riscv: ftrace: Reduce the detour code size to half

Use a temporary register to reduce the size of detour code from 16 bytes to
8 bytes. The previous implementation is from 'commit afc76b8b8011 ("riscv:
Using PATCHABLE_FUNCTION_ENTRY instead of MCOUNT")'.

Before the patch:
<func_prolog>:
 0: REG_S  ra, -SZREG(sp)
 4: auipc  ra, ?
 8: jalr   ?(ra)
12: REG_L  ra, -SZREG(sp)
 (func_boddy)

After the patch:
<func_prolog>:
 0: auipc  t0, ?
 4: jalr   t0, ?(t0)
 (func_boddy)

This patch not just reduces the size of detour code, but also fixes an
important issue:

An Ftrace callback registered with FTRACE_OPS_FL_IPMODIFY flag can
actually change the instruction pointer, e.g. to "replace" the given
kernel function with a new one, which is needed for livepatching, etc.

In this case, the trampoline (ftrace_regs_caller) would not return to
<func_prolog+12> but would rather jump to the new function. So, "REG_L
ra, -SZREG(sp)" would not run and the original return address would not
be restored. The kernel is likely to hang or crash as a result.

This can be easily demonstrated if one tries to "replace", say,
cmdline_proc_show() with a new function with the same signature using
instruction_pointer_set(&fregs->regs, new_func_addr) in the Ftrace
callback.

Link: https://lore.kernel.org/linux-riscv/20221122075440.1165172-1-suagrfillet@gmail.com/
Link: https://lore.kernel.org/linux-riscv/d7d5730b-ebef-68e5-5046-e763e1ee6164@yadro.com/
Co-developed-by: Song Shuai <suagrfillet@gmail.com>
Signed-off-by: Song Shuai <suagrfillet@gmail.com>
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Cc: Evgenii Shatokhin <e.shatokhin@yadro.com>
Reviewed-by: Evgenii Shatokhin <e.shatokhin@yadro.com>
Link: https://lore.kernel.org/r/20230112090603.1295340-4-guoren@kernel.org
Cc: stable@vger.kernel.org
Fixes: 10626c32e382 ("riscv/ftrace: Add basic support")
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

1 files changed, 19 insertions, 46 deletions

diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 2086f6585773..5bff37af4770 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -55,12 +55,15 @@ static int ftrace_check_current_call(unsigned long hook_pos,
 }
 
 static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
-				bool enable)
+				bool enable, bool ra)
 {
 	unsigned int call[2];
 	unsigned int nops[2] = {NOP4, NOP4};
 
-	make_call(hook_pos, target, call);
+	if (ra)
+		make_call_ra(hook_pos, target, call);
+	else
+		make_call_t0(hook_pos, target, call);
 
 	/* Replace the auipc-jalr pair at once. Return -EPERM on write error. */
 	if (patch_text_nosync
@@ -70,42 +73,13 @@ static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
 	return 0;
 }
 
-/*
- * Put 5 instructions with 16 bytes at the front of function within
- * patchable function entry nops' area.
- *
- * 0: REG_S  ra, -SZREG(sp)
- * 1: auipc  ra, 0x?
- * 2: jalr   -?(ra)
- * 3: REG_L  ra, -SZREG(sp)
- *
- * So the opcodes is:
- * 0: 0xfe113c23 (sd)/0xfe112e23 (sw)
- * 1: 0x???????? -> auipc
- * 2: 0x???????? -> jalr
- * 3: 0xff813083 (ld)/0xffc12083 (lw)
- */
-#if __riscv_xlen == 64
-#define INSN0	0xfe113c23
-#define INSN3	0xff813083
-#elif __riscv_xlen == 32
-#define INSN0	0xfe112e23
-#define INSN3	0xffc12083
-#endif
-
-#define FUNC_ENTRY_SIZE	16
-#define FUNC_ENTRY_JMP	4
-
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned int call[4] = {INSN0, 0, 0, INSN3};
-	unsigned long target = addr;
-	unsigned long caller = rec->ip + FUNC_ENTRY_JMP;
+	unsigned int call[2];
 
-	call[1] = to_auipc_insn((unsigned int)(target - caller));
-	call[2] = to_jalr_insn((unsigned int)(target - caller));
+	make_call_t0(rec->ip, addr, call);
 
-	if (patch_text_nosync((void *)rec->ip, call, FUNC_ENTRY_SIZE))
+	if (patch_text_nosync((void *)rec->ip, call, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	return 0;
@@ -114,15 +88,14 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		    unsigned long addr)
 {
-	unsigned int nops[4] = {NOP4, NOP4, NOP4, NOP4};
+	unsigned int nops[2] = {NOP4, NOP4};
 
-	if (patch_text_nosync((void *)rec->ip, nops, FUNC_ENTRY_SIZE))
+	if (patch_text_nosync((void *)rec->ip, nops, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	return 0;
 }
 
-
 /*
  * This is called early on, and isn't wrapped by
  * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold
@@ -144,10 +117,10 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	int ret = __ftrace_modify_call((unsigned long)&ftrace_call,
-				       (unsigned long)func, true);
+				       (unsigned long)func, true, true);
 	if (!ret) {
 		ret = __ftrace_modify_call((unsigned long)&ftrace_regs_call,
-					   (unsigned long)func, true);
+					   (unsigned long)func, true, true);
 	}
 
 	return ret;
@@ -159,16 +132,16 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 		       unsigned long addr)
 {
 	unsigned int call[2];
-	unsigned long caller = rec->ip + FUNC_ENTRY_JMP;
+	unsigned long caller = rec->ip;
 	int ret;
 
-	make_call(caller, old_addr, call);
+	make_call_t0(caller, old_addr, call);
 	ret = ftrace_check_current_call(caller, call);
 
 	if (ret)
 		return ret;
 
-	return __ftrace_modify_call(caller, addr, true);
+	return __ftrace_modify_call(caller, addr, true, false);
 }
 #endif
 
@@ -203,12 +176,12 @@ int ftrace_enable_ftrace_graph_caller(void)
 	int ret;
 
 	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, true);
+				    (unsigned long)&prepare_ftrace_return, true, true);
 	if (ret)
 		return ret;
 
 	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
-				    (unsigned long)&prepare_ftrace_return, true);
+				    (unsigned long)&prepare_ftrace_return, true, true);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
@@ -216,12 +189,12 @@ int ftrace_disable_ftrace_graph_caller(void)
 	int ret;
 
 	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, false);
+				    (unsigned long)&prepare_ftrace_return, false, true);
 	if (ret)
 		return ret;
 
 	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
-				    (unsigned long)&prepare_ftrace_return, false);
+				    (unsigned long)&prepare_ftrace_return, false, true);
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */