From 0ba12d10817a8db1fd7d96d3283ec6c0b294aeab Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Thu, 21 May 2009 16:45:19 +0300
Subject: KVM: Move common KVM Kconfig items to new file virt/kvm/Kconfig

Reduce Kconfig code duplication.

Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/Kconfig | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 5a152a52796..46019dccce1 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -2,8 +2,7 @@
 # KVM configuration
 #
 
-config HAVE_KVM_IRQCHIP
-       bool
+source "virt/kvm/Kconfig"
 
 menuconfig VIRTUALIZATION
 	bool "Virtualization"
-- 
cgit v1.2.3-70-g09d2


From 2986b8c72c272ea58edd37903b042c6da985627d Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Tue, 2 Jun 2009 11:46:14 +1000
Subject: KVM: powerpc: fix some init/exit annotations

Fixes a couple of warnings like this one:

WARNING: arch/powerpc/kvm/kvm-440.o(.text+0x1e8c): Section mismatch in reference from the function kvmppc_44x_exit() to the function .exit.text:kvmppc_booke_exit()
The function kvmppc_44x_exit() references a function in an exit section.
Often the function kvmppc_booke_exit() has valid usage outside the exit section
and the fix is to remove the __exit annotation of kvmppc_booke_exit.

Also add some __init annotations on obvious routines.

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/44x.c   | 4 ++--
 arch/powerpc/kvm/booke.c | 2 +-
 arch/powerpc/kvm/e500.c  | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index 0cef809cec2..f4d1b55aa70 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -138,7 +138,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_44x);
 }
 
-static int kvmppc_44x_init(void)
+static int __init kvmppc_44x_init(void)
 {
 	int r;
 
@@ -149,7 +149,7 @@ static int kvmppc_44x_init(void)
 	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), THIS_MODULE);
 }
 
-static void kvmppc_44x_exit(void)
+static void __exit kvmppc_44x_exit(void)
 {
 	kvmppc_booke_exit();
 }
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 642e4204cf2..e7bf4d02948 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -520,7 +520,7 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 	return kvmppc_core_vcpu_translate(vcpu, tr);
 }
 
-int kvmppc_booke_init(void)
+int __init kvmppc_booke_init(void)
 {
 	unsigned long ivor[16];
 	unsigned long max_ivor = 0;
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index d8067fd81cd..674e796f7aa 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -132,7 +132,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
-static int kvmppc_e500_init(void)
+static int __init kvmppc_e500_init(void)
 {
 	int r, i;
 	unsigned long ivor[3];
@@ -160,7 +160,7 @@ static int kvmppc_e500_init(void)
 	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), THIS_MODULE);
 }
 
-static void kvmppc_e500_exit(void)
+static void __init kvmppc_e500_exit(void)
 {
 	kvmppc_booke_exit();
 }
-- 
cgit v1.2.3-70-g09d2


From 0cfb50e50dd27539fed9ba3cb33b0f22c0cddef0 Mon Sep 17 00:00:00 2001
From: Liu Yu <yu.liu@freescale.com>
Date: Fri, 5 Jun 2009 14:54:29 +0800
Subject: KVM: ppc: e500: Move to Book-3e MMU definitions

According to commit 70fe3af8403f85196bb74f22ce4813db7dfedc1a.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/e500_tlb.c | 10 +++++-----
 arch/powerpc/kvm/e500_tlb.h |  6 +++---
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index 0e773fc2d5e..a2048ac095a 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -269,7 +269,7 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 	tlbsel = (vcpu_e500->mas4 >> 28) & 0x1;
 	victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
 	pidsel = (vcpu_e500->mas4 >> 16) & 0xf;
-	tsized = (vcpu_e500->mas4 >> 8) & 0xf;
+	tsized = (vcpu_e500->mas4 >> 7) & 0x1f;
 
 	vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
 		| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);
@@ -309,7 +309,7 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	vcpu_e500->shadow_pages[tlbsel][esel] = new_page;
 
 	/* Force TS=1 IPROT=0 TSIZE=4KB for all guest mappings. */
-	stlbe->mas1 = MAS1_TSIZE(BOOKE_PAGESZ_4K)
+	stlbe->mas1 = MAS1_TSIZE(BOOK3E_PAGESZ_4K)
 		| MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID;
 	stlbe->mas2 = (gvaddr & MAS2_EPN)
 		| e500_shadow_mas2_attrib(gtlbe->mas2,
@@ -545,7 +545,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 		case 0:
 			/* TLB0 */
 			gtlbe->mas1 &= ~MAS1_TSIZE(~0);
-			gtlbe->mas1 |= MAS1_TSIZE(BOOKE_PAGESZ_4K);
+			gtlbe->mas1 |= MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 
 			stlbsel = 0;
 			sesel = kvmppc_e500_stlbe_map(vcpu_e500, 0, esel);
@@ -679,14 +679,14 @@ void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
 
 	/* Insert large initial mapping for guest. */
 	tlbe = &vcpu_e500->guest_tlb[1][0];
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_256M);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
 	tlbe->mas2 = 0;
 	tlbe->mas3 = E500_TLB_SUPER_PERM_MASK;
 	tlbe->mas7 = 0;
 
 	/* 4K map for serial output. Used by kernel wrapper. */
 	tlbe = &vcpu_e500->guest_tlb[1][1];
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_4K);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
 	tlbe->mas3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
 	tlbe->mas7 = 0;
diff --git a/arch/powerpc/kvm/e500_tlb.h b/arch/powerpc/kvm/e500_tlb.h
index 45b064b7690..d28e3010a5e 100644
--- a/arch/powerpc/kvm/e500_tlb.h
+++ b/arch/powerpc/kvm/e500_tlb.h
@@ -16,7 +16,7 @@
 #define __KVM_E500_TLB_H__
 
 #include <linux/kvm_host.h>
-#include <asm/mmu-fsl-booke.h>
+#include <asm/mmu-book3e.h>
 #include <asm/tlb.h>
 #include <asm/kvm_e500.h>
 
@@ -59,7 +59,7 @@ extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
 /* TLB helper functions */
 static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
 {
-	return (tlbe->mas1 >> 8) & 0xf;
+	return (tlbe->mas1 >> 7) & 0x1f;
 }
 
 static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
@@ -70,7 +70,7 @@ static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
 static inline u64 get_tlb_bytes(const struct tlbe *tlbe)
 {
 	unsigned int pgsize = get_tlb_size(tlbe);
-	return 1ULL << 10 << (pgsize << 1);
+	return 1ULL << 10 << pgsize;
 }
 
 static inline gva_t get_tlb_end(const struct tlbe *tlbe)
-- 
cgit v1.2.3-70-g09d2


From 5b7c1a2c17e77cd5416755bb9ac63278996f6c51 Mon Sep 17 00:00:00 2001
From: Liu Yu <yu.liu@freescale.com>
Date: Fri, 5 Jun 2009 14:54:30 +0800
Subject: KVM: ppc: e500: Directly pass pvr to guest

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h | 1 -
 arch/powerpc/kvm/e500.c             | 3 ---
 arch/powerpc/kvm/emulate.c          | 2 +-
 3 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index fddc3ed715f..d4caa6127f5 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -153,7 +153,6 @@ struct kvm_vcpu_arch {
 	u32 pid;
 	u32 swap_pid;
 
-	u32 pvr;
 	u32 ccr0;
 	u32 ccr1;
 	u32 dbcr0;
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 674e796f7aa..64949eef43f 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -60,9 +60,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvmppc_e500_tlb_setup(vcpu_e500);
 
-	/* Use the same core vertion as host's */
-	vcpu->arch.pvr = mfspr(SPRN_PVR);
-
 	return 0;
 }
 
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index a561d6e8da1..f8b8248cb9b 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -187,7 +187,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			case SPRN_SRR1:
 				vcpu->arch.gpr[rt] = vcpu->arch.srr1; break;
 			case SPRN_PVR:
-				vcpu->arch.gpr[rt] = vcpu->arch.pvr; break;
+				vcpu->arch.gpr[rt] = mfspr(SPRN_PVR); break;
 
 			/* Note: mftb and TBRL/TBWL are user-accessible, so
 			 * the guest can always access the real TB anyways.
-- 
cgit v1.2.3-70-g09d2


From 06579dd9c12f36ac575460a226d2020d84a0128b Mon Sep 17 00:00:00 2001
From: Liu Yu <yu.liu@freescale.com>
Date: Fri, 5 Jun 2009 14:54:31 +0800
Subject: KVM: ppc: e500: Add MMUCFG and PVR emulation

Latest kernel started to use these two registers.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/e500_emulate.c | 3 +++
 arch/powerpc/kvm/emulate.c      | 2 ++
 2 files changed, 5 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 3f760414b9f..be95b8d8e3b 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -180,6 +180,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_MMUCSR0:
 		vcpu->arch.gpr[rt] = 0; break;
 
+	case SPRN_MMUCFG:
+		vcpu->arch.gpr[rt] = mfspr(SPRN_MMUCFG); break;
+
 	/* extra exceptions */
 	case SPRN_IVOR32:
 		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index f8b8248cb9b..28a8237fe78 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -188,6 +188,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 				vcpu->arch.gpr[rt] = vcpu->arch.srr1; break;
 			case SPRN_PVR:
 				vcpu->arch.gpr[rt] = mfspr(SPRN_PVR); break;
+			case SPRN_PIR:
+				vcpu->arch.gpr[rt] = mfspr(SPRN_PIR); break;
 
 			/* Note: mftb and TBRL/TBWL are user-accessible, so
 			 * the guest can always access the real TB anyways.
-- 
cgit v1.2.3-70-g09d2


From 988a2cae6a3c0dea6df59808a935a9a697bfc28c Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Tue, 9 Jun 2009 15:56:29 +0300
Subject: KVM: Use macro to iterate over vcpus.

[christian: remove unused variables on s390]

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/ia64/kvm/kvm-ia64.c   | 29 ++++++++++++++---------------
 arch/powerpc/kvm/powerpc.c | 16 ++++++++++------
 arch/s390/kvm/kvm-s390.c   | 31 +++++++++++++++----------------
 arch/x86/kvm/i8254.c       |  7 ++-----
 arch/x86/kvm/mmu.c         |  6 +++---
 arch/x86/kvm/x86.c         | 25 ++++++++++++-------------
 include/linux/kvm_host.h   | 11 +++++++++++
 virt/kvm/irq_comm.c        |  6 ++----
 virt/kvm/kvm_main.c        | 19 +++++++------------
 9 files changed, 76 insertions(+), 74 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index d1f7bcda2c7..5c766bd82b0 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -337,13 +337,12 @@ static struct kvm_vcpu *lid_to_vcpu(struct kvm *kvm, unsigned long id,
 {
 	union ia64_lid lid;
 	int i;
+	struct kvm_vcpu *vcpu;
 
-	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) {
-		if (kvm->vcpus[i]) {
-			lid.val = VCPU_LID(kvm->vcpus[i]);
-			if (lid.id == id && lid.eid == eid)
-				return kvm->vcpus[i];
-		}
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		lid.val = VCPU_LID(vcpu);
+		if (lid.id == id && lid.eid == eid)
+			return vcpu;
 	}
 
 	return NULL;
@@ -409,21 +408,21 @@ static int handle_global_purge(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	struct kvm *kvm = vcpu->kvm;
 	struct call_data call_data;
 	int i;
+	struct kvm_vcpu *vcpui;
 
 	call_data.ptc_g_data = p->u.ptc_g_data;
 
-	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) {
-		if (!kvm->vcpus[i] || kvm->vcpus[i]->arch.mp_state ==
-						KVM_MP_STATE_UNINITIALIZED ||
-					vcpu == kvm->vcpus[i])
+	kvm_for_each_vcpu(i, vcpui, kvm) {
+		if (vcpui->arch.mp_state == KVM_MP_STATE_UNINITIALIZED ||
+				vcpu == vcpui)
 			continue;
 
-		if (waitqueue_active(&kvm->vcpus[i]->wq))
-			wake_up_interruptible(&kvm->vcpus[i]->wq);
+		if (waitqueue_active(&vcpui->wq))
+			wake_up_interruptible(&vcpui->wq);
 
-		if (kvm->vcpus[i]->cpu != -1) {
-			call_data.vcpu = kvm->vcpus[i];
-			smp_call_function_single(kvm->vcpus[i]->cpu,
+		if (vcpui->cpu != -1) {
+			call_data.vcpu = vcpui;
+			smp_call_function_single(vcpui->cpu,
 					vcpu_global_purge, &call_data, 1);
 		} else
 			printk(KERN_WARNING"kvm: Uninit vcpu received ipi!\n");
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 2cf915e51e7..7ad30e0a1b9 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -122,13 +122,17 @@ struct kvm *kvm_arch_create_vm(void)
 static void kvmppc_free_vcpus(struct kvm *kvm)
 {
 	unsigned int i;
+	struct kvm_vcpu *vcpu;
 
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (kvm->vcpus[i]) {
-			kvm_arch_vcpu_free(kvm->vcpus[i]);
-			kvm->vcpus[i] = NULL;
-		}
-	}
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_arch_vcpu_free(vcpu);
+
+	mutex_lock(&kvm->lock);
+	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
+		kvm->vcpus[i] = NULL;
+
+	atomic_set(&kvm->online_vcpus, 0);
+	mutex_unlock(&kvm->lock);
 }
 
 void kvm_arch_sync_events(struct kvm *kvm)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 098bfa6fbdf..07ced89740d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -211,13 +211,17 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 static void kvm_free_vcpus(struct kvm *kvm)
 {
 	unsigned int i;
+	struct kvm_vcpu *vcpu;
 
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (kvm->vcpus[i]) {
-			kvm_arch_vcpu_destroy(kvm->vcpus[i]);
-			kvm->vcpus[i] = NULL;
-		}
-	}
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_arch_vcpu_destroy(vcpu);
+
+	mutex_lock(&kvm->lock);
+	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
+		kvm->vcpus[i] = NULL;
+
+	atomic_set(&kvm->online_vcpus, 0);
+	mutex_unlock(&kvm->lock);
 }
 
 void kvm_arch_sync_events(struct kvm *kvm)
@@ -314,8 +318,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	BUG_ON(!kvm->arch.sca);
 	if (!kvm->arch.sca->cpu[id].sda)
 		kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
-	else
-		BUG_ON(!kvm->vcpus[id]); /* vcpu does already exist */
 	vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32);
 	vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
 
@@ -683,6 +685,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 				int user_alloc)
 {
 	int i;
+	struct kvm_vcpu *vcpu;
 
 	/* A few sanity checks. We can have exactly one memory slot which has
 	   to start at guest virtual zero and which has to be located at a
@@ -707,14 +710,10 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 		return -EINVAL;
 
 	/* request update of sie control block for all available vcpus */
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (kvm->vcpus[i]) {
-			if (test_and_set_bit(KVM_REQ_MMU_RELOAD,
-						&kvm->vcpus[i]->requests))
-				continue;
-			kvm_s390_inject_sigp_stop(kvm->vcpus[i],
-						  ACTION_RELOADVCPU_ON_STOP);
-		}
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
+			continue;
+		kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP);
 	}
 
 	return 0;
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 06d8f84ae8a..15fc95b2fc0 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -669,11 +669,8 @@ static void __inject_pit_timer_intr(struct kvm *kvm)
 	 * VCPU0, and only if its LVT0 is in EXTINT mode.
 	 */
 	if (kvm->arch.vapics_in_nmi_mode > 0)
-		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-			vcpu = kvm->vcpus[i];
-			if (vcpu)
-				kvm_apic_nmi_wd_deliver(vcpu);
-		}
+		kvm_for_each_vcpu(i, vcpu, kvm)
+			kvm_apic_nmi_wd_deliver(vcpu);
 }
 
 void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d443a421ca3..5f97dbd2429 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1347,10 +1347,10 @@ static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte)
 static void kvm_mmu_reset_last_pte_updated(struct kvm *kvm)
 {
 	int i;
+	struct kvm_vcpu *vcpu;
 
-	for (i = 0; i < KVM_MAX_VCPUS; ++i)
-		if (kvm->vcpus[i])
-			kvm->vcpus[i]->arch.last_pte_updated = NULL;
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		vcpu->arch.last_pte_updated = NULL;
 }
 
 static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d8adc1da76d..89862a80e32 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2946,10 +2946,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 
 	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
-		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-			vcpu = kvm->vcpus[i];
-			if (!vcpu)
-				continue;
+		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (vcpu->cpu != freq->cpu)
 				continue;
 			if (!kvm_request_guest_time_update(vcpu))
@@ -4678,20 +4675,22 @@ static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
 static void kvm_free_vcpus(struct kvm *kvm)
 {
 	unsigned int i;
+	struct kvm_vcpu *vcpu;
 
 	/*
 	 * Unpin any mmu pages first.
 	 */
-	for (i = 0; i < KVM_MAX_VCPUS; ++i)
-		if (kvm->vcpus[i])
-			kvm_unload_vcpu_mmu(kvm->vcpus[i]);
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		if (kvm->vcpus[i]) {
-			kvm_arch_vcpu_free(kvm->vcpus[i]);
-			kvm->vcpus[i] = NULL;
-		}
-	}
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_unload_vcpu_mmu(vcpu);
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_arch_vcpu_free(vcpu);
+
+	mutex_lock(&kvm->lock);
+	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
+		kvm->vcpus[i] = NULL;
 
+	atomic_set(&kvm->online_vcpus, 0);
+	mutex_unlock(&kvm->lock);
 }
 
 void kvm_arch_sync_events(struct kvm *kvm)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d3fdf1a738c..c6e4d02067f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -179,6 +179,17 @@ struct kvm {
 #define kvm_printf(kvm, fmt ...) printk(KERN_DEBUG fmt)
 #define vcpu_printf(vcpu, fmt...) kvm_printf(vcpu->kvm, fmt)
 
+static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
+{
+	smp_rmb();
+	return kvm->vcpus[i];
+}
+
+#define kvm_for_each_vcpu(idx, vcpup, kvm) \
+	for (idx = 0, vcpup = kvm_get_vcpu(kvm, idx); \
+	     idx < atomic_read(&kvm->online_vcpus) && vcpup; \
+	     vcpup = kvm_get_vcpu(kvm, ++idx))
+
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id);
 void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
 
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 08a9a49481b..bb8a1b5e41c 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -68,10 +68,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 			kvm_is_dm_lowest_prio(irq))
 		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
 
-	for (i = 0; i < KVM_MAX_VCPUS; i++) {
-		vcpu = kvm->vcpus[i];
-
-		if (!vcpu || !kvm_apic_present(vcpu))
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_apic_present(vcpu))
 			continue;
 
 		if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 25e1f9c97b1..777fe533cfe 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -738,10 +738,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 
 	me = get_cpu();
 	spin_lock(&kvm->requests_lock);
-	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-		vcpu = kvm->vcpus[i];
-		if (!vcpu)
-			continue;
+	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (test_and_set_bit(req, &vcpu->requests))
 			continue;
 		cpu = vcpu->cpu;
@@ -1718,7 +1715,7 @@ static int create_vcpu_fd(struct kvm_vcpu *vcpu)
 static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 {
 	int r;
-	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu *vcpu, *v;
 
 	vcpu = kvm_arch_vcpu_create(kvm, id);
 	if (IS_ERR(vcpu))
@@ -1736,8 +1733,8 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 		goto vcpu_destroy;
 	}
 
-	for (r = 0; r < atomic_read(&kvm->online_vcpus); r++)
-		if (kvm->vcpus[r]->vcpu_id == id) {
+	kvm_for_each_vcpu(r, v, kvm)
+		if (v->vcpu_id == id) {
 			r = -EEXIST;
 			goto vcpu_destroy;
 		}
@@ -2526,11 +2523,9 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 	*val = 0;
 	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
-		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
-			vcpu = kvm->vcpus[i];
-			if (vcpu)
-				*val += *(u32 *)((void *)vcpu + offset);
-		}
+		kvm_for_each_vcpu(i, vcpu, kvm)
+			*val += *(u32 *)((void *)vcpu + offset);
+
 	spin_unlock(&kvm_lock);
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From ec04b2604c3707a46db1d26d98f82b11d0844669 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <joerg.roedel@amd.com>
Date: Fri, 19 Jun 2009 15:16:23 +0200
Subject: KVM: Prepare memslot data structures for multiple hugepage sizes

[avi: fix build on non-x86]

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/ia64/include/asm/kvm_host.h    |  3 +-
 arch/powerpc/include/asm/kvm_host.h |  3 +-
 arch/s390/include/asm/kvm_host.h    |  6 +++-
 arch/x86/include/asm/kvm_host.h     | 12 ++++----
 arch/x86/kvm/mmu.c                  | 30 ++++++++++----------
 arch/x86/kvm/paging_tmpl.h          |  3 +-
 include/linux/kvm_host.h            |  2 +-
 virt/kvm/kvm_main.c                 | 56 ++++++++++++++++++++++++++-----------
 8 files changed, 73 insertions(+), 42 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index 9cf1c4b1f92..d9b6325a932 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -235,7 +235,8 @@ struct kvm_vm_data {
 #define KVM_REQ_PTC_G		32
 #define KVM_REQ_RESUME		33
 
-#define KVM_PAGES_PER_HPAGE	1
+#define KVM_NR_PAGE_SIZES	1
+#define KVM_PAGES_PER_HPAGE(x)	1
 
 struct kvm;
 struct kvm_vcpu;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index d4caa6127f5..c9c930ed11d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -34,7 +34,8 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
 /* We don't currently support large pages. */
-#define KVM_PAGES_PER_HPAGE (1UL << 31)
+#define KVM_NR_PAGE_SIZES	1
+#define KVM_PAGES_PER_HPAGE(x)	(1UL<<31)
 
 struct kvm;
 struct kvm_run;
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 75535d4d7a0..78e07a622b4 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -40,7 +40,11 @@ struct sca_block {
 	struct sca_entry cpu[64];
 } __attribute__((packed));
 
-#define KVM_PAGES_PER_HPAGE 256
+#define KVM_NR_PAGE_SIZES 2
+#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + ((x) - 1) * 8)
+#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x))
+#define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
+#define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
 
 #define CPUSTAT_HOST       0x80000000
 #define CPUSTAT_WAIT       0x10000000
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 19027ab2041..30b625d8e5f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -54,12 +54,12 @@
 #define INVALID_PAGE (~(hpa_t)0)
 #define UNMAPPED_GVA (~(gpa_t)0)
 
-/* shadow tables are PAE even on non-PAE hosts */
-#define KVM_HPAGE_SHIFT 21
-#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT)
-#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1))
-
-#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE)
+/* KVM Hugepage definitions for x86 */
+#define KVM_NR_PAGE_SIZES	2
+#define KVM_HPAGE_SHIFT(x)	(PAGE_SHIFT + (((x) - 1) * 9))
+#define KVM_HPAGE_SIZE(x)	(1UL << KVM_HPAGE_SHIFT(x))
+#define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
+#define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
 
 #define DE_VECTOR 0
 #define DB_VECTOR 1
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 12974de88aa..b67585c1ef0 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -394,9 +394,9 @@ static int *slot_largepage_idx(gfn_t gfn, struct kvm_memory_slot *slot)
 {
 	unsigned long idx;
 
-	idx = (gfn / KVM_PAGES_PER_HPAGE) -
-	      (slot->base_gfn / KVM_PAGES_PER_HPAGE);
-	return &slot->lpage_info[idx].write_count;
+	idx = (gfn / KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL)) -
+	      (slot->base_gfn / KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL));
+	return &slot->lpage_info[0][idx].write_count;
 }
 
 static void account_shadowed(struct kvm *kvm, gfn_t gfn)
@@ -485,10 +485,10 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage)
 	if (!lpage)
 		return &slot->rmap[gfn - slot->base_gfn];
 
-	idx = (gfn / KVM_PAGES_PER_HPAGE) -
-	      (slot->base_gfn / KVM_PAGES_PER_HPAGE);
+	idx = (gfn / KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL)) -
+	      (slot->base_gfn / KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL));
 
-	return &slot->lpage_info[idx].rmap_pde;
+	return &slot->lpage_info[0][idx].rmap_pde;
 }
 
 /*
@@ -731,11 +731,11 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 		end = start + (memslot->npages << PAGE_SHIFT);
 		if (hva >= start && hva < end) {
 			gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
+			int idx = gfn_offset /
+			          KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL);
 			retval |= handler(kvm, &memslot->rmap[gfn_offset]);
 			retval |= handler(kvm,
-					  &memslot->lpage_info[
-						  gfn_offset /
-						  KVM_PAGES_PER_HPAGE].rmap_pde);
+					&memslot->lpage_info[0][idx].rmap_pde);
 		}
 	}
 
@@ -1876,8 +1876,9 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
 	pfn_t pfn;
 	unsigned long mmu_seq;
 
-	if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
-		gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+	if (is_largepage_backed(vcpu, gfn &
+			~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1))) {
+		gfn &= ~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
 		largepage = 1;
 	}
 
@@ -2082,8 +2083,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
 	if (r)
 		return r;
 
-	if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
-		gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+	if (is_largepage_backed(vcpu, gfn &
+			~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1))) {
+		gfn &= ~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
 		largepage = 1;
 	}
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
@@ -2485,7 +2487,7 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
 
 	if (is_large_pte(gpte) && is_largepage_backed(vcpu, gfn)) {
-		gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+		gfn &= ~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
 		vcpu->arch.update_pte.largepage = 1;
 	}
 	vcpu->arch.update_pte.mmu_seq = vcpu->kvm->mmu_notifier_seq;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 322e8113aee..53e129cec5f 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -401,7 +401,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 
 	if (walker.level == PT_DIRECTORY_LEVEL) {
 		gfn_t large_gfn;
-		large_gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE-1);
+		large_gfn = walker.gfn &
+			~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
 		if (is_largepage_backed(vcpu, large_gfn)) {
 			walker.gfn = large_gfn;
 			largepage = 1;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 6988858dc56..06af936a250 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -103,7 +103,7 @@ struct kvm_memory_slot {
 	struct {
 		unsigned long rmap_pde;
 		int write_count;
-	} *lpage_info;
+	} *lpage_info[KVM_NR_PAGE_SIZES - 1];
 	unsigned long userspace_addr;
 	int user_alloc;
 };
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1da8072d61b..8361662e7e0 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1001,19 +1001,25 @@ out:
 static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 				  struct kvm_memory_slot *dont)
 {
+	int i;
+
 	if (!dont || free->rmap != dont->rmap)
 		vfree(free->rmap);
 
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
 		vfree(free->dirty_bitmap);
 
-	if (!dont || free->lpage_info != dont->lpage_info)
-		vfree(free->lpage_info);
+
+	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		if (!dont || free->lpage_info[i] != dont->lpage_info[i]) {
+			vfree(free->lpage_info[i]);
+			free->lpage_info[i] = NULL;
+		}
+	}
 
 	free->npages = 0;
 	free->dirty_bitmap = NULL;
 	free->rmap = NULL;
-	free->lpage_info = NULL;
 }
 
 void kvm_free_physmem(struct kvm *kvm)
@@ -1087,7 +1093,8 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	int r;
 	gfn_t base_gfn;
 	unsigned long npages, ugfn;
-	unsigned long largepages, i;
+	int lpages;
+	unsigned long i, j;
 	struct kvm_memory_slot *memslot;
 	struct kvm_memory_slot old, new;
 
@@ -1161,33 +1168,48 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		else
 			new.userspace_addr = 0;
 	}
-	if (npages && !new.lpage_info) {
-		largepages = 1 + (base_gfn + npages - 1) / KVM_PAGES_PER_HPAGE;
-		largepages -= base_gfn / KVM_PAGES_PER_HPAGE;
+	if (!npages)
+		goto skip_lpage;
 
-		new.lpage_info = vmalloc(largepages * sizeof(*new.lpage_info));
+	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+		int level = i + 2;
 
-		if (!new.lpage_info)
+		/* Avoid unused variable warning if no large pages */
+		(void)level;
+
+		if (new.lpage_info[i])
+			continue;
+
+		lpages = 1 + (base_gfn + npages - 1) /
+			     KVM_PAGES_PER_HPAGE(level);
+		lpages -= base_gfn / KVM_PAGES_PER_HPAGE(level);
+
+		new.lpage_info[i] = vmalloc(lpages * sizeof(*new.lpage_info[i]));
+
+		if (!new.lpage_info[i])
 			goto out_free;
 
-		memset(new.lpage_info, 0, largepages * sizeof(*new.lpage_info));
+		memset(new.lpage_info[i], 0,
+		       lpages * sizeof(*new.lpage_info[i]));
 
-		if (base_gfn % KVM_PAGES_PER_HPAGE)
-			new.lpage_info[0].write_count = 1;
-		if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE)
-			new.lpage_info[largepages-1].write_count = 1;
+		if (base_gfn % KVM_PAGES_PER_HPAGE(level))
+			new.lpage_info[i][0].write_count = 1;
+		if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE(level))
+			new.lpage_info[i][lpages - 1].write_count = 1;
 		ugfn = new.userspace_addr >> PAGE_SHIFT;
 		/*
 		 * If the gfn and userspace address are not aligned wrt each
 		 * other, or if explicitly asked to, disable large page
 		 * support for this slot
 		 */
-		if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE - 1) ||
+		if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) ||
 		    !largepages_enabled)
-			for (i = 0; i < largepages; ++i)
-				new.lpage_info[i].write_count = 1;
+			for (j = 0; j < lpages; ++j)
+				new.lpage_info[i][j].write_count = 1;
 	}
 
+skip_lpage:
+
 	/* Allocate page dirty bitmap if needed */
 	if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
 		unsigned dirty_bytes = ALIGN(npages, BITS_PER_LONG) / 8;
-- 
cgit v1.2.3-70-g09d2


From 46f43c6ee022c3aeb9686b104234b9f27fac03c2 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Thu, 18 Jun 2009 11:47:27 -0300
Subject: KVM: powerpc: convert marker probes to event trace

[avi: make it build]
[avi: fold trace-arch.h into trace.h]

CC: Hollis Blanchard <hollisb@us.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/44x_tlb.c  |  11 ++---
 arch/powerpc/kvm/Makefile   |   4 ++
 arch/powerpc/kvm/e500_tlb.c |  16 +++----
 arch/powerpc/kvm/emulate.c  |   3 +-
 arch/powerpc/kvm/powerpc.c  |   3 ++
 arch/powerpc/kvm/trace.h    | 104 ++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 126 insertions(+), 15 deletions(-)
 create mode 100644 arch/powerpc/kvm/trace.h

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 4a16f472cc1..ff3cb63b811 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -30,6 +30,7 @@
 #include "timing.h"
 
 #include "44x_tlb.h"
+#include "trace.h"
 
 #ifndef PPC44x_TLBE_SIZE
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_4K
@@ -263,7 +264,7 @@ static void kvmppc_44x_shadow_release(struct kvmppc_vcpu_44x *vcpu_44x,
 
 	/* XXX set tlb_44x_index to stlb_index? */
 
-	KVMTRACE_1D(STLB_INVAL, &vcpu_44x->vcpu, stlb_index, handler);
+	trace_kvm_stlb_inval(stlb_index);
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
@@ -365,8 +366,8 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
 	/* Insert shadow mapping into hardware TLB. */
 	kvmppc_44x_tlbe_set_modified(vcpu_44x, victim);
 	kvmppc_44x_tlbwe(victim, &stlbe);
-	KVMTRACE_5D(STLB_WRITE, vcpu, victim, stlbe.tid, stlbe.word0, stlbe.word1,
-	            stlbe.word2, handler);
+	trace_kvm_stlb_write(victim, stlbe.tid, stlbe.word0, stlbe.word1,
+			     stlbe.word2);
 }
 
 /* For a particular guest TLB entry, invalidate the corresponding host TLB
@@ -485,8 +486,8 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 		kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 	}
 
-	KVMTRACE_5D(GTLB_WRITE, vcpu, gtlb_index, tlbe->tid, tlbe->word0,
-	            tlbe->word1, tlbe->word2, handler);
+	trace_kvm_gtlb_write(gtlb_index, tlbe->tid, tlbe->word0, tlbe->word1,
+			     tlbe->word2);
 
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
 	return EMULATE_DONE;
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 459c7ee580f..4f407f2662f 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -10,6 +10,10 @@ common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
 
 common-objs-$(CONFIG_KVM_TRACE)  += $(addprefix ../../../virt/kvm/, kvm_trace.o)
 
+CFLAGS_44x_tlb.o  := -I.
+CFLAGS_e500_tlb.o := -I.
+CFLAGS_emulate.o  := -I.
+
 kvm-objs := $(common-objs-y) powerpc.o emulate.o
 obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o
 obj-$(CONFIG_KVM) += kvm.o
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index a2048ac095a..fb1e1dc11ba 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -22,6 +22,7 @@
 
 #include "../mm/mmu_decl.h"
 #include "e500_tlb.h"
+#include "trace.h"
 
 #define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1)
 
@@ -224,9 +225,8 @@ static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 	kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
 	stlbe->mas1 = 0;
-	KVMTRACE_5D(STLB_INVAL, &vcpu_e500->vcpu, index_of(tlbsel, esel),
-			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
-			handler);
+	trace_kvm_stlb_inval(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
+			     stlbe->mas3, stlbe->mas7);
 }
 
 static void kvmppc_e500_tlb1_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
@@ -319,9 +319,8 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 				vcpu_e500->vcpu.arch.msr & MSR_PR);
 	stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN;
 
-	KVMTRACE_5D(STLB_WRITE, &vcpu_e500->vcpu, index_of(tlbsel, esel),
-			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
-			handler);
+	trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
+			     stlbe->mas3, stlbe->mas7);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
@@ -535,9 +534,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 	gtlbe->mas3 = vcpu_e500->mas3;
 	gtlbe->mas7 = vcpu_e500->mas7;
 
-	KVMTRACE_5D(GTLB_WRITE, vcpu, vcpu_e500->mas0,
-			gtlbe->mas1, gtlbe->mas2, gtlbe->mas3, gtlbe->mas7,
-			handler);
+	trace_kvm_gtlb_write(vcpu_e500->mas0, gtlbe->mas1, gtlbe->mas2,
+			     gtlbe->mas3, gtlbe->mas7);
 
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 28a8237fe78..7737146af3f 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -29,6 +29,7 @@
 #include <asm/kvm_ppc.h>
 #include <asm/disassemble.h>
 #include "timing.h"
+#include "trace.h"
 
 #define OP_TRAP 3
 
@@ -419,7 +420,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		}
 	}
 
-	KVMTRACE_3D(PPC_INSTR, vcpu, inst, (int)vcpu->arch.pc, emulated, entryexit);
+	trace_kvm_ppc_instr(inst, vcpu->arch.pc, emulated);
 
 	if (advance)
 		vcpu->arch.pc += 4; /* Advance past emulated instruction. */
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 7ad30e0a1b9..0341391eff1 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -31,6 +31,9 @@
 #include "timing.h"
 #include "../mm/mmu_decl.h"
 
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn;
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
new file mode 100644
index 00000000000..67f219de045
--- /dev/null
+++ b/arch/powerpc/kvm/trace.h
@@ -0,0 +1,104 @@
+#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace
+
+/*
+ * Tracepoint for guest mode entry.
+ */
+TRACE_EVENT(kvm_ppc_instr,
+	TP_PROTO(unsigned int inst, unsigned long pc, unsigned int emulate),
+	TP_ARGS(inst, pc, emulate),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	inst		)
+		__field(	unsigned long,	pc		)
+		__field(	unsigned int,	emulate		)
+	),
+
+	TP_fast_assign(
+		__entry->inst		= inst;
+		__entry->pc		= pc;
+		__entry->emulate	= emulate;
+	),
+
+	TP_printk("inst %u pc 0x%lx emulate %u\n",
+		  __entry->inst, __entry->pc, __entry->emulate)
+);
+
+TRACE_EVENT(kvm_stlb_inval,
+	TP_PROTO(unsigned int stlb_index),
+	TP_ARGS(stlb_index),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	stlb_index	)
+	),
+
+	TP_fast_assign(
+		__entry->stlb_index	= stlb_index;
+	),
+
+	TP_printk("stlb_index %u", __entry->stlb_index)
+);
+
+TRACE_EVENT(kvm_stlb_write,
+	TP_PROTO(unsigned int victim, unsigned int tid, unsigned int word0,
+		 unsigned int word1, unsigned int word2),
+	TP_ARGS(victim, tid, word0, word1, word2),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	victim		)
+		__field(	unsigned int,	tid		)
+		__field(	unsigned int,	word0		)
+		__field(	unsigned int,	word1		)
+		__field(	unsigned int,	word2		)
+	),
+
+	TP_fast_assign(
+		__entry->victim		= victim;
+		__entry->tid		= tid;
+		__entry->word0		= word0;
+		__entry->word1		= word1;
+		__entry->word2		= word2;
+	),
+
+	TP_printk("victim %u tid %u w0 %u w1 %u w2 %u",
+		__entry->victim, __entry->tid, __entry->word0,
+		__entry->word1, __entry->word2)
+);
+
+TRACE_EVENT(kvm_gtlb_write,
+	TP_PROTO(unsigned int gtlb_index, unsigned int tid, unsigned int word0,
+		 unsigned int word1, unsigned int word2),
+	TP_ARGS(gtlb_index, tid, word0, word1, word2),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	gtlb_index	)
+		__field(	unsigned int,	tid		)
+		__field(	unsigned int,	word0		)
+		__field(	unsigned int,	word1		)
+		__field(	unsigned int,	word2		)
+	),
+
+	TP_fast_assign(
+		__entry->gtlb_index	= gtlb_index;
+		__entry->tid		= tid;
+		__entry->word0		= word0;
+		__entry->word1		= word1;
+		__entry->word2		= word2;
+	),
+
+	TP_printk("gtlb_index %u tid %u w0 %u w1 %u w2 %u",
+		__entry->gtlb_index, __entry->tid, __entry->word0,
+		__entry->word1, __entry->word2)
+);
+
+#endif /* _TRACE_KVM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
-- 
cgit v1.2.3-70-g09d2


From 2023a29cbe34139afcea8f65f8aef78c325c5dc0 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Thu, 18 Jun 2009 11:47:28 -0300
Subject: KVM: remove old KVMTRACE support code

Return EOPNOTSUPP for KVM_TRACE_ENABLE/PAUSE/DISABLE ioctls.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/ia64/kvm/Kconfig     |   3 -
 arch/powerpc/kvm/Kconfig  |  11 --
 arch/powerpc/kvm/Makefile |   2 -
 arch/s390/kvm/Kconfig     |   3 -
 arch/x86/kvm/Kconfig      |  12 --
 arch/x86/kvm/Makefile     |   1 -
 include/linux/kvm.h       |  31 +----
 include/linux/kvm_host.h  |  31 -----
 virt/kvm/kvm_main.c       |   3 +-
 virt/kvm/kvm_trace.c      | 285 ----------------------------------------------
 10 files changed, 2 insertions(+), 380 deletions(-)
 delete mode 100644 virt/kvm/kvm_trace.c

(limited to 'arch/powerpc')

diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig
index cbadd8a6523..ef3e7be29ca 100644
--- a/arch/ia64/kvm/Kconfig
+++ b/arch/ia64/kvm/Kconfig
@@ -47,9 +47,6 @@ config KVM_INTEL
 	  Provides support for KVM on Itanium 2 processors equipped with the VT
 	  extensions.
 
-config KVM_TRACE
-       bool
-
 source drivers/virtio/Kconfig
 
 endif # VIRTUALIZATION
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 46019dccce1..c2992684661 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -58,17 +58,6 @@ config KVM_E500
 
 	  If unsure, say N.
 
-config KVM_TRACE
-	bool "KVM trace support"
-	depends on KVM && MARKERS && SYSFS
-	select RELAY
-	select DEBUG_FS
-	default n
-	---help---
-	  This option allows reading a trace of kvm-related events through
-	  relayfs.  Note the ABI is not considered stable and will be
-	  modified in future updates.
-
 source drivers/virtio/Kconfig
 
 endif # VIRTUALIZATION
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 4f407f2662f..37655fe19f2 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -8,8 +8,6 @@ EXTRA_CFLAGS += -Ivirt/kvm -Iarch/powerpc/kvm
 
 common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
 
-common-objs-$(CONFIG_KVM_TRACE)  += $(addprefix ../../../virt/kvm/, kvm_trace.o)
-
 CFLAGS_44x_tlb.o  := -I.
 CFLAGS_e500_tlb.o := -I.
 CFLAGS_emulate.o  := -I.
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index ad75ce33be1..bf164fc2186 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -34,9 +34,6 @@ config KVM
 
 	  If unsure, say N.
 
-config KVM_TRACE
-       bool
-
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
 source drivers/virtio/Kconfig
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 7fbedfd34d6..b84e571f417 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -62,18 +62,6 @@ config KVM_AMD
 	  To compile this as a module, choose M here: the module
 	  will be called kvm-amd.
 
-config KVM_TRACE
-	bool "KVM trace support"
-	depends on KVM && SYSFS
-	select MARKERS
-	select RELAY
-	select DEBUG_FS
-	default n
-	---help---
-	  This option allows reading a trace of kvm-related events through
-	  relayfs.  Note the ABI is not considered stable and will be
-	  modified in future updates.
-
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
 source drivers/lguest/Kconfig
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 7c56850b82c..afaaa7627d9 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -7,7 +7,6 @@ CFLAGS_vmx.o := -I.
 
 kvm-y			+= $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
 				coalesced_mmio.o irq_comm.o eventfd.o)
-kvm-$(CONFIG_KVM_TRACE)	+= $(addprefix ../../../virt/kvm/, kvm_trace.o)
 kvm-$(CONFIG_IOMMU_API)	+= $(addprefix ../../../virt/kvm/, iommu.o)
 
 kvm-y			+= x86.o mmu.o x86_emulate.o i8259.o irq.o lapic.o \
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 671051829da..76c640834ea 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -14,7 +14,7 @@
 
 #define KVM_API_VERSION 12
 
-/* for KVM_TRACE_ENABLE */
+/* for KVM_TRACE_ENABLE, deprecated */
 struct kvm_user_trace_setup {
 	__u32 buf_size; /* sub_buffer size of each per-cpu */
 	__u32 buf_nr; /* the number of sub_buffers of each per-cpu */
@@ -325,35 +325,6 @@ struct kvm_guest_debug {
 #define KVM_TRC_CYCLE_SIZE      8
 #define KVM_TRC_EXTRA_MAX       7
 
-/* This structure represents a single trace buffer record. */
-struct kvm_trace_rec {
-	/* variable rec_val
-	 * is split into:
-	 * bits 0 - 27  -> event id
-	 * bits 28 -30  -> number of extra data args of size u32
-	 * bits 31      -> binary indicator for if tsc is in record
-	 */
-	__u32 rec_val;
-	__u32 pid;
-	__u32 vcpu_id;
-	union {
-		struct {
-			__u64 timestamp;
-			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
-		} __attribute__((packed)) timestamp;
-		struct {
-			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
-		} notimestamp;
-	} u;
-};
-
-#define TRACE_REC_EVENT_ID(val) \
-		(0x0fffffff & (val))
-#define TRACE_REC_NUM_DATA_ARGS(val) \
-		(0x70000000 & ((val) << 28))
-#define TRACE_REC_TCS(val) \
-		(0x80000000 & ((val) << 31))
-
 #define KVMIO 0xAE
 
 /*
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 06af936a250..0604d56f6ee 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -482,37 +482,6 @@ struct kvm_stats_debugfs_item {
 extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;
 
-#define KVMTRACE_5D(evt, vcpu, d1, d2, d3, d4, d5, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 5, d1, d2, d3, d4, d5)
-#define KVMTRACE_4D(evt, vcpu, d1, d2, d3, d4, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 4, d1, d2, d3, d4, 0)
-#define KVMTRACE_3D(evt, vcpu, d1, d2, d3, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 3, d1, d2, d3, 0, 0)
-#define KVMTRACE_2D(evt, vcpu, d1, d2, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 2, d1, d2, 0, 0, 0)
-#define KVMTRACE_1D(evt, vcpu, d1, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 1, d1, 0, 0, 0, 0)
-#define KVMTRACE_0D(evt, vcpu, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 0, 0, 0, 0, 0, 0)
-
-#ifdef CONFIG_KVM_TRACE
-int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg);
-void kvm_trace_cleanup(void);
-#else
-static inline
-int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg)
-{
-	return -EINVAL;
-}
-#define kvm_trace_cleanup() ((void)0)
-#endif
-
 #ifdef KVM_ARCH_WANT_MMU_NOTIFIER
 static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_seq)
 {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f1e2e8c373c..bbb4029d7c4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2398,7 +2398,7 @@ static long kvm_dev_ioctl(struct file *filp,
 	case KVM_TRACE_ENABLE:
 	case KVM_TRACE_PAUSE:
 	case KVM_TRACE_DISABLE:
-		r = kvm_trace_ioctl(ioctl, arg);
+		r = -EOPNOTSUPP;
 		break;
 	default:
 		return kvm_arch_dev_ioctl(filp, ioctl, arg);
@@ -2748,7 +2748,6 @@ EXPORT_SYMBOL_GPL(kvm_init);
 
 void kvm_exit(void)
 {
-	kvm_trace_cleanup();
 	tracepoint_synchronize_unregister();
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);
diff --git a/virt/kvm/kvm_trace.c b/virt/kvm/kvm_trace.c
deleted file mode 100644
index f5987444644..00000000000
--- a/virt/kvm/kvm_trace.c
+++ /dev/null
@@ -1,285 +0,0 @@
-/*
- * kvm trace
- *
- * It is designed to allow debugging traces of kvm to be generated
- * on UP / SMP machines.  Each trace entry can be timestamped so that
- * it's possible to reconstruct a chronological record of trace events.
- * The implementation refers to blktrace kernel support.
- *
- * Copyright (c) 2008 Intel Corporation
- * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
- *
- * Authors: Feng(Eric) Liu, eric.e.liu@intel.com
- *
- * Date:    Feb 2008
- */
-
-#include <linux/module.h>
-#include <linux/relay.h>
-#include <linux/debugfs.h>
-#include <linux/ktime.h>
-
-#include <linux/kvm_host.h>
-
-#define KVM_TRACE_STATE_RUNNING 	(1 << 0)
-#define KVM_TRACE_STATE_PAUSE 		(1 << 1)
-#define KVM_TRACE_STATE_CLEARUP 	(1 << 2)
-
-struct kvm_trace {
-	int trace_state;
-	struct rchan *rchan;
-	struct dentry *lost_file;
-	atomic_t lost_records;
-};
-static struct kvm_trace *kvm_trace;
-
-struct kvm_trace_probe {
-	const char *name;
-	const char *format;
-	u32 timestamp_in;
-	marker_probe_func *probe_func;
-};
-
-static inline int calc_rec_size(int timestamp, int extra)
-{
-	int rec_size = KVM_TRC_HEAD_SIZE;
-
-	rec_size += extra;
-	return timestamp ? rec_size += KVM_TRC_CYCLE_SIZE : rec_size;
-}
-
-static void kvm_add_trace(void *probe_private, void *call_data,
-			  const char *format, va_list *args)
-{
-	struct kvm_trace_probe *p = probe_private;
-	struct kvm_trace *kt = kvm_trace;
-	struct kvm_trace_rec rec;
-	struct kvm_vcpu *vcpu;
-	int    i, size;
-	u32    extra;
-
-	if (unlikely(kt->trace_state != KVM_TRACE_STATE_RUNNING))
-		return;
-
-	rec.rec_val	= TRACE_REC_EVENT_ID(va_arg(*args, u32));
-	vcpu		= va_arg(*args, struct kvm_vcpu *);
-	rec.pid		= current->tgid;
-	rec.vcpu_id	= vcpu->vcpu_id;
-
-	extra   	= va_arg(*args, u32);
-	WARN_ON(!(extra <= KVM_TRC_EXTRA_MAX));
-	extra 		= min_t(u32, extra, KVM_TRC_EXTRA_MAX);
-
-	rec.rec_val |= TRACE_REC_TCS(p->timestamp_in)
-			| TRACE_REC_NUM_DATA_ARGS(extra);
-
-	if (p->timestamp_in) {
-		rec.u.timestamp.timestamp = ktime_to_ns(ktime_get());
-
-		for (i = 0; i < extra; i++)
-			rec.u.timestamp.extra_u32[i] = va_arg(*args, u32);
-	} else {
-		for (i = 0; i < extra; i++)
-			rec.u.notimestamp.extra_u32[i] = va_arg(*args, u32);
-	}
-
-	size = calc_rec_size(p->timestamp_in, extra * sizeof(u32));
-	relay_write(kt->rchan, &rec, size);
-}
-
-static struct kvm_trace_probe kvm_trace_probes[] = {
-	{ "kvm_trace_entryexit", "%u %p %u %u %u %u %u %u", 1, kvm_add_trace },
-	{ "kvm_trace_handler", "%u %p %u %u %u %u %u %u", 0, kvm_add_trace },
-};
-
-static int lost_records_get(void *data, u64 *val)
-{
-	struct kvm_trace *kt = data;
-
-	*val = atomic_read(&kt->lost_records);
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(kvm_trace_lost_ops, lost_records_get, NULL, "%llu\n");
-
-/*
- *  The relay channel is used in "no-overwrite" mode, it keeps trace of how
- *  many times we encountered a full subbuffer, to tell user space app the
- *  lost records there were.
- */
-static int kvm_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
-				     void *prev_subbuf, size_t prev_padding)
-{
-	struct kvm_trace *kt;
-
-	if (!relay_buf_full(buf)) {
-		if (!prev_subbuf) {
-			/*
-			 * executed only once when the channel is opened
-			 * save metadata as first record
-			 */
-			subbuf_start_reserve(buf, sizeof(u32));
-			*(u32 *)subbuf = 0x12345678;
-		}
-
-		return 1;
-	}
-
-	kt = buf->chan->private_data;
-	atomic_inc(&kt->lost_records);
-
-	return 0;
-}
-
-static struct dentry *kvm_create_buf_file_callack(const char *filename,
-						 struct dentry *parent,
-						 int mode,
-						 struct rchan_buf *buf,
-						 int *is_global)
-{
-	return debugfs_create_file(filename, mode, parent, buf,
-				   &relay_file_operations);
-}
-
-static int kvm_remove_buf_file_callback(struct dentry *dentry)
-{
-	debugfs_remove(dentry);
-	return 0;
-}
-
-static struct rchan_callbacks kvm_relay_callbacks = {
-	.subbuf_start 		= kvm_subbuf_start_callback,
-	.create_buf_file 	= kvm_create_buf_file_callack,
-	.remove_buf_file 	= kvm_remove_buf_file_callback,
-};
-
-static int do_kvm_trace_enable(struct kvm_user_trace_setup *kuts)
-{
-	struct kvm_trace *kt;
-	int i, r = -ENOMEM;
-
-	if (!kuts->buf_size || !kuts->buf_nr)
-		return -EINVAL;
-
-	kt = kzalloc(sizeof(*kt), GFP_KERNEL);
-	if (!kt)
-		goto err;
-
-	r = -EIO;
-	atomic_set(&kt->lost_records, 0);
-	kt->lost_file = debugfs_create_file("lost_records", 0444, kvm_debugfs_dir,
-					    kt, &kvm_trace_lost_ops);
-	if (!kt->lost_file)
-		goto err;
-
-	kt->rchan = relay_open("trace", kvm_debugfs_dir, kuts->buf_size,
-				kuts->buf_nr, &kvm_relay_callbacks, kt);
-	if (!kt->rchan)
-		goto err;
-
-	kvm_trace = kt;
-
-	for (i = 0; i < ARRAY_SIZE(kvm_trace_probes); i++) {
-		struct kvm_trace_probe *p = &kvm_trace_probes[i];
-
-		r = marker_probe_register(p->name, p->format, p->probe_func, p);
-		if (r)
-			printk(KERN_INFO "Unable to register probe %s\n",
-			       p->name);
-	}
-
-	kvm_trace->trace_state = KVM_TRACE_STATE_RUNNING;
-
-	return 0;
-err:
-	if (kt) {
-		if (kt->lost_file)
-			debugfs_remove(kt->lost_file);
-		if (kt->rchan)
-			relay_close(kt->rchan);
-		kfree(kt);
-	}
-	return r;
-}
-
-static int kvm_trace_enable(char __user *arg)
-{
-	struct kvm_user_trace_setup kuts;
-	int ret;
-
-	ret = copy_from_user(&kuts, arg, sizeof(kuts));
-	if (ret)
-		return -EFAULT;
-
-	ret = do_kvm_trace_enable(&kuts);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-static int kvm_trace_pause(void)
-{
-	struct kvm_trace *kt = kvm_trace;
-	int r = -EINVAL;
-
-	if (kt == NULL)
-		return r;
-
-	if (kt->trace_state == KVM_TRACE_STATE_RUNNING) {
-		kt->trace_state = KVM_TRACE_STATE_PAUSE;
-		relay_flush(kt->rchan);
-		r = 0;
-	}
-
-	return r;
-}
-
-void kvm_trace_cleanup(void)
-{
-	struct kvm_trace *kt = kvm_trace;
-	int i;
-
-	if (kt == NULL)
-		return;
-
-	if (kt->trace_state == KVM_TRACE_STATE_RUNNING ||
-	    kt->trace_state == KVM_TRACE_STATE_PAUSE) {
-
-		kt->trace_state = KVM_TRACE_STATE_CLEARUP;
-
-		for (i = 0; i < ARRAY_SIZE(kvm_trace_probes); i++) {
-			struct kvm_trace_probe *p = &kvm_trace_probes[i];
-			marker_probe_unregister(p->name, p->probe_func, p);
-		}
-		marker_synchronize_unregister();
-
-		relay_close(kt->rchan);
-		debugfs_remove(kt->lost_file);
-		kfree(kt);
-	}
-}
-
-int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg)
-{
-	void __user *argp = (void __user *)arg;
-	long r = -EINVAL;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	switch (ioctl) {
-	case KVM_TRACE_ENABLE:
-		r = kvm_trace_enable(argp);
-		break;
-	case KVM_TRACE_PAUSE:
-		r = kvm_trace_pause();
-		break;
-	case KVM_TRACE_DISABLE:
-		r = 0;
-		kvm_trace_cleanup();
-		break;
-	}
-
-	return r;
-}
-- 
cgit v1.2.3-70-g09d2


From a1b37100d9e29c1f8dc3e2f5490a205c80180e01 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 9 Jul 2009 15:33:52 +0300
Subject: KVM: Reduce runnability interface with arch support code

Remove kvm_cpu_has_interrupt() and kvm_arch_interrupt_allowed() from
interface between general code and arch code. kvm_arch_vcpu_runnable()
checks for interrupts instead.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/ia64/kvm/kvm-ia64.c        | 16 ++--------------
 arch/powerpc/kvm/powerpc.c      | 13 +------------
 arch/s390/kvm/interrupt.c       |  8 +-------
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/x86.c              |  6 ++++--
 include/linux/kvm_host.h        |  2 --
 virt/kvm/kvm_main.c             |  4 +---
 7 files changed, 11 insertions(+), 40 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index d7aa6bb8f47..0ad09f05efa 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1935,19 +1935,6 @@ int kvm_highest_pending_irq(struct kvm_vcpu *vcpu)
     return find_highest_bits((int *)&vpd->irr[0]);
 }
 
-int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
-{
-	if (kvm_highest_pending_irq(vcpu) != -1)
-		return 1;
-	return 0;
-}
-
-int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
-{
-	/* do real check here */
-	return 1;
-}
-
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.timer_fired;
@@ -1960,7 +1947,8 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE;
+	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) ||
+		(kvm_highest_pending_irq(vcpu) != -1);
 }
 
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 0341391eff1..2a4551f78f6 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -39,20 +39,9 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 	return gfn;
 }
 
-int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
-{
-	return !!(v->arch.pending_exceptions);
-}
-
-int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
-{
-	/* do real check here */
-	return 1;
-}
-
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	return !(v->arch.msr & MSR_WE);
+	return !(v->arch.msr & MSR_WE) || !!(v->arch.pending_exceptions);
 }
 
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 4d613415c43..2c2f9835341 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -283,7 +283,7 @@ static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
+static int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
@@ -320,12 +320,6 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
 	return rc;
 }
 
-int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
-{
-	/* do real check here */
-	return 1;
-}
-
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
 	return 0;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3f4f00a2353..08732d7b6d9 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -797,6 +797,8 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
 int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
+int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 11cfd897aac..b87d65d89a0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4890,8 +4890,10 @@ void kvm_arch_flush_shadow(struct kvm *kvm)
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE
-	       || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
-	       || vcpu->arch.nmi_pending;
+		|| vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
+		|| vcpu->arch.nmi_pending ||
+		(kvm_arch_interrupt_allowed(vcpu) &&
+		 kvm_cpu_has_interrupt(vcpu));
 }
 
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2c6a5f00874..4af56036a6b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -332,7 +332,6 @@ int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
 void kvm_arch_check_processor_compat(void *rtn);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
-int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 
 void kvm_free_physmem(struct kvm *kvm);
 
@@ -341,7 +340,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm);
 void kvm_free_all_assigned_devices(struct kvm *kvm);
 void kvm_arch_sync_events(struct kvm *kvm);
 
-int kvm_cpu_has_interrupt(struct kvm_vcpu *v);
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d7b9bbba26d..532af9b41ee 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1666,9 +1666,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	for (;;) {
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
-		if ((kvm_arch_interrupt_allowed(vcpu) &&
-					kvm_cpu_has_interrupt(vcpu)) ||
-				kvm_arch_vcpu_runnable(vcpu)) {
+		if (kvm_arch_vcpu_runnable(vcpu)) {
 			set_bit(KVM_REQ_UNHALT, &vcpu->requests);
 			break;
 		}
-- 
cgit v1.2.3-70-g09d2