x86/asm/entry/64: Save R11 into pt_regs->flags on SYSCALL64 fastpath

Before this patch, R11 was saved in pt_regs->r11.

Which looks natural, but requires messy shuffling to/from iret
frame whenever ptrace or e.g. sys_iopl() wants to modify flags -
because that's how this register is used by SYSCALL/SYSRET.

This patch saves R11 in pt_regs->flags, and uses that value for
the SYSRET64 instruction. Shuffling is eliminated.

FIXUP/RESTORE_TOP_OF_STACK are simplified.

stub_iopl is no longer needed: pt_regs->flags needs no fixing up.

Testing shows that syscall fast path is ~54.3 ns before
and after the patch (on 2.7 GHz Sandy Bridge CPU).

Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Will Drewry <wad@chromium.org>
Link: http://lkml.kernel.org/r/1425926364-9526-2-git-send-email-dvlasenk@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index f1a962f..4b5f7bf 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -95,9 +95,11 @@
 	CFI_ADJUST_CFA_OFFSET 15*8+\addskip
 	.endm
 
-	.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8plus=1
-	.if \r8plus
+	.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
+	.if \r11
 	movq_cfi r11, 6*8+\offset
+	.endif
+	.if \r8910
 	movq_cfi r10, 7*8+\offset
 	movq_cfi r9,  8*8+\offset
 	movq_cfi r8,  9*8+\offset
@@ -113,16 +115,19 @@
 	movq_cfi rdi, 14*8+\offset
 	.endm
 	.macro SAVE_C_REGS offset=0
-	SAVE_C_REGS_HELPER \offset, 1, 1, 1
+	SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
 	.endm
 	.macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0
-	SAVE_C_REGS_HELPER \offset, 0, 0, 1
+	SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1
 	.endm
 	.macro SAVE_C_REGS_EXCEPT_R891011
-	SAVE_C_REGS_HELPER 0, 1, 1, 0
+	SAVE_C_REGS_HELPER 0, 1, 1, 0, 0
 	.endm
 	.macro SAVE_C_REGS_EXCEPT_RCX_R891011
-	SAVE_C_REGS_HELPER 0, 1, 0, 0
+	SAVE_C_REGS_HELPER 0, 1, 0, 0, 0
+	.endm
+	.macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11
+	SAVE_C_REGS_HELPER 0, 0, 0, 1, 0
 	.endm
 
 	.macro SAVE_EXTRA_REGS offset=0
@@ -179,6 +184,9 @@
 	.macro RESTORE_C_REGS_EXCEPT_R11
 	RESTORE_C_REGS_HELPER 1,1,0,1,1
 	.endm
+	.macro RESTORE_C_REGS_EXCEPT_RCX_R11
+	RESTORE_C_REGS_HELPER 1,0,0,1,1
+	.endm
 	.macro RESTORE_RSI_RDI
 	RESTORE_C_REGS_HELPER 0,0,0,0,0
 	.endm