[PATCH v5 18/19] iommufd: Add additional invariant assertions

From: Jason Gunthorpe <jgg@nvidia.com>
To: bpf@vger.kernel.org, Jonathan Corbet <corbet@lwn.net>,
	David Woodhouse <dwmw2@infradead.org>,
	iommu@lists.linux.dev, Joerg Roedel <joro@8bytes.org>,
	Kevin Tian <kevin.tian@intel.com>,
	linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org,
	llvm@lists.linux.dev, Nathan Chancellor <nathan@kernel.org>,
	Nick Desaulniers <ndesaulniers@google.com>,
	Miguel Ojeda <ojeda@kernel.org>,
	Robin Murphy <robin.murphy@arm.com>,
	Shuah Khan <shuah@kernel.org>,
	Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>,
	Tom Rix <trix@redhat.com>, Will Deacon <will@kernel.org>
Cc: Anthony Krowiak <akrowiak@linux.ibm.com>,
	Alex Williamson <alex.williamson@redhat.com>,
	Bagas Sanjaya <bagasdotme@gmail.com>,
	Lu Baolu <baolu.lu@linux.intel.com>,
	Chaitanya Kulkarni <chaitanyak@nvidia.com>,
	Cornelia Huck <cohuck@redhat.com>,
	Daniel Jordan <daniel.m.jordan@oracle.com>,
	David Gibson <david@gibson.dropbear.id.au>,
	Eric Auger <eric.auger@redhat.com>,
	Eric Farman <farman@linux.ibm.com>,
	Jason Wang <jasowang@redhat.com>,
	Jean-Philippe Brucker <jean-philippe@linaro.org>,
	Jason Herne <jjherne@linux.ibm.com>,
	Joao Martins <joao.m.martins@oracle.com>,
	kvm@vger.kernel.org, Lixiao Yang <lixiao.yang@intel.com>,
	Matthew Rosato <mjrosato@linux.ibm.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Nicolin Chen <nicolinc@nvidia.com>,
	Halil Pasic <pasic@linux.ibm.com>,
	Niklas Schnelle <schnelle@linux.ibm.com>,
	Shameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com>,
	Yi Liu <yi.l.liu@intel.com>, Keqian Zhu <zhukeqian1@huawei.com>
Subject: [PATCH v5 18/19] iommufd: Add additional invariant assertions
Date: Wed, 16 Nov 2022 17:00:54 -0400	[thread overview]
Message-ID: <18-v5-4001c2997bd0+30c-iommufd_jgg@nvidia.com> (raw)
In-Reply-To: <0-v5-4001c2997bd0+30c-iommufd_jgg@nvidia.com>

These are on performance paths so we protect them using the
CONFIG_IOMMUFD_TEST to not take a hit during normal operation.

These are useful when running the test suite and syzkaller to find data
structure inconsistencies early.

Tested-by: Yi Liu <yi.l.liu@intel.com>
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com> # s390
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/device.c       |  5 ++++
 drivers/iommu/iommufd/io_pagetable.c | 22 +++++++++++++++
 drivers/iommu/iommufd/io_pagetable.h |  3 ++
 drivers/iommu/iommufd/pages.c        | 42 ++++++++++++++++++++++++++--
 4 files changed, 70 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index a9105237ec4131..07d4dcc0dbf5e1 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -621,6 +621,11 @@ int iommufd_access_pin_pages(struct iommufd_access *access, unsigned long iova,
 	struct iopt_area *area;
 	int rc;
 
+	/* Driver's ops don't support pin_pages */
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
+	    WARN_ON(access->iova_alignment != PAGE_SIZE || !access->ops->unmap))
+		return -EINVAL;
+
 	if (!length)
 		return -EINVAL;
 	if (check_add_overflow(iova, length - 1, &last_iova))
diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c
index 4f4a9d9aac570e..3467cea795684c 100644
--- a/drivers/iommu/iommufd/io_pagetable.c
+++ b/drivers/iommu/iommufd/io_pagetable.c
@@ -251,6 +251,11 @@ static int iopt_alloc_area_pages(struct io_pagetable *iopt,
 			(uintptr_t)elm->pages->uptr + elm->start_byte, length);
 		if (rc)
 			goto out_unlock;
+		if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
+		    WARN_ON(iopt_check_iova(iopt, *dst_iova, length))) {
+			rc = -EINVAL;
+			goto out_unlock;
+		}
 	} else {
 		rc = iopt_check_iova(iopt, *dst_iova, length);
 		if (rc)
@@ -277,6 +282,8 @@ static int iopt_alloc_area_pages(struct io_pagetable *iopt,
 
 static void iopt_abort_area(struct iopt_area *area)
 {
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
+		WARN_ON(area->pages);
 	if (area->iopt) {
 		down_write(&area->iopt->iova_rwsem);
 		interval_tree_remove(&area->node, &area->iopt->area_itree);
@@ -642,6 +649,9 @@ void iopt_destroy_table(struct io_pagetable *iopt)
 {
 	struct interval_tree_node *node;
 
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
+		iopt_remove_reserved_iova(iopt, NULL);
+
 	while ((node = interval_tree_iter_first(&iopt->allowed_itree, 0,
 						ULONG_MAX))) {
 		interval_tree_remove(node, &iopt->allowed_itree);
@@ -688,6 +698,8 @@ static void iopt_unfill_domain(struct io_pagetable *iopt,
 				continue;
 
 			mutex_lock(&pages->mutex);
+			if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
+				WARN_ON(!area->storage_domain);
 			if (area->storage_domain == domain)
 				area->storage_domain = storage_domain;
 			mutex_unlock(&pages->mutex);
@@ -792,6 +804,16 @@ static int iopt_check_iova_alignment(struct io_pagetable *iopt,
 		    (iopt_area_length(area) & align_mask) ||
 		    (area->page_offset & align_mask))
 			return -EADDRINUSE;
+
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) {
+		struct iommufd_access *access;
+		unsigned long index;
+
+		xa_for_each(&iopt->access_list, index, access)
+			if (WARN_ON(access->iova_alignment >
+				    new_iova_alignment))
+				return -EADDRINUSE;
+	}
 	return 0;
 }
 
diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h
index 2ee6942c3ef4a5..83e7c175f2a277 100644
--- a/drivers/iommu/iommufd/io_pagetable.h
+++ b/drivers/iommu/iommufd/io_pagetable.h
@@ -101,6 +101,9 @@ static inline size_t iopt_area_length(struct iopt_area *area)
 static inline unsigned long iopt_area_start_byte(struct iopt_area *area,
 						 unsigned long iova)
 {
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
+		WARN_ON(iova < iopt_area_iova(area) ||
+			iova > iopt_area_last_iova(area));
 	return (iova - iopt_area_iova(area)) + area->page_offset +
 	       iopt_area_index(area) * PAGE_SIZE;
 }
diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c
index c5d2d9a8c56203..429fa3b0a239cd 100644
--- a/drivers/iommu/iommufd/pages.c
+++ b/drivers/iommu/iommufd/pages.c
@@ -162,12 +162,20 @@ void interval_tree_double_span_iter_next(
 
 static void iopt_pages_add_npinned(struct iopt_pages *pages, size_t npages)
 {
-	pages->npinned += npages;
+	int rc;
+
+	rc = check_add_overflow(pages->npinned, npages, &pages->npinned);
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
+		WARN_ON(rc || pages->npinned > pages->npages);
 }
 
 static void iopt_pages_sub_npinned(struct iopt_pages *pages, size_t npages)
 {
-	pages->npinned -= npages;
+	int rc;
+
+	rc = check_sub_overflow(pages->npinned, npages, &pages->npinned);
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
+		WARN_ON(rc || pages->npinned > pages->npages);
 }
 
 static void iopt_pages_err_unpin(struct iopt_pages *pages,
@@ -189,6 +197,9 @@ static void iopt_pages_err_unpin(struct iopt_pages *pages,
 static unsigned long iopt_area_index_to_iova(struct iopt_area *area,
 					     unsigned long index)
 {
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
+		WARN_ON(index < iopt_area_index(area) ||
+			index > iopt_area_last_index(area));
 	index -= iopt_area_index(area);
 	if (index == 0)
 		return iopt_area_iova(area);
@@ -198,6 +209,9 @@ static unsigned long iopt_area_index_to_iova(struct iopt_area *area,
 static unsigned long iopt_area_index_to_iova_last(struct iopt_area *area,
 						  unsigned long index)
 {
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
+		WARN_ON(index < iopt_area_index(area) ||
+			index > iopt_area_last_index(area));
 	if (index == iopt_area_last_index(area))
 		return iopt_area_last_iova(area);
 	return iopt_area_iova(area) - area->page_offset +
@@ -286,6 +300,8 @@ static void batch_skip_carry(struct pfn_batch *batch, unsigned int skip_pfns)
 {
 	if (!batch->total_pfns)
 		return;
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
+		WARN_ON(batch->total_pfns != batch->npfns[0]);
 	skip_pfns = min(batch->total_pfns, skip_pfns);
 	batch->pfns[0] += skip_pfns;
 	batch->npfns[0] -= skip_pfns;
@@ -301,6 +317,8 @@ static int __batch_init(struct pfn_batch *batch, size_t max_pages, void *backup,
 	batch->pfns = temp_kmalloc(&size, backup, backup_len);
 	if (!batch->pfns)
 		return -ENOMEM;
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && WARN_ON(size < elmsz))
+		return -EINVAL;
 	batch->array_size = size / elmsz;
 	batch->npfns = (u32 *)(batch->pfns + batch->array_size);
 	batch_clear(batch);
@@ -429,6 +447,10 @@ static int batch_iommu_map_small(struct iommu_domain *domain,
 	unsigned long start_iova = iova;
 	int rc;
 
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST))
+		WARN_ON(paddr % PAGE_SIZE || iova % PAGE_SIZE ||
+			size % PAGE_SIZE);
+
 	while (size) {
 		rc = iommu_map(domain, iova, paddr, PAGE_SIZE, prot);
 		if (rc)
@@ -718,6 +740,10 @@ static int pfn_reader_user_pin(struct pfn_reader_user *user,
 	uintptr_t uptr;
 	long rc;
 
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
+	    WARN_ON(last_index < start_index))
+		return -EINVAL;
+
 	if (!user->upages) {
 		/* All undone in pfn_reader_destroy() */
 		user->upages_len =
@@ -956,6 +982,10 @@ static int pfn_reader_fill_span(struct pfn_reader *pfns)
 	struct iopt_area *area;
 	int rc;
 
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
+	    WARN_ON(span->last_used < start_index))
+		return -EINVAL;
+
 	if (span->is_used == 1) {
 		batch_from_xarray(&pfns->batch, &pfns->pages->pinned_pfns,
 				  start_index, span->last_used);
@@ -1008,6 +1038,10 @@ static int pfn_reader_next(struct pfn_reader *pfns)
 	while (pfns->batch_end_index != pfns->last_index + 1) {
 		unsigned int npfns = pfns->batch.total_pfns;
 
+		if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
+		    WARN_ON(interval_tree_double_span_iter_done(&pfns->span)))
+			return -EINVAL;
+
 		rc = pfn_reader_fill_span(pfns);
 		if (rc)
 			return rc;
@@ -1091,6 +1125,10 @@ static int pfn_reader_first(struct pfn_reader *pfns, struct iopt_pages *pages,
 {
 	int rc;
 
+	if (IS_ENABLED(CONFIG_IOMMUFD_TEST) &&
+	    WARN_ON(last_index < start_index))
+		return -EINVAL;
+
 	rc = pfn_reader_init(pfns, pages, start_index, last_index);
 	if (rc)
 		return rc;
-- 
2.38.1

