diff mbox series

[PATCHv2,45/59] x86/mm: Keep reference counts on hardware key usage for MKTME

Message ID 20190731150813.26289-46-kirill.shutemov@linux.intel.com
State New, archived
Headers show
Series Intel MKTME enabling | expand

Commit Message

Kirill A. Shutemov July 31, 2019, 3:07 p.m. UTC
From: Alison Schofield <alison.schofield@intel.com>

The MKTME (Multi-Key Total Memory Encryption) Key Service needs
a reference count the key usage. This reference count is used
to determine when a hardware encryption KeyID is no longer in use
and can be freed and reassigned to another Userspace Key.

The MKTME Key service does the percpu_ref_init and _kill.

Encrypted VMA's and encrypted pages are included in the reference
counts per keyid.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/include/asm/mktme.h |  5 +++++
 arch/x86/mm/mktme.c          | 37 ++++++++++++++++++++++++++++++++++--
 include/linux/mm.h           |  2 ++
 kernel/fork.c                |  2 ++
 4 files changed, 44 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/arch/x86/include/asm/mktme.h b/arch/x86/include/asm/mktme.h
index e8f7f80bb013..a5f664d3805b 100644
--- a/arch/x86/include/asm/mktme.h
+++ b/arch/x86/include/asm/mktme.h
@@ -20,6 +20,11 @@  extern unsigned int mktme_algs;
 extern void mprotect_set_encrypt(struct vm_area_struct *vma, int newkeyid,
 				unsigned long start, unsigned long end);
 
+/* MTKME encrypt_count for VMAs */
+extern struct percpu_ref *encrypt_count;
+extern void vma_get_encrypt_ref(struct vm_area_struct *vma);
+extern void vma_put_encrypt_ref(struct vm_area_struct *vma);
+
 DECLARE_STATIC_KEY_FALSE(mktme_enabled_key);
 static inline bool mktme_enabled(void)
 {
diff --git a/arch/x86/mm/mktme.c b/arch/x86/mm/mktme.c
index 05bbf5058ade..17366d81c21b 100644
--- a/arch/x86/mm/mktme.c
+++ b/arch/x86/mm/mktme.c
@@ -84,11 +84,12 @@  void mprotect_set_encrypt(struct vm_area_struct *vma, int newkeyid,
 
 	if (oldkeyid == newkeyid)
 		return;
-
+	vma_put_encrypt_ref(vma);
 	newprot = pgprot_val(vma->vm_page_prot);
 	newprot &= ~mktme_keyid_mask();
 	newprot |= (unsigned long)newkeyid << mktme_keyid_shift();
 	vma->vm_page_prot = __pgprot(newprot);
+	vma_get_encrypt_ref(vma);
 
 	/*
 	 * The VMA doesn't have any inherited pages.
@@ -97,6 +98,18 @@  void mprotect_set_encrypt(struct vm_area_struct *vma, int newkeyid,
 	unlink_anon_vmas(vma);
 }
 
+void vma_get_encrypt_ref(struct vm_area_struct *vma)
+{
+	if (vma_keyid(vma))
+		percpu_ref_get(&encrypt_count[vma_keyid(vma)]);
+}
+
+void vma_put_encrypt_ref(struct vm_area_struct *vma)
+{
+	if (vma_keyid(vma))
+		percpu_ref_put(&encrypt_count[vma_keyid(vma)]);
+}
+
 /* Prepare page to be used for encryption. Called from page allocator. */
 void __prep_encrypted_page(struct page *page, int order, int keyid, bool zero)
 {
@@ -137,6 +150,22 @@  void __prep_encrypted_page(struct page *page, int order, int keyid, bool zero)
 
 		page++;
 	}
+
+	/*
+	 * Make sure the KeyID cannot be freed until the last page that
+	 * uses the KeyID is gone.
+	 *
+	 * This is required because the page may live longer than VMA it
+	 * is mapped into (i.e. in get_user_pages() case) and having
+	 * refcounting per-VMA is not enough.
+	 *
+	 * Taking a reference per-4K helps in case if the page will be
+	 * split after the allocation. free_encrypted_page() will balance
+	 * out the refcount even if the page was split and freed as bunch
+	 * of 4K pages.
+	 */
+
+	percpu_ref_get_many(&encrypt_count[keyid], 1 << order);
 }
 
 /*
@@ -145,7 +174,9 @@  void __prep_encrypted_page(struct page *page, int order, int keyid, bool zero)
  */
 void free_encrypted_page(struct page *page, int order)
 {
-	int i;
+	int i, keyid;
+
+	keyid = page_keyid(page);
 
 	/*
 	 * The hardware/CPU does not enforce coherency between mappings
@@ -177,6 +208,8 @@  void free_encrypted_page(struct page *page, int order)
 		lookup_page_ext(page)->keyid = 0;
 		page++;
 	}
+
+	percpu_ref_put_many(&encrypt_count[keyid], 1 << order);
 }
 
 static int sync_direct_mapping_pte(unsigned long keyid,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8551b5ebdedf..be27cb0cc0c7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2911,6 +2911,8 @@  static inline void mprotect_set_encrypt(struct vm_area_struct *vma,
 					int newkeyid,
 					unsigned long start,
 					unsigned long end) {}
+static inline void vma_get_encrypt_ref(struct vm_area_struct *vma) {}
+static inline void vma_put_encrypt_ref(struct vm_area_struct *vma) {}
 #endif /* CONFIG_X86_INTEL_MKTME */
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index d8ae0f1b4148..00735092d370 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -349,12 +349,14 @@  struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 	if (new) {
 		*new = *orig;
 		INIT_LIST_HEAD(&new->anon_vma_chain);
+		vma_get_encrypt_ref(new);
 	}
 	return new;
 }
 
 void vm_area_free(struct vm_area_struct *vma)
 {
+	vma_put_encrypt_ref(vma);
 	kmem_cache_free(vm_area_cachep, vma);
 }