cfi: add __cficanonical

With CONFIG_CFI_CLANG, the compiler replaces a function address taken
in C code with the address of a local jump table entry, which passes
runtime indirect call checks. However, the compiler won't replace
addresses taken in assembly code, which will result in a CFI failure
if we later jump to such an address in instrumented C code. The code
generated for the non-canonical jump table looks this:

  <noncanonical.cfi_jt>: /* In C, &noncanonical points here */
	jmp noncanonical
  ...
  <noncanonical>:        /* function body */
	...

This change adds the __cficanonical attribute, which tells the
compiler to use a canonical jump table for the function instead. This
means the compiler will rename the actual function to <function>.cfi
and points the original symbol to the jump table entry instead:

  <canonical>:           /* jump table entry */
	jmp canonical.cfi
  ...
  <canonical.cfi>:       /* function body */
	...

As a result, the address taken in assembly, or other non-instrumented
code always points to the jump table and therefore, can be used for
indirect calls in instrumented code without tripping CFI checks.

Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>   # pci.h
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20210408182843.1754385-3-samitolvanen@google.com

include/linux/compiler-clang.h

@@ -63,3 +63,4 @@
 #endif
 
 #define __nocfi		__attribute__((__no_sanitize__("cfi")))
+#define __cficanonical	__attribute__((__cfi_canonical_jump_table__))

include/linux/compiler_types.h

@@ -246,6 +246,10 @@ struct ftrace_likely_data {
 # define __nocfi
 #endif
 
+#ifndef __cficanonical
+# define __cficanonical
+#endif
+
 #ifndef asm_volatile_goto
 #define asm_volatile_goto(x...) asm goto(x)
 #endif

include/linux/init.h

@@ -220,8 +220,8 @@ extern bool initcall_debug;
 	__initcall_name(initstub, __iid, id)
 
 #define __define_initcall_stub(__stub, fn)			\
-	int __init __stub(void);				\
+	int __init __cficanonical __stub(void);			\
-	int __init __stub(void)					\
+	int __init __cficanonical __stub(void)			\
 	{ 							\
 		return fn();					\
 	}							\

include/linux/pci.h

@@ -1944,8 +1944,8 @@ enum pci_fixup_pass {
 #ifdef CONFIG_LTO_CLANG
 #define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class,	\
 				  class_shift, hook, stub)		\
-	void stub(struct pci_dev *dev);					\
+	void __cficanonical stub(struct pci_dev *dev);			\
-	void stub(struct pci_dev *dev)					\
+	void __cficanonical stub(struct pci_dev *dev)			\
 	{ 								\
 		hook(dev); 						\
 	}								\