diff options
author | Paul Mackerras <paulus@ozlabs.org> | 2018-11-16 13:28:18 +0300 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2019-09-16 09:21:58 +0300 |
commit | d3984e80d7f27c1283ea51e067ec8311619d9c3d (patch) | |
tree | b06570d82bc938545694a668d3878d3ca03fbbb3 /arch/powerpc/kvm | |
parent | d88b01d04c6a16dee1fa172db5064af2768b33a7 (diff) | |
download | linux-d3984e80d7f27c1283ea51e067ec8311619d9c3d.tar.xz |
KVM: PPC: Book3S HV: Fix race between kvm_unmap_hva_range and MMU mode switch
[ Upstream commit 234ff0b729ad882d20f7996591a964965647addf ]
Testing has revealed an occasional crash which appears to be caused
by a race between kvmppc_switch_mmu_to_hpt and kvm_unmap_hva_range_hv.
The symptom is a NULL pointer dereference in __find_linux_pte() called
from kvm_unmap_radix() with kvm->arch.pgtable == NULL.
Looking at kvmppc_switch_mmu_to_hpt(), it does indeed clear
kvm->arch.pgtable (via kvmppc_free_radix()) before setting
kvm->arch.radix to NULL, and there is nothing to prevent
kvm_unmap_hva_range_hv() or the other MMU callback functions from
being called concurrently with kvmppc_switch_mmu_to_hpt() or
kvmppc_switch_mmu_to_radix().
This patch therefore adds calls to spin_lock/unlock on the kvm->mmu_lock
around the assignments to kvm->arch.radix, and makes sure that the
partition-scoped radix tree or HPT is only freed after changing
kvm->arch.radix.
This also takes the kvm->mmu_lock in kvmppc_rmap_reset() to make sure
that the clearing of each rmap array (one per memslot) doesn't happen
concurrently with use of the array in the kvm_unmap_hva_range_hv()
or the other MMU callbacks.
Fixes: 18c3640cefc7 ("KVM: PPC: Book3S HV: Add infrastructure for running HPT guests on radix host")
Cc: stable@vger.kernel.org # v4.15+
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Diffstat (limited to 'arch/powerpc/kvm')
-rw-r--r-- | arch/powerpc/kvm/book3s_64_mmu_hv.c | 3 | ||||
-rw-r--r-- | arch/powerpc/kvm/book3s_hv.c | 15 |
2 files changed, 14 insertions, 4 deletions
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 68e14afecac8..a488c105b923 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -744,12 +744,15 @@ void kvmppc_rmap_reset(struct kvm *kvm) srcu_idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, slots) { + /* Mutual exclusion with kvm_unmap_hva_range etc. */ + spin_lock(&kvm->mmu_lock); /* * This assumes it is acceptable to lose reference and * change bits across a reset. */ memset(memslot->arch.rmap, 0, memslot->npages * sizeof(*memslot->arch.rmap)); + spin_unlock(&kvm->mmu_lock); } srcu_read_unlock(&kvm->srcu, srcu_idx); } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 083dcedba11c..9595db30e6b8 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3813,12 +3813,15 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) /* Must be called with kvm->lock held and mmu_ready = 0 and no vcpus running */ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) { + kvmppc_rmap_reset(kvm); + kvm->arch.process_table = 0; + /* Mutual exclusion with kvm_unmap_hva_range etc. */ + spin_lock(&kvm->mmu_lock); + kvm->arch.radix = 0; + spin_unlock(&kvm->mmu_lock); kvmppc_free_radix(kvm); kvmppc_update_lpcr(kvm, LPCR_VPM1, LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR); - kvmppc_rmap_reset(kvm); - kvm->arch.radix = 0; - kvm->arch.process_table = 0; return 0; } @@ -3831,10 +3834,14 @@ int kvmppc_switch_mmu_to_radix(struct kvm *kvm) if (err) return err; + kvmppc_rmap_reset(kvm); + /* Mutual exclusion with kvm_unmap_hva_range etc. */ + spin_lock(&kvm->mmu_lock); + kvm->arch.radix = 1; + spin_unlock(&kvm->mmu_lock); kvmppc_free_hpt(&kvm->arch.hpt); kvmppc_update_lpcr(kvm, LPCR_UPRT | LPCR_GTSE | LPCR_HR, LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR); - kvm->arch.radix = 1; return 0; } |