arm64: Add USER_STACKTRACE support

Currently, userstacktrace is unsupported for ftrace and uprobe
tracers on arm64. This patch uses the perf_callchain_user() code
as blueprint to implement the arch_stack_walk_user() which add
userstacktrace support on arm64.
Meanwhile, we can use arch_stack_walk_user() to simplify the
implementation of perf_callchain_user().
This patch is tested pass with ftrace, uprobe and perf tracers
profiling userstacktrace cases.

Tested-by: chenqiwu <qiwu.chen@transsion.com>
Signed-off-by: chenqiwu <qiwu.chen@transsion.com>
Link: https://lore.kernel.org/r/20231219022229.10230-1-qiwu.chen@transsion.com
Signed-off-by: Will Deacon <will@kernel.org>

arch/arm64/Kconfig

@@ -258,6 +258,7 @@ config ARM64
 	select TRACE_IRQFLAGS_SUPPORT
 	select TRACE_IRQFLAGS_NMI_SUPPORT
 	select HAVE_SOFTIRQ_ON_OWN_STACK
+	select USER_STACKTRACE_SUPPORT
 	help
 	  ARM 64-bit (AArch64) Linux support.
 

arch/arm64/kernel/perf_callchain.c

@@ -10,95 +10,13 @@
 
 #include <asm/pointer_auth.h>
 
-struct frame_tail {
+static bool callchain_trace(void *data, unsigned long pc)
-	struct frame_tail	__user *fp;
-	unsigned long		lr;
-} __attribute__((packed));
-
-/*
- * Get the return address for a single stackframe and return a pointer to the
- * next frame tail.
- */
-static struct frame_tail __user *
-user_backtrace(struct frame_tail __user *tail,
-	       struct perf_callchain_entry_ctx *entry)
 {
-	struct frame_tail buftail;
+	struct perf_callchain_entry_ctx *entry = data;
-	unsigned long err;
-	unsigned long lr;
 
-	/* Also check accessibility of one struct frame_tail beyond */
+	return perf_callchain_store(entry, pc) == 0;
-	if (!access_ok(tail, sizeof(buftail)))
-		return NULL;
-
-	pagefault_disable();
-	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
-	pagefault_enable();
-
-	if (err)
-		return NULL;
-
-	lr = ptrauth_strip_user_insn_pac(buftail.lr);
-
-	perf_callchain_store(entry, lr);
-
-	/*
-	 * Frame pointers should strictly progress back up the stack
-	 * (towards higher addresses).
-	 */
-	if (tail >= buftail.fp)
-		return NULL;
-
-	return buftail.fp;
 }
 
-#ifdef CONFIG_COMPAT
-/*
- * The registers we're interested in are at the end of the variable
- * length saved register structure. The fp points at the end of this
- * structure so the address of this struct is:
- * (struct compat_frame_tail *)(xxx->fp)-1
- *
- * This code has been adapted from the ARM OProfile support.
- */
-struct compat_frame_tail {
-	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
-	u32		sp;
-	u32		lr;
-} __attribute__((packed));
-
-static struct compat_frame_tail __user *
-compat_user_backtrace(struct compat_frame_tail __user *tail,
-		      struct perf_callchain_entry_ctx *entry)
-{
-	struct compat_frame_tail buftail;
-	unsigned long err;
-
-	/* Also check accessibility of one struct frame_tail beyond */
-	if (!access_ok(tail, sizeof(buftail)))
-		return NULL;
-
-	pagefault_disable();
-	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
-	pagefault_enable();
-
-	if (err)
-		return NULL;
-
-	perf_callchain_store(entry, buftail.lr);
-
-	/*
-	 * Frame pointers should strictly progress back up the stack
-	 * (towards higher addresses).
-	 */
-	if (tail + 1 >= (struct compat_frame_tail __user *)
-			compat_ptr(buftail.fp))
-		return NULL;
-
-	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
-}
-#endif /* CONFIG_COMPAT */
-
 void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 			 struct pt_regs *regs)
 {
@@ -107,35 +25,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 		return;
 	}
 
-	perf_callchain_store(entry, regs->pc);
+	arch_stack_walk_user(callchain_trace, entry, regs);
-
-	if (!compat_user_mode(regs)) {
-		/* AARCH64 mode */
-		struct frame_tail __user *tail;
-
-		tail = (struct frame_tail __user *)regs->regs[29];
-
-		while (entry->nr < entry->max_stack &&
-		       tail && !((unsigned long)tail & 0x7))
-			tail = user_backtrace(tail, entry);
-	} else {
-#ifdef CONFIG_COMPAT
-		/* AARCH32 compat mode */
-		struct compat_frame_tail __user *tail;
-
-		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
-
-		while ((entry->nr < entry->max_stack) &&
-			tail && !((unsigned long)tail & 0x3))
-			tail = compat_user_backtrace(tail, entry);
-#endif
-	}
-}
-
-static bool callchain_trace(void *data, unsigned long pc)
-{
-	struct perf_callchain_entry_ctx *entry = data;
-	return perf_callchain_store(entry, pc) == 0;
 }
 
 void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,

arch/arm64/kernel/stacktrace.c

@@ -324,3 +324,123 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 	dump_backtrace(NULL, tsk, loglvl);
 	barrier();
 }
+
+/*
+ * The struct defined for userspace stack frame in AARCH64 mode.
+ */
+struct frame_tail {
+	struct frame_tail	__user *fp;
+	unsigned long		lr;
+} __attribute__((packed));
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static struct frame_tail __user *
+unwind_user_frame(struct frame_tail __user *tail, void *cookie,
+	       stack_trace_consume_fn consume_entry)
+{
+	struct frame_tail buftail;
+	unsigned long err;
+	unsigned long lr;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	lr = ptrauth_strip_user_insn_pac(buftail.lr);
+
+	if (!consume_entry(cookie, lr))
+		return NULL;
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail >= buftail.fp)
+		return NULL;
+
+	return buftail.fp;
+}
+
+#ifdef CONFIG_COMPAT
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct compat_frame_tail *)(xxx->fp)-1
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct compat_frame_tail {
+	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
+	u32		sp;
+	u32		lr;
+} __attribute__((packed));
+
+static struct compat_frame_tail __user *
+unwind_compat_user_frame(struct compat_frame_tail __user *tail, void *cookie,
+				stack_trace_consume_fn consume_entry)
+{
+	struct compat_frame_tail buftail;
+	unsigned long err;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	if (!consume_entry(cookie, buftail.lr))
+		return NULL;
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail + 1 >= (struct compat_frame_tail __user *)
+			compat_ptr(buftail.fp))
+		return NULL;
+
+	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+}
+#endif /* CONFIG_COMPAT */
+
+
+void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+					const struct pt_regs *regs)
+{
+	if (!consume_entry(cookie, regs->pc))
+		return;
+
+	if (!compat_user_mode(regs)) {
+		/* AARCH64 mode */
+		struct frame_tail __user *tail;
+
+		tail = (struct frame_tail __user *)regs->regs[29];
+		while (tail && !((unsigned long)tail & 0x7))
+			tail = unwind_user_frame(tail, cookie, consume_entry);
+	} else {
+#ifdef CONFIG_COMPAT
+		/* AARCH32 compat mode */
+		struct compat_frame_tail __user *tail;
+
+		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
+		while (tail && !((unsigned long)tail & 0x3))
+			tail = unwind_compat_user_frame(tail, cookie, consume_entry);
+#endif
+	}
+}