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;
IronPort-SDR: Ktpf7wdsvxjiAoD4G6UC+4kNQW91H9mIfnmy6IgKMswgLE30+xxfY2kPIBSuWlq2fHlyYbD4Ki
 BxT7rubujhSw==
From:   Andra Paraschiv <andraprs@amazon.com>
To:     <linux-kernel@vger.kernel.org>
CC:     Anthony Liguori <aliguori@amazon.com>,
        Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Colm MacCarthaigh <colmmacc@amazon.com>,
        "Bjoern Doebel" <doebel@amazon.de>,
        David Woodhouse <dwmw@amazon.co.uk>,
        "Frank van der Linden" <fllinden@amazon.com>,
        Alexander Graf <graf@amazon.de>,
        Greg KH <gregkh@linuxfoundation.org>,
        Martin Pohlack <mpohlack@amazon.de>,
        "Matt Wilson" <msw@amazon.com>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Balbir Singh <sblbir@amazon.com>,
        Stefano Garzarella <sgarzare@redhat.com>,
        "Stefan Hajnoczi" <stefanha@redhat.com>,
        Stewart Smith <trawets@amazon.com>,
        "Uwe Dannowski" <uwed@amazon.de>, <kvm@vger.kernel.org>,
        <ne-devel-upstream@amazon.com>,
        Andra Paraschiv <andraprs@amazon.com>
Subject: [PATCH v4 11/18] nitro_enclaves: Add logic for enclave memory region set
Date:   Mon, 22 Jun 2020 23:03:22 +0300
Message-ID: <20200622200329.52996-12-andraprs@amazon.com>
In-Reply-To: <20200622200329.52996-1-andraprs@amazon.com>
References: <20200622200329.52996-1-andraprs@amazon.com>
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Another resource that is being set for an enclave is memory. User space
memory regions, that need to be backed by contiguous memory regions,
are associated with the enclave.

One solution for allocating / reserving contiguous memory regions, that
is used for integration, is hugetlbfs. The user space process that is
associated with the enclave passes to the driver these memory regions.

The enclave memory regions need to be from the same NUMA node as the
enclave CPUs.

Add ioctl command logic for setting user space memory region for an
enclave.

Signed-off-by: Alexandru Vasile <lexnv@amazon.com>
Signed-off-by: Andra Paraschiv <andraprs@amazon.com>
---
Changelog

v3 -> v4

* Check enclave memory regions are from the same NUMA node as the
  enclave CPUs.
* Use dev_err instead of custom NE log pattern.
* Update the NE ioctl call to match the decoupling from the KVM API.

v2 -> v3

* Remove the WARN_ON calls.
* Update static calls sanity checks.
* Update kzfree() calls to kfree().

v1 -> v2

* Add log pattern for NE.
* Update goto labels to match their purpose.
* Remove the BUG_ON calls.
* Check if enclave max memory regions is reached when setting an enclave
  memory region.
* Check if enclave state is init when setting an enclave memory region.
---
 drivers/virt/nitro_enclaves/ne_misc_dev.c | 257 ++++++++++++++++++++++
 1 file changed, 257 insertions(+)

diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev.c b/drivers/virt/nitro_enclaves/ne_misc_dev.c
index cfdefa52ed2a..17ccb6cdbd75 100644
--- a/drivers/virt/nitro_enclaves/ne_misc_dev.c
+++ b/drivers/virt/nitro_enclaves/ne_misc_dev.c
@@ -476,6 +476,233 @@ static int ne_create_vcpu_ioctl(struct ne_enclave *ne_enclave, u32 vcpu_id)
 	return rc;
 }
 
+/**
+ * ne_sanity_check_user_mem_region - Sanity check the userspace memory
+ * region received during the set user memory region ioctl call.
+ *
+ * This function gets called with the ne_enclave mutex held.
+ *
+ * @ne_enclave: private data associated with the current enclave.
+ * @mem_region: user space memory region to be sanity checked.
+ *
+ * @returns: 0 on success, negative return value on failure.
+ */
+static int ne_sanity_check_user_mem_region(struct ne_enclave *ne_enclave,
+	struct ne_user_memory_region *mem_region)
+{
+	if (ne_enclave->mm != current->mm)
+		return -EIO;
+
+	if ((mem_region->memory_size % NE_MIN_MEM_REGION_SIZE) != 0) {
+		dev_err_ratelimited(ne_misc_dev.this_device,
+				    "Mem size not multiple of 2 MiB\n");
+
+		return -EINVAL;
+	}
+
+	if ((mem_region->userspace_addr & (NE_MIN_MEM_REGION_SIZE - 1)) ||
+	    !access_ok((void __user *)(unsigned long)mem_region->userspace_addr,
+		       mem_region->memory_size)) {
+		dev_err_ratelimited(ne_misc_dev.this_device,
+				    "Invalid user space addr range\n");
+
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * ne_set_user_memory_region_ioctl - Add user space memory region to the slot
+ * associated with the current enclave.
+ *
+ * This function gets called with the ne_enclave mutex held.
+ *
+ * @ne_enclave: private data associated with the current enclave.
+ * @mem_region: user space memory region to be associated with the given slot.
+ *
+ * @returns: 0 on success, negative return value on failure.
+ */
+static int ne_set_user_memory_region_ioctl(struct ne_enclave *ne_enclave,
+	struct ne_user_memory_region *mem_region)
+{
+	struct ne_pci_dev_cmd_reply cmd_reply = {};
+	long gup_rc = 0;
+	unsigned long i = 0;
+	struct ne_mem_region *ne_mem_region = NULL;
+	unsigned long nr_phys_contig_mem_regions = 0;
+	unsigned long nr_pinned_pages = 0;
+	struct page **phys_contig_mem_regions = NULL;
+	int rc = -EINVAL;
+	struct slot_add_mem_req slot_add_mem_req = {};
+
+	rc = ne_sanity_check_user_mem_region(ne_enclave, mem_region);
+	if (rc < 0)
+		return rc;
+
+	ne_mem_region = kzalloc(sizeof(*ne_mem_region), GFP_KERNEL);
+	if (!ne_mem_region)
+		return -ENOMEM;
+
+	/*
+	 * TODO: Update nr_pages value to handle contiguous virtual address
+	 * ranges mapped to non-contiguous physical regions. Hugetlbfs can give
+	 * 2 MiB / 1 GiB contiguous physical regions.
+	 */
+	ne_mem_region->nr_pages = mem_region->memory_size /
+		NE_MIN_MEM_REGION_SIZE;
+
+	ne_mem_region->pages = kcalloc(ne_mem_region->nr_pages,
+				       sizeof(*ne_mem_region->pages),
+				       GFP_KERNEL);
+	if (!ne_mem_region->pages) {
+		kfree(ne_mem_region);
+
+		return -ENOMEM;
+	}
+
+	phys_contig_mem_regions = kcalloc(ne_mem_region->nr_pages,
+					  sizeof(*phys_contig_mem_regions),
+					  GFP_KERNEL);
+	if (!phys_contig_mem_regions) {
+		kfree(ne_mem_region->pages);
+		kfree(ne_mem_region);
+
+		return -ENOMEM;
+	}
+
+	/*
+	 * TODO: Handle non-contiguous memory regions received from user space.
+	 * Hugetlbfs can give 2 MiB / 1 GiB contiguous physical regions. The
+	 * virtual address space can be seen as contiguous, although it is
+	 * mapped underneath to 2 MiB / 1 GiB physical regions e.g. 8 MiB
+	 * virtual address space mapped to 4 physically contiguous regions of 2
+	 * MiB.
+	 */
+	do {
+		unsigned long tmp_nr_pages = ne_mem_region->nr_pages -
+			nr_pinned_pages;
+		struct page **tmp_pages = ne_mem_region->pages +
+			nr_pinned_pages;
+		u64 tmp_userspace_addr = mem_region->userspace_addr +
+			nr_pinned_pages * NE_MIN_MEM_REGION_SIZE;
+
+		gup_rc = get_user_pages(tmp_userspace_addr, tmp_nr_pages,
+					FOLL_GET, tmp_pages, NULL);
+		if (gup_rc < 0) {
+			rc = gup_rc;
+
+			dev_err_ratelimited(ne_misc_dev.this_device,
+					    "Error in gup [rc=%d]\n", rc);
+
+			unpin_user_pages(ne_mem_region->pages, nr_pinned_pages);
+
+			goto free_mem_region;
+		}
+
+		nr_pinned_pages += gup_rc;
+
+	} while (nr_pinned_pages < ne_mem_region->nr_pages);
+
+	/*
+	 * TODO: Update checks once physically contiguous regions are collected
+	 * based on the user space address and get_user_pages() results.
+	 */
+	for (i = 0; i < ne_mem_region->nr_pages; i++) {
+		if (!PageHuge(ne_mem_region->pages[i])) {
+			dev_err_ratelimited(ne_misc_dev.this_device,
+					    "Not a hugetlbfs page\n");
+
+			goto unpin_pages;
+		}
+
+		if (huge_page_size(page_hstate(ne_mem_region->pages[i])) !=
+		    NE_MIN_MEM_REGION_SIZE) {
+			dev_err_ratelimited(ne_misc_dev.this_device,
+					    "Page size isn't 2 MiB\n");
+
+			goto unpin_pages;
+		}
+
+		if (ne_enclave->numa_node !=
+		    page_to_nid(ne_mem_region->pages[i])) {
+			dev_err_ratelimited(ne_misc_dev.this_device,
+					    "Page isn't from NUMA node %d\n",
+					    ne_enclave->numa_node);
+
+			goto unpin_pages;
+		}
+
+		/*
+		 * TODO: Update once handled non-contiguous memory regions
+		 * received from user space.
+		 */
+		phys_contig_mem_regions[i] = ne_mem_region->pages[i];
+	}
+
+	/*
+	 * TODO: Update once handled non-contiguous memory regions received
+	 * from user space.
+	 */
+	nr_phys_contig_mem_regions = ne_mem_region->nr_pages;
+
+	if ((ne_enclave->nr_mem_regions + nr_phys_contig_mem_regions) >
+	    ne_enclave->max_mem_regions) {
+		dev_err_ratelimited(ne_misc_dev.this_device,
+				    "Reached max memory regions %lld\n",
+				    ne_enclave->max_mem_regions);
+
+		goto unpin_pages;
+	}
+
+	for (i = 0; i < nr_phys_contig_mem_regions; i++) {
+		u64 phys_addr = page_to_phys(phys_contig_mem_regions[i]);
+
+		slot_add_mem_req.slot_uid = ne_enclave->slot_uid;
+		slot_add_mem_req.paddr = phys_addr;
+		/*
+		 * TODO: Update memory size of physical contiguous memory
+		 * region, in case of non-contiguous memory regions received
+		 * from user space.
+		 */
+		slot_add_mem_req.size = NE_MIN_MEM_REGION_SIZE;
+
+		rc = ne_do_request(ne_enclave->pdev, SLOT_ADD_MEM,
+				   &slot_add_mem_req, sizeof(slot_add_mem_req),
+				   &cmd_reply, sizeof(cmd_reply));
+		if (rc < 0) {
+			dev_err_ratelimited(ne_misc_dev.this_device,
+					    "Error in slot add mem [rc=%d]\n",
+					    rc);
+
+			/* TODO: Only unpin memory regions not added. */
+			goto unpin_pages;
+		}
+
+		ne_enclave->mem_size += slot_add_mem_req.size;
+		ne_enclave->nr_mem_regions++;
+
+		memset(&slot_add_mem_req, 0, sizeof(slot_add_mem_req));
+		memset(&cmd_reply, 0, sizeof(cmd_reply));
+	}
+
+	list_add(&ne_mem_region->mem_region_list_entry,
+		 &ne_enclave->mem_regions_list);
+
+	kfree(phys_contig_mem_regions);
+
+	return 0;
+
+unpin_pages:
+	unpin_user_pages(ne_mem_region->pages, ne_mem_region->nr_pages);
+free_mem_region:
+	kfree(phys_contig_mem_regions);
+	kfree(ne_mem_region->pages);
+	kfree(ne_mem_region);
+
+	return rc;
+}
+
 static long ne_enclave_ioctl(struct file *file, unsigned int cmd,
 			     unsigned long arg)
 {
@@ -561,6 +788,36 @@ static long ne_enclave_ioctl(struct file *file, unsigned int cmd,
 		return 0;
 	}
 
+	case NE_SET_USER_MEMORY_REGION: {
+		struct ne_user_memory_region mem_region = {};
+		int rc = -EINVAL;
+
+		if (copy_from_user(&mem_region, (void *)arg,
+				   sizeof(mem_region))) {
+			dev_err_ratelimited(ne_misc_dev.this_device,
+					    "Error in copy from user\n");
+
+			return -EFAULT;
+		}
+
+		mutex_lock(&ne_enclave->enclave_info_mutex);
+
+		if (ne_enclave->state != NE_STATE_INIT) {
+			dev_err_ratelimited(ne_misc_dev.this_device,
+					    "Enclave isn't in init state\n");
+
+			mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+			return -EINVAL;
+		}
+
+		rc = ne_set_user_memory_region_ioctl(ne_enclave, &mem_region);
+
+		mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+		return rc;
+	}
+
 	default:
 		return -ENOTTY;
 	}
-- 
2.20.1 (Apple Git-117)


Amazon Development Center (Romania) S.R.L. registered office: 27A Sf. Lazar Street, UBC5, floor 2, Iasi, Iasi County, 700045, Romania. Registered in Romania. Registration number J22/2621/2005.