powerpc/32s: Do kuep_lock() and kuep_unlock() in assembly

When interrupt and syscall entries where converted to C, KUEP locking
and unlocking was also converted. It improved performance by unrolling
the loop, and allowed easily implementing boot time deactivation of
KUEP.

However, null_syscall selftest shows that KUEP is still heavy
(361 cycles with KUEP, 212 cycles without).

A way to improve more is to group 'mtsr's together, instead of
repeating 'addi' + 'mtsr' several times.

In order to do that, more registers need to be available. In C, GCC
will always be able to provide the requested number of registers, but
at the cost of saving some data on the stack, which is counter
performant here.

So let's do it in assembly, when we have full control of which
register can be used. It also has the advantage of locking earlier
and unlocking later and it helps GCC generating less tricky code.
The only drawback is to make boot time deactivation less straight
forward and require 'hand' instruction patching.

Group 'mtsr's by 4.

With this change, null_syscall selftest reports 336 cycles. Without
the change it was 361 cycles, that's a 7% reduction.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/115cb279e9b9948dfd93a065e047081c59e3a2a6.1634627931.git.christophe.leroy@csgroup.eu

4 files changed, 41 insertions, 3 deletions

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index c62dd9815965..0756829b2f7f 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -73,6 +73,34 @@ prepare_transfer_to_handler:
 _ASM_NOKPROBE_SYMBOL(prepare_transfer_to_handler)
 #endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_E500 */
 
+#if defined(CONFIG_PPC_KUEP) && defined(CONFIG_PPC_BOOK3S_32)
+	.globl	__kuep_lock
+__kuep_lock:
+	mfsr    r9,0
+	rlwinm  r9,r9,0,8,3
+	oris    r9,r9,SR_NX@h
+	update_user_segments_by_4 r9, r10, r11, r12
+	blr
+
+__kuep_unlock:
+	mfsr    r9,0
+	rlwinm  r9,r9,0,8,2
+	update_user_segments_by_4 r9, r10, r11, r12
+	blr
+
+.macro	kuep_lock
+	bl	__kuep_lock
+.endm
+.macro	kuep_unlock
+	bl	__kuep_unlock
+.endm
+#else
+.macro	kuep_lock
+.endm
+.macro	kuep_unlock
+.endm
+#endif
+
 	.globl	transfer_to_syscall
 transfer_to_syscall:
 	stw	r11, GPR1(r1)
@@ -93,6 +121,7 @@ transfer_to_syscall:
 	SAVE_GPRS(3, 8, r1)
 	addi	r2,r10,-THREAD
 	SAVE_NVGPRS(r1)
+	kuep_lock
 
 	/* Calling convention has r9 = orig r0, r10 = regs */
 	addi	r10,r1,STACK_FRAME_OVERHEAD
@@ -109,6 +138,7 @@ ret_from_syscall:
 	cmplwi	cr0,r5,0
 	bne-	2f
 #endif /* CONFIG_PPC_47x */
+	kuep_unlock
 	lwz	r4,_LINK(r1)
 	lwz	r5,_CCR(r1)
 	mtlr	r4
@@ -272,6 +302,7 @@ interrupt_return:
 	beq	.Lkernel_interrupt_return
 	bl	interrupt_exit_user_prepare
 	cmpwi	r3,0
+	kuep_unlock
 	bne-	.Lrestore_nvgprs
 
 .Lfast_user_interrupt_return:
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 25887303651a..40d23a863b28 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -135,6 +135,12 @@ _ASM_NOKPROBE_SYMBOL(\name\()_virt)
 	andi.	r12,r9,MSR_PR
 	bne	777f
 	bl	prepare_transfer_to_handler
+#ifdef CONFIG_PPC_KUEP
+	b	778f
+777:
+	bl	__kuep_lock
+778:
+#endif
 777:
 #endif
 .endm
diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S
index 68e5c0a7e99d..fa84744d6b24 100644
--- a/arch/powerpc/kernel/head_book3s_32.S
+++ b/arch/powerpc/kernel/head_book3s_32.S
@@ -931,7 +931,11 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 _GLOBAL(load_segment_registers)
 	li	r0, NUM_USER_SEGMENTS /* load up user segment register values */
 	mtctr	r0		/* for context 0 */
+#ifdef CONFIG_PPC_KUEP
+	lis	r3, SR_NX@h	/* Kp = 0, Ks = 0, VSID = 0 */
+#else
 	li	r3, 0		/* Kp = 0, Ks = 0, VSID = 0 */
+#endif
 	li	r4, 0
 3:	mtsrin	r3, r4
 	addi	r3, r3, 0x111	/* increment VSID */
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index 835b626cd476..75dc045bdcb8 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -81,8 +81,6 @@ notrace long system_call_exception(long r3, long r4, long r5,
 {
 	syscall_fn f;
 
-	kuep_lock();
-
 	regs->orig_gpr3 = r3;
 
 	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
@@ -406,7 +404,6 @@ again:
 
 	/* Restore user access locks last */
 	kuap_user_restore(regs);
-	kuep_unlock();
 
 	return ret;
 }