Merge tag 'objtool-core-2025-12-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull objtool updates from Ingo Molnar:

 - klp-build livepatch module generation (Josh Poimboeuf)

   Introduce new objtool features and a klp-build script to generate
   livepatch modules using a source .patch as input.

   This builds on concepts from the longstanding out-of-tree kpatch
   project which began in 2012 and has been used for many years to
   generate livepatch modules for production kernels. However, this is a
   complete rewrite which incorporates hard-earned lessons from 12+
   years of maintaining kpatch.

   Key improvements compared to kpatch-build:

    - Integrated with objtool: Leverages objtool's existing control-flow
      graph analysis to help detect changed functions.

    - Works on vmlinux.o: Supports late-linked objects, making it
      compatible with LTO, IBT, and similar.

    - Simplified code base: ~3k fewer lines of code.

    - Upstream: No more out-of-tree #ifdef hacks, far less cruft.

    - Cleaner internals: Vastly simplified logic for
      symbol/section/reloc inclusion and special section extraction.

    - Robust __LINE__ macro handling: Avoids false positive binary diffs
      caused by the __LINE__ macro by introducing a fix-patch-lines
      script which injects #line directives into the source .patch to
      preserve the original line numbers at compile time.

 - Disassemble code with libopcodes instead of running objdump
   (Alexandre Chartre)

 - Disassemble support (-d option to objtool) by Alexandre Chartre,
   which supports the decoding of various Linux kernel code generation
   specials such as alternatives:

      17ef:  sched_balance_find_dst_group+0x62f                 mov    0x34(%r9),%edx
      17f3:  sched_balance_find_dst_group+0x633               | <alternative.17f3>             | X86_FEATURE_POPCNT
      17f3:  sched_balance_find_dst_group+0x633               | call   0x17f8 <__sw_hweight64> | popcnt %rdi,%rax
      17f8:  sched_balance_find_dst_group+0x638                 cmp    %eax,%edx

   ... jump table alternatives:

      1895:  sched_use_asym_prio+0x5                            test   $0x8,%ch
      1898:  sched_use_asym_prio+0x8                            je     0x18a9 <sched_use_asym_prio+0x19>
      189a:  sched_use_asym_prio+0xa                          | <jump_table.189a>                        | JUMP
      189a:  sched_use_asym_prio+0xa                          | jmp    0x18ae <sched_use_asym_prio+0x1e> | nop2
      189c:  sched_use_asym_prio+0xc                            mov    $0x1,%eax
      18a1:  sched_use_asym_prio+0x11                           and    $0x80,%ecx

   ... exception table alternatives:

    native_read_msr:
      5b80:  native_read_msr+0x0                                                     mov    %edi,%ecx
      5b82:  native_read_msr+0x2                                                   | <ex_table.5b82> | EXCEPTION
      5b82:  native_read_msr+0x2                                                   | rdmsr           | resume at 0x5b84 <native_read_msr+0x4>
      5b84:  native_read_msr+0x4                                                     shl    $0x20,%rdx

   .... x86 feature flag decoding (also see the X86_FEATURE_POPCNT
        example in sched_balance_find_dst_group() above):

      2faaf:  start_thread_common.constprop.0+0x1f                                    jne    0x2fba4 <start_thread_common.constprop.0+0x114>
      2fab5:  start_thread_common.constprop.0+0x25                                  | <alternative.2fab5>                  | X86_FEATURE_ALWAYS                                  | X86_BUG_NULL_SEG
      2fab5:  start_thread_common.constprop.0+0x25                                  | jmp    0x2faba <.altinstr_aux+0x2f4> | jmp    0x4b0 <start_thread_common.constprop.0+0x3f> | nop5
      2faba:  start_thread_common.constprop.0+0x2a                                    mov    $0x2b,%eax

   ... NOP sequence shortening:

      1048e2:  snapshot_write_finalize+0xc2                                            je     0x104917 <snapshot_write_finalize+0xf7>
      1048e4:  snapshot_write_finalize+0xc4                                            nop6
      1048ea:  snapshot_write_finalize+0xca                                            nop11
      1048f5:  snapshot_write_finalize+0xd5                                            nop11
      104900:  snapshot_write_finalize+0xe0                                            mov    %rax,%rcx
      104903:  snapshot_write_finalize+0xe3                                            mov    0x10(%rdx),%rax

   ... and much more.

 - Function validation tracing support (Alexandre Chartre)

 - Various -ffunction-sections fixes (Josh Poimboeuf)

 - Clang AutoFDO (Automated Feedback-Directed Optimizations) support
   (Josh Poimboeuf)

 - Misc fixes and cleanups (Borislav Petkov, Chen Ni, Dylan Hatch, Ingo
   Molnar, John Wang, Josh Poimboeuf, Pankaj Raghav, Peter Zijlstra,
   Thorsten Blum)

* tag 'objtool-core-2025-12-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (129 commits)
  objtool: Fix segfault on unknown alternatives
  objtool: Build with disassembly can fail when including bdf.h
  objtool: Trim trailing NOPs in alternative
  objtool: Add wide output for disassembly
  objtool: Compact output for alternatives with one instruction
  objtool: Improve naming of group alternatives
  objtool: Add Function to get the name of a CPU feature
  objtool: Provide access to feature and flags of group alternatives
  objtool: Fix address references in alternatives
  objtool: Disassemble jump table alternatives
  objtool: Disassemble exception table alternatives
  objtool: Print addresses with alternative instructions
  objtool: Disassemble group alternatives
  objtool: Print headers for alternatives
  objtool: Preserve alternatives order
  objtool: Add the --disas=<function-pattern> action
  objtool: Do not validate IBT for .return_sites and .call_sites
  objtool: Improve tracing of alternative instructions
  objtool: Add functions to better name alternatives
  objtool: Identify the different types of alternatives
  ...

4 files changed, 117 insertions, 20 deletions

diff --git a/tools/objtool/arch/x86/Build b/tools/objtool/arch/x86/Build
index 3dedb2fd8f3a..febee0b8ee0b 100644
--- a/tools/objtool/arch/x86/Build
+++ b/tools/objtool/arch/x86/Build
@@ -1,5 +1,5 @@
-objtool-y += special.o
 objtool-y += decode.o
+objtool-y += special.o
 objtool-y += orc.o
 
 inat_tables_script = ../arch/x86/tools/gen-insn-attr-x86.awk
@@ -12,3 +12,14 @@ $(OUTPUT)arch/x86/lib/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
 $(OUTPUT)arch/x86/decode.o: $(OUTPUT)arch/x86/lib/inat-tables.c
 
 CFLAGS_decode.o += -I$(OUTPUT)arch/x86/lib
+
+cpu_features = ../arch/x86/include/asm/cpufeatures.h
+cpu_features_script = ../arch/x86/tools/gen-cpu-feature-names-x86.awk
+
+$(OUTPUT)arch/x86/lib/cpu-feature-names.c: $(cpu_features_script) $(cpu_features)
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,gen)$(AWK) -f $(cpu_features_script) $(cpu_features) > $@
+
+$(OUTPUT)arch/x86/special.o: $(OUTPUT)arch/x86/lib/cpu-feature-names.c
+
+CFLAGS_special.o += -I$(OUTPUT)arch/x86/lib
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 0ad5cc70ecbe..f4af82508228 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -16,14 +16,22 @@
 
 #include <asm/orc_types.h>
 #include <objtool/check.h>
+#include <objtool/disas.h>
 #include <objtool/elf.h>
 #include <objtool/arch.h>
 #include <objtool/warn.h>
-#include <objtool/endianness.h>
 #include <objtool/builtin.h>
 #include <arch/elf.h>
 
-int arch_ftrace_match(char *name)
+const char *arch_reg_name[CFI_NUM_REGS] = {
+	"rax", "rcx", "rdx", "rbx",
+	"rsp", "rbp", "rsi", "rdi",
+	"r8",  "r9",  "r10", "r11",
+	"r12", "r13", "r14", "r15",
+	"ra"
+};
+
+int arch_ftrace_match(const char *name)
 {
 	return !strcmp(name, "__fentry__");
 }
@@ -68,9 +76,65 @@ bool arch_callee_saved_reg(unsigned char reg)
 	}
 }
 
-unsigned long arch_dest_reloc_offset(int addend)
+/* Undo the effects of __pa_symbol() if necessary */
+static unsigned long phys_to_virt(unsigned long pa)
+{
+	s64 va = pa;
+
+	if (va > 0)
+		va &= ~(0x80000000);
+
+	return va;
+}
+
+s64 arch_insn_adjusted_addend(struct instruction *insn, struct reloc *reloc)
+{
+	s64 addend = reloc_addend(reloc);
+
+	if (arch_pc_relative_reloc(reloc))
+		addend += insn->offset + insn->len - reloc_offset(reloc);
+
+	return phys_to_virt(addend);
+}
+
+static void scan_for_insn(struct section *sec, unsigned long offset,
+			  unsigned long *insn_off, unsigned int *insn_len)
 {
-	return addend + 4;
+	unsigned long o = 0;
+	struct insn insn;
+
+	while (1) {
+
+		insn_decode(&insn, sec->data->d_buf + o, sec_size(sec) - o,
+			    INSN_MODE_64);
+
+		if (o + insn.length > offset) {
+			*insn_off = o;
+			*insn_len = insn.length;
+			return;
+		}
+
+		o += insn.length;
+	}
+}
+
+u64 arch_adjusted_addend(struct reloc *reloc)
+{
+	unsigned int type = reloc_type(reloc);
+	s64 addend = reloc_addend(reloc);
+	unsigned long insn_off;
+	unsigned int insn_len;
+
+	if (type == R_X86_64_PLT32)
+		return addend + 4;
+
+	if (type != R_X86_64_PC32 || !is_text_sec(reloc->sec->base))
+		return addend;
+
+	scan_for_insn(reloc->sec->base, reloc_offset(reloc),
+		      &insn_off, &insn_len);
+
+	return addend + insn_off + insn_len - reloc_offset(reloc);
 }
 
 unsigned long arch_jump_destination(struct instruction *insn)
@@ -189,15 +253,6 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 	op2 = ins.opcode.bytes[1];
 	op3 = ins.opcode.bytes[2];
 
-	/*
-	 * XXX hack, decoder is buggered and thinks 0xea is 7 bytes long.
-	 */
-	if (op1 == 0xea) {
-		insn->len = 1;
-		insn->type = INSN_BUG;
-		return 0;
-	}
-
 	if (ins.rex_prefix.nbytes) {
 		rex = ins.rex_prefix.bytes[0];
 		rex_w = X86_REX_W(rex) >> 3;
@@ -503,6 +558,12 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 		break;
 
 	case 0x90:
+		if (rex_b) /* XCHG %r8, %rax */
+			break;
+
+		if (prefix == 0xf3) /* REP NOP := PAUSE */
+			break;
+
 		insn->type = INSN_NOP;
 		break;
 
@@ -556,13 +617,14 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 
 		} else if (op2 == 0x0b || op2 == 0xb9) {
 
-			/* ud2 */
+			/* ud2, ud1 */
 			insn->type = INSN_BUG;
 
-		} else if (op2 == 0x0d || op2 == 0x1f) {
+		} else if (op2 == 0x1f) {
 
-			/* nopl/nopw */
-			insn->type = INSN_NOP;
+			/* 0f 1f /0 := NOPL */
+			if (modrm_reg == 0)
+				insn->type = INSN_NOP;
 
 		} else if (op2 == 0x1e) {
 
@@ -692,6 +754,10 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 		insn->type = INSN_SYSRET;
 		break;
 
+	case 0xd6: /* udb */
+		insn->type = INSN_BUG;
+		break;
+
 	case 0xe0: /* loopne */
 	case 0xe1: /* loope */
 	case 0xe2: /* loop */
@@ -892,3 +958,14 @@ bool arch_absolute_reloc(struct elf *elf, struct reloc *reloc)
 		return false;
 	}
 }
+
+#ifdef DISAS
+
+int arch_disas_info_init(struct disassemble_info *dinfo)
+{
+	return disas_info_init(dinfo, bfd_arch_i386,
+			       bfd_mach_i386_i386, bfd_mach_x86_64,
+			       "att");
+}
+
+#endif /* DISAS */
diff --git a/tools/objtool/arch/x86/orc.c b/tools/objtool/arch/x86/orc.c
index 7176b9ec5b05..735e150ca6b7 100644
--- a/tools/objtool/arch/x86/orc.c
+++ b/tools/objtool/arch/x86/orc.c
@@ -5,7 +5,6 @@
 #include <objtool/check.h>
 #include <objtool/orc.h>
 #include <objtool/warn.h>
-#include <objtool/endianness.h>
 
 int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, struct instruction *insn)
 {
diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c
index 06ca4a2659a4..e817a3fff449 100644
--- a/tools/objtool/arch/x86/special.c
+++ b/tools/objtool/arch/x86/special.c
@@ -4,6 +4,10 @@
 #include <objtool/special.h>
 #include <objtool/builtin.h>
 #include <objtool/warn.h>
+#include <asm/cpufeatures.h>
+
+/* cpu feature name array generated from cpufeatures.h */
+#include "cpu-feature-names.c"
 
 void arch_handle_alternative(struct special_alt *alt)
 {
@@ -89,7 +93,7 @@ struct reloc *arch_find_switch_table(struct objtool_file *file,
 	/* 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 ||
+	if (!text_reloc || !is_sec_sym(text_reloc->sym) ||
 	    !text_reloc->sym->sec->rodata)
 		return NULL;
 
@@ -134,3 +138,9 @@ struct reloc *arch_find_switch_table(struct objtool_file *file,
 	*table_size = 0;
 	return rodata_reloc;
 }
+
+const char *arch_cpu_feature_name(int feature_number)
+{
+	return (feature_number < ARRAY_SIZE(cpu_feature_names)) ?
+		cpu_feature_names[feature_number] : NULL;
+}