x86/asm/crypto: Simplify stack usage in sha-mb functions

sha1_mb_mgr_flush_avx2() and sha1_mb_mgr_submit_avx2() both allocate a
lot of stack space which is never used.  Also, many of the registers
being saved aren't being clobbered so there's no need to save them.
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Bernd Petrovitsch <bernd@petrovitsch.priv.at>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Chris J Arges <chris.j.arges@canonical.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michal Marek <mmarek@suse.cz>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Pedro Alves <palves@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: live-patching@vger.kernel.org
Link: http://lkml.kernel.org/r/9402e4d87580d6b2376ed95f67b84bdcce3c830e.1453405861.git.jpoimboe@redhat.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S

@@ -86,16 +86,6 @@
 #define extra_blocks    %arg2
 #define p               %arg2
 
-
-# STACK_SPACE needs to be an odd multiple of 8
-_XMM_SAVE_SIZE  = 10*16
-_GPR_SAVE_SIZE  = 8*8
-_ALIGN_SIZE     = 8
-
-_XMM_SAVE       = 0
-_GPR_SAVE       = _XMM_SAVE + _XMM_SAVE_SIZE
-STACK_SPACE     = _GPR_SAVE + _GPR_SAVE_SIZE + _ALIGN_SIZE
-
 .macro LABEL prefix n
 \prefix\n\():
 .endm
@@ -113,16 +103,7 @@ offset = \_offset
 # JOB* sha1_mb_mgr_flush_avx2(MB_MGR *state)
 # arg 1 : rcx : state
 ENTRY(sha1_mb_mgr_flush_avx2)
-	mov	%rsp, %r10
-	sub     $STACK_SPACE, %rsp
-	and     $~31, %rsp
-	mov     %rbx, _GPR_SAVE(%rsp)
-	mov     %r10, _GPR_SAVE+8*1(%rsp) #save rsp
-	mov	%rbp, _GPR_SAVE+8*3(%rsp)
-	mov	%r12, _GPR_SAVE+8*4(%rsp)
-	mov	%r13, _GPR_SAVE+8*5(%rsp)
-	mov	%r14, _GPR_SAVE+8*6(%rsp)
-	mov	%r15, _GPR_SAVE+8*7(%rsp)
+	push	%rbx
 
 	# If bit (32+3) is set, then all lanes are empty
 	mov     _unused_lanes(state), unused_lanes
@@ -230,16 +211,7 @@ len_is_0:
 	mov     tmp2_w, offset(job_rax)
 
 return:
-
-	mov     _GPR_SAVE(%rsp), %rbx
-	mov     _GPR_SAVE+8*1(%rsp), %r10 #saved rsp
-	mov	_GPR_SAVE+8*3(%rsp), %rbp
-	mov	_GPR_SAVE+8*4(%rsp), %r12
-	mov	_GPR_SAVE+8*5(%rsp), %r13
-	mov	_GPR_SAVE+8*6(%rsp), %r14
-	mov	_GPR_SAVE+8*7(%rsp), %r15
-	mov     %r10, %rsp
-
+	pop	%rbx
 	ret
 
 return_null:

arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S

@@ -94,25 +94,12 @@ DWORD_tmp	= %r9d
 
 lane_data       = %r10
 
-# STACK_SPACE needs to be an odd multiple of 8
-STACK_SPACE     = 8*8 + 16*10 + 8
-
 # JOB* submit_mb_mgr_submit_avx2(MB_MGR *state, job_sha1 *job)
 # arg 1 : rcx : state
 # arg 2 : rdx : job
 ENTRY(sha1_mb_mgr_submit_avx2)
-
-	mov	%rsp, %r10
-	sub     $STACK_SPACE, %rsp
-	and	$~31, %rsp
-
-	mov     %rbx, (%rsp)
-	mov	%r10, 8*2(%rsp)	#save old rsp
-	mov     %rbp, 8*3(%rsp)
-	mov	%r12, 8*4(%rsp)
-	mov	%r13, 8*5(%rsp)
-	mov	%r14, 8*6(%rsp)
-	mov	%r15, 8*7(%rsp)
+	push	%rbx
+	push	%rbp
 
 	mov     _unused_lanes(state), unused_lanes
 	mov	unused_lanes, lane
@@ -203,16 +190,8 @@ len_is_0:
 	movl    DWORD_tmp, _result_digest+1*16(job_rax)
 
 return:
-
-	mov     (%rsp), %rbx
-	mov	8*2(%rsp), %r10	#save old rsp
-	mov     8*3(%rsp), %rbp
-	mov	8*4(%rsp), %r12
-	mov	8*5(%rsp), %r13
-	mov	8*6(%rsp), %r14
-	mov	8*7(%rsp), %r15
-	mov     %r10, %rsp
-
+	pop	%rbp
+	pop	%rbx
 	ret
 
 return_null: