From:   Chen Guokai <chenguokai17@mails.ucas.ac.cn>
To:     paul.walmsley@sifive.com, palmer@dabbelt.com,
        aou@eecs.berkeley.edu, rostedt@goodmis.org, mingo@redhat.com,
        sfr@canb.auug.org.au
Cc:     linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org,
        liaochang1@huawei.com, Chen Guokai <chenguokai17@mails.ucas.ac.cn>
Subject: [PATCH v6 06/13] riscv/kprobe: Add code to check if kprobe can be optimized
Date:   Fri, 27 Jan 2023 21:05:34 +0800
Message-Id: <20230127130541.1250865-7-chenguokai17@mails.ucas.ac.cn>
In-Reply-To: <20230127130541.1250865-1-chenguokai17@mails.ucas.ac.cn>
References: <20230127130541.1250865-1-chenguokai17@mails.ucas.ac.cn>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Liao Chang <liaochang1@huawei.com>

For the RVI and RVC hybrid encoding kernel, although AUIPC/JALR just
occupy 8 bytes space, the patched code is 10 bytes at the worst case
to ensure no RVI is truncated, so to check if kprobe satisfies the
requirement of jump optimization, it has to find out an instruction
window large enough to patch AUIPC/JALR(and padding C.NOP), and ensure
no instruction nearby jumps into the patching window.

Besides that, this series does not support the simulation of pc-relative
instruction in optprobe handler yet, so the patching window should not
includes pc-relative instruction.

Signed-off-by: Liao Chang <liaochang1@huawei.com>
Co-developed-by: Chen Guokai <chenguokai17@mails.ucas.ac.cn>
Signed-off-by: Chen Guokai <chenguokai17@mails.ucas.ac.cn>
---
 arch/riscv/kernel/probes/opt.c | 94 +++++++++++++++++++++++++++++++++-
 1 file changed, 93 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/probes/opt.c b/arch/riscv/kernel/probes/opt.c
index d38ed1a52c93..d84aa1420fa2 100644
--- a/arch/riscv/kernel/probes/opt.c
+++ b/arch/riscv/kernel/probes/opt.c
@@ -269,6 +269,50 @@ static void find_free_registers(struct kprobe *kp, struct optimized_kprobe *op,
 	*ra = (kw == 1UL) ? 0 : __builtin_ctzl(kw & ~1UL);
 }
 
+static bool insn_jump_into_range(unsigned long addr, unsigned long start,
+				 unsigned long end)
+{
+	kprobe_opcode_t insn = *(kprobe_opcode_t *)addr;
+	unsigned long target, offset = GET_INSN_LENGTH(insn);
+
+#ifdef CONFIG_RISCV_ISA_C
+	if (offset == RVC_INSN_LEN) {
+		if (riscv_insn_is_c_beqz(insn) || riscv_insn_is_c_bnez(insn))
+			target = addr + rvc_branch_imme(insn);
+		else if (riscv_insn_is_c_jal(insn) || riscv_insn_is_c_j(insn))
+			target = addr + rvc_jal_imme(insn);
+		else
+			target = 0;
+		return (target >= start) && (target < end);
+	}
+#endif
+
+	if (riscv_insn_is_branch(insn))
+		target = addr + rvi_branch_imme(insn);
+	else if (riscv_insn_is_jal(insn))
+		target = addr + rvi_jal_imme(insn);
+	else
+		target = 0;
+	return (target >= start) && (target < end);
+}
+
+static int search_copied_insn(unsigned long paddr, struct optimized_kprobe *op)
+{
+	int i =  1;
+	struct arch_probe_insn api;
+	unsigned long offset = GET_INSN_LENGTH(*(kprobe_opcode_t *)paddr);
+
+	while ((i++ < MAX_COPIED_INSN) && (offset < 2 * RVI_INSN_LEN)) {
+		if (riscv_probe_decode_insn((kprobe_opcode_t *)(paddr + offset),
+					    &api) != INSN_GOOD)
+			return -1;
+		offset += GET_INSN_LENGTH(*(kprobe_opcode_t *)(paddr + offset));
+	}
+
+	op->optinsn.length = offset;
+	return 0;
+}
+
 /*
  * The kprobe based on breakpoint just requires the instrumented instruction
  * supports execute out-of-line or simulation, besides that, optimized kprobe
@@ -276,7 +320,55 @@ static void find_free_registers(struct kprobe *kp, struct optimized_kprobe *op,
  */
 static bool can_optimize(unsigned long paddr, struct optimized_kprobe *op)
 {
-	return false;
+	int ret;
+	struct arch_probe_insn api;
+	unsigned long addr, size = 0, offset = 0;
+	struct kprobe *kp = get_kprobe((kprobe_opcode_t *)paddr);
+
+	/*
+	 * Skip optimization if kprobe has been disarmed or instrumented
+	 * instruction doest not support XOI.
+	 */
+	if (!kp || (riscv_probe_decode_insn(&kp->opcode, &api) != INSN_GOOD))
+		return false;
+
+	/*
+	 * Find a instruction window large enough to contain a pair
+	 * of AUIPC/JALR, and ensure each instruction in this window
+	 * supports XOI.
+	 */
+	ret = search_copied_insn(paddr, op);
+	if (ret)
+		return false;
+
+	if (!kallsyms_lookup_size_offset(paddr, &size, &offset))
+		return false;
+
+	/* Check there is enough space for relative jump(AUIPC/JALR) */
+	if (size - offset <= op->optinsn.length)
+		return false;
+
+	/*
+	 * Decode instructions until function end, check any instruction
+	 * don't jump into the window used to emit optprobe(AUIPC/JALR).
+	 */
+	addr = paddr - offset;
+	while (addr < paddr) {
+		if (insn_jump_into_range(addr, paddr + RVC_INSN_LEN,
+					 paddr + op->optinsn.length))
+			return false;
+		addr += GET_INSN_LENGTH(*(kprobe_opcode_t *)addr);
+	}
+
+	addr = paddr + op->optinsn.length;
+	while (addr < paddr - offset + size) {
+		if (insn_jump_into_range(addr, paddr + RVC_INSN_LEN,
+					 paddr + op->optinsn.length))
+			return false;
+		addr += GET_INSN_LENGTH(*(kprobe_opcode_t *)addr);
+	}
+
+	return true;
 }
 
 int arch_prepared_optinsn(struct arch_optimized_insn *optinsn)
-- 
2.34.1