Merge branch 'for-queue' of https://github.com/agraf/linux-2.6 into queue

* 'for-queue' of https://github.com/agraf/linux-2.6:
  PPC: ePAPR: Convert hcall header to uapi (round 2)
  KVM: PPC: Book3S HV: Fix thinko in try_lock_hpte()
  KVM: PPC: Book3S HV: Allow DTL to be set to address 0, length 0
  KVM: PPC: Book3S HV: Fix accounting of stolen time
  KVM: PPC: Book3S HV: Run virtual core whenever any vcpus in it can run
  KVM: PPC: Book3S HV: Fixes for late-joining threads
  KVM: PPC: Book3s HV: Don't access runnable threads list without vcore lock
  KVM: PPC: Book3S HV: Fix some races in starting secondary threads
  KVM: PPC: Book3S HV: Allow KVM guests to stop secondary threads coming online
  PPC: ePAPR: Convert header to uapi
  KVM: PPC: Move mtspr/mfspr emulation into own functions
  KVM: Documentation: Fix reentry-to-be-consistent paragraph
  KVM: PPC: 44x: fix DCR read/write

Documentation/virtual/kvm/api.txt

@@ -2183,7 +2183,8 @@ executed a memory-mapped I/O instruction which could not be satisfied
 by kvm.  The 'data' member contains the written data if 'is_write' is
 true, and should be filled by application code otherwise.
 
-NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO and KVM_EXIT_OSI, the corresponding
+NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_DCR
+      and KVM_EXIT_PAPR the corresponding
 operations are complete (and guest state is consistent) only after userspace
 has re-entered the kernel with KVM_RUN.  The kernel side will first finish
 incomplete operations and then check for pending signals.  Userspace

arch/powerpc/include/asm/kvm_asm.h

@@ -118,6 +118,7 @@
 
 #define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */
+#define RESUME_FLAG_ARCH1	(1<<2)
 
 #define RESUME_GUEST            0
 #define RESUME_GUEST_NV         RESUME_FLAG_NV

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -60,7 +60,7 @@ static inline long try_lock_hpte(unsigned long *hpte, unsigned long bits)
 		     "	ori	%0,%0,%4\n"
 		     "  stdcx.	%0,0,%2\n"
 		     "	beq+	2f\n"
-		     "	li	%1,%3\n"
+		     "	mr	%1,%3\n"
 		     "2:	isync"
 		     : "=&r" (tmp), "=&r" (old)
 		     : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK)

arch/powerpc/include/asm/kvm_host.h

@@ -289,9 +289,10 @@ struct kvmppc_vcore {
 
 /* Values for vcore_state */
 #define VCORE_INACTIVE	0
-#define VCORE_RUNNING	1
-#define VCORE_EXITING	2
-#define VCORE_SLEEPING	3
+#define VCORE_SLEEPING	1
+#define VCORE_STARTING	2
+#define VCORE_RUNNING	3
+#define VCORE_EXITING	4
 
 /*
  * Struct used to manage memory for a virtual processor area
@@ -558,13 +559,17 @@ struct kvm_vcpu_arch {
 	unsigned long dtl_index;
 	u64 stolen_logged;
 	struct kvmppc_vpa slb_shadow;
+
+	spinlock_t tbacct_lock;
+	u64 busy_stolen;
+	u64 busy_preempt;
 #endif
 };
 
 /* Values for vcpu->arch.state */
-#define KVMPPC_VCPU_STOPPED		0
-#define KVMPPC_VCPU_BUSY_IN_HOST	1
-#define KVMPPC_VCPU_RUNNABLE		2
+#define KVMPPC_VCPU_NOTREADY		0
+#define KVMPPC_VCPU_RUNNABLE		1
+#define KVMPPC_VCPU_BUSY_IN_HOST	2
 
 /* Values for vcpu->arch.io_gpr */
 #define KVM_MMIO_REG_MASK	0x001f

arch/powerpc/include/asm/smp.h

@@ -67,6 +67,14 @@ void generic_mach_cpu_die(void);
 void generic_set_cpu_dead(unsigned int cpu);
 void generic_set_cpu_up(unsigned int cpu);
 int generic_check_cpu_restart(unsigned int cpu);
+
+extern void inhibit_secondary_onlining(void);
+extern void uninhibit_secondary_onlining(void);
+
+#else /* HOTPLUG_CPU */
+static inline void inhibit_secondary_onlining(void) {}
+static inline void uninhibit_secondary_onlining(void) {}
+
 #endif
 
 #ifdef CONFIG_PPC64

arch/powerpc/include/uapi/asm/Kbuild

@@ -7,6 +7,7 @@ header-y += bootx.h
 header-y += byteorder.h
 header-y += cputable.h
 header-y += elf.h
+header-y += epapr_hcalls.h
 header-y += errno.h
 header-y += fcntl.h
 header-y += ioctl.h
@@ -42,4 +43,3 @@ header-y += termios.h
 header-y += types.h
 header-y += ucontext.h
 header-y += unistd.h
-header-y += epapr_hcalls.h

arch/powerpc/kernel/smp.c

@@ -427,6 +427,45 @@ int generic_check_cpu_restart(unsigned int cpu)
 {
 	return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE;
 }
+
+static atomic_t secondary_inhibit_count;
+
+/*
+ * Don't allow secondary CPU threads to come online
+ */
+void inhibit_secondary_onlining(void)
+{
+	/*
+	 * This makes secondary_inhibit_count stable during cpu
+	 * online/offline operations.
+	 */
+	get_online_cpus();
+
+	atomic_inc(&secondary_inhibit_count);
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(inhibit_secondary_onlining);
+
+/*
+ * Allow secondary CPU threads to come online again
+ */
+void uninhibit_secondary_onlining(void)
+{
+	get_online_cpus();
+	atomic_dec(&secondary_inhibit_count);
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(uninhibit_secondary_onlining);
+
+static int secondaries_inhibited(void)
+{
+	return atomic_read(&secondary_inhibit_count);
+}
+
+#else /* HOTPLUG_CPU */
+
+#define secondaries_inhibited()		0
+
 #endif
 
 static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
@@ -445,6 +484,13 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int rc, c;
 
+	/*
+	 * Don't allow secondary threads to come online if inhibited
+	 */
+	if (threads_per_core > 1 && secondaries_inhibited() &&
+	    cpu % threads_per_core != 0)
+		return -EBUSY;
+
 	if (smp_ops == NULL ||
 	    (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu)))
 		return -EINVAL;

arch/powerpc/kvm/44x_emulate.c

@@ -46,6 +46,7 @@ static int emulate_mtdcr(struct kvm_vcpu *vcpu, int rs, int dcrn)
 		vcpu->run->dcr.dcrn = dcrn;
 		vcpu->run->dcr.data = kvmppc_get_gpr(vcpu, rs);
 		vcpu->run->dcr.is_write = 1;
+		vcpu->arch.dcr_is_write = 1;
 		vcpu->arch.dcr_needed = 1;
 		kvmppc_account_exit(vcpu, DCR_EXITS);
 		return EMULATE_DO_DCR;
@@ -80,6 +81,7 @@ static int emulate_mfdcr(struct kvm_vcpu *vcpu, int rt, int dcrn)
 		vcpu->run->dcr.dcrn = dcrn;
 		vcpu->run->dcr.data =  0;
 		vcpu->run->dcr.is_write = 0;
+		vcpu->arch.dcr_is_write = 0;
 		vcpu->arch.io_gpr = rt;
 		vcpu->arch.dcr_needed = 1;
 		kvmppc_account_exit(vcpu, DCR_EXITS);

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -134,8 +134,11 @@ kvm_start_guest:
 
 27:	/* XXX should handle hypervisor maintenance interrupts etc. here */
 
+	/* reload vcpu pointer after clearing the IPI */
+	ld	r4,HSTATE_KVM_VCPU(r13)
+	cmpdi	r4,0
 	/* if we have no vcpu to run, go back to sleep */
-	beq	cr1,kvm_no_guest
+	beq	kvm_no_guest
 
 	/* were we napping due to cede? */
 	lbz	r0,HSTATE_NAPPING(r13)
@@ -1587,6 +1590,10 @@ secondary_too_late:
 	.endr
 
 secondary_nap:
+	/* Clear our vcpu pointer so we don't come back in early */
+	li	r0, 0
+	std	r0, HSTATE_KVM_VCPU(r13)
+	lwsync
 	/* Clear any pending IPI - assume we're a secondary thread */
 	ld	r5, HSTATE_XICS_PHYS(r13)
 	li	r7, XICS_XIRR
@@ -1612,8 +1619,6 @@ secondary_nap:
 kvm_no_guest:
 	li	r0, KVM_HWTHREAD_IN_NAP
 	stb	r0, HSTATE_HWTHREAD_STATE(r13)
-	li	r0, 0
-	std	r0, HSTATE_KVM_VCPU(r13)
 
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR

arch/powerpc/kvm/emulate.c

@@ -131,6 +131,125 @@ u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb)
 	return vcpu->arch.dec - jd;
 }
 
+static int kvmppc_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+{
+	enum emulation_result emulated = EMULATE_DONE;
+	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
+
+	switch (sprn) {
+	case SPRN_SRR0:
+		vcpu->arch.shared->srr0 = spr_val;
+		break;
+	case SPRN_SRR1:
+		vcpu->arch.shared->srr1 = spr_val;
+		break;
+
+	/* XXX We need to context-switch the timebase for
+	 * watchdog and FIT. */
+	case SPRN_TBWL: break;
+	case SPRN_TBWU: break;
+
+	case SPRN_MSSSR0: break;
+
+	case SPRN_DEC:
+		vcpu->arch.dec = spr_val;
+		kvmppc_emulate_dec(vcpu);
+		break;
+
+	case SPRN_SPRG0:
+		vcpu->arch.shared->sprg0 = spr_val;
+		break;
+	case SPRN_SPRG1:
+		vcpu->arch.shared->sprg1 = spr_val;
+		break;
+	case SPRN_SPRG2:
+		vcpu->arch.shared->sprg2 = spr_val;
+		break;
+	case SPRN_SPRG3:
+		vcpu->arch.shared->sprg3 = spr_val;
+		break;
+
+	default:
+		emulated = kvmppc_core_emulate_mtspr(vcpu, sprn,
+						     spr_val);
+		if (emulated == EMULATE_FAIL)
+			printk(KERN_INFO "mtspr: unknown spr "
+				"0x%x\n", sprn);
+		break;
+	}
+
+	kvmppc_set_exit_type(vcpu, EMULATED_MTSPR_EXITS);
+
+	return emulated;
+}
+
+static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+{
+	enum emulation_result emulated = EMULATE_DONE;
+	ulong spr_val = 0;
+
+	switch (sprn) {
+	case SPRN_SRR0:
+		spr_val = vcpu->arch.shared->srr0;
+		break;
+	case SPRN_SRR1:
+		spr_val = vcpu->arch.shared->srr1;
+		break;
+	case SPRN_PVR:
+		spr_val = vcpu->arch.pvr;
+		break;
+	case SPRN_PIR:
+		spr_val = vcpu->vcpu_id;
+		break;
+	case SPRN_MSSSR0:
+		spr_val = 0;
+		break;
+
+	/* Note: mftb and TBRL/TBWL are user-accessible, so
+	 * the guest can always access the real TB anyways.
+	 * In fact, we probably will never see these traps. */
+	case SPRN_TBWL:
+		spr_val = get_tb() >> 32;
+		break;
+	case SPRN_TBWU:
+		spr_val = get_tb();
+		break;
+
+	case SPRN_SPRG0:
+		spr_val = vcpu->arch.shared->sprg0;
+		break;
+	case SPRN_SPRG1:
+		spr_val = vcpu->arch.shared->sprg1;
+		break;
+	case SPRN_SPRG2:
+		spr_val = vcpu->arch.shared->sprg2;
+		break;
+	case SPRN_SPRG3:
+		spr_val = vcpu->arch.shared->sprg3;
+		break;
+	/* Note: SPRG4-7 are user-readable, so we don't get
+	 * a trap. */
+
+	case SPRN_DEC:
+		spr_val = kvmppc_get_dec(vcpu, get_tb());
+		break;
+	default:
+		emulated = kvmppc_core_emulate_mfspr(vcpu, sprn,
+						     &spr_val);
+		if (unlikely(emulated == EMULATE_FAIL)) {
+			printk(KERN_INFO "mfspr: unknown spr "
+				"0x%x\n", sprn);
+		}
+		break;
+	}
+
+	if (emulated == EMULATE_DONE)
+		kvmppc_set_gpr(vcpu, rt, spr_val);
+	kvmppc_set_exit_type(vcpu, EMULATED_MFSPR_EXITS);
+
+	return emulated;
+}
+
 /* XXX to do:
  * lhax
  * lhaux
@@ -156,7 +275,6 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	int sprn = get_sprn(inst);
 	enum emulation_result emulated = EMULATE_DONE;
 	int advance = 1;
-	ulong spr_val = 0;
 
 	/* this default type might be overwritten by subcategories */
 	kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS);
@@ -236,62 +354,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 
 		case OP_31_XOP_MFSPR:
-			switch (sprn) {
-			case SPRN_SRR0:
-				spr_val = vcpu->arch.shared->srr0;
-				break;
-			case SPRN_SRR1:
-				spr_val = vcpu->arch.shared->srr1;
-				break;
-			case SPRN_PVR:
-				spr_val = vcpu->arch.pvr;
-				break;
-			case SPRN_PIR:
-				spr_val = vcpu->vcpu_id;
-				break;
-			case SPRN_MSSSR0:
-				spr_val = 0;
-				break;
-
-			/* Note: mftb and TBRL/TBWL are user-accessible, so
-			 * the guest can always access the real TB anyways.
-			 * In fact, we probably will never see these traps. */
-			case SPRN_TBWL:
-				spr_val = get_tb() >> 32;
-				break;
-			case SPRN_TBWU:
-				spr_val = get_tb();
-				break;
-
-			case SPRN_SPRG0:
-				spr_val = vcpu->arch.shared->sprg0;
-				break;
-			case SPRN_SPRG1:
-				spr_val = vcpu->arch.shared->sprg1;
-				break;
-			case SPRN_SPRG2:
-				spr_val = vcpu->arch.shared->sprg2;
-				break;
-			case SPRN_SPRG3:
-				spr_val = vcpu->arch.shared->sprg3;
-				break;
-			/* Note: SPRG4-7 are user-readable, so we don't get
-			 * a trap. */
-
-			case SPRN_DEC:
-				spr_val = kvmppc_get_dec(vcpu, get_tb());
-				break;
-			default:
-				emulated = kvmppc_core_emulate_mfspr(vcpu, sprn,
-								     &spr_val);
-				if (unlikely(emulated == EMULATE_FAIL)) {
-					printk(KERN_INFO "mfspr: unknown spr "
-						"0x%x\n", sprn);
-				}
-				break;
-			}
-			kvmppc_set_gpr(vcpu, rt, spr_val);
-			kvmppc_set_exit_type(vcpu, EMULATED_MFSPR_EXITS);
+			emulated = kvmppc_emulate_mfspr(vcpu, sprn, rt);
 			break;
 
 		case OP_31_XOP_STHX:
@@ -308,49 +371,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			break;
 
 		case OP_31_XOP_MTSPR:
-			spr_val = kvmppc_get_gpr(vcpu, rs);
-			switch (sprn) {
-			case SPRN_SRR0:
-				vcpu->arch.shared->srr0 = spr_val;
-				break;
-			case SPRN_SRR1:
-				vcpu->arch.shared->srr1 = spr_val;
-				break;
-
-			/* XXX We need to context-switch the timebase for
-			 * watchdog and FIT. */
-			case SPRN_TBWL: break;
-			case SPRN_TBWU: break;
-
-			case SPRN_MSSSR0: break;
-
-			case SPRN_DEC:
-				vcpu->arch.dec = spr_val;
-				kvmppc_emulate_dec(vcpu);
-				break;
-
-			case SPRN_SPRG0:
-				vcpu->arch.shared->sprg0 = spr_val;
-				break;
-			case SPRN_SPRG1:
-				vcpu->arch.shared->sprg1 = spr_val;
-				break;
-			case SPRN_SPRG2:
-				vcpu->arch.shared->sprg2 = spr_val;
-				break;
-			case SPRN_SPRG3:
-				vcpu->arch.shared->sprg3 = spr_val;
-				break;
-
-			default:
-				emulated = kvmppc_core_emulate_mtspr(vcpu, sprn,
-								     spr_val);
-				if (emulated == EMULATE_FAIL)
-					printk(KERN_INFO "mtspr: unknown spr "
-						"0x%x\n", sprn);
-				break;
-			}
-			kvmppc_set_exit_type(vcpu, EMULATED_MTSPR_EXITS);
+			emulated = kvmppc_emulate_mtspr(vcpu, sprn, rs);
 			break;
 
 		case OP_31_XOP_DCBI: