powerpc/32s: Save content of sr0 to avoid 'mfsr'

Calling 'mfsr' to get the content of segment registers is heavy,
in addition it requires clearing of the 'reserved' bits.

In order to avoid this operation, save it in mm context and in
thread struct.

The saved sr0 is the one used by kernel, this means that on
locking entry it can be used as is.

For unlocking, the only thing to do is to clear SR_NX.

This improves null_syscall selftest by 12 cycles, ie 4%.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/b02baf2ed8f09bad910dfaeeb7353b2ae6830525.1634627931.git.christophe.leroy@csgroup.eu

8 files changed, 33 insertions, 14 deletions

diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h
index e2f7ccc13edb..7be27862329f 100644
--- a/arch/powerpc/include/asm/book3s/32/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h
@@ -175,9 +175,14 @@ struct hash_pte {
 
 typedef struct {
 	unsigned long id;
+	unsigned long sr0;
 	void __user *vdso;
 } mm_context_t;
 
+#ifdef CONFIG_PPC_KUEP
+#define INIT_MM_CONTEXT(mm) .context.sr0 = SR_NX
+#endif
+
 void update_bats(void);
 static inline void cleanup_cpu_mmu_context(void) { }
 
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 978a80308466..fe1ef1d7523b 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -157,6 +157,7 @@ struct thread_struct {
 #ifdef CONFIG_PPC_BOOK3S_32
 	unsigned long	r0, r3, r4, r5, r6, r8, r9, r11;
 	unsigned long	lr, ctr;
+	unsigned long	sr0;
 #endif
 #endif /* CONFIG_PPC32 */
 	/* Debug Registers */
@@ -278,6 +279,12 @@ struct thread_struct {
 #define SPEFSCR_INIT
 #endif
 
+#ifdef CONFIG_PPC_BOOK3S_32
+#define SR0_INIT	.sr0 = IS_ENABLED(CONFIG_PPC_KUEP) ? SR_NX : 0,
+#else
+#define SR0_INIT
+#endif
+
 #if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
 #define INIT_THREAD { \
 	.ksp = INIT_SP, \
@@ -285,6 +292,7 @@ struct thread_struct {
 	.kuap = ~0UL, /* KUAP_NONE */ \
 	.fpexc_mode = MSR_FE0 | MSR_FE1, \
 	SPEFSCR_INIT \
+	SR0_INIT \
 }
 #elif defined(CONFIG_PPC32)
 #define INIT_THREAD { \
@@ -292,6 +300,7 @@ struct thread_struct {
 	.pgdir = swapper_pg_dir, \
 	.fpexc_mode = MSR_FE0 | MSR_FE1, \
 	SPEFSCR_INIT \
+	SR0_INIT \
 }
 #else
 #define INIT_THREAD  { \
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index b823f484c640..cf3436b7b166 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -139,6 +139,7 @@ int main(void)
 	OFFSET(THR11, thread_struct, r11);
 	OFFSET(THLR, thread_struct, lr);
 	OFFSET(THCTR, thread_struct, ctr);
+	OFFSET(THSR0, thread_struct, sr0);
 #endif
 #ifdef CONFIG_SPE
 	OFFSET(THREAD_EVR0, thread_struct, evr[0]);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 0756829b2f7f..035bf4f3eb5d 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -76,15 +76,13 @@ _ASM_NOKPROBE_SYMBOL(prepare_transfer_to_handler)
 #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
+	lwz	r9, THREAD+THSR0(r2)
 	update_user_segments_by_4 r9, r10, r11, r12
 	blr
 
 __kuep_unlock:
-	mfsr    r9,0
-	rlwinm  r9,r9,0,8,2
+	lwz	r9, THREAD+THSR0(r2)
+	rlwinm  r9,r9,0,~SR_NX
 	update_user_segments_by_4 r9, r10, r11, r12
 	blr
 
diff --git a/arch/powerpc/mm/book3s32/kuap.c b/arch/powerpc/mm/book3s32/kuap.c
index 0f920f09af57..28676cabb005 100644
--- a/arch/powerpc/mm/book3s32/kuap.c
+++ b/arch/powerpc/mm/book3s32/kuap.c
@@ -20,8 +20,11 @@ EXPORT_SYMBOL(kuap_unlock_all_ool);
 
 void setup_kuap(bool disabled)
 {
-	if (!disabled)
+	if (!disabled) {
 		kuap_lock_all_ool();
+		init_mm.context.sr0 |= SR_KS;
+		current->thread.sr0 |= SR_KS;
+	}
 
 	if (smp_processor_id() != boot_cpuid)
 		return;
diff --git a/arch/powerpc/mm/book3s32/kuep.c b/arch/powerpc/mm/book3s32/kuep.c
index bac1420d028b..78fc48eee510 100644
--- a/arch/powerpc/mm/book3s32/kuep.c
+++ b/arch/powerpc/mm/book3s32/kuep.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <asm/code-patching.h>
 #include <asm/kup.h>
 #include <asm/smp.h>
 
diff --git a/arch/powerpc/mm/book3s32/mmu_context.c b/arch/powerpc/mm/book3s32/mmu_context.c
index e2708e387dc3..269a3eb25a73 100644
--- a/arch/powerpc/mm/book3s32/mmu_context.c
+++ b/arch/powerpc/mm/book3s32/mmu_context.c
@@ -69,6 +69,12 @@ EXPORT_SYMBOL_GPL(__init_new_context);
 int init_new_context(struct task_struct *t, struct mm_struct *mm)
 {
 	mm->context.id = __init_new_context();
+	mm->context.sr0 = CTX_TO_VSID(mm->context.id, 0);
+
+	if (!kuep_is_disabled())
+		mm->context.sr0 |= SR_NX;
+	if (!kuap_is_disabled())
+		mm->context.sr0 |= SR_KS;
 
 	return 0;
 }
@@ -108,20 +114,13 @@ void __init mmu_context_init(void)
 void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
 {
 	long id = next->context.id;
-	unsigned long val;
 
 	if (id < 0)
 		panic("mm_struct %p has no context ID", next);
 
 	isync();
 
-	val = CTX_TO_VSID(id, 0);
-	if (!kuep_is_disabled())
-		val |= SR_NX;
-	if (!kuap_is_disabled())
-		val |= SR_KS;
-
-	update_user_segments(val);
+	update_user_segments(next->context.sr0);
 
 	if (IS_ENABLED(CONFIG_BDI_SWITCH))
 		abatron_pteptrs[1] = next->pgd;
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index 74246536b832..e618d5442a28 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -18,6 +18,9 @@ static inline void switch_mm_pgdir(struct task_struct *tsk,
 {
 	/* 32-bit keeps track of the current PGDIR in the thread struct */
 	tsk->thread.pgdir = mm->pgd;
+#ifdef CONFIG_PPC_BOOK3S_32
+	tsk->thread.sr0 = mm->context.sr0;
+#endif
 }
 #elif defined(CONFIG_PPC_BOOK3E_64)
 static inline void switch_mm_pgdir(struct task_struct *tsk,