[PATCH 1/3] lib/crypto: x86/sha1: Follow the normal %rbp convention

[Eric Biggers <ebiggers@kernel.org>]

Some of the SHA-1 assembly functions push callee-save GPRs to the stack
*before* they set up the frame pointer (%rbp).  (They are leaf
functions, but they need to set up a frame pointer anyway because they
allocate a 16- or 32-byte-aligned buffer on the stack.)

As a result, during these functions, 8(%rbp) doesn't contain a return
address like it is supposed to.

This differs from the convention used by C code, and it interferes with
the frame pointer unwinder (CONFIG_UNWINDER_FRAME_POINTER=y).
Specifically, if a call trace is dumped in these functions, then all
entries are populated purely from the fallback scan of the entire stack:

    RIP: 0010:sha1_transform_avx2+0x1921/0x1ea0
    [...]
    Call Trace:
     <TASK>
     ? sha1_transform_avx+0x2a9/0xc90
     ? sha1_blocks_avx2+0x78/0x140
     ? kernel_fpu_end+0x2d/0x40
     ? sha1_blocks_avx2+0x52/0x140
     ? sha1_update+0x77/0x220
     [...]
     ? do_syscall_64+0x6f/0x3e0

With this fix to follow the normal %rbp convention, the call trace is
generated reliably:

    RIP: 0010:sha1_transform_avx2+0x66e/0x1ea0
    [...]
    Call Trace:
     <TASK>
     sha1_blocks_avx2+0x78/0x140
     sha1_update+0x77/0x220
     [...]
     do_syscall_64+0x6f/0x3e0

Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 lib/crypto/x86/sha1-avx2-asm.S      | 10 +++++-----
 lib/crypto/x86/sha1-ssse3-and-avx.S |  9 +++++----
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/lib/crypto/x86/sha1-avx2-asm.S b/lib/crypto/x86/sha1-avx2-asm.S
index 91b2dc6db179..ca64d7104a47 100644
--- a/lib/crypto/x86/sha1-avx2-asm.S
+++ b/lib/crypto/x86/sha1-avx2-asm.S
@@ -622,6 +622,9 @@
 .macro SHA1_VECTOR_ASM  name
 	SYM_FUNC_START(\name)
 
+	push	%rbp
+	mov	%rsp, %rbp
+
 	push	%rbx
 	push	%r12
 	push	%r13
@@ -631,8 +634,6 @@
 	RESERVE_STACK  = (W_SIZE*4 + 8+24)
 
 	/* Align stack */
-	push	%rbp
-	mov	%rsp, %rbp
 	and	$~(0x20-1), %rsp
 	sub	$RESERVE_STACK, %rsp
 
@@ -651,14 +652,13 @@
 
 	avx2_zeroupper
 
-	mov	%rbp, %rsp
-	pop	%rbp
-
+	lea	-40(%rbp), %rsp
 	pop	%r15
 	pop	%r14
 	pop	%r13
 	pop	%r12
 	pop	%rbx
+	pop	%rbp
 
 	RET
 
diff --git a/lib/crypto/x86/sha1-ssse3-and-avx.S b/lib/crypto/x86/sha1-ssse3-and-avx.S
index 78b48cb09c5b..fe0faaf494c7 100644
--- a/lib/crypto/x86/sha1-ssse3-and-avx.S
+++ b/lib/crypto/x86/sha1-ssse3-and-avx.S
@@ -69,11 +69,12 @@
 .macro SHA1_VECTOR_ASM  name
 	SYM_FUNC_START(\name)
 
-	push	%rbx
-	push	%r12
 	push	%rbp
 	mov	%rsp, %rbp
 
+	push	%rbx
+	push	%r12
+
 	sub	$64, %rsp		# allocate workspace
 	and	$~15, %rsp		# align stack
 
@@ -95,10 +96,10 @@
 	xor	%eax, %eax
 	rep stosq
 
-	mov	%rbp, %rsp		# deallocate workspace
-	pop	%rbp
+	lea	-16(%rbp), %rsp		# deallocate workspace
 	pop	%r12
 	pop	%rbx
+	pop	%rbp
 	RET
 
 	SYM_FUNC_END(\name)
-- 
2.56.0