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
  ...

1 files changed, 203 insertions, 0 deletions

diff --git a/tools/objtool/trace.c b/tools/objtool/trace.c
new file mode 100644
index 000000000000..5dec44dab781
--- /dev/null
+++ b/tools/objtool/trace.c
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2025, Oracle and/or its affiliates.
+ */
+
+#include <objtool/trace.h>
+
+bool trace;
+int trace_depth;
+
+/*
+ * Macros to trace CFI state attributes changes.
+ */
+
+#define TRACE_CFI_ATTR(attr, prev, next, fmt, ...)		\
+({								\
+	if ((prev)->attr != (next)->attr)			\
+		TRACE("%s=" fmt " ", #attr, __VA_ARGS__);	\
+})
+
+#define TRACE_CFI_ATTR_BOOL(attr, prev, next)			\
+	TRACE_CFI_ATTR(attr, prev, next,			\
+		       "%s", (next)->attr ? "true" : "false")
+
+#define TRACE_CFI_ATTR_NUM(attr, prev, next, fmt)		\
+	TRACE_CFI_ATTR(attr, prev, next, fmt, (next)->attr)
+
+#define CFI_REG_NAME_MAXLEN   16
+
+/*
+ * Return the name of a register. Note that the same static buffer
+ * is returned if the name is dynamically generated.
+ */
+static const char *cfi_reg_name(unsigned int reg)
+{
+	static char rname_buffer[CFI_REG_NAME_MAXLEN];
+	const char *rname;
+
+	switch (reg) {
+	case CFI_UNDEFINED:
+		return "<undefined>";
+	case CFI_CFA:
+		return "cfa";
+	case CFI_SP_INDIRECT:
+		return "(sp)";
+	case CFI_BP_INDIRECT:
+		return "(bp)";
+	}
+
+	if (reg < CFI_NUM_REGS) {
+		rname = arch_reg_name[reg];
+		if (rname)
+			return rname;
+	}
+
+	if (snprintf(rname_buffer, CFI_REG_NAME_MAXLEN, "r%d", reg) == -1)
+		return "<error>";
+
+	return (const char *)rname_buffer;
+}
+
+/*
+ * Functions and macros to trace CFI registers changes.
+ */
+
+static void trace_cfi_reg(const char *prefix, int reg, const char *fmt,
+			  int base_prev, int offset_prev,
+			  int base_next, int offset_next)
+{
+	char *rname;
+
+	if (base_prev == base_next && offset_prev == offset_next)
+		return;
+
+	if (prefix)
+		TRACE("%s:", prefix);
+
+	if (base_next == CFI_UNDEFINED) {
+		TRACE("%1$s=<undef> ", cfi_reg_name(reg));
+	} else {
+		rname = strdup(cfi_reg_name(reg));
+		TRACE(fmt, rname, cfi_reg_name(base_next), offset_next);
+		free(rname);
+	}
+}
+
+static void trace_cfi_reg_val(const char *prefix, int reg,
+			      int base_prev, int offset_prev,
+			      int base_next, int offset_next)
+{
+	trace_cfi_reg(prefix, reg, "%1$s=%2$s%3$+d ",
+		      base_prev, offset_prev, base_next, offset_next);
+}
+
+static void trace_cfi_reg_ref(const char *prefix, int reg,
+			      int base_prev, int offset_prev,
+			      int base_next, int offset_next)
+{
+	trace_cfi_reg(prefix, reg, "%1$s=(%2$s%3$+d) ",
+		      base_prev, offset_prev, base_next, offset_next);
+}
+
+#define TRACE_CFI_REG_VAL(reg, prev, next)				\
+	trace_cfi_reg_val(NULL, reg, prev.base, prev.offset,		\
+			  next.base, next.offset)
+
+#define TRACE_CFI_REG_REF(reg, prev, next)				\
+	trace_cfi_reg_ref(NULL, reg, prev.base, prev.offset,		\
+			  next.base, next.offset)
+
+void trace_insn_state(struct instruction *insn, struct insn_state *sprev,
+		      struct insn_state *snext)
+{
+	struct cfi_state *cprev, *cnext;
+	int i;
+
+	if (!memcmp(sprev, snext, sizeof(struct insn_state)))
+		return;
+
+	cprev = &sprev->cfi;
+	cnext = &snext->cfi;
+
+	disas_print_insn(stderr, objtool_disas_ctx, insn,
+			 trace_depth - 1, "state: ");
+
+	/* print registers changes */
+	TRACE_CFI_REG_VAL(CFI_CFA, cprev->cfa, cnext->cfa);
+	for (i = 0; i < CFI_NUM_REGS; i++) {
+		TRACE_CFI_REG_VAL(i, cprev->vals[i], cnext->vals[i]);
+		TRACE_CFI_REG_REF(i, cprev->regs[i], cnext->regs[i]);
+	}
+
+	/* print attributes changes */
+	TRACE_CFI_ATTR_NUM(stack_size, cprev, cnext, "%d");
+	TRACE_CFI_ATTR_BOOL(drap, cprev, cnext);
+	if (cnext->drap) {
+		trace_cfi_reg_val("drap", cnext->drap_reg,
+				  cprev->drap_reg, cprev->drap_offset,
+				  cnext->drap_reg, cnext->drap_offset);
+	}
+	TRACE_CFI_ATTR_BOOL(bp_scratch, cprev, cnext);
+	TRACE_CFI_ATTR_NUM(instr, sprev, snext, "%d");
+	TRACE_CFI_ATTR_NUM(uaccess_stack, sprev, snext, "%u");
+
+	TRACE("\n");
+
+	insn->trace = 1;
+}
+
+void trace_alt_begin(struct instruction *orig_insn, struct alternative *alt,
+		     char *alt_name)
+{
+	struct instruction *alt_insn;
+	char suffix[2];
+
+	alt_insn = alt->insn;
+
+	if (alt->type == ALT_TYPE_EX_TABLE) {
+		/*
+		 * When there is an exception table then the instruction
+		 * at the original location is executed but it can cause
+		 * an exception. In that case, the execution will be
+		 * redirected to the alternative instruction.
+		 *
+		 * The instruction at the original location can have
+		 * instruction alternatives, so we just print the location
+		 * of the instruction that can cause the exception and
+		 * not the instruction itself.
+		 */
+		TRACE_ALT_INFO_NOADDR(orig_insn, "/ ", "%s for instruction at 0x%lx <%s+0x%lx>",
+				      alt_name,
+				      orig_insn->offset, orig_insn->sym->name,
+				      orig_insn->offset - orig_insn->sym->offset);
+	} else {
+		TRACE_ALT_INFO_NOADDR(orig_insn, "/ ", "%s", alt_name);
+	}
+
+	if (alt->type == ALT_TYPE_JUMP_TABLE) {
+		/*
+		 * For a jump alternative, if the default instruction is
+		 * a NOP then it is replaced with the jmp instruction,
+		 * otherwise it is replaced with a NOP instruction.
+		 */
+		trace_depth++;
+		if (orig_insn->type == INSN_NOP) {
+			suffix[0] = (orig_insn->len == 5) ? 'q' : '\0';
+			TRACE_ADDR(orig_insn, "jmp%-3s %lx <%s+0x%lx>", suffix,
+				   alt_insn->offset, alt_insn->sym->name,
+				   alt_insn->offset - alt_insn->sym->offset);
+		} else {
+			TRACE_ADDR(orig_insn, "nop%d", orig_insn->len);
+			trace_depth--;
+		}
+	}
+}
+
+void trace_alt_end(struct instruction *orig_insn, struct alternative *alt,
+		   char *alt_name)
+{
+	if (alt->type == ALT_TYPE_JUMP_TABLE && orig_insn->type == INSN_NOP)
+		trace_depth--;
+	TRACE_ALT_INFO_NOADDR(orig_insn, "\\ ", "%s", alt_name);
+}