Hi all,
This addresses a couple of issues Will has found with the refcounting of
page-tables at EL2. Patch 01 fixes a nasty bug, and probably wants to go
in -stable. Patch 02 fixes a small inconsistency which made it harder to
find refcount-related bugs at EL2.
Feedback welcome !
Thanks,
Quentin
Quentin Perret (2):
KVM: arm64: Fix host stage-2 PGD refcount
KVM: arm64: Report corrupted refcount at EL2
arch/arm64/kvm/hyp/include/nvhe/gfp.h | 1 +
arch/arm64/kvm/hyp/nvhe/mem_protect.c | 6 +++++-
arch/arm64/kvm/hyp/nvhe/page_alloc.c | 15 +++++++++++++++
3 files changed, 21 insertions(+), 1 deletion(-)
--
2.33.0.800.g4c38ced690-goog
Hi all,
This is v2 of the series previously posted here:
https://lore.kernel.org/kvmarm/[email protected]/
This addresses a couple of issues Will has found with the refcounting of
page-tables at EL2. Patch 01 fixes a nasty bug, and probably wants to go
in -stable. Patch 02 fixes a small inconsistency which made it harder to
find refcount-related bugs at EL2.
Changes since v1:
- applied Acked-by from Will;
- better comment + commit message for patch 01 (Marc).
Thanks!
Quentin
Quentin Perret (2):
KVM: arm64: Fix host stage-2 PGD refcount
KVM: arm64: Report corrupted refcount at EL2
arch/arm64/kvm/hyp/include/nvhe/gfp.h | 1 +
arch/arm64/kvm/hyp/nvhe/mem_protect.c | 13 ++++++++++++-
arch/arm64/kvm/hyp/nvhe/page_alloc.c | 15 +++++++++++++++
3 files changed, 28 insertions(+), 1 deletion(-)
--
2.33.0.800.g4c38ced690-goog
The KVM page-table library refcounts the pages of concatenated stage-2
PGDs individually. However, when running KVM in protected mode, the
host's stage-2 PGD is currently managed by EL2 as a single high-order
compound page, which can cause the refcount of the tail pages to reach 0
when they shouldn't, hence corrupting the page-table.
Fix this by introducing a new hyp_split_page() helper in the EL2 page
allocator (matching the kernel's split_page() function), and make use of
it from host_s2_zalloc_pages_exact().
Fixes: 1025c8c0c6ac ("KVM: arm64: Wrap the host with a stage 2")
Acked-by: Will Deacon <[email protected]>
Suggested-by: Will Deacon <[email protected]>
Signed-off-by: Quentin Perret <[email protected]>
---
arch/arm64/kvm/hyp/include/nvhe/gfp.h | 1 +
arch/arm64/kvm/hyp/nvhe/mem_protect.c | 13 ++++++++++++-
arch/arm64/kvm/hyp/nvhe/page_alloc.c | 14 ++++++++++++++
3 files changed, 27 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index fb0f523d1492..0a048dc06a7d 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -24,6 +24,7 @@ struct hyp_pool {
/* Allocation */
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order);
+void hyp_split_page(struct hyp_page *page);
void hyp_get_page(struct hyp_pool *pool, void *addr);
void hyp_put_page(struct hyp_pool *pool, void *addr);
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index bacd493a4eac..34eeb524b686 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -35,7 +35,18 @@ const u8 pkvm_hyp_id = 1;
static void *host_s2_zalloc_pages_exact(size_t size)
{
- return hyp_alloc_pages(&host_s2_pool, get_order(size));
+ void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size));
+
+ hyp_split_page(hyp_virt_to_page(addr));
+
+ /*
+ * The size of concatenated PGDs is always a power of two of PAGE_SIZE,
+ * so there should be no need to free any of the tail pages to make the
+ * allocation exact.
+ */
+ WARN_ON(size != (PAGE_SIZE << get_order(size)));
+
+ return addr;
}
static void *host_s2_zalloc_page(void *pool)
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index 41fc25bdfb34..a6e874e61a40 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -193,6 +193,20 @@ void hyp_get_page(struct hyp_pool *pool, void *addr)
hyp_spin_unlock(&pool->lock);
}
+void hyp_split_page(struct hyp_page *p)
+{
+ unsigned short order = p->order;
+ unsigned int i;
+
+ p->order = 0;
+ for (i = 1; i < (1 << order); i++) {
+ struct hyp_page *tail = p + i;
+
+ tail->order = 0;
+ hyp_set_page_refcounted(tail);
+ }
+}
+
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
{
unsigned short i = order;
--
2.33.0.800.g4c38ced690-goog
Some of the refcount manipulation helpers used at EL2 are instrumented
to catch a corrupted state, but not all of them are treated equally. Let's
make things more consistent by instrumenting hyp_page_ref_dec_and_test()
as well.
Acked-by: Will Deacon <[email protected]>
Suggested-by: Will Deacon <[email protected]>
Signed-off-by: Quentin Perret <[email protected]>
---
arch/arm64/kvm/hyp/nvhe/page_alloc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index a6e874e61a40..0bd7701ad1df 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -152,6 +152,7 @@ static inline void hyp_page_ref_inc(struct hyp_page *p)
static inline int hyp_page_ref_dec_and_test(struct hyp_page *p)
{
+ BUG_ON(!p->refcount);
p->refcount--;
return (p->refcount == 0);
}
--
2.33.0.800.g4c38ced690-goog
Some of the refcount manipulation helpers used at EL2 are instrumented
to catch a corrupt state, but not all of them are treated equally. Let's
make things more consistent by instrumenting hyp_page_ref_dec_and_test()
as well.
Suggested-by: Will Deacon <[email protected]>
Signed-off-by: Quentin Perret <[email protected]>
---
arch/arm64/kvm/hyp/nvhe/page_alloc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index a6e874e61a40..0bd7701ad1df 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -152,6 +152,7 @@ static inline void hyp_page_ref_inc(struct hyp_page *p)
static inline int hyp_page_ref_dec_and_test(struct hyp_page *p)
{
+ BUG_ON(!p->refcount);
p->refcount--;
return (p->refcount == 0);
}
--
2.33.0.800.g4c38ced690-goog
The KVM page-table library refcounts the pages of concatenated stage-2
PGDs individually. However, the host's stage-2 PGD is currently managed
by EL2 as a single high-order compound page, which can cause the
refcount of the tail pages to reach 0 when they really shouldn't, hence
corrupting the page-table.
Fix this by introducing a new hyp_split_page() helper in the EL2 page
allocator (matching EL1's split_page() function), and make use of it
from host_s2_zalloc_page().
Fixes: 1025c8c0c6ac ("KVM: arm64: Wrap the host with a stage 2")
Suggested-by: Will Deacon <[email protected]>
Signed-off-by: Quentin Perret <[email protected]>
---
arch/arm64/kvm/hyp/include/nvhe/gfp.h | 1 +
arch/arm64/kvm/hyp/nvhe/mem_protect.c | 6 +++++-
arch/arm64/kvm/hyp/nvhe/page_alloc.c | 14 ++++++++++++++
3 files changed, 20 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index fb0f523d1492..0a048dc06a7d 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -24,6 +24,7 @@ struct hyp_pool {
/* Allocation */
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order);
+void hyp_split_page(struct hyp_page *page);
void hyp_get_page(struct hyp_pool *pool, void *addr);
void hyp_put_page(struct hyp_pool *pool, void *addr);
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index bacd493a4eac..93a79736c283 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -35,7 +35,11 @@ const u8 pkvm_hyp_id = 1;
static void *host_s2_zalloc_pages_exact(size_t size)
{
- return hyp_alloc_pages(&host_s2_pool, get_order(size));
+ void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size));
+
+ hyp_split_page(hyp_virt_to_page(addr));
+
+ return addr;
}
static void *host_s2_zalloc_page(void *pool)
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index 41fc25bdfb34..a6e874e61a40 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -193,6 +193,20 @@ void hyp_get_page(struct hyp_pool *pool, void *addr)
hyp_spin_unlock(&pool->lock);
}
+void hyp_split_page(struct hyp_page *p)
+{
+ unsigned short order = p->order;
+ unsigned int i;
+
+ p->order = 0;
+ for (i = 1; i < (1 << order); i++) {
+ struct hyp_page *tail = p + i;
+
+ tail->order = 0;
+ hyp_set_page_refcounted(tail);
+ }
+}
+
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
{
unsigned short i = order;
--
2.33.0.800.g4c38ced690-goog
On Tue, 5 Oct 2021 10:01:40 +0100, Quentin Perret wrote:
> This is v2 of the series previously posted here:
>
> https://lore.kernel.org/kvmarm/[email protected]/
>
> This addresses a couple of issues Will has found with the refcounting of
> page-tables at EL2. Patch 01 fixes a nasty bug, and probably wants to go
> in -stable. Patch 02 fixes a small inconsistency which made it harder to
> find refcount-related bugs at EL2.
>
> [...]
Applied to fixes, thanks!
[1/2] KVM: arm64: Fix host stage-2 PGD refcount
commit: 1d58a17ef54599506d44c45ac95be27273a4d2b1
[2/2] KVM: arm64: Report corrupted refcount at EL2
commit: 7615c2a514788559c6684234b8fc27f3a843c2c6
Cheers,
M.
--
Without deviation from the norm, progress is not possible.