KVM: Use dedicated mutex to protect kvm_usage_count to avoid deadlock

Use a dedicated mutex to guard kvm_usage_count to fix a potential deadlock
on x86 due to a chain of locks and SRCU synchronizations.  Translating the
below lockdep splat, CPU1 #6 will wait on CPU0 #1, CPU0 #8 will wait on
CPU2 #3, and CPU2 #7 will wait on CPU1 #4 (if there's a writer, due to the
fairness of r/w semaphores).

    CPU0                     CPU1                     CPU2
1   lock(&kvm->slots_lock);
2                                                     lock(&vcpu->mutex);
3                                                     lock(&kvm->srcu);
4                            lock(cpu_hotplug_lock);
5                            lock(kvm_lock);
6                            lock(&kvm->slots_lock);
7                                                     lock(cpu_hotplug_lock);
8   sync(&kvm->srcu);

Note, there are likely more potential deadlocks in KVM x86, e.g. the same
pattern of taking cpu_hotplug_lock outside of kvm_lock likely exists with
__kvmclock_cpufreq_notifier(), but actually triggering such deadlocks is
beyond rare due to the combination of dependencies and timings involved.
E.g. the cpufreq notifier is only used on older CPUs without a constant
TSC, mucking with the NX hugepage mitigation while VMs are running is very
uncommon, and doing so while also onlining/offlining a CPU (necessary to
generate contention on cpu_hotplug_lock) would be even more unusual.

  ======================================================
  WARNING: possible circular locking dependency detected
  6.10.0-smp--c257535a0c9d-pip #330 Tainted: G S         O
  ------------------------------------------------------
  tee/35048 is trying to acquire lock:
  ff6a80eced71e0a8 (&kvm->slots_lock){+.+.}-{3:3}, at: set_nx_huge_pages+0x179/0x1e0 [kvm]

  but task is already holding lock:
  ffffffffc07abb08 (kvm_lock){+.+.}-{3:3}, at: set_nx_huge_pages+0x14a/0x1e0 [kvm]

  which lock already depends on the new lock.

   the existing dependency chain (in reverse order) is:

  -> #3 (kvm_lock){+.+.}-{3:3}:
         __mutex_lock+0x6a/0xb40
         mutex_lock_nested+0x1f/0x30
         kvm_dev_ioctl+0x4fb/0xe50 [kvm]
         __se_sys_ioctl+0x7b/0xd0
         __x64_sys_ioctl+0x21/0x30
         x64_sys_call+0x15d0/0x2e60
         do_syscall_64+0x83/0x160
         entry_SYSCALL_64_after_hwframe+0x76/0x7e

  -> #2 (cpu_hotplug_lock){++++}-{0:0}:
         cpus_read_lock+0x2e/0xb0
         static_key_slow_inc+0x16/0x30
         kvm_lapic_set_base+0x6a/0x1c0 [kvm]
         kvm_set_apic_base+0x8f/0xe0 [kvm]
         kvm_set_msr_common+0x9ae/0xf80 [kvm]
         vmx_set_msr+0xa54/0xbe0 [kvm_intel]
         __kvm_set_msr+0xb6/0x1a0 [kvm]
         kvm_arch_vcpu_ioctl+0xeca/0x10c0 [kvm]
         kvm_vcpu_ioctl+0x485/0x5b0 [kvm]
         __se_sys_ioctl+0x7b/0xd0
         __x64_sys_ioctl+0x21/0x30
         x64_sys_call+0x15d0/0x2e60
         do_syscall_64+0x83/0x160
         entry_SYSCALL_64_after_hwframe+0x76/0x7e

  -> #1 (&kvm->srcu){.+.+}-{0:0}:
         __synchronize_srcu+0x44/0x1a0
         synchronize_srcu_expedited+0x21/0x30
         kvm_swap_active_memslots+0x110/0x1c0 [kvm]
         kvm_set_memslot+0x360/0x620 [kvm]
         __kvm_set_memory_region+0x27b/0x300 [kvm]
         kvm_vm_ioctl_set_memory_region+0x43/0x60 [kvm]
         kvm_vm_ioctl+0x295/0x650 [kvm]
         __se_sys_ioctl+0x7b/0xd0
         __x64_sys_ioctl+0x21/0x30
         x64_sys_call+0x15d0/0x2e60
         do_syscall_64+0x83/0x160
         entry_SYSCALL_64_after_hwframe+0x76/0x7e

  -> #0 (&kvm->slots_lock){+.+.}-{3:3}:
         __lock_acquire+0x15ef/0x2e30
         lock_acquire+0xe0/0x260
         __mutex_lock+0x6a/0xb40
         mutex_lock_nested+0x1f/0x30
         set_nx_huge_pages+0x179/0x1e0 [kvm]
         param_attr_store+0x93/0x100
         module_attr_store+0x22/0x40
         sysfs_kf_write+0x81/0xb0
         kernfs_fop_write_iter+0x133/0x1d0
         vfs_write+0x28d/0x380
         ksys_write+0x70/0xe0
         __x64_sys_write+0x1f/0x30
         x64_sys_call+0x281b/0x2e60
         do_syscall_64+0x83/0x160
         entry_SYSCALL_64_after_hwframe+0x76/0x7e

Cc: Chao Gao <[email protected]>
Fixes: 0bf5049 ("KVM: Drop kvm_count_lock and instead protect kvm_usage_count with kvm_lock")
Cc: [email protected]
Signed-off-by: Sean Christopherson <[email protected]>

Author: sean-jc

Documentation/virt/kvm/locking.rst

@@ -227,7 +227,13 @@ time it will be set using the Dirty tracking mechanism described above.
 :Type:		mutex
 :Arch:		any
 :Protects:	- vm_list
-		- kvm_usage_count
+
+``kvm_usage_count``
+^^^^^^^^^^^^^^^^^^^
+
+:Type:		mutex
+:Arch:		any
+:Protects:	- kvm_usage_count
 		- hardware virtualization enable/disable
 :Comment:	KVM also disables CPU hotplug via cpus_read_lock() during
 		enable/disable.
@@ -290,11 +296,12 @@ time it will be set using the Dirty tracking mechanism described above.
 		wakeup.
 
 ``vendor_module_lock``
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+^^^^^^^^^^^^^^^^^^^^^^
 :Type:		mutex
 :Arch:		x86
 :Protects:	loading a vendor module (kvm_amd or kvm_intel)
-:Comment:	Exists because using kvm_lock leads to deadlock.  cpu_hotplug_lock is
-    taken outside of kvm_lock, e.g. in KVM's CPU online/offline callbacks, and
-    many operations need to take cpu_hotplug_lock when loading a vendor module,
-    e.g. updating static calls.
+:Comment:	Exists because using kvm_lock leads to deadlock.  kvm_lock is taken
+    in notifiers, e.g. __kvmclock_cpufreq_notifier(), that may be invoked while
+    cpu_hotplug_lock is held, e.g. from cpufreq_boost_trigger_state(), and many
+    operations need to take cpu_hotplug_lock when loading a vendor module, e.g.
+    updating static calls.

virt/kvm/kvm_main.c

@@ -5590,6 +5590,7 @@ __visible bool kvm_rebooting;
 EXPORT_SYMBOL_GPL(kvm_rebooting);
 
 static DEFINE_PER_CPU(bool, hardware_enabled);
+static DEFINE_MUTEX(kvm_usage_lock);
 static int kvm_usage_count;
 
 static int __hardware_enable_nolock(void)
@@ -5622,10 +5623,10 @@ static int kvm_online_cpu(unsigned int cpu)
 	 * be enabled. Otherwise running VMs would encounter unrecoverable
 	 * errors when scheduled to this CPU.
 	 */
-	mutex_lock(&kvm_lock);
+	mutex_lock(&kvm_usage_lock);
 	if (kvm_usage_count)
 		ret = __hardware_enable_nolock();
-	mutex_unlock(&kvm_lock);
+	mutex_unlock(&kvm_usage_lock);
 	return ret;
 }
 
@@ -5645,10 +5646,10 @@ static void hardware_disable_nolock(void *junk)
 
 static int kvm_offline_cpu(unsigned int cpu)
 {
-	mutex_lock(&kvm_lock);
+	mutex_lock(&kvm_usage_lock);
 	if (kvm_usage_count)
 		hardware_disable_nolock(NULL);
-	mutex_unlock(&kvm_lock);
+	mutex_unlock(&kvm_usage_lock);
 	return 0;
 }
 
@@ -5664,9 +5665,9 @@ static void hardware_disable_all_nolock(void)
 static void hardware_disable_all(void)
 {
 	cpus_read_lock();
-	mutex_lock(&kvm_lock);
+	mutex_lock(&kvm_usage_lock);
 	hardware_disable_all_nolock();
-	mutex_unlock(&kvm_lock);
+	mutex_unlock(&kvm_usage_lock);
 	cpus_read_unlock();
 }
 
@@ -5697,7 +5698,7 @@ static int hardware_enable_all(void)
 	 * enable hardware multiple times.
 	 */
 	cpus_read_lock();
-	mutex_lock(&kvm_lock);
+	mutex_lock(&kvm_usage_lock);
 
 	r = 0;
 
@@ -5711,7 +5712,7 @@ static int hardware_enable_all(void)
 		}
 	}
 
-	mutex_unlock(&kvm_lock);
+	mutex_unlock(&kvm_usage_lock);
 	cpus_read_unlock();
 
 	return r;
@@ -5739,13 +5740,13 @@ static int kvm_suspend(void)
 {
 	/*
 	 * Secondary CPUs and CPU hotplug are disabled across the suspend/resume
-	 * callbacks, i.e. no need to acquire kvm_lock to ensure the usage count
-	 * is stable.  Assert that kvm_lock is not held to ensure the system
-	 * isn't suspended while KVM is enabling hardware.  Hardware enabling
-	 * can be preempted, but the task cannot be frozen until it has dropped
-	 * all locks (userspace tasks are frozen via a fake signal).
+	 * callbacks, i.e. no need to acquire kvm_usage_lock to ensure the usage
+	 * count is stable.  Assert that kvm_usage_lock is not held to ensure
+	 * the system isn't suspended while KVM is enabling hardware.  Hardware
+	 * enabling can be preempted, but the task cannot be frozen until it has
+	 * dropped all locks (userspace tasks are frozen via a fake signal).
 	 */
-	lockdep_assert_not_held(&kvm_lock);
+	lockdep_assert_not_held(&kvm_usage_lock);
 	lockdep_assert_irqs_disabled();
 
 	if (kvm_usage_count)
@@ -5755,7 +5756,7 @@ static int kvm_suspend(void)
 
 static void kvm_resume(void)
 {
-	lockdep_assert_not_held(&kvm_lock);
+	lockdep_assert_not_held(&kvm_usage_lock);
 	lockdep_assert_irqs_disabled();
 
 	if (kvm_usage_count)