KVM: PPC: Book3S HV: Fix spinlock/mutex ordering issue in kvmppc_set_lpcr()

Currently, kvmppc_set_lpcr() has a spinlock around the whole function,
and inside that does mutex_lock(&kvm->lock).  It is not permitted to
take a mutex while holding a spinlock, because the mutex_lock might
call schedule().  In addition, this causes lockdep to warn about a
lock ordering issue:

======================================================
[ INFO: possible circular locking dependency detected ]
3.18.0-kvm-04645-gdfea862-dirty #131 Not tainted
-------------------------------------------------------
qemu-system-ppc/8179 is trying to acquire lock:
 (&kvm->lock){+.+.+.}, at: [<d00000000ecc1f54>] .kvmppc_set_lpcr+0xf4/0x1c0 [kvm_hv]

but task is already holding lock:
 (&(&vcore->lock)->rlock){+.+...}, at: [<d00000000ecc1ea0>] .kvmppc_set_lpcr+0x40/0x1c0 [kvm_hv]

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (&(&vcore->lock)->rlock){+.+...}:
       [<c000000000b3c120>] .mutex_lock_nested+0x80/0x570
       [<d00000000ecc7a14>] .kvmppc_vcpu_run_hv+0xc4/0xe40 [kvm_hv]
       [<d00000000eb9f5cc>] .kvmppc_vcpu_run+0x2c/0x40 [kvm]
       [<d00000000eb9cb24>] .kvm_arch_vcpu_ioctl_run+0x54/0x160 [kvm]
       [<d00000000eb94478>] .kvm_vcpu_ioctl+0x4a8/0x7b0 [kvm]
       [<c00000000026cbb4>] .do_vfs_ioctl+0x444/0x770
       [<c00000000026cfa4>] .SyS_ioctl+0xc4/0xe0
       [<c000000000009264>] syscall_exit+0x0/0x98

-> #0 (&kvm->lock){+.+.+.}:
       [<c0000000000ff28c>] .lock_acquire+0xcc/0x1a0
       [<c000000000b3c120>] .mutex_lock_nested+0x80/0x570
       [<d00000000ecc1f54>] .kvmppc_set_lpcr+0xf4/0x1c0 [kvm_hv]
       [<d00000000ecc510c>] .kvmppc_set_one_reg_hv+0x4dc/0x990 [kvm_hv]
       [<d00000000eb9f234>] .kvmppc_set_one_reg+0x44/0x330 [kvm]
       [<d00000000eb9c9dc>] .kvm_vcpu_ioctl_set_one_reg+0x5c/0x150 [kvm]
       [<d00000000eb9ced4>] .kvm_arch_vcpu_ioctl+0x214/0x2c0 [kvm]
       [<d00000000eb940b0>] .kvm_vcpu_ioctl+0xe0/0x7b0 [kvm]
       [<c00000000026cbb4>] .do_vfs_ioctl+0x444/0x770
       [<c00000000026cfa4>] .SyS_ioctl+0xc4/0xe0
       [<c000000000009264>] syscall_exit+0x0/0x98

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&(&vcore->lock)->rlock);
                               lock(&kvm->lock);
                               lock(&(&vcore->lock)->rlock);
  lock(&kvm->lock);

 *** DEADLOCK ***

2 locks held by qemu-system-ppc/8179:
 #0:  (&vcpu->mutex){+.+.+.}, at: [<d00000000eb93f18>] .vcpu_load+0x28/0x90 [kvm]
 #1:  (&(&vcore->lock)->rlock){+.+...}, at: [<d00000000ecc1ea0>] .kvmppc_set_lpcr+0x40/0x1c0 [kvm_hv]

stack backtrace:
CPU: 4 PID: 8179 Comm: qemu-system-ppc Not tainted 3.18.0-kvm-04645-gdfea862-dirty #131
Call Trace:
[c000001a66c0f310] [c000000000b486ac] .dump_stack+0x88/0xb4 (unreliable)
[c000001a66c0f390] [c0000000000f8bec] .print_circular_bug+0x27c/0x3d0
[c000001a66c0f440] [c0000000000fe9e8] .__lock_acquire+0x2028/0x2190
[c000001a66c0f5d0] [c0000000000ff28c] .lock_acquire+0xcc/0x1a0
[c000001a66c0f6a0] [c000000000b3c120] .mutex_lock_nested+0x80/0x570
[c000001a66c0f7c0] [d00000000ecc1f54] .kvmppc_set_lpcr+0xf4/0x1c0 [kvm_hv]
[c000001a66c0f860] [d00000000ecc510c] .kvmppc_set_one_reg_hv+0x4dc/0x990 [kvm_hv]
[c000001a66c0f8d0] [d00000000eb9f234] .kvmppc_set_one_reg+0x44/0x330 [kvm]
[c000001a66c0f960] [d00000000eb9c9dc] .kvm_vcpu_ioctl_set_one_reg+0x5c/0x150 [kvm]
[c000001a66c0f9f0] [d00000000eb9ced4] .kvm_arch_vcpu_ioctl+0x214/0x2c0 [kvm]
[c000001a66c0faf0] [d00000000eb940b0] .kvm_vcpu_ioctl+0xe0/0x7b0 [kvm]
[c000001a66c0fcb0] [c00000000026cbb4] .do_vfs_ioctl+0x444/0x770
[c000001a66c0fd90] [c00000000026cfa4] .SyS_ioctl+0xc4/0xe0
[c000001a66c0fe30] [c000000000009264] syscall_exit+0x0/0x98

This fixes it by moving the mutex_lock()/mutex_unlock() pair outside
the spin-locked region.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index de4018a1bc4bd290ecd0e970bd51960b281497c3..b2731933f80775e87bba59a53ee265a013298ad4 100644 (file)
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -942,20 +942,20 @@ static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
 static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
                bool preserve_top32)
 {
+       struct kvm *kvm = vcpu->kvm;
        struct kvmppc_vcore *vc = vcpu->arch.vcore;
        u64 mask;
 
+       mutex_lock(&kvm->lock);
        spin_lock(&vc->lock);
        /*
         * If ILE (interrupt little-endian) has changed, update the
         * MSR_LE bit in the intr_msr for each vcpu in this vcore.
         */
        if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) {
-               struct kvm *kvm = vcpu->kvm;
                struct kvm_vcpu *vcpu;
                int i;
 
-               mutex_lock(&kvm->lock);
                kvm_for_each_vcpu(i, vcpu, kvm) {
                        if (vcpu->arch.vcore != vc)
                                continue;
@@ -964,7 +964,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
                        else
                                vcpu->arch.intr_msr &= ~MSR_LE;
                }
-               mutex_unlock(&kvm->lock);
        }
 
        /*
@@ -981,6 +980,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
                mask &= 0xFFFFFFFF;
        vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
        spin_unlock(&vc->lock);
+       mutex_unlock(&kvm->lock);
 }
 
 static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,