[PATCH 2/2] powerpc: tm: Enable transactional memory (TM) lazily for userspace

[Cyril Bur]

Currently the MSR TM bit is always set if the hardware is TM capable.
This adds extra overhead as it means the TM SPRS (TFHAR, TEXASR and
TFAIR) must be swapped for each process regardless of if they use TM.

For processes that don't use TM the TM MSR bit can be turned off
allowing the kernel to avoid the expensive swap of the TM registers.

A TM unavailable exception will occur if a thread does use TM and the
kernel will enable MSR_TM and leave it so for some time afterwards.

Signed-off-by: Cyril Bur <cyrilbur at gmail.com>
---
 arch/powerpc/include/asm/processor.h |  1 +
 arch/powerpc/kernel/process.c        | 28 +++++++++++++++++++++++-----
 arch/powerpc/kernel/traps.c          |  9 +++++++++
 3 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index b3e0cfc..c07c31b 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -257,6 +257,7 @@ struct thread_struct {
 	int		used_spe;	/* set if process has used spe */
 #endif /* CONFIG_SPE */
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	u8	load_tm;
 	u64		tm_tfhar;	/* Transaction fail handler addr */
 	u64		tm_texasr;	/* Transaction exception & summary */
 	u64		tm_tfiar;	/* Transaction fail instr address reg */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 11f7a64..cd81dd4 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -811,6 +811,12 @@ static inline bool hw_brk_match(struct arch_hw_breakpoint *a,
 }
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+
+static inline bool tm_enabled(struct task_struct *tsk)
+{
+	return tsk && tsk->thread.regs && (tsk->thread.regs->msr & MSR_TM);
+}
+
 static void tm_reclaim_thread(struct thread_struct *thr,
 			      struct thread_info *ti, uint8_t cause)
 {
@@ -891,6 +897,9 @@ void tm_recheckpoint(struct thread_struct *thread,
 {
 	unsigned long flags;
 
+	if (!(thread->regs->msr & MSR_TM))
+		return;
+
 	/* We really can't be interrupted here as the TEXASR registers can't
 	 * change and later in the trecheckpoint code, we have a userspace R1.
 	 * So let's hard disable over this region.
@@ -923,7 +932,7 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new)
 	 * unavailable later, we are unable to determine which set of FP regs
 	 * need to be restored.
 	 */
-	if (!new->thread.regs)
+	if (!tm_enabled(new))
 		return;
 
 	if (!MSR_TM_ACTIVE(new->thread.regs->msr)){
@@ -954,8 +963,16 @@ static inline void __switch_to_tm(struct task_struct *prev,
 		struct task_struct *new)
 {
 	if (cpu_has_feature(CPU_FTR_TM)) {
-		tm_enable();
-		tm_reclaim_task(prev);
+		if (tm_enabled(prev) || tm_enabled(new))
+			tm_enable();
+
+		if (tm_enabled(prev)) {
+			prev->thread.load_tm++;
+			tm_reclaim_task(prev);
+			if (!MSR_TM_ACTIVE(prev->thread.regs->msr) && prev->thread.load_tm == 0)
+				prev->thread.regs->msr &= ~MSR_TM;
+		}
+
 		tm_recheckpoint_new_task(new);
 	}
 }
@@ -1392,6 +1409,9 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	 * transitions the CPU out of TM mode.  Hence we need to call
 	 * tm_recheckpoint_new_task() (on the same task) to restore the
 	 * checkpointed state back and the TM mode.
+	 *
+	 * Can't pass dst because it isn't ready. Doesn't matter, passing
+	 * dst is only important for __switch_to()
 	 */
 	__switch_to_tm(src, src);
 
@@ -1635,8 +1655,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.used_spe = 0;
 #endif /* CONFIG_SPE */
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	if (cpu_has_feature(CPU_FTR_TM))
-		regs->msr |= MSR_TM;
 	current->thread.tm_tfhar = 0;
 	current->thread.tm_texasr = 0;
 	current->thread.tm_tfiar = 0;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index cd40130..9bb3895 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1374,6 +1374,15 @@ void vsx_unavailable_exception(struct pt_regs *regs)
 #ifdef CONFIG_PPC64
 static void tm_unavailable(struct pt_regs *regs)
 {
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (user_mode(regs)) {
+		current->thread.load_tm++;
+		regs->msr |= MSR_TM;
+		tm_enable();
+		tm_restore_sprs(&current->thread);
+		return;
+	}
+#endif
 	pr_emerg("Unrecoverable TM Unavailable Exception "
 			"%lx at %lx\n", regs->trap, regs->nip);
 	die("Unrecoverable TM Unavailable Exception", regs, SIGABRT);
-- 
2.9.3