From: David Stevens <[email protected]>
This patch series adds support for mapping non-refcount VM_IO and
VM_PFNMAP memory into the guest.
Currently, the gfn_to_pfn functions require being able to pin the target
pfn, so they will fail if the pfn returned by follow_pte isn't a
ref-counted page. However, the KVM secondary MMUs do not require that
the pfn be pinned, since they are integrated with the mmu notifier API.
This series adds a new set of gfn_to_pfn_page functions which parallel
the gfn_to_pfn functions but do not pin the pfn. The new functions
return the page from gup if it was present, so callers can use it and
call put_page when done.
The gfn_to_pfn functions should be depreciated, since as they are unsafe
due to relying on trying to obtain a struct page from a pfn returned by
follow_pte. I added new functions instead of simply adding another
optional parameter to the existing functions to make it easier to track
down users of the deprecated functions.
This series updates x86 and arm64 secondary MMUs to the new API.
v2 -> v3:
- rebase on kvm next branch
v1 -> v2:
- Introduce new gfn_to_pfn_page functions instead of modifying the
behavior of existing gfn_to_pfn functions, to make the change less
invasive.
- Drop changes to mmu_audit.c
- Include Nicholas Piggin's patch to avoid corrupting refcount in the
follow_pte case, and use it in depreciated gfn_to_pfn functions.
- Rebase on kvm/next
David Stevens (4):
KVM: mmu: introduce new gfn_to_pfn_page functions
KVM: x86/mmu: use gfn_to_pfn_page
KVM: arm64/mmu: use gfn_to_pfn_page
KVM: mmu: remove over-aggressive warnings
arch/arm64/kvm/mmu.c | 26 +++--
arch/x86/kvm/mmu/mmu.c | 50 +++++----
arch/x86/kvm/mmu/mmu_internal.h | 3 +-
arch/x86/kvm/mmu/paging_tmpl.h | 23 ++--
arch/x86/kvm/mmu/tdp_mmu.c | 6 +-
arch/x86/kvm/mmu/tdp_mmu.h | 4 +-
arch/x86/kvm/x86.c | 6 +-
include/linux/kvm_host.h | 17 +++
virt/kvm/kvm_main.c | 188 +++++++++++++++++++++++---------
9 files changed, 220 insertions(+), 103 deletions(-)
--
2.33.0.rc2.250.ged5fa647cd-goog
From: David Stevens <[email protected]>
Introduce new gfn_to_pfn_page functions that parallel existing
gfn_to_pfn functions. The new functions are identical except they take
an additional out parameter that is used to return the struct page if
the hva was resolved by gup. This allows callers to differentiate the
gup and follow_pte cases, which in turn allows callers to only touch the
page refcount when necessitated by gup.
The old gfn_to_pfn functions are depreciated, and all callers should be
migrated to the new gfn_to_pfn_page functions. In the interim, the
gfn_to_pfn functions are reimplemented as wrappers of the corresponding
gfn_to_pfn_page functions. The wrappers take a reference to the pfn's
page that had previously been taken in hva_to_pfn_remapped.
Signed-off-by: David Stevens <[email protected]>
---
include/linux/kvm_host.h | 17 ++++
virt/kvm/kvm_main.c | 186 ++++++++++++++++++++++++++++-----------
2 files changed, 152 insertions(+), 51 deletions(-)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e4d712e9f760..2e7400ae4982 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -868,6 +868,19 @@ kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
bool atomic, bool *async, bool write_fault,
bool *writable, hva_t *hva);
+kvm_pfn_t gfn_to_pfn_page(struct kvm *kvm, gfn_t gfn, struct page **page);
+kvm_pfn_t gfn_to_pfn_page_prot(struct kvm *kvm, gfn_t gfn,
+ bool write_fault, bool *writable,
+ struct page **page);
+kvm_pfn_t gfn_to_pfn_page_memslot(struct kvm_memory_slot *slot,
+ gfn_t gfn, struct page **page);
+kvm_pfn_t gfn_to_pfn_page_memslot_atomic(struct kvm_memory_slot *slot,
+ gfn_t gfn, struct page **page);
+kvm_pfn_t __gfn_to_pfn_page_memslot(struct kvm_memory_slot *slot,
+ gfn_t gfn, bool atomic, bool *async,
+ bool write_fault, bool *writable,
+ hva_t *hva, struct page **page);
+
void kvm_release_pfn_clean(kvm_pfn_t pfn);
void kvm_release_pfn_dirty(kvm_pfn_t pfn);
void kvm_set_pfn_dirty(kvm_pfn_t pfn);
@@ -949,6 +962,10 @@ struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
+kvm_pfn_t kvm_vcpu_gfn_to_pfn_page_atomic(struct kvm_vcpu *vcpu, gfn_t gfn,
+ struct page **page);
+kvm_pfn_t kvm_vcpu_gfn_to_pfn_page(struct kvm_vcpu *vcpu, gfn_t gfn,
+ struct page **page);
int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
struct gfn_to_pfn_cache *cache, bool atomic);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 3e67c93ca403..5c47ea93df23 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2216,9 +2216,9 @@ static inline int check_user_page_hwpoison(unsigned long addr)
* only part that runs if we can in atomic context.
*/
static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
- bool *writable, kvm_pfn_t *pfn)
+ bool *writable, kvm_pfn_t *pfn,
+ struct page **page)
{
- struct page *page[1];
/*
* Fast pin a writable pfn only if it is a write fault request
@@ -2229,7 +2229,7 @@ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
return false;
if (get_user_page_fast_only(addr, FOLL_WRITE, page)) {
- *pfn = page_to_pfn(page[0]);
+ *pfn = page_to_pfn(*page);
if (writable)
*writable = true;
@@ -2244,10 +2244,9 @@ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
* 1 indicates success, -errno is returned if error is detected.
*/
static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
- bool *writable, kvm_pfn_t *pfn)
+ bool *writable, kvm_pfn_t *pfn, struct page **page)
{
unsigned int flags = FOLL_HWPOISON;
- struct page *page;
int npages = 0;
might_sleep();
@@ -2260,7 +2259,7 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
if (async)
flags |= FOLL_NOWAIT;
- npages = get_user_pages_unlocked(addr, 1, &page, flags);
+ npages = get_user_pages_unlocked(addr, 1, page, flags);
if (npages != 1)
return npages;
@@ -2270,11 +2269,11 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
if (get_user_page_fast_only(addr, FOLL_WRITE, &wpage)) {
*writable = true;
- put_page(page);
- page = wpage;
+ put_page(*page);
+ *page = wpage;
}
}
- *pfn = page_to_pfn(page);
+ *pfn = page_to_pfn(*page);
return npages;
}
@@ -2289,13 +2288,6 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault)
return true;
}
-static int kvm_try_get_pfn(kvm_pfn_t pfn)
-{
- if (kvm_is_reserved_pfn(pfn))
- return 1;
- return get_page_unless_zero(pfn_to_page(pfn));
-}
-
static int hva_to_pfn_remapped(struct vm_area_struct *vma,
unsigned long addr, bool *async,
bool write_fault, bool *writable,
@@ -2335,26 +2327,6 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
*writable = pte_write(*ptep);
pfn = pte_pfn(*ptep);
- /*
- * Get a reference here because callers of *hva_to_pfn* and
- * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the
- * returned pfn. This is only needed if the VMA has VM_MIXEDMAP
- * set, but the kvm_get_pfn/kvm_release_pfn_clean pair will
- * simply do nothing for reserved pfns.
- *
- * Whoever called remap_pfn_range is also going to call e.g.
- * unmap_mapping_range before the underlying pages are freed,
- * causing a call to our MMU notifier.
- *
- * Certain IO or PFNMAP mappings can be backed with valid
- * struct pages, but be allocated without refcounting e.g.,
- * tail pages of non-compound higher order allocations, which
- * would then underflow the refcount when the caller does the
- * required put_page. Don't allow those pages here.
- */
- if (!kvm_try_get_pfn(pfn))
- r = -EFAULT;
-
out:
pte_unmap_unlock(ptep, ptl);
*p_pfn = pfn;
@@ -2376,8 +2348,9 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
* 2): @write_fault = false && @writable, @writable will tell the caller
* whether the mapping is writable.
*/
-static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
- bool write_fault, bool *writable)
+static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic,
+ bool *async, bool write_fault, bool *writable,
+ struct page **page)
{
struct vm_area_struct *vma;
kvm_pfn_t pfn = 0;
@@ -2386,13 +2359,14 @@ static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
/* we can do it either atomically or asynchronously, not both */
BUG_ON(atomic && async);
- if (hva_to_pfn_fast(addr, write_fault, writable, &pfn))
+ if (hva_to_pfn_fast(addr, write_fault, writable, &pfn, page))
return pfn;
if (atomic)
return KVM_PFN_ERR_FAULT;
- npages = hva_to_pfn_slow(addr, async, write_fault, writable, &pfn);
+ npages = hva_to_pfn_slow(addr, async, write_fault, writable,
+ &pfn, page);
if (npages == 1)
return pfn;
@@ -2424,12 +2398,14 @@ static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
return pfn;
}
-kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
- bool atomic, bool *async, bool write_fault,
- bool *writable, hva_t *hva)
+kvm_pfn_t __gfn_to_pfn_page_memslot(struct kvm_memory_slot *slot,
+ gfn_t gfn, bool atomic, bool *async,
+ bool write_fault, bool *writable,
+ hva_t *hva, struct page **page)
{
unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
+ *page = NULL;
if (hva)
*hva = addr;
@@ -2452,45 +2428,153 @@ kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
}
return hva_to_pfn(addr, atomic, async, write_fault,
- writable);
+ writable, page);
+}
+EXPORT_SYMBOL_GPL(__gfn_to_pfn_page_memslot);
+
+kvm_pfn_t gfn_to_pfn_page_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
+ bool *writable, struct page **page)
+{
+ return __gfn_to_pfn_page_memslot(gfn_to_memslot(kvm, gfn), gfn, false,
+ NULL, write_fault, writable, NULL,
+ page);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_page_prot);
+
+kvm_pfn_t gfn_to_pfn_page_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
+ struct page **page)
+{
+ return __gfn_to_pfn_page_memslot(slot, gfn, false, NULL, true,
+ NULL, NULL, page);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_page_memslot);
+
+kvm_pfn_t gfn_to_pfn_page_memslot_atomic(struct kvm_memory_slot *slot,
+ gfn_t gfn, struct page **page)
+{
+ return __gfn_to_pfn_page_memslot(slot, gfn, true, NULL, true, NULL,
+ NULL, page);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_page_memslot_atomic);
+
+kvm_pfn_t kvm_vcpu_gfn_to_pfn_page_atomic(struct kvm_vcpu *vcpu, gfn_t gfn,
+ struct page **page)
+{
+ return gfn_to_pfn_page_memslot_atomic(
+ kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, page);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_page_atomic);
+
+kvm_pfn_t gfn_to_pfn_page(struct kvm *kvm, gfn_t gfn, struct page **page)
+{
+ return gfn_to_pfn_page_memslot(gfn_to_memslot(kvm, gfn), gfn, page);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_page);
+
+kvm_pfn_t kvm_vcpu_gfn_to_pfn_page(struct kvm_vcpu *vcpu, gfn_t gfn,
+ struct page **page)
+{
+ return gfn_to_pfn_page_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn),
+ gfn, page);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_page);
+
+static kvm_pfn_t ensure_pfn_ref(struct page *page, kvm_pfn_t pfn)
+{
+ if (page || is_error_pfn(pfn) || kvm_is_reserved_pfn(pfn))
+ return pfn;
+
+ /*
+ * Certain IO or PFNMAP mappings can be backed with valid
+ * struct pages, but be allocated without refcounting e.g.,
+ * tail pages of non-compound higher order allocations, which
+ * would then underflow the refcount when the caller does the
+ * required put_page. Don't allow those pages here.
+ */
+ if (get_page_unless_zero(pfn_to_page(pfn)))
+ return pfn;
+
+ return KVM_PFN_ERR_FAULT;
+}
+
+kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
+ bool atomic, bool *async, bool write_fault,
+ bool *writable, hva_t *hva)
+{
+ struct page *page;
+ kvm_pfn_t pfn;
+
+ pfn = __gfn_to_pfn_page_memslot(slot, gfn, atomic, async,
+ write_fault, writable, hva, &page);
+
+ return ensure_pfn_ref(page, pfn);
}
EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);
kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
bool *writable)
{
- return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL,
- write_fault, writable, NULL);
+ struct page *page;
+ kvm_pfn_t pfn;
+
+ pfn = gfn_to_pfn_page_prot(kvm, gfn, write_fault, writable, &page);
+
+ return ensure_pfn_ref(page, pfn);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
{
- return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL);
+ struct page *page;
+ kvm_pfn_t pfn;
+
+ pfn = gfn_to_pfn_page_memslot(slot, gfn, &page);
+
+ return ensure_pfn_ref(page, pfn);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);
kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn)
{
- return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL);
+ struct page *page;
+ kvm_pfn_t pfn;
+
+ pfn = gfn_to_pfn_page_memslot_atomic(slot, gfn, &page);
+
+ return ensure_pfn_ref(page, pfn);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);
kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn)
{
- return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
+ struct page *page;
+ kvm_pfn_t pfn;
+
+ pfn = kvm_vcpu_gfn_to_pfn_page_atomic(vcpu, gfn, &page);
+
+ return ensure_pfn_ref(page, pfn);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic);
kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
{
- return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn);
+ struct page *page;
+ kvm_pfn_t pfn;
+
+ pfn = gfn_to_pfn_page(kvm, gfn, &page);
+
+ return ensure_pfn_ref(page, pfn);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn);
kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
- return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
+ struct page *page;
+ kvm_pfn_t pfn;
+
+ pfn = kvm_vcpu_gfn_to_pfn_page(vcpu, gfn, &page);
+
+ return ensure_pfn_ref(page, pfn);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn);
--
2.33.0.rc2.250.ged5fa647cd-goog
From: David Stevens <[email protected]>
Covert usages of the deprecated gfn_to_pfn functions to the new
gfn_to_pfn_page functions.
Signed-off-by: David Stevens <[email protected]>
---
arch/x86/kvm/mmu/mmu.c | 43 ++++++++++++++++++++-------------
arch/x86/kvm/mmu/mmu_internal.h | 3 ++-
arch/x86/kvm/mmu/paging_tmpl.h | 23 +++++++++++-------
arch/x86/kvm/mmu/tdp_mmu.c | 6 ++---
arch/x86/kvm/mmu/tdp_mmu.h | 4 +--
arch/x86/kvm/x86.c | 6 +++--
6 files changed, 51 insertions(+), 34 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index c04e30f6e0db..d2b99c2f7dfa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2789,8 +2789,9 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
return ret;
}
-static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
- bool no_dirty_log)
+static kvm_pfn_t pte_prefetch_gfn_to_pfn_page(struct kvm_vcpu *vcpu,
+ gfn_t gfn, bool no_dirty_log,
+ struct page **page)
{
struct kvm_memory_slot *slot;
@@ -2798,7 +2799,7 @@ static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
if (!slot)
return KVM_PFN_ERR_FAULT;
- return gfn_to_pfn_memslot_atomic(slot, gfn);
+ return gfn_to_pfn_page_memslot_atomic(slot, gfn, page);
}
static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
@@ -2929,7 +2930,8 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
int max_level, kvm_pfn_t *pfnp,
- bool huge_page_disallowed, int *req_level)
+ struct page *page, bool huge_page_disallowed,
+ int *req_level)
{
struct kvm_memory_slot *slot;
kvm_pfn_t pfn = *pfnp;
@@ -2941,6 +2943,9 @@ int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
if (unlikely(max_level == PG_LEVEL_4K))
return PG_LEVEL_4K;
+ if (!page)
+ return PG_LEVEL_4K;
+
if (is_error_noslot_pfn(pfn) || kvm_is_reserved_pfn(pfn))
return PG_LEVEL_4K;
@@ -2990,7 +2995,8 @@ void disallowed_hugepage_adjust(u64 spte, gfn_t gfn, int cur_level,
}
static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
- int map_writable, int max_level, kvm_pfn_t pfn,
+ int map_writable, int max_level,
+ kvm_pfn_t pfn, struct page *page,
bool prefault, bool is_tdp)
{
bool nx_huge_page_workaround_enabled = is_nx_huge_page_enabled();
@@ -3003,7 +3009,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
gfn_t gfn = gpa >> PAGE_SHIFT;
gfn_t base_gfn = gfn;
- level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn,
+ level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn, page,
huge_page_disallowed, &req_level);
trace_kvm_mmu_spte_requested(gpa, level, pfn);
@@ -3899,8 +3905,9 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
}
static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
- gpa_t cr2_or_gpa, kvm_pfn_t *pfn, hva_t *hva,
- bool write, bool *writable, int *r)
+ gpa_t cr2_or_gpa, kvm_pfn_t *pfn,
+ hva_t *hva, bool write, bool *writable,
+ struct page **page, int *r)
{
struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
bool async;
@@ -3934,8 +3941,8 @@ static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
}
async = false;
- *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async,
- write, writable, hva);
+ *pfn = __gfn_to_pfn_page_memslot(slot, gfn, false, &async,
+ write, writable, hva, page);
if (!async)
return false; /* *pfn has correct page already */
@@ -3949,8 +3956,8 @@ static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
goto out_retry;
}
- *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL,
- write, writable, hva);
+ *pfn = __gfn_to_pfn_page_memslot(slot, gfn, false, NULL,
+ write, writable, hva, page);
out_retry:
*r = RET_PF_RETRY;
@@ -3967,6 +3974,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
gfn_t gfn = gpa >> PAGE_SHIFT;
unsigned long mmu_seq;
kvm_pfn_t pfn;
+ struct page *page;
hva_t hva;
int r;
@@ -3985,7 +3993,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
smp_rmb();
if (kvm_faultin_pfn(vcpu, prefault, gfn, gpa, &pfn, &hva,
- write, &map_writable, &r))
+ write, &map_writable, &page, &r))
return r;
if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r))
@@ -4006,17 +4014,18 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
if (is_tdp_mmu_fault)
r = kvm_tdp_mmu_map(vcpu, gpa, error_code, map_writable, max_level,
- pfn, prefault);
+ pfn, page, prefault);
else
- r = __direct_map(vcpu, gpa, error_code, map_writable, max_level, pfn,
- prefault, is_tdp);
+ r = __direct_map(vcpu, gpa, error_code, map_writable, max_level,
+ pfn, page, prefault, is_tdp);
out_unlock:
if (is_tdp_mmu_fault)
read_unlock(&vcpu->kvm->mmu_lock);
else
write_unlock(&vcpu->kvm->mmu_lock);
- kvm_release_pfn_clean(pfn);
+ if (page)
+ put_page(page);
return r;
}
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 62bb8f758b3f..bd3cfeb6420f 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -163,7 +163,8 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
kvm_pfn_t pfn, int max_level);
int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
int max_level, kvm_pfn_t *pfnp,
- bool huge_page_disallowed, int *req_level);
+ struct page *page, bool huge_page_disallowed,
+ int *req_level);
void disallowed_hugepage_adjust(u64 spte, gfn_t gfn, int cur_level,
kvm_pfn_t *pfnp, int *goal_levelp);
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 7d03e9b7ccfa..4a61b96fcdef 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -564,6 +564,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
unsigned pte_access;
gfn_t gfn;
kvm_pfn_t pfn;
+ struct page *page;
if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
return false;
@@ -573,8 +574,8 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
gfn = gpte_to_gfn(gpte);
pte_access = sp->role.access & FNAME(gpte_access)(gpte);
FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
- pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
- no_dirty_log && (pte_access & ACC_WRITE_MASK));
+ pfn = pte_prefetch_gfn_to_pfn_page(vcpu, gfn,
+ no_dirty_log && (pte_access & ACC_WRITE_MASK), &page);
if (is_error_pfn(pfn))
return false;
@@ -585,7 +586,8 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
mmu_set_spte(vcpu, spte, pte_access, false, PG_LEVEL_4K, gfn, pfn,
true, true);
- kvm_release_pfn_clean(pfn);
+ if (page)
+ put_page(page);
return true;
}
@@ -665,8 +667,8 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
*/
static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
struct guest_walker *gw, u32 error_code,
- int max_level, kvm_pfn_t pfn, bool map_writable,
- bool prefault)
+ int max_level, kvm_pfn_t pfn, struct page *page,
+ bool map_writable, bool prefault)
{
bool nx_huge_page_workaround_enabled = is_nx_huge_page_enabled();
bool write_fault = error_code & PFERR_WRITE_MASK;
@@ -723,7 +725,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
}
level = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn,
- huge_page_disallowed, &req_level);
+ page, huge_page_disallowed,
+ &req_level);
trace_kvm_mmu_spte_requested(addr, gw->level, pfn);
@@ -830,6 +833,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
struct guest_walker walker;
int r;
kvm_pfn_t pfn;
+ struct page *page;
hva_t hva;
unsigned long mmu_seq;
bool map_writable, is_self_change_mapping;
@@ -882,7 +886,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
smp_rmb();
if (kvm_faultin_pfn(vcpu, prefault, walker.gfn, addr, &pfn, &hva,
- write_fault, &map_writable, &r))
+ write_fault, &map_writable, &page, &r))
return r;
if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r))
@@ -916,13 +920,14 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
r = make_mmu_pages_available(vcpu);
if (r)
goto out_unlock;
- r = FNAME(fetch)(vcpu, addr, &walker, error_code, max_level, pfn,
+ r = FNAME(fetch)(vcpu, addr, &walker, error_code, max_level, pfn, page,
map_writable, prefault);
kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
out_unlock:
write_unlock(&vcpu->kvm->mmu_lock);
- kvm_release_pfn_clean(pfn);
+ if (page)
+ put_page(page);
return r;
}
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 64ccfc1fa553..dec735081c5e 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -987,8 +987,8 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write,
* page tables and SPTEs to translate the faulting guest physical address.
*/
int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
- int map_writable, int max_level, kvm_pfn_t pfn,
- bool prefault)
+ int map_writable, int max_level,
+ kvm_pfn_t pfn, struct page *page, bool prefault)
{
bool nx_huge_page_workaround_enabled = is_nx_huge_page_enabled();
bool write = error_code & PFERR_WRITE_MASK;
@@ -1004,7 +1004,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
int level;
int req_level;
- level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn,
+ level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn, page,
huge_page_disallowed, &req_level);
trace_kvm_mmu_spte_requested(gpa, level, pfn);
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 358f447d4012..75526618601a 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -49,8 +49,8 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm);
int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
- int map_writable, int max_level, kvm_pfn_t pfn,
- bool prefault);
+ int map_writable, int max_level,
+ kvm_pfn_t pfn, struct page *page, bool prefault);
bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
bool flush);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1a00af1b076b..9b32ce593f1b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7523,6 +7523,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
{
gpa_t gpa = cr2_or_gpa;
kvm_pfn_t pfn;
+ struct page *page;
if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF))
return false;
@@ -7552,7 +7553,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
* retry instruction -> write #PF -> emulation fail -> retry
* instruction -> ...
*/
- pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa));
+ pfn = gfn_to_pfn_page(vcpu->kvm, gpa_to_gfn(gpa), &page);
/*
* If the instruction failed on the error pfn, it can not be fixed,
@@ -7561,7 +7562,8 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
if (is_error_noslot_pfn(pfn))
return false;
- kvm_release_pfn_clean(pfn);
+ if (page)
+ put_page(page);
/* The instructions are well-emulated on direct mmu. */
if (vcpu->arch.mmu->direct_map) {
--
2.33.0.rc2.250.ged5fa647cd-goog
From: David Stevens <[email protected]>
Covert usages of the deprecated gfn_to_pfn functions to the new
gfn_to_pfn_page functions.
Signed-off-by: David Stevens <[email protected]>
---
arch/arm64/kvm/mmu.c | 26 ++++++++++++++++----------
1 file changed, 16 insertions(+), 10 deletions(-)
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 0625bf2353c2..56859999b211 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -782,7 +782,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
static unsigned long
transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
unsigned long hva, kvm_pfn_t *pfnp,
- phys_addr_t *ipap)
+ struct page **page, phys_addr_t *ipap)
{
kvm_pfn_t pfn = *pfnp;
@@ -791,7 +791,7 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
* sure that the HVA and IPA are sufficiently aligned and that the
* block map is contained within the memslot.
*/
- if (kvm_is_transparent_hugepage(pfn) &&
+ if (*page && kvm_is_transparent_hugepage(pfn) &&
fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) {
/*
* The address we faulted on is backed by a transparent huge
@@ -812,10 +812,11 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
* page accordingly.
*/
*ipap &= PMD_MASK;
- kvm_release_pfn_clean(pfn);
+ put_page(*page);
pfn &= ~(PTRS_PER_PMD - 1);
- kvm_get_pfn(pfn);
*pfnp = pfn;
+ *page = pfn_to_page(pfn);
+ get_page(*page);
return PMD_SIZE;
}
@@ -908,6 +909,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
short vma_shift;
gfn_t gfn;
kvm_pfn_t pfn;
+ struct page *page;
bool logging_active = memslot_is_logging(memslot);
unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
unsigned long vma_pagesize, fault_granule;
@@ -1009,8 +1011,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
*/
smp_rmb();
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
- write_fault, &writable, NULL);
+ pfn = __gfn_to_pfn_page_memslot(memslot, gfn, false, NULL,
+ write_fault, &writable, NULL, &page);
if (pfn == KVM_PFN_ERR_HWPOISON) {
kvm_send_hwpoison_signal(hva, vma_shift);
return 0;
@@ -1052,7 +1054,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
*/
if (vma_pagesize == PAGE_SIZE && !(force_pte || device))
vma_pagesize = transparent_hugepage_adjust(memslot, hva,
- &pfn, &fault_ipa);
+ &pfn, &page,
+ &fault_ipa);
if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {
/* Check the VMM hasn't introduced a new VM_SHARED VMA */
@@ -1090,14 +1093,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
/* Mark the page dirty only if the fault is handled successfully */
if (writable && !ret) {
- kvm_set_pfn_dirty(pfn);
+ if (page)
+ kvm_set_pfn_dirty(pfn);
mark_page_dirty_in_slot(kvm, memslot, gfn);
}
out_unlock:
spin_unlock(&kvm->mmu_lock);
- kvm_set_pfn_accessed(pfn);
- kvm_release_pfn_clean(pfn);
+ if (page) {
+ kvm_set_pfn_accessed(pfn);
+ put_page(page);
+ }
return ret != -EAGAIN ? ret : 0;
}
--
2.33.0.rc2.250.ged5fa647cd-goog
From: David Stevens <[email protected]>
Remove two warnings that require ref counts for pages to be non-zero, as
mapped pfns from follow_pfn may not have an initialized ref count.
Signed-off-by: David Stevens <[email protected]>
---
arch/x86/kvm/mmu/mmu.c | 7 -------
virt/kvm/kvm_main.c | 2 +-
2 files changed, 1 insertion(+), 8 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d2b99c2f7dfa..88ceded7f022 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -623,13 +623,6 @@ static int mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep)
pfn = spte_to_pfn(old_spte);
- /*
- * KVM does not hold the refcount of the page used by
- * kvm mmu, before reclaiming the page, we should
- * unmap it from mmu first.
- */
- WARN_ON(!kvm_is_reserved_pfn(pfn) && !page_count(pfn_to_page(pfn)));
-
if (is_accessed_spte(old_spte))
kvm_set_pfn_accessed(pfn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5c47ea93df23..e5ddf238ec64 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -168,7 +168,7 @@ bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
* the device has been pinned, e.g. by get_user_pages(). WARN if the
* page_count() is zero to help detect bad usage of this helper.
*/
- if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn))))
+ if (!pfn_valid(pfn) || !page_count(pfn_to_page(pfn)))
return false;
return is_zone_device_page(pfn_to_page(pfn));
--
2.33.0.rc2.250.ged5fa647cd-goog
Is there any feedback on these patches? CVE-2021-22543 was fixed by
disallowing mapping of non-refcounted memory. These patches add proper
support for mapping that type of memory.
-David
On Wed, Aug 25, 2021 at 11:50 AM David Stevens <[email protected]> wrote:
>
> From: David Stevens <[email protected]>
>
> This patch series adds support for mapping non-refcount VM_IO and
> VM_PFNMAP memory into the guest.
>
> Currently, the gfn_to_pfn functions require being able to pin the target
> pfn, so they will fail if the pfn returned by follow_pte isn't a
> ref-counted page. However, the KVM secondary MMUs do not require that
> the pfn be pinned, since they are integrated with the mmu notifier API.
> This series adds a new set of gfn_to_pfn_page functions which parallel
> the gfn_to_pfn functions but do not pin the pfn. The new functions
> return the page from gup if it was present, so callers can use it and
> call put_page when done.
>
> The gfn_to_pfn functions should be depreciated, since as they are unsafe
> due to relying on trying to obtain a struct page from a pfn returned by
> follow_pte. I added new functions instead of simply adding another
> optional parameter to the existing functions to make it easier to track
> down users of the deprecated functions.
>
> This series updates x86 and arm64 secondary MMUs to the new API.
>
> v2 -> v3:
> - rebase on kvm next branch
> v1 -> v2:
> - Introduce new gfn_to_pfn_page functions instead of modifying the
> behavior of existing gfn_to_pfn functions, to make the change less
> invasive.
> - Drop changes to mmu_audit.c
> - Include Nicholas Piggin's patch to avoid corrupting refcount in the
> follow_pte case, and use it in depreciated gfn_to_pfn functions.
> - Rebase on kvm/next
>
> David Stevens (4):
> KVM: mmu: introduce new gfn_to_pfn_page functions
> KVM: x86/mmu: use gfn_to_pfn_page
> KVM: arm64/mmu: use gfn_to_pfn_page
> KVM: mmu: remove over-aggressive warnings
>
> arch/arm64/kvm/mmu.c | 26 +++--
> arch/x86/kvm/mmu/mmu.c | 50 +++++----
> arch/x86/kvm/mmu/mmu_internal.h | 3 +-
> arch/x86/kvm/mmu/paging_tmpl.h | 23 ++--
> arch/x86/kvm/mmu/tdp_mmu.c | 6 +-
> arch/x86/kvm/mmu/tdp_mmu.h | 4 +-
> arch/x86/kvm/x86.c | 6 +-
> include/linux/kvm_host.h | 17 +++
> virt/kvm/kvm_main.c | 188 +++++++++++++++++++++++---------
> 9 files changed, 220 insertions(+), 103 deletions(-)
>
> --
> 2.33.0.rc2.250.ged5fa647cd-goog
>
On 21/09/21 08:27, David Stevens wrote:
> Is there any feedback on these patches? CVE-2021-22543 was fixed by
> disallowing mapping of non-refcounted memory. These patches add proper
> support for mapping that type of memory.
Sorry, I was busy the past few weeks and I'm now back to KVM work.
Paolo
On 25/08/21 04:50, David Stevens wrote:
> From: David Stevens <[email protected]>
>
> This patch series adds support for mapping non-refcount VM_IO and
> VM_PFNMAP memory into the guest.
>
> Currently, the gfn_to_pfn functions require being able to pin the target
> pfn, so they will fail if the pfn returned by follow_pte isn't a
> ref-counted page. However, the KVM secondary MMUs do not require that
> the pfn be pinned, since they are integrated with the mmu notifier API.
> This series adds a new set of gfn_to_pfn_page functions which parallel
> the gfn_to_pfn functions but do not pin the pfn. The new functions
> return the page from gup if it was present, so callers can use it and
> call put_page when done.
>
> The gfn_to_pfn functions should be depreciated, since as they are unsafe
> due to relying on trying to obtain a struct page from a pfn returned by
> follow_pte. I added new functions instead of simply adding another
> optional parameter to the existing functions to make it easier to track
> down users of the deprecated functions.
>
> This series updates x86 and arm64 secondary MMUs to the new API.
>
> v2 -> v3:
> - rebase on kvm next branch
Hi David,
this needs a rebase. I have pushed my current queue, but note that
parts of it are still untested.
A bigger question here is the gfn_to_pfn caches and how to properly
invalidate them. However your patch doesn't make things worse (only a
bit inconsistent because pointing certain MSRs to a VM_PFNMAP|VM_IO page
can fail).
Paolo
> v1 -> v2:
> - Introduce new gfn_to_pfn_page functions instead of modifying the
> behavior of existing gfn_to_pfn functions, to make the change less
> invasive.
> - Drop changes to mmu_audit.c
> - Include Nicholas Piggin's patch to avoid corrupting refcount in the
> follow_pte case, and use it in depreciated gfn_to_pfn functions.
> - Rebase on kvm/next
>
> David Stevens (4):
> KVM: mmu: introduce new gfn_to_pfn_page functions
> KVM: x86/mmu: use gfn_to_pfn_page
> KVM: arm64/mmu: use gfn_to_pfn_page
> KVM: mmu: remove over-aggressive warnings
>
> arch/arm64/kvm/mmu.c | 26 +++--
> arch/x86/kvm/mmu/mmu.c | 50 +++++----
> arch/x86/kvm/mmu/mmu_internal.h | 3 +-
> arch/x86/kvm/mmu/paging_tmpl.h | 23 ++--
> arch/x86/kvm/mmu/tdp_mmu.c | 6 +-
> arch/x86/kvm/mmu/tdp_mmu.h | 4 +-
> arch/x86/kvm/x86.c | 6 +-
> include/linux/kvm_host.h | 17 +++
> virt/kvm/kvm_main.c | 188 +++++++++++++++++++++++---------
> 9 files changed, 220 insertions(+), 103 deletions(-)
>