x86/alternatives: Add nested alternatives macros

Instead of making increasingly complicated ALTERNATIVE_n()
implementations, use a nested alternative expression.

The only difference between:

  ALTERNATIVE_2(oldinst, newinst1, flag1, newinst2, flag2)

and

  ALTERNATIVE(ALTERNATIVE(oldinst, newinst1, flag1),
              newinst2, flag2)

is that the outer alternative can add additional padding when the inner
alternative is the shorter one, which then results in
alt_instr::instrlen being inconsistent.

However, this is easily remedied since the alt_instr entries will be
consecutive and it is trivial to compute the max(alt_instr::instrlen) at
runtime while patching.

Specifically, after this the ALTERNATIVE_2 macro, after CPP expansion
(and manual layout), looks like this:

  .macro ALTERNATIVE_2 oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2
  740:
  740: \oldinstr ;
  741: .skip -(((744f-743f)-(741b-740b)) > 0) * ((744f-743f)-(741b-740b)),0x90 ;
  742: .pushsection .altinstructions,"a" ;
  	altinstr_entry 740b,743f,\ft_flags1,742b-740b,744f-743f ;
  .popsection ;
  .pushsection .altinstr_replacement,"ax" ;
  743: \newinstr1 ;
  744: .popsection ; ;
  741: .skip -(((744f-743f)-(741b-740b)) > 0) * ((744f-743f)-(741b-740b)),0x90 ;
  742: .pushsection .altinstructions,"a" ;
  altinstr_entry 740b,743f,\ft_flags2,742b-740b,744f-743f ;
  .popsection ;
  .pushsection .altinstr_replacement,"ax" ;
  743: \newinstr2 ;
  744: .popsection ;
  .endm

The only label that is ambiguous is 740, however they all reference the
same spot, so that doesn't matter.

NOTE: obviously only @oldinstr may be an alternative; making @newinstr
an alternative would mean patching .altinstr_replacement which very
likely isn't what is intended, also the labels will be confused in that
case.

  [ bp: Debug an issue where it would match the wrong two insns and
    and consider them nested due to the same signed offsets in the
    .alternative section and use instr_va() to compare the full virtual
    addresses instead.

    - Use new labels to denote that the new, nested
    alternatives are being used when staring at preprocessed output.

    - Use the %c constraint everywhere instead of %P and document the
      difference for future reference. ]

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Co-developed-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230628104952.GA2439977@hirez.programming.kicks-ass.net

2 files changed, 31 insertions, 8 deletions

diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c
index 4134d27c696b..4ea0f9815fda 100644
--- a/tools/objtool/arch/x86/special.c
+++ b/tools/objtool/arch/x86/special.c
@@ -9,6 +9,29 @@
 
 void arch_handle_alternative(unsigned short feature, struct special_alt *alt)
 {
+	static struct special_alt *group, *prev;
+
+	/*
+	 * Recompute orig_len for nested ALTERNATIVE()s.
+	 */
+	if (group && group->orig_sec == alt->orig_sec &&
+	             group->orig_off == alt->orig_off) {
+
+		struct special_alt *iter = group;
+		for (;;) {
+			unsigned int len = max(iter->orig_len, alt->orig_len);
+			iter->orig_len = alt->orig_len = len;
+
+			if (iter == prev)
+				break;
+
+			iter = list_next_entry(iter, list);
+		}
+
+	} else group = alt;
+
+	prev = alt;
+
 	switch (feature) {
 	case X86_FEATURE_SMAP:
 		/*
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index 91b1950f5bd8..097a69db82a0 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -84,6 +84,14 @@ static int get_alt_entry(struct elf *elf, const struct special_entry *entry,
 						  entry->new_len);
 	}
 
+	orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig);
+	if (!orig_reloc) {
+		WARN_FUNC("can't find orig reloc", sec, offset + entry->orig);
+		return -1;
+	}
+
+	reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off);
+
 	if (entry->feature) {
 		unsigned short feature;
 
@@ -94,14 +102,6 @@ static int get_alt_entry(struct elf *elf, const struct special_entry *entry,
 		arch_handle_alternative(feature, alt);
 	}
 
-	orig_reloc = find_reloc_by_dest(elf, sec, offset + entry->orig);
-	if (!orig_reloc) {
-		WARN_FUNC("can't find orig reloc", sec, offset + entry->orig);
-		return -1;
-	}
-
-	reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off);
-
 	if (!entry->group || alt->new_len) {
 		new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new);
 		if (!new_reloc) {