objtool: Make instruction::stack_ops a single-linked list

 struct instruction {
 	struct list_head           list;                 /*     0    16 */
 	struct hlist_node          hash;                 /*    16    16 */
 	struct list_head           call_node;            /*    32    16 */
 	struct section *           sec;                  /*    48     8 */
 	long unsigned int          offset;               /*    56     8 */
 	/* --- cacheline 1 boundary (64 bytes) --- */
 	unsigned int               len;                  /*    64     4 */
 	enum insn_type             type;                 /*    68     4 */
 	long unsigned int          immediate;            /*    72     8 */
 	u16                        dead_end:1;           /*    80: 0  2 */
 	u16                        ignore:1;             /*    80: 1  2 */
 	u16                        ignore_alts:1;        /*    80: 2  2 */
 	u16                        hint:1;               /*    80: 3  2 */
 	u16                        save:1;               /*    80: 4  2 */
 	u16                        restore:1;            /*    80: 5  2 */
 	u16                        retpoline_safe:1;     /*    80: 6  2 */
 	u16                        noendbr:1;            /*    80: 7  2 */
 	u16                        entry:1;              /*    80: 8  2 */

 	/* XXX 7 bits hole, try to pack */

 	s8                         instr;                /*    82     1 */
 	u8                         visited;              /*    83     1 */

 	/* XXX 4 bytes hole, try to pack */

 	struct alt_group *         alt_group;            /*    88     8 */
 	struct symbol *            call_dest;            /*    96     8 */
 	struct instruction *       jump_dest;            /*   104     8 */
 	struct instruction *       first_jump_src;       /*   112     8 */
 	struct reloc *             jump_table;           /*   120     8 */
 	/* --- cacheline 2 boundary (128 bytes) --- */
 	struct reloc *             reloc;                /*   128     8 */
 	struct list_head           alts;                 /*   136    16 */
 	struct symbol *            sym;                  /*   152     8 */
-	struct list_head           stack_ops;            /*   160    16 */
-	struct cfi_state *         cfi;                  /*   176     8 */
+	struct stack_op *          stack_ops;            /*   160     8 */
+	struct cfi_state *         cfi;                  /*   168     8 */

-	/* size: 184, cachelines: 3, members: 29 */
-	/* sum members: 178, holes: 1, sum holes: 4 */
+	/* size: 176, cachelines: 3, members: 29 */
+	/* sum members: 170, holes: 1, sum holes: 4 */
 	/* sum bitfield members: 9 bits, bit holes: 1, sum bit holes: 7 bits */
-	/* last cacheline: 56 bytes */
+	/* last cacheline: 48 bytes */
 };

pre:	5:58.22 real,   226.69 user,    131.22 sys,     26221520 mem
post:	5:58.50 real,   229.64 user,    128.65 sys,     26221520 mem

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org> # build only
Tested-by: Thomas Weißschuh <linux@weissschuh.net> # compile and run
Link: https://lore.kernel.org/r/20230208172245.362196959@infradead.org

Author: Peter Zijlstra

tools/objtool/arch/x86/decode.c

@@ -105,7 +105,7 @@ bool arch_pc_relative_reloc(struct reloc *reloc)
 #define ADD_OP(op) \
 	if (!(op = calloc(1, sizeof(*op)))) \
 		return -1; \
-	else for (list_add_tail(&op->list, ops_list); op; op = NULL)
+	else for (*ops_list = op, ops_list = &op->next; op; op = NULL)
 
 /*
  * Helpers to decode ModRM/SIB:
@@ -148,7 +148,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
 			    unsigned long offset, unsigned int maxlen,
 			    struct instruction *insn)
 {
-	struct list_head *ops_list = &insn->stack_ops;
+	struct stack_op **ops_list = &insn->stack_ops;
 	const struct elf *elf = file->elf;
 	struct insn ins;
 	int x86_64, ret;

tools/objtool/check.c

@@ -398,7 +398,6 @@ static int decode_instructions(struct objtool_file *file)
 			}
 			memset(insn, 0, sizeof(*insn));
 			INIT_LIST_HEAD(&insn->alts);
-			INIT_LIST_HEAD(&insn->stack_ops);
 			INIT_LIST_HEAD(&insn->call_node);
 
 			insn->sec = sec;
@@ -1331,12 +1330,13 @@ static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *i
 
 static void remove_insn_ops(struct instruction *insn)
 {
-	struct stack_op *op, *tmp;
+	struct stack_op *op, *next;
 
-	list_for_each_entry_safe(op, tmp, &insn->stack_ops, list) {
-		list_del(&op->list);
+	for (op = insn->stack_ops; op; op = next) {
+		next = op->next;
 		free(op);
 	}
+	insn->stack_ops = NULL;
 }
 
 static void annotate_call_site(struct objtool_file *file,
@@ -1781,7 +1781,6 @@ static int handle_group_alt(struct objtool_file *file,
 		}
 		memset(nop, 0, sizeof(*nop));
 		INIT_LIST_HEAD(&nop->alts);
-		INIT_LIST_HEAD(&nop->stack_ops);
 
 		nop->sec = special_alt->new_sec;
 		nop->offset = special_alt->new_off + special_alt->new_len;
@@ -3226,7 +3225,7 @@ static int handle_insn_ops(struct instruction *insn,
 {
 	struct stack_op *op;
 
-	list_for_each_entry(op, &insn->stack_ops, list) {
+	for (op = insn->stack_ops; op; op = op->next) {
 
 		if (update_cfi_state(insn, next_insn, &state->cfi, op))
 			return 1;

tools/objtool/include/objtool/arch.h

@@ -62,9 +62,9 @@ struct op_src {
 };
 
 struct stack_op {
+	struct stack_op *next;
 	struct op_dest dest;
 	struct op_src src;
-	struct list_head list;
 };
 
 struct instruction;

tools/objtool/include/objtool/check.h

@@ -68,7 +68,7 @@ struct instruction {
 	struct reloc *reloc;
 	struct list_head alts;
 	struct symbol *sym;
-	struct list_head stack_ops;
+	struct stack_op *stack_ops;
 	struct cfi_state *cfi;
 };