x86/sgx: Add a page reclaimer

Just like normal RAM, there is a limited amount of enclave memory available
and overcommitting it is a very valuable tool to reduce resource use.
Introduce a simple reclaim mechanism for enclave pages.

In contrast to normal page reclaim, the kernel cannot directly access
enclave memory.  To get around this, the SGX architecture provides a set of
functions to help.  Among other things, these functions copy enclave memory
to and from normal memory, encrypting it and protecting its integrity in
the process.

Implement a page reclaimer by using these functions. Picks victim pages in
LRU fashion from all the enclaves running in the system.  A new kernel
thread (ksgxswapd) reclaims pages in the background based on watermarks,
similar to normal kswapd.

All enclave pages can be reclaimed, architecturally.  But, there are some
limits to this, such as the special SECS metadata page which must be
reclaimed last.  The page version array (used to mitigate replaying old
reclaimed pages) is also architecturally reclaimable, but not yet
implemented.  The end result is that the vast majority of enclave pages are
currently reclaimable.

Co-developed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Jethro Beekman <jethro@fortanix.com>
Link: https://lkml.kernel.org/r/20201112220135.165028-22-jarkko@kernel.org

1 files changed, 479 insertions, 4 deletions

diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 57eff300f487..b74dadf85989 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -12,11 +12,90 @@
 #include "encls.h"
 #include "sgx.h"
 
+/*
+ * ELDU: Load an EPC page as unblocked. For more info, see "OS Management of EPC
+ * Pages" in the SDM.
+ */
+static int __sgx_encl_eldu(struct sgx_encl_page *encl_page,
+			   struct sgx_epc_page *epc_page,
+			   struct sgx_epc_page *secs_page)
+{
+	unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK;
+	struct sgx_encl *encl = encl_page->encl;
+	struct sgx_pageinfo pginfo;
+	struct sgx_backing b;
+	pgoff_t page_index;
+	int ret;
+
+	if (secs_page)
+		page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base);
+	else
+		page_index = PFN_DOWN(encl->size);
+
+	ret = sgx_encl_get_backing(encl, page_index, &b);
+	if (ret)
+		return ret;
+
+	pginfo.addr = encl_page->desc & PAGE_MASK;
+	pginfo.contents = (unsigned long)kmap_atomic(b.contents);
+	pginfo.metadata = (unsigned long)kmap_atomic(b.pcmd) +
+			  b.pcmd_offset;
+
+	if (secs_page)
+		pginfo.secs = (u64)sgx_get_epc_virt_addr(secs_page);
+	else
+		pginfo.secs = 0;
+
+	ret = __eldu(&pginfo, sgx_get_epc_virt_addr(epc_page),
+		     sgx_get_epc_virt_addr(encl_page->va_page->epc_page) + va_offset);
+	if (ret) {
+		if (encls_failed(ret))
+			ENCLS_WARN(ret, "ELDU");
+
+		ret = -EFAULT;
+	}
+
+	kunmap_atomic((void *)(unsigned long)(pginfo.metadata - b.pcmd_offset));
+	kunmap_atomic((void *)(unsigned long)pginfo.contents);
+
+	sgx_encl_put_backing(&b, false);
+
+	return ret;
+}
+
+static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page,
+					  struct sgx_epc_page *secs_page)
+{
+
+	unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK;
+	struct sgx_encl *encl = encl_page->encl;
+	struct sgx_epc_page *epc_page;
+	int ret;
+
+	epc_page = sgx_alloc_epc_page(encl_page, false);
+	if (IS_ERR(epc_page))
+		return epc_page;
+
+	ret = __sgx_encl_eldu(encl_page, epc_page, secs_page);
+	if (ret) {
+		sgx_free_epc_page(epc_page);
+		return ERR_PTR(ret);
+	}
+
+	sgx_free_va_slot(encl_page->va_page, va_offset);
+	list_move(&encl_page->va_page->list, &encl->va_pages);
+	encl_page->desc &= ~SGX_ENCL_PAGE_VA_OFFSET_MASK;
+	encl_page->epc_page = epc_page;
+
+	return epc_page;
+}
+
 static struct sgx_encl_page *sgx_encl_load_page(struct sgx_encl *encl,
 						unsigned long addr,
 						unsigned long vm_flags)
 {
 	unsigned long vm_prot_bits = vm_flags & (VM_READ | VM_WRITE | VM_EXEC);
+	struct sgx_epc_page *epc_page;
 	struct sgx_encl_page *entry;
 
 	entry = xa_load(&encl->page_array, PFN_DOWN(addr));
@@ -31,11 +110,27 @@ static struct sgx_encl_page *sgx_encl_load_page(struct sgx_encl *encl,
 	if ((entry->vm_max_prot_bits & vm_prot_bits) != vm_prot_bits)
 		return ERR_PTR(-EFAULT);
 
-	/* No page found. */
-	if (!entry->epc_page)
-		return ERR_PTR(-EFAULT);
-
 	/* Entry successfully located. */
+	if (entry->epc_page) {
+		if (entry->desc & SGX_ENCL_PAGE_BEING_RECLAIMED)
+			return ERR_PTR(-EBUSY);
+
+		return entry;
+	}
+
+	if (!(encl->secs.epc_page)) {
+		epc_page = sgx_encl_eldu(&encl->secs, NULL);
+		if (IS_ERR(epc_page))
+			return ERR_CAST(epc_page);
+	}
+
+	epc_page = sgx_encl_eldu(entry, encl->secs.epc_page);
+	if (IS_ERR(epc_page))
+		return ERR_CAST(epc_page);
+
+	encl->secs_child_cnt++;
+	sgx_mark_page_reclaimable(entry->epc_page);
+
 	return entry;
 }
 
@@ -51,12 +146,23 @@ static vm_fault_t sgx_vma_fault(struct vm_fault *vmf)
 
 	encl = vma->vm_private_data;
 
+	/*
+	 * It's very unlikely but possible that allocating memory for the
+	 * mm_list entry of a forked process failed in sgx_vma_open(). When
+	 * this happens, vm_private_data is set to NULL.
+	 */
+	if (unlikely(!encl))
+		return VM_FAULT_SIGBUS;
+
 	mutex_lock(&encl->lock);
 
 	entry = sgx_encl_load_page(encl, addr, vma->vm_flags);
 	if (IS_ERR(entry)) {
 		mutex_unlock(&encl->lock);
 
+		if (PTR_ERR(entry) == -EBUSY)
+			return VM_FAULT_NOPAGE;
+
 		return VM_FAULT_SIGBUS;
 	}
 
@@ -76,11 +182,29 @@ static vm_fault_t sgx_vma_fault(struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 	}
 
+	sgx_encl_test_and_clear_young(vma->vm_mm, entry);
 	mutex_unlock(&encl->lock);
 
 	return VM_FAULT_NOPAGE;
 }
 
+static void sgx_vma_open(struct vm_area_struct *vma)
+{
+	struct sgx_encl *encl = vma->vm_private_data;
+
+	/*
+	 * It's possible but unlikely that vm_private_data is NULL. This can
+	 * happen in a grandchild of a process, when sgx_encl_mm_add() had
+	 * failed to allocate memory in this callback.
+	 */
+	if (unlikely(!encl))
+		return;
+
+	if (sgx_encl_mm_add(encl, vma->vm_mm))
+		vma->vm_private_data = NULL;
+}
+
+
 /**
  * sgx_encl_may_map() - Check if a requested VMA mapping is allowed
  * @encl:		an enclave pointer
@@ -151,4 +275,355 @@ static int sgx_vma_mprotect(struct vm_area_struct *vma, unsigned long start,
 const struct vm_operations_struct sgx_vm_ops = {
 	.fault = sgx_vma_fault,
 	.mprotect = sgx_vma_mprotect,
+	.open = sgx_vma_open,
+};
+
+/**
+ * sgx_encl_release - Destroy an enclave instance
+ * @kref:	address of a kref inside &sgx_encl
+ *
+ * Used together with kref_put(). Frees all the resources associated with the
+ * enclave and the instance itself.
+ */
+void sgx_encl_release(struct kref *ref)
+{
+	struct sgx_encl *encl = container_of(ref, struct sgx_encl, refcount);
+	struct sgx_va_page *va_page;
+	struct sgx_encl_page *entry;
+	unsigned long index;
+
+	xa_for_each(&encl->page_array, index, entry) {
+		if (entry->epc_page) {
+			/*
+			 * The page and its radix tree entry cannot be freed
+			 * if the page is being held by the reclaimer.
+			 */
+			if (sgx_unmark_page_reclaimable(entry->epc_page))
+				continue;
+
+			sgx_free_epc_page(entry->epc_page);
+			encl->secs_child_cnt--;
+			entry->epc_page = NULL;
+		}
+
+		kfree(entry);
+	}
+
+	xa_destroy(&encl->page_array);
+
+	if (!encl->secs_child_cnt && encl->secs.epc_page) {
+		sgx_free_epc_page(encl->secs.epc_page);
+		encl->secs.epc_page = NULL;
+	}
+
+	while (!list_empty(&encl->va_pages)) {
+		va_page = list_first_entry(&encl->va_pages, struct sgx_va_page,
+					   list);
+		list_del(&va_page->list);
+		sgx_free_epc_page(va_page->epc_page);
+		kfree(va_page);
+	}
+
+	if (encl->backing)
+		fput(encl->backing);
+
+	cleanup_srcu_struct(&encl->srcu);
+
+	WARN_ON_ONCE(!list_empty(&encl->mm_list));
+
+	/* Detect EPC page leak's. */
+	WARN_ON_ONCE(encl->secs_child_cnt);
+	WARN_ON_ONCE(encl->secs.epc_page);
+
+	kfree(encl);
+}
+
+/*
+ * 'mm' is exiting and no longer needs mmu notifications.
+ */
+static void sgx_mmu_notifier_release(struct mmu_notifier *mn,
+				     struct mm_struct *mm)
+{
+	struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier);
+	struct sgx_encl_mm *tmp = NULL;
+
+	/*
+	 * The enclave itself can remove encl_mm.  Note, objects can't be moved
+	 * off an RCU protected list, but deletion is ok.
+	 */
+	spin_lock(&encl_mm->encl->mm_lock);
+	list_for_each_entry(tmp, &encl_mm->encl->mm_list, list) {
+		if (tmp == encl_mm) {
+			list_del_rcu(&encl_mm->list);
+			break;
+		}
+	}
+	spin_unlock(&encl_mm->encl->mm_lock);
+
+	if (tmp == encl_mm) {
+		synchronize_srcu(&encl_mm->encl->srcu);
+		mmu_notifier_put(mn);
+	}
+}
+
+static void sgx_mmu_notifier_free(struct mmu_notifier *mn)
+{
+	struct sgx_encl_mm *encl_mm = container_of(mn, struct sgx_encl_mm, mmu_notifier);
+
+	kfree(encl_mm);
+}
+
+static const struct mmu_notifier_ops sgx_mmu_notifier_ops = {
+	.release		= sgx_mmu_notifier_release,
+	.free_notifier		= sgx_mmu_notifier_free,
 };
+
+static struct sgx_encl_mm *sgx_encl_find_mm(struct sgx_encl *encl,
+					    struct mm_struct *mm)
+{
+	struct sgx_encl_mm *encl_mm = NULL;
+	struct sgx_encl_mm *tmp;
+	int idx;
+
+	idx = srcu_read_lock(&encl->srcu);
+
+	list_for_each_entry_rcu(tmp, &encl->mm_list, list) {
+		if (tmp->mm == mm) {
+			encl_mm = tmp;
+			break;
+		}
+	}
+
+	srcu_read_unlock(&encl->srcu, idx);
+
+	return encl_mm;
+}
+
+int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm)
+{
+	struct sgx_encl_mm *encl_mm;
+	int ret;
+
+	/*
+	 * Even though a single enclave may be mapped into an mm more than once,
+	 * each 'mm' only appears once on encl->mm_list. This is guaranteed by
+	 * holding the mm's mmap lock for write before an mm can be added or
+	 * remove to an encl->mm_list.
+	 */
+	mmap_assert_write_locked(mm);
+
+	/*
+	 * It's possible that an entry already exists in the mm_list, because it
+	 * is removed only on VFS release or process exit.
+	 */
+	if (sgx_encl_find_mm(encl, mm))
+		return 0;
+
+	encl_mm = kzalloc(sizeof(*encl_mm), GFP_KERNEL);
+	if (!encl_mm)
+		return -ENOMEM;
+
+	encl_mm->encl = encl;
+	encl_mm->mm = mm;
+	encl_mm->mmu_notifier.ops = &sgx_mmu_notifier_ops;
+
+	ret = __mmu_notifier_register(&encl_mm->mmu_notifier, mm);
+	if (ret) {
+		kfree(encl_mm);
+		return ret;
+	}
+
+	spin_lock(&encl->mm_lock);
+	list_add_rcu(&encl_mm->list, &encl->mm_list);
+	/* Pairs with smp_rmb() in sgx_reclaimer_block(). */
+	smp_wmb();
+	encl->mm_list_version++;
+	spin_unlock(&encl->mm_lock);
+
+	return 0;
+}
+
+static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
+					      pgoff_t index)
+{
+	struct inode *inode = encl->backing->f_path.dentry->d_inode;
+	struct address_space *mapping = inode->i_mapping;
+	gfp_t gfpmask = mapping_gfp_mask(mapping);
+
+	return shmem_read_mapping_page_gfp(mapping, index, gfpmask);
+}
+
+/**
+ * sgx_encl_get_backing() - Pin the backing storage
+ * @encl:	an enclave pointer
+ * @page_index:	enclave page index
+ * @backing:	data for accessing backing storage for the page
+ *
+ * Pin the backing storage pages for storing the encrypted contents and Paging
+ * Crypto MetaData (PCMD) of an enclave page.
+ *
+ * Return:
+ *   0 on success,
+ *   -errno otherwise.
+ */
+int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
+			 struct sgx_backing *backing)
+{
+	pgoff_t pcmd_index = PFN_DOWN(encl->size) + 1 + (page_index >> 5);
+	struct page *contents;
+	struct page *pcmd;
+
+	contents = sgx_encl_get_backing_page(encl, page_index);
+	if (IS_ERR(contents))
+		return PTR_ERR(contents);
+
+	pcmd = sgx_encl_get_backing_page(encl, pcmd_index);
+	if (IS_ERR(pcmd)) {
+		put_page(contents);
+		return PTR_ERR(pcmd);
+	}
+
+	backing->page_index = page_index;
+	backing->contents = contents;
+	backing->pcmd = pcmd;
+	backing->pcmd_offset =
+		(page_index & (PAGE_SIZE / sizeof(struct sgx_pcmd) - 1)) *
+		sizeof(struct sgx_pcmd);
+
+	return 0;
+}
+
+/**
+ * sgx_encl_put_backing() - Unpin the backing storage
+ * @backing:	data for accessing backing storage for the page
+ * @do_write:	mark pages dirty
+ */
+void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write)
+{
+	if (do_write) {
+		set_page_dirty(backing->pcmd);
+		set_page_dirty(backing->contents);
+	}
+
+	put_page(backing->pcmd);
+	put_page(backing->contents);
+}
+
+static int sgx_encl_test_and_clear_young_cb(pte_t *ptep, unsigned long addr,
+					    void *data)
+{
+	pte_t pte;
+	int ret;
+
+	ret = pte_young(*ptep);
+	if (ret) {
+		pte = pte_mkold(*ptep);
+		set_pte_at((struct mm_struct *)data, addr, ptep, pte);
+	}
+
+	return ret;
+}
+
+/**
+ * sgx_encl_test_and_clear_young() - Test and reset the accessed bit
+ * @mm:		mm_struct that is checked
+ * @page:	enclave page to be tested for recent access
+ *
+ * Checks the Access (A) bit from the PTE corresponding to the enclave page and
+ * clears it.
+ *
+ * Return: 1 if the page has been recently accessed and 0 if not.
+ */
+int sgx_encl_test_and_clear_young(struct mm_struct *mm,
+				  struct sgx_encl_page *page)
+{
+	unsigned long addr = page->desc & PAGE_MASK;
+	struct sgx_encl *encl = page->encl;
+	struct vm_area_struct *vma;
+	int ret;
+
+	ret = sgx_encl_find(mm, addr, &vma);
+	if (ret)
+		return 0;
+
+	if (encl != vma->vm_private_data)
+		return 0;
+
+	ret = apply_to_page_range(vma->vm_mm, addr, PAGE_SIZE,
+				  sgx_encl_test_and_clear_young_cb, vma->vm_mm);
+	if (ret < 0)
+		return 0;
+
+	return ret;
+}
+
+/**
+ * sgx_alloc_va_page() - Allocate a Version Array (VA) page
+ *
+ * Allocate a free EPC page and convert it to a Version Array (VA) page.
+ *
+ * Return:
+ *   a VA page,
+ *   -errno otherwise
+ */
+struct sgx_epc_page *sgx_alloc_va_page(void)
+{
+	struct sgx_epc_page *epc_page;
+	int ret;
+
+	epc_page = sgx_alloc_epc_page(NULL, true);
+	if (IS_ERR(epc_page))
+		return ERR_CAST(epc_page);
+
+	ret = __epa(sgx_get_epc_virt_addr(epc_page));
+	if (ret) {
+		WARN_ONCE(1, "EPA returned %d (0x%x)", ret, ret);
+		sgx_free_epc_page(epc_page);
+		return ERR_PTR(-EFAULT);
+	}
+
+	return epc_page;
+}
+
+/**
+ * sgx_alloc_va_slot - allocate a VA slot
+ * @va_page:	a &struct sgx_va_page instance
+ *
+ * Allocates a slot from a &struct sgx_va_page instance.
+ *
+ * Return: offset of the slot inside the VA page
+ */
+unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page)
+{
+	int slot = find_first_zero_bit(va_page->slots, SGX_VA_SLOT_COUNT);
+
+	if (slot < SGX_VA_SLOT_COUNT)
+		set_bit(slot, va_page->slots);
+
+	return slot << 3;
+}
+
+/**
+ * sgx_free_va_slot - free a VA slot
+ * @va_page:	a &struct sgx_va_page instance
+ * @offset:	offset of the slot inside the VA page
+ *
+ * Frees a slot from a &struct sgx_va_page instance.
+ */
+void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset)
+{
+	clear_bit(offset >> 3, va_page->slots);
+}
+
+/**
+ * sgx_va_page_full - is the VA page full?
+ * @va_page:	a &struct sgx_va_page instance
+ *
+ * Return: true if all slots have been taken
+ */
+bool sgx_va_page_full(struct sgx_va_page *va_page)
+{
+	int slot = find_first_zero_bit(va_page->slots, SGX_VA_SLOT_COUNT);
+
+	return slot == SGX_VA_SLOT_COUNT;
+}