[PATCH v3 0/4] KVM: lockdep improvements

[PATCH v3 0/4] KVM: lockdep improvements

[Maxim Levitsky]

This is	a continuation of my 'extract lock_all_vcpus/unlock_all_vcpus'
patch series.

Implement the suggestion of using lockdep's "nest_lock" feature
when locking all KVM vCPUs by adding mutex_trylock_nest_lock() and
mutex_lock_killable_nest_lock() and use these functions	in the
implementation of the
kvm_trylock_all_vcpus()/kvm_lock_all_vcpus()/kvm_unlock_all_vcpus().

Those changes allow removal of a custom workaround that was needed to
silence the lockdep warning in the SEV code and also stop lockdep from
complaining in case of ARM and RISC-V code which doesn't include the above
mentioned workaround.

Finally, it's worth noting that this patch series removes a fair
amount of duplicate code by implementing the logic in one place.

Best regards,
	Maxim Levitsky

Maxim Levitsky (4):
  arm64: KVM: use mutex_trylock_nest_lock when locking all vCPUs
  RISC-V: KVM: switch to kvm_lock/unlock_all_vcpus
  locking/mutex: implement mutex_lock_killable_nest_lock
  x86: KVM: SEV: implement kvm_lock_all_vcpus and use it

 arch/arm64/include/asm/kvm_host.h     |  3 --
 arch/arm64/kvm/arch_timer.c           |  4 +-
 arch/arm64/kvm/arm.c                  | 43 ----------------
 arch/arm64/kvm/vgic/vgic-init.c       |  4 +-
 arch/arm64/kvm/vgic/vgic-its.c        |  8 +--
 arch/arm64/kvm/vgic/vgic-kvm-device.c | 12 ++---
 arch/riscv/kvm/aia_device.c           | 34 +------------
 arch/x86/kvm/svm/sev.c                | 72 ++-------------------------
 include/linux/kvm_host.h              |  4 ++
 include/linux/mutex.h                 | 17 +++++--
 kernel/locking/mutex.c                |  7 +--
 virt/kvm/kvm_main.c                   | 59 ++++++++++++++++++++++
 12 files changed, 100 insertions(+), 167 deletions(-)

-- 
2.46.0

[PATCH v3 1/4] arm64: KVM: use mutex_trylock_nest_lock when locking all vCPUs

[Maxim Levitsky]

Use mutex_trylock_nest_lock instead of mutex_trylock when locking all vCPUs
of a VM, to avoid triggering a lockdep warning, if the VM is configured to
have more than MAX_LOCK_DEPTH vCPUs.

This fixes the following false lockdep warning:

[  328.171264] BUG: MAX_LOCK_DEPTH too low!
[  328.175227] turning off the locking correctness validator.
[  328.180726] Please attach the output of /proc/lock_stat to the bug report
[  328.187531] depth: 48  max: 48!
[  328.190678] 48 locks held by qemu-kvm/11664:
[  328.194957]  #0: ffff800086de5ba0 (&kvm->lock){+.+.}-{3:3}, at: kvm_ioctl_create_device+0x174/0x5b0
[  328.204048]  #1: ffff0800e78800b8 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0
[  328.212521]  #2: ffff07ffeee51e98 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0
[  328.220991]  #3: ffff0800dc7d80b8 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0
[  328.229463]  #4: ffff07ffe0c980b8 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0
[  328.237934]  #5: ffff0800a3883c78 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0
[  328.246405]  #6: ffff07fffbe480b8 (&vcpu->mutex){+.+.}-{3:3}, at: lock_all_vcpus+0x16c/0x2a0

Since the locking of all vCPUs is a primitive that can be useful in other
architectures that are supported by KVM, also move the code to kvm_main.c

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 arch/arm64/include/asm/kvm_host.h     |  3 --
 arch/arm64/kvm/arch_timer.c           |  4 +--
 arch/arm64/kvm/arm.c                  | 43 ---------------------------
 arch/arm64/kvm/vgic/vgic-init.c       |  4 +--
 arch/arm64/kvm/vgic/vgic-its.c        |  8 ++---
 arch/arm64/kvm/vgic/vgic-kvm-device.c | 12 ++++----
 include/linux/kvm_host.h              |  3 ++
 virt/kvm/kvm_main.c                   | 34 +++++++++++++++++++++
 8 files changed, 51 insertions(+), 60 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e98cfe7855a6..96ce0b01a61e 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1263,9 +1263,6 @@ int __init populate_sysreg_config(const struct sys_reg_desc *sr,
 				  unsigned int idx);
 int __init populate_nv_trap_config(void);
 
-bool lock_all_vcpus(struct kvm *kvm);
-void unlock_all_vcpus(struct kvm *kvm);
-
 void kvm_calculate_traps(struct kvm_vcpu *vcpu);
 
 /* MMIO helpers */
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 5133dcbfe9f7..fdbc8beec930 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -1766,7 +1766,7 @@ int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm,
 
 	mutex_lock(&kvm->lock);
 
-	if (lock_all_vcpus(kvm)) {
+	if (!kvm_trylock_all_vcpus(kvm)) {
 		set_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &kvm->arch.flags);
 
 		/*
@@ -1778,7 +1778,7 @@ int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm,
 		kvm->arch.timer_data.voffset = offset->counter_offset;
 		kvm->arch.timer_data.poffset = offset->counter_offset;
 
-		unlock_all_vcpus(kvm);
+		kvm_unlock_all_vcpus(kvm);
 	} else {
 		ret = -EBUSY;
 	}
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 68fec8c95fee..d31f42a71bdc 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1914,49 +1914,6 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 	}
 }
 
-/* unlocks vcpus from @vcpu_lock_idx and smaller */
-static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx)
-{
-	struct kvm_vcpu *tmp_vcpu;
-
-	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
-		tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
-		mutex_unlock(&tmp_vcpu->mutex);
-	}
-}
-
-void unlock_all_vcpus(struct kvm *kvm)
-{
-	lockdep_assert_held(&kvm->lock);
-
-	unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1);
-}
-
-/* Returns true if all vcpus were locked, false otherwise */
-bool lock_all_vcpus(struct kvm *kvm)
-{
-	struct kvm_vcpu *tmp_vcpu;
-	unsigned long c;
-
-	lockdep_assert_held(&kvm->lock);
-
-	/*
-	 * Any time a vcpu is in an ioctl (including running), the
-	 * core KVM code tries to grab the vcpu->mutex.
-	 *
-	 * By grabbing the vcpu->mutex of all VCPUs we ensure that no
-	 * other VCPUs can fiddle with the state while we access it.
-	 */
-	kvm_for_each_vcpu(c, tmp_vcpu, kvm) {
-		if (!mutex_trylock(&tmp_vcpu->mutex)) {
-			unlock_vcpus(kvm, c - 1);
-			return false;
-		}
-	}
-
-	return true;
-}
-
 static unsigned long nvhe_percpu_size(void)
 {
 	return (unsigned long)CHOOSE_NVHE_SYM(__per_cpu_end) -
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 1f33e71c2a73..6a426d403a6b 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -88,7 +88,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 	lockdep_assert_held(&kvm->lock);
 
 	ret = -EBUSY;
-	if (!lock_all_vcpus(kvm))
+	if (kvm_trylock_all_vcpus(kvm))
 		return ret;
 
 	mutex_lock(&kvm->arch.config_lock);
@@ -142,7 +142,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
 
 out_unlock:
 	mutex_unlock(&kvm->arch.config_lock);
-	unlock_all_vcpus(kvm);
+	kvm_unlock_all_vcpus(kvm);
 	return ret;
 }
 
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index fb96802799c6..7454388e3646 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -1999,7 +1999,7 @@ static int vgic_its_attr_regs_access(struct kvm_device *dev,
 
 	mutex_lock(&dev->kvm->lock);
 
-	if (!lock_all_vcpus(dev->kvm)) {
+	if (kvm_trylock_all_vcpus(dev->kvm)) {
 		mutex_unlock(&dev->kvm->lock);
 		return -EBUSY;
 	}
@@ -2034,7 +2034,7 @@ static int vgic_its_attr_regs_access(struct kvm_device *dev,
 	}
 out:
 	mutex_unlock(&dev->kvm->arch.config_lock);
-	unlock_all_vcpus(dev->kvm);
+	kvm_unlock_all_vcpus(dev->kvm);
 	mutex_unlock(&dev->kvm->lock);
 	return ret;
 }
@@ -2704,7 +2704,7 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
 
 	mutex_lock(&kvm->lock);
 
-	if (!lock_all_vcpus(kvm)) {
+	if (kvm_trylock_all_vcpus(kvm)) {
 		mutex_unlock(&kvm->lock);
 		return -EBUSY;
 	}
@@ -2726,7 +2726,7 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
 
 	mutex_unlock(&its->its_lock);
 	mutex_unlock(&kvm->arch.config_lock);
-	unlock_all_vcpus(kvm);
+	kvm_unlock_all_vcpus(kvm);
 	mutex_unlock(&kvm->lock);
 	return ret;
 }
diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index 359094f68c23..f9ae790163fb 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -268,7 +268,7 @@ static int vgic_set_common_attr(struct kvm_device *dev,
 				return -ENXIO;
 			mutex_lock(&dev->kvm->lock);
 
-			if (!lock_all_vcpus(dev->kvm)) {
+			if (kvm_trylock_all_vcpus(dev->kvm)) {
 				mutex_unlock(&dev->kvm->lock);
 				return -EBUSY;
 			}
@@ -276,7 +276,7 @@ static int vgic_set_common_attr(struct kvm_device *dev,
 			mutex_lock(&dev->kvm->arch.config_lock);
 			r = vgic_v3_save_pending_tables(dev->kvm);
 			mutex_unlock(&dev->kvm->arch.config_lock);
-			unlock_all_vcpus(dev->kvm);
+			kvm_unlock_all_vcpus(dev->kvm);
 			mutex_unlock(&dev->kvm->lock);
 			return r;
 		}
@@ -390,7 +390,7 @@ static int vgic_v2_attr_regs_access(struct kvm_device *dev,
 
 	mutex_lock(&dev->kvm->lock);
 
-	if (!lock_all_vcpus(dev->kvm)) {
+	if (kvm_trylock_all_vcpus(dev->kvm)) {
 		mutex_unlock(&dev->kvm->lock);
 		return -EBUSY;
 	}
@@ -415,7 +415,7 @@ static int vgic_v2_attr_regs_access(struct kvm_device *dev,
 
 out:
 	mutex_unlock(&dev->kvm->arch.config_lock);
-	unlock_all_vcpus(dev->kvm);
+	kvm_unlock_all_vcpus(dev->kvm);
 	mutex_unlock(&dev->kvm->lock);
 
 	if (!ret && !is_write)
@@ -554,7 +554,7 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 
 	mutex_lock(&dev->kvm->lock);
 
-	if (!lock_all_vcpus(dev->kvm)) {
+	if (kvm_trylock_all_vcpus(dev->kvm)) {
 		mutex_unlock(&dev->kvm->lock);
 		return -EBUSY;
 	}
@@ -611,7 +611,7 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev,
 
 out:
 	mutex_unlock(&dev->kvm->arch.config_lock);
-	unlock_all_vcpus(dev->kvm);
+	kvm_unlock_all_vcpus(dev->kvm);
 	mutex_unlock(&dev->kvm->lock);
 
 	if (!ret && uaccess && !is_write) {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1dedc421b3e3..10d6652c7aa0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1015,6 +1015,9 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
 
 void kvm_destroy_vcpus(struct kvm *kvm);
 
+int kvm_trylock_all_vcpus(struct kvm *kvm);
+void kvm_unlock_all_vcpus(struct kvm *kvm);
+
 void vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 69782df3617f..834f08dfa24c 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1368,6 +1368,40 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+/*
+ * Try to lock all of the VM's vCPUs.
+ * Assumes that the kvm->lock is held.
+ */
+int kvm_trylock_all_vcpus(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu;
+	unsigned long i, j;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		if (!mutex_trylock_nest_lock(&vcpu->mutex, &kvm->lock))
+			goto out_unlock;
+	return 0;
+
+out_unlock:
+	kvm_for_each_vcpu(j, vcpu, kvm) {
+		if (i == j)
+			break;
+		mutex_unlock(&vcpu->mutex);
+	}
+	return -EINTR;
+}
+EXPORT_SYMBOL_GPL(kvm_trylock_all_vcpus);
+
+void kvm_unlock_all_vcpus(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu;
+	unsigned long i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		mutex_unlock(&vcpu->mutex);
+}
+EXPORT_SYMBOL_GPL(kvm_unlock_all_vcpus);
+
 /*
  * Allocation size is twice as large as the actual dirty bitmap size.
  * See kvm_vm_ioctl_get_dirty_log() why this is needed.
-- 
2.46.0

[PATCH v3 2/4] RISC-V: KVM: switch to kvm_lock/unlock_all_vcpus

[Maxim Levitsky]

Use the kvm_trylock_all_vcpus()/unlock_all_vcpus() instead of riscv's own
implementation, to avoid triggering a lockdep warning,
if the VM is configured to have more than MAX_LOCK_DEPTH vCPUs.

Compile tested only.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 arch/riscv/kvm/aia_device.c | 34 ++--------------------------------
 1 file changed, 2 insertions(+), 32 deletions(-)

diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c
index 39cd26af5a69..6315821f0d69 100644
--- a/arch/riscv/kvm/aia_device.c
+++ b/arch/riscv/kvm/aia_device.c
@@ -12,36 +12,6 @@
 #include <linux/kvm_host.h>
 #include <linux/uaccess.h>
 
-static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx)
-{
-	struct kvm_vcpu *tmp_vcpu;
-
-	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
-		tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
-		mutex_unlock(&tmp_vcpu->mutex);
-	}
-}
-
-static void unlock_all_vcpus(struct kvm *kvm)
-{
-	unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1);
-}
-
-static bool lock_all_vcpus(struct kvm *kvm)
-{
-	struct kvm_vcpu *tmp_vcpu;
-	unsigned long c;
-
-	kvm_for_each_vcpu(c, tmp_vcpu, kvm) {
-		if (!mutex_trylock(&tmp_vcpu->mutex)) {
-			unlock_vcpus(kvm, c - 1);
-			return false;
-		}
-	}
-
-	return true;
-}
-
 static int aia_create(struct kvm_device *dev, u32 type)
 {
 	int ret;
@@ -53,7 +23,7 @@ static int aia_create(struct kvm_device *dev, u32 type)
 		return -EEXIST;
 
 	ret = -EBUSY;
-	if (!lock_all_vcpus(kvm))
+	if (kvm_trylock_all_vcpus(kvm))
 		return ret;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -65,7 +35,7 @@ static int aia_create(struct kvm_device *dev, u32 type)
 	kvm->arch.aia.in_kernel = true;
 
 out_unlock:
-	unlock_all_vcpus(kvm);
+	kvm_unlock_all_vcpus(kvm);
 	return ret;
 }
 
-- 
2.46.0

[PATCH v3 3/4] locking/mutex: implement mutex_lock_killable_nest_lock

[Maxim Levitsky]

KVM's SEV intra-host migration code needs to lock all vCPUs
of the source and the target VM, before it proceeds with the migration.

The number of vCPUs that belong to each VM is not bounded by anything
except a self-imposed KVM limit of CONFIG_KVM_MAX_NR_VCPUS vCPUs which is
significantly larger than the depth of lockdep's lock stack.

Luckily, the locks in both of the cases mentioned above, are held under
the 'kvm->lock' of each VM, which means that we can use the little
known lockdep feature called a "nest_lock" to support this use case in
a cleaner way, compared to the way it's currently done.

Implement and expose 'mutex_lock_killable_nest_lock' for this
purpose.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 include/linux/mutex.h  | 17 +++++++++++++----
 kernel/locking/mutex.c |  7 ++++---
 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index da4518cfd59c..a039fa8c1780 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -156,16 +156,15 @@ static inline int __devm_mutex_init(struct device *dev, struct mutex *lock)
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
 extern void _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock);
-
 extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock,
 					unsigned int subclass);
-extern int __must_check mutex_lock_killable_nested(struct mutex *lock,
-					unsigned int subclass);
+extern int __must_check _mutex_lock_killable(struct mutex *lock,
+		unsigned int subclass, struct lockdep_map *nest_lock);
 extern void mutex_lock_io_nested(struct mutex *lock, unsigned int subclass);
 
 #define mutex_lock(lock) mutex_lock_nested(lock, 0)
 #define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0)
-#define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0)
+#define mutex_lock_killable(lock) _mutex_lock_killable(lock, 0, NULL)
 #define mutex_lock_io(lock) mutex_lock_io_nested(lock, 0)
 
 #define mutex_lock_nest_lock(lock, nest_lock)				\
@@ -174,6 +173,15 @@ do {									\
 	_mutex_lock_nest_lock(lock, &(nest_lock)->dep_map);		\
 } while (0)
 
+#define mutex_lock_killable_nest_lock(lock, nest_lock)			\
+(									\
+	typecheck(struct lockdep_map *, &(nest_lock)->dep_map),		\
+	_mutex_lock_killable(lock, 0, &(nest_lock)->dep_map)		\
+)
+
+#define mutex_lock_killable_nested(lock, subclass) \
+	_mutex_lock_killable(lock, subclass, NULL)
+
 #else
 extern void mutex_lock(struct mutex *lock);
 extern int __must_check mutex_lock_interruptible(struct mutex *lock);
@@ -183,6 +191,7 @@ extern void mutex_lock_io(struct mutex *lock);
 # define mutex_lock_nested(lock, subclass) mutex_lock(lock)
 # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
 # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
+# define mutex_lock_killable_nest_lock(lock, nest_lock) mutex_lock_killable(lock)
 # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
 # define mutex_lock_io_nested(lock, subclass) mutex_lock_io(lock)
 #endif
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index c75a838d3bae..234923121ff0 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -808,11 +808,12 @@ _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
 EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
 
 int __sched
-mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
+_mutex_lock_killable(struct mutex *lock, unsigned int subclass,
+				      struct lockdep_map *nest)
 {
-	return __mutex_lock(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_);
+	return __mutex_lock(lock, TASK_KILLABLE, subclass, nest, _RET_IP_);
 }
-EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);
+EXPORT_SYMBOL_GPL(_mutex_lock_killable);
 
 int __sched
 mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
-- 
2.46.0

[PATCH v3 4/4] x86: KVM: SEV: implement kvm_lock_all_vcpus and use it

[Maxim Levitsky]

Implement kvm_lock_all_vcpus() and use it instead of
sev own sev_{lock|unlock}_vcpus_for_migration().

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 arch/x86/kvm/svm/sev.c   | 72 +++-------------------------------------
 include/linux/kvm_host.h |  1 +
 virt/kvm/kvm_main.c      | 25 ++++++++++++++
 3 files changed, 30 insertions(+), 68 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0bc708ee2788..16db6179013d 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1882,70 +1882,6 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
 	atomic_set_release(&src_sev->migration_in_progress, 0);
 }
 
-/* vCPU mutex subclasses.  */
-enum sev_migration_role {
-	SEV_MIGRATION_SOURCE = 0,
-	SEV_MIGRATION_TARGET,
-	SEV_NR_MIGRATION_ROLES,
-};
-
-static int sev_lock_vcpus_for_migration(struct kvm *kvm,
-					enum sev_migration_role role)
-{
-	struct kvm_vcpu *vcpu;
-	unsigned long i, j;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (mutex_lock_killable_nested(&vcpu->mutex, role))
-			goto out_unlock;
-
-#ifdef CONFIG_PROVE_LOCKING
-		if (!i)
-			/*
-			 * Reset the role to one that avoids colliding with
-			 * the role used for the first vcpu mutex.
-			 */
-			role = SEV_NR_MIGRATION_ROLES;
-		else
-			mutex_release(&vcpu->mutex.dep_map, _THIS_IP_);
-#endif
-	}
-
-	return 0;
-
-out_unlock:
-
-	kvm_for_each_vcpu(j, vcpu, kvm) {
-		if (i == j)
-			break;
-
-#ifdef CONFIG_PROVE_LOCKING
-		if (j)
-			mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_);
-#endif
-
-		mutex_unlock(&vcpu->mutex);
-	}
-	return -EINTR;
-}
-
-static void sev_unlock_vcpus_for_migration(struct kvm *kvm)
-{
-	struct kvm_vcpu *vcpu;
-	unsigned long i;
-	bool first = true;
-
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (first)
-			first = false;
-		else
-			mutex_acquire(&vcpu->mutex.dep_map,
-				      SEV_NR_MIGRATION_ROLES, 0, _THIS_IP_);
-
-		mutex_unlock(&vcpu->mutex);
-	}
-}
-
 static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
 {
 	struct kvm_sev_info *dst = to_kvm_sev_info(dst_kvm);
@@ -2083,10 +2019,10 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 		charged = true;
 	}
 
-	ret = sev_lock_vcpus_for_migration(kvm, SEV_MIGRATION_SOURCE);
+	ret = kvm_lock_all_vcpus(kvm);
 	if (ret)
 		goto out_dst_cgroup;
-	ret = sev_lock_vcpus_for_migration(source_kvm, SEV_MIGRATION_TARGET);
+	ret = kvm_lock_all_vcpus(source_kvm);
 	if (ret)
 		goto out_dst_vcpu;
 
@@ -2100,9 +2036,9 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 	ret = 0;
 
 out_source_vcpu:
-	sev_unlock_vcpus_for_migration(source_kvm);
+	kvm_unlock_all_vcpus(source_kvm);
 out_dst_vcpu:
-	sev_unlock_vcpus_for_migration(kvm);
+	kvm_unlock_all_vcpus(kvm);
 out_dst_cgroup:
 	/* Operates on the source on success, on the destination on failure.  */
 	if (charged)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 10d6652c7aa0..a6140415c693 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1016,6 +1016,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
 void kvm_destroy_vcpus(struct kvm *kvm);
 
 int kvm_trylock_all_vcpus(struct kvm *kvm);
+int kvm_lock_all_vcpus(struct kvm *kvm);
 void kvm_unlock_all_vcpus(struct kvm *kvm);
 
 void vcpu_load(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 834f08dfa24c..9211b07b0565 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1392,6 +1392,31 @@ int kvm_trylock_all_vcpus(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_trylock_all_vcpus);
 
+/*
+ * Lock all of the VM's vCPUs.
+ * Assumes that the kvm->lock is held.
+ * Returns -EINTR if the process is killed.
+ */
+int kvm_lock_all_vcpus(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu;
+	unsigned long i, j;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		if (mutex_lock_killable_nest_lock(&vcpu->mutex, &kvm->lock))
+			goto out_unlock;
+	return 0;
+
+out_unlock:
+	kvm_for_each_vcpu(j, vcpu, kvm) {
+		if (i == j)
+			break;
+		mutex_unlock(&vcpu->mutex);
+	}
+	return -EINTR;
+}
+EXPORT_SYMBOL_GPL(kvm_lock_all_vcpus);
+
 void kvm_unlock_all_vcpus(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
-- 
2.46.0

Re: [PATCH v3 0/4] KVM: lockdep improvements

[mlevitsk]

On Wed, 2025-04-30 at 16:23 -0400, Maxim Levitsky wrote:
> This is	a continuation of my 'extract
> lock_all_vcpus/unlock_all_vcpus'
> patch series.
> 
> Implement the suggestion of using lockdep's "nest_lock" feature
> when locking all KVM vCPUs by adding mutex_trylock_nest_lock() and
> mutex_lock_killable_nest_lock() and use these functions	in the
> implementation of the
> kvm_trylock_all_vcpus()/kvm_lock_all_vcpus()/kvm_unlock_all_vcpus().
> 
> Those changes allow removal of a custom workaround that was needed to
> silence the lockdep warning in the SEV code and also stop lockdep
> from
> complaining in case of ARM and RISC-V code which doesn't include the
> above
> mentioned workaround.
> 
> Finally, it's worth noting that this patch series removes a fair
> amount of duplicate code by implementing the logic in one place.
> 
> Best regards,
> 	Maxim Levitsky
> 
> Maxim Levitsky (4):
>   arm64: KVM: use mutex_trylock_nest_lock when locking all vCPUs
>   RISC-V: KVM: switch to kvm_lock/unlock_all_vcpus
>   locking/mutex: implement mutex_lock_killable_nest_lock
>   x86: KVM: SEV: implement kvm_lock_all_vcpus and use it
> 
>  arch/arm64/include/asm/kvm_host.h     |  3 --
>  arch/arm64/kvm/arch_timer.c           |  4 +-
>  arch/arm64/kvm/arm.c                  | 43 ----------------
>  arch/arm64/kvm/vgic/vgic-init.c       |  4 +-
>  arch/arm64/kvm/vgic/vgic-its.c        |  8 +--
>  arch/arm64/kvm/vgic/vgic-kvm-device.c | 12 ++---
>  arch/riscv/kvm/aia_device.c           | 34 +------------
>  arch/x86/kvm/svm/sev.c                | 72 ++-----------------------
> --
>  include/linux/kvm_host.h              |  4 ++
>  include/linux/mutex.h                 | 17 +++++--
>  kernel/locking/mutex.c                |  7 +--
>  virt/kvm/kvm_main.c                   | 59 ++++++++++++++++++++++
>  12 files changed, 100 insertions(+), 167 deletions(-)
> 
> -- 
> 2.46.0
> 
> 


I forgot to send first patch in the series, resending.

Best regards,
	Maxim Levitsky

Re: [PATCH v3 1/4] arm64: KVM: use mutex_trylock_nest_lock when locking all vCPUs

[kernel test robot]

Hi Maxim,

kernel test robot noticed the following build errors:

[auto build test ERROR on kvm/queue]
[also build test ERROR on kvm/next kvmarm/next tip/locking/core linus/master v6.15-rc5 next-20250507]
[cannot apply to kvm/linux-next]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Maxim-Levitsky/arm64-KVM-use-mutex_trylock_nest_lock-when-locking-all-vCPUs/20250501-042643
base:   https://git.kernel.org/pub/scm/virt/kvm/kvm.git queue
patch link:    https://lore.kernel.org/r/20250430202311.364641-2-mlevitsk%40redhat.com
patch subject: [PATCH v3 1/4] arm64: KVM: use mutex_trylock_nest_lock when locking all vCPUs
config: x86_64-rhel-9.4 (https://download.01.org/0day-ci/archive/20250508/202505080024.CZZ0ssB5-lkp@intel.com/config)
compiler: gcc-12 (Debian 12.2.0-14) 12.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250508/202505080024.CZZ0ssB5-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202505080024.CZZ0ssB5-lkp@intel.com/

All errors (new ones prefixed by >>):

   arch/x86/kvm/../../../virt/kvm/kvm_main.c: In function 'kvm_trylock_all_vcpus':
>> arch/x86/kvm/../../../virt/kvm/kvm_main.c:1381:22: error: implicit declaration of function 'mutex_trylock_nest_lock'; did you mean 'mutex_lock_nest_lock'? [-Werror=implicit-function-declaration]
    1381 |                 if (!mutex_trylock_nest_lock(&vcpu->mutex, &kvm->lock))
         |                      ^~~~~~~~~~~~~~~~~~~~~~~
         |                      mutex_lock_nest_lock
   cc1: some warnings being treated as errors


vim +1381 arch/x86/kvm/../../../virt/kvm/kvm_main.c

  1370	
  1371	/*
  1372	 * Try to lock all of the VM's vCPUs.
  1373	 * Assumes that the kvm->lock is held.
  1374	 */
  1375	int kvm_trylock_all_vcpus(struct kvm *kvm)
  1376	{
  1377		struct kvm_vcpu *vcpu;
  1378		unsigned long i, j;
  1379	
  1380		kvm_for_each_vcpu(i, vcpu, kvm)
> 1381			if (!mutex_trylock_nest_lock(&vcpu->mutex, &kvm->lock))
  1382				goto out_unlock;
  1383		return 0;
  1384	
  1385	out_unlock:
  1386		kvm_for_each_vcpu(j, vcpu, kvm) {
  1387			if (i == j)
  1388				break;
  1389			mutex_unlock(&vcpu->mutex);
  1390		}
  1391		return -EINTR;
  1392	}
  1393	EXPORT_SYMBOL_GPL(kvm_trylock_all_vcpus);
  1394	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki