From:   Reinette Chatre <reinette.chatre@intel.com>
To:     dave.hansen@linux.intel.com, jarkko@kernel.org, tglx@linutronix.de,
        bp@alien8.de, luto@kernel.org, mingo@redhat.com,
        linux-sgx@vger.kernel.org, x86@kernel.org
Cc:     seanjc@google.com, kai.huang@intel.com, cathy.zhang@intel.com,
        cedric.xing@intel.com, haitao.huang@intel.com,
        mark.shanahan@intel.com, hpa@zytor.com,
        linux-kernel@vger.kernel.org
Subject: [PATCH 07/25] x86/sgx: Move PTE zap code to separate function
Date:   Wed,  1 Dec 2021 11:23:05 -0800
Message-Id: <bd228c90c139437bb4fcc4b7b99063bfd3eb1439.1638381245.git.reinette.chatre@intel.com>
In-Reply-To: <cover.1638381245.git.reinette.chatre@intel.com>
References: <cover.1638381245.git.reinette.chatre@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

The SGX reclaimer removes page table entries pointing to pages that are
moved to swap. SGX2 enables changes to pages belonging to an initialized
enclave, for example changing page permissions. Supporting SGX2 requires
this ability to remove page table entries that is available in the
SGX reclaimer code.

Factor out the code removing page table entries to a separate function,
fixing accuracy of comments in the process, and make it available to other
areas within the SGX code.

Since the code will no longer be unique to the reclaimer it is relocated
to be with the rest of the enclave code in encl.c interacting with the
page table.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
---
 arch/x86/kernel/cpu/sgx/encl.c | 45 +++++++++++++++++++++++++++++++++-
 arch/x86/kernel/cpu/sgx/encl.h |  2 +-
 arch/x86/kernel/cpu/sgx/main.c | 31 ++---------------------
 3 files changed, 47 insertions(+), 31 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index c29e10541d12..ba39186d5a28 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -587,7 +587,7 @@ int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm)
 
 	spin_lock(&encl->mm_lock);
 	list_add_rcu(&encl_mm->list, &encl->mm_list);
-	/* Pairs with smp_rmb() in sgx_reclaimer_block(). */
+	/* Pairs with smp_rmb() in sgx_zap_enclave_ptes(). */
 	smp_wmb();
 	encl->mm_list_version++;
 	spin_unlock(&encl->mm_lock);
@@ -776,6 +776,49 @@ int sgx_encl_test_and_clear_young(struct mm_struct *mm,
 	return ret;
 }
 
+/**
+ * sgx_zap_enclave_ptes - remove PTEs mapping the address from enclave
+ * @encl: the enclave
+ * @addr: page aligned pointer to single page for which PTEs will be removed
+ *
+ * Multiple VMAs may have an enclave page mapped. Remove the PTE mapping
+ * @addr from each VMA. Ensure that page fault handler is ready to handle
+ * new mappings of @addr before calling this function.
+ */
+void sgx_zap_enclave_ptes(struct sgx_encl *encl, unsigned long addr)
+{
+	unsigned long mm_list_version;
+	struct sgx_encl_mm *encl_mm;
+	struct vm_area_struct *vma;
+	int idx, ret;
+
+	do {
+		mm_list_version = encl->mm_list_version;
+
+		/* Pairs with smp_wmb() in sgx_encl_mm_add(). */
+		smp_rmb();
+
+		idx = srcu_read_lock(&encl->srcu);
+
+		list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
+			if (!mmget_not_zero(encl_mm->mm))
+				continue;
+
+			mmap_read_lock(encl_mm->mm);
+
+			ret = sgx_encl_find(encl_mm->mm, addr, &vma);
+			if (!ret && encl == vma->vm_private_data)
+				zap_vma_ptes(vma, addr, PAGE_SIZE);
+
+			mmap_read_unlock(encl_mm->mm);
+
+			mmput_async(encl_mm->mm);
+		}
+
+		srcu_read_unlock(&encl->srcu, idx);
+	} while (unlikely(encl->mm_list_version != mm_list_version));
+}
+
 /**
  * sgx_alloc_va_page() - Allocate a Version Array (VA) page
  *
diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
index becb68503baa..82e21088e68b 100644
--- a/arch/x86/kernel/cpu/sgx/encl.h
+++ b/arch/x86/kernel/cpu/sgx/encl.h
@@ -112,7 +112,7 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
 void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write);
 int sgx_encl_test_and_clear_young(struct mm_struct *mm,
 				  struct sgx_encl_page *page);
-
+void sgx_zap_enclave_ptes(struct sgx_encl *encl, unsigned long addr);
 struct sgx_epc_page *sgx_alloc_va_page(void);
 unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page);
 void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset);
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index e5be992897f4..9b96f4e0a17a 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -135,36 +135,9 @@ static void sgx_reclaimer_block(struct sgx_epc_page *epc_page)
 	struct sgx_encl_page *page = epc_page->owner;
 	unsigned long addr = page->desc & PAGE_MASK;
 	struct sgx_encl *encl = page->encl;
-	unsigned long mm_list_version;
-	struct sgx_encl_mm *encl_mm;
-	struct vm_area_struct *vma;
-	int idx, ret;
-
-	do {
-		mm_list_version = encl->mm_list_version;
-
-		/* Pairs with smp_rmb() in sgx_encl_mm_add(). */
-		smp_rmb();
-
-		idx = srcu_read_lock(&encl->srcu);
-
-		list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
-			if (!mmget_not_zero(encl_mm->mm))
-				continue;
-
-			mmap_read_lock(encl_mm->mm);
-
-			ret = sgx_encl_find(encl_mm->mm, addr, &vma);
-			if (!ret && encl == vma->vm_private_data)
-				zap_vma_ptes(vma, addr, PAGE_SIZE);
-
-			mmap_read_unlock(encl_mm->mm);
-
-			mmput_async(encl_mm->mm);
-		}
+	int ret;
 
-		srcu_read_unlock(&encl->srcu, idx);
-	} while (unlikely(encl->mm_list_version != mm_list_version));
+	sgx_zap_enclave_ptes(encl, addr);
 
 	mutex_lock(&encl->lock);
 
-- 
2.25.1