s390: add options to change branch prediction behaviour for the kernel

Add the PPA instruction to the system entry and exit path to switch
the kernel to a different branch prediction behaviour. The instructions
are added via CPU alternatives and can be disabled with the "nospec"
or the "nobp=0" kernel parameter. If the default behaviour selected
with CONFIG_KERNEL_NOBP is set to "n" then the "nobp=1" parameter can be
used to enable the changed kernel branch prediction.

Acked-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 5d87eda..e6d7550 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -159,6 +159,34 @@
 		tm	off+\addr, \mask
 	.endm
 
+	.macro BPOFF
+	.pushsection .altinstr_replacement, "ax"
+660:	.long	0xb2e8c000
+	.popsection
+661:	.long	0x47000000
+	.pushsection .altinstructions, "a"
+	.long 661b - .
+	.long 660b - .
+	.word 82
+	.byte 4
+	.byte 4
+	.popsection
+	.endm
+
+	.macro BPON
+	.pushsection .altinstr_replacement, "ax"
+662:	.long	0xb2e8d000
+	.popsection
+663:	.long	0x47000000
+	.pushsection .altinstructions, "a"
+	.long 663b - .
+	.long 662b - .
+	.word 82
+	.byte 4
+	.byte 4
+	.popsection
+	.endm
+
 	.section .kprobes.text, "ax"
 .Ldummy:
 	/*
@@ -171,6 +199,11 @@
 	 */
 	nop	0
 
+ENTRY(__bpon)
+	.globl __bpon
+	BPON
+	br	%r14
+
 /*
  * Scheduler resume function, called by switch_to
  *  gpr2 = (task_struct *) prev
@@ -226,8 +259,11 @@
 	jnz	.Lsie_skip
 	TSTMSK	__LC_CPU_FLAGS,_CIF_FPU
 	jo	.Lsie_skip			# exit if fp/vx regs changed
+	BPON
 .Lsie_entry:
 	sie	0(%r14)
+.Lsie_exit:
+	BPOFF
 .Lsie_skip:
 	ni	__SIE_PROG0C+3(%r14),0xfe	# no longer in SIE
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
@@ -279,6 +315,7 @@
 	stpt	__LC_SYNC_ENTER_TIMER
 .Lsysc_stmg:
 	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
+	BPOFF
 	lg	%r12,__LC_CURRENT
 	lghi	%r13,__TASK_thread
 	lghi	%r14,_PIF_SYSCALL
@@ -325,6 +362,7 @@
 	jnz	.Lsysc_work			# check for work
 	TSTMSK	__LC_CPU_FLAGS,_CIF_WORK
 	jnz	.Lsysc_work
+	BPON
 .Lsysc_restore:
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
@@ -530,6 +568,7 @@
 
 ENTRY(pgm_check_handler)
 	stpt	__LC_SYNC_ENTER_TIMER
+	BPOFF
 	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
 	lg	%r10,__LC_LAST_BREAK
 	lg	%r12,__LC_CURRENT
@@ -637,6 +676,7 @@
 ENTRY(io_int_handler)
 	STCK	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
+	BPOFF
 	stmg	%r8,%r15,__LC_SAVE_AREA_ASYNC
 	lg	%r12,__LC_CURRENT
 	larl	%r13,cleanup_critical
@@ -687,9 +727,13 @@
 	lg	%r14,__LC_VDSO_PER_CPU
 	lmg	%r0,%r10,__PT_R0(%r11)
 	mvc	__LC_RETURN_PSW(16),__PT_PSW(%r11)
+	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
+	jno	.Lio_exit_kernel
+	BPON
 .Lio_exit_timer:
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
+.Lio_exit_kernel:
 	lmg	%r11,%r15,__PT_R11(%r11)
 	lpswe	__LC_RETURN_PSW
 .Lio_done:
@@ -860,6 +904,7 @@
 ENTRY(ext_int_handler)
 	STCK	__LC_INT_CLOCK
 	stpt	__LC_ASYNC_ENTER_TIMER
+	BPOFF
 	stmg	%r8,%r15,__LC_SAVE_AREA_ASYNC
 	lg	%r12,__LC_CURRENT
 	larl	%r13,cleanup_critical
@@ -908,6 +953,7 @@
 .Lpsw_idle_stcctm:
 #endif
 	oi	__LC_CPU_FLAGS+7,_CIF_ENABLED_WAIT
+	BPON
 	STCK	__CLOCK_IDLE_ENTER(%r2)
 	stpt	__TIMER_IDLE_ENTER(%r2)
 .Lpsw_idle_lpsw:
@@ -1008,6 +1054,7 @@
  */
 ENTRY(mcck_int_handler)
 	STCK	__LC_MCCK_CLOCK
+	BPOFF
 	la	%r1,4095		# validate r1
 	spt	__LC_CPU_TIMER_SAVE_AREA-4095(%r1)	# validate cpu timer
 	sckc	__LC_CLOCK_COMPARATOR			# validate comparator
@@ -1118,6 +1165,7 @@
 	mvc	__LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW
 	tm	__LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
 	jno	0f
+	BPON
 	stpt	__LC_EXIT_TIMER
 	mvc	__VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
 0:	lmg	%r11,%r15,__PT_R11(%r11)