[PATCH v4 02/23] perf llvm: Fix arm64 adrp instruction disassembly mismatch with objdump

[Tengda Wu]

The operands of 'adrp' instructions parsed by libllvm are currently
represented as raw immediates rather than the "address <symbol+offset>"
format used by objdump. This inconsistency causes arm64_mov__parse()
to fail when parsing these instructions during post-processing.

Example of the mismatch:
  Current: adrp  x18, 8014
  Fix:     adrp  x18, ffff800081f5f000 <this_cpu_vector>

Fix this by manually extracting the target address from the raw adrp
instruction via symbol_lookup_callback(). The address is then converted
to a specific symbol during symbol__disassemble_llvm() and formatted
to match objdump's output, ensuring compatibility with existing
parsers.

Signed-off-by: Tengda Wu <wutengda@xxxxxxxxxxxxxxx>
---
 tools/perf/util/llvm.c | 50 ++++++++++++++++++++++++++++++++++++++----
 1 file changed, 46 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/llvm.c b/tools/perf/util/llvm.c
index a0deb742a733..6b53b283205a 100644
--- a/tools/perf/util/llvm.c
+++ b/tools/perf/util/llvm.c
@@ -9,8 +9,10 @@
 #include "symbol.h"
 #include <errno.h>
 #include <fcntl.h>
+#include <string.h>
 #include <unistd.h>
 #include <linux/zalloc.h>
+#include <linux/bitops.h>
 
 #ifdef HAVE_LIBLLVM_SUPPORT
 #include "llvm-c-helpers.h"
@@ -108,6 +110,16 @@ symbol_lookup_callback(void *disinfo, uint64_t value,
 		storage->branch_addr = value;
 	else if (*ref_type == LLVMDisassembler_ReferenceType_In_PCrel_Load)
 		storage->pcrel_load_addr = value;
+	else if (*ref_type == LLVMDisassembler_ReferenceType_In_ARM64_ADRP) {
+		uint64_t adrp_imm;
+
+		/* immhi (bits 23:5) and immlo (bits 30:29) */
+		adrp_imm = ((value & 0x00ffffe0) >> 3) | ((value >> 29) & 0x3);
+		adrp_imm = sign_extend64(adrp_imm, 20);
+
+		/* Calculate the target page address */
+		storage->pcrel_load_addr = (address & ~0xfffULL) + (adrp_imm << 12);
+	}
 	*ref_type = LLVMDisassembler_ReferenceType_InOut_None;
 	return NULL;
 }
@@ -230,10 +242,40 @@ int symbol__disassemble_llvm(const char *filename, struct symbol *sym,
 		if (storage.pcrel_load_addr != 0) {
 			char *name = llvm_name_for_data(dso, filename,
 							storage.pcrel_load_addr);
-			disasm_len += scnprintf(disasm_buf + disasm_len,
-						sizeof(disasm_buf) - disasm_len,
-						"  # %#"PRIx64,
-						storage.pcrel_load_addr);
+
+			if (arch__is_arm64(args->arch)) {
+				/*
+				 * For arm64, replace the immediate operand with
+				 * the resolved address to match objdump's output.
+				 *
+				 * Example conversion:
+				 *   From: adrp  x18, 8014
+				 *   To:   adrp  x18, ffff800081f5f000
+				 */
+				char *s = strchr(disasm_buf, ',');
+
+				if (s == NULL)
+					goto err;
+
+				s++;
+				*s = '\0';
+				disasm_len = strlen(disasm_buf);
+				disasm_len += scnprintf(disasm_buf + disasm_len,
+							sizeof(disasm_buf) - disasm_len,
+							" %"PRIx64,
+							storage.pcrel_load_addr);
+			} else {
+				/*
+				 * For other archs, append the resolved address
+				 * as an inline comment.
+				 */
+				disasm_len += scnprintf(disasm_buf + disasm_len,
+							sizeof(disasm_buf) - disasm_len,
+							"  # %#"PRIx64,
+							storage.pcrel_load_addr);
+			}
+
+			/* Append the resolved symbol name if available */
 			if (name) {
 				disasm_len += scnprintf(disasm_buf + disasm_len,
 							sizeof(disasm_buf) -
-- 
2.34.1