Re: [PATCH v3] kallsyms: strip LTO suffixes from static functions

[Nathan Chancellor]

On Mon, Jun 28, 2021 at 01:31:06PM -0700, Nick Desaulniers wrote:
> Similar to:
> commit 8b8e6b5d3b01 ("kallsyms: strip ThinLTO hashes from static
> functions")
> 
> It's very common for compilers to modify the symbol name for static
> functions as part of optimizing transformations. That makes hooking
> static functions (that weren't inlined or DCE'd) with kprobes difficult.
> 
> LLVM has yet another name mangling scheme used by thin LTO.  Strip off
> these suffixes so that we can continue to hook such static functions.
> 
> Reported-by: KE.LI(Lieke) <like1@xxxxxxxx>
> Signed-off-by: Nick Desaulniers <ndesaulniers@xxxxxxxxxx>
> ---
> Changes v2 -> V3:
> * Un-nest preprocessor checks, as per Nathan.
> 
> Changes v1 -> v2:
> * Both mangling schemes can occur for thinLTO + CFI, this new scheme can
>   also occur for thinLTO without CFI. Split cleanup_symbol_name() into
>   two function calls.
> * Drop KE.LI's tested by tag.
> * Do not carry Fangrui's Reviewed by tag.
> * Drop the inline keyword; it is meaningless.
>  kernel/kallsyms.c | 32 +++++++++++++++++++++++++++++---
>  1 file changed, 29 insertions(+), 3 deletions(-)
> 
> diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
> index 4067564ec59f..143c69e7e75d 100644
> --- a/kernel/kallsyms.c
> +++ b/kernel/kallsyms.c
> @@ -171,6 +171,26 @@ static unsigned long kallsyms_sym_address(int idx)
>  	return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
>  }
>  
> +#ifdef CONFIG_LTO_CLANG_THIN
> +/*
> + * LLVM appends a suffix for local variables that must be promoted to global
> + * scope as part of thin LTO. foo() becomes foo.llvm.974640843467629774. This
> + * can break hooking of static functions with kprobes.
> + */
> +static bool cleanup_symbol_name_thinlto(char *s)
> +{
> +	char *res;
> +
> +	res = strstr(s, ".llvm.");
> +	if (res)
> +		*res = '\0';
> +
> +	return res != NULL;
> +}
> +#else
> +static bool cleanup_symbol_name_thinlto(char *s) { return false; }
> +#endif /* CONFIG_LTO_CLANG_THIN */
> +
>  #if defined(CONFIG_CFI_CLANG) && defined(CONFIG_LTO_CLANG_THIN)
>  /*
>   * LLVM appends a hash to static function names when ThinLTO and CFI are
> @@ -178,7 +198,7 @@ static unsigned long kallsyms_sym_address(int idx)
>   * This causes confusion and potentially breaks user space tools, so we
>   * strip the suffix from expanded symbol names.
>   */
> -static inline bool cleanup_symbol_name(char *s)
> +static bool cleanup_symbol_name_thinlto_cfi(char *s)
>  {
>  	char *res;
>  
> @@ -189,8 +209,14 @@ static inline bool cleanup_symbol_name(char *s)
>  	return res != NULL;
>  }
>  #else
> -static inline bool cleanup_symbol_name(char *s) { return false; }
> -#endif
> +static bool cleanup_symbol_name_thinlto_cfi(char *s) { return false; }
> +#endif /* CONFIG_CFI_CLANG && CONFIG_LTO_CLANG_THIN */
> +
> +static bool cleanup_symbol_name(char *s)
> +{
> +	return cleanup_symbol_name_thinlto(s) &&
> +		cleanup_symbol_name_thinlto_cfi(s);
> +}
>  
>  /* Lookup the address for this symbol. Returns 0 if not found. */
>  unsigned long kallsyms_lookup_name(const char *name)
> -- 
> 2.32.0.93.g670b81a890-goog
> 

Is there any reason that we cannot eliminate the stubs and combine the
functions, or am I missing something? Completely untested diff.

diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index c851ca0ed357..014b59ad68a3 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -161,26 +161,36 @@ static unsigned long kallsyms_sym_address(int idx)
 	return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
 }
 
-#if defined(CONFIG_CFI_CLANG) && defined(CONFIG_LTO_CLANG_THIN)
-/*
- * LLVM appends a hash to static function names when ThinLTO and CFI are
- * both enabled, i.e. foo() becomes foo$707af9a22804d33c81801f27dcfe489b.
- * This causes confusion and potentially breaks user space tools, so we
- * strip the suffix from expanded symbol names.
- */
-static inline bool cleanup_symbol_name(char *s)
+static inline bool cleanup_symbol_name_thinlto(char *s)
 {
 	char *res;
 
-	res = strrchr(s, '$');
+	if (!IS_ENABLED(CONFIG_LTO_CLANG_THIN))
+		return false;
+
+	/*
+	 * LLVM appends a suffix for local variables that must be promoted to global
+	 * scope as part of ThinLTO. foo() becomes foo.llvm.974640843467629774. This
+	 * can break hooking of static functions with kprobes.
+	 */
+	res = strstr(s, ".llvm.");
 	if (res)
 		*res = '\0';
 
+	/*
+	 * LLVM appends a hash to static function names when ThinLTO and CFI are
+	 * both enabled, i.e. foo() becomes foo$707af9a22804d33c81801f27dcfe489b.
+	 * This causes confusion and potentially breaks user space tools, so we
+	 * strip the suffix from expanded symbol names.
+	 */
+	if (IS_ENABLED(CONFIG_CFI_CLANG)) {
+		res = strrchr(s, '$');
+		if (res)
+			*res = '\0';
+	}
+
 	return res != NULL;
 }
-#else
-static inline bool cleanup_symbol_name(char *s) { return false; }
-#endif
 
 /* Lookup the address for this symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name)
@@ -195,7 +205,7 @@ unsigned long kallsyms_lookup_name(const char *name)
 		if (strcmp(namebuf, name) == 0)
 			return kallsyms_sym_address(i);
 
-		if (cleanup_symbol_name(namebuf) && strcmp(namebuf, name) == 0)
+		if (cleanup_symbol_name_thinlto(namebuf) && strcmp(namebuf, name) == 0)
 			return kallsyms_sym_address(i);
 	}
 	return module_kallsyms_lookup_name(name);