types.h>
 
 static unsigned char op_to_cfi_reg[][2] = {
 	{CFI_AX, CFI_R8},
@@ -583,3 +584,39 @@ const char *arch_nop_insn(int len)
 
 	return nops[len-1];
 }
+
+int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg)
+{
+	struct cfi_reg *cfa = &insn->cfi.cfa;
+
+	switch (sp_reg) {
+	case ORC_REG_UNDEFINED:
+		cfa->base = CFI_UNDEFINED;
+		break;
+	case ORC_REG_SP:
+		cfa->base = CFI_SP;
+		break;
+	case ORC_REG_BP:
+		cfa->base = CFI_BP;
+		break;
+	case ORC_REG_SP_INDIRECT:
+		cfa->base = CFI_SP_INDIRECT;
+		break;
+	case ORC_REG_R10:
+		cfa->base = CFI_R10;
+		break;
+	case ORC_REG_R13:
+		cfa->base = CFI_R13;
+		break;
+	case ORC_REG_DI:
+		cfa->base = CFI_DI;
+		break;
+	case ORC_REG_DX:
+		cfa->base = CFI_DX;
+		break;
+	default:
+		return -1;
+	}
+
+	return 0;
+}

tools/objtool/arch/x86/include/arch_special.h

+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _X86_ARCH_SPECIAL_H
+#define _X86_ARCH_SPECIAL_H
+
+#define EX_ENTRY_SIZE		12
+#define EX_ORIG_OFFSET		0
+#define EX_NEW_OFFSET		4
+
+#define JUMP_ENTRY_SIZE		16
+#define JUMP_ORIG_OFFSET	0
+#define JUMP_NEW_OFFSET		4
+
+#define ALT_ENTRY_SIZE		13
+#define ALT_ORIG_OFFSET		0
+#define ALT_NEW_OFFSET		4
+#define ALT_FEATURE_OFFSET	8
+#define ALT_ORIG_LEN_OFFSET	10
+#define ALT_NEW_LEN_OFFSET	11
+
+#endif /* _X86_ARCH_SPECIAL_H */

tools/objtool/arch/x86/special.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <string.h>
+
+#include "../../special.h"
+#include "../../builtin.h"
+
+#define X86_FEATURE_POPCNT (4 * 32 + 23)
+#define X86_FEATURE_SMAP   (9 * 32 + 20)
+
+void arch_handle_alternative(unsigned short feature, struct special_alt *alt)
+{
+	switch (feature) {
+	case X86_FEATURE_SMAP:
+		/*
+		 * If UACCESS validation is enabled; force that alternative;
+		 * otherwise force it the other way.
+		 *
+		 * What we want to avoid is having both the original and the
+		 * alternative code flow at the same time, in that case we can
+		 * find paths that see the STAC but take the NOP instead of
+		 * CLAC and the other way around.
+		 */
+		if (uaccess)
+			alt->skip_orig = true;
+		else
+			alt->skip_alt = true;
+		break;
+	case X86_FEATURE_POPCNT:
+		/*
+		 * It has been requested that we don't validate the !POPCNT
+		 * feature path which is a "very very small percentage of
+		 * machines".
+		 */
+		alt->skip_orig = true;
+		break;
+	default:
+		break;
+	}
+}
+
+bool arch_support_alt_relocation(struct special_alt *special_alt,
+				 struct instruction *insn,
+				 struct reloc *reloc)
+{
+	/*
+	 * The x86 alternatives code adjusts the offsets only when it
+	 * encounters a branch instruction at the very beginning of the
+	 * replacement group.
+	 */
+	return insn->offset == special_alt->new_off &&
+	       (insn->type == INSN_CALL || is_static_jump(insn));
+}
+
+/*
+ * There are 3 basic jump table patterns:
+ *
+ * 1. jmpq *[rodata addr](,%reg,8)
+ *
+ *    This is the most common case by far.  It jumps to an address in a simple
+ *    jump table which is stored in .rodata.
+ *
+ * 2. jmpq *[rodata addr](%rip)
+ *
+ *    This is caused by a rare GCC quirk, currently only seen in three driver
+ *    functions in the kernel, only with certain obscure non-distro configs.
+ *
+ *    As part of an optimization, GCC makes a copy of an existing switch jump
+ *    table, modifies it, and then hard-codes the jump (albeit with an indirect
+ *    jump) to use a single entry in the table.  The rest of the jump table and
+ *    some of its jump targets remain as dead code.
+ *
+ *    In such a case we can just crudely ignore all unreachable instruction
+ *    warnings for the entire object file.  Ideally we would just ignore them
+ *    for the function, but that would require redesigning the code quite a
+ *    bit.  And honestly that's just not worth doing: unreachable instruction
+ *    warnings are of questionable value anyway, and this is such a rare issue.
+ *
+ * 3. mov [rodata addr],%reg1
+ *    ... some instructions ...
+ *    jmpq *(%reg1,%reg2,8)
+ *
+ *    This is a fairly uncommon pattern which is new for GCC 6.  As of this
+ *    writing, there are 11 occurrences of it in the allmodconfig kernel.
+ *
+ *    As of GCC 7 there are quite a few more of these and the 'in between' code
+ *    is significant. Esp. with KASAN enabled some of the code between the mov
+ *    and jmpq uses .rodata itself, which can confuse things.
+ *
+ *    TODO: Once we have DWARF CFI and smarter instruction decoding logic,
+ *    ensure the same register is used in the mov and jump instructions.
+ *
+ *    NOTE: RETPOLINE made it harder still to decode dynamic jumps.
+ */
+struct reloc *arch_find_switch_table(struct objtool_file *file,
+				    struct instruction *insn)
+{
+	struct reloc  *text_reloc, *rodata_reloc;
+	struct section *table_sec;
+	unsigned long table_offset;
+
+	/* look for a relocation which references .rodata */
+	text_reloc = find_reloc_by_dest_range(file->elf, insn->sec,
+					      insn->offset, insn->len);
+	if (!text_reloc || text_reloc->sym->type != STT_SECTION ||
+	    !text_reloc->sym->sec->rodata)
+		return NULL;
+
+	table_offset = text_reloc->addend;
+	table_sec = text_reloc->sym->sec;
+
+	if (text_reloc->type == R_X86_64_PC32)
+		table_offset += 4;
+
+	/*
+	 * Make sure the .rodata address isn't associated with a
+	 * symbol.  GCC jump tables are anonymous data.
+	 *
+	 * Also support C jump tables which are in the same format as
+	 * switch jump tables.  For objtool to recognize them, they
+	 * need to be placed in the C_JUMP_TABLE_SECTION section.  They
+	 * have symbols associated with them.
+	 */
+	if (find_symbol_containing(table_sec, table_offset) &&
+	    strcmp(table_sec->name, C_JUMP_TABLE_SECTION))
+		return NULL;
+
+	/*
+	 * Each table entry has a rela associated with it.  The rela
+	 * should reference text in the same function as the original
+	 * instruction.
+	 */
+	rodata_reloc = find_reloc_by_dest(file->elf, table_sec, table_offset);
+	if (!rodata_reloc)
+		return NULL;
+
+	/*
+	 * Use of RIP-relative switch jumps is quite rare, and
+	 * indicates a rare GCC quirk/bug which can leave dead
+	 * code behind.
+	 */
+	if (text_reloc->type == R_X86_64_PC32)
+		file->ignore_unreachables = true;
+
+	return rodata_reloc;
+}

tools/objtool/builtin-check.c

@@ -41,6 +41,8 @@ const struct option check_options[] = {
 int cmd_check(int argc, const char **argv)
 {
 	const char *objname, *s;
+	struct objtool_file *file;
+	int ret;
 
 	argc = parse_options(argc, argv, check_options, check_usage, 0);
 
@@ -53,5 +55,16 @@ int cmd_check(int argc, const char **argv)
 	if (s && !s[9])
 		vmlinux = true;
 
-	return check(objname, false);
+	file = objtool_open_read(objname);
+	if (!file)
+		return 1;
+
+	ret = check(file);
+	if (ret)
+		return ret;
+
+	if (file->elf->changed)
+		return elf_write(file->elf);
+
+	return 0;
 }

tools/objtool/builtin-orc.c

@@ -31,13 +31,38 @@ int cmd_orc(int argc, const char **argv)
 		usage_with_options(orc_usage, check_options);
 
 	if (!strncmp(argv[0], "gen", 3)) {
+		struct objtool_file *file;
+		int ret;
+
 		argc = parse_options(argc, argv, check_options, orc_usage, 0);
 		if (argc != 1)
 			usage_with_options(orc_usage, check_options);
 
 		objname = argv[0];
 
-		return check(objname, true);
+		file = objtool_open_read(objname);
+		if (!file)
+			return 1;
+
+		ret = check(file);
+		if (ret)
+			return ret;
+
+		if (list_empty(&file->insn_list))
+			return 0;
+
+		ret = create_orc(file);
+		if (ret)
+			return ret;
+
+		ret = create_orc_sections(file);
+		if (ret)
+			return ret;
+
+		if (!file->elf->changed)
+			return 0;
+
+		return elf_write(file->elf);
 	}
 
 	if (!strcmp(argv[0], "dump")) {

tools/objtool/check.c

@@ -14,21 +14,19 @@
 #include "warn.h"
 #include "arch_elf.h"
 
+#include <linux/objtool.h>
 #include <linux/hashtable.h>
 #include <linux/kernel.h>
 #include <linux/static_call_types.h>
 
 #define FAKE_JUMP_OFFSET -1
 
-#define C_JUMP_TABLE_SECTION ".rodata..c_jump_table"
-
 struct alternative {
 	struct list_head list;
 	struct instruction *insn;
 	bool skip_orig;
 };
 
-const char *objname;
 struct cfi_init_state initial_func_cfi;
 
 struct instruction *find_insn(struct objtool_file *file,
@@ -111,12 +109,6 @@ static struct instruction *prev_insn_same_sym(struct objtool_file *file,
 	for (insn = next_insn_same_sec(file, insn); insn;		\
 	     insn = next_insn_same_sec(file, insn))
 
-static bool is_static_jump(struct instruction *insn)
-{
-	return insn->type == INSN_JUMP_CONDITIONAL ||
-	       insn->type == INSN_JUMP_UNCONDITIONAL;
-}
-
 static bool is_sibling_call(struct instruction *insn)
 {
 	/* An indirect jump is either a sibling call or a jump to a table. */
@@ -591,6 +583,8 @@ static const char *uaccess_safe_builtin[] = {
 	"__asan_store4_noabort",
 	"__asan_store8_noabort",
 	"__asan_store16_noabort",
+	"__kasan_check_read",
+	"__kasan_check_write",
 	/* KASAN in-line */
 	"__asan_report_load_n_noabort",
 	"__asan_report_load1_noabort",
@@ -879,6 +873,17 @@ static void remove_insn_ops(struct instruction *insn)
 	}
 }
 
+static struct symbol *find_call_destination(struct section *sec, unsigned long offset)
+{
+	struct symbol *call_dest;
+
+	call_dest = find_func_by_offset(sec, offset);
+	if (!call_dest)
+		call_dest = find_symbol_by_offset(sec, offset);
+
+	return call_dest;
+}
+
 /*
  * Find the destination instructions for all calls.
  */
@@ -896,9 +901,7 @@ static int add_call_destinations(struct objtool_file *file)
 					       insn->offset, insn->len);
 		if (!reloc) {
 			dest_off = arch_jump_destination(insn);
-			insn->call_dest = find_func_by_offset(insn->sec, dest_off);
-			if (!insn->call_dest)
-				insn->call_dest = find_symbol_by_offset(insn->sec, dest_off);
+			insn->call_dest = find_call_destination(insn->sec, dest_off);
 
 			if (insn->ignore)
 				continue;
@@ -916,7 +919,7 @@ static int add_call_destinations(struct objtool_file *file)
 
 		} else if (reloc->sym->type == STT_SECTION) {
 			dest_off = arch_dest_reloc_offset(reloc->addend);
-			insn->call_dest = find_func_by_offset(reloc->sym->sec,
+			insn->call_dest = find_call_destination(reloc->sym->sec,
 								dest_off);
 			if (!insn->call_dest) {
 				WARN_FUNC("can't find call dest symbol at %s+0x%lx",
@@ -1029,6 +1032,8 @@ static int handle_group_alt(struct objtool_file *file,
 	alt_group = alt_group_next_index++;
 	insn = *new_insn;
 	sec_for_each_insn_from(file, insn) {
+		struct reloc *alt_reloc;
+
 		if (insn->offset >= special_alt->new_off + special_alt->new_len)
 			break;
 
@@ -1045,14 +1050,11 @@ static int handle_group_alt(struct objtool_file *file,
 		 * .altinstr_replacement section, unless the arch's
 		 * alternatives code can adjust the relative offsets
 		 * accordingly.
-		 *
-		 * The x86 alternatives code adjusts the offsets only when it
-		 * encounters a branch instruction at the very beginning of the
-		 * replacement group.
 		 */
-		if ((insn->offset != special_alt->new_off ||
-		    (insn->type != INSN_CALL && !is_static_jump(insn))) &&
-		    find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len)) {
+		alt_reloc = find_reloc_by_dest_range(file->elf, insn->sec,
+						   insn->offset, insn->len);
+		if (alt_reloc &&
+		    !arch_support_alt_relocation(special_alt, insn, alt_reloc)) {
 
 			WARN_FUNC("unsupported relocation in alternatives section",
 				  insn->sec, insn->offset);
@@ -1254,56 +1256,15 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn,
 }
 
 /*
- * find_jump_table() - Given a dynamic jump, find the switch jump table in
- * .rodata associated with it.
- *
- * There are 3 basic patterns:
- *
- * 1. jmpq *[rodata addr](,%reg,8)
- *
- *    This is the most common case by far.  It jumps to an address in a simple
- *    jump table which is stored in .rodata.
- *
- * 2. jmpq *[rodata addr](%rip)
- *
- *    This is caused by a rare GCC quirk, currently only seen in three driver
- *    functions in the kernel, only with certain obscure non-distro configs.
- *
- *    As part of an optimization, GCC makes a copy of an existing switch jump
- *    table, modifies it, and then hard-codes the jump (albeit with an indirect
- *    jump) to use a single entry in the table.  The rest of the jump table and
- *    some of its jump targets remain as dead code.
- *
- *    In such a case we can just crudely ignore all unreachable instruction
- *    warnings for the entire object file.  Ideally we would just ignore them
- *    for the function, but that would require redesigning the code quite a
- *    bit.  And honestly that's just not worth doing: unreachable instruction
- *    warnings are of questionable value anyway, and this is such a rare issue.
- *
- * 3. mov [rodata addr],%reg1
- *    ... some instructions ...
- *    jmpq *(%reg1,%reg2,8)
- *
- *    This is a fairly uncommon pattern which is new for GCC 6.  As of this
- *    writing, there are 11 occurrences of it in the allmodconfig kernel.
- *
- *    As of GCC 7 there are quite a few more of these and the 'in between' code
- *    is significant. Esp. with KASAN enabled some of the code between the mov
- *    and jmpq uses .rodata itself, which can confuse things.
- *
- *    TODO: Once we have DWARF CFI and smarter instruction decoding logic,
- *    ensure the same register is used in the mov and jump instructions.
- *
- *    NOTE: RETPOLINE made it harder still to decode dynamic jumps.
+ * find_jump_table() - Given a dynamic jump, find the switch jump table
+ * associated with it.
  */
 static struct reloc *find_jump_table(struct objtool_file *file,
 				      struct symbol *func,
 				      struct instruction *insn)
 {
-	struct reloc *text_reloc, *table_reloc;
+	struct reloc *table_reloc;
 	struct instruction *dest_insn, *orig_insn = insn;
-	struct section *table_sec;
-	unsigned long table_offset;
 
 	/*
 	 * Backward search using the @first_jump_src links, these help avoid
@@ -1324,52 +1285,13 @@ static struct reloc *find_jump_table(struct objtool_file *file,
 		     insn->jump_dest->offset > orig_insn->offset))
 		    break;
 
-		/* look for a relocation which references .rodata */
-		text_reloc = find_reloc_by_dest_range(file->elf, insn->sec,
-						    insn->offset, insn->len);
-		if (!text_reloc || text_reloc->sym->type != STT_SECTION ||
-		    !text_reloc->sym->sec->rodata)
-			continue;
-
-		table_offset = text_reloc->addend;
-		table_sec = text_reloc->sym->sec;
-
-		if (text_reloc->type == R_X86_64_PC32)
-			table_offset += 4;
-
-		/*
-		 * Make sure the .rodata address isn't associated with a
-		 * symbol.  GCC jump tables are anonymous data.
-		 *
-		 * Also support C jump tables which are in the same format as
-		 * switch jump tables.  For objtool to recognize them, they
-		 * need to be placed in the C_JUMP_TABLE_SECTION section.  They
-		 * have symbols associated with them.
-		 */
-		if (find_symbol_containing(table_sec, table_offset) &&
-		    strcmp(table_sec->name, C_JUMP_TABLE_SECTION))
-			continue;
-
-		/*
-		 * Each table entry has a reloc associated with it.  The reloc
-		 * should reference text in the same function as the original
-		 * instruction.
-		 */
-		table_reloc = find_reloc_by_dest(file->elf, table_sec, table_offset);
+		table_reloc = arch_find_switch_table(file, insn);
 		if (!table_reloc)
 			continue;
 		dest_insn = find_insn(file, table_reloc->sym->sec, table_reloc->addend);
 		if (!dest_insn || !dest_insn->func || dest_insn->func->pfunc != func)
 			continue;
 
-		/*
-		 * Use of RIP-relative switch jumps is quite rare, and
-		 * indicates a rare GCC quirk/bug which can leave dead code
-		 * behind.
-		 */
-		if (text_reloc->type == R_X86_64_PC32)
-			file->ignore_unreachables = true;
-
 		return table_reloc;
 	}
 
@@ -1512,32 +1434,7 @@ static int read_unwind_hints(struct objtool_file *file)
 
 		insn->hint = true;
 
-		switch (hint->sp_reg) {
-		case ORC_REG_UNDEFINED:
-			cfa->base = CFI_UNDEFINED;
-			break;
-		case ORC_REG_SP:
-			cfa->base = CFI_SP;
-			break;
-		case ORC_REG_BP:
-			cfa->base = CFI_BP;
-			break;
-		case ORC_REG_SP_INDIRECT:
-			cfa->base = CFI_SP_INDIRECT;
-			break;
-		case ORC_REG_R10:
-			cfa->base = CFI_R10;
-			break;
-		case ORC_REG_R13:
-			cfa->base = CFI_R13;
-			break;
-		case ORC_REG_DI:
-			cfa->base = CFI_DI;
-			break;
-		case ORC_REG_DX:
-			cfa->base = CFI_DX;
-			break;
-		default:
+		if (arch_decode_hint_reg(insn, hint->sp_reg)) {
 			WARN_FUNC("unsupported unwind_hint sp base reg %d",
 				  insn->sec, insn->offset, hint->sp_reg);
 			return -1;
@@ -1951,7 +1848,8 @@ static int update_cfi_state(struct instruction *insn, struct cfi_state *cfi,
 		return 0;
 	}
 
-	if (cfi->type == ORC_TYPE_REGS || cfi->type == ORC_TYPE_REGS_IRET)
+	if (cfi->type == UNWIND_HINT_TYPE_REGS ||
+	    cfi->type == UNWIND_HINT_TYPE_REGS_PARTIAL)
 		return update_cfi_state_regs(insn, cfi, op);
 
 	switch (op->dest.type) {
@@ -2199,7 +2097,7 @@ static int update_cfi_state(struct instruction *insn, struct cfi_state *cfi,
 				/* drap: push %rbp */
 				cfi->stack_size = 0;
 
-			} else if (regs[op->src.reg].base == CFI_UNDEFINED) {
+			} else {
 
 				/* drap: push %reg */
 				save_reg(cfi, op->src.reg, CFI_BP, -cfi->stack_size);
@@ -2228,9 +2126,7 @@ static int update_cfi_state(struct instruction *insn, struct cfi_state *cfi,
 
 				/* save drap offset so we know when to restore it */
 				cfi->drap_offset = op->dest.offset;
-			}
-
-			else if (regs[op->src.reg].base == CFI_UNDEFINED) {
+			} else {
 
 				/* drap: mov reg, disp(%rbp) */
 				save_reg(cfi, op->src.reg, CFI_BP, op->dest.offset);
@@ -2800,9 +2696,10 @@ static bool is_ubsan_insn(struct instruction *insn)
 			"__ubsan_handle_builtin_unreachable"));
 }
 
-static bool ignore_unreachable_insn(struct instruction *insn)
+static bool ignore_unreachable_insn(struct objtool_file *file, struct instruction *insn)
 {
 	int i;
+	struct instruction *prev_insn;
 
 	if (insn->ignore || insn->type == INSN_NOP)
 		return true;
@@ -2819,6 +2716,9 @@ static bool ignore_unreachable_insn(struct instruction *insn)
 	    !strcmp(insn->sec->name, ".altinstr_aux"))
 		return true;
 
+	if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->offset == FAKE_JUMP_OFFSET)
+		return true;
+
 	if (!insn->func)
 		return false;
 
@@ -2827,8 +2727,11 @@ static bool ignore_unreachable_insn(struct instruction *insn)
 	 * __builtin_unreachable().  The BUG() macro has an unreachable() after
 	 * the UD2, which causes GCC's undefined trap logic to emit another UD2
 	 * (or occasionally a JMP to UD2).
+	 *
+	 * It may also insert a UD2 after calling a __noreturn function.
 	 */
-	if (list_prev_entry(insn, list)->dead_end &&
+	prev_insn = list_prev_entry(insn, list);
+	if ((prev_insn->dead_end || dead_end_function(file, prev_insn->call_dest)) &&
 	    (insn->type == INSN_BUG ||
 	     (insn->type == INSN_JUMP_UNCONDITIONAL &&
 	      insn->jump_dest && insn->jump_dest->type == INSN_BUG)))
@@ -2955,7 +2858,7 @@ static int validate_reachable_instructions(struct objtool_file *file)
 		return 0;
 
 	for_each_insn(file, insn) {
-		if (insn->visited || ignore_unreachable_insn(insn))
+		if (insn->visited || ignore_unreachable_insn(file, insn))
 			continue;
 
 		WARN_FUNC("unreachable instruction", insn->sec, insn->offset);
@@ -2965,37 +2868,22 @@ static int validate_reachable_instructions(struct objtool_file *file)
 	return 0;
 }
 
-static struct objtool_file file;
-
-int check(const char *_objname, bool orc)
+int check(struct objtool_file *file)
 {
 	int ret, warnings = 0;
 
-	objname = _objname;
-
-	file.elf = elf_open_read(objname, O_RDWR);
-	if (!file.elf)
-		return 1;
-
-	INIT_LIST_HEAD(&file.insn_list);
-	hash_init(file.insn_hash);
-	INIT_LIST_HEAD(&file.static_call_list);
-	file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment");
-	file.ignore_unreachables = no_unreachable;
-	file.hints = false;
-
 	arch_initial_func_cfi_state(&initial_func_cfi);
 
-	ret = decode_sections(&file);
+	ret = decode_sections(file);
 	if (ret < 0)
 		goto out;
 	warnings += ret;
 
-	if (list_empty(&file.insn_list))
+	if (list_empty(&file->insn_list))
 		goto out;
 
 	if (vmlinux && !validate_dup) {
-		ret = validate_vmlinux_functions(&file);
+		ret = validate_vmlinux_functions(file);
 		if (ret < 0)
 			goto out;
 
@@ -3004,50 +2892,34 @@ int check(const char *_objname, bool orc)
 	}
 
 	if (retpoline) {
-		ret = validate_retpoline(&file);
+		ret = validate_retpoline(file);
 		if (ret < 0)
 			return ret;
 		warnings += ret;
 	}
 
-	ret = validate_functions(&file);
+	ret = validate_functions(file);
 	if (ret < 0)
 		goto out;
 	warnings += ret;
 
-	ret = validate_unwind_hints(&file, NULL);
+	ret = validate_unwind_hints(file, NULL);
 	if (ret < 0)
 		goto out;
 	warnings += ret;
 
 	if (!warnings) {
-		ret = validate_reachable_instructions(&file);
+		ret = validate_reachable_instructions(file);
 		if (ret < 0)
 			goto out;
 		warnings += ret;
 	}
 
-	ret = create_static_call_sections(&file);
+	ret = create_static_call_sections(file);
 	if (ret < 0)
 		goto out;
 	warnings += ret;
 
-	if (orc) {
-		ret = create_orc(&file);
-		if (ret < 0)
-			goto out;
-
-		ret = create_orc_sections(&file);
-		if (ret < 0)
-			goto out;
-	}
-
-	if (file.elf->changed) {
-		ret = elf_write(file.elf);
-		if (ret < 0)
-			goto out;
-	}
-
 out:
 	if (ret < 0) {
 		/*

tools/objtool/check.h

@@ -43,9 +43,17 @@ struct instruction {
 	struct symbol *func;
 	struct list_head stack_ops;
 	struct cfi_state cfi;
+#ifdef INSN_USE_ORC
 	struct orc_entry orc;
+#endif
 };
 
+static inline bool is_static_jump(struct instruction *insn)
+{
+	return insn->type == INSN_JUMP_CONDITIONAL ||
+	       insn->type == INSN_JUMP_UNCONDITIONAL;
+}
+
 struct instruction *find_insn(struct objtool_file *file,
 			      struct section *sec, unsigned long offset);
 
@@ -58,5 +66,4 @@ struct instruction *find_insn(struct objtool_file *file,
 			insn->sec == sec;				\
 	     insn = list_next_entry(insn, list))
 
-
 #endif /* _CHECK_H */

tools/objtool/objtool.c

@@ -22,6 +22,8 @@
 #include <linux/kernel.h>
 
 #include "builtin.h"
+#include "objtool.h"
+#include "warn.h"
 
 struct cmd_struct {
 	const char *name;
@@ -39,6 +41,34 @@ static struct cmd_struct objtool_cmds[] = {
 
 bool help;
 
+const char *objname;
+static struct objtool_file file;
+
+struct objtool_file *objtool_open_read(const char *_objname)
+{
+	if (objname) {
+		if (strcmp(objname, _objname)) {
+			WARN("won't handle more than one file at a time");
+			return NULL;
+		}
+		return &file;
+	}
+	objname = _objname;
+
+	file.elf = elf_open_read(objname, O_RDWR);
+	if (!file.elf)
+		return NULL;
+
+	INIT_LIST_HEAD(&file.insn_list);
+	hash_init(file.insn_hash);
+	INIT_LIST_HEAD(&file.static_call_list);
+	file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment");
+	file.ignore_unreachables = no_unreachable;
+	file.hints = false;
+
+	return &file;
+}
+
 static void cmd_usage(void)
 {
 	unsigned int i, longest = 0;

tools/objtool/objtool.h

@@ -12,6 +12,8 @@
 
 #include "elf.h"
 
+#define __weak __attribute__((weak))
+
 struct objtool_file {
 	struct elf *elf;
 	struct list_head insn_list;
@@ -20,7 +22,9 @@ struct objtool_file {
 	bool ignore_unreachables, c_file, hints, rodata;
 };
 
-int check(const char *objname, bool orc);
+struct objtool_file *objtool_open_read(const char *_objname);
+
+int check(struct objtool_file *file);
 int orc_dump(const char *objname);
 int create_orc(struct objtool_file *file);
 int create_orc_sections(struct objtool_file *file);

tools/objtool/orc_dump.c

@@ -4,6 +4,7 @@
  */
 
 #include <unistd.h>
+#include <linux/objtool.h>
 #include <asm/orc_types.h>
 #include "objtool.h"
 #include "warn.h"
@@ -37,12 +38,12 @@ static const char *reg_name(unsigned int reg)
 static const char *orc_type_name(unsigned int type)
 {
 	switch (type) {
-	case ORC_TYPE_CALL:
+	case UNWIND_HINT_TYPE_CALL:
 		return "call";
-	case ORC_TYPE_REGS:
+	case UNWIND_HINT_TYPE_REGS:
 		return "regs";
-	case ORC_TYPE_REGS_IRET:
-		return "iret";
+	case UNWIND_HINT_TYPE_REGS_PARTIAL:
+		return "regs (partial)";
 	default:
 		return "?";
 	}

tools/objtool/orc_gen.c

@@ -6,6 +6,9 @@
 #include <stdlib.h>
 #include <string.h>
 
+#include <linux/objtool.h>
+#include <asm/orc_types.h>
+
 #include "check.h"
 #include "warn.h"
 
@@ -18,6 +21,9 @@ int create_orc(struct objtool_file *file)
 		struct cfi_reg *cfa = &insn->cfi.cfa;
 		struct cfi_reg *bp = &insn->cfi.regs[CFI_BP];
 
+		if (!insn->sec->text)
+			continue;
+
 		orc->end = insn->cfi.end;
 
 		if (cfa->base == CFI_UNDEFINED) {
@@ -143,7 +149,7 @@ int create_orc_sections(struct objtool_file *file)
 	struct orc_entry empty = {
 		.sp_reg = ORC_REG_UNDEFINED,
 		.bp_reg  = ORC_REG_UNDEFINED,
-		.type    = ORC_TYPE_CALL,
+		.type    = UNWIND_HINT_TYPE_CALL,
 	};
 
 	sec = find_section_by_name(file->elf, ".orc_unwind");

tools/objtool/special.c

@@ -14,24 +14,7 @@
 #include "builtin.h"
 #include "special.h"
 #include "warn.h"
-
-#define EX_ENTRY_SIZE		12
-#define EX_ORIG_OFFSET		0
-#define EX_NEW_OFFSET		4
-
-#define JUMP_ENTRY_SIZE		16
-#define JUMP_ORIG_OFFSET	0
-#define JUMP_NEW_OFFSET		4
-
-#define ALT_ENTRY_SIZE		13
-#define ALT_ORIG_OFFSET		0
-#define ALT_NEW_OFFSET		4
-#define ALT_FEATURE_OFFSET	8
-#define ALT_ORIG_LEN_OFFSET	10
-#define ALT_NEW_LEN_OFFSET	11
-
-#define X86_FEATURE_POPCNT (4*32+23)
-#define X86_FEATURE_SMAP   (9*32+20)
+#include "arch_special.h"
 
 struct special_entry {
 	const char *sec;
@@ -68,6 +51,10 @@ struct special_entry entries[] = {
 	{},
 };
 
+void __weak arch_handle_alternative(unsigned short feature, struct special_alt *alt)
+{
+}
+
 static int get_alt_entry(struct elf *elf, struct special_entry *entry,
 			 struct section *sec, int idx,
 			 struct special_alt *alt)
@@ -92,30 +79,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
 
 		feature = *(unsigned short *)(sec->data->d_buf + offset +
 					      entry->feature);
-
-		/*
-		 * It has been requested that we don't validate the !POPCNT
-		 * feature path which is a "very very small percentage of
-		 * machines".
-		 */
-		if (feature == X86_FEATURE_POPCNT)
-			alt->skip_orig = true;
-
-		/*
-		 * If UACCESS validation is enabled; force that alternative;
-		 * otherwise force it the other way.
-		 *
-		 * What we want to avoid is having both the original and the
-		 * alternative code flow at the same time, in that case we can
-		 * find paths that see the STAC but take the NOP instead of
-		 * CLAC and the other way around.
-		 */
-		if (feature == X86_FEATURE_SMAP) {
-			if (uaccess)
-				alt->skip_orig = true;
-			else
-				alt->skip_alt = true;
-		}
+		arch_handle_alternative(feature, alt);
 	}
 
 	orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig);

tools/objtool/special.h

@@ -7,8 +7,11 @@
 #define _SPECIAL_H
 
 #include <stdbool.h>
+#include "check.h"
 #include "elf.h"
 
+#define C_JUMP_TABLE_SECTION ".rodata..c_jump_table"
+
 struct special_alt {
 	struct list_head list;
 
@@ -28,4 +31,11 @@ struct special_alt {
 
 int special_get_alts(struct elf *elf, struct list_head *alts);
 
+void arch_handle_alternative(unsigned short feature, struct special_alt *alt);
+
+bool arch_support_alt_relocation(struct special_alt *special_alt,
+				 struct instruction *insn,
+				 struct reloc *reloc);
+struct reloc *arch_find_switch_table(struct objtool_file *file,
+				    struct instruction *insn);
 #endif /* _SPECIAL_H */

tools/objtool/sync-check.sh

 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
-FILES='
+if [ -z "$SRCARCH" ]; then
+	echo 'sync-check.sh: error: missing $SRCARCH environment variable' >&2
+	exit 1
+fi
+
+FILES="include/linux/objtool.h"
+
+if [ "$SRCARCH" = "x86" ]; then
+FILES="$FILES
 arch/x86/include/asm/inat_types.h
 arch/x86/include/asm/orc_types.h
 arch/x86/include/asm/emulate_prefix.h
 arch/x86/lib/x86-opcode-map.txt
 arch/x86/tools/gen-insn-attr-x86.awk
 include/linux/static_call_types.h
-'
+arch/x86/include/asm/inat.h     -I '^#include [\"<]\(asm/\)*inat_types.h[\">]'
+arch/x86/include/asm/insn.h     -I '^#include [\"<]\(asm/\)*inat.h[\">]'
+arch/x86/lib/inat.c             -I '^#include [\"<]\(../include/\)*asm/insn.h[\">]'
+arch/x86/lib/insn.c             -I '^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]' -I '^#include [\"<]\(../include/\)*asm/emulate_prefix.h[\">]'
+"
+fi
 
 check_2 () {
   file1=$1
@@ -41,11 +54,12 @@ fi
 
 cd ../..
 
-for i in $FILES; do
-  check $i
-done
+while read -r file_entry; do
+    if [ -z "$file_entry" ]; then
+	continue
+    fi
 
-check arch/x86/include/asm/inat.h     '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"'
-check arch/x86/include/asm/insn.h     '-I "^#include [\"<]\(asm/\)*inat.h[\">]"'
-check arch/x86/lib/inat.c             '-I "^#include [\"<]\(../include/\)*asm/insn.h[\">]"'
-check arch/x86/lib/insn.c             '-I "^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]" -I "^#include [\"<]\(../include/\)*asm/emulate_prefix.h[\">]"'
+    check $file_entry
+done <<EOF
+$FILES
+EOF

tools/objtool/weak.c

@@ -9,17 +9,13 @@
 #include <errno.h>
 #include "objtool.h"
 
-#define __weak __attribute__((weak))
-
 #define UNSUPPORTED(name)						\
 ({									\
 	fprintf(stderr, "error: objtool: " name " not implemented\n");	\
 	return ENOSYS;							\
 })
 
-const char __weak *objname;
-
-int __weak check(const char *_objname, bool orc)
+int __weak check(struct objtool_file *file)
 {
 	UNSUPPORTED("check subcommand");
 }

tools/perf/Makefile.config

@@ -16,7 +16,7 @@ $(shell printf "" > $(OUTPUT).config-detected)
 detected     = $(shell echo "$(1)=y"       >> $(OUTPUT).config-detected)
 detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
 
-CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
+CFLAGS := $(EXTRA_CFLAGS) $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))
 
 include $(srctree)/tools/scripts/Makefile.arch