On Mon, Nov 15, 2021, Ben Gardon wrote:
> When recursively clearing out disconnected pts, the range based TLB
> flush in handle_removed_tdp_mmu_page uses the wrong starting GFN,
> resulting in the flush mostly missing the affected range. Fix this by
> using base_gfn for the flush.
>
> In response to feedback from David Matlack on the RFC version of this
> patch, also move a few definitions into the for loop in the function to
> prevent unintended references to them in the future.
Rats, I didn't read David's feedback or I would've responded there.
> Fixes: a066e61f13cf ("KVM: x86/mmu: Factor out handling of removed page tables")
> CC: stable@xxxxxxxxxxxxxxx
>
> Signed-off-by: Ben Gardon <bgardon@xxxxxxxxxx>
> ---
> arch/x86/kvm/mmu/tdp_mmu.c | 10 ++++------
> 1 file changed, 4 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index 7c5dd83e52de..4bd541050d21 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -317,9 +317,6 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
> struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
> int level = sp->role.level;
> gfn_t base_gfn = sp->gfn;
> - u64 old_child_spte;
> - u64 *sptep;
> - gfn_t gfn;
> int i;
>
> trace_kvm_mmu_prepare_zap_page(sp);
> @@ -327,8 +324,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
> tdp_mmu_unlink_page(kvm, sp, shared);
>
> for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
> - sptep = rcu_dereference(pt) + i;
> - gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
> + u64 *sptep = rcu_dereference(pt) + i;
> + gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
> + u64 old_child_spte;
TL;DR: this type of optional refactoring doesn't belong in a patch Cc'd for stable,
and my personal preference is to always declare variables at function scope (it's
not a hard rule though, Paolo has overruled me at least once :-) ).
Declaring variables in an inner scope is not always "better". In particular, it
can lead to variable shadowing, which can lead to functional issues of a different
sort. Most shadowing is fairly obvious, and truly egregious bugs will often result
in the compiler complaining about consuming an uninitialized variable.
But the worst-case scenario is if the inner scope shadows a function parameter, in
which the case the compiler will not complain and will even consume an uninitialized
variable without warning. IIRC, we actually had a Hyper-V bug of that nature
where an incoming @vcpu was shadowed. Examples below.
So yes, on one hand moving the declarations inside the loop avoid potential flavor
of bug, but they create the possibility for an entirely different class of bugs.
The main reason I prefer declaring at function scope is that I find it easier to
visually detect using variables after a for loop, versus detecting that a variable
is being shadowed, especially if the function is largish and the two declarations
don't fit on the screen.
There are of course counter-examples, e.g. commit 5c49d1850ddd ("KVM: VMX: Fix a
TSX_CTRL_CPUID_CLEAR field mask issue") immediately jumps to mind, so there's
certainly an element of personal preference.
E.g. this will fail with "error: ‘sptep’ redeclared as different kind of symbol
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 4e226cdb40d9..011639bf633c 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -369,7 +369,7 @@ static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp,
* early rcu_dereferences in the function.
*/
static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
- bool shared)
+ bool shared, u64 *sptep)
{
struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
int level = sp->role.level;
@@ -431,8 +431,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
shared);
}
- kvm_flush_remote_tlbs_with_address(kvm, gfn,
- KVM_PAGES_PER_HPAGE(level + 1));
+ if (sptep)
+ kvm_flush_remote_tlbs_with_address(kvm, gfn,
+ KVM_PAGES_PER_HPAGE(level + 1));
call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
}
@@ -532,7 +533,7 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
*/
if (was_present && !was_leaf && (is_leaf || !is_present))
handle_removed_tdp_mmu_page(kvm,
- spte_to_child_pt(old_spte, level), shared);
+ spte_to_child_pt(old_spte, level), shared, NULL);
}
static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
whereas moving the second declaration into the loop will compile happily.
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 4e226cdb40d9..3e83fd66c0dc 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -369,13 +369,12 @@ static void tdp_mmu_unlink_page(struct kvm *kvm, struct kvm_mmu_page *sp,
* early rcu_dereferences in the function.
*/
static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
- bool shared)
+ bool shared, u64 *sptep)
{
struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
int level = sp->role.level;
gfn_t base_gfn = sp->gfn;
u64 old_child_spte;
- u64 *sptep;
gfn_t gfn;
int i;
@@ -384,7 +383,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
tdp_mmu_unlink_page(kvm, sp, shared);
for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
- sptep = rcu_dereference(pt) + i;
+ u64 *sptep = rcu_dereference(pt) + i;
gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
if (shared) {
@@ -431,8 +430,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
shared);
}
- kvm_flush_remote_tlbs_with_address(kvm, gfn,
- KVM_PAGES_PER_HPAGE(level + 1));
+ if (sptep)
+ kvm_flush_remote_tlbs_with_address(kvm, gfn,
+ KVM_PAGES_PER_HPAGE(level + 1));
call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
}
@@ -532,7 +532,7 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
*/
if (was_present && !was_leaf && (is_leaf || !is_present))
handle_removed_tdp_mmu_page(kvm,
- spte_to_child_pt(old_spte, level), shared);
+ spte_to_child_pt(old_spte, level), shared, NULL);
}
static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
