KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8

This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip.  Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core.  With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.

Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.

To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread.  In addition we extend the core_info struct to
have information on each subcore.  When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.

Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode.  It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.

This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap.  In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered.  The default is 6.

With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch.  These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.

It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest.  In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path.  In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

arch/powerpc/include/asm/kvm_book3s_asm.h

@@ -25,6 +25,12 @@
 #define XICS_MFRR		0xc
 #define XICS_IPI		2	/* interrupt source # for IPIs */
 
+/* Maximum number of threads per physical core */
+#define MAX_SMT_THREADS		8
+
+/* Maximum number of subcores per physical core */
+#define MAX_SUBCORES		4
+
 #ifdef __ASSEMBLY__
 
 #ifdef CONFIG_KVM_BOOK3S_HANDLER
@@ -65,6 +71,19 @@ kvmppc_resume_\intno:
 
 #else  /*__ASSEMBLY__ */
 
+struct kvmppc_vcore;
+
+/* Struct used for coordinating micro-threading (split-core) mode changes */
+struct kvm_split_mode {
+	unsigned long	rpr;
+	unsigned long	pmmar;
+	unsigned long	ldbar;
+	u8		subcore_size;
+	u8		do_nap;
+	u8		napped[MAX_SMT_THREADS];
+	struct kvmppc_vcore *master_vcs[MAX_SUBCORES];
+};
+
 /*
  * This struct goes in the PACA on 64-bit processors.  It is used
  * to store host state that needs to be saved when we enter a guest
@@ -100,6 +119,7 @@ struct kvmppc_host_state {
 	u64 host_spurr;
 	u64 host_dscr;
 	u64 dec_expires;
+	struct kvm_split_mode *kvm_split_mode;
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	u64 cfar;

arch/powerpc/include/asm/kvm_host.h

@@ -302,6 +302,9 @@ struct kvmppc_vcore {
 #define VCORE_EXIT_MAP(vc)	((vc)->entry_exit_map >> 8)
 #define VCORE_IS_EXITING(vc)	(VCORE_EXIT_MAP(vc) != 0)
 
+/* This bit is used when a vcore exit is triggered from outside the vcore */
+#define VCORE_EXIT_REQ		0x10000
+
 /*
  * Values for vcore_state.
  * Note that these are arranged such that lower values

arch/powerpc/kernel/asm-offsets.c

@@ -676,7 +676,14 @@ int main(void)
 	HSTATE_FIELD(HSTATE_DSCR, host_dscr);
 	HSTATE_FIELD(HSTATE_DABR, dabr);
 	HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
+	HSTATE_FIELD(HSTATE_SPLIT_MODE, kvm_split_mode);
 	DEFINE(IPI_PRIORITY, IPI_PRIORITY);
+	DEFINE(KVM_SPLIT_RPR, offsetof(struct kvm_split_mode, rpr));
+	DEFINE(KVM_SPLIT_PMMAR, offsetof(struct kvm_split_mode, pmmar));
+	DEFINE(KVM_SPLIT_LDBAR, offsetof(struct kvm_split_mode, ldbar));
+	DEFINE(KVM_SPLIT_SIZE, offsetof(struct kvm_split_mode, subcore_size));
+	DEFINE(KVM_SPLIT_DO_NAP, offsetof(struct kvm_split_mode, do_nap));
+	DEFINE(KVM_SPLIT_NAPPED, offsetof(struct kvm_split_mode, napped));
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #ifdef CONFIG_PPC_BOOK3S_64

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -239,7 +239,8 @@ void kvmhv_commence_exit(int trap)
 {
 	struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
 	int ptid = local_paca->kvm_hstate.ptid;
-	int me, ee;
+	struct kvm_split_mode *sip = local_paca->kvm_hstate.kvm_split_mode;
+	int me, ee, i;
 
 	/* Set our bit in the threads-exiting-guest map in the 0xff00
 	   bits of vcore->entry_exit_map */
@@ -259,4 +260,26 @@ void kvmhv_commence_exit(int trap)
 	 */
 	if (trap != BOOK3S_INTERRUPT_HV_DECREMENTER)
 		kvmhv_interrupt_vcore(vc, ee & ~(1 << ptid));
+
+	/*
+	 * If we are doing dynamic micro-threading, interrupt the other
+	 * subcores to pull them out of their guests too.
+	 */
+	if (!sip)
+		return;
+
+	for (i = 0; i < MAX_SUBCORES; ++i) {
+		vc = sip->master_vcs[i];
+		if (!vc)
+			break;
+		do {
+			ee = vc->entry_exit_map;
+			/* Already asked to exit? */
+			if ((ee >> 8) != 0)
+				break;
+		} while (cmpxchg(&vc->entry_exit_map, ee,
+				 ee | VCORE_EXIT_REQ) != ee);
+		if ((ee >> 8) == 0)
+			kvmhv_interrupt_vcore(vc, ee);
+	}
 }

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -128,6 +128,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	subf	r4, r4, r3
 	mtspr	SPRN_DEC, r4
 
+	/* hwthread_req may have got set by cede or no vcpu, so clear it */
+	li	r0, 0
+	stb	r0, HSTATE_HWTHREAD_REQ(r13)
+
 	/*
 	 * For external and machine check interrupts, we need
 	 * to call the Linux handler to process the interrupt.
@@ -215,7 +219,6 @@ kvm_novcpu_wakeup:
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	li	r0, 0
 	stb	r0, HSTATE_NAPPING(r13)
-	stb	r0, HSTATE_HWTHREAD_REQ(r13)
 
 	/* check the wake reason */
 	bl	kvmppc_check_wake_reason
@@ -315,10 +318,10 @@ kvm_start_guest:
 	cmpdi	r3, 0
 	bge	kvm_no_guest
 
-	/* get vcpu pointer, NULL if we have no vcpu to run */
-	ld	r4,HSTATE_KVM_VCPU(r13)
-	cmpdi	r4,0
-	/* if we have no vcpu to run, go back to sleep */
+	/* get vcore pointer, NULL if we have nothing to run */
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	cmpdi	r5,0
+	/* if we have no vcore to run, go back to sleep */
 	beq	kvm_no_guest
 
 kvm_secondary_got_guest:
@@ -327,21 +330,42 @@ kvm_secondary_got_guest:
 	ld	r6, PACA_DSCR_DEFAULT(r13)
 	std	r6, HSTATE_DSCR(r13)
 
-	/* Order load of vcore, ptid etc. after load of vcpu */
+	/* On thread 0 of a subcore, set HDEC to max */
+	lbz	r4, HSTATE_PTID(r13)
+	cmpwi	r4, 0
+	bne	63f
+	lis	r6, 0x7fff
+	ori	r6, r6, 0xffff
+	mtspr	SPRN_HDEC, r6
+	/* and set per-LPAR registers, if doing dynamic micro-threading */
+	ld	r6, HSTATE_SPLIT_MODE(r13)
+	cmpdi	r6, 0
+	beq	63f
+	ld	r0, KVM_SPLIT_RPR(r6)
+	mtspr	SPRN_RPR, r0
+	ld	r0, KVM_SPLIT_PMMAR(r6)
+	mtspr	SPRN_PMMAR, r0
+	ld	r0, KVM_SPLIT_LDBAR(r6)
+	mtspr	SPRN_LDBAR, r0
+	isync
+63:
+	/* Order load of vcpu after load of vcore */
 	lwsync
+	ld	r4, HSTATE_KVM_VCPU(r13)
 	bl	kvmppc_hv_entry
 
 	/* Back from the guest, go back to nap */
-	/* Clear our vcpu pointer so we don't come back in early */
+	/* Clear our vcpu and vcore pointers so we don't come back in early */
 	li	r0, 0
+	std	r0, HSTATE_KVM_VCPU(r13)
 	/*
-	 * Once we clear HSTATE_KVM_VCPU(r13), the code in
+	 * Once we clear HSTATE_KVM_VCORE(r13), the code in
 	 * kvmppc_run_core() is going to assume that all our vcpu
 	 * state is visible in memory.  This lwsync makes sure
 	 * that that is true.
 	 */
 	lwsync
-	std	r0, HSTATE_KVM_VCPU(r13)
+	std	r0, HSTATE_KVM_VCORE(r13)
 
 /*
  * At this point we have finished executing in the guest.
@@ -374,16 +398,63 @@ kvm_no_guest:
 	b	power7_wakeup_loss
 
 53:	HMT_LOW
-	ld	r4, HSTATE_KVM_VCPU(r13)
-	cmpdi	r4, 0
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	cmpdi	r5, 0
+	bne	60f
+	ld	r3, HSTATE_SPLIT_MODE(r13)
+	cmpdi	r3, 0
+	beq	kvm_no_guest
+	lbz	r0, KVM_SPLIT_DO_NAP(r3)
+	cmpwi	r0, 0
 	beq	kvm_no_guest
 	HMT_MEDIUM
+	b	kvm_unsplit_nap
+60:	HMT_MEDIUM
 	b	kvm_secondary_got_guest
 
 54:	li	r0, KVM_HWTHREAD_IN_KVM
 	stb	r0, HSTATE_HWTHREAD_STATE(r13)
 	b	kvm_no_guest
 
+/*
+ * Here the primary thread is trying to return the core to
+ * whole-core mode, so we need to nap.
+ */
+kvm_unsplit_nap:
+	/* clear any pending message */
+BEGIN_FTR_SECTION
+	lis	r6, (PPC_DBELL_SERVER << (63-36))@h
+	PPC_MSGCLR(6)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	/* Set kvm_split_mode.napped[tid] = 1 */
+	ld	r3, HSTATE_SPLIT_MODE(r13)
+	li	r0, 1
+	lhz	r4, PACAPACAINDEX(r13)
+	clrldi	r4, r4, 61	/* micro-threading => P8 => 8 threads/core */
+	addi	r4, r4, KVM_SPLIT_NAPPED
+	stbx	r0, r3, r4
+	/* Check the do_nap flag again after setting napped[] */
+	sync
+	lbz	r0, KVM_SPLIT_DO_NAP(r3)
+	cmpwi	r0, 0
+	beq	57f
+	li	r3, (LPCR_PECEDH | LPCR_PECE0) >> 4
+	mfspr	r4, SPRN_LPCR
+	rlwimi	r4, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
+	mtspr	SPRN_LPCR, r4
+	isync
+	std	r0, HSTATE_SCRATCH0(r13)
+	ptesync
+	ld	r0, HSTATE_SCRATCH0(r13)
+1:	cmpd	r0, r0
+	bne	1b
+	nap
+	b	.
+
+57:	li	r0, 0
+	stbx	r0, r3, r4
+	b	kvm_no_guest
+
 /******************************************************************************
  *                                                                            *
  *                               Entry code                                   *
@@ -854,7 +925,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	cmpwi	r0, 0
 	bne	21f
 	HMT_LOW
-20:	lbz	r0, VCORE_IN_GUEST(r5)
+20:	lwz	r3, VCORE_ENTRY_EXIT(r5)
+	cmpwi	r3, 0x100
+	bge	no_switch_exit
+	lbz	r0, VCORE_IN_GUEST(r5)
 	cmpwi	r0, 0
 	beq	20b
 	HMT_MEDIUM
@@ -985,9 +1059,13 @@ secondary_too_late:
 #endif
 11:	b	kvmhv_switch_to_host
 
+no_switch_exit:
+	HMT_MEDIUM
+	li	r12, 0
+	b	12f
 hdec_soon:
 	li	r12, BOOK3S_INTERRUPT_HV_DECREMENTER
-	stw	r12, VCPU_TRAP(r4)
+12:	stw	r12, VCPU_TRAP(r4)
 	mr	r9, r4
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
 	addi	r3, r4, VCPU_TB_RMEXIT
@@ -1545,12 +1623,17 @@ kvmhv_switch_to_host:
 
 	/* Primary thread waits for all the secondaries to exit guest */
 15:	lwz	r3,VCORE_ENTRY_EXIT(r5)
-	srwi	r0,r3,8
+	rlwinm	r0,r3,32-8,0xff
 	clrldi	r3,r3,56
 	cmpw	r3,r0
 	bne	15b
 	isync
 
+	/* Did we actually switch to the guest at all? */
+	lbz	r6, VCORE_IN_GUEST(r5)
+	cmpwi	r6, 0
+	beq	19f
+
 	/* Primary thread switches back to host partition */
 	ld	r6,KVM_HOST_SDR1(r4)
 	lwz	r7,KVM_HOST_LPID(r4)
@@ -1594,7 +1677,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 18:
 	/* Signal secondary CPUs to continue */
 	stb	r0,VCORE_IN_GUEST(r5)
-	lis	r8,0x7fff		/* MAX_INT@h */
+19:	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
 
 16:	ld	r8,KVM_HOST_LPCR(r4)