x86/its: FineIBT-paranoid vs ITS

commit e52c1dc7455d32c8a55f9949d300e5e87d011fa6 upstream.

FineIBT-paranoid was using the retpoline bytes for the paranoid check,
disabling retpolines, because all parts that have IBT also have eIBRS
and thus don't need no stinking retpolines.

Except... ITS needs the retpolines for indirect calls must not be in
the first half of a cacheline :-/

So what was the paranoid call sequence:

  <fineibt_paranoid_start>:
   0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
   6:   45 3b 53 f7             cmp    -0x9(%r11), %r10d
   a:   4d 8d 5b <f0>           lea    -0x10(%r11), %r11
   e:   75 fd                   jne    d <fineibt_paranoid_start+0xd>
  10:   41 ff d3                call   *%r11
  13:   90                      nop

Now becomes:

  <fineibt_paranoid_start>:
   0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
   6:   45 3b 53 f7             cmp    -0x9(%r11), %r10d
   a:   4d 8d 5b f0             lea    -0x10(%r11), %r11
   e:   2e e8 XX XX XX XX	cs call __x86_indirect_paranoid_thunk_r11

  Where the paranoid_thunk looks like:

   1d:  <ea>                    (bad)
   __x86_indirect_paranoid_thunk_r11:
   1e:  75 fd                   jne 1d
   __x86_indirect_its_thunk_r11:
   20:  41 ff eb                jmp *%r11
   23:  cc                      int3

[ dhansen: remove initialization to false ]

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Pawan Gupta <[email protected]>
Signed-off-by: Dave Hansen <[email protected]>
Reviewed-by: Alexandre Chartre <[email protected]>
[ Just a portion of the original commit, in order to fix a build issue
  in stable kernels due to backports ]
Tested-by: Holger Hoffstätte <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: Peter Zijlstra

arch/x86/include/asm/alternative.h

@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
+#include <asm/bug.h>
 
 #define ALTINSTR_FLAG_INV	(1 << 15)
 #define ALT_NOT(feat)		((feat) | ALTINSTR_FLAG_INV)
@@ -85,10 +86,17 @@ struct module;
 extern void its_init_mod(struct module *mod);
 extern void its_fini_mod(struct module *mod);
 extern void its_free_mod(struct module *mod);
+extern u8 *its_static_thunk(int reg);
 #else /* CONFIG_MITIGATION_ITS */
 static inline void its_init_mod(struct module *mod) { }
 static inline void its_fini_mod(struct module *mod) { }
 static inline void its_free_mod(struct module *mod) { }
+static inline u8 *its_static_thunk(int reg)
+{
+	WARN_ONCE(1, "ITS not compiled in");
+
+	return NULL;
+}
 #endif
 
 #if defined(CONFIG_RETHUNK) && defined(CONFIG_OBJTOOL)

arch/x86/kernel/alternative.c

@@ -596,6 +596,14 @@ static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg)
 	/* Lower-half of the cacheline? */
 	return !(addr & 0x20);
 }
+
+u8 *its_static_thunk(int reg)
+{
+	u8 *thunk = __x86_indirect_its_thunk_array[reg];
+
+	return thunk;
+}
+
 #endif
 
 /*

arch/x86/net/bpf_jit_comp.c

@@ -467,7 +467,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
 	if (IS_ENABLED(CONFIG_MITIGATION_ITS) &&
 	    cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) {
 		OPTIMIZER_HIDE_VAR(reg);
-		emit_jump(&prog, &__x86_indirect_its_thunk_array[reg], ip);
+		emit_jump(&prog, its_static_thunk(reg), ip);
 	} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
 		EMIT_LFENCE();
 		EMIT2(0xFF, 0xE0 + reg);