Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Sender: "tmroeder via sendgmr" <tmroeder@tmroeder.kir.corp.google.com>
Date:   Thu, 19 Nov 2020 10:59:19 -0800
Message-Id: <20201119185919.2742954-1-tmroeder@google.com>
Mime-Version: 1.0
Subject: [PATCH] nvme: Cache DMA descriptors to prevent corruption.
From:   Tom Roeder <tmroeder@google.com>
To:     Keith Busch <kbusch@kernel.org>, Jens Axboe <axboe@fb.com>,
        Christoph Hellwig <hch@lst.de>,
        Sagi Grimberg <sagi@grimberg.me>
Cc:     Peter Gonda <pgonda@google.com>,
        Marios Pomonis <pomonis@google.com>,
        linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org,
        Tom Roeder <tmroeder@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

This patch changes the NVMe PCI implementation to cache host_mem_descs
in non-DMA memory instead of depending on descriptors stored in DMA
memory. This change is needed under the malicious-hypervisor threat
model assumed by the AMD SEV and Intel TDX architectures, which encrypt
guest memory to make it unreadable. Some versions of these architectures
also make it cryptographically hard to modify guest memory without
detection.

On these architectures, Linux generally leaves DMA memory unencrypted so
that devices can still communicate directly with the kernel: DMA memory
remains readable to and modifiable by devices. This means that this
memory is also accessible to a hypervisor.

However, this means that a malicious hypervisor could modify the addr or
size fields of descriptors and cause the NVMe driver to call
dma_free_attrs on arbitrary addresses or on the right addresses but with
the wrong size. To prevent this attack, this commit changes the code to
cache those descriptors in non-DMA memory and to use the cached values
when freeing the memory they describe.

Tested: Built and ran with Google-internal NVMe tests.
Tested-by: Tom Roeder <tmroeder@google.com>
Signed-off-by: Tom Roeder <tmroeder@google.com>
---
 drivers/nvme/host/pci.c | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 3be352403839..28ebe1304cae 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -148,6 +148,10 @@ struct nvme_dev {
 	u32 nr_host_mem_descs;
 	dma_addr_t host_mem_descs_dma;
 	struct nvme_host_mem_buf_desc *host_mem_descs;
+	/* Cache the host_mem_descs in non-DMA memory so a malicious hypervisor
+	 * can't change them.
+	 */
+	struct nvme_host_mem_buf_desc *host_mem_descs_cache;
 	void **host_mem_desc_bufs;
 	unsigned int nr_allocated_queues;
 	unsigned int nr_write_queues;
@@ -1874,7 +1878,11 @@ static void nvme_free_host_mem(struct nvme_dev *dev)
 	int i;
 
 	for (i = 0; i < dev->nr_host_mem_descs; i++) {
-		struct nvme_host_mem_buf_desc *desc = &dev->host_mem_descs[i];
+		/* Use the cached version to free the DMA allocations, not a
+		 * version that could be controlled by a malicious hypervisor.
+		 */
+		struct nvme_host_mem_buf_desc *desc =
+			&dev->host_mem_descs_cache[i];
 		size_t size = le32_to_cpu(desc->size) * NVME_CTRL_PAGE_SIZE;
 
 		dma_free_attrs(dev->dev, size, dev->host_mem_desc_bufs[i],
@@ -1888,6 +1896,8 @@ static void nvme_free_host_mem(struct nvme_dev *dev)
 			dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs),
 			dev->host_mem_descs, dev->host_mem_descs_dma);
 	dev->host_mem_descs = NULL;
+	kfree(dev->host_mem_descs_cache);
+	dev->host_mem_descs_cache = NULL;
 	dev->nr_host_mem_descs = 0;
 }
 
@@ -1895,6 +1905,7 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
 		u32 chunk_size)
 {
 	struct nvme_host_mem_buf_desc *descs;
+	struct nvme_host_mem_buf_desc *descs_cache;
 	u32 max_entries, len;
 	dma_addr_t descs_dma;
 	int i = 0;
@@ -1913,9 +1924,13 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
 	if (!descs)
 		goto out;
 
+	descs_cache = kcalloc(max_entries, sizeof(*descs), GFP_KERNEL);
+	if (!descs_cache)
+		goto out_free_descs;
+
 	bufs = kcalloc(max_entries, sizeof(*bufs), GFP_KERNEL);
 	if (!bufs)
-		goto out_free_descs;
+		goto out_free_descs_cache;
 
 	for (size = 0; size < preferred && i < max_entries; size += len) {
 		dma_addr_t dma_addr;
@@ -1928,6 +1943,8 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
 
 		descs[i].addr = cpu_to_le64(dma_addr);
 		descs[i].size = cpu_to_le32(len / NVME_CTRL_PAGE_SIZE);
+		descs_cache[i].addr = cpu_to_le64(dma_addr);
+		descs_cache[i].size = cpu_to_le32(len / NVME_CTRL_PAGE_SIZE);
 		i++;
 	}
 
@@ -1937,20 +1954,24 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
 	dev->nr_host_mem_descs = i;
 	dev->host_mem_size = size;
 	dev->host_mem_descs = descs;
+	dev->host_mem_descs_cache = descs_cache;
 	dev->host_mem_descs_dma = descs_dma;
 	dev->host_mem_desc_bufs = bufs;
 	return 0;
 
 out_free_bufs:
 	while (--i >= 0) {
-		size_t size = le32_to_cpu(descs[i].size) * NVME_CTRL_PAGE_SIZE;
+		size_t size =
+			le32_to_cpu(descs_cache[i].size) * NVME_CTRL_PAGE_SIZE;
 
 		dma_free_attrs(dev->dev, size, bufs[i],
-			       le64_to_cpu(descs[i].addr),
+			       le64_to_cpu(descs_cache[i].addr),
 			       DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN);
 	}
 
 	kfree(bufs);
+out_free_descs_cache:
+	kfree(descs_cache);
 out_free_descs:
 	dma_free_coherent(dev->dev, max_entries * sizeof(*descs), descs,
 			descs_dma);
-- 
2.29.2.299.gdc1121823c-goog