diff options
| author | Paul Mackerras <paulus@ozlabs.org> | 2019-05-29 11:54:00 +1000 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2019-06-22 08:17:23 +0200 |
| commit | fffbde146c6d0bf1d57478f86431a6605cd61982 (patch) | |
| tree | 6a98a3ad6dd0316843c79ddbc2616bbaf606dcc2 /arch/powerpc/include | |
| parent | 83a91e47809798aa24b0d97f8b00012bf81a4b25 (diff) | |
KVM: PPC: Book3S: Use new mutex to synchronize access to rtas token list
[ Upstream commit 1659e27d2bc1ef47b6d031abe01b467f18cb72d9 ]
Currently the Book 3S KVM code uses kvm->lock to synchronize access
to the kvm->arch.rtas_tokens list. Because this list is scanned
inside kvmppc_rtas_hcall(), which is called with the vcpu mutex held,
taking kvm->lock cause a lock inversion problem, which could lead to
a deadlock.
To fix this, we add a new mutex, kvm->arch.rtas_token_lock, which nests
inside the vcpu mutexes, and use that instead of kvm->lock when
accessing the rtas token list.
This removes the lockdep_assert_held() in kvmppc_rtas_tokens_free().
At this point we don't hold the new mutex, but that is OK because
kvmppc_rtas_tokens_free() is only called when the whole VM is being
destroyed, and at that point nothing can be looking up a token in
the list.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Diffstat (limited to 'arch/powerpc/include')
| -rw-r--r-- | arch/powerpc/include/asm/kvm_host.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 5e12e19940e2..defa553fe823 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -271,6 +271,7 @@ struct kvm_arch { #ifdef CONFIG_PPC_BOOK3S_64 struct list_head spapr_tce_tables; struct list_head rtas_tokens; + struct mutex rtas_token_lock; DECLARE_BITMAP(enabled_hcalls, MAX_HCALL_OPCODE/4 + 1); #endif #ifdef CONFIG_KVM_MPIC |