x86/alternatives, kvm: Fix a couple of CALLs without a frame pointer

objtool complains:

  arch/x86/kvm/kvm.o: warning: objtool: .altinstr_replacement+0xc5: call without frame pointer save/setup
  vmlinux.o: warning: objtool: .altinstr_replacement+0x2eb: call without frame pointer save/setup

Make sure %rSP is an output operand to the respective asm() statements.

The test_cc() hunk and ALT_OUTPUT_SP() courtesy of peterz. Also from him
add some helpful debugging info to the documentation.

Now on to the explanations:

tl;dr: The alternatives macros are pretty fragile.

If I do ALT_OUTPUT_SP(output) in order to be able to package in a %rsp
reference for objtool so that a stack frame gets properly generated, the
inline asm input operand with positional argument 0 in clear_page():

	"0" (page)

gets "renumbered" due to the added

	: "+r" (current_stack_pointer), "=D" (page)

and then gcc says:

  ./arch/x86/include/asm/page_64.h:53:9: error: inconsistent operand constraints in an ‘asm’

The fix is to use an explicit "D" constraint which points to a singleton
register class (gcc terminology) which ends up doing what is expected
here: the page pointer - input and output - should be in the same %rdi
register.

Other register classes have more than one register in them - example:
"r" and "=r" or "A":

  ‘A’
	The ‘a’ and ‘d’ registers.  This class is used for
	instructions that return double word results in the ‘ax:dx’
	register pair.  Single word values will be allocated either in
	‘ax’ or ‘dx’.

so using "D" and "=D" just works in this particular case.

And yes, one would say, sure, why don't you do "+D" but then:

  : "+r" (current_stack_pointer), "+D" (page)
  : [old] "i" (clear_page_orig), [new1] "i" (clear_page_rep), [new2] "i" (clear_page_erms),
  : "cc", "memory", "rax", "rcx")

now find the Waldo^Wcomma which throws a wrench into all this.

Because that silly macro has an "input..." consume-all last macro arg
and in it, one is supposed to supply input *and* clobbers, leading to
silly syntax snafus.

Yap, they need to be cleaned up, one fine day...

Closes: https://lore.kernel.org/oe-kbuild-all/202406141648.jO9qNGLa-lkp@intel.com/
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Sean Christopherson <seanjc@google.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20240625112056.GDZnqoGDXgYuWBDUwu@fat_crate.local

1 files changed, 19 insertions, 0 deletions

diff --git a/tools/objtool/Documentation/objtool.txt b/tools/objtool/Documentation/objtool.txt
index fe39c2a8ef0d..7c3ee959b63c 100644
--- a/tools/objtool/Documentation/objtool.txt
+++ b/tools/objtool/Documentation/objtool.txt
@@ -284,6 +284,25 @@ the objtool maintainers.
 
    Otherwise the stack frame may not get created before the call.
 
+   objtool can help with pinpointing the exact function where it happens:
+
+   $ OBJTOOL_ARGS="--verbose" make arch/x86/kvm/
+
+   arch/x86/kvm/kvm.o: warning: objtool: .altinstr_replacement+0xc5: call without frame pointer save/setup
+   arch/x86/kvm/kvm.o: warning: objtool:   em_loop.part.0+0x29: (alt)
+   arch/x86/kvm/kvm.o: warning: objtool:   em_loop.part.0+0x0: <=== (sym)
+    LD [M]  arch/x86/kvm/kvm-intel.o
+   0000 0000000000028220 <em_loop.part.0>:
+   0000    28220:  0f b6 47 61             movzbl 0x61(%rdi),%eax
+   0004    28224:  3c e2                   cmp    $0xe2,%al
+   0006    28226:  74 2c                   je     28254 <em_loop.part.0+0x34>
+   0008    28228:  48 8b 57 10             mov    0x10(%rdi),%rdx
+   000c    2822c:  83 f0 05                xor    $0x5,%eax
+   000f    2822f:  48 c1 e0 04             shl    $0x4,%rax
+   0013    28233:  25 f0 00 00 00          and    $0xf0,%eax
+   0018    28238:  81 e2 d5 08 00 00       and    $0x8d5,%edx
+   001e    2823e:  80 ce 02                or     $0x2,%dh
+   ...
 
 2. file.o: warning: objtool: .text+0x53: unreachable instruction