powerpc/powernv: Provide a way to force a core into SMT4 mode

POWER9 processors up to and including "Nimbus" v2.2 have hardware
bugs relating to transactional memory and thread reconfiguration.
One of these bugs has a workaround which is to get the core into
SMT4 state temporarily.  This workaround is only needed when
running bare-metal.

This patch provides a function which gets the core into SMT4 mode
by preventing threads from going to a stop state, and waking up
those which are already in a stop state.  Once at least 3 threads
are not in a stop state, the core will be in SMT4 and we can
continue.

To do this, we add a "dont_stop" flag to the paca to tell the
thread not to go into a stop state.  If this flag is set,
power9_idle_stop() just returns immediately with a return value
of 0.  The pnv_power9_force_smt4_catch() function does the following:

1. Set the dont_stop flag for each thread in the core, except
   ourselves (in fact we use an atomic_inc() in case more than
   one thread is calling this function concurrently).
2. See how many threads are awake, indicated by their
   requested_psscr field in the paca being 0.  If this is at
   least 3, skip to step 5.
3. Send a doorbell interrupt to each thread that was seen as
   being in a stop state in step 2.
4. Until at least 3 threads are awake, scan the threads to which
   we sent a doorbell interrupt and check if they are awake now.

This relies on the following properties:

- Once dont_stop is non-zero, requested_psccr can't go from zero to
  non-zero, except transiently (and without the thread doing stop).
- requested_psscr being zero guarantees that the thread isn't in
  a state-losing stop state where thread reconfiguration could occur.
- Doing stop with a PSSCR value of 0 won't be a state-losing stop
  and thus won't allow thread reconfiguration.
- Once threads_per_core/2 + 1 (i.e. 3) threads are awake, the core
  must be in SMT4 mode, since SMT modes are powers of 2.

This does add a sync to power9_idle_stop(), which is necessary to
provide the correct ordering between setting requested_psscr and
checking dont_stop.  The overhead of the sync should be unnoticeable
compared to the latency of going into and out of a stop state.

Because some objected to incurring this extra latency on systems where
the XER[SO] bug is not relevant, I have put the test in
power9_idle_stop inside a feature section.  This means that
pnv_power9_force_smt4_catch() WILL NOT WORK correctly on systems
without the CPU_FTR_P9_TM_XER_SO_BUG feature bit set, and will
probably hang the system.

In order to cater for uses where the caller has an operation that
has to be done while the core is in SMT4, the core continues to be
kept in SMT4 after pnv_power9_force_smt4_catch() function returns,
until the pnv_power9_force_smt4_release() function is called.
It undoes the effect of step 1 above and allows the other threads
to go into a stop state.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

6 files changed, 110 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 7330150bfe34..4e14d2304d5f 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -126,4 +126,7 @@ extern int __ucmpdi2(u64, u64);
 void _mcount(void);
 unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
 
+void pnv_power9_force_smt4_catch(void);
+void pnv_power9_force_smt4_release(void);
+
 #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index b62c31037cad..4803cc1b011b 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -32,6 +32,7 @@
 #include <asm/accounting.h>
 #include <asm/hmi.h>
 #include <asm/cpuidle.h>
+#include <asm/atomic.h>
 
 register struct paca_struct *local_paca asm("r13");
 
@@ -177,6 +178,8 @@ struct paca_struct {
 	u8 thread_mask;
 	/* Mask to denote subcore sibling threads */
 	u8 subcore_sibling_mask;
+	/* Flag to request this thread not to stop */
+	atomic_t dont_stop;
 	/*
 	 * Pointer to an array which contains pointer
 	 * to the sibling threads' paca.
diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h
index dc5f6a5d4575..d1c2d2e658cf 100644
--- a/arch/powerpc/include/asm/powernv.h
+++ b/arch/powerpc/include/asm/powernv.h
@@ -40,6 +40,7 @@ static inline int pnv_npu2_handle_fault(struct npu_context *context,
 }
 
 static inline void pnv_tm_init(void) { }
+static inline void pnv_power9_force_smt4(void) { }
 #endif
 
 #endif /* _ASM_POWERNV_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index ea5eb91b836e..dbefe30d4daa 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -759,6 +759,7 @@ int main(void)
 	OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask);
 	OFFSET(PACA_SIBLING_PACA_PTRS, paca_struct, thread_sibling_pacas);
 	OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr);
+	OFFSET(PACA_DONT_STOP, paca_struct, dont_stop);
 #define STOP_SPR(x, f)	OFFSET(x, paca_struct, stop_sprs.f)
 	STOP_SPR(STOP_PID, pid);
 	STOP_SPR(STOP_LDBAR, ldbar);
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 01e1c1997893..89157cf452e3 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -339,6 +339,7 @@ power_enter_stop:
 	bne	 .Lhandle_esl_ec_set
 	PPC_STOP
 	li	r3,0  /* Since we didn't lose state, return 0 */
+	std	r3, PACA_REQ_PSSCR(r13)
 
 	/*
 	 * pnv_wakeup_noloss() expects r12 to contain the SRR1 value so
@@ -429,11 +430,29 @@ ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_ARCH_207S, 66);		\
  * r3 contains desired PSSCR register value.
  */
 _GLOBAL(power9_idle_stop)
+BEGIN_FTR_SECTION
+	lwz	r5, PACA_DONT_STOP(r13)
+	cmpwi	r5, 0
+	bne	1f
 	std	r3, PACA_REQ_PSSCR(r13)
+	sync
+	lwz	r5, PACA_DONT_STOP(r13)
+	cmpwi	r5, 0
+	bne	1f
+END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 	mtspr 	SPRN_PSSCR,r3
 	LOAD_REG_ADDR(r4,power_enter_stop)
 	b	pnv_powersave_common
 	/* No return */
+1:
+	/*
+	 * We get here when TM / thread reconfiguration bug workaround
+	 * code wants to get the CPU into SMT4 mode, and therefore
+	 * we are being asked not to stop.
+	 */
+	li	r3, 0
+	std	r3, PACA_REQ_PSSCR(r13)
+	blr		/* return 0 for wakeup cause / SRR1 value */
 
 /*
  * On waking up from stop 0,1,2 with ESL=1 on POWER9 DD1,
@@ -584,6 +603,8 @@ FTR_SECTION_ELSE_NESTED(71)
 	mfspr	r5, SPRN_PSSCR
 	rldicl  r5,r5,4,60
 ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_POWER9_DD1, 71)
+	li	r0, 0		/* clear requested_psscr to say we're awake */
+	std	r0, PACA_REQ_PSSCR(r13)
 	cmpd	cr4,r5,r4
 	bge	cr4,pnv_wakeup_tb_loss /* returns to caller */
 
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 443d5ca71995..99a760eae964 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -24,6 +24,7 @@
 #include <asm/code-patching.h>
 #include <asm/smp.h>
 #include <asm/runlatch.h>
+#include <asm/dbell.h>
 
 #include "powernv.h"
 #include "subcore.h"
@@ -387,6 +388,86 @@ void power9_idle(void)
 	power9_idle_type(pnv_default_stop_val, pnv_default_stop_mask);
 }
 
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+/*
+ * This is used in working around bugs in thread reconfiguration
+ * on POWER9 (at least up to Nimbus DD2.2) relating to transactional
+ * memory and the way that XER[SO] is checkpointed.
+ * This function forces the core into SMT4 in order by asking
+ * all other threads not to stop, and sending a message to any
+ * that are in a stop state.
+ * Must be called with preemption disabled.
+ *
+ * DO NOT call this unless cpu_has_feature(CPU_FTR_P9_TM_XER_SO_BUG) is
+ * true; otherwise this function will hang the system, due to the
+ * optimization in power9_idle_stop.
+ */
+void pnv_power9_force_smt4_catch(void)
+{
+	int cpu, cpu0, thr;
+	struct paca_struct *tpaca;
+	int awake_threads = 1;		/* this thread is awake */
+	int poke_threads = 0;
+	int need_awake = threads_per_core;
+
+	cpu = smp_processor_id();
+	cpu0 = cpu & ~(threads_per_core - 1);
+	tpaca = &paca[cpu0];
+	for (thr = 0; thr < threads_per_core; ++thr) {
+		if (cpu != cpu0 + thr)
+			atomic_inc(&tpaca[thr].dont_stop);
+	}
+	/* order setting dont_stop vs testing requested_psscr */
+	mb();
+	for (thr = 0; thr < threads_per_core; ++thr) {
+		if (!tpaca[thr].requested_psscr)
+			++awake_threads;
+		else
+			poke_threads |= (1 << thr);
+	}
+
+	/* If at least 3 threads are awake, the core is in SMT4 already */
+	if (awake_threads < need_awake) {
+		/* We have to wake some threads; we'll use msgsnd */
+		for (thr = 0; thr < threads_per_core; ++thr) {
+			if (poke_threads & (1 << thr)) {
+				ppc_msgsnd_sync();
+				ppc_msgsnd(PPC_DBELL_MSGTYPE, 0,
+					   tpaca[thr].hw_cpu_id);
+			}
+		}
+		/* now spin until at least 3 threads are awake */
+		do {
+			for (thr = 0; thr < threads_per_core; ++thr) {
+				if ((poke_threads & (1 << thr)) &&
+				    !tpaca[thr].requested_psscr) {
+					++awake_threads;
+					poke_threads &= ~(1 << thr);
+				}
+			}
+		} while (awake_threads < need_awake);
+	}
+}
+EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_catch);
+
+void pnv_power9_force_smt4_release(void)
+{
+	int cpu, cpu0, thr;
+	struct paca_struct *tpaca;
+
+	cpu = smp_processor_id();
+	cpu0 = cpu & ~(threads_per_core - 1);
+	tpaca = &paca[cpu0];
+
+	/* clear all the dont_stop flags */
+	for (thr = 0; thr < threads_per_core; ++thr) {
+		if (cpu != cpu0 + thr)
+			atomic_dec(&tpaca[thr].dont_stop);
+	}
+}
+EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_release);
+#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
+
 #ifdef CONFIG_HOTPLUG_CPU
 static void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val)
 {