diff options
author | Yanan Wang <wangyanan55@huawei.com> | 2021-01-14 20:13:49 +0800 |
---|---|---|
committer | Marc Zyngier <maz@kernel.org> | 2021-01-25 16:30:20 +0000 |
commit | 694d071f8d85d504055540a27f0dbe9dbf44584e (patch) | |
tree | acd08976046541564071fd4839856f354357516b /arch/arm64/kvm | |
parent | 8ed80051c8c31d1587722fdb3af16677eba9d693 (diff) |
KVM: arm64: Filter out the case of only changing permissions from stage-2 map path
(1) During running time of a a VM with numbers of vCPUs, if some vCPUs
access the same GPA almost at the same time and the stage-2 mapping of
the GPA has not been built yet, as a result they will all cause
translation faults. The first vCPU builds the mapping, and the followed
ones end up updating the valid leaf PTE. Note that these vCPUs might
want different access permissions (RO, RW, RX, RWX, etc.).
(2) It's inevitable that we sometimes will update an existing valid leaf
PTE in the map path, and we perform break-before-make in this case.
Then more unnecessary translation faults could be caused if the
*break stage* of BBM is just catched by other vCPUS.
With (1) and (2), something unsatisfactory could happen: vCPU A causes
a translation fault and builds the mapping with RW permissions, vCPU B
then update the valid leaf PTE with break-before-make and permissions
are updated back to RO. Besides, *break stage* of BBM may trigger more
translation faults. Finally, some useless small loops could occur.
We can make some optimization to solve above problems: When we need to
update a valid leaf PTE in the map path, let's filter out the case where
this update only change access permissions, and don't update the valid
leaf PTE here in this case. Instead, let the vCPU enter back the guest
and it will exit next time to go through the relax_perms path without
break-before-make if it still wants more permissions.
Signed-off-by: Yanan Wang <wangyanan55@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210114121350.123684-3-wangyanan55@huawei.com
Diffstat (limited to 'arch/arm64/kvm')
-rw-r--r-- | arch/arm64/kvm/hyp/pgtable.c | 32 |
1 files changed, 21 insertions, 11 deletions
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index a11ac874bc2a..4d177ce1d536 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -45,6 +45,10 @@ #define KVM_PTE_LEAF_ATTR_HI_S2_XN BIT(54) +#define KVM_PTE_LEAF_ATTR_S2_PERMS (KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R | \ + KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \ + KVM_PTE_LEAF_ATTR_HI_S2_XN) + struct kvm_pgtable_walk_data { struct kvm_pgtable *pgt; struct kvm_pgtable_walker *walker; @@ -460,22 +464,27 @@ static int stage2_map_set_prot_attr(enum kvm_pgtable_prot prot, return 0; } -static bool stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, - struct stage2_map_data *data) +static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, + kvm_pte_t *ptep, + struct stage2_map_data *data) { kvm_pte_t new, old = *ptep; u64 granule = kvm_granule_size(level), phys = data->phys; struct page *page = virt_to_page(ptep); if (!kvm_block_mapping_supported(addr, end, phys, level)) - return false; + return -E2BIG; new = kvm_init_valid_leaf_pte(phys, data->attr, level); if (kvm_pte_valid(old)) { - /* Tolerate KVM recreating the exact same mapping */ - if (old == new) - goto out; + /* + * Skip updating the PTE if we are trying to recreate the exact + * same mapping or only change the access permissions. Instead, + * the vCPU will exit one more time from guest if still needed + * and then go through the path of relaxing permissions. + */ + if (!((old ^ new) & (~KVM_PTE_LEAF_ATTR_S2_PERMS))) + return -EAGAIN; /* * There's an existing different valid leaf entry, so perform @@ -488,9 +497,8 @@ static bool stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, smp_store_release(ptep, new); get_page(page); -out: data->phys += granule; - return true; + return 0; } static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level, @@ -518,6 +526,7 @@ static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level, static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, struct stage2_map_data *data) { + int ret; kvm_pte_t *childp, pte = *ptep; struct page *page = virt_to_page(ptep); @@ -528,8 +537,9 @@ static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, return 0; } - if (stage2_map_walker_try_leaf(addr, end, level, ptep, data)) - return 0; + ret = stage2_map_walker_try_leaf(addr, end, level, ptep, data); + if (ret != -E2BIG) + return ret; if (WARN_ON(level == KVM_PGTABLE_MAX_LEVELS - 1)) return -EINVAL; |