1 files changed, 169 insertions, 43 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index fd5e84d0ec47..b672ca15f265 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -43,9 +43,8 @@ struct dyn_ftrace;
 
 char *arch_ftrace_match_adjust(char *str, const char *search);
 
-#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
-struct fgraph_ret_regs;
-unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs);
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS
+unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs);
 #else
 unsigned long ftrace_return_to_handler(unsigned long frame_pointer);
 #endif
@@ -113,14 +112,61 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val
 
 #ifdef CONFIG_FUNCTION_TRACER
 
-extern int ftrace_enabled;
+#include <linux/ftrace_regs.h>
 
-#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+extern int ftrace_enabled;
 
+/**
+ * ftrace_regs - ftrace partial/optimal register set
+ *
+ * ftrace_regs represents a group of registers which is used at the
+ * function entry and exit. There are three types of registers.
+ *
+ * - Registers for passing the parameters to callee, including the stack
+ *   pointer. (e.g. rcx, rdx, rdi, rsi, r8, r9 and rsp on x86_64)
+ * - Registers for passing the return values to caller.
+ *   (e.g. rax and rdx on x86_64)
+ * - Registers for hooking the function call and return including the
+ *   frame pointer (the frame pointer is architecture/config dependent)
+ *   (e.g. rip, rbp and rsp for x86_64)
+ *
+ * Also, architecture dependent fields can be used for internal process.
+ * (e.g. orig_ax on x86_64)
+ *
+ * Basically, ftrace_regs stores the registers related to the context.
+ * On function entry, registers for function parameters and hooking the
+ * function call are stored, and on function exit, registers for function
+ * return value and frame pointers are stored.
+ *
+ * And also, it dpends on the context that which registers are restored
+ * from the ftrace_regs.
+ * On the function entry, those registers will be restored except for
+ * the stack pointer, so that user can change the function parameters
+ * and instruction pointer (e.g. live patching.)
+ * On the function exit, only registers which is used for return values
+ * are restored.
+ *
+ * NOTE: user *must not* access regs directly, only do it via APIs, because
+ * the member can be changed according to the architecture.
+ * This is why the structure is empty here, so that nothing accesses
+ * the ftrace_regs directly.
+ */
 struct ftrace_regs {
-	struct pt_regs		regs;
+	/* Nothing to see here, use the accessor functions! */
 };
-#define arch_ftrace_get_regs(fregs) (&(fregs)->regs)
+
+#define ftrace_regs_size()	sizeof(struct __arch_ftrace_regs)
+
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+/*
+ * Architectures that define HAVE_DYNAMIC_FTRACE_WITH_ARGS must define their own
+ * arch_ftrace_get_regs() where it only returns pt_regs *if* it is fully
+ * populated. It should return NULL otherwise.
+ */
+static inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs)
+{
+	return &arch_ftrace_regs(fregs)->regs;
+}
 
 /*
  * ftrace_regs_set_instruction_pointer() is to be defined by the architecture
@@ -130,6 +176,12 @@ struct ftrace_regs {
 #define ftrace_regs_set_instruction_pointer(fregs, ip) do { } while (0)
 #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 
+#ifdef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS
+
+static_assert(sizeof(struct pt_regs) == ftrace_regs_size());
+
+#endif /* CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */
+
 static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs)
 {
 	if (!fregs)
@@ -138,6 +190,54 @@ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs
 	return arch_ftrace_get_regs(fregs);
 }
 
+#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) || \
+	defined(CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS)
+
+static __always_inline struct pt_regs *
+ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+	/*
+	 * If CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS=y, ftrace_regs memory
+	 * layout is including pt_regs. So always returns that address.
+	 * Since arch_ftrace_get_regs() will check some members and may return
+	 * NULL, we can not use it.
+	 */
+	return &arch_ftrace_regs(fregs)->regs;
+}
+
+#endif /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS || CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */
+
+#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+
+/*
+ * Please define arch dependent pt_regs which compatible to the
+ * perf_arch_fetch_caller_regs() but based on ftrace_regs.
+ * This requires
+ *   - user_mode(_regs) returns false (always kernel mode).
+ *   - able to use the _regs for stack trace.
+ */
+#ifndef arch_ftrace_fill_perf_regs
+/* As same as perf_arch_fetch_caller_regs(), do nothing by default */
+#define arch_ftrace_fill_perf_regs(fregs, _regs) do {} while (0)
+#endif
+
+static __always_inline struct pt_regs *
+ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+	arch_ftrace_fill_perf_regs(fregs, regs);
+	return regs;
+}
+
+#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
+
+static __always_inline struct pt_regs *
+ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+	return &arch_ftrace_regs(fregs)->regs;
+}
+
+#endif
+
 /*
  * When true, the ftrace_regs_{get,set}_*() functions may be used on fregs.
  * Note: this can be true even when ftrace_get_regs() cannot provide a pt_regs.
@@ -150,22 +250,22 @@ static __always_inline bool ftrace_regs_has_args(struct ftrace_regs *fregs)
 	return ftrace_get_regs(fregs) != NULL;
 }
 
-#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
-#define ftrace_regs_get_instruction_pointer(fregs) \
-	instruction_pointer(ftrace_get_regs(fregs))
-#define ftrace_regs_get_argument(fregs, n) \
-	regs_get_kernel_argument(ftrace_get_regs(fregs), n)
-#define ftrace_regs_get_stack_pointer(fregs) \
-	kernel_stack_pointer(ftrace_get_regs(fregs))
-#define ftrace_regs_return_value(fregs) \
-	regs_return_value(ftrace_get_regs(fregs))
-#define ftrace_regs_set_return_value(fregs, ret) \
-	regs_set_return_value(ftrace_get_regs(fregs), ret)
-#define ftrace_override_function_with_return(fregs) \
-	override_function_with_return(ftrace_get_regs(fregs))
-#define ftrace_regs_query_register_offset(name) \
-	regs_query_register_offset(name)
-#endif
+#ifdef CONFIG_HAVE_REGS_AND_STACK_ACCESS_API
+static __always_inline unsigned long
+ftrace_regs_get_kernel_stack_nth(struct ftrace_regs *fregs, unsigned int nth)
+{
+	unsigned long *stackp;
+
+	stackp = (unsigned long *)ftrace_regs_get_stack_pointer(fregs);
+	if (((unsigned long)(stackp + nth) & ~(THREAD_SIZE - 1)) ==
+	    ((unsigned long)stackp & ~(THREAD_SIZE - 1)))
+		return *(stackp + nth);
+
+	return 0;
+}
+#else /* !CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */
+#define ftrace_regs_get_kernel_stack_nth(fregs, nth)	(0L)
+#endif /* CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */
 
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
 			      struct ftrace_ops *op, struct ftrace_regs *fregs);
@@ -228,6 +328,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  * DIRECT - Used by the direct ftrace_ops helper for direct functions
  *            (internal ftrace only, should not be used by others)
  * SUBOP  - Is controlled by another op in field managed.
+ * GRAPH  - Is a component of the fgraph_ops structure
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= BIT(0),
@@ -249,6 +350,7 @@ enum {
 	FTRACE_OPS_FL_PERMANENT                 = BIT(16),
 	FTRACE_OPS_FL_DIRECT			= BIT(17),
 	FTRACE_OPS_FL_SUBOP			= BIT(18),
+	FTRACE_OPS_FL_GRAPH			= BIT(19),
 };
 
 #ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
@@ -469,8 +571,6 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs,
 
 #ifdef CONFIG_STACK_TRACER
 
-extern int stack_tracer_enabled;
-
 int stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer,
 		       size_t *lenp, loff_t *ppos);
 
@@ -522,6 +622,21 @@ enum {
 	FTRACE_MAY_SLEEP		= (1 << 5),
 };
 
+/* Arches can override ftrace_get_symaddr() to convert fentry_ip to symaddr. */
+#ifndef ftrace_get_symaddr
+/**
+ * ftrace_get_symaddr - return the symbol address from fentry_ip
+ * @fentry_ip: the address of ftrace location
+ *
+ * Get the symbol address from @fentry_ip (fast path). If there is no fast
+ * search path, this returns 0.
+ * User may need to use kallsyms API to find the symbol address.
+ */
+#define ftrace_get_symaddr(fentry_ip) (0)
+#endif
+
+void ftrace_sync_ipi(void *data);
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 void ftrace_arch_code_modify_prepare(void);
@@ -1015,6 +1130,17 @@ struct ftrace_graph_ent {
 } __packed;
 
 /*
+ * Structure that defines an entry function trace with retaddr.
+ * It's already packed but the attribute "packed" is needed
+ * to remove extra padding at the end.
+ */
+struct fgraph_retaddr_ent {
+	unsigned long func; /* Current function */
+	int depth;
+	unsigned long retaddr;  /* Return address */
+} __packed;
+
+/*
  * Structure that defines a return function trace.
  * It's already packed but the attribute "packed" is needed
  * to remove extra padding at the end.
@@ -1027,19 +1153,21 @@ struct ftrace_graph_ret {
 	int depth;
 	/* Number of functions that overran the depth limit for current task */
 	unsigned int overrun;
-	unsigned long long calltime;
-	unsigned long long rettime;
 } __packed;
 
 struct fgraph_ops;
 
 /* Type of the callback handlers for tracing function graph*/
 typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *,
-				       struct fgraph_ops *); /* return */
+				       struct fgraph_ops *,
+				       struct ftrace_regs *); /* return */
 typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *,
-				      struct fgraph_ops *); /* entry */
+				      struct fgraph_ops *,
+				      struct ftrace_regs *); /* entry */
 
-extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, struct fgraph_ops *gops);
+extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
+				   struct fgraph_ops *gops,
+				   struct ftrace_regs *fregs);
 bool ftrace_pids_enabled(struct ftrace_ops *ops);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -1055,6 +1183,7 @@ struct fgraph_ops {
 
 void *fgraph_reserve_data(int idx, int size_bytes);
 void *fgraph_retrieve_data(int idx, int *size_bytes);
+void *fgraph_retrieve_parent_data(int idx, int *size_bytes, int depth);
 
 /*
  * Stack of return addresses for functions
@@ -1064,10 +1193,6 @@ void *fgraph_retrieve_data(int idx, int *size_bytes);
 struct ftrace_ret_stack {
 	unsigned long ret;
 	unsigned long func;
-	unsigned long long calltime;
-#ifdef CONFIG_FUNCTION_PROFILER
-	unsigned long long subtime;
-#endif
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	unsigned long fp;
 #endif
@@ -1082,11 +1207,19 @@ struct ftrace_ret_stack {
 extern void return_to_handler(void);
 
 extern int
-function_graph_enter(unsigned long ret, unsigned long func,
-		     unsigned long frame_pointer, unsigned long *retp);
+function_graph_enter_regs(unsigned long ret, unsigned long func,
+			  unsigned long frame_pointer, unsigned long *retp,
+			  struct ftrace_regs *fregs);
+
+static inline int function_graph_enter(unsigned long ret, unsigned long func,
+				       unsigned long fp, unsigned long *retp)
+{
+	return function_graph_enter_regs(ret, func, fp, retp, NULL);
+}
 
 struct ftrace_ret_stack *
 ftrace_graph_get_ret_stack(struct task_struct *task, int skip);
+unsigned long ftrace_graph_top_ret_addr(struct task_struct *task);
 
 unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 				    unsigned long ret, unsigned long *retp);
@@ -1167,16 +1300,9 @@ static inline void unpause_graph_tracing(void) { }
 #ifdef CONFIG_TRACING
 enum ftrace_dump_mode;
 
-#define MAX_TRACER_SIZE		100
-extern char ftrace_dump_on_oops[];
 extern int ftrace_dump_on_oops_enabled(void);
-extern int tracepoint_printk;
 
 extern void disable_trace_on_warning(void);
-extern int __disable_trace_on_warning;
-
-int tracepoint_printk_sysctl(const struct ctl_table *table, int write,
-			     void *buffer, size_t *lenp, loff_t *ppos);
 
 #else /* CONFIG_TRACING */
 static inline void  disable_trace_on_warning(void) { }