2022-10-25 15:35:07

by Chao Peng

[permalink] [raw]
Subject: [PATCH v9 7/8] KVM: Handle page fault for private memory

A memslot with KVM_MEM_PRIVATE being set can include both fd-based
private memory and hva-based shared memory. Architecture code (like TDX
code) can tell whether the on-going fault is private or not. This patch
adds a 'is_private' field to kvm_page_fault to indicate this and
architecture code is expected to set it.

To handle page fault for such memslot, the handling logic is different
depending on whether the fault is private or shared. KVM checks if
'is_private' matches the host's view of the page (maintained in
mem_attr_array).
- For a successful match, private pfn is obtained with
restrictedmem_get_page () from private fd and shared pfn is obtained
with existing get_user_pages().
- For a failed match, KVM causes a KVM_EXIT_MEMORY_FAULT exit to
userspace. Userspace then can convert memory between private/shared
in host's view and retry the fault.

Co-developed-by: Yu Zhang <[email protected]>
Signed-off-by: Yu Zhang <[email protected]>
Signed-off-by: Chao Peng <[email protected]>
---
arch/x86/kvm/mmu/mmu.c | 56 +++++++++++++++++++++++++++++++--
arch/x86/kvm/mmu/mmu_internal.h | 14 ++++++++-
arch/x86/kvm/mmu/mmutrace.h | 1 +
arch/x86/kvm/mmu/spte.h | 6 ++++
arch/x86/kvm/mmu/tdp_mmu.c | 3 +-
include/linux/kvm_host.h | 28 +++++++++++++++++
6 files changed, 103 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 67a9823a8c35..10017a9f26ee 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3030,7 +3030,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,

int kvm_mmu_max_mapping_level(struct kvm *kvm,
const struct kvm_memory_slot *slot, gfn_t gfn,
- int max_level)
+ int max_level, bool is_private)
{
struct kvm_lpage_info *linfo;
int host_level;
@@ -3042,6 +3042,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
break;
}

+ if (is_private)
+ return max_level;
+
if (max_level == PG_LEVEL_4K)
return PG_LEVEL_4K;

@@ -3070,7 +3073,8 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
* level, which will be used to do precise, accurate accounting.
*/
fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
- fault->gfn, fault->max_level);
+ fault->gfn, fault->max_level,
+ fault->is_private);
if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
return;

@@ -4141,6 +4145,32 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
}

+static inline u8 order_to_level(int order)
+{
+ BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
+
+ if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
+ return PG_LEVEL_1G;
+
+ if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
+ return PG_LEVEL_2M;
+
+ return PG_LEVEL_4K;
+}
+
+static int kvm_faultin_pfn_private(struct kvm_page_fault *fault)
+{
+ int order;
+ struct kvm_memory_slot *slot = fault->slot;
+
+ if (kvm_restricted_mem_get_pfn(slot, fault->gfn, &fault->pfn, &order))
+ return RET_PF_RETRY;
+
+ fault->max_level = min(order_to_level(order), fault->max_level);
+ fault->map_writable = !(slot->flags & KVM_MEM_READONLY);
+ return RET_PF_CONTINUE;
+}
+
static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
{
struct kvm_memory_slot *slot = fault->slot;
@@ -4173,6 +4203,22 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
return RET_PF_EMULATE;
}

+ if (kvm_slot_can_be_private(slot) &&
+ fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
+ vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
+ if (fault->is_private)
+ vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
+ else
+ vcpu->run->memory.flags = 0;
+ vcpu->run->memory.padding = 0;
+ vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
+ vcpu->run->memory.size = PAGE_SIZE;
+ return RET_PF_USER;
+ }
+
+ if (fault->is_private)
+ return kvm_faultin_pfn_private(fault);
+
async = false;
fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
fault->write, &fault->map_writable,
@@ -5557,6 +5603,9 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
return -EIO;
}

+ if (r == RET_PF_USER)
+ return 0;
+
if (r < 0)
return r;
if (r != RET_PF_EMULATE)
@@ -6408,7 +6457,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
*/
if (sp->role.direct &&
sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
- PG_LEVEL_NUM)) {
+ PG_LEVEL_NUM,
+ false)) {
kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);

if (kvm_available_flush_tlb_with_range())
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 582def531d4d..5cdff5ca546c 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -188,6 +188,7 @@ struct kvm_page_fault {

/* Derived from mmu and global state. */
const bool is_tdp;
+ const bool is_private;
const bool nx_huge_page_workaround_enabled;

/*
@@ -236,6 +237,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
* RET_PF_RETRY: let CPU fault again on the address.
* RET_PF_EMULATE: mmio page fault, emulate the instruction directly.
* RET_PF_INVALID: the spte is invalid, let the real page fault path update it.
+ * RET_PF_USER: need to exit to userspace to handle this fault.
* RET_PF_FIXED: The faulting entry has been fixed.
* RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU.
*
@@ -252,6 +254,7 @@ enum {
RET_PF_RETRY,
RET_PF_EMULATE,
RET_PF_INVALID,
+ RET_PF_USER,
RET_PF_FIXED,
RET_PF_SPURIOUS,
};
@@ -309,7 +312,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,

int kvm_mmu_max_mapping_level(struct kvm *kvm,
const struct kvm_memory_slot *slot, gfn_t gfn,
- int max_level);
+ int max_level, bool is_private);
void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level);

@@ -318,4 +321,13 @@ void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);

+#ifndef CONFIG_HAVE_KVM_RESTRICTED_MEM
+static inline int kvm_restricted_mem_get_pfn(struct kvm_memory_slot *slot,
+ gfn_t gfn, kvm_pfn_t *pfn, int *order)
+{
+ WARN_ON_ONCE(1);
+ return -EOPNOTSUPP;
+}
+#endif /* CONFIG_HAVE_KVM_RESTRICTED_MEM */
+
#endif /* __KVM_X86_MMU_INTERNAL_H */
diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
index ae86820cef69..2d7555381955 100644
--- a/arch/x86/kvm/mmu/mmutrace.h
+++ b/arch/x86/kvm/mmu/mmutrace.h
@@ -58,6 +58,7 @@ TRACE_DEFINE_ENUM(RET_PF_CONTINUE);
TRACE_DEFINE_ENUM(RET_PF_RETRY);
TRACE_DEFINE_ENUM(RET_PF_EMULATE);
TRACE_DEFINE_ENUM(RET_PF_INVALID);
+TRACE_DEFINE_ENUM(RET_PF_USER);
TRACE_DEFINE_ENUM(RET_PF_FIXED);
TRACE_DEFINE_ENUM(RET_PF_SPURIOUS);

diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 7670c13ce251..9acdf72537ce 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -315,6 +315,12 @@ static inline bool is_dirty_spte(u64 spte)
return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK;
}

+static inline bool is_private_spte(u64 spte)
+{
+ /* FIXME: Query C-bit/S-bit for SEV/TDX. */
+ return false;
+}
+
static inline u64 get_rsvd_bits(struct rsvd_bits_validate *rsvd_check, u64 pte,
int level)
{
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 672f0432d777..9f97aac90606 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1768,7 +1768,8 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
continue;

max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,
- iter.gfn, PG_LEVEL_NUM);
+ iter.gfn, PG_LEVEL_NUM,
+ is_private_spte(iter.old_spte));
if (max_mapping_level < iter.level)
continue;

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 6ce36065532c..69300fc6d572 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2301,6 +2301,34 @@ static inline void kvm_arch_update_mem_attr(struct kvm *kvm,
}
#endif

+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+ return !xa_load(&kvm->mem_attr_array, gfn);
+}
+
+#else /* !CONFIG_KVM_GENERIC_PRIVATE_MEM */
+
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+ return false;
+}
+
#endif /* CONFIG_KVM_GENERIC_PRIVATE_MEM */

+#ifdef CONFIG_HAVE_KVM_RESTRICTED_MEM
+static inline int kvm_restricted_mem_get_pfn(struct kvm_memory_slot *slot,
+ gfn_t gfn, kvm_pfn_t *pfn, int *order)
+{
+ int ret;
+ struct page *page;
+ pgoff_t index = gfn - slot->base_gfn +
+ (slot->restricted_offset >> PAGE_SHIFT);
+
+ ret = restrictedmem_get_page(slot->restricted_file, index,
+ &page, order);
+ *pfn = page_to_pfn(page);
+ return ret;
+}
+#endif /* CONFIG_HAVE_KVM_RESTRICTED_MEM */
+
#endif
--
2.25.1



2022-10-26 22:44:22

by Isaku Yamahata

[permalink] [raw]
Subject: Re: [PATCH v9 7/8] KVM: Handle page fault for private memory

On Tue, Oct 25, 2022 at 11:13:43PM +0800,
Chao Peng <[email protected]> wrote:

> A memslot with KVM_MEM_PRIVATE being set can include both fd-based
> private memory and hva-based shared memory. Architecture code (like TDX
> code) can tell whether the on-going fault is private or not. This patch
> adds a 'is_private' field to kvm_page_fault to indicate this and
> architecture code is expected to set it.
>
> To handle page fault for such memslot, the handling logic is different
> depending on whether the fault is private or shared. KVM checks if
> 'is_private' matches the host's view of the page (maintained in
> mem_attr_array).
> - For a successful match, private pfn is obtained with
> restrictedmem_get_page () from private fd and shared pfn is obtained
> with existing get_user_pages().
> - For a failed match, KVM causes a KVM_EXIT_MEMORY_FAULT exit to
> userspace. Userspace then can convert memory between private/shared
> in host's view and retry the fault.
>
> Co-developed-by: Yu Zhang <[email protected]>
> Signed-off-by: Yu Zhang <[email protected]>
> Signed-off-by: Chao Peng <[email protected]>
> ---
> arch/x86/kvm/mmu/mmu.c | 56 +++++++++++++++++++++++++++++++--
> arch/x86/kvm/mmu/mmu_internal.h | 14 ++++++++-
> arch/x86/kvm/mmu/mmutrace.h | 1 +
> arch/x86/kvm/mmu/spte.h | 6 ++++
> arch/x86/kvm/mmu/tdp_mmu.c | 3 +-
> include/linux/kvm_host.h | 28 +++++++++++++++++
> 6 files changed, 103 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 67a9823a8c35..10017a9f26ee 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -3030,7 +3030,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
>
> int kvm_mmu_max_mapping_level(struct kvm *kvm,
> const struct kvm_memory_slot *slot, gfn_t gfn,
> - int max_level)
> + int max_level, bool is_private)
> {
> struct kvm_lpage_info *linfo;
> int host_level;
> @@ -3042,6 +3042,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
> break;
> }
>
> + if (is_private)
> + return max_level;

Below PG_LEVEL_NUM is passed by zap_collapsible_spte_range(). It doesn't make
sense.

> +
> if (max_level == PG_LEVEL_4K)
> return PG_LEVEL_4K;
>
> @@ -3070,7 +3073,8 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
> * level, which will be used to do precise, accurate accounting.
> */
> fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
> - fault->gfn, fault->max_level);
> + fault->gfn, fault->max_level,
> + fault->is_private);
> if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
> return;
>
> @@ -4141,6 +4145,32 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
> kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
> }
>
> +static inline u8 order_to_level(int order)
> +{
> + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
> +
> + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
> + return PG_LEVEL_1G;
> +
> + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
> + return PG_LEVEL_2M;
> +
> + return PG_LEVEL_4K;
> +}
> +
> +static int kvm_faultin_pfn_private(struct kvm_page_fault *fault)
> +{
> + int order;
> + struct kvm_memory_slot *slot = fault->slot;
> +
> + if (kvm_restricted_mem_get_pfn(slot, fault->gfn, &fault->pfn, &order))
> + return RET_PF_RETRY;
> +
> + fault->max_level = min(order_to_level(order), fault->max_level);
> + fault->map_writable = !(slot->flags & KVM_MEM_READONLY);
> + return RET_PF_CONTINUE;
> +}
> +
> static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> {
> struct kvm_memory_slot *slot = fault->slot;
> @@ -4173,6 +4203,22 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> return RET_PF_EMULATE;
> }
>
> + if (kvm_slot_can_be_private(slot) &&
> + fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
> + vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
> + if (fault->is_private)
> + vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
> + else
> + vcpu->run->memory.flags = 0;
> + vcpu->run->memory.padding = 0;
> + vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
> + vcpu->run->memory.size = PAGE_SIZE;
> + return RET_PF_USER;
> + }
> +
> + if (fault->is_private)
> + return kvm_faultin_pfn_private(fault);
> +
> async = false;
> fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
> fault->write, &fault->map_writable,
> @@ -5557,6 +5603,9 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
> return -EIO;
> }
>
> + if (r == RET_PF_USER)
> + return 0;
> +
> if (r < 0)
> return r;
> if (r != RET_PF_EMULATE)
> @@ -6408,7 +6457,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
> */
> if (sp->role.direct &&
> sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
> - PG_LEVEL_NUM)) {
> + PG_LEVEL_NUM,
> + false)) {
> kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
>
> if (kvm_available_flush_tlb_with_range())
> diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
> index 582def531d4d..5cdff5ca546c 100644
> --- a/arch/x86/kvm/mmu/mmu_internal.h
> +++ b/arch/x86/kvm/mmu/mmu_internal.h
> @@ -188,6 +188,7 @@ struct kvm_page_fault {
>
> /* Derived from mmu and global state. */
> const bool is_tdp;
> + const bool is_private;
> const bool nx_huge_page_workaround_enabled;
>
> /*
> @@ -236,6 +237,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
> * RET_PF_RETRY: let CPU fault again on the address.
> * RET_PF_EMULATE: mmio page fault, emulate the instruction directly.
> * RET_PF_INVALID: the spte is invalid, let the real page fault path update it.
> + * RET_PF_USER: need to exit to userspace to handle this fault.
> * RET_PF_FIXED: The faulting entry has been fixed.
> * RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU.
> *
> @@ -252,6 +254,7 @@ enum {
> RET_PF_RETRY,
> RET_PF_EMULATE,
> RET_PF_INVALID,
> + RET_PF_USER,
> RET_PF_FIXED,
> RET_PF_SPURIOUS,
> };
> @@ -309,7 +312,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
>
> int kvm_mmu_max_mapping_level(struct kvm *kvm,
> const struct kvm_memory_slot *slot, gfn_t gfn,
> - int max_level);
> + int max_level, bool is_private);
> void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
> void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level);
>
> @@ -318,4 +321,13 @@ void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
> void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
> void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
>
> +#ifndef CONFIG_HAVE_KVM_RESTRICTED_MEM
> +static inline int kvm_restricted_mem_get_pfn(struct kvm_memory_slot *slot,
> + gfn_t gfn, kvm_pfn_t *pfn, int *order)
> +{
> + WARN_ON_ONCE(1);
> + return -EOPNOTSUPP;
> +}
> +#endif /* CONFIG_HAVE_KVM_RESTRICTED_MEM */
> +
> #endif /* __KVM_X86_MMU_INTERNAL_H */
> diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
> index ae86820cef69..2d7555381955 100644
> --- a/arch/x86/kvm/mmu/mmutrace.h
> +++ b/arch/x86/kvm/mmu/mmutrace.h
> @@ -58,6 +58,7 @@ TRACE_DEFINE_ENUM(RET_PF_CONTINUE);
> TRACE_DEFINE_ENUM(RET_PF_RETRY);
> TRACE_DEFINE_ENUM(RET_PF_EMULATE);
> TRACE_DEFINE_ENUM(RET_PF_INVALID);
> +TRACE_DEFINE_ENUM(RET_PF_USER);
> TRACE_DEFINE_ENUM(RET_PF_FIXED);
> TRACE_DEFINE_ENUM(RET_PF_SPURIOUS);
>
> diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
> index 7670c13ce251..9acdf72537ce 100644
> --- a/arch/x86/kvm/mmu/spte.h
> +++ b/arch/x86/kvm/mmu/spte.h
> @@ -315,6 +315,12 @@ static inline bool is_dirty_spte(u64 spte)
> return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK;
> }
>
> +static inline bool is_private_spte(u64 spte)
> +{
> + /* FIXME: Query C-bit/S-bit for SEV/TDX. */
> + return false;
> +}
> +

PFN encoded in spte doesn't make sense. In VMM for TDX, private-vs-shared is
determined by S-bit of GFN.


> static inline u64 get_rsvd_bits(struct rsvd_bits_validate *rsvd_check, u64 pte,
> int level)
> {
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index 672f0432d777..9f97aac90606 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -1768,7 +1768,8 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
> continue;
>
> max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,
> - iter.gfn, PG_LEVEL_NUM);
> + iter.gfn, PG_LEVEL_NUM,
> + is_private_spte(iter.old_spte));
> if (max_mapping_level < iter.level)
> continue;

This is to merge pages into a large page on the next kvm page fault. large page
support is not yet supported. Let's skip the private slot until large page
support is done.
--
Isaku Yamahata <[email protected]>

2022-10-28 07:35:42

by Chao Peng

[permalink] [raw]
Subject: Re: [PATCH v9 7/8] KVM: Handle page fault for private memory

On Wed, Oct 26, 2022 at 02:54:25PM -0700, Isaku Yamahata wrote:
> On Tue, Oct 25, 2022 at 11:13:43PM +0800,
> Chao Peng <[email protected]> wrote:
>
> > A memslot with KVM_MEM_PRIVATE being set can include both fd-based
> > private memory and hva-based shared memory. Architecture code (like TDX
> > code) can tell whether the on-going fault is private or not. This patch
> > adds a 'is_private' field to kvm_page_fault to indicate this and
> > architecture code is expected to set it.
> >
> > To handle page fault for such memslot, the handling logic is different
> > depending on whether the fault is private or shared. KVM checks if
> > 'is_private' matches the host's view of the page (maintained in
> > mem_attr_array).
> > - For a successful match, private pfn is obtained with
> > restrictedmem_get_page () from private fd and shared pfn is obtained
> > with existing get_user_pages().
> > - For a failed match, KVM causes a KVM_EXIT_MEMORY_FAULT exit to
> > userspace. Userspace then can convert memory between private/shared
> > in host's view and retry the fault.
> >
> > Co-developed-by: Yu Zhang <[email protected]>
> > Signed-off-by: Yu Zhang <[email protected]>
> > Signed-off-by: Chao Peng <[email protected]>
> > ---
> > arch/x86/kvm/mmu/mmu.c | 56 +++++++++++++++++++++++++++++++--
> > arch/x86/kvm/mmu/mmu_internal.h | 14 ++++++++-
> > arch/x86/kvm/mmu/mmutrace.h | 1 +
> > arch/x86/kvm/mmu/spte.h | 6 ++++
> > arch/x86/kvm/mmu/tdp_mmu.c | 3 +-
> > include/linux/kvm_host.h | 28 +++++++++++++++++
> > 6 files changed, 103 insertions(+), 5 deletions(-)
> >
> > diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> > index 67a9823a8c35..10017a9f26ee 100644
> > --- a/arch/x86/kvm/mmu/mmu.c
> > +++ b/arch/x86/kvm/mmu/mmu.c
> > @@ -3030,7 +3030,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
> >
> > int kvm_mmu_max_mapping_level(struct kvm *kvm,
> > const struct kvm_memory_slot *slot, gfn_t gfn,
> > - int max_level)
> > + int max_level, bool is_private)
> > {
> > struct kvm_lpage_info *linfo;
> > int host_level;
> > @@ -3042,6 +3042,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
> > break;
> > }
> >
> > + if (is_private)
> > + return max_level;
>
> Below PG_LEVEL_NUM is passed by zap_collapsible_spte_range(). It doesn't make
> sense.
>
> > +
> > if (max_level == PG_LEVEL_4K)
> > return PG_LEVEL_4K;
> >
> > @@ -3070,7 +3073,8 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
> > * level, which will be used to do precise, accurate accounting.
> > */
> > fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
> > - fault->gfn, fault->max_level);
> > + fault->gfn, fault->max_level,
> > + fault->is_private);
> > if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
> > return;
> >
> > @@ -4141,6 +4145,32 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
> > kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
> > }
> >
> > +static inline u8 order_to_level(int order)
> > +{
> > + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
> > +
> > + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
> > + return PG_LEVEL_1G;
> > +
> > + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
> > + return PG_LEVEL_2M;
> > +
> > + return PG_LEVEL_4K;
> > +}
> > +
> > +static int kvm_faultin_pfn_private(struct kvm_page_fault *fault)
> > +{
> > + int order;
> > + struct kvm_memory_slot *slot = fault->slot;
> > +
> > + if (kvm_restricted_mem_get_pfn(slot, fault->gfn, &fault->pfn, &order))
> > + return RET_PF_RETRY;
> > +
> > + fault->max_level = min(order_to_level(order), fault->max_level);
> > + fault->map_writable = !(slot->flags & KVM_MEM_READONLY);
> > + return RET_PF_CONTINUE;
> > +}
> > +
> > static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> > {
> > struct kvm_memory_slot *slot = fault->slot;
> > @@ -4173,6 +4203,22 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> > return RET_PF_EMULATE;
> > }
> >
> > + if (kvm_slot_can_be_private(slot) &&
> > + fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
> > + vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
> > + if (fault->is_private)
> > + vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
> > + else
> > + vcpu->run->memory.flags = 0;
> > + vcpu->run->memory.padding = 0;
> > + vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
> > + vcpu->run->memory.size = PAGE_SIZE;
> > + return RET_PF_USER;
> > + }
> > +
> > + if (fault->is_private)
> > + return kvm_faultin_pfn_private(fault);
> > +
> > async = false;
> > fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
> > fault->write, &fault->map_writable,
> > @@ -5557,6 +5603,9 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
> > return -EIO;
> > }
> >
> > + if (r == RET_PF_USER)
> > + return 0;
> > +
> > if (r < 0)
> > return r;
> > if (r != RET_PF_EMULATE)
> > @@ -6408,7 +6457,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
> > */
> > if (sp->role.direct &&
> > sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
> > - PG_LEVEL_NUM)) {
> > + PG_LEVEL_NUM,
> > + false)) {
> > kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
> >
> > if (kvm_available_flush_tlb_with_range())
> > diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
> > index 582def531d4d..5cdff5ca546c 100644
> > --- a/arch/x86/kvm/mmu/mmu_internal.h
> > +++ b/arch/x86/kvm/mmu/mmu_internal.h
> > @@ -188,6 +188,7 @@ struct kvm_page_fault {
> >
> > /* Derived from mmu and global state. */
> > const bool is_tdp;
> > + const bool is_private;
> > const bool nx_huge_page_workaround_enabled;
> >
> > /*
> > @@ -236,6 +237,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
> > * RET_PF_RETRY: let CPU fault again on the address.
> > * RET_PF_EMULATE: mmio page fault, emulate the instruction directly.
> > * RET_PF_INVALID: the spte is invalid, let the real page fault path update it.
> > + * RET_PF_USER: need to exit to userspace to handle this fault.
> > * RET_PF_FIXED: The faulting entry has been fixed.
> > * RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU.
> > *
> > @@ -252,6 +254,7 @@ enum {
> > RET_PF_RETRY,
> > RET_PF_EMULATE,
> > RET_PF_INVALID,
> > + RET_PF_USER,
> > RET_PF_FIXED,
> > RET_PF_SPURIOUS,
> > };
> > @@ -309,7 +312,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
> >
> > int kvm_mmu_max_mapping_level(struct kvm *kvm,
> > const struct kvm_memory_slot *slot, gfn_t gfn,
> > - int max_level);
> > + int max_level, bool is_private);
> > void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
> > void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level);
> >
> > @@ -318,4 +321,13 @@ void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
> > void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
> > void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
> >
> > +#ifndef CONFIG_HAVE_KVM_RESTRICTED_MEM
> > +static inline int kvm_restricted_mem_get_pfn(struct kvm_memory_slot *slot,
> > + gfn_t gfn, kvm_pfn_t *pfn, int *order)
> > +{
> > + WARN_ON_ONCE(1);
> > + return -EOPNOTSUPP;
> > +}
> > +#endif /* CONFIG_HAVE_KVM_RESTRICTED_MEM */
> > +
> > #endif /* __KVM_X86_MMU_INTERNAL_H */
> > diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
> > index ae86820cef69..2d7555381955 100644
> > --- a/arch/x86/kvm/mmu/mmutrace.h
> > +++ b/arch/x86/kvm/mmu/mmutrace.h
> > @@ -58,6 +58,7 @@ TRACE_DEFINE_ENUM(RET_PF_CONTINUE);
> > TRACE_DEFINE_ENUM(RET_PF_RETRY);
> > TRACE_DEFINE_ENUM(RET_PF_EMULATE);
> > TRACE_DEFINE_ENUM(RET_PF_INVALID);
> > +TRACE_DEFINE_ENUM(RET_PF_USER);
> > TRACE_DEFINE_ENUM(RET_PF_FIXED);
> > TRACE_DEFINE_ENUM(RET_PF_SPURIOUS);
> >
> > diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
> > index 7670c13ce251..9acdf72537ce 100644
> > --- a/arch/x86/kvm/mmu/spte.h
> > +++ b/arch/x86/kvm/mmu/spte.h
> > @@ -315,6 +315,12 @@ static inline bool is_dirty_spte(u64 spte)
> > return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK;
> > }
> >
> > +static inline bool is_private_spte(u64 spte)
> > +{
> > + /* FIXME: Query C-bit/S-bit for SEV/TDX. */
> > + return false;
> > +}
> > +
>
> PFN encoded in spte doesn't make sense. In VMM for TDX, private-vs-shared is
> determined by S-bit of GFN.

My understanding is we will have software bit in the spte, will we? In
current TDX code I see we have SPTE_SHARED_MASK bit defined.

>
>
> > static inline u64 get_rsvd_bits(struct rsvd_bits_validate *rsvd_check, u64 pte,
> > int level)
> > {
> > diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> > index 672f0432d777..9f97aac90606 100644
> > --- a/arch/x86/kvm/mmu/tdp_mmu.c
> > +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> > @@ -1768,7 +1768,8 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
> > continue;
> >
> > max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,
> > - iter.gfn, PG_LEVEL_NUM);
> > + iter.gfn, PG_LEVEL_NUM,
> > + is_private_spte(iter.old_spte));
> > if (max_mapping_level < iter.level)
> > continue;
>
> This is to merge pages into a large page on the next kvm page fault. large page
> support is not yet supported. Let's skip the private slot until large page
> support is done.

So what your suggestion is passing in a 'false' at this time for
'is_private'? Unless we will decide not use the above is_private_spte,
this code does not hurt, right? is_private_spte() return false before
we finally get chance to add the large page support.

Thanks,
Chao
> --
> Isaku Yamahata <[email protected]>

2022-11-01 00:08:21

by Isaku Yamahata

[permalink] [raw]
Subject: Re: [PATCH v9 7/8] KVM: Handle page fault for private memory

On Fri, Oct 28, 2022 at 02:55:45PM +0800,
Chao Peng <[email protected]> wrote:

> On Wed, Oct 26, 2022 at 02:54:25PM -0700, Isaku Yamahata wrote:
> > On Tue, Oct 25, 2022 at 11:13:43PM +0800,
> > Chao Peng <[email protected]> wrote:
> >
> > > A memslot with KVM_MEM_PRIVATE being set can include both fd-based
> > > private memory and hva-based shared memory. Architecture code (like TDX
> > > code) can tell whether the on-going fault is private or not. This patch
> > > adds a 'is_private' field to kvm_page_fault to indicate this and
> > > architecture code is expected to set it.
> > >
> > > To handle page fault for such memslot, the handling logic is different
> > > depending on whether the fault is private or shared. KVM checks if
> > > 'is_private' matches the host's view of the page (maintained in
> > > mem_attr_array).
> > > - For a successful match, private pfn is obtained with
> > > restrictedmem_get_page () from private fd and shared pfn is obtained
> > > with existing get_user_pages().
> > > - For a failed match, KVM causes a KVM_EXIT_MEMORY_FAULT exit to
> > > userspace. Userspace then can convert memory between private/shared
> > > in host's view and retry the fault.
> > >
> > > Co-developed-by: Yu Zhang <[email protected]>
> > > Signed-off-by: Yu Zhang <[email protected]>
> > > Signed-off-by: Chao Peng <[email protected]>
> > > ---
> > > arch/x86/kvm/mmu/mmu.c | 56 +++++++++++++++++++++++++++++++--
> > > arch/x86/kvm/mmu/mmu_internal.h | 14 ++++++++-
> > > arch/x86/kvm/mmu/mmutrace.h | 1 +
> > > arch/x86/kvm/mmu/spte.h | 6 ++++
> > > arch/x86/kvm/mmu/tdp_mmu.c | 3 +-
> > > include/linux/kvm_host.h | 28 +++++++++++++++++
> > > 6 files changed, 103 insertions(+), 5 deletions(-)
> > >
> > > diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> > > index 67a9823a8c35..10017a9f26ee 100644
> > > --- a/arch/x86/kvm/mmu/mmu.c
> > > +++ b/arch/x86/kvm/mmu/mmu.c
> > > @@ -3030,7 +3030,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
> > >
> > > int kvm_mmu_max_mapping_level(struct kvm *kvm,
> > > const struct kvm_memory_slot *slot, gfn_t gfn,
> > > - int max_level)
> > > + int max_level, bool is_private)
> > > {
> > > struct kvm_lpage_info *linfo;
> > > int host_level;
> > > @@ -3042,6 +3042,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
> > > break;
> > > }
> > >
> > > + if (is_private)
> > > + return max_level;
> >
> > Below PG_LEVEL_NUM is passed by zap_collapsible_spte_range(). It doesn't make
> > sense.
> >
> > > +
> > > if (max_level == PG_LEVEL_4K)
> > > return PG_LEVEL_4K;
> > >
> > > @@ -3070,7 +3073,8 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
> > > * level, which will be used to do precise, accurate accounting.
> > > */
> > > fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
> > > - fault->gfn, fault->max_level);
> > > + fault->gfn, fault->max_level,
> > > + fault->is_private);
> > > if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
> > > return;
> > >
> > > @@ -4141,6 +4145,32 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
> > > kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
> > > }
> > >
> > > +static inline u8 order_to_level(int order)
> > > +{
> > > + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
> > > +
> > > + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
> > > + return PG_LEVEL_1G;
> > > +
> > > + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
> > > + return PG_LEVEL_2M;
> > > +
> > > + return PG_LEVEL_4K;
> > > +}
> > > +
> > > +static int kvm_faultin_pfn_private(struct kvm_page_fault *fault)
> > > +{
> > > + int order;
> > > + struct kvm_memory_slot *slot = fault->slot;
> > > +
> > > + if (kvm_restricted_mem_get_pfn(slot, fault->gfn, &fault->pfn, &order))
> > > + return RET_PF_RETRY;
> > > +
> > > + fault->max_level = min(order_to_level(order), fault->max_level);
> > > + fault->map_writable = !(slot->flags & KVM_MEM_READONLY);
> > > + return RET_PF_CONTINUE;
> > > +}
> > > +
> > > static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> > > {
> > > struct kvm_memory_slot *slot = fault->slot;
> > > @@ -4173,6 +4203,22 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> > > return RET_PF_EMULATE;
> > > }
> > >
> > > + if (kvm_slot_can_be_private(slot) &&
> > > + fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
> > > + vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
> > > + if (fault->is_private)
> > > + vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
> > > + else
> > > + vcpu->run->memory.flags = 0;
> > > + vcpu->run->memory.padding = 0;
> > > + vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
> > > + vcpu->run->memory.size = PAGE_SIZE;
> > > + return RET_PF_USER;
> > > + }
> > > +
> > > + if (fault->is_private)
> > > + return kvm_faultin_pfn_private(fault);
> > > +
> > > async = false;
> > > fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
> > > fault->write, &fault->map_writable,
> > > @@ -5557,6 +5603,9 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
> > > return -EIO;
> > > }
> > >
> > > + if (r == RET_PF_USER)
> > > + return 0;
> > > +
> > > if (r < 0)
> > > return r;
> > > if (r != RET_PF_EMULATE)
> > > @@ -6408,7 +6457,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
> > > */
> > > if (sp->role.direct &&
> > > sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
> > > - PG_LEVEL_NUM)) {
> > > + PG_LEVEL_NUM,
> > > + false)) {
> > > kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
> > >
> > > if (kvm_available_flush_tlb_with_range())
> > > diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
> > > index 582def531d4d..5cdff5ca546c 100644
> > > --- a/arch/x86/kvm/mmu/mmu_internal.h
> > > +++ b/arch/x86/kvm/mmu/mmu_internal.h
> > > @@ -188,6 +188,7 @@ struct kvm_page_fault {
> > >
> > > /* Derived from mmu and global state. */
> > > const bool is_tdp;
> > > + const bool is_private;
> > > const bool nx_huge_page_workaround_enabled;
> > >
> > > /*
> > > @@ -236,6 +237,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
> > > * RET_PF_RETRY: let CPU fault again on the address.
> > > * RET_PF_EMULATE: mmio page fault, emulate the instruction directly.
> > > * RET_PF_INVALID: the spte is invalid, let the real page fault path update it.
> > > + * RET_PF_USER: need to exit to userspace to handle this fault.
> > > * RET_PF_FIXED: The faulting entry has been fixed.
> > > * RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU.
> > > *
> > > @@ -252,6 +254,7 @@ enum {
> > > RET_PF_RETRY,
> > > RET_PF_EMULATE,
> > > RET_PF_INVALID,
> > > + RET_PF_USER,
> > > RET_PF_FIXED,
> > > RET_PF_SPURIOUS,
> > > };
> > > @@ -309,7 +312,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
> > >
> > > int kvm_mmu_max_mapping_level(struct kvm *kvm,
> > > const struct kvm_memory_slot *slot, gfn_t gfn,
> > > - int max_level);
> > > + int max_level, bool is_private);
> > > void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
> > > void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level);
> > >
> > > @@ -318,4 +321,13 @@ void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
> > > void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
> > > void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
> > >
> > > +#ifndef CONFIG_HAVE_KVM_RESTRICTED_MEM
> > > +static inline int kvm_restricted_mem_get_pfn(struct kvm_memory_slot *slot,
> > > + gfn_t gfn, kvm_pfn_t *pfn, int *order)
> > > +{
> > > + WARN_ON_ONCE(1);
> > > + return -EOPNOTSUPP;
> > > +}
> > > +#endif /* CONFIG_HAVE_KVM_RESTRICTED_MEM */
> > > +
> > > #endif /* __KVM_X86_MMU_INTERNAL_H */
> > > diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
> > > index ae86820cef69..2d7555381955 100644
> > > --- a/arch/x86/kvm/mmu/mmutrace.h
> > > +++ b/arch/x86/kvm/mmu/mmutrace.h
> > > @@ -58,6 +58,7 @@ TRACE_DEFINE_ENUM(RET_PF_CONTINUE);
> > > TRACE_DEFINE_ENUM(RET_PF_RETRY);
> > > TRACE_DEFINE_ENUM(RET_PF_EMULATE);
> > > TRACE_DEFINE_ENUM(RET_PF_INVALID);
> > > +TRACE_DEFINE_ENUM(RET_PF_USER);
> > > TRACE_DEFINE_ENUM(RET_PF_FIXED);
> > > TRACE_DEFINE_ENUM(RET_PF_SPURIOUS);
> > >
> > > diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
> > > index 7670c13ce251..9acdf72537ce 100644
> > > --- a/arch/x86/kvm/mmu/spte.h
> > > +++ b/arch/x86/kvm/mmu/spte.h
> > > @@ -315,6 +315,12 @@ static inline bool is_dirty_spte(u64 spte)
> > > return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK;
> > > }
> > >
> > > +static inline bool is_private_spte(u64 spte)
> > > +{
> > > + /* FIXME: Query C-bit/S-bit for SEV/TDX. */
> > > + return false;
> > > +}
> > > +
> >
> > PFN encoded in spte doesn't make sense. In VMM for TDX, private-vs-shared is
> > determined by S-bit of GFN.
>
> My understanding is we will have software bit in the spte, will we? In
> current TDX code I see we have SPTE_SHARED_MASK bit defined.

I'm afraid that you're referring old version. It's not. For TDX, gfn needs
to be checked. Which isn't encoded in spte.


> > > static inline u64 get_rsvd_bits(struct rsvd_bits_validate *rsvd_check, u64 pte,
> > > int level)
> > > {
> > > diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> > > index 672f0432d777..9f97aac90606 100644
> > > --- a/arch/x86/kvm/mmu/tdp_mmu.c
> > > +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> > > @@ -1768,7 +1768,8 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
> > > continue;
> > >
> > > max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,
> > > - iter.gfn, PG_LEVEL_NUM);
> > > + iter.gfn, PG_LEVEL_NUM,
> > > + is_private_spte(iter.old_spte));
> > > if (max_mapping_level < iter.level)
> > > continue;
> >
> > This is to merge pages into a large page on the next kvm page fault. large page
> > support is not yet supported. Let's skip the private slot until large page
> > support is done.
>
> So what your suggestion is passing in a 'false' at this time for
> 'is_private'? Unless we will decide not use the above is_private_spte,
> this code does not hurt, right? is_private_spte() return false before
> we finally get chance to add the large page support.

Let's pass false always for now.
--
Isaku Yamahata <[email protected]>

2022-11-01 12:00:17

by Chao Peng

[permalink] [raw]
Subject: Re: [PATCH v9 7/8] KVM: Handle page fault for private memory

On Mon, Oct 31, 2022 at 05:02:50PM -0700, Isaku Yamahata wrote:
> On Fri, Oct 28, 2022 at 02:55:45PM +0800,
> Chao Peng <[email protected]> wrote:
>
> > On Wed, Oct 26, 2022 at 02:54:25PM -0700, Isaku Yamahata wrote:
> > > On Tue, Oct 25, 2022 at 11:13:43PM +0800,
> > > Chao Peng <[email protected]> wrote:
> > >
> > > > A memslot with KVM_MEM_PRIVATE being set can include both fd-based
> > > > private memory and hva-based shared memory. Architecture code (like TDX
> > > > code) can tell whether the on-going fault is private or not. This patch
> > > > adds a 'is_private' field to kvm_page_fault to indicate this and
> > > > architecture code is expected to set it.
> > > >
> > > > To handle page fault for such memslot, the handling logic is different
> > > > depending on whether the fault is private or shared. KVM checks if
> > > > 'is_private' matches the host's view of the page (maintained in
> > > > mem_attr_array).
> > > > - For a successful match, private pfn is obtained with
> > > > restrictedmem_get_page () from private fd and shared pfn is obtained
> > > > with existing get_user_pages().
> > > > - For a failed match, KVM causes a KVM_EXIT_MEMORY_FAULT exit to
> > > > userspace. Userspace then can convert memory between private/shared
> > > > in host's view and retry the fault.
> > > >
> > > > Co-developed-by: Yu Zhang <[email protected]>
> > > > Signed-off-by: Yu Zhang <[email protected]>
> > > > Signed-off-by: Chao Peng <[email protected]>
> > > > ---
> > > > arch/x86/kvm/mmu/mmu.c | 56 +++++++++++++++++++++++++++++++--
> > > > arch/x86/kvm/mmu/mmu_internal.h | 14 ++++++++-
> > > > arch/x86/kvm/mmu/mmutrace.h | 1 +
> > > > arch/x86/kvm/mmu/spte.h | 6 ++++
> > > > arch/x86/kvm/mmu/tdp_mmu.c | 3 +-
> > > > include/linux/kvm_host.h | 28 +++++++++++++++++
> > > > 6 files changed, 103 insertions(+), 5 deletions(-)
> > > >
> > > > diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> > > > index 67a9823a8c35..10017a9f26ee 100644
> > > > --- a/arch/x86/kvm/mmu/mmu.c
> > > > +++ b/arch/x86/kvm/mmu/mmu.c
> > > > @@ -3030,7 +3030,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
> > > >
> > > > int kvm_mmu_max_mapping_level(struct kvm *kvm,
> > > > const struct kvm_memory_slot *slot, gfn_t gfn,
> > > > - int max_level)
> > > > + int max_level, bool is_private)
> > > > {
> > > > struct kvm_lpage_info *linfo;
> > > > int host_level;
> > > > @@ -3042,6 +3042,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
> > > > break;
> > > > }
> > > >
> > > > + if (is_private)
> > > > + return max_level;
> > >
> > > Below PG_LEVEL_NUM is passed by zap_collapsible_spte_range(). It doesn't make
> > > sense.
> > >
> > > > +
> > > > if (max_level == PG_LEVEL_4K)
> > > > return PG_LEVEL_4K;
> > > >
> > > > @@ -3070,7 +3073,8 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
> > > > * level, which will be used to do precise, accurate accounting.
> > > > */
> > > > fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
> > > > - fault->gfn, fault->max_level);
> > > > + fault->gfn, fault->max_level,
> > > > + fault->is_private);
> > > > if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
> > > > return;
> > > >
> > > > @@ -4141,6 +4145,32 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
> > > > kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
> > > > }
> > > >
> > > > +static inline u8 order_to_level(int order)
> > > > +{
> > > > + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
> > > > +
> > > > + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
> > > > + return PG_LEVEL_1G;
> > > > +
> > > > + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
> > > > + return PG_LEVEL_2M;
> > > > +
> > > > + return PG_LEVEL_4K;
> > > > +}
> > > > +
> > > > +static int kvm_faultin_pfn_private(struct kvm_page_fault *fault)
> > > > +{
> > > > + int order;
> > > > + struct kvm_memory_slot *slot = fault->slot;
> > > > +
> > > > + if (kvm_restricted_mem_get_pfn(slot, fault->gfn, &fault->pfn, &order))
> > > > + return RET_PF_RETRY;
> > > > +
> > > > + fault->max_level = min(order_to_level(order), fault->max_level);
> > > > + fault->map_writable = !(slot->flags & KVM_MEM_READONLY);
> > > > + return RET_PF_CONTINUE;
> > > > +}
> > > > +
> > > > static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> > > > {
> > > > struct kvm_memory_slot *slot = fault->slot;
> > > > @@ -4173,6 +4203,22 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> > > > return RET_PF_EMULATE;
> > > > }
> > > >
> > > > + if (kvm_slot_can_be_private(slot) &&
> > > > + fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
> > > > + vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
> > > > + if (fault->is_private)
> > > > + vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
> > > > + else
> > > > + vcpu->run->memory.flags = 0;
> > > > + vcpu->run->memory.padding = 0;
> > > > + vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
> > > > + vcpu->run->memory.size = PAGE_SIZE;
> > > > + return RET_PF_USER;
> > > > + }
> > > > +
> > > > + if (fault->is_private)
> > > > + return kvm_faultin_pfn_private(fault);
> > > > +
> > > > async = false;
> > > > fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
> > > > fault->write, &fault->map_writable,
> > > > @@ -5557,6 +5603,9 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
> > > > return -EIO;
> > > > }
> > > >
> > > > + if (r == RET_PF_USER)
> > > > + return 0;
> > > > +
> > > > if (r < 0)
> > > > return r;
> > > > if (r != RET_PF_EMULATE)
> > > > @@ -6408,7 +6457,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
> > > > */
> > > > if (sp->role.direct &&
> > > > sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
> > > > - PG_LEVEL_NUM)) {
> > > > + PG_LEVEL_NUM,
> > > > + false)) {
> > > > kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
> > > >
> > > > if (kvm_available_flush_tlb_with_range())
> > > > diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
> > > > index 582def531d4d..5cdff5ca546c 100644
> > > > --- a/arch/x86/kvm/mmu/mmu_internal.h
> > > > +++ b/arch/x86/kvm/mmu/mmu_internal.h
> > > > @@ -188,6 +188,7 @@ struct kvm_page_fault {
> > > >
> > > > /* Derived from mmu and global state. */
> > > > const bool is_tdp;
> > > > + const bool is_private;
> > > > const bool nx_huge_page_workaround_enabled;
> > > >
> > > > /*
> > > > @@ -236,6 +237,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
> > > > * RET_PF_RETRY: let CPU fault again on the address.
> > > > * RET_PF_EMULATE: mmio page fault, emulate the instruction directly.
> > > > * RET_PF_INVALID: the spte is invalid, let the real page fault path update it.
> > > > + * RET_PF_USER: need to exit to userspace to handle this fault.
> > > > * RET_PF_FIXED: The faulting entry has been fixed.
> > > > * RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU.
> > > > *
> > > > @@ -252,6 +254,7 @@ enum {
> > > > RET_PF_RETRY,
> > > > RET_PF_EMULATE,
> > > > RET_PF_INVALID,
> > > > + RET_PF_USER,
> > > > RET_PF_FIXED,
> > > > RET_PF_SPURIOUS,
> > > > };
> > > > @@ -309,7 +312,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
> > > >
> > > > int kvm_mmu_max_mapping_level(struct kvm *kvm,
> > > > const struct kvm_memory_slot *slot, gfn_t gfn,
> > > > - int max_level);
> > > > + int max_level, bool is_private);
> > > > void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault);
> > > > void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level);
> > > >
> > > > @@ -318,4 +321,13 @@ void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
> > > > void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
> > > > void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
> > > >
> > > > +#ifndef CONFIG_HAVE_KVM_RESTRICTED_MEM
> > > > +static inline int kvm_restricted_mem_get_pfn(struct kvm_memory_slot *slot,
> > > > + gfn_t gfn, kvm_pfn_t *pfn, int *order)
> > > > +{
> > > > + WARN_ON_ONCE(1);
> > > > + return -EOPNOTSUPP;
> > > > +}
> > > > +#endif /* CONFIG_HAVE_KVM_RESTRICTED_MEM */
> > > > +
> > > > #endif /* __KVM_X86_MMU_INTERNAL_H */
> > > > diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
> > > > index ae86820cef69..2d7555381955 100644
> > > > --- a/arch/x86/kvm/mmu/mmutrace.h
> > > > +++ b/arch/x86/kvm/mmu/mmutrace.h
> > > > @@ -58,6 +58,7 @@ TRACE_DEFINE_ENUM(RET_PF_CONTINUE);
> > > > TRACE_DEFINE_ENUM(RET_PF_RETRY);
> > > > TRACE_DEFINE_ENUM(RET_PF_EMULATE);
> > > > TRACE_DEFINE_ENUM(RET_PF_INVALID);
> > > > +TRACE_DEFINE_ENUM(RET_PF_USER);
> > > > TRACE_DEFINE_ENUM(RET_PF_FIXED);
> > > > TRACE_DEFINE_ENUM(RET_PF_SPURIOUS);
> > > >
> > > > diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
> > > > index 7670c13ce251..9acdf72537ce 100644
> > > > --- a/arch/x86/kvm/mmu/spte.h
> > > > +++ b/arch/x86/kvm/mmu/spte.h
> > > > @@ -315,6 +315,12 @@ static inline bool is_dirty_spte(u64 spte)
> > > > return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK;
> > > > }
> > > >
> > > > +static inline bool is_private_spte(u64 spte)
> > > > +{
> > > > + /* FIXME: Query C-bit/S-bit for SEV/TDX. */
> > > > + return false;
> > > > +}
> > > > +
> > >
> > > PFN encoded in spte doesn't make sense. In VMM for TDX, private-vs-shared is
> > > determined by S-bit of GFN.
> >
> > My understanding is we will have software bit in the spte, will we? In
> > current TDX code I see we have SPTE_SHARED_MASK bit defined.
>
> I'm afraid that you're referring old version. It's not. For TDX, gfn needs
> to be checked. Which isn't encoded in spte.

Okay.

>
>
> > > > static inline u64 get_rsvd_bits(struct rsvd_bits_validate *rsvd_check, u64 pte,
> > > > int level)
> > > > {
> > > > diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> > > > index 672f0432d777..9f97aac90606 100644
> > > > --- a/arch/x86/kvm/mmu/tdp_mmu.c
> > > > +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> > > > @@ -1768,7 +1768,8 @@ static void zap_collapsible_spte_range(struct kvm *kvm,
> > > > continue;
> > > >
> > > > max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot,
> > > > - iter.gfn, PG_LEVEL_NUM);
> > > > + iter.gfn, PG_LEVEL_NUM,
> > > > + is_private_spte(iter.old_spte));
> > > > if (max_mapping_level < iter.level)
> > > > continue;
> > >
> > > This is to merge pages into a large page on the next kvm page fault. large page
> > > support is not yet supported. Let's skip the private slot until large page
> > > support is done.
> >
> > So what your suggestion is passing in a 'false' at this time for
> > 'is_private'? Unless we will decide not use the above is_private_spte,
> > this code does not hurt, right? is_private_spte() return false before
> > we finally get chance to add the large page support.
>
> Let's pass false always for now.

Good to me. Thanks.

Chao
> --
> Isaku Yamahata <[email protected]>

2022-11-16 20:55:41

by Ackerley Tng

[permalink] [raw]
Subject: Re: [PATCH v9 7/8] KVM: Handle page fault for private memory

> A memslot with KVM_MEM_PRIVATE being set can include both fd-based
> private memory and hva-based shared memory. Architecture code (like TDX
> code) can tell whether the on-going fault is private or not. This patch
> adds a 'is_private' field to kvm_page_fault to indicate this and
> architecture code is expected to set it.
>
> To handle page fault for such memslot, the handling logic is different
> depending on whether the fault is private or shared. KVM checks if
> 'is_private' matches the host's view of the page (maintained in
> mem_attr_array).
> - For a successful match, private pfn is obtained with
> restrictedmem_get_page () from private fd and shared pfn is obtained
> with existing get_user_pages().
> - For a failed match, KVM causes a KVM_EXIT_MEMORY_FAULT exit to
> userspace. Userspace then can convert memory between private/shared
> in host's view and retry the fault.
>
> Co-developed-by: Yu Zhang <[email protected]>
> Signed-off-by: Yu Zhang <[email protected]>
> Signed-off-by: Chao Peng <[email protected]>
> ---
> arch/x86/kvm/mmu/mmu.c | 56 +++++++++++++++++++++++++++++++--
> arch/x86/kvm/mmu/mmu_internal.h | 14 ++++++++-
> arch/x86/kvm/mmu/mmutrace.h | 1 +
> arch/x86/kvm/mmu/spte.h | 6 ++++
> arch/x86/kvm/mmu/tdp_mmu.c | 3 +-
> include/linux/kvm_host.h | 28 +++++++++++++++++
> 6 files changed, 103 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 67a9823a8c35..10017a9f26ee 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -3030,7 +3030,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
>
> int kvm_mmu_max_mapping_level(struct kvm *kvm,
> const struct kvm_memory_slot *slot, gfn_t gfn,
> - int max_level)
> + int max_level, bool is_private)
> {
> struct kvm_lpage_info *linfo;
> int host_level;
> @@ -3042,6 +3042,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
> break;
> }
>
> + if (is_private)
> + return max_level;
> +
> if (max_level == PG_LEVEL_4K)
> return PG_LEVEL_4K;
>
> @@ -3070,7 +3073,8 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
> * level, which will be used to do precise, accurate accounting.
> */
> fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
> - fault->gfn, fault->max_level);
> + fault->gfn, fault->max_level,
> + fault->is_private);
> if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
> return;
>
> @@ -4141,6 +4145,32 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
> kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
> }
>
> +static inline u8 order_to_level(int order)
> +{
> + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
> +
> + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
> + return PG_LEVEL_1G;
> +
> + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
> + return PG_LEVEL_2M;
> +
> + return PG_LEVEL_4K;
> +}
> +
> +static int kvm_faultin_pfn_private(struct kvm_page_fault *fault)
> +{
> + int order;
> + struct kvm_memory_slot *slot = fault->slot;
> +
> + if (kvm_restricted_mem_get_pfn(slot, fault->gfn, &fault->pfn, &order))
>+ return RET_PF_RETRY;
>+
>+ fault->max_level = min(order_to_level(order), fault->max_level);
>+ fault->map_writable = !(slot->flags & KVM_MEM_READONLY);
>+ return RET_PF_CONTINUE;
>+}
>+
> static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> {
> struct kvm_memory_slot *slot = fault->slot;
>@@ -4173,6 +4203,22 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> return RET_PF_EMULATE;
> }
>
>+ if (kvm_slot_can_be_private(slot) &&
>+ fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
>+ vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
>+ if (fault->is_private)
>+ vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
>+ else
>+ vcpu->run->memory.flags = 0;
>+ vcpu->run->memory.padding = 0;
>+ vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
>+ vcpu->run->memory.size = PAGE_SIZE;
>+ return RET_PF_USER;
>+ }
>+
>+ if (fault->is_private)
>+ return kvm_faultin_pfn_private(fault);
>+

Since each memslot may also not be backed by restricted memory, we
should also check if the memslot has been set up for private memory
with

if (fault->is_private && kvm_slot_can_be_private(slot))
return kvm_faultin_pfn_private(fault);

Without this check, restrictedmem_get_page will get called with NULL
in slot->restricted_file, which causes a NULL pointer dereference.

> async = false;
> fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
> fault->write, &fault->map_writable,
>@@ -5557,6 +5603,9 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
> return -EIO;
> }
>
>+ if (r == RET_PF_USER)
>+ return 0;
>+
> if (r < 0)
> return r;
> if (r != RET_PF_EMULATE)
>@@ -6408,7 +6457,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
> */
> if (sp->role.direct &&
> sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
>- PG_LEVEL_NUM)) {
>+ PG_LEVEL_NUM,
>+ false)) {
> kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
>
> if (kvm_available_flush_tlb_with_range())

2022-11-16 22:39:48

by Sean Christopherson

[permalink] [raw]
Subject: Re: [PATCH v9 7/8] KVM: Handle page fault for private memory

On Wed, Nov 16, 2022, Ackerley Tng wrote:
> >@@ -4173,6 +4203,22 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> > return RET_PF_EMULATE;
> > }
> >
> >+ if (kvm_slot_can_be_private(slot) &&
> >+ fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
> >+ vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
> >+ if (fault->is_private)
> >+ vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
> >+ else
> >+ vcpu->run->memory.flags = 0;
> >+ vcpu->run->memory.padding = 0;
> >+ vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
> >+ vcpu->run->memory.size = PAGE_SIZE;
> >+ return RET_PF_USER;
> >+ }
> >+
> >+ if (fault->is_private)
> >+ return kvm_faultin_pfn_private(fault);
> >+
>
> Since each memslot may also not be backed by restricted memory, we
> should also check if the memslot has been set up for private memory
> with
>
> if (fault->is_private && kvm_slot_can_be_private(slot))
> return kvm_faultin_pfn_private(fault);
>
> Without this check, restrictedmem_get_page will get called with NULL
> in slot->restricted_file, which causes a NULL pointer dereference.

Hmm, silently skipping the faultin would result in KVM faulting in the shared
portion of the memslot, and I believe would end up mapping that pfn as private,
i.e. would map a non-UPM PFN as a private mapping. For TDX and SNP, that would
be double ungood as it would let the host access memory that is mapped private,
i.e. lead to #MC or #PF(RMP) in the host.

I believe the correct solution is to drop the "can be private" check from the
above check, and instead handle that in kvm_faultin_pfn_private(). That would fix
another bug, e.g. if the fault is shared, the slot can't be private, but for
whatever reason userspace marked the gfn as private. Even though KVM might be
able service the fault, the correct thing to do in that case is to exit to userspace.

E.g.

---
arch/x86/kvm/mmu/mmu.c | 36 ++++++++++++++++++++++--------------
1 file changed, 22 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 10017a9f26ee..e2ac8873938e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4158,11 +4158,29 @@ static inline u8 order_to_level(int order)
return PG_LEVEL_4K;
}

-static int kvm_faultin_pfn_private(struct kvm_page_fault *fault)
+static int kvm_do_memory_fault_exit(struct kvm_vcpu *vcpu,
+ struct kvm_page_fault *fault)
+{
+ vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
+ if (fault->is_private)
+ vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
+ else
+ vcpu->run->memory.flags = 0;
+ vcpu->run->memory.padding = 0;
+ vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
+ vcpu->run->memory.size = PAGE_SIZE;
+ return RET_PF_USER;
+}
+
+static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
+ struct kvm_page_fault *fault)
{
int order;
struct kvm_memory_slot *slot = fault->slot;

+ if (kvm_slot_can_be_private(slot))
+ return kvm_do_memory_fault_exit(vcpu, fault);
+
if (kvm_restricted_mem_get_pfn(slot, fault->gfn, &fault->pfn, &order))
return RET_PF_RETRY;

@@ -4203,21 +4221,11 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
return RET_PF_EMULATE;
}

- if (kvm_slot_can_be_private(slot) &&
- fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
- vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
- if (fault->is_private)
- vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
- else
- vcpu->run->memory.flags = 0;
- vcpu->run->memory.padding = 0;
- vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
- vcpu->run->memory.size = PAGE_SIZE;
- return RET_PF_USER;
- }
+ if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn))
+ return kvm_do_memory_fault_exit(vcpu, fault);

if (fault->is_private)
- return kvm_faultin_pfn_private(fault);
+ return kvm_faultin_pfn_private(vcpu, fault);

async = false;
fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,

base-commit: 969d761bb7b8654605937f31ae76123dcb7f15a3
--


2022-11-17 14:04:04

by Chao Peng

[permalink] [raw]
Subject: Re: [PATCH v9 7/8] KVM: Handle page fault for private memory

On Wed, Nov 16, 2022 at 10:13:07PM +0000, Sean Christopherson wrote:
> On Wed, Nov 16, 2022, Ackerley Tng wrote:
> > >@@ -4173,6 +4203,22 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> > > return RET_PF_EMULATE;
> > > }
> > >
> > >+ if (kvm_slot_can_be_private(slot) &&
> > >+ fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
> > >+ vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
> > >+ if (fault->is_private)
> > >+ vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
> > >+ else
> > >+ vcpu->run->memory.flags = 0;
> > >+ vcpu->run->memory.padding = 0;
> > >+ vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
> > >+ vcpu->run->memory.size = PAGE_SIZE;
> > >+ return RET_PF_USER;
> > >+ }
> > >+
> > >+ if (fault->is_private)
> > >+ return kvm_faultin_pfn_private(fault);
> > >+
> >
> > Since each memslot may also not be backed by restricted memory, we
> > should also check if the memslot has been set up for private memory
> > with
> >
> > if (fault->is_private && kvm_slot_can_be_private(slot))
> > return kvm_faultin_pfn_private(fault);
> >
> > Without this check, restrictedmem_get_page will get called with NULL
> > in slot->restricted_file, which causes a NULL pointer dereference.
>
> Hmm, silently skipping the faultin would result in KVM faulting in the shared
> portion of the memslot, and I believe would end up mapping that pfn as private,
> i.e. would map a non-UPM PFN as a private mapping. For TDX and SNP, that would
> be double ungood as it would let the host access memory that is mapped private,
> i.e. lead to #MC or #PF(RMP) in the host.

That's correct.

>
> I believe the correct solution is to drop the "can be private" check from the
> above check, and instead handle that in kvm_faultin_pfn_private(). That would fix
> another bug, e.g. if the fault is shared, the slot can't be private, but for
> whatever reason userspace marked the gfn as private. Even though KVM might be
> able service the fault, the correct thing to do in that case is to exit to userspace.

It makes sense to me.

Chao
>
> E.g.
>
> ---
> arch/x86/kvm/mmu/mmu.c | 36 ++++++++++++++++++++++--------------
> 1 file changed, 22 insertions(+), 14 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 10017a9f26ee..e2ac8873938e 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -4158,11 +4158,29 @@ static inline u8 order_to_level(int order)
> return PG_LEVEL_4K;
> }
>
> -static int kvm_faultin_pfn_private(struct kvm_page_fault *fault)
> +static int kvm_do_memory_fault_exit(struct kvm_vcpu *vcpu,
> + struct kvm_page_fault *fault)
> +{
> + vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
> + if (fault->is_private)
> + vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
> + else
> + vcpu->run->memory.flags = 0;
> + vcpu->run->memory.padding = 0;
> + vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
> + vcpu->run->memory.size = PAGE_SIZE;
> + return RET_PF_USER;
> +}
> +
> +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
> + struct kvm_page_fault *fault)
> {
> int order;
> struct kvm_memory_slot *slot = fault->slot;
>
> + if (kvm_slot_can_be_private(slot))
> + return kvm_do_memory_fault_exit(vcpu, fault);
> +
> if (kvm_restricted_mem_get_pfn(slot, fault->gfn, &fault->pfn, &order))
> return RET_PF_RETRY;
>
> @@ -4203,21 +4221,11 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> return RET_PF_EMULATE;
> }
>
> - if (kvm_slot_can_be_private(slot) &&
> - fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
> - vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
> - if (fault->is_private)
> - vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
> - else
> - vcpu->run->memory.flags = 0;
> - vcpu->run->memory.padding = 0;
> - vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
> - vcpu->run->memory.size = PAGE_SIZE;
> - return RET_PF_USER;
> - }
> + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn))
> + return kvm_do_memory_fault_exit(vcpu, fault);
>
> if (fault->is_private)
> - return kvm_faultin_pfn_private(fault);
> + return kvm_faultin_pfn_private(vcpu, fault);
>
> async = false;
> fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
>
> base-commit: 969d761bb7b8654605937f31ae76123dcb7f15a3
> --