From c72ceafbd12cf95e088681ae5e535ef1a78bf0ed Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Fri, 29 Mar 2024 16:24:42 -0500
Subject: mm: Introduce AS_INACCESSIBLE for encrypted/confidential memory

filemap users like guest_memfd may use page cache pages to
allocate/manage memory that is only intended to be accessed by guests
via hardware protections like encryption. Writes to memory of this sort
in common paths like truncation may cause unexpected behavior such as
writing garbage instead of zeros when attempting to zero pages, or
worse, triggering hardware protections that are considered fatal as far
as the kernel is concerned.

Introduce a new address_space flag, AS_INACCESSIBLE, and use this
initially to prevent zero'ing of pages during truncation, with the
understanding that it is up to the owner of the mapping to handle this
specially if needed.

This is admittedly a rather blunt solution, but it seems like
there are no other places that should take into account the
flag to keep its promise.

Link: https://lore.kernel.org/lkml/ZR9LYhpxTaTk6PJX@google.com/
Cc: Matthew Wilcox <willy@infradead.org>
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-ID: <20240329212444.395559-5-michael.roth@amd.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/pagemap.h | 1 +
 mm/truncate.c           | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 2df35e65557d..f879c1d54da7 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -207,6 +207,7 @@ enum mapping_flags {
 	AS_STABLE_WRITES,	/* must wait for writeback before modifying
 				   folio contents */
 	AS_UNMOVABLE,		/* The mapping cannot be moved, ever */
+	AS_INACCESSIBLE,	/* Do not attempt direct R/W access to the mapping */
 };
 
 /**
diff --git a/mm/truncate.c b/mm/truncate.c
index 725b150e47ac..c501338c7ebd 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -233,7 +233,8 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 	 * doing a complex calculation here, and then doing the zeroing
 	 * anyway if the page split fails.
 	 */
-	folio_zero_range(folio, offset, length);
+	if (!(folio->mapping->flags & AS_INACCESSIBLE))
+		folio_zero_range(folio, offset, length);
 
 	if (folio_has_private(folio))
 		folio_invalidate(folio, offset, length);
-- 
cgit v1.2.3-58-ga151


From 1d23040caa8bef867572ae814b5f8b5fa44eccd3 Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Fri, 29 Mar 2024 16:24:43 -0500
Subject: KVM: guest_memfd: Use AS_INACCESSIBLE when creating guest_memfd inode

truncate_inode_pages_range() may attempt to zero pages before truncating
them, and this will occur before arch-specific invalidations can be
triggered via .invalidate_folio/.free_folio hooks via kvm_gmem_aops. For
AMD SEV-SNP this would result in an RMP #PF being generated by the
hardware, which is currently treated as fatal (and even if specifically
allowed for, would not result in anything other than garbage being
written to guest pages due to encryption). On Intel TDX this would also
result in undesirable behavior.

Set the AS_INACCESSIBLE flag to prevent the MM from attempting
unexpected accesses of this sort during operations like truncation.

This may also in some cases yield a decent performance improvement for
guest_memfd userspace implementations that hole-punch ranges immediately
after private->shared conversions via KVM_SET_MEMORY_ATTRIBUTES, since
the current implementation of truncate_inode_pages_range() always ends
up zero'ing an entire 4K range if it is backing by a 2M folio.

Link: https://lore.kernel.org/lkml/ZR9LYhpxTaTk6PJX@google.com/
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-ID: <20240329212444.395559-6-michael.roth@amd.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/guest_memfd.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 0f4e0cf4f158..5a929536ecf2 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -357,6 +357,7 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 	inode->i_private = (void *)(unsigned long)flags;
 	inode->i_op = &kvm_gmem_iops;
 	inode->i_mapping->a_ops = &kvm_gmem_aops;
+	inode->i_mapping->flags |= AS_INACCESSIBLE;
 	inode->i_mode |= S_IFREG;
 	inode->i_size = size;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
-- 
cgit v1.2.3-58-ga151


From 70623723778a5156a03bc6e601be5df8c1fddb75 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 14 Feb 2024 11:31:43 -0500
Subject: KVM: guest_memfd: pass error up from filemap_grab_folio

Some SNP ioctls will require the page not to be in the pagecache, and as such they
will want to return EEXIST to userspace.  Start by passing the error up from
filemap_grab_folio.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/guest_memfd.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 5a929536ecf2..c27828b0d42d 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -19,8 +19,8 @@ static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
 
 	/* TODO: Support huge pages. */
 	folio = filemap_grab_folio(inode->i_mapping, index);
-	if (IS_ERR_OR_NULL(folio))
-		return NULL;
+	if (IS_ERR(folio))
+		return folio;
 
 	/*
 	 * Use the up-to-date flag to track whether or not the memory has been
@@ -146,8 +146,8 @@ static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
 		}
 
 		folio = kvm_gmem_get_folio(inode, index);
-		if (!folio) {
-			r = -ENOMEM;
+		if (IS_ERR(folio)) {
+			r = PTR_ERR(folio);
 			break;
 		}
 
@@ -505,8 +505,8 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 	}
 
 	folio = kvm_gmem_get_folio(file_inode(file), index);
-	if (!folio) {
-		r = -ENOMEM;
+	if (IS_ERR(folio)) {
+		r = PTR_ERR(folio);
 		goto out_fput;
 	}
 
-- 
cgit v1.2.3-58-ga151


From fa30b0dc91c815b9579d6f758437c35db059f5ae Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 4 Apr 2024 13:25:19 -0400
Subject: KVM: guest_memfd: limit overzealous WARN

Because kvm_gmem_get_pfn() is called from the page fault path without
any of the slots_lock, filemap lock or mmu_lock taken, it is
possible for it to race with kvm_gmem_unbind().  This is not a
problem, as any PTE that is installed temporarily will be zapped
before the guest has the occasion to run.

However, it is not possible to have a complete unbind+bind
racing with the page fault, because deleting the memslot
will call synchronize_srcu_expedited() and wait for the
page fault to be resolved.  Thus, we can still warn if
the file is there and is not the one we expect.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/guest_memfd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index c27828b0d42d..fd32288d0fbc 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -499,7 +499,8 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 
 	gmem = file->private_data;
 
-	if (WARN_ON_ONCE(xa_load(&gmem->bindings, index) != slot)) {
+	if (xa_load(&gmem->bindings, index) != slot) {
+		WARN_ON_ONCE(xa_load(&gmem->bindings, index));
 		r = -EIO;
 		goto out_fput;
 	}
-- 
cgit v1.2.3-58-ga151


From 3bb2531e20bff99f9cd8719ee7aea8bd82687173 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Tue, 7 May 2024 12:54:03 -0400
Subject: KVM: guest_memfd: Add hook for initializing memory

guest_memfd pages are generally expected to be in some arch-defined
initial state prior to using them for guest memory. For SEV-SNP this
initial state is 'private', or 'guest-owned', and requires additional
operations to move these pages into a 'private' state by updating the
corresponding entries the RMP table.

Allow for an arch-defined hook to handle updates of this sort, and go
ahead and implement one for x86 so KVM implementations like AMD SVM can
register a kvm_x86_ops callback to handle these updates for SEV-SNP
guests.

The preparation callback is always called when allocating/grabbing
folios via gmem, and it is up to the architecture to keep track of
whether or not the pages are already in the expected state (e.g. the RMP
table in the case of SEV-SNP).

In some cases, it is necessary to defer the preparation of the pages to
handle things like in-place encryption of initial guest memory payloads
before marking these pages as 'private'/'guest-owned'.  Add an argument
(always true for now) to kvm_gmem_get_folio() that allows for the
preparation callback to be bypassed.  To detect possible issues in
the way userspace initializes memory, it is only possible to add an
unprepared page if it is not already included in the filemap.

Link: https://lore.kernel.org/lkml/ZLqVdvsF11Ddo7Dq@google.com/
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-Id: <20231230172351.574091-5-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  1 +
 arch/x86/kvm/x86.c                 |  6 +++++
 include/linux/kvm_host.h           |  5 ++++
 virt/kvm/Kconfig                   |  4 +++
 virt/kvm/guest_memfd.c             | 51 +++++++++++++++++++++++++++++++++++---
 6 files changed, 65 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 5187fcf4b610..d26fcad13e36 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -139,6 +139,7 @@ KVM_X86_OP(vcpu_deliver_sipi_vector)
 KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
 KVM_X86_OP_OPTIONAL(get_untagged_addr)
 KVM_X86_OP_OPTIONAL(alloc_apic_backing_page)
+KVM_X86_OP_OPTIONAL_RET0(gmem_prepare)
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_OPTIONAL
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0369e9efe429..738ad82a3e67 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1812,6 +1812,7 @@ struct kvm_x86_ops {
 
 	gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
 	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
+	int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2d2619d3eee4..972524ddcfdb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13598,6 +13598,12 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
 
+#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order)
+{
+	return static_call(kvm_x86_gmem_prepare)(kvm, pfn, gfn, max_order);
+}
+#endif
 
 int kvm_spec_ctrl_test_value(u64 value)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index afbc99264ffa..1af069ab657c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2443,4 +2443,9 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 }
 #endif /* CONFIG_KVM_PRIVATE_MEM */
 
+#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order);
+bool kvm_arch_gmem_prepare_needed(struct kvm *kvm);
+#endif
+
 #endif
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 29b73eedfe74..ca870157b2ed 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -109,3 +109,7 @@ config KVM_GENERIC_PRIVATE_MEM
        select KVM_GENERIC_MEMORY_ATTRIBUTES
        select KVM_PRIVATE_MEM
        bool
+
+config HAVE_KVM_GMEM_PREPARE
+       bool
+       depends on KVM_PRIVATE_MEM
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index fd32288d0fbc..0176089be731 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -13,7 +13,43 @@ struct kvm_gmem {
 	struct list_head entry;
 };
 
-static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
+static int kvm_gmem_prepare_folio(struct inode *inode, pgoff_t index, struct folio *folio)
+{
+#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+	struct list_head *gmem_list = &inode->i_mapping->i_private_list;
+	struct kvm_gmem *gmem;
+
+	list_for_each_entry(gmem, gmem_list, entry) {
+		struct kvm_memory_slot *slot;
+		struct kvm *kvm = gmem->kvm;
+		struct page *page;
+		kvm_pfn_t pfn;
+		gfn_t gfn;
+		int rc;
+
+		if (!kvm_arch_gmem_prepare_needed(kvm))
+			continue;
+
+		slot = xa_load(&gmem->bindings, index);
+		if (!slot)
+			continue;
+
+		page = folio_file_page(folio, index);
+		pfn = page_to_pfn(page);
+		gfn = slot->base_gfn + index - slot->gmem.pgoff;
+		rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, compound_order(compound_head(page)));
+		if (rc) {
+			pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx, error %d.\n",
+					    index, rc);
+			return rc;
+		}
+	}
+
+#endif
+	return 0;
+}
+
+static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index, bool prepare)
 {
 	struct folio *folio;
 
@@ -41,6 +77,15 @@ static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
 		folio_mark_uptodate(folio);
 	}
 
+	if (prepare) {
+		int r =	kvm_gmem_prepare_folio(inode, index, folio);
+		if (r < 0) {
+			folio_unlock(folio);
+			folio_put(folio);
+			return ERR_PTR(r);
+		}
+	}
+
 	/*
 	 * Ignore accessed, referenced, and dirty flags.  The memory is
 	 * unevictable and there is no storage to write back to.
@@ -145,7 +190,7 @@ static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
 			break;
 		}
 
-		folio = kvm_gmem_get_folio(inode, index);
+		folio = kvm_gmem_get_folio(inode, index, true);
 		if (IS_ERR(folio)) {
 			r = PTR_ERR(folio);
 			break;
@@ -505,7 +550,7 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 		goto out_fput;
 	}
 
-	folio = kvm_gmem_get_folio(file_inode(file), index);
+	folio = kvm_gmem_get_folio(file_inode(file), index, true);
 	if (IS_ERR(folio)) {
 		r = PTR_ERR(folio);
 		goto out_fput;
-- 
cgit v1.2.3-58-ga151


From 17573fd971f9e31ddee420eca8359ceff87e9e51 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 4 Apr 2024 13:27:46 -0400
Subject: KVM: guest_memfd: extract __kvm_gmem_get_pfn()

In preparation for adding a function that walks a set of pages
provided by userspace and populates them in a guest_memfd,
add a version of kvm_gmem_get_pfn() that has a "bool prepare"
argument and passes it down to kvm_gmem_get_folio().

Populating guest memory has to call repeatedly __kvm_gmem_get_pfn()
on the same file, so make the new function take struct file*.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/guest_memfd.c | 40 ++++++++++++++++++++++++----------------
 1 file changed, 24 insertions(+), 16 deletions(-)

diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 0176089be731..bfe437098b79 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -528,33 +528,29 @@ void kvm_gmem_unbind(struct kvm_memory_slot *slot)
 	fput(file);
 }
 
-int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
-		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
+static int __kvm_gmem_get_pfn(struct file *file, struct kvm_memory_slot *slot,
+		       gfn_t gfn, kvm_pfn_t *pfn, int *max_order, bool prepare)
 {
 	pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff;
-	struct kvm_gmem *gmem;
+	struct kvm_gmem *gmem = file->private_data;
 	struct folio *folio;
 	struct page *page;
-	struct file *file;
 	int r;
 
-	file = kvm_gmem_get_file(slot);
-	if (!file)
+	if (file != slot->gmem.file) {
+		WARN_ON_ONCE(slot->gmem.file);
 		return -EFAULT;
+	}
 
 	gmem = file->private_data;
-
 	if (xa_load(&gmem->bindings, index) != slot) {
 		WARN_ON_ONCE(xa_load(&gmem->bindings, index));
-		r = -EIO;
-		goto out_fput;
+		return -EIO;
 	}
 
-	folio = kvm_gmem_get_folio(file_inode(file), index, true);
-	if (IS_ERR(folio)) {
-		r = PTR_ERR(folio);
-		goto out_fput;
-	}
+	folio = kvm_gmem_get_folio(file_inode(file), index, prepare);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
 
 	if (folio_test_hwpoison(folio)) {
 		r = -EHWPOISON;
@@ -571,9 +567,21 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 
 out_unlock:
 	folio_unlock(folio);
-out_fput:
-	fput(file);
 
 	return r;
 }
+
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
+{
+	struct file *file = kvm_gmem_get_file(slot);
+	int r;
+
+	if (!file)
+		return -EFAULT;
+
+	r = __kvm_gmem_get_pfn(file, slot, gfn, pfn, max_order, true);
+	fput(file);
+	return r;
+}
 EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);
-- 
cgit v1.2.3-58-ga151


From 1f6c06b177513e8a47c43e95d1985dbd9cff3ddd Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 14 Feb 2024 12:09:06 -0500
Subject: KVM: guest_memfd: Add interface for populating gmem pages with user
 data

During guest run-time, kvm_arch_gmem_prepare() is issued as needed to
prepare newly-allocated gmem pages prior to mapping them into the guest.
In the case of SEV-SNP, this mainly involves setting the pages to
private in the RMP table.

However, for the GPA ranges comprising the initial guest payload, which
are encrypted/measured prior to starting the guest, the gmem pages need
to be accessed prior to setting them to private in the RMP table so they
can be initialized with the userspace-provided data. Additionally, an
SNP firmware call is needed afterward to encrypt them in-place and
measure the contents into the guest's launch digest.

While it is possible to bypass the kvm_arch_gmem_prepare() hooks so that
this handling can be done in an open-coded/vendor-specific manner, this
may expose more gmem-internal state/dependencies to external callers
than necessary. Try to avoid this by implementing an interface that
tries to handle as much of the common functionality inside gmem as
possible, while also making it generic enough to potentially be
usable/extensible for TDX as well.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 27 +++++++++++++++++++++++++
 virt/kvm/guest_memfd.c   | 52 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 79 insertions(+)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1af069ab657c..1ae65774d9fa 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2448,4 +2448,31 @@ int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_ord
 bool kvm_arch_gmem_prepare_needed(struct kvm *kvm);
 #endif
 
+/**
+ * kvm_gmem_populate() - Populate/prepare a GPA range with guest data
+ *
+ * @kvm: KVM instance
+ * @gfn: starting GFN to be populated
+ * @src: userspace-provided buffer containing data to copy into GFN range
+ *       (passed to @post_populate, and incremented on each iteration
+ *       if not NULL)
+ * @npages: number of pages to copy from userspace-buffer
+ * @post_populate: callback to issue for each gmem page that backs the GPA
+ *                 range
+ * @opaque: opaque data to pass to @post_populate callback
+ *
+ * This is primarily intended for cases where a gmem-backed GPA range needs
+ * to be initialized with userspace-provided data prior to being mapped into
+ * the guest as a private page. This should be called with the slots->lock
+ * held so that caller-enforced invariants regarding the expected memory
+ * attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES.
+ *
+ * Returns the number of pages that were populated.
+ */
+typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
+				    void __user *src, int order, void *opaque);
+
+long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages,
+		       kvm_gmem_populate_cb post_populate, void *opaque);
+
 #endif
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index bfe437098b79..5d6c87bb13f6 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -585,3 +585,55 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);
+
+long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages,
+		       kvm_gmem_populate_cb post_populate, void *opaque)
+{
+	struct file *file;
+	struct kvm_memory_slot *slot;
+	void __user *p;
+
+	int ret = 0, max_order;
+	long i;
+
+	lockdep_assert_held(&kvm->slots_lock);
+	if (npages < 0)
+		return -EINVAL;
+
+	slot = gfn_to_memslot(kvm, start_gfn);
+	if (!kvm_slot_can_be_private(slot))
+		return -EINVAL;
+
+	file = kvm_gmem_get_file(slot);
+	if (!file)
+		return -EFAULT;
+
+	filemap_invalidate_lock(file->f_mapping);
+
+	npages = min_t(ulong, slot->npages - (start_gfn - slot->base_gfn), npages);
+	for (i = 0; i < npages; i += (1 << max_order)) {
+		gfn_t gfn = start_gfn + i;
+		kvm_pfn_t pfn;
+
+		ret = __kvm_gmem_get_pfn(file, slot, gfn, &pfn, &max_order, false);
+		if (ret)
+			break;
+
+		if (!IS_ALIGNED(gfn, (1 << max_order)) ||
+		    (npages - i) < (1 << max_order))
+			max_order = 0;
+
+		p = src ? src + i * PAGE_SIZE : NULL;
+		ret = post_populate(kvm, gfn, pfn, p, max_order, opaque);
+
+		put_page(pfn_to_page(pfn));
+		if (ret)
+			break;
+	}
+
+	filemap_invalidate_unlock(file->f_mapping);
+
+	fput(file);
+	return ret && !i ? ret : i;
+}
+EXPORT_SYMBOL_GPL(kvm_gmem_populate);
-- 
cgit v1.2.3-58-ga151


From a90764f0e4ed5350cc9caeb384e0fb356c032587 Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Sat, 30 Dec 2023 11:23:21 -0600
Subject: KVM: guest_memfd: Add hook for invalidating memory

In some cases, like with SEV-SNP, guest memory needs to be updated in a
platform-specific manner before it can be safely freed back to the host.
Wire up arch-defined hooks to the .free_folio kvm_gmem_aops callback to
allow for special handling of this sort when freeing memory in response
to FALLOC_FL_PUNCH_HOLE operations and when releasing the inode, and go
ahead and define an arch-specific hook for x86 since it will be needed
for handling memory used for SEV-SNP guests.

Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-Id: <20231230172351.574091-6-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  1 +
 arch/x86/kvm/x86.c                 |  7 +++++++
 include/linux/kvm_host.h           |  4 ++++
 virt/kvm/Kconfig                   |  4 ++++
 virt/kvm/guest_memfd.c             | 14 ++++++++++++++
 6 files changed, 31 insertions(+)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index d26fcad13e36..c81990937ab4 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -140,6 +140,7 @@ KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
 KVM_X86_OP_OPTIONAL(get_untagged_addr)
 KVM_X86_OP_OPTIONAL(alloc_apic_backing_page)
 KVM_X86_OP_OPTIONAL_RET0(gmem_prepare)
+KVM_X86_OP_OPTIONAL(gmem_invalidate)
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_OPTIONAL
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 738ad82a3e67..51bb4b785d6a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1813,6 +1813,7 @@ struct kvm_x86_ops {
 	gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
 	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
 	int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
+	void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 972524ddcfdb..83b8260443a3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13605,6 +13605,13 @@ int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_ord
 }
 #endif
 
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
+{
+	static_call_cond(kvm_x86_gmem_invalidate)(start, end);
+}
+#endif
+
 int kvm_spec_ctrl_test_value(u64 value)
 {
 	/*
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1ae65774d9fa..b43b96f876fe 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2475,4 +2475,8 @@ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
 long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages,
 		       kvm_gmem_populate_cb post_populate, void *opaque);
 
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
+#endif
+
 #endif
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index ca870157b2ed..754c6c923427 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -113,3 +113,7 @@ config KVM_GENERIC_PRIVATE_MEM
 config HAVE_KVM_GMEM_PREPARE
        bool
        depends on KVM_PRIVATE_MEM
+
+config HAVE_KVM_GMEM_INVALIDATE
+       bool
+       depends on KVM_PRIVATE_MEM
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 5d6c87bb13f6..dfe50c64a552 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -343,10 +343,24 @@ static int kvm_gmem_error_folio(struct address_space *mapping, struct folio *fol
 	return MF_DELAYED;
 }
 
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+static void kvm_gmem_free_folio(struct folio *folio)
+{
+	struct page *page = folio_page(folio, 0);
+	kvm_pfn_t pfn = page_to_pfn(page);
+	int order = folio_order(folio);
+
+	kvm_arch_gmem_invalidate(pfn, pfn + (1ul << order));
+}
+#endif
+
 static const struct address_space_operations kvm_gmem_aops = {
 	.dirty_folio = noop_dirty_folio,
 	.migrate_folio	= kvm_gmem_migrate_folio,
 	.error_remove_folio = kvm_gmem_error_folio,
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+	.free_folio = kvm_gmem_free_folio,
+#endif
 };
 
 static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path,
-- 
cgit v1.2.3-58-ga151


From f32fb32820b1139b29300733f339adbe0f10652d Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Wed, 1 May 2024 03:51:52 -0500
Subject: KVM: x86: Add hook for determining max NPT mapping level

In the case of SEV-SNP, whether or not a 2MB page can be mapped via a
2MB mapping in the guest's nested page table depends on whether or not
any subpages within the range have already been initialized as private
in the RMP table. The existing mixed-attribute tracking in KVM is
insufficient here, for instance:

- gmem allocates 2MB page
- guest issues PVALIDATE on 2MB page
- guest later converts a subpage to shared
- SNP host code issues PSMASH to split 2MB RMP mapping to 4K
- KVM MMU splits NPT mapping to 4K
- guest later converts that shared page back to private

At this point there are no mixed attributes, and KVM would normally
allow for 2MB NPT mappings again, but this is actually not allowed
because the RMP table mappings are 4K and cannot be promoted on the
hypervisor side, so the NPT mappings must still be limited to 4K to
match this.

Add a hook to determine the max NPT mapping size in situations like
this.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Message-ID: <20240501085210.2213060-3-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  1 +
 arch/x86/kvm/mmu/mmu.c             | 23 +++++++++++++++++++++--
 3 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index c81990937ab4..566d19b02483 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -140,6 +140,7 @@ KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
 KVM_X86_OP_OPTIONAL(get_untagged_addr)
 KVM_X86_OP_OPTIONAL(alloc_apic_backing_page)
 KVM_X86_OP_OPTIONAL_RET0(gmem_prepare)
+KVM_X86_OP_OPTIONAL_RET0(private_max_mapping_level)
 KVM_X86_OP_OPTIONAL(gmem_invalidate)
 
 #undef KVM_X86_OP
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 51bb4b785d6a..0804b6019673 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1814,6 +1814,7 @@ struct kvm_x86_ops {
 	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
 	int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
 	void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end);
+	int (*private_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 5ae0f2f503b4..bce8e18ba1df 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4270,6 +4270,25 @@ static inline u8 kvm_max_level_for_order(int order)
 	return PG_LEVEL_4K;
 }
 
+static u8 kvm_max_private_mapping_level(struct kvm *kvm, kvm_pfn_t pfn,
+					u8 max_level, int gmem_order)
+{
+	u8 req_max_level;
+
+	if (max_level == PG_LEVEL_4K)
+		return PG_LEVEL_4K;
+
+	max_level = min(kvm_max_level_for_order(gmem_order), max_level);
+	if (max_level == PG_LEVEL_4K)
+		return PG_LEVEL_4K;
+
+	req_max_level = static_call(kvm_x86_private_max_mapping_level)(kvm, pfn);
+	if (req_max_level)
+		max_level = min(max_level, req_max_level);
+
+	return req_max_level;
+}
+
 static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 				   struct kvm_page_fault *fault)
 {
@@ -4287,9 +4306,9 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 		return r;
 	}
 
-	fault->max_level = min(kvm_max_level_for_order(max_order),
-			       fault->max_level);
 	fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
+	fault->max_level = kvm_max_private_mapping_level(vcpu->kvm, fault->pfn,
+							 fault->max_level, max_order);
 
 	return RET_PF_CONTINUE;
 }
-- 
cgit v1.2.3-58-ga151


From b74d002d3d587c38d01853580fd257db30edd1d0 Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Thu, 9 May 2024 18:05:29 -0500
Subject: KVM: MMU: Disable fast path if KVM_EXIT_MEMORY_FAULT is needed

For hardware-protected VMs like SEV-SNP guests, certain conditions like
attempting to perform a write to a page which is not in the state that
the guest expects it to be in can result in a nested/extended #PF which
can only be satisfied by the host performing an implicit page state
change to transition the page into the expected shared/private state.
This is generally handled by generating a KVM_EXIT_MEMORY_FAULT event
that gets forwarded to userspace to handle via
KVM_SET_MEMORY_ATTRIBUTES.

However, the fast_page_fault() code might misconstrue this situation as
being the result of a write-protected access, and treat it as a spurious
case when it sees that writes are already allowed for the sPTE. This
results in the KVM MMU trying to resume the guest rather than taking any
action to satisfy the real source of the #PF such as generating a
KVM_EXIT_MEMORY_FAULT, resulting in the guest spinning on nested #PFs.

Check for this condition and bail out of the fast path if it is
detected.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Cc: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Isaku Yamahata <isaku.yamahata@intel.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 037b8fbf4e6c..b68151eec4b4 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3305,7 +3305,7 @@ static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu,
 	return RET_PF_CONTINUE;
 }
 
-static bool page_fault_can_be_fast(struct kvm_page_fault *fault)
+static bool page_fault_can_be_fast(struct kvm *kvm, struct kvm_page_fault *fault)
 {
 	/*
 	 * Page faults with reserved bits set, i.e. faults on MMIO SPTEs, only
@@ -3316,6 +3316,26 @@ static bool page_fault_can_be_fast(struct kvm_page_fault *fault)
 	if (fault->rsvd)
 		return false;
 
+	/*
+	 * For hardware-protected VMs, certain conditions like attempting to
+	 * perform a write to a page which is not in the state that the guest
+	 * expects it to be in can result in a nested/extended #PF. In this
+	 * case, the below code might misconstrue this situation as being the
+	 * result of a write-protected access, and treat it as a spurious case
+	 * rather than taking any action to satisfy the real source of the #PF
+	 * such as generating a KVM_EXIT_MEMORY_FAULT. This can lead to the
+	 * guest spinning on a #PF indefinitely, so don't attempt the fast path
+	 * in this case.
+	 *
+	 * Note that the kvm_mem_is_private() check might race with an
+	 * attribute update, but this will either result in the guest spinning
+	 * on RET_PF_SPURIOUS until the update completes, or an actual spurious
+	 * case might go down the slow path. Either case will resolve itself.
+	 */
+	if (kvm->arch.has_private_mem &&
+	    fault->is_private != kvm_mem_is_private(kvm, fault->gfn))
+		return false;
+
 	/*
 	 * #PF can be fast if:
 	 *
@@ -3416,7 +3436,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 	u64 *sptep;
 	uint retry_count = 0;
 
-	if (!page_fault_can_be_fast(fault))
+	if (!page_fault_can_be_fast(vcpu->kvm, fault))
 		return ret;
 
 	walk_shadow_page_lockless_begin(vcpu);
-- 
cgit v1.2.3-58-ga151


From a8e31983335554193c2cb373161d08880230abfd Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Wed, 1 May 2024 03:51:53 -0500
Subject: KVM: SEV: Select KVM_GENERIC_PRIVATE_MEM when CONFIG_KVM_AMD_SEV=y

SEV-SNP relies on private memory support to run guests, so make sure to
enable that support via the CONFIG_KVM_GENERIC_PRIVATE_MEM config
option.

Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-ID: <20240501085210.2213060-4-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index d64fb2b3eb69..5e72faca4e8f 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -136,6 +136,7 @@ config KVM_AMD_SEV
 	depends on KVM_AMD && X86_64
 	depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
 	select ARCH_HAS_CC_PLATFORM
+	select KVM_GENERIC_PRIVATE_MEM
 	help
 	  Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
 	  with Encrypted State (SEV-ES) on AMD processors.
-- 
cgit v1.2.3-58-ga151


From 1dfe571c12cf99244b933208fb77f29471ded677 Mon Sep 17 00:00:00 2001
From: Brijesh Singh <brijesh.singh@amd.com>
Date: Wed, 1 May 2024 03:51:54 -0500
Subject: KVM: SEV: Add initial SEV-SNP support

SEV-SNP builds upon existing SEV and SEV-ES functionality while adding
new hardware-based security protection. SEV-SNP adds strong memory
encryption and integrity protection to help prevent malicious
hypervisor-based attacks such as data replay, memory re-mapping, and
more, to create an isolated execution environment.

Define a new KVM_X86_SNP_VM type which makes use of these capabilities
and extend the KVM_SEV_INIT2 ioctl to support it. Also add a basic
helper to check whether SNP is enabled and set PFERR_PRIVATE_ACCESS for
private #NPFs so they are handled appropriately by KVM MMU.

Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20240501085210.2213060-5-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/svm.h      |  3 ++-
 arch/x86/include/uapi/asm/kvm.h |  1 +
 arch/x86/kvm/svm/sev.c          | 21 ++++++++++++++++++++-
 arch/x86/kvm/svm/svm.c          |  8 +++++++-
 arch/x86/kvm/svm/svm.h          | 12 ++++++++++++
 5 files changed, 42 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 728c98175b9c..544a43c1cf11 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -285,7 +285,8 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_
 
 #define AVIC_HPA_MASK	~((0xFFFULL << 52) | 0xFFF)
 
-#define SVM_SEV_FEAT_DEBUG_SWAP                        BIT(5)
+#define SVM_SEV_FEAT_SNP_ACTIVE				BIT(0)
+#define SVM_SEV_FEAT_DEBUG_SWAP				BIT(5)
 
 struct vmcb_seg {
 	u16 selector;
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 9fae1b73b529..d2ae5fcc0275 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -874,5 +874,6 @@ struct kvm_hyperv_eventfd {
 #define KVM_X86_SW_PROTECTED_VM	1
 #define KVM_X86_SEV_VM		2
 #define KVM_X86_SEV_ES_VM	3
+#define KVM_X86_SNP_VM		4
 
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0623cfaa7bb0..b3345d45b989 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -47,6 +47,9 @@ module_param_named(sev, sev_enabled, bool, 0444);
 static bool sev_es_enabled = true;
 module_param_named(sev_es, sev_es_enabled, bool, 0444);
 
+/* enable/disable SEV-SNP support */
+static bool sev_snp_enabled;
+
 /* enable/disable SEV-ES DebugSwap support */
 static bool sev_es_debug_swap_enabled = true;
 module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
@@ -288,6 +291,9 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
 	if (sev->es_active && !sev->ghcb_version)
 		sev->ghcb_version = GHCB_VERSION_DEFAULT;
 
+	if (vm_type == KVM_X86_SNP_VM)
+		sev->vmsa_features |= SVM_SEV_FEAT_SNP_ACTIVE;
+
 	ret = sev_asid_new(sev);
 	if (ret)
 		goto e_no_asid;
@@ -348,7 +354,8 @@ static int sev_guest_init2(struct kvm *kvm, struct kvm_sev_cmd *argp)
 		return -EINVAL;
 
 	if (kvm->arch.vm_type != KVM_X86_SEV_VM &&
-	    kvm->arch.vm_type != KVM_X86_SEV_ES_VM)
+	    kvm->arch.vm_type != KVM_X86_SEV_ES_VM &&
+	    kvm->arch.vm_type != KVM_X86_SNP_VM)
 		return -EINVAL;
 
 	if (copy_from_user(&data, u64_to_user_ptr(argp->data), sizeof(data)))
@@ -2328,11 +2335,16 @@ void __init sev_set_cpu_caps(void)
 		kvm_cpu_cap_set(X86_FEATURE_SEV_ES);
 		kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_ES_VM);
 	}
+	if (sev_snp_enabled) {
+		kvm_cpu_cap_set(X86_FEATURE_SEV_SNP);
+		kvm_caps.supported_vm_types |= BIT(KVM_X86_SNP_VM);
+	}
 }
 
 void __init sev_hardware_setup(void)
 {
 	unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
+	bool sev_snp_supported = false;
 	bool sev_es_supported = false;
 	bool sev_supported = false;
 
@@ -2413,6 +2425,7 @@ void __init sev_hardware_setup(void)
 	sev_es_asid_count = min_sev_asid - 1;
 	WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count));
 	sev_es_supported = true;
+	sev_snp_supported = sev_snp_enabled && cc_platform_has(CC_ATTR_HOST_SEV_SNP);
 
 out:
 	if (boot_cpu_has(X86_FEATURE_SEV))
@@ -2425,9 +2438,15 @@ out:
 		pr_info("SEV-ES %s (ASIDs %u - %u)\n",
 			sev_es_supported ? "enabled" : "disabled",
 			min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1);
+	if (boot_cpu_has(X86_FEATURE_SEV_SNP))
+		pr_info("SEV-SNP %s (ASIDs %u - %u)\n",
+			sev_snp_supported ? "enabled" : "disabled",
+			min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1);
 
 	sev_enabled = sev_supported;
 	sev_es_enabled = sev_es_supported;
+	sev_snp_enabled = sev_snp_supported;
+
 	if (!sev_es_enabled || !cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP) ||
 	    !cpu_feature_enabled(X86_FEATURE_NO_NESTED_DATA_BP))
 		sev_es_debug_swap_enabled = false;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index c8dc25886c16..66d5e2e46a66 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2057,6 +2057,9 @@ static int npf_interception(struct kvm_vcpu *vcpu)
 	if (WARN_ON_ONCE(error_code & PFERR_SYNTHETIC_MASK))
 		error_code &= ~PFERR_SYNTHETIC_MASK;
 
+	if (sev_snp_guest(vcpu->kvm) && (error_code & PFERR_GUEST_ENC_MASK))
+		error_code |= PFERR_PRIVATE_ACCESS;
+
 	trace_kvm_page_fault(vcpu, fault_address, error_code);
 	return kvm_mmu_page_fault(vcpu, fault_address, error_code,
 			static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
@@ -4902,8 +4905,11 @@ static int svm_vm_init(struct kvm *kvm)
 
 	if (type != KVM_X86_DEFAULT_VM &&
 	    type != KVM_X86_SW_PROTECTED_VM) {
-		kvm->arch.has_protected_state = (type == KVM_X86_SEV_ES_VM);
+		kvm->arch.has_protected_state =
+			(type == KVM_X86_SEV_ES_VM || type == KVM_X86_SNP_VM);
 		to_kvm_sev_info(kvm)->need_init = true;
+
+		kvm->arch.has_private_mem = (type == KVM_X86_SNP_VM);
 	}
 
 	if (!pause_filter_count || !pause_filter_thresh)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index be57213cd295..583e035d38f8 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -349,6 +349,18 @@ static __always_inline bool sev_es_guest(struct kvm *kvm)
 #endif
 }
 
+static __always_inline bool sev_snp_guest(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_AMD_SEV
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+
+	return (sev->vmsa_features & SVM_SEV_FEAT_SNP_ACTIVE) &&
+	       !WARN_ON_ONCE(!sev_es_guest(kvm));
+#else
+	return false;
+#endif
+}
+
 static inline void vmcb_mark_all_dirty(struct vmcb *vmcb)
 {
 	vmcb->control.clean = 0;
-- 
cgit v1.2.3-58-ga151


From 136d8bc931c84fbe4c70c2d6e0a4d20a2aa90505 Mon Sep 17 00:00:00 2001
From: Brijesh Singh <brijesh.singh@amd.com>
Date: Wed, 1 May 2024 03:51:55 -0500
Subject: KVM: SEV: Add KVM_SEV_SNP_LAUNCH_START command

KVM_SEV_SNP_LAUNCH_START begins the launch process for an SEV-SNP guest.
The command initializes a cryptographic digest context used to construct
the measurement of the guest. Other commands can then at that point be
used to load/encrypt data into the guest's initial launch image.

For more information see the SEV-SNP specification.

Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Message-ID: <20240501085210.2213060-6-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../virt/kvm/x86/amd-memory-encryption.rst         |  28 +++-
 arch/x86/include/uapi/asm/kvm.h                    |  11 ++
 arch/x86/kvm/svm/sev.c                             | 176 ++++++++++++++++++++-
 arch/x86/kvm/svm/svm.h                             |   1 +
 4 files changed, 212 insertions(+), 4 deletions(-)

diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
index 9677a0714a39..dd179e162a87 100644
--- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst
+++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
@@ -466,6 +466,30 @@ issued by the hypervisor to make the guest ready for execution.
 
 Returns: 0 on success, -negative on error
 
+18. KVM_SEV_SNP_LAUNCH_START
+----------------------------
+
+The KVM_SNP_LAUNCH_START command is used for creating the memory encryption
+context for the SEV-SNP guest. It must be called prior to issuing
+KVM_SEV_SNP_LAUNCH_UPDATE or KVM_SEV_SNP_LAUNCH_FINISH;
+
+Parameters (in): struct  kvm_sev_snp_launch_start
+
+Returns: 0 on success, -negative on error
+
+::
+
+        struct kvm_sev_snp_launch_start {
+                __u64 policy;           /* Guest policy to use. */
+                __u8 gosvw[16];         /* Guest OS visible workarounds. */
+                __u16 flags;            /* Must be zero. */
+                __u8 pad0[6];
+                __u64 pad1[4];
+        };
+
+See SNP_LAUNCH_START in the SEV-SNP specification [snp-fw-abi]_ for further
+details on the input parameters in ``struct kvm_sev_snp_launch_start``.
+
 Device attribute API
 ====================
 
@@ -497,9 +521,11 @@ References
 ==========
 
 
-See [white-paper]_, [api-spec]_, [amd-apm]_ and [kvm-forum]_ for more info.
+See [white-paper]_, [api-spec]_, [amd-apm]_, [kvm-forum]_, and [snp-fw-abi]_
+for more info.
 
 .. [white-paper] https://developer.amd.com/wordpress/media/2013/12/AMD_Memory_Encryption_Whitepaper_v7-Public.pdf
 .. [api-spec] https://support.amd.com/TechDocs/55766_SEV-KM_API_Specification.pdf
 .. [amd-apm] https://support.amd.com/TechDocs/24593.pdf (section 15.34)
 .. [kvm-forum]  https://www.linux-kvm.org/images/7/74/02x08A-Thomas_Lendacky-AMDs_Virtualizatoin_Memory_Encryption_Technology.pdf
+.. [snp-fw-abi] https://www.amd.com/system/files/TechDocs/56860.pdf
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index d2ae5fcc0275..693a80ffe40a 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -697,6 +697,9 @@ enum sev_cmd_id {
 	/* Second time is the charm; improved versions of the above ioctls.  */
 	KVM_SEV_INIT2,
 
+	/* SNP-specific commands */
+	KVM_SEV_SNP_LAUNCH_START = 100,
+
 	KVM_SEV_NR_MAX,
 };
 
@@ -824,6 +827,14 @@ struct kvm_sev_receive_update_data {
 	__u32 pad2;
 };
 
+struct kvm_sev_snp_launch_start {
+	__u64 policy;
+	__u8 gosvw[16];
+	__u16 flags;
+	__u8 pad0[6];
+	__u64 pad1[4];
+};
+
 #define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
 #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
 
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index b3345d45b989..b372ae5c8c58 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -25,6 +25,7 @@
 #include <asm/fpu/xcr.h>
 #include <asm/fpu/xstate.h>
 #include <asm/debugreg.h>
+#include <asm/sev.h>
 
 #include "mmu.h"
 #include "x86.h"
@@ -59,6 +60,21 @@ static u64 sev_supported_vmsa_features;
 #define AP_RESET_HOLD_NAE_EVENT		1
 #define AP_RESET_HOLD_MSR_PROTO		2
 
+/* As defined by SEV-SNP Firmware ABI, under "Guest Policy". */
+#define SNP_POLICY_MASK_API_MINOR	GENMASK_ULL(7, 0)
+#define SNP_POLICY_MASK_API_MAJOR	GENMASK_ULL(15, 8)
+#define SNP_POLICY_MASK_SMT		BIT_ULL(16)
+#define SNP_POLICY_MASK_RSVD_MBO	BIT_ULL(17)
+#define SNP_POLICY_MASK_DEBUG		BIT_ULL(19)
+#define SNP_POLICY_MASK_SINGLE_SOCKET	BIT_ULL(20)
+
+#define SNP_POLICY_MASK_VALID		(SNP_POLICY_MASK_API_MINOR	| \
+					 SNP_POLICY_MASK_API_MAJOR	| \
+					 SNP_POLICY_MASK_SMT		| \
+					 SNP_POLICY_MASK_RSVD_MBO	| \
+					 SNP_POLICY_MASK_DEBUG		| \
+					 SNP_POLICY_MASK_SINGLE_SOCKET)
+
 static u8 sev_enc_bit;
 static DECLARE_RWSEM(sev_deactivate_lock);
 static DEFINE_MUTEX(sev_bitmap_lock);
@@ -69,6 +85,8 @@ static unsigned int nr_asids;
 static unsigned long *sev_asid_bitmap;
 static unsigned long *sev_reclaim_asid_bitmap;
 
+static int snp_decommission_context(struct kvm *kvm);
+
 struct enc_region {
 	struct list_head list;
 	unsigned long npages;
@@ -95,12 +113,17 @@ static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
 	down_write(&sev_deactivate_lock);
 
 	wbinvd_on_all_cpus();
-	ret = sev_guest_df_flush(&error);
+
+	if (sev_snp_enabled)
+		ret = sev_do_cmd(SEV_CMD_SNP_DF_FLUSH, NULL, &error);
+	else
+		ret = sev_guest_df_flush(&error);
 
 	up_write(&sev_deactivate_lock);
 
 	if (ret)
-		pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error);
+		pr_err("SEV%s: DF_FLUSH failed, ret=%d, error=%#x\n",
+		       sev_snp_enabled ? "-SNP" : "", ret, error);
 
 	return ret;
 }
@@ -1998,6 +2021,106 @@ int sev_dev_get_attr(u32 group, u64 attr, u64 *val)
 	}
 }
 
+/*
+ * The guest context contains all the information, keys and metadata
+ * associated with the guest that the firmware tracks to implement SEV
+ * and SNP features. The firmware stores the guest context in hypervisor
+ * provide page via the SNP_GCTX_CREATE command.
+ */
+static void *snp_context_create(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct sev_data_snp_addr data = {};
+	void *context;
+	int rc;
+
+	/* Allocate memory for context page */
+	context = snp_alloc_firmware_page(GFP_KERNEL_ACCOUNT);
+	if (!context)
+		return NULL;
+
+	data.address = __psp_pa(context);
+	rc = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_GCTX_CREATE, &data, &argp->error);
+	if (rc) {
+		pr_warn("Failed to create SEV-SNP context, rc %d fw_error %d",
+			rc, argp->error);
+		snp_free_firmware_page(context);
+		return NULL;
+	}
+
+	return context;
+}
+
+static int snp_bind_asid(struct kvm *kvm, int *error)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_data_snp_activate data = {0};
+
+	data.gctx_paddr = __psp_pa(sev->snp_context);
+	data.asid = sev_get_asid(kvm);
+	return sev_issue_cmd(kvm, SEV_CMD_SNP_ACTIVATE, &data, error);
+}
+
+static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_data_snp_launch_start start = {0};
+	struct kvm_sev_snp_launch_start params;
+	int rc;
+
+	if (!sev_snp_guest(kvm))
+		return -ENOTTY;
+
+	if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
+		return -EFAULT;
+
+	/* Don't allow userspace to allocate memory for more than 1 SNP context. */
+	if (sev->snp_context)
+		return -EINVAL;
+
+	sev->snp_context = snp_context_create(kvm, argp);
+	if (!sev->snp_context)
+		return -ENOTTY;
+
+	if (params.flags)
+		return -EINVAL;
+
+	if (params.policy & ~SNP_POLICY_MASK_VALID)
+		return -EINVAL;
+
+	/* Check for policy bits that must be set */
+	if (!(params.policy & SNP_POLICY_MASK_RSVD_MBO) ||
+	    !(params.policy & SNP_POLICY_MASK_SMT))
+		return -EINVAL;
+
+	if (params.policy & SNP_POLICY_MASK_SINGLE_SOCKET)
+		return -EINVAL;
+
+	start.gctx_paddr = __psp_pa(sev->snp_context);
+	start.policy = params.policy;
+	memcpy(start.gosvw, params.gosvw, sizeof(params.gosvw));
+	rc = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_LAUNCH_START, &start, &argp->error);
+	if (rc) {
+		pr_debug("%s: SEV_CMD_SNP_LAUNCH_START firmware command failed, rc %d\n",
+			 __func__, rc);
+		goto e_free_context;
+	}
+
+	sev->fd = argp->sev_fd;
+	rc = snp_bind_asid(kvm, &argp->error);
+	if (rc) {
+		pr_debug("%s: Failed to bind ASID to SEV-SNP context, rc %d\n",
+			 __func__, rc);
+		goto e_free_context;
+	}
+
+	return 0;
+
+e_free_context:
+	snp_decommission_context(kvm);
+
+	return rc;
+}
+
 int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;
@@ -2021,6 +2144,15 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 		goto out;
 	}
 
+	/*
+	 * Once KVM_SEV_INIT2 initializes a KVM instance as an SNP guest, only
+	 * allow the use of SNP-specific commands.
+	 */
+	if (sev_snp_guest(kvm) && sev_cmd.id < KVM_SEV_SNP_LAUNCH_START) {
+		r = -EPERM;
+		goto out;
+	}
+
 	switch (sev_cmd.id) {
 	case KVM_SEV_ES_INIT:
 		if (!sev_es_enabled) {
@@ -2085,6 +2217,9 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 	case KVM_SEV_RECEIVE_FINISH:
 		r = sev_receive_finish(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_SNP_LAUNCH_START:
+		r = snp_launch_start(kvm, &sev_cmd);
+		break;
 	default:
 		r = -EINVAL;
 		goto out;
@@ -2280,6 +2415,31 @@ e_source_fput:
 	return ret;
 }
 
+static int snp_decommission_context(struct kvm *kvm)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_data_snp_addr data = {};
+	int ret;
+
+	/* If context is not created then do nothing */
+	if (!sev->snp_context)
+		return 0;
+
+	/* Do the decommision, which will unbind the ASID from the SNP context */
+	data.address = __sme_pa(sev->snp_context);
+	down_write(&sev_deactivate_lock);
+	ret = sev_do_cmd(SEV_CMD_SNP_DECOMMISSION, &data, NULL);
+	up_write(&sev_deactivate_lock);
+
+	if (WARN_ONCE(ret, "Failed to release guest context, ret %d", ret))
+		return ret;
+
+	snp_free_firmware_page(sev->snp_context);
+	sev->snp_context = NULL;
+
+	return 0;
+}
+
 void sev_vm_destroy(struct kvm *kvm)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
@@ -2321,7 +2481,17 @@ void sev_vm_destroy(struct kvm *kvm)
 		}
 	}
 
-	sev_unbind_asid(kvm, sev->handle);
+	if (sev_snp_guest(kvm)) {
+		/*
+		 * Decomission handles unbinding of the ASID. If it fails for
+		 * some unexpected reason, just leak the ASID.
+		 */
+		if (snp_decommission_context(kvm))
+			return;
+	} else {
+		sev_unbind_asid(kvm, sev->handle);
+	}
+
 	sev_asid_free(sev);
 }
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 583e035d38f8..305772d36490 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -93,6 +93,7 @@ struct kvm_sev_info {
 	struct list_head mirror_entry; /* Use as a list entry of mirrors */
 	struct misc_cg *misc_cg; /* For misc cgroup accounting */
 	atomic_t migration_in_progress;
+	void *snp_context;      /* SNP guest context page */
 };
 
 struct kvm_svm {
-- 
cgit v1.2.3-58-ga151


From dee5a47cc7a45287ec1137edb745bb4dffbe85f6 Mon Sep 17 00:00:00 2001
From: Brijesh Singh <brijesh.singh@amd.com>
Date: Wed, 1 May 2024 03:51:56 -0500
Subject: KVM: SEV: Add KVM_SEV_SNP_LAUNCH_UPDATE command

A key aspect of a launching an SNP guest is initializing it with a
known/measured payload which is then encrypted into guest memory as
pre-validated private pages and then measured into the cryptographic
launch context created with KVM_SEV_SNP_LAUNCH_START so that the guest
can attest itself after booting.

Since all private pages are provided by guest_memfd, make use of the
kvm_gmem_populate() interface to handle this. The general flow is that
guest_memfd will handle allocating the pages associated with the GPA
ranges being initialized by each particular call of
KVM_SEV_SNP_LAUNCH_UPDATE, copying data from userspace into those pages,
and then the post_populate callback will do the work of setting the
RMP entries for these pages to private and issuing the SNP firmware
calls to encrypt/measure them.

For more information see the SEV-SNP specification.

Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Message-ID: <20240501085210.2213060-7-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../virt/kvm/x86/amd-memory-encryption.rst         |  54 +++++
 arch/x86/include/uapi/asm/kvm.h                    |  19 ++
 arch/x86/kvm/svm/sev.c                             | 230 +++++++++++++++++++++
 3 files changed, 303 insertions(+)

diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
index dd179e162a87..cc16a7426d18 100644
--- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst
+++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
@@ -490,6 +490,60 @@ Returns: 0 on success, -negative on error
 See SNP_LAUNCH_START in the SEV-SNP specification [snp-fw-abi]_ for further
 details on the input parameters in ``struct kvm_sev_snp_launch_start``.
 
+19. KVM_SEV_SNP_LAUNCH_UPDATE
+-----------------------------
+
+The KVM_SEV_SNP_LAUNCH_UPDATE command is used for loading userspace-provided
+data into a guest GPA range, measuring the contents into the SNP guest context
+created by KVM_SEV_SNP_LAUNCH_START, and then encrypting/validating that GPA
+range so that it will be immediately readable using the encryption key
+associated with the guest context once it is booted, after which point it can
+attest the measurement associated with its context before unlocking any
+secrets.
+
+It is required that the GPA ranges initialized by this command have had the
+KVM_MEMORY_ATTRIBUTE_PRIVATE attribute set in advance. See the documentation
+for KVM_SET_MEMORY_ATTRIBUTES for more details on this aspect.
+
+Upon success, this command is not guaranteed to have processed the entire
+range requested. Instead, the ``gfn_start``, ``uaddr``, and ``len`` fields of
+``struct kvm_sev_snp_launch_update`` will be updated to correspond to the
+remaining range that has yet to be processed. The caller should continue
+calling this command until those fields indicate the entire range has been
+processed, e.g. ``len`` is 0, ``gfn_start`` is equal to the last GFN in the
+range plus 1, and ``uaddr`` is the last byte of the userspace-provided source
+buffer address plus 1. In the case where ``type`` is KVM_SEV_SNP_PAGE_TYPE_ZERO,
+``uaddr`` will be ignored completely.
+
+Parameters (in): struct  kvm_sev_snp_launch_update
+
+Returns: 0 on success, < 0 on error, -EAGAIN if caller should retry
+
+::
+
+        struct kvm_sev_snp_launch_update {
+                __u64 gfn_start;        /* Guest page number to load/encrypt data into. */
+                __u64 uaddr;            /* Userspace address of data to be loaded/encrypted. */
+                __u64 len;              /* 4k-aligned length in bytes to copy into guest memory.*/
+                __u8 type;              /* The type of the guest pages being initialized. */
+                __u8 pad0;
+                __u16 flags;            /* Must be zero. */
+                __u32 pad1;
+                __u64 pad2[4];
+
+        };
+
+where the allowed values for page_type are #define'd as::
+
+        KVM_SEV_SNP_PAGE_TYPE_NORMAL
+        KVM_SEV_SNP_PAGE_TYPE_ZERO
+        KVM_SEV_SNP_PAGE_TYPE_UNMEASURED
+        KVM_SEV_SNP_PAGE_TYPE_SECRETS
+        KVM_SEV_SNP_PAGE_TYPE_CPUID
+
+See the SEV-SNP spec [snp-fw-abi]_ for further details on how each page type is
+used/measured.
+
 Device attribute API
 ====================
 
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 693a80ffe40a..5935dc8a7e02 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -699,6 +699,7 @@ enum sev_cmd_id {
 
 	/* SNP-specific commands */
 	KVM_SEV_SNP_LAUNCH_START = 100,
+	KVM_SEV_SNP_LAUNCH_UPDATE,
 
 	KVM_SEV_NR_MAX,
 };
@@ -835,6 +836,24 @@ struct kvm_sev_snp_launch_start {
 	__u64 pad1[4];
 };
 
+/* Kept in sync with firmware values for simplicity. */
+#define KVM_SEV_SNP_PAGE_TYPE_NORMAL		0x1
+#define KVM_SEV_SNP_PAGE_TYPE_ZERO		0x3
+#define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED	0x4
+#define KVM_SEV_SNP_PAGE_TYPE_SECRETS		0x5
+#define KVM_SEV_SNP_PAGE_TYPE_CPUID		0x6
+
+struct kvm_sev_snp_launch_update {
+	__u64 gfn_start;
+	__u64 uaddr;
+	__u64 len;
+	__u8 type;
+	__u8 pad0;
+	__u16 flags;
+	__u32 pad1;
+	__u64 pad2[4];
+};
+
 #define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
 #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
 
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index b372ae5c8c58..c966f2224624 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -259,6 +259,45 @@ static void sev_decommission(unsigned int handle)
 	sev_guest_decommission(&decommission, NULL);
 }
 
+/*
+ * Certain page-states, such as Pre-Guest and Firmware pages (as documented
+ * in Chapter 5 of the SEV-SNP Firmware ABI under "Page States") cannot be
+ * directly transitioned back to normal/hypervisor-owned state via RMPUPDATE
+ * unless they are reclaimed first.
+ *
+ * Until they are reclaimed and subsequently transitioned via RMPUPDATE, they
+ * might not be usable by the host due to being set as immutable or still
+ * being associated with a guest ASID.
+ */
+static int snp_page_reclaim(u64 pfn)
+{
+	struct sev_data_snp_page_reclaim data = {0};
+	int err, rc;
+
+	data.paddr = __sme_set(pfn << PAGE_SHIFT);
+	rc = sev_do_cmd(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err);
+	if (WARN_ONCE(rc, "Failed to reclaim PFN %llx", pfn))
+		snp_leak_pages(pfn, 1);
+
+	return rc;
+}
+
+/*
+ * Transition a page to hypervisor-owned/shared state in the RMP table. This
+ * should not fail under normal conditions, but leak the page should that
+ * happen since it will no longer be usable by the host due to RMP protections.
+ */
+static int host_rmp_make_shared(u64 pfn, enum pg_level level)
+{
+	int rc;
+
+	rc = rmp_make_shared(pfn, level);
+	if (WARN_ON_ONCE(rc))
+		snp_leak_pages(pfn, page_level_size(level) >> PAGE_SHIFT);
+
+	return rc;
+}
+
 static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
 {
 	struct sev_data_deactivate deactivate;
@@ -2121,6 +2160,194 @@ e_free_context:
 	return rc;
 }
 
+struct sev_gmem_populate_args {
+	__u8 type;
+	int sev_fd;
+	int fw_error;
+};
+
+static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pfn,
+				  void __user *src, int order, void *opaque)
+{
+	struct sev_gmem_populate_args *sev_populate_args = opaque;
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	int n_private = 0, ret, i;
+	int npages = (1 << order);
+	gfn_t gfn;
+
+	if (WARN_ON_ONCE(sev_populate_args->type != KVM_SEV_SNP_PAGE_TYPE_ZERO && !src))
+		return -EINVAL;
+
+	for (gfn = gfn_start, i = 0; gfn < gfn_start + npages; gfn++, i++) {
+		struct sev_data_snp_launch_update fw_args = {0};
+		bool assigned;
+		int level;
+
+		if (!kvm_mem_is_private(kvm, gfn)) {
+			pr_debug("%s: Failed to ensure GFN 0x%llx has private memory attribute set\n",
+				 __func__, gfn);
+			ret = -EINVAL;
+			goto err;
+		}
+
+		ret = snp_lookup_rmpentry((u64)pfn + i, &assigned, &level);
+		if (ret || assigned) {
+			pr_debug("%s: Failed to ensure GFN 0x%llx RMP entry is initial shared state, ret: %d assigned: %d\n",
+				 __func__, gfn, ret, assigned);
+			ret = -EINVAL;
+			goto err;
+		}
+
+		if (src) {
+			void *vaddr = kmap_local_pfn(pfn + i);
+
+			ret = copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE);
+			if (ret)
+				goto err;
+			kunmap_local(vaddr);
+		}
+
+		ret = rmp_make_private(pfn + i, gfn << PAGE_SHIFT, PG_LEVEL_4K,
+				       sev_get_asid(kvm), true);
+		if (ret)
+			goto err;
+
+		n_private++;
+
+		fw_args.gctx_paddr = __psp_pa(sev->snp_context);
+		fw_args.address = __sme_set(pfn_to_hpa(pfn + i));
+		fw_args.page_size = PG_LEVEL_TO_RMP(PG_LEVEL_4K);
+		fw_args.page_type = sev_populate_args->type;
+
+		ret = __sev_issue_cmd(sev_populate_args->sev_fd, SEV_CMD_SNP_LAUNCH_UPDATE,
+				      &fw_args, &sev_populate_args->fw_error);
+		if (ret)
+			goto fw_err;
+	}
+
+	return 0;
+
+fw_err:
+	/*
+	 * If the firmware command failed handle the reclaim and cleanup of that
+	 * PFN specially vs. prior pages which can be cleaned up below without
+	 * needing to reclaim in advance.
+	 *
+	 * Additionally, when invalid CPUID function entries are detected,
+	 * firmware writes the expected values into the page and leaves it
+	 * unencrypted so it can be used for debugging and error-reporting.
+	 *
+	 * Copy this page back into the source buffer so userspace can use this
+	 * information to provide information on which CPUID leaves/fields
+	 * failed CPUID validation.
+	 */
+	if (!snp_page_reclaim(pfn + i) && !host_rmp_make_shared(pfn + i, PG_LEVEL_4K) &&
+	    sev_populate_args->type == KVM_SEV_SNP_PAGE_TYPE_CPUID &&
+	    sev_populate_args->fw_error == SEV_RET_INVALID_PARAM) {
+		void *vaddr = kmap_local_pfn(pfn + i);
+
+		if (copy_to_user(src + i * PAGE_SIZE, vaddr, PAGE_SIZE))
+			pr_debug("Failed to write CPUID page back to userspace\n");
+
+		kunmap_local(vaddr);
+	}
+
+	/* pfn + i is hypervisor-owned now, so skip below cleanup for it. */
+	n_private--;
+
+err:
+	pr_debug("%s: exiting with error ret %d (fw_error %d), restoring %d gmem PFNs to shared.\n",
+		 __func__, ret, sev_populate_args->fw_error, n_private);
+	for (i = 0; i < n_private; i++)
+		host_rmp_make_shared(pfn + i, PG_LEVEL_4K);
+
+	return ret;
+}
+
+static int snp_launch_update(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_gmem_populate_args sev_populate_args = {0};
+	struct kvm_sev_snp_launch_update params;
+	struct kvm_memory_slot *memslot;
+	long npages, count;
+	void __user *src;
+	int ret = 0;
+
+	if (!sev_snp_guest(kvm) || !sev->snp_context)
+		return -EINVAL;
+
+	if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
+		return -EFAULT;
+
+	pr_debug("%s: GFN start 0x%llx length 0x%llx type %d flags %d\n", __func__,
+		 params.gfn_start, params.len, params.type, params.flags);
+
+	if (!PAGE_ALIGNED(params.len) || params.flags ||
+	    (params.type != KVM_SEV_SNP_PAGE_TYPE_NORMAL &&
+	     params.type != KVM_SEV_SNP_PAGE_TYPE_ZERO &&
+	     params.type != KVM_SEV_SNP_PAGE_TYPE_UNMEASURED &&
+	     params.type != KVM_SEV_SNP_PAGE_TYPE_SECRETS &&
+	     params.type != KVM_SEV_SNP_PAGE_TYPE_CPUID))
+		return -EINVAL;
+
+	npages = params.len / PAGE_SIZE;
+
+	/*
+	 * For each GFN that's being prepared as part of the initial guest
+	 * state, the following pre-conditions are verified:
+	 *
+	 *   1) The backing memslot is a valid private memslot.
+	 *   2) The GFN has been set to private via KVM_SET_MEMORY_ATTRIBUTES
+	 *      beforehand.
+	 *   3) The PFN of the guest_memfd has not already been set to private
+	 *      in the RMP table.
+	 *
+	 * The KVM MMU relies on kvm->mmu_invalidate_seq to retry nested page
+	 * faults if there's a race between a fault and an attribute update via
+	 * KVM_SET_MEMORY_ATTRIBUTES, and a similar approach could be utilized
+	 * here. However, kvm->slots_lock guards against both this as well as
+	 * concurrent memslot updates occurring while these checks are being
+	 * performed, so use that here to make it easier to reason about the
+	 * initial expected state and better guard against unexpected
+	 * situations.
+	 */
+	mutex_lock(&kvm->slots_lock);
+
+	memslot = gfn_to_memslot(kvm, params.gfn_start);
+	if (!kvm_slot_can_be_private(memslot)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	sev_populate_args.sev_fd = argp->sev_fd;
+	sev_populate_args.type = params.type;
+	src = params.type == KVM_SEV_SNP_PAGE_TYPE_ZERO ? NULL : u64_to_user_ptr(params.uaddr);
+
+	count = kvm_gmem_populate(kvm, params.gfn_start, src, npages,
+				  sev_gmem_post_populate, &sev_populate_args);
+	if (count < 0) {
+		argp->error = sev_populate_args.fw_error;
+		pr_debug("%s: kvm_gmem_populate failed, ret %ld (fw_error %d)\n",
+			 __func__, count, argp->error);
+		ret = -EIO;
+	} else {
+		params.gfn_start += count;
+		params.len -= count * PAGE_SIZE;
+		if (params.type != KVM_SEV_SNP_PAGE_TYPE_ZERO)
+			params.uaddr += count * PAGE_SIZE;
+
+		ret = 0;
+		if (copy_to_user(u64_to_user_ptr(argp->data), &params, sizeof(params)))
+			ret = -EFAULT;
+	}
+
+out:
+	mutex_unlock(&kvm->slots_lock);
+
+	return ret;
+}
+
 int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;
@@ -2220,6 +2447,9 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 	case KVM_SEV_SNP_LAUNCH_START:
 		r = snp_launch_start(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_SNP_LAUNCH_UPDATE:
+		r = snp_launch_update(kvm, &sev_cmd);
+		break;
 	default:
 		r = -EINVAL;
 		goto out;
-- 
cgit v1.2.3-58-ga151


From ad27ce155566f2b4400fa865859834592bd18777 Mon Sep 17 00:00:00 2001
From: Brijesh Singh <brijesh.singh@amd.com>
Date: Wed, 1 May 2024 03:51:57 -0500
Subject: KVM: SEV: Add KVM_SEV_SNP_LAUNCH_FINISH command

Add a KVM_SEV_SNP_LAUNCH_FINISH command to finalize the cryptographic
launch digest which stores the measurement of the guest at launch time.
Also extend the existing SNP firmware data structures to support
disabling the use of Versioned Chip Endorsement Keys (VCEK) by guests as
part of this command.

While finalizing the launch flow, the code also issues the LAUNCH_UPDATE
SNP firmware commands to encrypt/measure the initial VMSA pages for each
configured vCPU, which requires setting the RMP entries for those pages
to private, so also add handling to clean up the RMP entries for these
pages whening freeing vCPUs during shutdown.

Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Harald Hoyer <harald@profian.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Message-ID: <20240501085210.2213060-8-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../virt/kvm/x86/amd-memory-encryption.rst         |  28 +++++
 arch/x86/include/uapi/asm/kvm.h                    |  17 +++
 arch/x86/kvm/svm/sev.c                             | 127 +++++++++++++++++++++
 include/linux/psp-sev.h                            |   4 +-
 4 files changed, 175 insertions(+), 1 deletion(-)

diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
index cc16a7426d18..1ddb6a86ce7f 100644
--- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst
+++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
@@ -544,6 +544,34 @@ where the allowed values for page_type are #define'd as::
 See the SEV-SNP spec [snp-fw-abi]_ for further details on how each page type is
 used/measured.
 
+20. KVM_SEV_SNP_LAUNCH_FINISH
+-----------------------------
+
+After completion of the SNP guest launch flow, the KVM_SEV_SNP_LAUNCH_FINISH
+command can be issued to make the guest ready for execution.
+
+Parameters (in): struct kvm_sev_snp_launch_finish
+
+Returns: 0 on success, -negative on error
+
+::
+
+        struct kvm_sev_snp_launch_finish {
+                __u64 id_block_uaddr;
+                __u64 id_auth_uaddr;
+                __u8 id_block_en;
+                __u8 auth_key_en;
+                __u8 vcek_disabled;
+                __u8 host_data[32];
+                __u8 pad0[3];
+                __u16 flags;                    /* Must be zero */
+                __u64 pad1[4];
+        };
+
+
+See SNP_LAUNCH_FINISH in the SEV-SNP specification [snp-fw-abi]_ for further
+details on the input parameters in ``struct kvm_sev_snp_launch_finish``.
+
 Device attribute API
 ====================
 
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 5935dc8a7e02..988b5204d636 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -700,6 +700,7 @@ enum sev_cmd_id {
 	/* SNP-specific commands */
 	KVM_SEV_SNP_LAUNCH_START = 100,
 	KVM_SEV_SNP_LAUNCH_UPDATE,
+	KVM_SEV_SNP_LAUNCH_FINISH,
 
 	KVM_SEV_NR_MAX,
 };
@@ -854,6 +855,22 @@ struct kvm_sev_snp_launch_update {
 	__u64 pad2[4];
 };
 
+#define KVM_SEV_SNP_ID_BLOCK_SIZE	96
+#define KVM_SEV_SNP_ID_AUTH_SIZE	4096
+#define KVM_SEV_SNP_FINISH_DATA_SIZE	32
+
+struct kvm_sev_snp_launch_finish {
+	__u64 id_block_uaddr;
+	__u64 id_auth_uaddr;
+	__u8 id_block_en;
+	__u8 auth_key_en;
+	__u8 vcek_disabled;
+	__u8 host_data[KVM_SEV_SNP_FINISH_DATA_SIZE];
+	__u8 pad0[3];
+	__u16 flags;
+	__u64 pad1[4];
+};
+
 #define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
 #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
 
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index c966f2224624..208bb8170d3f 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -75,6 +75,8 @@ static u64 sev_supported_vmsa_features;
 					 SNP_POLICY_MASK_DEBUG		| \
 					 SNP_POLICY_MASK_SINGLE_SOCKET)
 
+#define INITIAL_VMSA_GPA 0xFFFFFFFFF000
+
 static u8 sev_enc_bit;
 static DECLARE_RWSEM(sev_deactivate_lock);
 static DEFINE_MUTEX(sev_bitmap_lock);
@@ -2348,6 +2350,115 @@ out:
 	return ret;
 }
 
+static int snp_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_data_snp_launch_update data = {};
+	struct kvm_vcpu *vcpu;
+	unsigned long i;
+	int ret;
+
+	data.gctx_paddr = __psp_pa(sev->snp_context);
+	data.page_type = SNP_PAGE_TYPE_VMSA;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct vcpu_svm *svm = to_svm(vcpu);
+		u64 pfn = __pa(svm->sev_es.vmsa) >> PAGE_SHIFT;
+
+		ret = sev_es_sync_vmsa(svm);
+		if (ret)
+			return ret;
+
+		/* Transition the VMSA page to a firmware state. */
+		ret = rmp_make_private(pfn, INITIAL_VMSA_GPA, PG_LEVEL_4K, sev->asid, true);
+		if (ret)
+			return ret;
+
+		/* Issue the SNP command to encrypt the VMSA */
+		data.address = __sme_pa(svm->sev_es.vmsa);
+		ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_LAUNCH_UPDATE,
+				      &data, &argp->error);
+		if (ret) {
+			if (!snp_page_reclaim(pfn))
+				host_rmp_make_shared(pfn, PG_LEVEL_4K);
+
+			return ret;
+		}
+
+		svm->vcpu.arch.guest_state_protected = true;
+	}
+
+	return 0;
+}
+
+static int snp_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_snp_launch_finish params;
+	struct sev_data_snp_launch_finish *data;
+	void *id_block = NULL, *id_auth = NULL;
+	int ret;
+
+	if (!sev_snp_guest(kvm))
+		return -ENOTTY;
+
+	if (!sev->snp_context)
+		return -EINVAL;
+
+	if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
+		return -EFAULT;
+
+	if (params.flags)
+		return -EINVAL;
+
+	/* Measure all vCPUs using LAUNCH_UPDATE before finalizing the launch flow. */
+	ret = snp_launch_update_vmsa(kvm, argp);
+	if (ret)
+		return ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
+	if (!data)
+		return -ENOMEM;
+
+	if (params.id_block_en) {
+		id_block = psp_copy_user_blob(params.id_block_uaddr, KVM_SEV_SNP_ID_BLOCK_SIZE);
+		if (IS_ERR(id_block)) {
+			ret = PTR_ERR(id_block);
+			goto e_free;
+		}
+
+		data->id_block_en = 1;
+		data->id_block_paddr = __sme_pa(id_block);
+
+		id_auth = psp_copy_user_blob(params.id_auth_uaddr, KVM_SEV_SNP_ID_AUTH_SIZE);
+		if (IS_ERR(id_auth)) {
+			ret = PTR_ERR(id_auth);
+			goto e_free_id_block;
+		}
+
+		data->id_auth_paddr = __sme_pa(id_auth);
+
+		if (params.auth_key_en)
+			data->auth_key_en = 1;
+	}
+
+	data->vcek_disabled = params.vcek_disabled;
+
+	memcpy(data->host_data, params.host_data, KVM_SEV_SNP_FINISH_DATA_SIZE);
+	data->gctx_paddr = __psp_pa(sev->snp_context);
+	ret = sev_issue_cmd(kvm, SEV_CMD_SNP_LAUNCH_FINISH, data, &argp->error);
+
+	kfree(id_auth);
+
+e_free_id_block:
+	kfree(id_block);
+
+e_free:
+	kfree(data);
+
+	return ret;
+}
+
 int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;
@@ -2450,6 +2561,9 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 	case KVM_SEV_SNP_LAUNCH_UPDATE:
 		r = snp_launch_update(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_SNP_LAUNCH_FINISH:
+		r = snp_launch_finish(kvm, &sev_cmd);
+		break;
 	default:
 		r = -EINVAL;
 		goto out;
@@ -2940,11 +3054,24 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu)
 
 	svm = to_svm(vcpu);
 
+	/*
+	 * If it's an SNP guest, then the VMSA was marked in the RMP table as
+	 * a guest-owned page. Transition the page to hypervisor state before
+	 * releasing it back to the system.
+	 */
+	if (sev_snp_guest(vcpu->kvm)) {
+		u64 pfn = __pa(svm->sev_es.vmsa) >> PAGE_SHIFT;
+
+		if (host_rmp_make_shared(pfn, PG_LEVEL_4K))
+			goto skip_vmsa_free;
+	}
+
 	if (vcpu->arch.guest_state_protected)
 		sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa);
 
 	__free_page(virt_to_page(svm->sev_es.vmsa));
 
+skip_vmsa_free:
 	if (svm->sev_es.ghcb_sa_free)
 		kvfree(svm->sev_es.ghcb_sa);
 }
diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 3705c2044fc0..903ddfea8585 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -658,6 +658,7 @@ struct sev_data_snp_launch_update {
  * @id_auth_paddr: system physical address of ID block authentication structure
  * @id_block_en: indicates whether ID block is present
  * @auth_key_en: indicates whether author key is present in authentication structure
+ * @vcek_disabled: indicates whether use of VCEK is allowed for attestation reports
  * @rsvd: reserved
  * @host_data: host-supplied data for guest, not interpreted by firmware
  */
@@ -667,7 +668,8 @@ struct sev_data_snp_launch_finish {
 	u64 id_auth_paddr;
 	u8 id_block_en:1;
 	u8 auth_key_en:1;
-	u64 rsvd:62;
+	u8 vcek_disabled:1;
+	u64 rsvd:61;
 	u8 host_data[32];
 } __packed;
 
-- 
cgit v1.2.3-58-ga151


From 0c76b1d08280649f789e1b537b397cefc43da7a0 Mon Sep 17 00:00:00 2001
From: Brijesh Singh <brijesh.singh@amd.com>
Date: Wed, 1 May 2024 03:51:58 -0500
Subject: KVM: SEV: Add support to handle GHCB GPA register VMGEXIT

SEV-SNP guests are required to perform a GHCB GPA registration. Before
using a GHCB GPA for a vCPU the first time, a guest must register the
vCPU GHCB GPA. If hypervisor can work with the guest requested GPA then
it must respond back with the same GPA otherwise return -1.

On VMEXIT, verify that the GHCB GPA matches with the registered value.
If a mismatch is detected, then abort the guest.

Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-ID: <20240501085210.2213060-9-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/sev-common.h |  8 +++++++
 arch/x86/kvm/svm/sev.c            | 48 ++++++++++++++++++++++++++++++++++-----
 arch/x86/kvm/svm/svm.h            |  7 ++++++
 3 files changed, 57 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index 5a8246dd532f..1006bfffe07a 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -59,6 +59,14 @@
 #define GHCB_MSR_AP_RESET_HOLD_RESULT_POS	12
 #define GHCB_MSR_AP_RESET_HOLD_RESULT_MASK	GENMASK_ULL(51, 0)
 
+/* Preferred GHCB GPA Request */
+#define GHCB_MSR_PREF_GPA_REQ		0x010
+#define GHCB_MSR_GPA_VALUE_POS		12
+#define GHCB_MSR_GPA_VALUE_MASK		GENMASK_ULL(51, 0)
+
+#define GHCB_MSR_PREF_GPA_RESP		0x011
+#define GHCB_MSR_PREF_GPA_NONE		0xfffffffffffff
+
 /* GHCB GPA Register */
 #define GHCB_MSR_REG_GPA_REQ		0x012
 #define GHCB_MSR_REG_GPA_REQ_VAL(v)			\
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 208bb8170d3f..557f462fde04 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3540,6 +3540,32 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 		set_ghcb_msr_bits(svm, GHCB_MSR_HV_FT_RESP,
 				  GHCB_MSR_INFO_MASK, GHCB_MSR_INFO_POS);
 		break;
+	case GHCB_MSR_PREF_GPA_REQ:
+		if (!sev_snp_guest(vcpu->kvm))
+			goto out_terminate;
+
+		set_ghcb_msr_bits(svm, GHCB_MSR_PREF_GPA_NONE, GHCB_MSR_GPA_VALUE_MASK,
+				  GHCB_MSR_GPA_VALUE_POS);
+		set_ghcb_msr_bits(svm, GHCB_MSR_PREF_GPA_RESP, GHCB_MSR_INFO_MASK,
+				  GHCB_MSR_INFO_POS);
+		break;
+	case GHCB_MSR_REG_GPA_REQ: {
+		u64 gfn;
+
+		if (!sev_snp_guest(vcpu->kvm))
+			goto out_terminate;
+
+		gfn = get_ghcb_msr_bits(svm, GHCB_MSR_GPA_VALUE_MASK,
+					GHCB_MSR_GPA_VALUE_POS);
+
+		svm->sev_es.ghcb_registered_gpa = gfn_to_gpa(gfn);
+
+		set_ghcb_msr_bits(svm, gfn, GHCB_MSR_GPA_VALUE_MASK,
+				  GHCB_MSR_GPA_VALUE_POS);
+		set_ghcb_msr_bits(svm, GHCB_MSR_REG_GPA_RESP, GHCB_MSR_INFO_MASK,
+				  GHCB_MSR_INFO_POS);
+		break;
+	}
 	case GHCB_MSR_TERM_REQ: {
 		u64 reason_set, reason_code;
 
@@ -3552,12 +3578,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 		pr_info("SEV-ES guest requested termination: %#llx:%#llx\n",
 			reason_set, reason_code);
 
-		vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
-		vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM;
-		vcpu->run->system_event.ndata = 1;
-		vcpu->run->system_event.data[0] = control->ghcb_gpa;
-
-		return 0;
+		goto out_terminate;
 	}
 	default:
 		/* Error, keep GHCB MSR value as-is */
@@ -3568,6 +3589,14 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 					    control->ghcb_gpa, ret);
 
 	return ret;
+
+out_terminate:
+	vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+	vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM;
+	vcpu->run->system_event.ndata = 1;
+	vcpu->run->system_event.data[0] = control->ghcb_gpa;
+
+	return 0;
 }
 
 int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
@@ -3603,6 +3632,13 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 	trace_kvm_vmgexit_enter(vcpu->vcpu_id, svm->sev_es.ghcb);
 
 	sev_es_sync_from_ghcb(svm);
+
+	/* SEV-SNP guest requires that the GHCB GPA must be registered */
+	if (sev_snp_guest(svm->vcpu.kvm) && !ghcb_gpa_is_registered(svm, ghcb_gpa)) {
+		vcpu_unimpl(&svm->vcpu, "vmgexit: GHCB GPA [%#llx] is not registered.\n", ghcb_gpa);
+		return -EINVAL;
+	}
+
 	ret = sev_es_validate_vmgexit(svm);
 	if (ret)
 		return ret;
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 305772d36490..202ac5494c19 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -209,6 +209,8 @@ struct vcpu_sev_es_state {
 	u32 ghcb_sa_len;
 	bool ghcb_sa_sync;
 	bool ghcb_sa_free;
+
+	u64 ghcb_registered_gpa;
 };
 
 struct vcpu_svm {
@@ -362,6 +364,11 @@ static __always_inline bool sev_snp_guest(struct kvm *kvm)
 #endif
 }
 
+static inline bool ghcb_gpa_is_registered(struct vcpu_svm *svm, u64 val)
+{
+	return svm->sev_es.ghcb_registered_gpa == val;
+}
+
 static inline void vmcb_mark_all_dirty(struct vmcb *vmcb)
 {
 	vmcb->control.clean = 0;
-- 
cgit v1.2.3-58-ga151


From d46b7b6a5f9ec652a9e3ac6344f679235c9b67da Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Wed, 1 May 2024 03:51:59 -0500
Subject: KVM: SEV: Add support to handle MSR based Page State Change VMGEXIT

SEV-SNP VMs can ask the hypervisor to change the page state in the RMP
table to be private or shared using the Page State Change MSR protocol
as defined in the GHCB specification.

When using gmem, private/shared memory is allocated through separate
pools, and KVM relies on userspace issuing a KVM_SET_MEMORY_ATTRIBUTES
KVM ioctl to tell the KVM MMU whether or not a particular GFN should be
backed by private memory or not.

Forward these page state change requests to userspace so that it can
issue the expected KVM ioctls. The KVM MMU will handle updating the RMP
entries when it is ready to map a private page into a guest.

Use the existing KVM_HC_MAP_GPA_RANGE hypercall format to deliver these
requests to userspace via KVM_EXIT_HYPERCALL.

Signed-off-by: Michael Roth <michael.roth@amd.com>
Co-developed-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Message-ID: <20240501085210.2213060-10-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/sev-common.h |  6 +++++
 arch/x86/kvm/svm/sev.c            | 48 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 54 insertions(+)

diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index 1006bfffe07a..6d68db812de1 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -101,11 +101,17 @@ enum psc_op {
 	/* GHCBData[11:0] */				\
 	GHCB_MSR_PSC_REQ)
 
+#define GHCB_MSR_PSC_REQ_TO_GFN(msr) (((msr) & GENMASK_ULL(51, 12)) >> 12)
+#define GHCB_MSR_PSC_REQ_TO_OP(msr) (((msr) & GENMASK_ULL(55, 52)) >> 52)
+
 #define GHCB_MSR_PSC_RESP		0x015
 #define GHCB_MSR_PSC_RESP_VAL(val)			\
 	/* GHCBData[63:32] */				\
 	(((u64)(val) & GENMASK_ULL(63, 32)) >> 32)
 
+/* Set highest bit as a generic error response */
+#define GHCB_MSR_PSC_RESP_ERROR (BIT_ULL(63) | GHCB_MSR_PSC_RESP)
+
 /* GHCB Hypervisor Feature Request/Response */
 #define GHCB_MSR_HV_FT_REQ		0x080
 #define GHCB_MSR_HV_FT_RESP		0x081
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 557f462fde04..438f2e8b8152 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3461,6 +3461,48 @@ static void set_ghcb_msr(struct vcpu_svm *svm, u64 value)
 	svm->vmcb->control.ghcb_gpa = value;
 }
 
+static int snp_complete_psc_msr(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (vcpu->run->hypercall.ret)
+		set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR);
+	else
+		set_ghcb_msr(svm, GHCB_MSR_PSC_RESP);
+
+	return 1; /* resume guest */
+}
+
+static int snp_begin_psc_msr(struct vcpu_svm *svm, u64 ghcb_msr)
+{
+	u64 gpa = gfn_to_gpa(GHCB_MSR_PSC_REQ_TO_GFN(ghcb_msr));
+	u8 op = GHCB_MSR_PSC_REQ_TO_OP(ghcb_msr);
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+
+	if (op != SNP_PAGE_STATE_PRIVATE && op != SNP_PAGE_STATE_SHARED) {
+		set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR);
+		return 1; /* resume guest */
+	}
+
+	if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) {
+		set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR);
+		return 1; /* resume guest */
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_HYPERCALL;
+	vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE;
+	vcpu->run->hypercall.args[0] = gpa;
+	vcpu->run->hypercall.args[1] = 1;
+	vcpu->run->hypercall.args[2] = (op == SNP_PAGE_STATE_PRIVATE)
+				       ? KVM_MAP_GPA_RANGE_ENCRYPTED
+				       : KVM_MAP_GPA_RANGE_DECRYPTED;
+	vcpu->run->hypercall.args[2] |= KVM_MAP_GPA_RANGE_PAGE_SZ_4K;
+
+	vcpu->arch.complete_userspace_io = snp_complete_psc_msr;
+
+	return 0; /* forward request to userspace */
+}
+
 static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -3566,6 +3608,12 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 				  GHCB_MSR_INFO_POS);
 		break;
 	}
+	case GHCB_MSR_PSC_REQ:
+		if (!sev_snp_guest(vcpu->kvm))
+			goto out_terminate;
+
+		ret = snp_begin_psc_msr(svm, control->ghcb_gpa);
+		break;
 	case GHCB_MSR_TERM_REQ: {
 		u64 reason_set, reason_code;
 
-- 
cgit v1.2.3-58-ga151


From 9b54e248d2644be71cb394eb85f31ad99e023a05 Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Wed, 1 May 2024 03:52:00 -0500
Subject: KVM: SEV: Add support to handle Page State Change VMGEXIT

SEV-SNP VMs can ask the hypervisor to change the page state in the RMP
table to be private or shared using the Page State Change NAE event
as defined in the GHCB specification version 2.

Forward these requests to userspace as KVM_EXIT_VMGEXITs, similar to how
it is done for requests that don't use a GHCB page.

As with the MSR-based page-state changes, use the existing
KVM_HC_MAP_GPA_RANGE hypercall format to deliver these requests to
userspace via KVM_EXIT_HYPERCALL.

Signed-off-by: Michael Roth <michael.roth@amd.com>
Co-developed-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Message-ID: <20240501085210.2213060-11-michael.roth@amd.com>
Co-developed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/sev-common.h |  11 +++
 arch/x86/kvm/svm/sev.c            | 188 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.h            |   5 +
 3 files changed, 204 insertions(+)

diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index 6d68db812de1..8647cc05e2f4 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -129,8 +129,19 @@ enum psc_op {
  *   The VMGEXIT_PSC_MAX_ENTRY determines the size of the PSC structure, which
  *   is a local stack variable in set_pages_state(). Do not increase this value
  *   without evaluating the impact to stack usage.
+ *
+ *   Use VMGEXIT_PSC_MAX_COUNT in cases where the actual GHCB-defined max value
+ *   is needed, such as when processing GHCB requests on the hypervisor side.
  */
 #define VMGEXIT_PSC_MAX_ENTRY		64
+#define VMGEXIT_PSC_MAX_COUNT		253
+
+#define VMGEXIT_PSC_ERROR_GENERIC	(0x100UL << 32)
+#define VMGEXIT_PSC_ERROR_INVALID_HDR	((1UL << 32) | 1)
+#define VMGEXIT_PSC_ERROR_INVALID_ENTRY	((1UL << 32) | 2)
+
+#define VMGEXIT_PSC_OP_PRIVATE		1
+#define VMGEXIT_PSC_OP_SHARED		2
 
 struct psc_hdr {
 	u16 cur_entry;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 438f2e8b8152..122219b3d3b7 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3274,6 +3274,10 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 	case SVM_VMGEXIT_HV_FEATURES:
 	case SVM_VMGEXIT_TERM_REQUEST:
 		break;
+	case SVM_VMGEXIT_PSC:
+		if (!sev_snp_guest(vcpu->kvm) || !kvm_ghcb_sw_scratch_is_valid(svm))
+			goto vmgexit_err;
+		break;
 	default:
 		reason = GHCB_ERR_INVALID_EVENT;
 		goto vmgexit_err;
@@ -3503,6 +3507,183 @@ static int snp_begin_psc_msr(struct vcpu_svm *svm, u64 ghcb_msr)
 	return 0; /* forward request to userspace */
 }
 
+struct psc_buffer {
+	struct psc_hdr hdr;
+	struct psc_entry entries[];
+} __packed;
+
+static int snp_begin_psc(struct vcpu_svm *svm, struct psc_buffer *psc);
+
+static void snp_complete_psc(struct vcpu_svm *svm, u64 psc_ret)
+{
+	svm->sev_es.psc_inflight = 0;
+	svm->sev_es.psc_idx = 0;
+	svm->sev_es.psc_2m = false;
+	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, psc_ret);
+}
+
+static void __snp_complete_one_psc(struct vcpu_svm *svm)
+{
+	struct psc_buffer *psc = svm->sev_es.ghcb_sa;
+	struct psc_entry *entries = psc->entries;
+	struct psc_hdr *hdr = &psc->hdr;
+	__u16 idx;
+
+	/*
+	 * Everything in-flight has been processed successfully. Update the
+	 * corresponding entries in the guest's PSC buffer and zero out the
+	 * count of in-flight PSC entries.
+	 */
+	for (idx = svm->sev_es.psc_idx; svm->sev_es.psc_inflight;
+	     svm->sev_es.psc_inflight--, idx++) {
+		struct psc_entry *entry = &entries[idx];
+
+		entry->cur_page = entry->pagesize ? 512 : 1;
+	}
+
+	hdr->cur_entry = idx;
+}
+
+static int snp_complete_one_psc(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct psc_buffer *psc = svm->sev_es.ghcb_sa;
+
+	if (vcpu->run->hypercall.ret) {
+		snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC);
+		return 1; /* resume guest */
+	}
+
+	__snp_complete_one_psc(svm);
+
+	/* Handle the next range (if any). */
+	return snp_begin_psc(svm, psc);
+}
+
+static int snp_begin_psc(struct vcpu_svm *svm, struct psc_buffer *psc)
+{
+	struct psc_entry *entries = psc->entries;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct psc_hdr *hdr = &psc->hdr;
+	struct psc_entry entry_start;
+	u16 idx, idx_start, idx_end;
+	int npages;
+	bool huge;
+	u64 gfn;
+
+	if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) {
+		snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC);
+		return 1;
+	}
+
+next_range:
+	/* There should be no other PSCs in-flight at this point. */
+	if (WARN_ON_ONCE(svm->sev_es.psc_inflight)) {
+		snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC);
+		return 1;
+	}
+
+	/*
+	 * The PSC descriptor buffer can be modified by a misbehaved guest after
+	 * validation, so take care to only use validated copies of values used
+	 * for things like array indexing.
+	 */
+	idx_start = hdr->cur_entry;
+	idx_end = hdr->end_entry;
+
+	if (idx_end >= VMGEXIT_PSC_MAX_COUNT) {
+		snp_complete_psc(svm, VMGEXIT_PSC_ERROR_INVALID_HDR);
+		return 1;
+	}
+
+	/* Find the start of the next range which needs processing. */
+	for (idx = idx_start; idx <= idx_end; idx++, hdr->cur_entry++) {
+		entry_start = entries[idx];
+
+		gfn = entry_start.gfn;
+		huge = entry_start.pagesize;
+		npages = huge ? 512 : 1;
+
+		if (entry_start.cur_page > npages || !IS_ALIGNED(gfn, npages)) {
+			snp_complete_psc(svm, VMGEXIT_PSC_ERROR_INVALID_ENTRY);
+			return 1;
+		}
+
+		if (entry_start.cur_page) {
+			/*
+			 * If this is a partially-completed 2M range, force 4K handling
+			 * for the remaining pages since they're effectively split at
+			 * this point. Subsequent code should ensure this doesn't get
+			 * combined with adjacent PSC entries where 2M handling is still
+			 * possible.
+			 */
+			npages -= entry_start.cur_page;
+			gfn += entry_start.cur_page;
+			huge = false;
+		}
+
+		if (npages)
+			break;
+	}
+
+	if (idx > idx_end) {
+		/* Nothing more to process. */
+		snp_complete_psc(svm, 0);
+		return 1;
+	}
+
+	svm->sev_es.psc_2m = huge;
+	svm->sev_es.psc_idx = idx;
+	svm->sev_es.psc_inflight = 1;
+
+	/*
+	 * Find all subsequent PSC entries that contain adjacent GPA
+	 * ranges/operations and can be combined into a single
+	 * KVM_HC_MAP_GPA_RANGE exit.
+	 */
+	while (++idx <= idx_end) {
+		struct psc_entry entry = entries[idx];
+
+		if (entry.operation != entry_start.operation ||
+		    entry.gfn != entry_start.gfn + npages ||
+		    entry.cur_page || !!entry.pagesize != huge)
+			break;
+
+		svm->sev_es.psc_inflight++;
+		npages += huge ? 512 : 1;
+	}
+
+	switch (entry_start.operation) {
+	case VMGEXIT_PSC_OP_PRIVATE:
+	case VMGEXIT_PSC_OP_SHARED:
+		vcpu->run->exit_reason = KVM_EXIT_HYPERCALL;
+		vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE;
+		vcpu->run->hypercall.args[0] = gfn_to_gpa(gfn);
+		vcpu->run->hypercall.args[1] = npages;
+		vcpu->run->hypercall.args[2] = entry_start.operation == VMGEXIT_PSC_OP_PRIVATE
+					       ? KVM_MAP_GPA_RANGE_ENCRYPTED
+					       : KVM_MAP_GPA_RANGE_DECRYPTED;
+		vcpu->run->hypercall.args[2] |= entry_start.pagesize
+						? KVM_MAP_GPA_RANGE_PAGE_SZ_2M
+						: KVM_MAP_GPA_RANGE_PAGE_SZ_4K;
+		vcpu->arch.complete_userspace_io = snp_complete_one_psc;
+		return 0; /* forward request to userspace */
+	default:
+		/*
+		 * Only shared/private PSC operations are currently supported, so if the
+		 * entire range consists of unsupported operations (e.g. SMASH/UNSMASH),
+		 * then consider the entire range completed and avoid exiting to
+		 * userspace. In theory snp_complete_psc() can always be called directly
+		 * at this point to complete the current range and start the next one,
+		 * but that could lead to unexpected levels of recursion.
+		 */
+		__snp_complete_one_psc(svm);
+		goto next_range;
+	}
+
+	unreachable();
+}
+
 static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -3761,6 +3942,13 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		vcpu->run->system_event.ndata = 1;
 		vcpu->run->system_event.data[0] = control->ghcb_gpa;
 		break;
+	case SVM_VMGEXIT_PSC:
+		ret = setup_vmgexit_scratch(svm, true, control->exit_info_2);
+		if (ret)
+			break;
+
+		ret = snp_begin_psc(svm, svm->sev_es.ghcb_sa);
+		break;
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		vcpu_unimpl(vcpu,
 			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 202ac5494c19..32d37ef5f580 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -210,6 +210,11 @@ struct vcpu_sev_es_state {
 	bool ghcb_sa_sync;
 	bool ghcb_sa_free;
 
+	/* SNP Page-State-Change buffer entries currently being processed */
+	u16 psc_idx;
+	u16 psc_inflight;
+	bool psc_2m;
+
 	u64 ghcb_registered_gpa;
 };
 
-- 
cgit v1.2.3-58-ga151


From c63cf135cc996fc88be95a9ba8b80e3cff8d275b Mon Sep 17 00:00:00 2001
From: Brijesh Singh <brijesh.singh@amd.com>
Date: Wed, 1 May 2024 03:52:01 -0500
Subject: KVM: SEV: Add support to handle RMP nested page faults

When SEV-SNP is enabled in the guest, the hardware places restrictions
on all memory accesses based on the contents of the RMP table. When
hardware encounters RMP check failure caused by the guest memory access
it raises the #NPF. The error code contains additional information on
the access type. See the APM volume 2 for additional information.

When using gmem, RMP faults resulting from mismatches between the state
in the RMP table vs. what the guest expects via its page table result
in KVM_EXIT_MEMORY_FAULTs being forwarded to userspace to handle. This
means the only expected case that needs to be handled in the kernel is
when the page size of the entry in the RMP table is larger than the
mapping in the nested page table, in which case a PSMASH instruction
needs to be issued to split the large RMP entry into individual 4K
entries so that subsequent accesses can succeed.

Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Message-ID: <20240501085210.2213060-12-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |   1 +
 arch/x86/include/asm/sev.h      |   3 ++
 arch/x86/kvm/mmu.h              |   2 -
 arch/x86/kvm/mmu/mmu.c          |   1 +
 arch/x86/kvm/svm/sev.c          | 109 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c          |  14 ++++--
 arch/x86/kvm/svm/svm.h          |   3 ++
 arch/x86/kvm/trace.h            |  31 ++++++++++++
 arch/x86/kvm/x86.c              |   1 +
 9 files changed, 159 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 8340fe9c4459..80dfcdab87eb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1942,6 +1942,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 				   const struct kvm_memory_slot *memslot);
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
+void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end);
 
 int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
 
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 93ed60080cfe..14394407245c 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -91,6 +91,9 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
 /* RMUPDATE detected 4K page and 2MB page overlap. */
 #define RMPUPDATE_FAIL_OVERLAP		4
 
+/* PSMASH failed due to concurrent access by another CPU */
+#define PSMASH_FAIL_INUSE		3
+
 /* RMP page size */
 #define RMP_PG_SIZE_4K			0
 #define RMP_PG_SIZE_2M			1
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 2e454316f2a2..dc80e72e4848 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -253,8 +253,6 @@ static inline bool kvm_mmu_honors_guest_mtrrs(struct kvm *kvm)
 	return __kvm_mmu_honors_guest_mtrrs(kvm_arch_has_noncoherent_dma(kvm));
 }
 
-void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end);
-
 int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
 
 int kvm_mmu_post_init_vm(struct kvm *kvm);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index b68151eec4b4..5095fb46713e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6802,6 +6802,7 @@ restart:
 
 	return need_tlb_flush;
 }
+EXPORT_SYMBOL_GPL(kvm_zap_gfn_range);
 
 static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm,
 					   const struct kvm_memory_slot *slot)
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 122219b3d3b7..f01cee8278ab 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3465,6 +3465,23 @@ static void set_ghcb_msr(struct vcpu_svm *svm, u64 value)
 	svm->vmcb->control.ghcb_gpa = value;
 }
 
+static int snp_rmptable_psmash(kvm_pfn_t pfn)
+{
+	int ret;
+
+	pfn = pfn & ~(KVM_PAGES_PER_HPAGE(PG_LEVEL_2M) - 1);
+
+	/*
+	 * PSMASH_FAIL_INUSE indicates another processor is modifying the
+	 * entry, so retry until that's no longer the case.
+	 */
+	do {
+		ret = psmash(pfn);
+	} while (ret == PSMASH_FAIL_INUSE);
+
+	return ret;
+}
+
 static int snp_complete_psc_msr(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -4229,3 +4246,95 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
 
 	return p;
 }
+
+void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
+{
+	struct kvm_memory_slot *slot;
+	struct kvm *kvm = vcpu->kvm;
+	int order, rmp_level, ret;
+	bool assigned;
+	kvm_pfn_t pfn;
+	gfn_t gfn;
+
+	gfn = gpa >> PAGE_SHIFT;
+
+	/*
+	 * The only time RMP faults occur for shared pages is when the guest is
+	 * triggering an RMP fault for an implicit page-state change from
+	 * shared->private. Implicit page-state changes are forwarded to
+	 * userspace via KVM_EXIT_MEMORY_FAULT events, however, so RMP faults
+	 * for shared pages should not end up here.
+	 */
+	if (!kvm_mem_is_private(kvm, gfn)) {
+		pr_warn_ratelimited("SEV: Unexpected RMP fault for non-private GPA 0x%llx\n",
+				    gpa);
+		return;
+	}
+
+	slot = gfn_to_memslot(kvm, gfn);
+	if (!kvm_slot_can_be_private(slot)) {
+		pr_warn_ratelimited("SEV: Unexpected RMP fault, non-private slot for GPA 0x%llx\n",
+				    gpa);
+		return;
+	}
+
+	ret = kvm_gmem_get_pfn(kvm, slot, gfn, &pfn, &order);
+	if (ret) {
+		pr_warn_ratelimited("SEV: Unexpected RMP fault, no backing page for private GPA 0x%llx\n",
+				    gpa);
+		return;
+	}
+
+	ret = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
+	if (ret || !assigned) {
+		pr_warn_ratelimited("SEV: Unexpected RMP fault, no assigned RMP entry found for GPA 0x%llx PFN 0x%llx error %d\n",
+				    gpa, pfn, ret);
+		goto out_no_trace;
+	}
+
+	/*
+	 * There are 2 cases where a PSMASH may be needed to resolve an #NPF
+	 * with PFERR_GUEST_RMP_BIT set:
+	 *
+	 * 1) RMPADJUST/PVALIDATE can trigger an #NPF with PFERR_GUEST_SIZEM
+	 *    bit set if the guest issues them with a smaller granularity than
+	 *    what is indicated by the page-size bit in the 2MB RMP entry for
+	 *    the PFN that backs the GPA.
+	 *
+	 * 2) Guest access via NPT can trigger an #NPF if the NPT mapping is
+	 *    smaller than what is indicated by the 2MB RMP entry for the PFN
+	 *    that backs the GPA.
+	 *
+	 * In both these cases, the corresponding 2M RMP entry needs to
+	 * be PSMASH'd to 512 4K RMP entries.  If the RMP entry is already
+	 * split into 4K RMP entries, then this is likely a spurious case which
+	 * can occur when there are concurrent accesses by the guest to a 2MB
+	 * GPA range that is backed by a 2MB-aligned PFN who's RMP entry is in
+	 * the process of being PMASH'd into 4K entries. These cases should
+	 * resolve automatically on subsequent accesses, so just ignore them
+	 * here.
+	 */
+	if (rmp_level == PG_LEVEL_4K)
+		goto out;
+
+	ret = snp_rmptable_psmash(pfn);
+	if (ret) {
+		/*
+		 * Look it up again. If it's 4K now then the PSMASH may have
+		 * raced with another process and the issue has already resolved
+		 * itself.
+		 */
+		if (!snp_lookup_rmpentry(pfn, &assigned, &rmp_level) &&
+		    assigned && rmp_level == PG_LEVEL_4K)
+			goto out;
+
+		pr_warn_ratelimited("SEV: Unable to split RMP entry for GPA 0x%llx PFN 0x%llx ret %d\n",
+				    gpa, pfn, ret);
+	}
+
+	kvm_zap_gfn_range(kvm, gfn, gfn + PTRS_PER_PMD);
+out:
+	trace_kvm_rmp_fault(vcpu, gpa, pfn, error_code, rmp_level, ret);
+out_no_trace:
+	put_page(pfn_to_page(pfn));
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 66d5e2e46a66..bdaf39571817 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2044,6 +2044,7 @@ static int pf_interception(struct kvm_vcpu *vcpu)
 static int npf_interception(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	int rc;
 
 	u64 fault_address = svm->vmcb->control.exit_info_2;
 	u64 error_code = svm->vmcb->control.exit_info_1;
@@ -2061,10 +2062,15 @@ static int npf_interception(struct kvm_vcpu *vcpu)
 		error_code |= PFERR_PRIVATE_ACCESS;
 
 	trace_kvm_page_fault(vcpu, fault_address, error_code);
-	return kvm_mmu_page_fault(vcpu, fault_address, error_code,
-			static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
-			svm->vmcb->control.insn_bytes : NULL,
-			svm->vmcb->control.insn_len);
+	rc = kvm_mmu_page_fault(vcpu, fault_address, error_code,
+				static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
+				svm->vmcb->control.insn_bytes : NULL,
+				svm->vmcb->control.insn_len);
+
+	if (rc > 0 && error_code & PFERR_GUEST_RMP_MASK)
+		sev_handle_rmp_fault(vcpu, fault_address, error_code);
+
+	return rc;
 }
 
 static int db_interception(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 32d37ef5f580..36b573427b85 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -728,6 +728,7 @@ void sev_hardware_unsetup(void);
 int sev_cpu_init(struct svm_cpu_data *sd);
 int sev_dev_get_attr(u32 group, u64 attr, u64 *val);
 extern unsigned int max_sev_asid;
+void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code);
 #else
 static inline struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) {
 	return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
@@ -741,6 +742,8 @@ static inline void sev_hardware_unsetup(void) {}
 static inline int sev_cpu_init(struct svm_cpu_data *sd) { return 0; }
 static inline int sev_dev_get_attr(u32 group, u64 attr, u64 *val) { return -ENXIO; }
 #define max_sev_asid 0
+static inline void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code) {}
+
 #endif
 
 /* vmenter.S */
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 9d0b02ef307e..f2ff6cc96854 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1834,6 +1834,37 @@ TRACE_EVENT(kvm_vmgexit_msr_protocol_exit,
 		  __entry->vcpu_id, __entry->ghcb_gpa, __entry->result)
 );
 
+/*
+ * Tracepoint for #NPFs due to RMP faults.
+ */
+TRACE_EVENT(kvm_rmp_fault,
+	TP_PROTO(struct kvm_vcpu *vcpu, u64 gpa, u64 pfn, u64 error_code,
+		 int rmp_level, int psmash_ret),
+	TP_ARGS(vcpu, gpa, pfn, error_code, rmp_level, psmash_ret),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, vcpu_id)
+		__field(u64, gpa)
+		__field(u64, pfn)
+		__field(u64, error_code)
+		__field(int, rmp_level)
+		__field(int, psmash_ret)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id	= vcpu->vcpu_id;
+		__entry->gpa		= gpa;
+		__entry->pfn		= pfn;
+		__entry->error_code	= error_code;
+		__entry->rmp_level	= rmp_level;
+		__entry->psmash_ret	= psmash_ret;
+	),
+
+	TP_printk("vcpu %u gpa %016llx pfn 0x%llx error_code 0x%llx rmp_level %d psmash_ret %d",
+		  __entry->vcpu_id, __entry->gpa, __entry->pfn,
+		  __entry->error_code, __entry->rmp_level, __entry->psmash_ret)
+);
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4b9ee2ca5675..a143c26a9221 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13997,6 +13997,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_enter);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault);
 
 static int __init kvm_x86_init(void)
 {
-- 
cgit v1.2.3-58-ga151


From e366f92ea99e1961fbad5e2110900e9f4fcb249b Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Wed, 1 May 2024 03:52:02 -0500
Subject: KVM: SEV: Support SEV-SNP AP Creation NAE event

Add support for the SEV-SNP AP Creation NAE event. This allows SEV-SNP
guests to alter the register state of the APs on their own. This allows
the guest a way of simulating INIT-SIPI.

A new event, KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, is created and used
so as to avoid updating the VMSA pointer while the vCPU is running.

For CREATE
  The guest supplies the GPA of the VMSA to be used for the vCPU with
  the specified APIC ID. The GPA is saved in the svm struct of the
  target vCPU, the KVM_REQ_UPDATE_PROTECTED_GUEST_STATE event is added
  to the vCPU and then the vCPU is kicked.

For CREATE_ON_INIT:
  The guest supplies the GPA of the VMSA to be used for the vCPU with
  the specified APIC ID the next time an INIT is performed. The GPA is
  saved in the svm struct of the target vCPU.

For DESTROY:
  The guest indicates it wishes to stop the vCPU. The GPA is cleared
  from the svm struct, the KVM_REQ_UPDATE_PROTECTED_GUEST_STATE event is
  added to vCPU and then the vCPU is kicked.

The KVM_REQ_UPDATE_PROTECTED_GUEST_STATE event handler will be invoked
as a result of the event or as a result of an INIT. If a new VMSA is to
be installed, the VMSA guest page is set as the VMSA in the vCPU VMCB
and the vCPU state is set to KVM_MP_STATE_RUNNABLE. If a new VMSA is not
to be installed, the VMSA is cleared in the vCPU VMCB and the vCPU state
is set to KVM_MP_STATE_HALTED to prevent it from being run.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Message-ID: <20240501085210.2213060-13-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |   1 +
 arch/x86/include/asm/svm.h      |   6 ++
 arch/x86/kvm/svm/sev.c          | 231 +++++++++++++++++++++++++++++++++++++++-
 arch/x86/kvm/svm/svm.c          |  11 +-
 arch/x86/kvm/svm/svm.h          |   9 ++
 arch/x86/kvm/x86.c              |  11 ++
 6 files changed, 266 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 80dfcdab87eb..aabf1648a56a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -121,6 +121,7 @@
 	KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_HV_TLB_FLUSH \
 	KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE	KVM_ARCH_REQ(34)
 
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 544a43c1cf11..f0dea3750ca9 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -286,8 +286,14 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_
 #define AVIC_HPA_MASK	~((0xFFFULL << 52) | 0xFFF)
 
 #define SVM_SEV_FEAT_SNP_ACTIVE				BIT(0)
+#define SVM_SEV_FEAT_RESTRICTED_INJECTION		BIT(3)
+#define SVM_SEV_FEAT_ALTERNATE_INJECTION		BIT(4)
 #define SVM_SEV_FEAT_DEBUG_SWAP				BIT(5)
 
+#define SVM_SEV_FEAT_INT_INJ_MODES		\
+	(SVM_SEV_FEAT_RESTRICTED_INJECTION |	\
+	 SVM_SEV_FEAT_ALTERNATE_INJECTION)
+
 struct vmcb_seg {
 	u16 selector;
 	u16 attrib;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index f01cee8278ab..0c1108ffc4ae 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -38,7 +38,7 @@
 #define GHCB_VERSION_DEFAULT	2ULL
 #define GHCB_VERSION_MIN	1ULL
 
-#define GHCB_HV_FT_SUPPORTED	GHCB_HV_FT_SNP
+#define GHCB_HV_FT_SUPPORTED	(GHCB_HV_FT_SNP | GHCB_HV_FT_SNP_AP_CREATION)
 
 /* enable/disable SEV support */
 static bool sev_enabled = true;
@@ -3267,6 +3267,13 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 		if (!kvm_ghcb_sw_scratch_is_valid(svm))
 			goto vmgexit_err;
 		break;
+	case SVM_VMGEXIT_AP_CREATION:
+		if (!sev_snp_guest(vcpu->kvm))
+			goto vmgexit_err;
+		if (lower_32_bits(control->exit_info_1) != SVM_VMGEXIT_AP_DESTROY)
+			if (!kvm_ghcb_rax_is_valid(svm))
+				goto vmgexit_err;
+		break;
 	case SVM_VMGEXIT_NMI_COMPLETE:
 	case SVM_VMGEXIT_AP_HLT_LOOP:
 	case SVM_VMGEXIT_AP_JUMP_TABLE:
@@ -3701,6 +3708,205 @@ next_range:
 	unreachable();
 }
 
+static int __sev_snp_update_protected_guest_state(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	WARN_ON(!mutex_is_locked(&svm->sev_es.snp_vmsa_mutex));
+
+	/* Mark the vCPU as offline and not runnable */
+	vcpu->arch.pv.pv_unhalted = false;
+	vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+
+	/* Clear use of the VMSA */
+	svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+
+	if (VALID_PAGE(svm->sev_es.snp_vmsa_gpa)) {
+		gfn_t gfn = gpa_to_gfn(svm->sev_es.snp_vmsa_gpa);
+		struct kvm_memory_slot *slot;
+		kvm_pfn_t pfn;
+
+		slot = gfn_to_memslot(vcpu->kvm, gfn);
+		if (!slot)
+			return -EINVAL;
+
+		/*
+		 * The new VMSA will be private memory guest memory, so
+		 * retrieve the PFN from the gmem backend.
+		 */
+		if (kvm_gmem_get_pfn(vcpu->kvm, slot, gfn, &pfn, NULL))
+			return -EINVAL;
+
+		/*
+		 * From this point forward, the VMSA will always be a
+		 * guest-mapped page rather than the initial one allocated
+		 * by KVM in svm->sev_es.vmsa. In theory, svm->sev_es.vmsa
+		 * could be free'd and cleaned up here, but that involves
+		 * cleanups like wbinvd_on_all_cpus() which would ideally
+		 * be handled during teardown rather than guest boot.
+		 * Deferring that also allows the existing logic for SEV-ES
+		 * VMSAs to be re-used with minimal SNP-specific changes.
+		 */
+		svm->sev_es.snp_has_guest_vmsa = true;
+
+		/* Use the new VMSA */
+		svm->vmcb->control.vmsa_pa = pfn_to_hpa(pfn);
+
+		/* Mark the vCPU as runnable */
+		vcpu->arch.pv.pv_unhalted = false;
+		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+
+		svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
+
+		/*
+		 * gmem pages aren't currently migratable, but if this ever
+		 * changes then care should be taken to ensure
+		 * svm->sev_es.vmsa is pinned through some other means.
+		 */
+		kvm_release_pfn_clean(pfn);
+	}
+
+	/*
+	 * When replacing the VMSA during SEV-SNP AP creation,
+	 * mark the VMCB dirty so that full state is always reloaded.
+	 */
+	vmcb_mark_all_dirty(svm->vmcb);
+
+	return 0;
+}
+
+/*
+ * Invoked as part of svm_vcpu_reset() processing of an init event.
+ */
+void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	int ret;
+
+	if (!sev_snp_guest(vcpu->kvm))
+		return;
+
+	mutex_lock(&svm->sev_es.snp_vmsa_mutex);
+
+	if (!svm->sev_es.snp_ap_waiting_for_reset)
+		goto unlock;
+
+	svm->sev_es.snp_ap_waiting_for_reset = false;
+
+	ret = __sev_snp_update_protected_guest_state(vcpu);
+	if (ret)
+		vcpu_unimpl(vcpu, "snp: AP state update on init failed\n");
+
+unlock:
+	mutex_unlock(&svm->sev_es.snp_vmsa_mutex);
+}
+
+static int sev_snp_ap_creation(struct vcpu_svm *svm)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct kvm_vcpu *target_vcpu;
+	struct vcpu_svm *target_svm;
+	unsigned int request;
+	unsigned int apic_id;
+	bool kick;
+	int ret;
+
+	request = lower_32_bits(svm->vmcb->control.exit_info_1);
+	apic_id = upper_32_bits(svm->vmcb->control.exit_info_1);
+
+	/* Validate the APIC ID */
+	target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, apic_id);
+	if (!target_vcpu) {
+		vcpu_unimpl(vcpu, "vmgexit: invalid AP APIC ID [%#x] from guest\n",
+			    apic_id);
+		return -EINVAL;
+	}
+
+	ret = 0;
+
+	target_svm = to_svm(target_vcpu);
+
+	/*
+	 * The target vCPU is valid, so the vCPU will be kicked unless the
+	 * request is for CREATE_ON_INIT. For any errors at this stage, the
+	 * kick will place the vCPU in an non-runnable state.
+	 */
+	kick = true;
+
+	mutex_lock(&target_svm->sev_es.snp_vmsa_mutex);
+
+	target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
+	target_svm->sev_es.snp_ap_waiting_for_reset = true;
+
+	/* Interrupt injection mode shouldn't change for AP creation */
+	if (request < SVM_VMGEXIT_AP_DESTROY) {
+		u64 sev_features;
+
+		sev_features = vcpu->arch.regs[VCPU_REGS_RAX];
+		sev_features ^= sev->vmsa_features;
+
+		if (sev_features & SVM_SEV_FEAT_INT_INJ_MODES) {
+			vcpu_unimpl(vcpu, "vmgexit: invalid AP injection mode [%#lx] from guest\n",
+				    vcpu->arch.regs[VCPU_REGS_RAX]);
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	switch (request) {
+	case SVM_VMGEXIT_AP_CREATE_ON_INIT:
+		kick = false;
+		fallthrough;
+	case SVM_VMGEXIT_AP_CREATE:
+		if (!page_address_valid(vcpu, svm->vmcb->control.exit_info_2)) {
+			vcpu_unimpl(vcpu, "vmgexit: invalid AP VMSA address [%#llx] from guest\n",
+				    svm->vmcb->control.exit_info_2);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		/*
+		 * Malicious guest can RMPADJUST a large page into VMSA which
+		 * will hit the SNP erratum where the CPU will incorrectly signal
+		 * an RMP violation #PF if a hugepage collides with the RMP entry
+		 * of VMSA page, reject the AP CREATE request if VMSA address from
+		 * guest is 2M aligned.
+		 */
+		if (IS_ALIGNED(svm->vmcb->control.exit_info_2, PMD_SIZE)) {
+			vcpu_unimpl(vcpu,
+				    "vmgexit: AP VMSA address [%llx] from guest is unsafe as it is 2M aligned\n",
+				    svm->vmcb->control.exit_info_2);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		target_svm->sev_es.snp_vmsa_gpa = svm->vmcb->control.exit_info_2;
+		break;
+	case SVM_VMGEXIT_AP_DESTROY:
+		break;
+	default:
+		vcpu_unimpl(vcpu, "vmgexit: invalid AP creation request [%#x] from guest\n",
+			    request);
+		ret = -EINVAL;
+		break;
+	}
+
+out:
+	if (kick) {
+		kvm_make_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
+
+		if (target_vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)
+			kvm_make_request(KVM_REQ_UNBLOCK, target_vcpu);
+
+		kvm_vcpu_kick(target_vcpu);
+	}
+
+	mutex_unlock(&target_svm->sev_es.snp_vmsa_mutex);
+
+	return ret;
+}
+
 static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -3966,6 +4172,15 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 
 		ret = snp_begin_psc(svm, svm->sev_es.ghcb_sa);
 		break;
+	case SVM_VMGEXIT_AP_CREATION:
+		ret = sev_snp_ap_creation(svm);
+		if (ret) {
+			ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
+			ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT);
+		}
+
+		ret = 1;
+		break;
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		vcpu_unimpl(vcpu,
 			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
@@ -4060,7 +4275,7 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	 * the VMSA will be NULL if this vCPU is the destination for intrahost
 	 * migration, and will be copied later.
 	 */
-	if (svm->sev_es.vmsa)
+	if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
 		svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
 
 	/* Can't intercept CR register access, HV can't modify CR registers */
@@ -4136,6 +4351,8 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm)
 	set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version,
 					    GHCB_VERSION_MIN,
 					    sev_enc_bit));
+
+	mutex_init(&svm->sev_es.snp_vmsa_mutex);
 }
 
 void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa)
@@ -4247,6 +4464,16 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
 	return p;
 }
 
+void sev_vcpu_unblocking(struct kvm_vcpu *vcpu)
+{
+	if (!sev_snp_guest(vcpu->kvm))
+		return;
+
+	if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu) &&
+	    vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)
+		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+}
+
 void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
 {
 	struct kvm_memory_slot *slot;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index bdaf39571817..546656606b44 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1398,6 +1398,9 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	svm->spec_ctrl = 0;
 	svm->virt_spec_ctrl = 0;
 
+	if (init_event)
+		sev_snp_init_protected_guest_state(vcpu);
+
 	init_vmcb(vcpu);
 
 	if (!init_event)
@@ -4940,6 +4943,12 @@ static void *svm_alloc_apic_backing_page(struct kvm_vcpu *vcpu)
 	return page_address(page);
 }
 
+static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu)
+{
+	sev_vcpu_unblocking(vcpu);
+	avic_vcpu_unblocking(vcpu);
+}
+
 static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.name = KBUILD_MODNAME,
 
@@ -4962,7 +4971,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.vcpu_load = svm_vcpu_load,
 	.vcpu_put = svm_vcpu_put,
 	.vcpu_blocking = avic_vcpu_blocking,
-	.vcpu_unblocking = avic_vcpu_unblocking,
+	.vcpu_unblocking = svm_vcpu_unblocking,
 
 	.update_exception_bitmap = svm_update_exception_bitmap,
 	.get_msr_feature = svm_get_msr_feature,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 36b573427b85..926bfce571a6 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -216,6 +216,11 @@ struct vcpu_sev_es_state {
 	bool psc_2m;
 
 	u64 ghcb_registered_gpa;
+
+	struct mutex snp_vmsa_mutex; /* Used to handle concurrent updates of VMSA. */
+	gpa_t snp_vmsa_gpa;
+	bool snp_ap_waiting_for_reset;
+	bool snp_has_guest_vmsa;
 };
 
 struct vcpu_svm {
@@ -729,6 +734,8 @@ int sev_cpu_init(struct svm_cpu_data *sd);
 int sev_dev_get_attr(u32 group, u64 attr, u64 *val);
 extern unsigned int max_sev_asid;
 void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code);
+void sev_vcpu_unblocking(struct kvm_vcpu *vcpu);
+void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
 #else
 static inline struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) {
 	return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
@@ -743,6 +750,8 @@ static inline int sev_cpu_init(struct svm_cpu_data *sd) { return 0; }
 static inline int sev_dev_get_attr(u32 group, u64 attr, u64 *val) { return -ENXIO; }
 #define max_sev_asid 0
 static inline void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code) {}
+static inline void sev_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
+static inline void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) {}
 
 #endif
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a143c26a9221..d29477910ffa 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10939,6 +10939,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 		if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu))
 			static_call(kvm_x86_update_cpu_dirty_logging)(vcpu);
+
+		if (kvm_check_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) {
+			kvm_vcpu_reset(vcpu, true);
+			if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE) {
+				r = 1;
+				goto out;
+			}
+		}
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win ||
@@ -13146,6 +13154,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 	if (kvm_test_request(KVM_REQ_PMI, vcpu))
 		return true;
 
+	if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu))
+		return true;
+
 	if (kvm_arch_interrupt_allowed(vcpu) &&
 	    (kvm_cpu_has_interrupt(vcpu) ||
 	    kvm_guest_apic_has_interrupt(vcpu)))
-- 
cgit v1.2.3-58-ga151


From 4f2e7aa1cfdf4374a4c876c9358e0d7035647eb1 Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Wed, 1 May 2024 03:52:03 -0500
Subject: KVM: SEV: Implement gmem hook for initializing private pages

This will handle the RMP table updates needed to put a page into a
private state before mapping it into an SEV-SNP guest.

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-ID: <20240501085210.2213060-14-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/Kconfig   |  1 +
 arch/x86/kvm/svm/sev.c | 98 ++++++++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c |  2 ++
 arch/x86/kvm/svm/svm.h |  5 +++
 arch/x86/kvm/x86.c     |  5 +++
 virt/kvm/guest_memfd.c |  4 +--
 6 files changed, 113 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 5e72faca4e8f..10768f13b240 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -137,6 +137,7 @@ config KVM_AMD_SEV
 	depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
 	select ARCH_HAS_CC_PLATFORM
 	select KVM_GENERIC_PRIVATE_MEM
+	select HAVE_KVM_GMEM_PREPARE
 	help
 	  Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
 	  with Encrypted State (SEV-ES) on AMD processors.
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0c1108ffc4ae..0ed6b96c01c3 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4565,3 +4565,101 @@ out:
 out_no_trace:
 	put_page(pfn_to_page(pfn));
 }
+
+static bool is_pfn_range_shared(kvm_pfn_t start, kvm_pfn_t end)
+{
+	kvm_pfn_t pfn = start;
+
+	while (pfn < end) {
+		int ret, rmp_level;
+		bool assigned;
+
+		ret = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
+		if (ret) {
+			pr_warn_ratelimited("SEV: Failed to retrieve RMP entry: PFN 0x%llx GFN start 0x%llx GFN end 0x%llx RMP level %d error %d\n",
+					    pfn, start, end, rmp_level, ret);
+			return false;
+		}
+
+		if (assigned) {
+			pr_debug("%s: overlap detected, PFN 0x%llx start 0x%llx end 0x%llx RMP level %d\n",
+				 __func__, pfn, start, end, rmp_level);
+			return false;
+		}
+
+		pfn++;
+	}
+
+	return true;
+}
+
+static u8 max_level_for_order(int order)
+{
+	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
+		return PG_LEVEL_2M;
+
+	return PG_LEVEL_4K;
+}
+
+static bool is_large_rmp_possible(struct kvm *kvm, kvm_pfn_t pfn, int order)
+{
+	kvm_pfn_t pfn_aligned = ALIGN_DOWN(pfn, PTRS_PER_PMD);
+
+	/*
+	 * If this is a large folio, and the entire 2M range containing the
+	 * PFN is currently shared, then the entire 2M-aligned range can be
+	 * set to private via a single 2M RMP entry.
+	 */
+	if (max_level_for_order(order) > PG_LEVEL_4K &&
+	    is_pfn_range_shared(pfn_aligned, pfn_aligned + PTRS_PER_PMD))
+		return true;
+
+	return false;
+}
+
+int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	kvm_pfn_t pfn_aligned;
+	gfn_t gfn_aligned;
+	int level, rc;
+	bool assigned;
+
+	if (!sev_snp_guest(kvm))
+		return 0;
+
+	rc = snp_lookup_rmpentry(pfn, &assigned, &level);
+	if (rc) {
+		pr_err_ratelimited("SEV: Failed to look up RMP entry: GFN %llx PFN %llx error %d\n",
+				   gfn, pfn, rc);
+		return -ENOENT;
+	}
+
+	if (assigned) {
+		pr_debug("%s: already assigned: gfn %llx pfn %llx max_order %d level %d\n",
+			 __func__, gfn, pfn, max_order, level);
+		return 0;
+	}
+
+	if (is_large_rmp_possible(kvm, pfn, max_order)) {
+		level = PG_LEVEL_2M;
+		pfn_aligned = ALIGN_DOWN(pfn, PTRS_PER_PMD);
+		gfn_aligned = ALIGN_DOWN(gfn, PTRS_PER_PMD);
+	} else {
+		level = PG_LEVEL_4K;
+		pfn_aligned = pfn;
+		gfn_aligned = gfn;
+	}
+
+	rc = rmp_make_private(pfn_aligned, gfn_to_gpa(gfn_aligned), level, sev->asid, false);
+	if (rc) {
+		pr_err_ratelimited("SEV: Failed to update RMP entry: GFN %llx PFN %llx level %d error %d\n",
+				   gfn, pfn, level, rc);
+		return -EINVAL;
+	}
+
+	pr_debug("%s: updated: gfn %llx pfn %llx pfn_aligned %llx max_order %d level %d\n",
+		 __func__, gfn, pfn, pfn_aligned, max_order, level);
+
+	return 0;
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 546656606b44..b9ecc06f8934 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -5081,6 +5081,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
 	.vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons,
 	.alloc_apic_backing_page = svm_alloc_apic_backing_page,
+
+	.gmem_prepare = sev_gmem_prepare,
 };
 
 /*
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 926bfce571a6..4203bd9012e9 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -736,6 +736,7 @@ extern unsigned int max_sev_asid;
 void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code);
 void sev_vcpu_unblocking(struct kvm_vcpu *vcpu);
 void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
+int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
 #else
 static inline struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) {
 	return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
@@ -752,6 +753,10 @@ static inline int sev_dev_get_attr(u32 group, u64 attr, u64 *val) { return -ENXI
 static inline void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code) {}
 static inline void sev_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 static inline void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) {}
+static inline int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order)
+{
+	return 0;
+}
 
 #endif
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d29477910ffa..d750546ec934 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13611,6 +13611,11 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
 
 #ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+bool kvm_arch_gmem_prepare_needed(struct kvm *kvm)
+{
+	return kvm->arch.vm_type == KVM_X86_SNP_VM;
+}
+
 int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order)
 {
 	return static_call(kvm_x86_gmem_prepare)(kvm, pfn, gfn, max_order);
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index dfe50c64a552..9714add38852 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -39,8 +39,8 @@ static int kvm_gmem_prepare_folio(struct inode *inode, pgoff_t index, struct fol
 		gfn = slot->base_gfn + index - slot->gmem.pgoff;
 		rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, compound_order(compound_head(page)));
 		if (rc) {
-			pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx, error %d.\n",
-					    index, rc);
+			pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx GFN %llx PFN %llx error %d.\n",
+					    index, gfn, pfn, rc);
 			return rc;
 		}
 	}
-- 
cgit v1.2.3-58-ga151


From 8eb01900b018b1bf20ce695758f30be71bd1b9ac Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Wed, 1 May 2024 03:52:04 -0500
Subject: KVM: SEV: Implement gmem hook for invalidating private pages

Implement a platform hook to do the work of restoring the direct map
entries of gmem-managed pages and transitioning the corresponding RMP
table entries back to the default shared/hypervisor-owned state.

Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-ID: <20240501085210.2213060-15-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/Kconfig   |  1 +
 arch/x86/kvm/svm/sev.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c |  1 +
 arch/x86/kvm/svm/svm.h |  2 ++
 4 files changed, 68 insertions(+)

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 10768f13b240..2a7f69abcac3 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -138,6 +138,7 @@ config KVM_AMD_SEV
 	select ARCH_HAS_CC_PLATFORM
 	select KVM_GENERIC_PRIVATE_MEM
 	select HAVE_KVM_GMEM_PREPARE
+	select HAVE_KVM_GMEM_INVALIDATE
 	help
 	  Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
 	  with Encrypted State (SEV-ES) on AMD processors.
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0ed6b96c01c3..dc00b89404a2 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4663,3 +4663,67 @@ int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order)
 
 	return 0;
 }
+
+void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
+{
+	kvm_pfn_t pfn;
+
+	pr_debug("%s: PFN start 0x%llx PFN end 0x%llx\n", __func__, start, end);
+
+	for (pfn = start; pfn < end;) {
+		bool use_2m_update = false;
+		int rc, rmp_level;
+		bool assigned;
+
+		rc = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
+		if (WARN_ONCE(rc, "SEV: Failed to retrieve RMP entry for PFN 0x%llx error %d\n",
+			      pfn, rc))
+			goto next_pfn;
+
+		if (!assigned)
+			goto next_pfn;
+
+		use_2m_update = IS_ALIGNED(pfn, PTRS_PER_PMD) &&
+				end >= (pfn + PTRS_PER_PMD) &&
+				rmp_level > PG_LEVEL_4K;
+
+		/*
+		 * If an unaligned PFN corresponds to a 2M region assigned as a
+		 * large page in the RMP table, PSMASH the region into individual
+		 * 4K RMP entries before attempting to convert a 4K sub-page.
+		 */
+		if (!use_2m_update && rmp_level > PG_LEVEL_4K) {
+			/*
+			 * This shouldn't fail, but if it does, report it, but
+			 * still try to update RMP entry to shared and pray this
+			 * was a spurious error that can be addressed later.
+			 */
+			rc = snp_rmptable_psmash(pfn);
+			WARN_ONCE(rc, "SEV: Failed to PSMASH RMP entry for PFN 0x%llx error %d\n",
+				  pfn, rc);
+		}
+
+		rc = rmp_make_shared(pfn, use_2m_update ? PG_LEVEL_2M : PG_LEVEL_4K);
+		if (WARN_ONCE(rc, "SEV: Failed to update RMP entry for PFN 0x%llx error %d\n",
+			      pfn, rc))
+			goto next_pfn;
+
+		/*
+		 * SEV-ES avoids host/guest cache coherency issues through
+		 * WBINVD hooks issued via MMU notifiers during run-time, and
+		 * KVM's VM destroy path at shutdown. Those MMU notifier events
+		 * don't cover gmem since there is no requirement to map pages
+		 * to a HVA in order to use them for a running guest. While the
+		 * shutdown path would still likely cover things for SNP guests,
+		 * userspace may also free gmem pages during run-time via
+		 * hole-punching operations on the guest_memfd, so flush the
+		 * cache entries for these pages before free'ing them back to
+		 * the host.
+		 */
+		clflush_cache_range(__va(pfn_to_hpa(pfn)),
+				    use_2m_update ? PMD_SIZE : PAGE_SIZE);
+next_pfn:
+		pfn += use_2m_update ? PTRS_PER_PMD : 1;
+		cond_resched();
+	}
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index b9ecc06f8934..653cdb23a7d1 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -5083,6 +5083,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.alloc_apic_backing_page = svm_alloc_apic_backing_page,
 
 	.gmem_prepare = sev_gmem_prepare,
+	.gmem_invalidate = sev_gmem_invalidate,
 };
 
 /*
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 4203bd9012e9..3cea024a7c18 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -737,6 +737,7 @@ void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code);
 void sev_vcpu_unblocking(struct kvm_vcpu *vcpu);
 void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
 int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
+void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
 #else
 static inline struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) {
 	return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
@@ -757,6 +758,7 @@ static inline int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, in
 {
 	return 0;
 }
+static inline void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) {}
 
 #endif
 
-- 
cgit v1.2.3-58-ga151


From b2104024f40cadd7d357981c51c6437a41d86f63 Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Wed, 1 May 2024 03:52:05 -0500
Subject: KVM: x86: Implement hook for determining max NPT mapping level

In the case of SEV-SNP, whether or not a 2MB page can be mapped via a
2MB mapping in the guest's nested page table depends on whether or not
any subpages within the range have already been initialized as private
in the RMP table. The existing mixed-attribute tracking in KVM is
insufficient here, for instance:

  - gmem allocates 2MB page
  - guest issues PVALIDATE on 2MB page
  - guest later converts a subpage to shared
  - SNP host code issues PSMASH to split 2MB RMP mapping to 4K
  - KVM MMU splits NPT mapping to 4K
  - guest later converts that shared page back to private

At this point there are no mixed attributes, and KVM would normally
allow for 2MB NPT mappings again, but this is actually not allowed
because the RMP table mappings are 4K and cannot be promoted on the
hypervisor side, so the NPT mappings must still be limited to 4K to
match this.

Implement a kvm_x86_ops.private_max_mapping_level() hook for SEV that
checks for this condition and adjusts the mapping level accordingly.

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-ID: <20240501085210.2213060-16-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 15 +++++++++++++++
 arch/x86/kvm/svm/svm.c |  1 +
 arch/x86/kvm/svm/svm.h |  5 +++++
 3 files changed, 21 insertions(+)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index dc00b89404a2..0bbbcadbac72 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4727,3 +4727,18 @@ next_pfn:
 		cond_resched();
 	}
 }
+
+int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+{
+	int level, rc;
+	bool assigned;
+
+	if (!sev_snp_guest(kvm))
+		return 0;
+
+	rc = snp_lookup_rmpentry(pfn, &assigned, &level);
+	if (rc || !assigned)
+		return PG_LEVEL_4K;
+
+	return level;
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 653cdb23a7d1..3d0549ca246f 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -5084,6 +5084,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 
 	.gmem_prepare = sev_gmem_prepare,
 	.gmem_invalidate = sev_gmem_invalidate,
+	.private_max_mapping_level = sev_private_max_mapping_level,
 };
 
 /*
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 3cea024a7c18..555c55f50298 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -738,6 +738,7 @@ void sev_vcpu_unblocking(struct kvm_vcpu *vcpu);
 void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
 int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
 void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
+int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
 #else
 static inline struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) {
 	return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
@@ -759,6 +760,10 @@ static inline int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, in
 	return 0;
 }
 static inline void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) {}
+static inline int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+{
+	return 0;
+}
 
 #endif
 
-- 
cgit v1.2.3-58-ga151


From ea262f8a7c360e71f3cb6c2151fd9bfcefd090e9 Mon Sep 17 00:00:00 2001
From: Ashish Kalra <ashish.kalra@amd.com>
Date: Wed, 1 May 2024 03:52:06 -0500
Subject: KVM: SEV: Avoid WBINVD for HVA-based MMU notifications for SNP

With SNP/guest_memfd, private/encrypted memory should not be mappable,
and MMU notifications for HVA-mapped memory will only be relevant to
unencrypted guest memory. Therefore, the rationale behind issuing a
wbinvd_on_all_cpus() in sev_guest_memory_reclaimed() should not apply
for SNP guests and can be ignored.

Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
[mdr: Add some clarifications in commit]
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-ID: <20240501085210.2213060-17-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0bbbcadbac72..a876a4186939 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3039,7 +3039,13 @@ do_wbinvd:
 
 void sev_guest_memory_reclaimed(struct kvm *kvm)
 {
-	if (!sev_guest(kvm))
+	/*
+	 * With SNP+gmem, private/encrypted memory is unreachable via the
+	 * hva-based mmu notifiers, so these events are only actually
+	 * pertaining to shared pages where there is no need to perform
+	 * the WBINVD to flush associated caches.
+	 */
+	if (!sev_guest(kvm) || sev_snp_guest(kvm))
 		return;
 
 	wbinvd_on_all_cpus();
-- 
cgit v1.2.3-58-ga151


From 6f627b425378915b6eda30908bedefc21b70b8c4 Mon Sep 17 00:00:00 2001
From: Brijesh Singh <brijesh.singh@amd.com>
Date: Wed, 1 May 2024 03:52:07 -0500
Subject: KVM: SVM: Add module parameter to enable SEV-SNP

Add a module parameter than can be used to enable or disable the SEV-SNP
feature. Now that KVM contains the support for the SNP set the GHCB
hypervisor feature flag to indicate that SNP is supported.

Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Message-ID: <20240501085210.2213060-18-michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index a876a4186939..176ba117413a 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -49,7 +49,8 @@ static bool sev_es_enabled = true;
 module_param_named(sev_es, sev_es_enabled, bool, 0444);
 
 /* enable/disable SEV-SNP support */
-static bool sev_snp_enabled;
+static bool sev_snp_enabled = true;
+module_param_named(sev_snp, sev_snp_enabled, bool, 0444);
 
 /* enable/disable SEV-ES DebugSwap support */
 static bool sev_es_debug_swap_enabled = true;
-- 
cgit v1.2.3-58-ga151


From febff040b1a6781c46b3670e73fbcb707e731e7e Mon Sep 17 00:00:00 2001
From: Michael Roth <michael.roth@amd.com>
Date: Tue, 28 May 2024 15:58:09 -0500
Subject: KVM: SEV: Automatically switch reclaimed pages to shared

Currently there's a consistent pattern of always calling
host_rmp_make_shared() immediately after snp_page_reclaim(), so go ahead
and handle it automatically as part of snp_page_reclaim(). Also rename
it to kvm_rmp_make_shared() to more easily distinguish it as a
KVM-specific variant of the more generic rmp_make_shared() helper.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 55 ++++++++++++++++++++++++++++----------------------
 1 file changed, 31 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 176ba117413a..39f8eeea5659 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -262,6 +262,21 @@ static void sev_decommission(unsigned int handle)
 	sev_guest_decommission(&decommission, NULL);
 }
 
+/*
+ * Transition a page to hypervisor-owned/shared state in the RMP table. This
+ * should not fail under normal conditions, but leak the page should that
+ * happen since it will no longer be usable by the host due to RMP protections.
+ */
+static int kvm_rmp_make_shared(struct kvm *kvm, u64 pfn, enum pg_level level)
+{
+	if (KVM_BUG_ON(rmp_make_shared(pfn, level), kvm)) {
+		snp_leak_pages(pfn, page_level_size(level) >> PAGE_SHIFT);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 /*
  * Certain page-states, such as Pre-Guest and Firmware pages (as documented
  * in Chapter 5 of the SEV-SNP Firmware ABI under "Page States") cannot be
@@ -271,32 +286,25 @@ static void sev_decommission(unsigned int handle)
  * Until they are reclaimed and subsequently transitioned via RMPUPDATE, they
  * might not be usable by the host due to being set as immutable or still
  * being associated with a guest ASID.
+ *
+ * Bug the VM and leak the page if reclaim fails, or if the RMP entry can't be
+ * converted back to shared, as the page is no longer usable due to RMP
+ * protections, and it's infeasible for the guest to continue on.
  */
-static int snp_page_reclaim(u64 pfn)
+static int snp_page_reclaim(struct kvm *kvm, u64 pfn)
 {
 	struct sev_data_snp_page_reclaim data = {0};
-	int err, rc;
+	int fw_err, rc;
 
 	data.paddr = __sme_set(pfn << PAGE_SHIFT);
-	rc = sev_do_cmd(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err);
-	if (WARN_ONCE(rc, "Failed to reclaim PFN %llx", pfn))
+	rc = sev_do_cmd(SEV_CMD_SNP_PAGE_RECLAIM, &data, &fw_err);
+	if (KVM_BUG(rc, kvm, "Failed to reclaim PFN %llx, rc %d fw_err %d", pfn, rc, fw_err)) {
 		snp_leak_pages(pfn, 1);
+		return -EIO;
+	}
 
-	return rc;
-}
-
-/*
- * Transition a page to hypervisor-owned/shared state in the RMP table. This
- * should not fail under normal conditions, but leak the page should that
- * happen since it will no longer be usable by the host due to RMP protections.
- */
-static int host_rmp_make_shared(u64 pfn, enum pg_level level)
-{
-	int rc;
-
-	rc = rmp_make_shared(pfn, level);
-	if (WARN_ON_ONCE(rc))
-		snp_leak_pages(pfn, page_level_size(level) >> PAGE_SHIFT);
+	if (kvm_rmp_make_shared(kvm, pfn, PG_LEVEL_4K))
+		return -EIO;
 
 	return rc;
 }
@@ -2244,7 +2252,7 @@ fw_err:
 	 * information to provide information on which CPUID leaves/fields
 	 * failed CPUID validation.
 	 */
-	if (!snp_page_reclaim(pfn + i) && !host_rmp_make_shared(pfn + i, PG_LEVEL_4K) &&
+	if (!snp_page_reclaim(kvm, pfn + i) &&
 	    sev_populate_args->type == KVM_SEV_SNP_PAGE_TYPE_CPUID &&
 	    sev_populate_args->fw_error == SEV_RET_INVALID_PARAM) {
 		void *vaddr = kmap_local_pfn(pfn + i);
@@ -2262,7 +2270,7 @@ err:
 	pr_debug("%s: exiting with error ret %d (fw_error %d), restoring %d gmem PFNs to shared.\n",
 		 __func__, ret, sev_populate_args->fw_error, n_private);
 	for (i = 0; i < n_private; i++)
-		host_rmp_make_shared(pfn + i, PG_LEVEL_4K);
+		kvm_rmp_make_shared(kvm, pfn + i, PG_LEVEL_4K);
 
 	return ret;
 }
@@ -2380,8 +2388,7 @@ static int snp_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
 		ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_LAUNCH_UPDATE,
 				      &data, &argp->error);
 		if (ret) {
-			if (!snp_page_reclaim(pfn))
-				host_rmp_make_shared(pfn, PG_LEVEL_4K);
+			snp_page_reclaim(kvm, pfn);
 
 			return ret;
 		}
@@ -3069,7 +3076,7 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu)
 	if (sev_snp_guest(vcpu->kvm)) {
 		u64 pfn = __pa(svm->sev_es.vmsa) >> PAGE_SHIFT;
 
-		if (host_rmp_make_shared(pfn, PG_LEVEL_4K))
+		if (kvm_rmp_make_shared(vcpu->kvm, pfn, PG_LEVEL_4K))
 			goto skip_vmsa_free;
 	}
 
-- 
cgit v1.2.3-58-ga151


From 73137f59246da530c29674a506f83a18fe327946 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 3 Jun 2024 12:37:26 -0400
Subject: KVM: SEV: Don't WARN() if RMP lookup fails when invalidating gmem
 pages

The hook only handles cleanup work specific to SNP, e.g. RMP table
entries and flushing caches for encrypted guest memory. When run on a
non-SNP-enabled host (currently only possible using
KVM_X86_SW_PROTECTED_VM, e.g. via KVM selftests), the callback is a noop
and will WARN due to the RMP table not being present. It's actually
expected in this case that the RMP table wouldn't be present and that
the hook should be a noop, so drop the WARN_ONCE().

Reported-by: Sean Christopherson <seanjc@google.com>
Closes: https://lore.kernel.org/kvm/ZkU3_y0UoPk5yAeK@google.com/
Fixes: 8eb01900b018 ("KVM: SEV: Implement gmem hook for invalidating private pages")
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 39f8eeea5659..526b9bfb7234 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4682,6 +4682,9 @@ void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
 {
 	kvm_pfn_t pfn;
 
+	if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
+		return;
+
 	pr_debug("%s: PFN start 0x%llx PFN end 0x%llx\n", __func__, start, end);
 
 	for (pfn = start; pfn < end;) {
@@ -4690,11 +4693,7 @@ void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
 		bool assigned;
 
 		rc = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
-		if (WARN_ONCE(rc, "SEV: Failed to retrieve RMP entry for PFN 0x%llx error %d\n",
-			      pfn, rc))
-			goto next_pfn;
-
-		if (!assigned)
+		if (rc || !assigned)
 			goto next_pfn;
 
 		use_2m_update = IS_ALIGNED(pfn, PTRS_PER_PMD) &&
-- 
cgit v1.2.3-58-ga151


From b2ec042347fde5df1239d228b4d86ca642944870 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Wed, 22 May 2024 13:31:58 -0500
Subject: KVM: SVM: Remove the need to trigger an UNBLOCK event on AP creation

All SNP APs are initially started using the APIC INIT/SIPI sequence in
the guest. This sequence moves the AP MP state from
KVM_MP_STATE_UNINITIALIZED to KVM_MP_STATE_RUNNABLE, so there is no need
to attempt the UNBLOCK.

As it is, the UNBLOCK support in SVM is only enabled when AVIC is
enabled. When AVIC is disabled, AP creation is still successful.

Remove the KVM_REQ_UNBLOCK request from the AP creation code and revert
the changes to the vcpu_unblocking() kvm_x86_ops path.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 14 --------------
 arch/x86/kvm/svm/svm.c |  8 +-------
 arch/x86/kvm/svm/svm.h |  2 --
 3 files changed, 1 insertion(+), 23 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 526b9bfb7234..20b92f4b0906 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3909,10 +3909,6 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm)
 out:
 	if (kick) {
 		kvm_make_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
-
-		if (target_vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)
-			kvm_make_request(KVM_REQ_UNBLOCK, target_vcpu);
-
 		kvm_vcpu_kick(target_vcpu);
 	}
 
@@ -4478,16 +4474,6 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
 	return p;
 }
 
-void sev_vcpu_unblocking(struct kvm_vcpu *vcpu)
-{
-	if (!sev_snp_guest(vcpu->kvm))
-		return;
-
-	if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu) &&
-	    vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)
-		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-}
-
 void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
 {
 	struct kvm_memory_slot *slot;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 3d0549ca246f..4fdfcbbb2e30 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4943,12 +4943,6 @@ static void *svm_alloc_apic_backing_page(struct kvm_vcpu *vcpu)
 	return page_address(page);
 }
 
-static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu)
-{
-	sev_vcpu_unblocking(vcpu);
-	avic_vcpu_unblocking(vcpu);
-}
-
 static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.name = KBUILD_MODNAME,
 
@@ -4971,7 +4965,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.vcpu_load = svm_vcpu_load,
 	.vcpu_put = svm_vcpu_put,
 	.vcpu_blocking = avic_vcpu_blocking,
-	.vcpu_unblocking = svm_vcpu_unblocking,
+	.vcpu_unblocking = avic_vcpu_unblocking,
 
 	.update_exception_bitmap = svm_update_exception_bitmap,
 	.get_msr_feature = svm_get_msr_feature,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 555c55f50298..f0ab0d93cd20 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -734,7 +734,6 @@ int sev_cpu_init(struct svm_cpu_data *sd);
 int sev_dev_get_attr(u32 group, u64 attr, u64 *val);
 extern unsigned int max_sev_asid;
 void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code);
-void sev_vcpu_unblocking(struct kvm_vcpu *vcpu);
 void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
 int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
 void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
@@ -753,7 +752,6 @@ static inline int sev_cpu_init(struct svm_cpu_data *sd) { return 0; }
 static inline int sev_dev_get_attr(u32 group, u64 attr, u64 *val) { return -ENXIO; }
 #define max_sev_asid 0
 static inline void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code) {}
-static inline void sev_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 static inline void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) {}
 static inline int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order)
 {
-- 
cgit v1.2.3-58-ga151