LoongArch/ftrace: Add dynamic function tracer support

The compiler has inserted 2 NOPs before the regular function prologue.
T series registers are available and safe because of LoongArch's psABI.

At runtime, we can replace nop with bl to enable ftrace call and replace
bl with nop to disable ftrace call. The bl instruction requires us to
save the original RA value, so it saves RA at t0 here.

Details are:

| Compiled   |       Disabled         |        Enabled         |
+------------+------------------------+------------------------+
| nop        | move     t0, ra        | move    t0, ra         |
| nop        | nop                    | bl      ftrace_caller  |
| func_body  | func_body              | func_body              |

The RA value will be recovered by ftrace_regs_entry, and restored into
RA before returning to the regular function prologue. When a function is
not being traced, the "move t0, ra" is not harmful.

1) ftrace_make_call, ftrace_make_nop (in kernel/ftrace.c)
   The two functions turn each recorded call site of filtered functions
   into a call to ftrace_caller or nops.

2) ftracce_update_ftrace_func (in kernel/ftrace.c)
   turns the nops at ftrace_call into a call to a generic entry for
   function tracers.

3) ftrace_caller (in kernel/mcount_dyn.S)
   The entry where each _mcount call sites calls to once they are
   filtered to be traced.

Co-developed-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Qing Zhang <zhangqing@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

1 files changed, 92 insertions, 0 deletions

diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c
index b1df0ec34bd1..4fd22b4413d0 100644
--- a/arch/loongarch/kernel/inst.c
+++ b/arch/loongarch/kernel/inst.c
@@ -2,8 +2,100 @@
 /*
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
+#include <linux/sizes.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
 #include <asm/inst.h>
 
+static DEFINE_RAW_SPINLOCK(patch_lock);
+
+int larch_insn_read(void *addr, u32 *insnp)
+{
+	int ret;
+	u32 val;
+
+	ret = copy_from_kernel_nofault(&val, addr, LOONGARCH_INSN_SIZE);
+	if (!ret)
+		*insnp = val;
+
+	return ret;
+}
+
+int larch_insn_write(void *addr, u32 insn)
+{
+	int ret;
+	unsigned long flags = 0;
+
+	raw_spin_lock_irqsave(&patch_lock, flags);
+	ret = copy_to_kernel_nofault(addr, &insn, LOONGARCH_INSN_SIZE);
+	raw_spin_unlock_irqrestore(&patch_lock, flags);
+
+	return ret;
+}
+
+int larch_insn_patch_text(void *addr, u32 insn)
+{
+	int ret;
+	u32 *tp = addr;
+
+	if ((unsigned long)tp & 3)
+		return -EINVAL;
+
+	ret = larch_insn_write(tp, insn);
+	if (!ret)
+		flush_icache_range((unsigned long)tp,
+				   (unsigned long)tp + LOONGARCH_INSN_SIZE);
+
+	return ret;
+}
+
+u32 larch_insn_gen_nop(void)
+{
+	return INSN_NOP;
+}
+
+u32 larch_insn_gen_bl(unsigned long pc, unsigned long dest)
+{
+	long offset = dest - pc;
+	unsigned int immediate_l, immediate_h;
+	union loongarch_instruction insn;
+
+	if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) {
+		pr_warn("The generated bl instruction is out of range.\n");
+		return INSN_BREAK;
+	}
+
+	offset >>= 2;
+
+	immediate_l = offset & 0xffff;
+	offset >>= 16;
+	immediate_h = offset & 0x3ff;
+
+	insn.reg0i26_format.opcode = bl_op;
+	insn.reg0i26_format.immediate_l = immediate_l;
+	insn.reg0i26_format.immediate_h = immediate_h;
+
+	return insn.word;
+}
+
+u32 larch_insn_gen_or(enum loongarch_gpr rd, enum loongarch_gpr rj, enum loongarch_gpr rk)
+{
+	union loongarch_instruction insn;
+
+	insn.reg3_format.opcode = or_op;
+	insn.reg3_format.rd = rd;
+	insn.reg3_format.rj = rj;
+	insn.reg3_format.rk = rk;
+
+	return insn.word;
+}
+
+u32 larch_insn_gen_move(enum loongarch_gpr rd, enum loongarch_gpr rj)
+{
+	return larch_insn_gen_or(rd, rj, 0);
+}
+
 u32 larch_insn_gen_lu32id(enum loongarch_gpr rd, int imm)
 {
 	union loongarch_instruction insn;