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, 38 insertions, 12 deletions

diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 04dad3380041..9e73922e1e2e 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -42,6 +42,14 @@ struct dyn_arch_ftrace {
  * 2) jalr: setting low-12 offset to ra, jump to ra, and set ra to
  *          return address (original pc + 4)
  *
+ *<ftrace enable>:
+ * 0: auipc  t0/ra, 0x?
+ * 4: jalr   t0/ra, ?(t0/ra)
+ *
+ *<ftrace disable>:
+ * 0: nop
+ * 4: nop
+ *
  * Dynamic ftrace generates probes to call sites, so we must deal with
  * both auipc and jalr at the same time.
  */
@@ -52,25 +60,43 @@ struct dyn_arch_ftrace {
 #define AUIPC_OFFSET_MASK	(0xfffff000)
 #define AUIPC_PAD		(0x00001000)
 #define JALR_SHIFT		20
-#define JALR_BASIC		(0x000080e7)
-#define AUIPC_BASIC		(0x00000097)
+#define JALR_RA			(0x000080e7)
+#define AUIPC_RA		(0x00000097)
+#define JALR_T0			(0x000282e7)
+#define AUIPC_T0		(0x00000297)
 #define NOP4			(0x00000013)
 
-#define make_call(caller, callee, call)					\
+#define to_jalr_t0(offset)						\
+	(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_T0)
+
+#define to_auipc_t0(offset)						\
+	((offset & JALR_SIGN_MASK) ?					\
+	(((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_T0) :	\
+	((offset & AUIPC_OFFSET_MASK) | AUIPC_T0))
+
+#define make_call_t0(caller, callee, call)				\
 do {									\
-	call[0] = to_auipc_insn((unsigned int)((unsigned long)callee -	\
-				(unsigned long)caller));		\
-	call[1] = to_jalr_insn((unsigned int)((unsigned long)callee -	\
-			       (unsigned long)caller));			\
+	unsigned int offset =						\
+		(unsigned long) callee - (unsigned long) caller;	\
+	call[0] = to_auipc_t0(offset);					\
+	call[1] = to_jalr_t0(offset);					\
 } while (0)
 
-#define to_jalr_insn(offset)						\
-	(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_BASIC)
+#define to_jalr_ra(offset)						\
+	(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_RA)
 
-#define to_auipc_insn(offset)						\
+#define to_auipc_ra(offset)						\
 	((offset & JALR_SIGN_MASK) ?					\
-	(((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_BASIC) :	\
-	((offset & AUIPC_OFFSET_MASK) | AUIPC_BASIC))
+	(((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_RA) :	\
+	((offset & AUIPC_OFFSET_MASK) | AUIPC_RA))
+
+#define make_call_ra(caller, callee, call)				\
+do {									\
+	unsigned int offset =						\
+		(unsigned long) callee - (unsigned long) caller;	\
+	call[0] = to_auipc_ra(offset);					\
+	call[1] = to_jalr_ra(offset);					\
+} while (0)
 
 /*
  * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here.