(2014/08/27 22:02), Wang Nan wrote:

+/*
+ * ARM can always optimize an instruction when using ARM ISA.
+ */

Hmm, this comment looks not correct anymore :)

+int arch_prepared_optinsn(struct arch_optimized_insn *optinsn)
+{
+	return optinsn->prepared;
+}

BTW, why don't you check optinsn->insn != NULL ?
If it is not prepared for optimizing,  optinsn->insn always be NULL.

[...]

+int arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
+{
+	u8 *buf;
+	unsigned long rel_chk;
+	unsigned long val;
+
+	if (!can_optimize(op))
+		return -EILSEQ;
+
+	op->optinsn.insn = get_optinsn_slot();
+	if (!op->optinsn.insn)
+		return -ENOMEM;
+
+	/*
+	 * Verify if the address gap is in 32MiB range, because this uses
+	 * a relative jump.
+	 *
+	 * kprobe opt use a 'b' instruction to branch to optinsn.insn.
+	 * According to ARM manual, branch instruction is:
+	 *
+	 *   31  28 27           24 23             0
+	 *  +------+---+---+---+---+----------------+
+	 *  | cond | 1 | 0 | 1 | 0 |      imm24     |
+	 *  +------+---+---+---+---+----------------+
+	 *
+	 * imm24 is a signed 24 bits integer. The real branch offset is computed
+	 * by: imm32 = SignExtend(imm24:'00', 32);
+	 *
+	 * So the maximum forward branch should be:
+	 *   (0x007fffff << 2) = 0x01fffffc =  0x1fffffc
+	 * The maximum backword branch should be:
+	 *   (0xff800000 << 2) = 0xfe000000 = -0x2000000
+	 *
+	 * We can simply check (rel & 0xfe000003):
+	 *  if rel is positive, (rel & 0xfe000000) shoule be 0
+	 *  if rel is negitive, (rel & 0xfe000000) should be 0xfe000000
+	 *  the last '3' is used for alignment checking.
+	 */
+	rel_chk = (unsigned long)((long)op->optinsn.insn -
+			(long)op->kp.addr + 8) & 0xfe000003;
+
+	if ((rel_chk != 0) && (rel_chk != 0xfe000000)) {
+		__arch_remove_optimized_kprobe(op, 0);
+		return -ERANGE;
+	}
+
+	buf = (u8 *)op->optinsn.insn;
+
+	/* Copy arch-dep-instance from template */
+	memcpy(buf, &optprobe_template_entry, TMPL_END_IDX);
+
+	/* Set probe information */
+	val = (unsigned long)op;
+	memcpy(buf + TMPL_VAL_IDX, &val, sizeof(val));
+
+	/* Set probe function call */
+	val = (unsigned long)optimized_callback;
+	memcpy(buf + TMPL_CALL_IDX, &val, sizeof(val));
+
+	flush_icache_range((unsigned long)buf,
+			   (unsigned long)buf + TMPL_END_IDX);
+
+	op->optinsn.prepared = true;
+	return 0;
+}
+

Thank you,

-- 
Masami HIRAMATSU
Software Platform Research Dept. Linux Technology Research Center
Hitachi, Ltd., Yokohama Research Laboratory
E-mail: masami.hiramatsu.pt at hitachi.com