ftrace: riscv: move from REGS to ARGS

This commit replaces riscv's support for FTRACE_WITH_REGS with support
for FTRACE_WITH_ARGS. This is required for the ongoing effort to stop
relying on stop_machine() for RISCV's implementation of ftrace.

The main relevant benefit that this change will bring for the above
use-case is that now we don't have separate ftrace_caller and
ftrace_regs_caller trampolines. This will allow the callsite to call
ftrace_caller by modifying a single instruction. Now the callsite can
do something similar to:

When not tracing:            |             When tracing:

func:                                      func:
  auipc t0, ftrace_caller_top                auipc t0, ftrace_caller_top
  nop  <=========<Enable/Disable>=========>  jalr  t0, ftrace_caller_bottom
  [...]                                      [...]

The above assumes that we are dropping the support of calling a direct
trampoline from the callsite. We need to drop this as the callsite can't
change the target address to call, it can only enable/disable a call to
a preset target (ftrace_caller in the above diagram). We can later optimize
this by calling an intermediate dispatcher trampoline before ftrace_caller.

Currently, ftrace_regs_caller saves all CPU registers in the format of
struct pt_regs and allows the tracer to modify them. We don't need to
save all of the CPU registers because at function entry only a subset of
pt_regs is live:

|----------+----------+---------------------------------------------|
| Register | ABI Name | Description                                 |
|----------+----------+---------------------------------------------|
| x1       | ra       | Return address for traced function          |
| x2       | sp       | Stack pointer                               |
| x5       | t0       | Return address for ftrace_caller trampoline |
| x8       | s0/fp    | Frame pointer                               |
| x10-11   | a0-1     | Function arguments/return values            |
| x12-17   | a2-7     | Function arguments                          |
|----------+----------+---------------------------------------------|

See RISCV calling convention[1] for the above table.

Saving just the live registers decreases the amount of stack space
required from 288 Bytes to 112 Bytes.

Basic testing was done with this on the VisionFive 2 development board.

Note:
  - Moving from REGS to ARGS will mean that RISCV will stop supporting
    KPROBES_ON_FTRACE as it requires full pt_regs to be saved.
  - KPROBES_ON_FTRACE will be supplanted by FPROBES see [2].

[1] https://riscv.org/wp-content/uploads/2015/01/riscv-calling.pdf
[2] https://lore.kernel.org/all/170887410337.564249.6360118840946697039.stgit@devnote2/

Signed-off-by: Puranjay Mohan <[email protected]>
Tested-by: Björn Töpel <[email protected]>
Reviewed-by: Björn Töpel <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Palmer Dabbelt <[email protected]>

Author: puranjaymohan

arch/riscv/Kconfig

@@ -128,7 +128,7 @@ config RISCV
 	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE)
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
-	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER

arch/riscv/include/asm/ftrace.h

@@ -124,20 +124,82 @@ struct dyn_ftrace;
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 #define ftrace_init_nop ftrace_init_nop
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+#define arch_ftrace_get_regs(regs) NULL
 struct ftrace_ops;
-struct ftrace_regs;
+struct ftrace_regs {
+	unsigned long epc;
+	unsigned long ra;
+	unsigned long sp;
+	unsigned long s0;
+	unsigned long t1;
+	union {
+		unsigned long args[8];
+		struct {
+			unsigned long a0;
+			unsigned long a1;
+			unsigned long a2;
+			unsigned long a3;
+			unsigned long a4;
+			unsigned long a5;
+			unsigned long a6;
+			unsigned long a7;
+		};
+	};
+};
+
+static __always_inline unsigned long ftrace_regs_get_instruction_pointer(const struct ftrace_regs
+									 *fregs)
+{
+	return fregs->epc;
+}
+
+static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
+								unsigned long pc)
+{
+	fregs->epc = pc;
+}
+
+static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs)
+{
+	return fregs->sp;
+}
+
+static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs,
+							      unsigned int n)
+{
+	if (n < 8)
+		return fregs->args[n];
+	return 0;
+}
+
+static __always_inline unsigned long ftrace_regs_get_return_value(const struct ftrace_regs *fregs)
+{
+	return fregs->a0;
+}
+
+static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs,
+							 unsigned long ret)
+{
+	fregs->a0 = ret;
+}
+
+static __always_inline void ftrace_override_function_with_return(struct ftrace_regs *fregs)
+{
+	fregs->epc = fregs->ra;
+}
+
+int ftrace_regs_query_register_offset(const char *name);
+
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs);
 #define ftrace_graph_func ftrace_graph_func
 
-static inline void __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
+static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr)
 {
-		regs->t1 = addr;
+	fregs->t1 = addr;
 }
-#define arch_ftrace_set_direct_caller(fregs, addr) \
-	__arch_ftrace_set_direct_caller(&(fregs)->regs, addr)
-#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 
 #endif /* __ASSEMBLY__ */
 

arch/riscv/kernel/asm-offsets.c

@@ -9,6 +9,7 @@
 #include <linux/kbuild.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/ftrace.h>
 #include <linux/suspend.h>
 #include <asm/kvm_host.h>
 #include <asm/thread_info.h>
@@ -488,4 +489,21 @@ void asm_offsets(void)
 	DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN));
 	OFFSET(STACKFRAME_FP, stackframe, fp);
 	OFFSET(STACKFRAME_RA, stackframe, ra);
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+	DEFINE(FREGS_SIZE_ON_STACK, ALIGN(sizeof(struct ftrace_regs), STACK_ALIGN));
+	DEFINE(FREGS_EPC,	    offsetof(struct ftrace_regs, epc));
+	DEFINE(FREGS_RA,	    offsetof(struct ftrace_regs, ra));
+	DEFINE(FREGS_SP,	    offsetof(struct ftrace_regs, sp));
+	DEFINE(FREGS_S0,	    offsetof(struct ftrace_regs, s0));
+	DEFINE(FREGS_T1,	    offsetof(struct ftrace_regs, t1));
+	DEFINE(FREGS_A0,	    offsetof(struct ftrace_regs, a0));
+	DEFINE(FREGS_A1,	    offsetof(struct ftrace_regs, a1));
+	DEFINE(FREGS_A2,	    offsetof(struct ftrace_regs, a2));
+	DEFINE(FREGS_A3,	    offsetof(struct ftrace_regs, a3));
+	DEFINE(FREGS_A4,	    offsetof(struct ftrace_regs, a4));
+	DEFINE(FREGS_A5,	    offsetof(struct ftrace_regs, a5));
+	DEFINE(FREGS_A6,	    offsetof(struct ftrace_regs, a6));
+	DEFINE(FREGS_A7,	    offsetof(struct ftrace_regs, a7));
+#endif
 }

arch/riscv/kernel/ftrace.c

@@ -127,10 +127,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	int ret = __ftrace_modify_call((unsigned long)&ftrace_call,
 				       (unsigned long)func, true, true);
-	if (!ret) {
-		ret = __ftrace_modify_call((unsigned long)&ftrace_regs_call,
-					   (unsigned long)func, true, true);
-	}
 
 	return ret;
 }
@@ -172,7 +168,7 @@ void arch_ftrace_update_code(int command)
 }
 #endif
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 		       unsigned long addr)
 {
@@ -214,16 +210,13 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	struct pt_regs *regs = arch_ftrace_get_regs(fregs);
-	unsigned long *parent = (unsigned long *)&regs->ra;
-
-	prepare_ftrace_return(parent, ip, frame_pointer(regs));
+	prepare_ftrace_return(&fregs->ra, ip, fregs->s0);
 }
-#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 extern void ftrace_graph_call(void);
 int ftrace_enable_ftrace_graph_caller(void)
 {
@@ -236,6 +229,6 @@ int ftrace_disable_ftrace_graph_caller(void)
 	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
 				    (unsigned long)&prepare_ftrace_return, false, true);
 }
-#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */