Re: [PATCH RFC v8 01/56] KVM: x86: Add 'fault_is_private' x86 op

[Isaku Yamahata <isaku.yamahata@gmail.com>]

On Mon, Feb 20, 2023 at 12:37:52PM -0600,
Michael Roth <michael.roth@amd.com> wrote:

> This callback is used by the KVM MMU to check whether a #NPF was for a
> private GPA or not.
> 
> In some cases the full 64-bit error code for the #NPF will be needed to
> make this determination, so also update kvm_mmu_do_page_fault() to
> accept the full 64-bit value so it can be plumbed through to the
> callback.

Here is a patch to change error code 64-bit.

From 428a676face7a06a90e59dca1c32941c9b6ee001 Mon Sep 17 00:00:00 2001
Message-Id: <428a676face7a06a90e59dca1c32941c9b6ee001.1679114841.git.isaku.yamahata@intel.com>
From: Isaku Yamahata <isaku.yamahata@intel.com>
Date: Fri, 17 Mar 2023 12:58:42 -0700
Subject: [PATCH 1/4] KVM: x86/mmu: Pass round full 64-bit error code for the
 KVM page fault

In some cases the full 64-bit error code for the KVM page fault will be
needed to make this determination, so also update kvm_mmu_do_page_fault()
to accept the full 64-bit value so it can be plumbed through to the
callback.

The upper 32 bits of error code is discarded at kvm_mmu_page_fault()
by lower_32_bits().  Now it's passed down as full 64 bits. It turns out
that only FNAME(page_fault) depends on it.  Move lower_32_bits() into
FNAME(page_fault).

The accesses of fault->error_code are as follows
- FNAME(page_fault): change to explicitly use lower_32_bits()
- kvm_tdp_page_fault(): explicit mask with PFERR_LEVEL_MASK
- kvm_mmu_page_fault(): explicit mask with PFERR_RSVD_MASK,
                        PFERR_NESTED_GUEST_PAGE
- mmutrace: changed u32 -> u64
- pgprintk(): change %x -> %llx

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
 arch/x86/kvm/mmu.h              | 2 +-
 arch/x86/kvm/mmu/mmu.c          | 7 +++----
 arch/x86/kvm/mmu/mmu_internal.h | 4 ++--
 arch/x86/kvm/mmu/mmutrace.h     | 2 +-
 arch/x86/kvm/mmu/paging_tmpl.h  | 4 ++--
 5 files changed, 9 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index de9c6b98c41b..4aaef2132b97 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -156,7 +156,7 @@ static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu)
 }
 
 kvm_pfn_t kvm_mmu_map_tdp_page(struct kvm_vcpu *vcpu, gpa_t gpa,
-			       u32 error_code, int max_level);
+			       u64 error_code, int max_level);
 
 /*
  * Check if a given access (described through the I/D, W/R and U/S bits of a
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 960609d72dd6..0ec94c72895c 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4860,7 +4860,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 static int nonpaging_page_fault(struct kvm_vcpu *vcpu,
 				struct kvm_page_fault *fault)
 {
-	pgprintk("%s: gva %llx error %x\n", __func__, fault->addr, fault->error_code);
+	pgprintk("%s: gva %llx error %llx\n", __func__, fault->addr, fault->error_code);
 
 	/* This path builds a PAE pagetable, we can map 2mb pages at maximum. */
 	fault->max_level = PG_LEVEL_2M;
@@ -4986,7 +4986,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 }
 
 kvm_pfn_t kvm_mmu_map_tdp_page(struct kvm_vcpu *vcpu, gpa_t gpa,
-			       u32 error_code, int max_level)
+			       u64 error_code, int max_level)
 {
 	int r;
 	struct kvm_page_fault fault = (struct kvm_page_fault) {
@@ -6238,8 +6238,7 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
 	}
 
 	if (r == RET_PF_INVALID) {
-		r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa,
-					  lower_32_bits(error_code), false);
+		r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, error_code, false);
 		if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm))
 			return -EIO;
 	}
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index aa0836191b5a..bb5709f1cb57 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -341,7 +341,7 @@ static inline bool is_nx_huge_page_enabled(struct kvm *kvm)
 struct kvm_page_fault {
 	/* arguments to kvm_mmu_do_page_fault.  */
 	const gpa_t addr;
-	const u32 error_code;
+	const u64 error_code;
 	const bool prefetch;
 
 	/* Derived from error_code.  */
@@ -427,7 +427,7 @@ enum {
 };
 
 static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
-					u32 err, bool prefetch)
+					u64 err, bool prefetch)
 {
 	struct kvm_page_fault fault = {
 		.addr = cr2_or_gpa,
diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
index 2d7555381955..2e77883c92f6 100644
--- a/arch/x86/kvm/mmu/mmutrace.h
+++ b/arch/x86/kvm/mmu/mmutrace.h
@@ -261,7 +261,7 @@ TRACE_EVENT(
 	TP_STRUCT__entry(
 		__field(int, vcpu_id)
 		__field(gpa_t, cr2_or_gpa)
-		__field(u32, error_code)
+		__field(u64, error_code)
 		__field(u64 *, sptep)
 		__field(u64, old_spte)
 		__field(u64, new_spte)
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 594af2e1fd2f..cab6822709e2 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -791,7 +791,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	int r;
 	bool is_self_change_mapping;
 
-	pgprintk("%s: addr %llx err %x\n", __func__, fault->addr, fault->error_code);
+	pgprintk("%s: addr %llx err %llx\n", __func__, fault->addr, fault->error_code);
 	WARN_ON_ONCE(fault->is_tdp);
 
 	/*
@@ -800,7 +800,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	 * The bit needs to be cleared before walking guest page tables.
 	 */
 	r = FNAME(walk_addr)(&walker, vcpu, fault->addr,
-			     fault->error_code & ~PFERR_RSVD_MASK);
+			     lower_32_bits(fault->error_code) & ~PFERR_RSVD_MASK);
 
 	/*
 	 * The page is not mapped by the guest.  Let the guest handle it.
-- 
2.25.1


-- 
Isaku Yamahata <isaku.yamahata@gmail.com>