summaryrefslogtreecommitdiffstats
path: root/drivers/virt/nitro_enclaves
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/virt/nitro_enclaves')
-rw-r--r--drivers/virt/nitro_enclaves/Kconfig26
-rw-r--r--drivers/virt/nitro_enclaves/Makefile9
-rw-r--r--drivers/virt/nitro_enclaves/ne_misc_dev.c1783
-rw-r--r--drivers/virt/nitro_enclaves/ne_misc_dev.h109
-rw-r--r--drivers/virt/nitro_enclaves/ne_misc_dev_test.c154
-rw-r--r--drivers/virt/nitro_enclaves/ne_pci_dev.c626
-rw-r--r--drivers/virt/nitro_enclaves/ne_pci_dev.h331
7 files changed, 3038 insertions, 0 deletions
diff --git a/drivers/virt/nitro_enclaves/Kconfig b/drivers/virt/nitro_enclaves/Kconfig
new file mode 100644
index 0000000000..dc4d25c262
--- /dev/null
+++ b/drivers/virt/nitro_enclaves/Kconfig
@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+
+# Amazon Nitro Enclaves (NE) support.
+# Nitro is a hypervisor that has been developed by Amazon.
+
+config NITRO_ENCLAVES
+ tristate "Nitro Enclaves Support"
+ depends on (ARM64 || X86) && HOTPLUG_CPU && PCI && SMP
+ help
+ This driver consists of support for enclave lifetime management
+ for Nitro Enclaves (NE).
+
+ To compile this driver as a module, choose M here.
+ The module will be called nitro_enclaves.
+
+config NITRO_ENCLAVES_MISC_DEV_TEST
+ bool "Tests for the misc device functionality of the Nitro Enclaves" if !KUNIT_ALL_TESTS
+ depends on NITRO_ENCLAVES && KUNIT=y
+ default KUNIT_ALL_TESTS
+ help
+ Enable KUnit tests for the misc device functionality of the Nitro
+ Enclaves. Select this option only if you will boot the kernel for
+ the purpose of running unit tests (e.g. under UML or qemu). If
+ unsure, say N.
diff --git a/drivers/virt/nitro_enclaves/Makefile b/drivers/virt/nitro_enclaves/Makefile
new file mode 100644
index 0000000000..da61260f2b
--- /dev/null
+++ b/drivers/virt/nitro_enclaves/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+
+# Enclave lifetime management support for Nitro Enclaves (NE).
+
+obj-$(CONFIG_NITRO_ENCLAVES) += nitro_enclaves.o
+
+nitro_enclaves-y := ne_pci_dev.o ne_misc_dev.o
diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev.c b/drivers/virt/nitro_enclaves/ne_misc_dev.c
new file mode 100644
index 0000000000..241b94f62e
--- /dev/null
+++ b/drivers/virt/nitro_enclaves/ne_misc_dev.c
@@ -0,0 +1,1783 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+/**
+ * DOC: Enclave lifetime management driver for Nitro Enclaves (NE).
+ * Nitro is a hypervisor that has been developed by Amazon.
+ */
+
+#include <linux/anon_inodes.h>
+#include <linux/capability.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/file.h>
+#include <linux/hugetlb.h>
+#include <linux/limits.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/nitro_enclaves.h>
+#include <linux/pci.h>
+#include <linux/poll.h>
+#include <linux/range.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <uapi/linux/vm_sockets.h>
+
+#include "ne_misc_dev.h"
+#include "ne_pci_dev.h"
+
+/**
+ * NE_CPUS_SIZE - Size for max 128 CPUs, for now, in a cpu-list string, comma
+ * separated. The NE CPU pool includes CPUs from a single NUMA
+ * node.
+ */
+#define NE_CPUS_SIZE (512)
+
+/**
+ * NE_EIF_LOAD_OFFSET - The offset where to copy the Enclave Image Format (EIF)
+ * image in enclave memory.
+ */
+#define NE_EIF_LOAD_OFFSET (8 * 1024UL * 1024UL)
+
+/**
+ * NE_MIN_ENCLAVE_MEM_SIZE - The minimum memory size an enclave can be launched
+ * with.
+ */
+#define NE_MIN_ENCLAVE_MEM_SIZE (64 * 1024UL * 1024UL)
+
+/**
+ * NE_MIN_MEM_REGION_SIZE - The minimum size of an enclave memory region.
+ */
+#define NE_MIN_MEM_REGION_SIZE (2 * 1024UL * 1024UL)
+
+/**
+ * NE_PARENT_VM_CID - The CID for the vsock device of the primary / parent VM.
+ */
+#define NE_PARENT_VM_CID (3)
+
+static long ne_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+
+static const struct file_operations ne_fops = {
+ .owner = THIS_MODULE,
+ .llseek = noop_llseek,
+ .unlocked_ioctl = ne_ioctl,
+};
+
+static struct miscdevice ne_misc_dev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "nitro_enclaves",
+ .fops = &ne_fops,
+ .mode = 0660,
+};
+
+struct ne_devs ne_devs = {
+ .ne_misc_dev = &ne_misc_dev,
+};
+
+/*
+ * TODO: Update logic to create new sysfs entries instead of using
+ * a kernel parameter e.g. if multiple sysfs files needed.
+ */
+static int ne_set_kernel_param(const char *val, const struct kernel_param *kp);
+
+static const struct kernel_param_ops ne_cpu_pool_ops = {
+ .get = param_get_string,
+ .set = ne_set_kernel_param,
+};
+
+static char ne_cpus[NE_CPUS_SIZE];
+static struct kparam_string ne_cpus_arg = {
+ .maxlen = sizeof(ne_cpus),
+ .string = ne_cpus,
+};
+
+module_param_cb(ne_cpus, &ne_cpu_pool_ops, &ne_cpus_arg, 0644);
+/* https://www.kernel.org/doc/html/latest/admin-guide/kernel-parameters.html#cpu-lists */
+MODULE_PARM_DESC(ne_cpus, "<cpu-list> - CPU pool used for Nitro Enclaves");
+
+/**
+ * struct ne_cpu_pool - CPU pool used for Nitro Enclaves.
+ * @avail_threads_per_core: Available full CPU cores to be dedicated to
+ * enclave(s). The cpumasks from the array, indexed
+ * by core id, contain all the threads from the
+ * available cores, that are not set for created
+ * enclave(s). The full CPU cores are part of the
+ * NE CPU pool.
+ * @mutex: Mutex for the access to the NE CPU pool.
+ * @nr_parent_vm_cores : The size of the available threads per core array.
+ * The total number of CPU cores available on the
+ * primary / parent VM.
+ * @nr_threads_per_core: The number of threads that a full CPU core has.
+ * @numa_node: NUMA node of the CPUs in the pool.
+ */
+struct ne_cpu_pool {
+ cpumask_var_t *avail_threads_per_core;
+ struct mutex mutex;
+ unsigned int nr_parent_vm_cores;
+ unsigned int nr_threads_per_core;
+ int numa_node;
+};
+
+static struct ne_cpu_pool ne_cpu_pool;
+
+/**
+ * struct ne_phys_contig_mem_regions - Contiguous physical memory regions.
+ * @num: The number of regions that currently has.
+ * @regions: The array of physical memory regions.
+ */
+struct ne_phys_contig_mem_regions {
+ unsigned long num;
+ struct range *regions;
+};
+
+/**
+ * ne_check_enclaves_created() - Verify if at least one enclave has been created.
+ * @void: No parameters provided.
+ *
+ * Context: Process context.
+ * Return:
+ * * True if at least one enclave is created.
+ * * False otherwise.
+ */
+static bool ne_check_enclaves_created(void)
+{
+ struct ne_pci_dev *ne_pci_dev = ne_devs.ne_pci_dev;
+ bool ret = false;
+
+ if (!ne_pci_dev)
+ return ret;
+
+ mutex_lock(&ne_pci_dev->enclaves_list_mutex);
+
+ if (!list_empty(&ne_pci_dev->enclaves_list))
+ ret = true;
+
+ mutex_unlock(&ne_pci_dev->enclaves_list_mutex);
+
+ return ret;
+}
+
+/**
+ * ne_setup_cpu_pool() - Set the NE CPU pool after handling sanity checks such
+ * as not sharing CPU cores with the primary / parent VM
+ * or not using CPU 0, which should remain available for
+ * the primary / parent VM. Offline the CPUs from the
+ * pool after the checks passed.
+ * @ne_cpu_list: The CPU list used for setting NE CPU pool.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_setup_cpu_pool(const char *ne_cpu_list)
+{
+ int core_id = -1;
+ unsigned int cpu = 0;
+ cpumask_var_t cpu_pool;
+ unsigned int cpu_sibling = 0;
+ unsigned int i = 0;
+ int numa_node = -1;
+ int rc = -EINVAL;
+
+ if (!zalloc_cpumask_var(&cpu_pool, GFP_KERNEL))
+ return -ENOMEM;
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ rc = cpulist_parse(ne_cpu_list, cpu_pool);
+ if (rc < 0) {
+ pr_err("%s: Error in cpulist parse [rc=%d]\n", ne_misc_dev.name, rc);
+
+ goto free_pool_cpumask;
+ }
+
+ cpu = cpumask_any(cpu_pool);
+ if (cpu >= nr_cpu_ids) {
+ pr_err("%s: No CPUs available in CPU pool\n", ne_misc_dev.name);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+
+ /*
+ * Check if the CPUs are online, to further get info about them
+ * e.g. numa node, core id, siblings.
+ */
+ for_each_cpu(cpu, cpu_pool)
+ if (cpu_is_offline(cpu)) {
+ pr_err("%s: CPU %d is offline, has to be online to get its metadata\n",
+ ne_misc_dev.name, cpu);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+
+ /*
+ * Check if the CPUs from the NE CPU pool are from the same NUMA node.
+ */
+ for_each_cpu(cpu, cpu_pool)
+ if (numa_node < 0) {
+ numa_node = cpu_to_node(cpu);
+ if (numa_node < 0) {
+ pr_err("%s: Invalid NUMA node %d\n",
+ ne_misc_dev.name, numa_node);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+ } else {
+ if (numa_node != cpu_to_node(cpu)) {
+ pr_err("%s: CPUs with different NUMA nodes\n",
+ ne_misc_dev.name);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+ }
+
+ /*
+ * Check if CPU 0 and its siblings are included in the provided CPU pool
+ * They should remain available for the primary / parent VM.
+ */
+ if (cpumask_test_cpu(0, cpu_pool)) {
+ pr_err("%s: CPU 0 has to remain available\n", ne_misc_dev.name);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+
+ for_each_cpu(cpu_sibling, topology_sibling_cpumask(0)) {
+ if (cpumask_test_cpu(cpu_sibling, cpu_pool)) {
+ pr_err("%s: CPU sibling %d for CPU 0 is in CPU pool\n",
+ ne_misc_dev.name, cpu_sibling);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+ }
+
+ /*
+ * Check if CPU siblings are included in the provided CPU pool. The
+ * expectation is that full CPU cores are made available in the CPU pool
+ * for enclaves.
+ */
+ for_each_cpu(cpu, cpu_pool) {
+ for_each_cpu(cpu_sibling, topology_sibling_cpumask(cpu)) {
+ if (!cpumask_test_cpu(cpu_sibling, cpu_pool)) {
+ pr_err("%s: CPU %d is not in CPU pool\n",
+ ne_misc_dev.name, cpu_sibling);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+ }
+ }
+
+ /* Calculate the number of threads from a full CPU core. */
+ cpu = cpumask_any(cpu_pool);
+ for_each_cpu(cpu_sibling, topology_sibling_cpumask(cpu))
+ ne_cpu_pool.nr_threads_per_core++;
+
+ ne_cpu_pool.nr_parent_vm_cores = nr_cpu_ids / ne_cpu_pool.nr_threads_per_core;
+
+ ne_cpu_pool.avail_threads_per_core = kcalloc(ne_cpu_pool.nr_parent_vm_cores,
+ sizeof(*ne_cpu_pool.avail_threads_per_core),
+ GFP_KERNEL);
+ if (!ne_cpu_pool.avail_threads_per_core) {
+ rc = -ENOMEM;
+
+ goto free_pool_cpumask;
+ }
+
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ if (!zalloc_cpumask_var(&ne_cpu_pool.avail_threads_per_core[i], GFP_KERNEL)) {
+ rc = -ENOMEM;
+
+ goto free_cores_cpumask;
+ }
+
+ /*
+ * Split the NE CPU pool in threads per core to keep the CPU topology
+ * after offlining the CPUs.
+ */
+ for_each_cpu(cpu, cpu_pool) {
+ core_id = topology_core_id(cpu);
+ if (core_id < 0 || core_id >= ne_cpu_pool.nr_parent_vm_cores) {
+ pr_err("%s: Invalid core id %d for CPU %d\n",
+ ne_misc_dev.name, core_id, cpu);
+
+ rc = -EINVAL;
+
+ goto clear_cpumask;
+ }
+
+ cpumask_set_cpu(cpu, ne_cpu_pool.avail_threads_per_core[core_id]);
+ }
+
+ /*
+ * CPUs that are given to enclave(s) should not be considered online
+ * by Linux anymore, as the hypervisor will degrade them to floating.
+ * The physical CPUs (full cores) are carved out of the primary / parent
+ * VM and given to the enclave VM. The same number of vCPUs would run
+ * on less pCPUs for the primary / parent VM.
+ *
+ * We offline them here, to not degrade performance and expose correct
+ * topology to Linux and user space.
+ */
+ for_each_cpu(cpu, cpu_pool) {
+ rc = remove_cpu(cpu);
+ if (rc != 0) {
+ pr_err("%s: CPU %d is not offlined [rc=%d]\n",
+ ne_misc_dev.name, cpu, rc);
+
+ goto online_cpus;
+ }
+ }
+
+ free_cpumask_var(cpu_pool);
+
+ ne_cpu_pool.numa_node = numa_node;
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return 0;
+
+online_cpus:
+ for_each_cpu(cpu, cpu_pool)
+ add_cpu(cpu);
+clear_cpumask:
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ cpumask_clear(ne_cpu_pool.avail_threads_per_core[i]);
+free_cores_cpumask:
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ free_cpumask_var(ne_cpu_pool.avail_threads_per_core[i]);
+ kfree(ne_cpu_pool.avail_threads_per_core);
+free_pool_cpumask:
+ free_cpumask_var(cpu_pool);
+ ne_cpu_pool.nr_parent_vm_cores = 0;
+ ne_cpu_pool.nr_threads_per_core = 0;
+ ne_cpu_pool.numa_node = -1;
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return rc;
+}
+
+/**
+ * ne_teardown_cpu_pool() - Online the CPUs from the NE CPU pool and cleanup the
+ * CPU pool.
+ * @void: No parameters provided.
+ *
+ * Context: Process context.
+ */
+static void ne_teardown_cpu_pool(void)
+{
+ unsigned int cpu = 0;
+ unsigned int i = 0;
+ int rc = -EINVAL;
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ if (!ne_cpu_pool.nr_parent_vm_cores) {
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return;
+ }
+
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++) {
+ for_each_cpu(cpu, ne_cpu_pool.avail_threads_per_core[i]) {
+ rc = add_cpu(cpu);
+ if (rc != 0)
+ pr_err("%s: CPU %d is not onlined [rc=%d]\n",
+ ne_misc_dev.name, cpu, rc);
+ }
+
+ cpumask_clear(ne_cpu_pool.avail_threads_per_core[i]);
+
+ free_cpumask_var(ne_cpu_pool.avail_threads_per_core[i]);
+ }
+
+ kfree(ne_cpu_pool.avail_threads_per_core);
+ ne_cpu_pool.nr_parent_vm_cores = 0;
+ ne_cpu_pool.nr_threads_per_core = 0;
+ ne_cpu_pool.numa_node = -1;
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+}
+
+/**
+ * ne_set_kernel_param() - Set the NE CPU pool value via the NE kernel parameter.
+ * @val: NE CPU pool string value.
+ * @kp : NE kernel parameter associated with the NE CPU pool.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_set_kernel_param(const char *val, const struct kernel_param *kp)
+{
+ char error_val[] = "";
+ int rc = -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (ne_check_enclaves_created()) {
+ pr_err("%s: The CPU pool is used by enclave(s)\n", ne_misc_dev.name);
+
+ return -EPERM;
+ }
+
+ ne_teardown_cpu_pool();
+
+ rc = ne_setup_cpu_pool(val);
+ if (rc < 0) {
+ pr_err("%s: Error in setup CPU pool [rc=%d]\n", ne_misc_dev.name, rc);
+
+ param_set_copystring(error_val, kp);
+
+ return rc;
+ }
+
+ rc = param_set_copystring(val, kp);
+ if (rc < 0) {
+ pr_err("%s: Error in param set copystring [rc=%d]\n", ne_misc_dev.name, rc);
+
+ ne_teardown_cpu_pool();
+
+ param_set_copystring(error_val, kp);
+
+ return rc;
+ }
+
+ return 0;
+}
+
+/**
+ * ne_donated_cpu() - Check if the provided CPU is already used by the enclave.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @cpu: CPU to check if already used.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * True if the provided CPU is already used by the enclave.
+ * * False otherwise.
+ */
+static bool ne_donated_cpu(struct ne_enclave *ne_enclave, unsigned int cpu)
+{
+ if (cpumask_test_cpu(cpu, ne_enclave->vcpu_ids))
+ return true;
+
+ return false;
+}
+
+/**
+ * ne_get_unused_core_from_cpu_pool() - Get the id of a full core from the
+ * NE CPU pool.
+ * @void: No parameters provided.
+ *
+ * Context: Process context. This function is called with the ne_enclave and
+ * ne_cpu_pool mutexes held.
+ * Return:
+ * * Core id.
+ * * -1 if no CPU core available in the pool.
+ */
+static int ne_get_unused_core_from_cpu_pool(void)
+{
+ int core_id = -1;
+ unsigned int i = 0;
+
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ if (!cpumask_empty(ne_cpu_pool.avail_threads_per_core[i])) {
+ core_id = i;
+
+ break;
+ }
+
+ return core_id;
+}
+
+/**
+ * ne_set_enclave_threads_per_core() - Set the threads of the provided core in
+ * the enclave data structure.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @core_id: Core id to get its threads from the NE CPU pool.
+ * @vcpu_id: vCPU id part of the provided core.
+ *
+ * Context: Process context. This function is called with the ne_enclave and
+ * ne_cpu_pool mutexes held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_set_enclave_threads_per_core(struct ne_enclave *ne_enclave,
+ int core_id, u32 vcpu_id)
+{
+ unsigned int cpu = 0;
+
+ if (core_id < 0 && vcpu_id == 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "No CPUs available in NE CPU pool\n");
+
+ return -NE_ERR_NO_CPUS_AVAIL_IN_POOL;
+ }
+
+ if (core_id < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "CPU %d is not in NE CPU pool\n", vcpu_id);
+
+ return -NE_ERR_VCPU_NOT_IN_CPU_POOL;
+ }
+
+ if (core_id >= ne_enclave->nr_parent_vm_cores) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Invalid core id %d - ne_enclave\n", core_id);
+
+ return -NE_ERR_VCPU_INVALID_CPU_CORE;
+ }
+
+ for_each_cpu(cpu, ne_cpu_pool.avail_threads_per_core[core_id])
+ cpumask_set_cpu(cpu, ne_enclave->threads_per_core[core_id]);
+
+ cpumask_clear(ne_cpu_pool.avail_threads_per_core[core_id]);
+
+ return 0;
+}
+
+/**
+ * ne_get_cpu_from_cpu_pool() - Get a CPU from the NE CPU pool, either from the
+ * remaining sibling(s) of a CPU core or the first
+ * sibling of a new CPU core.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @vcpu_id: vCPU to get from the NE CPU pool.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_get_cpu_from_cpu_pool(struct ne_enclave *ne_enclave, u32 *vcpu_id)
+{
+ int core_id = -1;
+ unsigned int cpu = 0;
+ unsigned int i = 0;
+ int rc = -EINVAL;
+
+ /*
+ * If previously allocated a thread of a core to this enclave, first
+ * check remaining sibling(s) for new CPU allocations, so that full
+ * CPU cores are used for the enclave.
+ */
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++)
+ for_each_cpu(cpu, ne_enclave->threads_per_core[i])
+ if (!ne_donated_cpu(ne_enclave, cpu)) {
+ *vcpu_id = cpu;
+
+ return 0;
+ }
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ /*
+ * If no remaining siblings, get a core from the NE CPU pool and keep
+ * track of all the threads in the enclave threads per core data structure.
+ */
+ core_id = ne_get_unused_core_from_cpu_pool();
+
+ rc = ne_set_enclave_threads_per_core(ne_enclave, core_id, *vcpu_id);
+ if (rc < 0)
+ goto unlock_mutex;
+
+ *vcpu_id = cpumask_any(ne_enclave->threads_per_core[core_id]);
+
+ rc = 0;
+
+unlock_mutex:
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return rc;
+}
+
+/**
+ * ne_get_vcpu_core_from_cpu_pool() - Get from the NE CPU pool the id of the
+ * core associated with the provided vCPU.
+ * @vcpu_id: Provided vCPU id to get its associated core id.
+ *
+ * Context: Process context. This function is called with the ne_enclave and
+ * ne_cpu_pool mutexes held.
+ * Return:
+ * * Core id.
+ * * -1 if the provided vCPU is not in the pool.
+ */
+static int ne_get_vcpu_core_from_cpu_pool(u32 vcpu_id)
+{
+ int core_id = -1;
+ unsigned int i = 0;
+
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ if (cpumask_test_cpu(vcpu_id, ne_cpu_pool.avail_threads_per_core[i])) {
+ core_id = i;
+
+ break;
+ }
+
+ return core_id;
+}
+
+/**
+ * ne_check_cpu_in_cpu_pool() - Check if the given vCPU is in the available CPUs
+ * from the pool.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @vcpu_id: ID of the vCPU to check if available in the NE CPU pool.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_check_cpu_in_cpu_pool(struct ne_enclave *ne_enclave, u32 vcpu_id)
+{
+ int core_id = -1;
+ unsigned int i = 0;
+ int rc = -EINVAL;
+
+ if (ne_donated_cpu(ne_enclave, vcpu_id)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "CPU %d already used\n", vcpu_id);
+
+ return -NE_ERR_VCPU_ALREADY_USED;
+ }
+
+ /*
+ * If previously allocated a thread of a core to this enclave, but not
+ * the full core, first check remaining sibling(s).
+ */
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++)
+ if (cpumask_test_cpu(vcpu_id, ne_enclave->threads_per_core[i]))
+ return 0;
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ /*
+ * If no remaining siblings, get from the NE CPU pool the core
+ * associated with the vCPU and keep track of all the threads in the
+ * enclave threads per core data structure.
+ */
+ core_id = ne_get_vcpu_core_from_cpu_pool(vcpu_id);
+
+ rc = ne_set_enclave_threads_per_core(ne_enclave, core_id, vcpu_id);
+ if (rc < 0)
+ goto unlock_mutex;
+
+ rc = 0;
+
+unlock_mutex:
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return rc;
+}
+
+/**
+ * ne_add_vcpu_ioctl() - Add a vCPU to the slot associated with the current
+ * enclave.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @vcpu_id: ID of the CPU to be associated with the given slot,
+ * apic id on x86.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_add_vcpu_ioctl(struct ne_enclave *ne_enclave, u32 vcpu_id)
+{
+ struct ne_pci_dev_cmd_reply cmd_reply = {};
+ struct pci_dev *pdev = ne_devs.ne_pci_dev->pdev;
+ int rc = -EINVAL;
+ struct slot_add_vcpu_req slot_add_vcpu_req = {};
+
+ if (ne_enclave->mm != current->mm)
+ return -EIO;
+
+ slot_add_vcpu_req.slot_uid = ne_enclave->slot_uid;
+ slot_add_vcpu_req.vcpu_id = vcpu_id;
+
+ rc = ne_do_request(pdev, SLOT_ADD_VCPU,
+ &slot_add_vcpu_req, sizeof(slot_add_vcpu_req),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in slot add vCPU [rc=%d]\n", rc);
+
+ return rc;
+ }
+
+ cpumask_set_cpu(vcpu_id, ne_enclave->vcpu_ids);
+
+ ne_enclave->nr_vcpus++;
+
+ return 0;
+}
+
+/**
+ * ne_sanity_check_user_mem_region() - Sanity check the user space memory
+ * region received during the set user
+ * memory region ioctl call.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @mem_region : User space memory region to be sanity checked.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 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)
+{
+ struct ne_mem_region *ne_mem_region = NULL;
+
+ if (ne_enclave->mm != current->mm)
+ return -EIO;
+
+ if (mem_region.memory_size & (NE_MIN_MEM_REGION_SIZE - 1)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "User space memory size is not multiple of 2 MiB\n");
+
+ return -NE_ERR_INVALID_MEM_REGION_SIZE;
+ }
+
+ if (!IS_ALIGNED(mem_region.userspace_addr, NE_MIN_MEM_REGION_SIZE)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "User space address is not 2 MiB aligned\n");
+
+ return -NE_ERR_UNALIGNED_MEM_REGION_ADDR;
+ }
+
+ 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 address range\n");
+
+ return -NE_ERR_INVALID_MEM_REGION_ADDR;
+ }
+
+ list_for_each_entry(ne_mem_region, &ne_enclave->mem_regions_list,
+ mem_region_list_entry) {
+ u64 memory_size = ne_mem_region->memory_size;
+ u64 userspace_addr = ne_mem_region->userspace_addr;
+
+ if ((userspace_addr <= mem_region.userspace_addr &&
+ mem_region.userspace_addr < (userspace_addr + memory_size)) ||
+ (mem_region.userspace_addr <= userspace_addr &&
+ (mem_region.userspace_addr + mem_region.memory_size) > userspace_addr)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "User space memory region already used\n");
+
+ return -NE_ERR_MEM_REGION_ALREADY_USED;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ne_sanity_check_user_mem_region_page() - Sanity check a page from the user space
+ * memory region received during the set
+ * user memory region ioctl call.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @mem_region_page: Page from the user space memory region to be sanity checked.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_sanity_check_user_mem_region_page(struct ne_enclave *ne_enclave,
+ struct page *mem_region_page)
+{
+ if (!PageHuge(mem_region_page)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Not a hugetlbfs page\n");
+
+ return -NE_ERR_MEM_NOT_HUGE_PAGE;
+ }
+
+ if (page_size(mem_region_page) & (NE_MIN_MEM_REGION_SIZE - 1)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Page size not multiple of 2 MiB\n");
+
+ return -NE_ERR_INVALID_PAGE_SIZE;
+ }
+
+ if (ne_enclave->numa_node != page_to_nid(mem_region_page)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Page is not from NUMA node %d\n",
+ ne_enclave->numa_node);
+
+ return -NE_ERR_MEM_DIFFERENT_NUMA_NODE;
+ }
+
+ return 0;
+}
+
+/**
+ * ne_sanity_check_phys_mem_region() - Sanity check the start address and the size
+ * of a physical memory region.
+ * @phys_mem_region_paddr : Physical start address of the region to be sanity checked.
+ * @phys_mem_region_size : Length of the region to be sanity checked.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_sanity_check_phys_mem_region(u64 phys_mem_region_paddr,
+ u64 phys_mem_region_size)
+{
+ if (phys_mem_region_size & (NE_MIN_MEM_REGION_SIZE - 1)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Physical mem region size is not multiple of 2 MiB\n");
+
+ return -EINVAL;
+ }
+
+ if (!IS_ALIGNED(phys_mem_region_paddr, NE_MIN_MEM_REGION_SIZE)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Physical mem region address is not 2 MiB aligned\n");
+
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * ne_merge_phys_contig_memory_regions() - Add a memory region and merge the adjacent
+ * regions if they are physically contiguous.
+ * @phys_contig_regions : Private data associated with the contiguous physical memory regions.
+ * @page_paddr : Physical start address of the region to be added.
+ * @page_size : Length of the region to be added.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int
+ne_merge_phys_contig_memory_regions(struct ne_phys_contig_mem_regions *phys_contig_regions,
+ u64 page_paddr, u64 page_size)
+{
+ unsigned long num = phys_contig_regions->num;
+ int rc = 0;
+
+ rc = ne_sanity_check_phys_mem_region(page_paddr, page_size);
+ if (rc < 0)
+ return rc;
+
+ /* Physically contiguous, just merge */
+ if (num && (phys_contig_regions->regions[num - 1].end + 1) == page_paddr) {
+ phys_contig_regions->regions[num - 1].end += page_size;
+ } else {
+ phys_contig_regions->regions[num].start = page_paddr;
+ phys_contig_regions->regions[num].end = page_paddr + page_size - 1;
+ phys_contig_regions->num++;
+ }
+
+ return 0;
+}
+
+/**
+ * ne_set_user_memory_region_ioctl() - Add user space memory region to the slot
+ * associated with the current enclave.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @mem_region : User space memory region to be associated with the given slot.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 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)
+{
+ long gup_rc = 0;
+ unsigned long i = 0;
+ unsigned long max_nr_pages = 0;
+ unsigned long memory_size = 0;
+ struct ne_mem_region *ne_mem_region = NULL;
+ struct pci_dev *pdev = ne_devs.ne_pci_dev->pdev;
+ struct ne_phys_contig_mem_regions phys_contig_mem_regions = {};
+ int rc = -EINVAL;
+
+ 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;
+
+ max_nr_pages = mem_region.memory_size / NE_MIN_MEM_REGION_SIZE;
+
+ ne_mem_region->pages = kcalloc(max_nr_pages, sizeof(*ne_mem_region->pages),
+ GFP_KERNEL);
+ if (!ne_mem_region->pages) {
+ rc = -ENOMEM;
+
+ goto free_mem_region;
+ }
+
+ phys_contig_mem_regions.regions = kcalloc(max_nr_pages,
+ sizeof(*phys_contig_mem_regions.regions),
+ GFP_KERNEL);
+ if (!phys_contig_mem_regions.regions) {
+ rc = -ENOMEM;
+
+ goto free_mem_region;
+ }
+
+ do {
+ i = ne_mem_region->nr_pages;
+
+ if (i == max_nr_pages) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Reached max nr of pages in the pages data struct\n");
+
+ rc = -ENOMEM;
+
+ goto put_pages;
+ }
+
+ gup_rc = get_user_pages_unlocked(mem_region.userspace_addr + memory_size, 1,
+ ne_mem_region->pages + i, FOLL_GET);
+
+ if (gup_rc < 0) {
+ rc = gup_rc;
+
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in get user pages [rc=%d]\n", rc);
+
+ goto put_pages;
+ }
+
+ rc = ne_sanity_check_user_mem_region_page(ne_enclave, ne_mem_region->pages[i]);
+ if (rc < 0)
+ goto put_pages;
+
+ rc = ne_merge_phys_contig_memory_regions(&phys_contig_mem_regions,
+ page_to_phys(ne_mem_region->pages[i]),
+ page_size(ne_mem_region->pages[i]));
+ if (rc < 0)
+ goto put_pages;
+
+ memory_size += page_size(ne_mem_region->pages[i]);
+
+ ne_mem_region->nr_pages++;
+ } while (memory_size < mem_region.memory_size);
+
+ if ((ne_enclave->nr_mem_regions + phys_contig_mem_regions.num) >
+ ne_enclave->max_mem_regions) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Reached max memory regions %lld\n",
+ ne_enclave->max_mem_regions);
+
+ rc = -NE_ERR_MEM_MAX_REGIONS;
+
+ goto put_pages;
+ }
+
+ for (i = 0; i < phys_contig_mem_regions.num; i++) {
+ u64 phys_region_addr = phys_contig_mem_regions.regions[i].start;
+ u64 phys_region_size = range_len(&phys_contig_mem_regions.regions[i]);
+
+ rc = ne_sanity_check_phys_mem_region(phys_region_addr, phys_region_size);
+ if (rc < 0)
+ goto put_pages;
+ }
+
+ ne_mem_region->memory_size = mem_region.memory_size;
+ ne_mem_region->userspace_addr = mem_region.userspace_addr;
+
+ list_add(&ne_mem_region->mem_region_list_entry, &ne_enclave->mem_regions_list);
+
+ for (i = 0; i < phys_contig_mem_regions.num; i++) {
+ struct ne_pci_dev_cmd_reply cmd_reply = {};
+ struct slot_add_mem_req slot_add_mem_req = {};
+
+ slot_add_mem_req.slot_uid = ne_enclave->slot_uid;
+ slot_add_mem_req.paddr = phys_contig_mem_regions.regions[i].start;
+ slot_add_mem_req.size = range_len(&phys_contig_mem_regions.regions[i]);
+
+ rc = ne_do_request(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);
+
+ kfree(phys_contig_mem_regions.regions);
+
+ /*
+ * Exit here without put pages as memory regions may
+ * already been added.
+ */
+ return rc;
+ }
+
+ ne_enclave->mem_size += slot_add_mem_req.size;
+ ne_enclave->nr_mem_regions++;
+ }
+
+ kfree(phys_contig_mem_regions.regions);
+
+ return 0;
+
+put_pages:
+ for (i = 0; i < ne_mem_region->nr_pages; i++)
+ put_page(ne_mem_region->pages[i]);
+free_mem_region:
+ kfree(phys_contig_mem_regions.regions);
+ kfree(ne_mem_region->pages);
+ kfree(ne_mem_region);
+
+ return rc;
+}
+
+/**
+ * ne_start_enclave_ioctl() - Trigger enclave start after the enclave resources,
+ * such as memory and CPU, have been set.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @enclave_start_info : Enclave info that includes enclave cid and flags.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_start_enclave_ioctl(struct ne_enclave *ne_enclave,
+ struct ne_enclave_start_info *enclave_start_info)
+{
+ struct ne_pci_dev_cmd_reply cmd_reply = {};
+ unsigned int cpu = 0;
+ struct enclave_start_req enclave_start_req = {};
+ unsigned int i = 0;
+ struct pci_dev *pdev = ne_devs.ne_pci_dev->pdev;
+ int rc = -EINVAL;
+
+ if (!ne_enclave->nr_mem_regions) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave has no mem regions\n");
+
+ return -NE_ERR_NO_MEM_REGIONS_ADDED;
+ }
+
+ if (ne_enclave->mem_size < NE_MIN_ENCLAVE_MEM_SIZE) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave memory is less than %ld\n",
+ NE_MIN_ENCLAVE_MEM_SIZE);
+
+ return -NE_ERR_ENCLAVE_MEM_MIN_SIZE;
+ }
+
+ if (!ne_enclave->nr_vcpus) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave has no vCPUs\n");
+
+ return -NE_ERR_NO_VCPUS_ADDED;
+ }
+
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++)
+ for_each_cpu(cpu, ne_enclave->threads_per_core[i])
+ if (!cpumask_test_cpu(cpu, ne_enclave->vcpu_ids)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Full CPU cores not used\n");
+
+ return -NE_ERR_FULL_CORES_NOT_USED;
+ }
+
+ enclave_start_req.enclave_cid = enclave_start_info->enclave_cid;
+ enclave_start_req.flags = enclave_start_info->flags;
+ enclave_start_req.slot_uid = ne_enclave->slot_uid;
+
+ rc = ne_do_request(pdev, ENCLAVE_START,
+ &enclave_start_req, sizeof(enclave_start_req),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in enclave start [rc=%d]\n", rc);
+
+ return rc;
+ }
+
+ ne_enclave->state = NE_STATE_RUNNING;
+
+ enclave_start_info->enclave_cid = cmd_reply.enclave_cid;
+
+ return 0;
+}
+
+/**
+ * ne_enclave_ioctl() - Ioctl function provided by the enclave file.
+ * @file: File associated with this ioctl function.
+ * @cmd: The command that is set for the ioctl call.
+ * @arg: The argument that is provided for the ioctl call.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static long ne_enclave_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct ne_enclave *ne_enclave = file->private_data;
+
+ switch (cmd) {
+ case NE_ADD_VCPU: {
+ int rc = -EINVAL;
+ u32 vcpu_id = 0;
+
+ if (copy_from_user(&vcpu_id, (void __user *)arg, sizeof(vcpu_id)))
+ 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 is not in init state\n");
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return -NE_ERR_NOT_IN_INIT_STATE;
+ }
+
+ if (vcpu_id >= (ne_enclave->nr_parent_vm_cores *
+ ne_enclave->nr_threads_per_core)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "vCPU id higher than max CPU id\n");
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return -NE_ERR_INVALID_VCPU;
+ }
+
+ if (!vcpu_id) {
+ /* Use the CPU pool for choosing a CPU for the enclave. */
+ rc = ne_get_cpu_from_cpu_pool(ne_enclave, &vcpu_id);
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in get CPU from pool [rc=%d]\n",
+ rc);
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return rc;
+ }
+ } else {
+ /* Check if the provided vCPU is available in the NE CPU pool. */
+ rc = ne_check_cpu_in_cpu_pool(ne_enclave, vcpu_id);
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in check CPU %d in pool [rc=%d]\n",
+ vcpu_id, rc);
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return rc;
+ }
+ }
+
+ rc = ne_add_vcpu_ioctl(ne_enclave, vcpu_id);
+ if (rc < 0) {
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return rc;
+ }
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ if (copy_to_user((void __user *)arg, &vcpu_id, sizeof(vcpu_id)))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ case NE_GET_IMAGE_LOAD_INFO: {
+ struct ne_image_load_info image_load_info = {};
+
+ if (copy_from_user(&image_load_info, (void __user *)arg, sizeof(image_load_info)))
+ 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 is not in init state\n");
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return -NE_ERR_NOT_IN_INIT_STATE;
+ }
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ if (!image_load_info.flags ||
+ image_load_info.flags >= NE_IMAGE_LOAD_MAX_FLAG_VAL) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Incorrect flag in enclave image load info\n");
+
+ return -NE_ERR_INVALID_FLAG_VALUE;
+ }
+
+ if (image_load_info.flags == NE_EIF_IMAGE)
+ image_load_info.memory_offset = NE_EIF_LOAD_OFFSET;
+
+ if (copy_to_user((void __user *)arg, &image_load_info, sizeof(image_load_info)))
+ return -EFAULT;
+
+ 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 __user *)arg, sizeof(mem_region)))
+ return -EFAULT;
+
+ if (mem_region.flags >= NE_MEMORY_REGION_MAX_FLAG_VAL) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Incorrect flag for user memory region\n");
+
+ return -NE_ERR_INVALID_FLAG_VALUE;
+ }
+
+ mutex_lock(&ne_enclave->enclave_info_mutex);
+
+ if (ne_enclave->state != NE_STATE_INIT) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave is not in init state\n");
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return -NE_ERR_NOT_IN_INIT_STATE;
+ }
+
+ rc = ne_set_user_memory_region_ioctl(ne_enclave, mem_region);
+ if (rc < 0) {
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return rc;
+ }
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return 0;
+ }
+
+ case NE_START_ENCLAVE: {
+ struct ne_enclave_start_info enclave_start_info = {};
+ int rc = -EINVAL;
+
+ if (copy_from_user(&enclave_start_info, (void __user *)arg,
+ sizeof(enclave_start_info)))
+ return -EFAULT;
+
+ if (enclave_start_info.flags >= NE_ENCLAVE_START_MAX_FLAG_VAL) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Incorrect flag in enclave start info\n");
+
+ return -NE_ERR_INVALID_FLAG_VALUE;
+ }
+
+ /*
+ * Do not use well-known CIDs - 0, 1, 2 - for enclaves.
+ * VMADDR_CID_ANY = -1U
+ * VMADDR_CID_HYPERVISOR = 0
+ * VMADDR_CID_LOCAL = 1
+ * VMADDR_CID_HOST = 2
+ * Note: 0 is used as a placeholder to auto-generate an enclave CID.
+ * http://man7.org/linux/man-pages/man7/vsock.7.html
+ */
+ if (enclave_start_info.enclave_cid > 0 &&
+ enclave_start_info.enclave_cid <= VMADDR_CID_HOST) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Well-known CID value, not to be used for enclaves\n");
+
+ return -NE_ERR_INVALID_ENCLAVE_CID;
+ }
+
+ if (enclave_start_info.enclave_cid == U32_MAX) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Well-known CID value, not to be used for enclaves\n");
+
+ return -NE_ERR_INVALID_ENCLAVE_CID;
+ }
+
+ /*
+ * Do not use the CID of the primary / parent VM for enclaves.
+ */
+ if (enclave_start_info.enclave_cid == NE_PARENT_VM_CID) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "CID of the parent VM, not to be used for enclaves\n");
+
+ return -NE_ERR_INVALID_ENCLAVE_CID;
+ }
+
+ /* 64-bit CIDs are not yet supported for the vsock device. */
+ if (enclave_start_info.enclave_cid > U32_MAX) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "64-bit CIDs not yet supported for the vsock device\n");
+
+ return -NE_ERR_INVALID_ENCLAVE_CID;
+ }
+
+ mutex_lock(&ne_enclave->enclave_info_mutex);
+
+ if (ne_enclave->state != NE_STATE_INIT) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave is not in init state\n");
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return -NE_ERR_NOT_IN_INIT_STATE;
+ }
+
+ rc = ne_start_enclave_ioctl(ne_enclave, &enclave_start_info);
+ if (rc < 0) {
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return rc;
+ }
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ if (copy_to_user((void __user *)arg, &enclave_start_info,
+ sizeof(enclave_start_info)))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ default:
+ return -ENOTTY;
+ }
+
+ return 0;
+}
+
+/**
+ * ne_enclave_remove_all_mem_region_entries() - Remove all memory region entries
+ * from the enclave data structure.
+ * @ne_enclave : Private data associated with the current enclave.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ */
+static void ne_enclave_remove_all_mem_region_entries(struct ne_enclave *ne_enclave)
+{
+ unsigned long i = 0;
+ struct ne_mem_region *ne_mem_region = NULL;
+ struct ne_mem_region *ne_mem_region_tmp = NULL;
+
+ list_for_each_entry_safe(ne_mem_region, ne_mem_region_tmp,
+ &ne_enclave->mem_regions_list,
+ mem_region_list_entry) {
+ list_del(&ne_mem_region->mem_region_list_entry);
+
+ for (i = 0; i < ne_mem_region->nr_pages; i++)
+ put_page(ne_mem_region->pages[i]);
+
+ kfree(ne_mem_region->pages);
+
+ kfree(ne_mem_region);
+ }
+}
+
+/**
+ * ne_enclave_remove_all_vcpu_id_entries() - Remove all vCPU id entries from
+ * the enclave data structure.
+ * @ne_enclave : Private data associated with the current enclave.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ */
+static void ne_enclave_remove_all_vcpu_id_entries(struct ne_enclave *ne_enclave)
+{
+ unsigned int cpu = 0;
+ unsigned int i = 0;
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++) {
+ for_each_cpu(cpu, ne_enclave->threads_per_core[i])
+ /* Update the available NE CPU pool. */
+ cpumask_set_cpu(cpu, ne_cpu_pool.avail_threads_per_core[i]);
+
+ free_cpumask_var(ne_enclave->threads_per_core[i]);
+ }
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ kfree(ne_enclave->threads_per_core);
+
+ free_cpumask_var(ne_enclave->vcpu_ids);
+}
+
+/**
+ * ne_pci_dev_remove_enclave_entry() - Remove the enclave entry from the data
+ * structure that is part of the NE PCI
+ * device private data.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @ne_pci_dev : Private data associated with the PCI device.
+ *
+ * Context: Process context. This function is called with the ne_pci_dev enclave
+ * mutex held.
+ */
+static void ne_pci_dev_remove_enclave_entry(struct ne_enclave *ne_enclave,
+ struct ne_pci_dev *ne_pci_dev)
+{
+ struct ne_enclave *ne_enclave_entry = NULL;
+ struct ne_enclave *ne_enclave_entry_tmp = NULL;
+
+ list_for_each_entry_safe(ne_enclave_entry, ne_enclave_entry_tmp,
+ &ne_pci_dev->enclaves_list, enclave_list_entry) {
+ if (ne_enclave_entry->slot_uid == ne_enclave->slot_uid) {
+ list_del(&ne_enclave_entry->enclave_list_entry);
+
+ break;
+ }
+ }
+}
+
+/**
+ * ne_enclave_release() - Release function provided by the enclave file.
+ * @inode: Inode associated with this file release function.
+ * @file: File associated with this release function.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_enclave_release(struct inode *inode, struct file *file)
+{
+ struct ne_pci_dev_cmd_reply cmd_reply = {};
+ struct enclave_stop_req enclave_stop_request = {};
+ struct ne_enclave *ne_enclave = file->private_data;
+ struct ne_pci_dev *ne_pci_dev = ne_devs.ne_pci_dev;
+ struct pci_dev *pdev = ne_pci_dev->pdev;
+ int rc = -EINVAL;
+ struct slot_free_req slot_free_req = {};
+
+ if (!ne_enclave)
+ return 0;
+
+ /*
+ * Early exit in case there is an error in the enclave creation logic
+ * and fput() is called on the cleanup path.
+ */
+ if (!ne_enclave->slot_uid)
+ return 0;
+
+ /*
+ * Acquire the enclave list mutex before the enclave mutex
+ * in order to avoid deadlocks with @ref ne_event_work_handler.
+ */
+ mutex_lock(&ne_pci_dev->enclaves_list_mutex);
+ mutex_lock(&ne_enclave->enclave_info_mutex);
+
+ if (ne_enclave->state != NE_STATE_INIT && ne_enclave->state != NE_STATE_STOPPED) {
+ enclave_stop_request.slot_uid = ne_enclave->slot_uid;
+
+ rc = ne_do_request(pdev, ENCLAVE_STOP,
+ &enclave_stop_request, sizeof(enclave_stop_request),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in enclave stop [rc=%d]\n", rc);
+
+ goto unlock_mutex;
+ }
+
+ memset(&cmd_reply, 0, sizeof(cmd_reply));
+ }
+
+ slot_free_req.slot_uid = ne_enclave->slot_uid;
+
+ rc = ne_do_request(pdev, SLOT_FREE,
+ &slot_free_req, sizeof(slot_free_req),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in slot free [rc=%d]\n", rc);
+
+ goto unlock_mutex;
+ }
+
+ ne_pci_dev_remove_enclave_entry(ne_enclave, ne_pci_dev);
+ ne_enclave_remove_all_mem_region_entries(ne_enclave);
+ ne_enclave_remove_all_vcpu_id_entries(ne_enclave);
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+ mutex_unlock(&ne_pci_dev->enclaves_list_mutex);
+
+ kfree(ne_enclave);
+
+ return 0;
+
+unlock_mutex:
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+ mutex_unlock(&ne_pci_dev->enclaves_list_mutex);
+
+ return rc;
+}
+
+/**
+ * ne_enclave_poll() - Poll functionality used for enclave out-of-band events.
+ * @file: File associated with this poll function.
+ * @wait: Poll table data structure.
+ *
+ * Context: Process context.
+ * Return:
+ * * Poll mask.
+ */
+static __poll_t ne_enclave_poll(struct file *file, poll_table *wait)
+{
+ __poll_t mask = 0;
+ struct ne_enclave *ne_enclave = file->private_data;
+
+ poll_wait(file, &ne_enclave->eventq, wait);
+
+ if (ne_enclave->has_event)
+ mask |= EPOLLHUP;
+
+ return mask;
+}
+
+static const struct file_operations ne_enclave_fops = {
+ .owner = THIS_MODULE,
+ .llseek = noop_llseek,
+ .poll = ne_enclave_poll,
+ .unlocked_ioctl = ne_enclave_ioctl,
+ .release = ne_enclave_release,
+};
+
+/**
+ * ne_create_vm_ioctl() - Alloc slot to be associated with an enclave. Create
+ * enclave file descriptor to be further used for enclave
+ * resources handling e.g. memory regions and CPUs.
+ * @ne_pci_dev : Private data associated with the PCI device.
+ * @slot_uid: User pointer to store the generated unique slot id
+ * associated with an enclave to.
+ *
+ * Context: Process context. This function is called with the ne_pci_dev enclave
+ * mutex held.
+ * Return:
+ * * Enclave fd on success.
+ * * Negative return value on failure.
+ */
+static int ne_create_vm_ioctl(struct ne_pci_dev *ne_pci_dev, u64 __user *slot_uid)
+{
+ struct ne_pci_dev_cmd_reply cmd_reply = {};
+ int enclave_fd = -1;
+ struct file *enclave_file = NULL;
+ unsigned int i = 0;
+ struct ne_enclave *ne_enclave = NULL;
+ struct pci_dev *pdev = ne_pci_dev->pdev;
+ int rc = -EINVAL;
+ struct slot_alloc_req slot_alloc_req = {};
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ if (!cpumask_empty(ne_cpu_pool.avail_threads_per_core[i]))
+ break;
+
+ if (i == ne_cpu_pool.nr_parent_vm_cores) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "No CPUs available in CPU pool\n");
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return -NE_ERR_NO_CPUS_AVAIL_IN_POOL;
+ }
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ ne_enclave = kzalloc(sizeof(*ne_enclave), GFP_KERNEL);
+ if (!ne_enclave)
+ return -ENOMEM;
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ ne_enclave->nr_parent_vm_cores = ne_cpu_pool.nr_parent_vm_cores;
+ ne_enclave->nr_threads_per_core = ne_cpu_pool.nr_threads_per_core;
+ ne_enclave->numa_node = ne_cpu_pool.numa_node;
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ ne_enclave->threads_per_core = kcalloc(ne_enclave->nr_parent_vm_cores,
+ sizeof(*ne_enclave->threads_per_core),
+ GFP_KERNEL);
+ if (!ne_enclave->threads_per_core) {
+ rc = -ENOMEM;
+
+ goto free_ne_enclave;
+ }
+
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++)
+ if (!zalloc_cpumask_var(&ne_enclave->threads_per_core[i], GFP_KERNEL)) {
+ rc = -ENOMEM;
+
+ goto free_cpumask;
+ }
+
+ if (!zalloc_cpumask_var(&ne_enclave->vcpu_ids, GFP_KERNEL)) {
+ rc = -ENOMEM;
+
+ goto free_cpumask;
+ }
+
+ enclave_fd = get_unused_fd_flags(O_CLOEXEC);
+ if (enclave_fd < 0) {
+ rc = enclave_fd;
+
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in getting unused fd [rc=%d]\n", rc);
+
+ goto free_cpumask;
+ }
+
+ enclave_file = anon_inode_getfile("ne-vm", &ne_enclave_fops, ne_enclave, O_RDWR);
+ if (IS_ERR(enclave_file)) {
+ rc = PTR_ERR(enclave_file);
+
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in anon inode get file [rc=%d]\n", rc);
+
+ goto put_fd;
+ }
+
+ rc = ne_do_request(pdev, SLOT_ALLOC,
+ &slot_alloc_req, sizeof(slot_alloc_req),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in slot alloc [rc=%d]\n", rc);
+
+ goto put_file;
+ }
+
+ init_waitqueue_head(&ne_enclave->eventq);
+ ne_enclave->has_event = false;
+ mutex_init(&ne_enclave->enclave_info_mutex);
+ ne_enclave->max_mem_regions = cmd_reply.mem_regions;
+ INIT_LIST_HEAD(&ne_enclave->mem_regions_list);
+ ne_enclave->mm = current->mm;
+ ne_enclave->slot_uid = cmd_reply.slot_uid;
+ ne_enclave->state = NE_STATE_INIT;
+
+ list_add(&ne_enclave->enclave_list_entry, &ne_pci_dev->enclaves_list);
+
+ if (copy_to_user(slot_uid, &ne_enclave->slot_uid, sizeof(ne_enclave->slot_uid))) {
+ /*
+ * As we're holding the only reference to 'enclave_file', fput()
+ * will call ne_enclave_release() which will do a proper cleanup
+ * of all so far allocated resources, leaving only the unused fd
+ * for us to free.
+ */
+ fput(enclave_file);
+ put_unused_fd(enclave_fd);
+
+ return -EFAULT;
+ }
+
+ fd_install(enclave_fd, enclave_file);
+
+ return enclave_fd;
+
+put_file:
+ fput(enclave_file);
+put_fd:
+ put_unused_fd(enclave_fd);
+free_cpumask:
+ free_cpumask_var(ne_enclave->vcpu_ids);
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++)
+ free_cpumask_var(ne_enclave->threads_per_core[i]);
+ kfree(ne_enclave->threads_per_core);
+free_ne_enclave:
+ kfree(ne_enclave);
+
+ return rc;
+}
+
+/**
+ * ne_ioctl() - Ioctl function provided by the NE misc device.
+ * @file: File associated with this ioctl function.
+ * @cmd: The command that is set for the ioctl call.
+ * @arg: The argument that is provided for the ioctl call.
+ *
+ * Context: Process context.
+ * Return:
+ * * Ioctl result (e.g. enclave file descriptor) on success.
+ * * Negative return value on failure.
+ */
+static long ne_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case NE_CREATE_VM: {
+ int enclave_fd = -1;
+ struct ne_pci_dev *ne_pci_dev = ne_devs.ne_pci_dev;
+ u64 __user *slot_uid = (void __user *)arg;
+
+ mutex_lock(&ne_pci_dev->enclaves_list_mutex);
+ enclave_fd = ne_create_vm_ioctl(ne_pci_dev, slot_uid);
+ mutex_unlock(&ne_pci_dev->enclaves_list_mutex);
+
+ return enclave_fd;
+ }
+
+ default:
+ return -ENOTTY;
+ }
+
+ return 0;
+}
+
+#if defined(CONFIG_NITRO_ENCLAVES_MISC_DEV_TEST)
+#include "ne_misc_dev_test.c"
+#endif
+
+static int __init ne_init(void)
+{
+ mutex_init(&ne_cpu_pool.mutex);
+
+ return pci_register_driver(&ne_pci_driver);
+}
+
+static void __exit ne_exit(void)
+{
+ pci_unregister_driver(&ne_pci_driver);
+
+ ne_teardown_cpu_pool();
+}
+
+module_init(ne_init);
+module_exit(ne_exit);
+
+MODULE_AUTHOR("Amazon.com, Inc. or its affiliates");
+MODULE_DESCRIPTION("Nitro Enclaves Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev.h b/drivers/virt/nitro_enclaves/ne_misc_dev.h
new file mode 100644
index 0000000000..2a4d2224ba
--- /dev/null
+++ b/drivers/virt/nitro_enclaves/ne_misc_dev.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#ifndef _NE_MISC_DEV_H_
+#define _NE_MISC_DEV_H_
+
+#include <linux/cpumask.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/wait.h>
+
+#include "ne_pci_dev.h"
+
+/**
+ * struct ne_mem_region - Entry in the enclave user space memory regions list.
+ * @mem_region_list_entry: Entry in the list of enclave memory regions.
+ * @memory_size: Size of the user space memory region.
+ * @nr_pages: Number of pages that make up the memory region.
+ * @pages: Pages that make up the user space memory region.
+ * @userspace_addr: User space address of the memory region.
+ */
+struct ne_mem_region {
+ struct list_head mem_region_list_entry;
+ u64 memory_size;
+ unsigned long nr_pages;
+ struct page **pages;
+ u64 userspace_addr;
+};
+
+/**
+ * struct ne_enclave - Per-enclave data used for enclave lifetime management.
+ * @enclave_info_mutex : Mutex for accessing this internal state.
+ * @enclave_list_entry : Entry in the list of created enclaves.
+ * @eventq: Wait queue used for out-of-band event notifications
+ * triggered from the PCI device event handler to
+ * the enclave process via the poll function.
+ * @has_event: Variable used to determine if the out-of-band event
+ * was triggered.
+ * @max_mem_regions: The maximum number of memory regions that can be
+ * handled by the hypervisor.
+ * @mem_regions_list: Enclave user space memory regions list.
+ * @mem_size: Enclave memory size.
+ * @mm : Enclave process abstraction mm data struct.
+ * @nr_mem_regions: Number of memory regions associated with the enclave.
+ * @nr_parent_vm_cores : The size of the threads per core array. The
+ * total number of CPU cores available on the
+ * parent / primary VM.
+ * @nr_threads_per_core: The number of threads that a full CPU core has.
+ * @nr_vcpus: Number of vcpus associated with the enclave.
+ * @numa_node: NUMA node of the enclave memory and CPUs.
+ * @slot_uid: Slot unique id mapped to the enclave.
+ * @state: Enclave state, updated during enclave lifetime.
+ * @threads_per_core: Enclave full CPU cores array, indexed by core id,
+ * consisting of cpumasks with all their threads.
+ * Full CPU cores are taken from the NE CPU pool
+ * and are available to the enclave.
+ * @vcpu_ids: Cpumask of the vCPUs that are set for the enclave.
+ */
+struct ne_enclave {
+ struct mutex enclave_info_mutex;
+ struct list_head enclave_list_entry;
+ wait_queue_head_t eventq;
+ bool has_event;
+ u64 max_mem_regions;
+ struct list_head mem_regions_list;
+ u64 mem_size;
+ struct mm_struct *mm;
+ unsigned int nr_mem_regions;
+ unsigned int nr_parent_vm_cores;
+ unsigned int nr_threads_per_core;
+ unsigned int nr_vcpus;
+ int numa_node;
+ u64 slot_uid;
+ u16 state;
+ cpumask_var_t *threads_per_core;
+ cpumask_var_t vcpu_ids;
+};
+
+/**
+ * enum ne_state - States available for an enclave.
+ * @NE_STATE_INIT: The enclave has not been started yet.
+ * @NE_STATE_RUNNING: The enclave was started and is running as expected.
+ * @NE_STATE_STOPPED: The enclave exited without userspace interaction.
+ */
+enum ne_state {
+ NE_STATE_INIT = 0,
+ NE_STATE_RUNNING = 2,
+ NE_STATE_STOPPED = U16_MAX,
+};
+
+/**
+ * struct ne_devs - Data structure to keep refs to the NE misc and PCI devices.
+ * @ne_misc_dev: Nitro Enclaves misc device.
+ * @ne_pci_dev : Nitro Enclaves PCI device.
+ */
+struct ne_devs {
+ struct miscdevice *ne_misc_dev;
+ struct ne_pci_dev *ne_pci_dev;
+};
+
+/* Nitro Enclaves (NE) data structure for keeping refs to the NE misc and PCI devices. */
+extern struct ne_devs ne_devs;
+
+#endif /* _NE_MISC_DEV_H_ */
diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev_test.c b/drivers/virt/nitro_enclaves/ne_misc_dev_test.c
new file mode 100644
index 0000000000..74df43b925
--- /dev/null
+++ b/drivers/virt/nitro_enclaves/ne_misc_dev_test.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <kunit/test.h>
+
+#define MAX_PHYS_REGIONS 16
+#define INVALID_VALUE (~0ull)
+
+struct ne_phys_regions_test {
+ u64 paddr;
+ u64 size;
+ int expect_rc;
+ unsigned long expect_num;
+ u64 expect_last_paddr;
+ u64 expect_last_size;
+} phys_regions_test_cases[] = {
+ /*
+ * Add the region from 0x1000 to (0x1000 + 0x200000 - 1):
+ * Expected result:
+ * Failed, start address is not 2M-aligned
+ *
+ * Now the instance of struct ne_phys_contig_mem_regions is:
+ * num = 0
+ * regions = {}
+ */
+ {0x1000, 0x200000, -EINVAL, 0, INVALID_VALUE, INVALID_VALUE},
+
+ /*
+ * Add the region from 0x200000 to (0x200000 + 0x1000 - 1):
+ * Expected result:
+ * Failed, size is not 2M-aligned
+ *
+ * Now the instance of struct ne_phys_contig_mem_regions is:
+ * num = 0
+ * regions = {}
+ */
+ {0x200000, 0x1000, -EINVAL, 0, INVALID_VALUE, INVALID_VALUE},
+
+ /*
+ * Add the region from 0x200000 to (0x200000 + 0x200000 - 1):
+ * Expected result:
+ * Successful
+ *
+ * Now the instance of struct ne_phys_contig_mem_regions is:
+ * num = 1
+ * regions = {
+ * {start=0x200000, end=0x3fffff}, // len=0x200000
+ * }
+ */
+ {0x200000, 0x200000, 0, 1, 0x200000, 0x200000},
+
+ /*
+ * Add the region from 0x0 to (0x0 + 0x200000 - 1):
+ * Expected result:
+ * Successful
+ *
+ * Now the instance of struct ne_phys_contig_mem_regions is:
+ * num = 2
+ * regions = {
+ * {start=0x200000, end=0x3fffff}, // len=0x200000
+ * {start=0x0, end=0x1fffff}, // len=0x200000
+ * }
+ */
+ {0x0, 0x200000, 0, 2, 0x0, 0x200000},
+
+ /*
+ * Add the region from 0x600000 to (0x600000 + 0x400000 - 1):
+ * Expected result:
+ * Successful
+ *
+ * Now the instance of struct ne_phys_contig_mem_regions is:
+ * num = 3
+ * regions = {
+ * {start=0x200000, end=0x3fffff}, // len=0x200000
+ * {start=0x0, end=0x1fffff}, // len=0x200000
+ * {start=0x600000, end=0x9fffff}, // len=0x400000
+ * }
+ */
+ {0x600000, 0x400000, 0, 3, 0x600000, 0x400000},
+
+ /*
+ * Add the region from 0xa00000 to (0xa00000 + 0x400000 - 1):
+ * Expected result:
+ * Successful, merging case!
+ *
+ * Now the instance of struct ne_phys_contig_mem_regions is:
+ * num = 3
+ * regions = {
+ * {start=0x200000, end=0x3fffff}, // len=0x200000
+ * {start=0x0, end=0x1fffff}, // len=0x200000
+ * {start=0x600000, end=0xdfffff}, // len=0x800000
+ * }
+ */
+ {0xa00000, 0x400000, 0, 3, 0x600000, 0x800000},
+
+ /*
+ * Add the region from 0x1000 to (0x1000 + 0x200000 - 1):
+ * Expected result:
+ * Failed, start address is not 2M-aligned
+ *
+ * Now the instance of struct ne_phys_contig_mem_regions is:
+ * num = 3
+ * regions = {
+ * {start=0x200000, end=0x3fffff}, // len=0x200000
+ * {start=0x0, end=0x1fffff}, // len=0x200000
+ * {start=0x600000, end=0xdfffff}, // len=0x800000
+ * }
+ */
+ {0x1000, 0x200000, -EINVAL, 3, 0x600000, 0x800000},
+};
+
+static void ne_misc_dev_test_merge_phys_contig_memory_regions(struct kunit *test)
+{
+ struct ne_phys_contig_mem_regions phys_contig_mem_regions = {};
+ int rc = 0;
+ int i = 0;
+
+ phys_contig_mem_regions.regions = kunit_kcalloc(test, MAX_PHYS_REGIONS,
+ sizeof(*phys_contig_mem_regions.regions),
+ GFP_KERNEL);
+ KUNIT_ASSERT_TRUE(test, phys_contig_mem_regions.regions);
+
+ for (i = 0; i < ARRAY_SIZE(phys_regions_test_cases); i++) {
+ struct ne_phys_regions_test *test_case = &phys_regions_test_cases[i];
+ unsigned long num = 0;
+
+ rc = ne_merge_phys_contig_memory_regions(&phys_contig_mem_regions,
+ test_case->paddr, test_case->size);
+ KUNIT_EXPECT_EQ(test, rc, test_case->expect_rc);
+ KUNIT_EXPECT_EQ(test, phys_contig_mem_regions.num, test_case->expect_num);
+
+ if (test_case->expect_last_paddr == INVALID_VALUE)
+ continue;
+
+ num = phys_contig_mem_regions.num;
+ KUNIT_EXPECT_EQ(test, phys_contig_mem_regions.regions[num - 1].start,
+ test_case->expect_last_paddr);
+ KUNIT_EXPECT_EQ(test, range_len(&phys_contig_mem_regions.regions[num - 1]),
+ test_case->expect_last_size);
+ }
+
+ kunit_kfree(test, phys_contig_mem_regions.regions);
+}
+
+static struct kunit_case ne_misc_dev_test_cases[] = {
+ KUNIT_CASE(ne_misc_dev_test_merge_phys_contig_memory_regions),
+ {}
+};
+
+static struct kunit_suite ne_misc_dev_test_suite = {
+ .name = "ne_misc_dev_test",
+ .test_cases = ne_misc_dev_test_cases,
+};
+
+kunit_test_suite(ne_misc_dev_test_suite);
diff --git a/drivers/virt/nitro_enclaves/ne_pci_dev.c b/drivers/virt/nitro_enclaves/ne_pci_dev.c
new file mode 100644
index 0000000000..6b81e8f3a5
--- /dev/null
+++ b/drivers/virt/nitro_enclaves/ne_pci_dev.c
@@ -0,0 +1,626 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+/**
+ * DOC: Nitro Enclaves (NE) PCI device driver.
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/nitro_enclaves.h>
+#include <linux/pci.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+
+#include "ne_misc_dev.h"
+#include "ne_pci_dev.h"
+
+/**
+ * NE_DEFAULT_TIMEOUT_MSECS - Default timeout to wait for a reply from
+ * the NE PCI device.
+ */
+#define NE_DEFAULT_TIMEOUT_MSECS (120000) /* 120 sec */
+
+static const struct pci_device_id ne_pci_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, PCI_DEVICE_ID_NE) },
+ { 0, }
+};
+
+MODULE_DEVICE_TABLE(pci, ne_pci_ids);
+
+/**
+ * ne_submit_request() - Submit command request to the PCI device based on the
+ * command type.
+ * @pdev: PCI device to send the command to.
+ * @cmd_type: Command type of the request sent to the PCI device.
+ * @cmd_request: Command request payload.
+ * @cmd_request_size: Size of the command request payload.
+ *
+ * Context: Process context. This function is called with the ne_pci_dev mutex held.
+ */
+static void ne_submit_request(struct pci_dev *pdev, enum ne_pci_dev_cmd_type cmd_type,
+ void *cmd_request, size_t cmd_request_size)
+{
+ struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+ memcpy_toio(ne_pci_dev->iomem_base + NE_SEND_DATA, cmd_request, cmd_request_size);
+
+ iowrite32(cmd_type, ne_pci_dev->iomem_base + NE_COMMAND);
+}
+
+/**
+ * ne_retrieve_reply() - Retrieve reply from the PCI device.
+ * @pdev: PCI device to receive the reply from.
+ * @cmd_reply: Command reply payload.
+ * @cmd_reply_size: Size of the command reply payload.
+ *
+ * Context: Process context. This function is called with the ne_pci_dev mutex held.
+ */
+static void ne_retrieve_reply(struct pci_dev *pdev, struct ne_pci_dev_cmd_reply *cmd_reply,
+ size_t cmd_reply_size)
+{
+ struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+ memcpy_fromio(cmd_reply, ne_pci_dev->iomem_base + NE_RECV_DATA, cmd_reply_size);
+}
+
+/**
+ * ne_wait_for_reply() - Wait for a reply of a PCI device command.
+ * @pdev: PCI device for which a reply is waited.
+ *
+ * Context: Process context. This function is called with the ne_pci_dev mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_wait_for_reply(struct pci_dev *pdev)
+{
+ struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+ int rc = -EINVAL;
+
+ /*
+ * TODO: Update to _interruptible and handle interrupted wait event
+ * e.g. -ERESTARTSYS, incoming signals + update timeout, if needed.
+ */
+ rc = wait_event_timeout(ne_pci_dev->cmd_reply_wait_q,
+ atomic_read(&ne_pci_dev->cmd_reply_avail) != 0,
+ msecs_to_jiffies(NE_DEFAULT_TIMEOUT_MSECS));
+ if (!rc)
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
+int ne_do_request(struct pci_dev *pdev, enum ne_pci_dev_cmd_type cmd_type,
+ void *cmd_request, size_t cmd_request_size,
+ struct ne_pci_dev_cmd_reply *cmd_reply, size_t cmd_reply_size)
+{
+ struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+ int rc = -EINVAL;
+
+ if (cmd_type <= INVALID_CMD || cmd_type >= MAX_CMD) {
+ dev_err_ratelimited(&pdev->dev, "Invalid cmd type=%u\n", cmd_type);
+
+ return -EINVAL;
+ }
+
+ if (!cmd_request) {
+ dev_err_ratelimited(&pdev->dev, "Null cmd request for cmd type=%u\n",
+ cmd_type);
+
+ return -EINVAL;
+ }
+
+ if (cmd_request_size > NE_SEND_DATA_SIZE) {
+ dev_err_ratelimited(&pdev->dev, "Invalid req size=%zu for cmd type=%u\n",
+ cmd_request_size, cmd_type);
+
+ return -EINVAL;
+ }
+
+ if (!cmd_reply) {
+ dev_err_ratelimited(&pdev->dev, "Null cmd reply for cmd type=%u\n",
+ cmd_type);
+
+ return -EINVAL;
+ }
+
+ if (cmd_reply_size > NE_RECV_DATA_SIZE) {
+ dev_err_ratelimited(&pdev->dev, "Invalid reply size=%zu for cmd type=%u\n",
+ cmd_reply_size, cmd_type);
+
+ return -EINVAL;
+ }
+
+ /*
+ * Use this mutex so that the PCI device handles one command request at
+ * a time.
+ */
+ mutex_lock(&ne_pci_dev->pci_dev_mutex);
+
+ atomic_set(&ne_pci_dev->cmd_reply_avail, 0);
+
+ ne_submit_request(pdev, cmd_type, cmd_request, cmd_request_size);
+
+ rc = ne_wait_for_reply(pdev);
+ if (rc < 0) {
+ dev_err_ratelimited(&pdev->dev, "Error in wait for reply for cmd type=%u [rc=%d]\n",
+ cmd_type, rc);
+
+ goto unlock_mutex;
+ }
+
+ ne_retrieve_reply(pdev, cmd_reply, cmd_reply_size);
+
+ atomic_set(&ne_pci_dev->cmd_reply_avail, 0);
+
+ if (cmd_reply->rc < 0) {
+ rc = cmd_reply->rc;
+
+ dev_err_ratelimited(&pdev->dev, "Error in cmd process logic, cmd type=%u [rc=%d]\n",
+ cmd_type, rc);
+
+ goto unlock_mutex;
+ }
+
+ rc = 0;
+
+unlock_mutex:
+ mutex_unlock(&ne_pci_dev->pci_dev_mutex);
+
+ return rc;
+}
+
+/**
+ * ne_reply_handler() - Interrupt handler for retrieving a reply matching a
+ * request sent to the PCI device for enclave lifetime
+ * management.
+ * @irq: Received interrupt for a reply sent by the PCI device.
+ * @args: PCI device private data structure.
+ *
+ * Context: Interrupt context.
+ * Return:
+ * * IRQ_HANDLED on handled interrupt.
+ */
+static irqreturn_t ne_reply_handler(int irq, void *args)
+{
+ struct ne_pci_dev *ne_pci_dev = (struct ne_pci_dev *)args;
+
+ atomic_set(&ne_pci_dev->cmd_reply_avail, 1);
+
+ /* TODO: Update to _interruptible. */
+ wake_up(&ne_pci_dev->cmd_reply_wait_q);
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * ne_event_work_handler() - Work queue handler for notifying enclaves on a
+ * state change received by the event interrupt
+ * handler.
+ * @work: Item containing the NE PCI device for which an out-of-band event
+ * was issued.
+ *
+ * An out-of-band event is being issued by the Nitro Hypervisor when at least
+ * one enclave is changing state without client interaction.
+ *
+ * Context: Work queue context.
+ */
+static void ne_event_work_handler(struct work_struct *work)
+{
+ struct ne_pci_dev_cmd_reply cmd_reply = {};
+ struct ne_enclave *ne_enclave = NULL;
+ struct ne_pci_dev *ne_pci_dev =
+ container_of(work, struct ne_pci_dev, notify_work);
+ struct pci_dev *pdev = ne_pci_dev->pdev;
+ int rc = -EINVAL;
+ struct slot_info_req slot_info_req = {};
+
+ mutex_lock(&ne_pci_dev->enclaves_list_mutex);
+
+ /*
+ * Iterate over all enclaves registered for the Nitro Enclaves
+ * PCI device and determine for which enclave(s) the out-of-band event
+ * is corresponding to.
+ */
+ list_for_each_entry(ne_enclave, &ne_pci_dev->enclaves_list, enclave_list_entry) {
+ mutex_lock(&ne_enclave->enclave_info_mutex);
+
+ /*
+ * Enclaves that were never started cannot receive out-of-band
+ * events.
+ */
+ if (ne_enclave->state != NE_STATE_RUNNING)
+ goto unlock;
+
+ slot_info_req.slot_uid = ne_enclave->slot_uid;
+
+ rc = ne_do_request(pdev, SLOT_INFO,
+ &slot_info_req, sizeof(slot_info_req),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0)
+ dev_err(&pdev->dev, "Error in slot info [rc=%d]\n", rc);
+
+ /* Notify enclave process that the enclave state changed. */
+ if (ne_enclave->state != cmd_reply.state) {
+ ne_enclave->state = cmd_reply.state;
+
+ ne_enclave->has_event = true;
+
+ wake_up_interruptible(&ne_enclave->eventq);
+ }
+
+unlock:
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+ }
+
+ mutex_unlock(&ne_pci_dev->enclaves_list_mutex);
+}
+
+/**
+ * ne_event_handler() - Interrupt handler for PCI device out-of-band events.
+ * This interrupt does not supply any data in the MMIO
+ * region. It notifies a change in the state of any of
+ * the launched enclaves.
+ * @irq: Received interrupt for an out-of-band event.
+ * @args: PCI device private data structure.
+ *
+ * Context: Interrupt context.
+ * Return:
+ * * IRQ_HANDLED on handled interrupt.
+ */
+static irqreturn_t ne_event_handler(int irq, void *args)
+{
+ struct ne_pci_dev *ne_pci_dev = (struct ne_pci_dev *)args;
+
+ queue_work(ne_pci_dev->event_wq, &ne_pci_dev->notify_work);
+
+ return IRQ_HANDLED;
+}
+
+/**
+ * ne_setup_msix() - Setup MSI-X vectors for the PCI device.
+ * @pdev: PCI device to setup the MSI-X for.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_setup_msix(struct pci_dev *pdev)
+{
+ struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+ int nr_vecs = 0;
+ int rc = -EINVAL;
+
+ nr_vecs = pci_msix_vec_count(pdev);
+ if (nr_vecs < 0) {
+ rc = nr_vecs;
+
+ dev_err(&pdev->dev, "Error in getting vec count [rc=%d]\n", rc);
+
+ return rc;
+ }
+
+ rc = pci_alloc_irq_vectors(pdev, nr_vecs, nr_vecs, PCI_IRQ_MSIX);
+ if (rc < 0) {
+ dev_err(&pdev->dev, "Error in alloc MSI-X vecs [rc=%d]\n", rc);
+
+ return rc;
+ }
+
+ /*
+ * This IRQ gets triggered every time the PCI device responds to a
+ * command request. The reply is then retrieved, reading from the MMIO
+ * space of the PCI device.
+ */
+ rc = request_irq(pci_irq_vector(pdev, NE_VEC_REPLY), ne_reply_handler,
+ 0, "enclave_cmd", ne_pci_dev);
+ if (rc < 0) {
+ dev_err(&pdev->dev, "Error in request irq reply [rc=%d]\n", rc);
+
+ goto free_irq_vectors;
+ }
+
+ ne_pci_dev->event_wq = create_singlethread_workqueue("ne_pci_dev_wq");
+ if (!ne_pci_dev->event_wq) {
+ rc = -ENOMEM;
+
+ dev_err(&pdev->dev, "Cannot get wq for dev events [rc=%d]\n", rc);
+
+ goto free_reply_irq_vec;
+ }
+
+ INIT_WORK(&ne_pci_dev->notify_work, ne_event_work_handler);
+
+ /*
+ * This IRQ gets triggered every time any enclave's state changes. Its
+ * handler then scans for the changes and propagates them to the user
+ * space.
+ */
+ rc = request_irq(pci_irq_vector(pdev, NE_VEC_EVENT), ne_event_handler,
+ 0, "enclave_evt", ne_pci_dev);
+ if (rc < 0) {
+ dev_err(&pdev->dev, "Error in request irq event [rc=%d]\n", rc);
+
+ goto destroy_wq;
+ }
+
+ return 0;
+
+destroy_wq:
+ destroy_workqueue(ne_pci_dev->event_wq);
+free_reply_irq_vec:
+ free_irq(pci_irq_vector(pdev, NE_VEC_REPLY), ne_pci_dev);
+free_irq_vectors:
+ pci_free_irq_vectors(pdev);
+
+ return rc;
+}
+
+/**
+ * ne_teardown_msix() - Teardown MSI-X vectors for the PCI device.
+ * @pdev: PCI device to teardown the MSI-X for.
+ *
+ * Context: Process context.
+ */
+static void ne_teardown_msix(struct pci_dev *pdev)
+{
+ struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+ free_irq(pci_irq_vector(pdev, NE_VEC_EVENT), ne_pci_dev);
+
+ flush_work(&ne_pci_dev->notify_work);
+ destroy_workqueue(ne_pci_dev->event_wq);
+
+ free_irq(pci_irq_vector(pdev, NE_VEC_REPLY), ne_pci_dev);
+
+ pci_free_irq_vectors(pdev);
+}
+
+/**
+ * ne_pci_dev_enable() - Select the PCI device version and enable it.
+ * @pdev: PCI device to select version for and then enable.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_pci_dev_enable(struct pci_dev *pdev)
+{
+ u8 dev_enable_reply = 0;
+ u16 dev_version_reply = 0;
+ struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+ iowrite16(NE_VERSION_MAX, ne_pci_dev->iomem_base + NE_VERSION);
+
+ dev_version_reply = ioread16(ne_pci_dev->iomem_base + NE_VERSION);
+ if (dev_version_reply != NE_VERSION_MAX) {
+ dev_err(&pdev->dev, "Error in pci dev version cmd\n");
+
+ return -EIO;
+ }
+
+ iowrite8(NE_ENABLE_ON, ne_pci_dev->iomem_base + NE_ENABLE);
+
+ dev_enable_reply = ioread8(ne_pci_dev->iomem_base + NE_ENABLE);
+ if (dev_enable_reply != NE_ENABLE_ON) {
+ dev_err(&pdev->dev, "Error in pci dev enable cmd\n");
+
+ return -EIO;
+ }
+
+ return 0;
+}
+
+/**
+ * ne_pci_dev_disable() - Disable the PCI device.
+ * @pdev: PCI device to disable.
+ *
+ * Context: Process context.
+ */
+static void ne_pci_dev_disable(struct pci_dev *pdev)
+{
+ u8 dev_disable_reply = 0;
+ struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+ const unsigned int sleep_time = 10; /* 10 ms */
+ unsigned int sleep_time_count = 0;
+
+ iowrite8(NE_ENABLE_OFF, ne_pci_dev->iomem_base + NE_ENABLE);
+
+ /*
+ * Check for NE_ENABLE_OFF in a loop, to handle cases when the device
+ * state is not immediately set to disabled and going through a
+ * transitory state of disabling.
+ */
+ while (sleep_time_count < NE_DEFAULT_TIMEOUT_MSECS) {
+ dev_disable_reply = ioread8(ne_pci_dev->iomem_base + NE_ENABLE);
+ if (dev_disable_reply == NE_ENABLE_OFF)
+ return;
+
+ msleep_interruptible(sleep_time);
+ sleep_time_count += sleep_time;
+ }
+
+ dev_disable_reply = ioread8(ne_pci_dev->iomem_base + NE_ENABLE);
+ if (dev_disable_reply != NE_ENABLE_OFF)
+ dev_err(&pdev->dev, "Error in pci dev disable cmd\n");
+}
+
+/**
+ * ne_pci_probe() - Probe function for the NE PCI device.
+ * @pdev: PCI device to match with the NE PCI driver.
+ * @id : PCI device id table associated with the NE PCI driver.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+ struct ne_pci_dev *ne_pci_dev = NULL;
+ int rc = -EINVAL;
+
+ ne_pci_dev = kzalloc(sizeof(*ne_pci_dev), GFP_KERNEL);
+ if (!ne_pci_dev)
+ return -ENOMEM;
+
+ rc = pci_enable_device(pdev);
+ if (rc < 0) {
+ dev_err(&pdev->dev, "Error in pci dev enable [rc=%d]\n", rc);
+
+ goto free_ne_pci_dev;
+ }
+
+ pci_set_master(pdev);
+
+ rc = pci_request_regions_exclusive(pdev, "nitro_enclaves");
+ if (rc < 0) {
+ dev_err(&pdev->dev, "Error in pci request regions [rc=%d]\n", rc);
+
+ goto disable_pci_dev;
+ }
+
+ ne_pci_dev->iomem_base = pci_iomap(pdev, PCI_BAR_NE, 0);
+ if (!ne_pci_dev->iomem_base) {
+ rc = -ENOMEM;
+
+ dev_err(&pdev->dev, "Error in pci iomap [rc=%d]\n", rc);
+
+ goto release_pci_regions;
+ }
+
+ pci_set_drvdata(pdev, ne_pci_dev);
+
+ rc = ne_setup_msix(pdev);
+ if (rc < 0) {
+ dev_err(&pdev->dev, "Error in pci dev msix setup [rc=%d]\n", rc);
+
+ goto iounmap_pci_bar;
+ }
+
+ ne_pci_dev_disable(pdev);
+
+ rc = ne_pci_dev_enable(pdev);
+ if (rc < 0) {
+ dev_err(&pdev->dev, "Error in ne_pci_dev enable [rc=%d]\n", rc);
+
+ goto teardown_msix;
+ }
+
+ atomic_set(&ne_pci_dev->cmd_reply_avail, 0);
+ init_waitqueue_head(&ne_pci_dev->cmd_reply_wait_q);
+ INIT_LIST_HEAD(&ne_pci_dev->enclaves_list);
+ mutex_init(&ne_pci_dev->enclaves_list_mutex);
+ mutex_init(&ne_pci_dev->pci_dev_mutex);
+ ne_pci_dev->pdev = pdev;
+
+ ne_devs.ne_pci_dev = ne_pci_dev;
+
+ rc = misc_register(ne_devs.ne_misc_dev);
+ if (rc < 0) {
+ dev_err(&pdev->dev, "Error in misc dev register [rc=%d]\n", rc);
+
+ goto disable_ne_pci_dev;
+ }
+
+ return 0;
+
+disable_ne_pci_dev:
+ ne_devs.ne_pci_dev = NULL;
+ ne_pci_dev_disable(pdev);
+teardown_msix:
+ ne_teardown_msix(pdev);
+iounmap_pci_bar:
+ pci_set_drvdata(pdev, NULL);
+ pci_iounmap(pdev, ne_pci_dev->iomem_base);
+release_pci_regions:
+ pci_release_regions(pdev);
+disable_pci_dev:
+ pci_disable_device(pdev);
+free_ne_pci_dev:
+ kfree(ne_pci_dev);
+
+ return rc;
+}
+
+/**
+ * ne_pci_remove() - Remove function for the NE PCI device.
+ * @pdev: PCI device associated with the NE PCI driver.
+ *
+ * Context: Process context.
+ */
+static void ne_pci_remove(struct pci_dev *pdev)
+{
+ struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+ misc_deregister(ne_devs.ne_misc_dev);
+
+ ne_devs.ne_pci_dev = NULL;
+
+ ne_pci_dev_disable(pdev);
+
+ ne_teardown_msix(pdev);
+
+ pci_set_drvdata(pdev, NULL);
+
+ pci_iounmap(pdev, ne_pci_dev->iomem_base);
+
+ pci_release_regions(pdev);
+
+ pci_disable_device(pdev);
+
+ kfree(ne_pci_dev);
+}
+
+/**
+ * ne_pci_shutdown() - Shutdown function for the NE PCI device.
+ * @pdev: PCI device associated with the NE PCI driver.
+ *
+ * Context: Process context.
+ */
+static void ne_pci_shutdown(struct pci_dev *pdev)
+{
+ struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+ if (!ne_pci_dev)
+ return;
+
+ misc_deregister(ne_devs.ne_misc_dev);
+
+ ne_devs.ne_pci_dev = NULL;
+
+ ne_pci_dev_disable(pdev);
+
+ ne_teardown_msix(pdev);
+
+ pci_set_drvdata(pdev, NULL);
+
+ pci_iounmap(pdev, ne_pci_dev->iomem_base);
+
+ pci_release_regions(pdev);
+
+ pci_disable_device(pdev);
+
+ kfree(ne_pci_dev);
+}
+
+/*
+ * TODO: Add suspend / resume functions for power management w/ CONFIG_PM, if
+ * needed.
+ */
+/* NE PCI device driver. */
+struct pci_driver ne_pci_driver = {
+ .name = "nitro_enclaves",
+ .id_table = ne_pci_ids,
+ .probe = ne_pci_probe,
+ .remove = ne_pci_remove,
+ .shutdown = ne_pci_shutdown,
+};
diff --git a/drivers/virt/nitro_enclaves/ne_pci_dev.h b/drivers/virt/nitro_enclaves/ne_pci_dev.h
new file mode 100644
index 0000000000..6e9f28971a
--- /dev/null
+++ b/drivers/virt/nitro_enclaves/ne_pci_dev.h
@@ -0,0 +1,331 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#ifndef _NE_PCI_DEV_H_
+#define _NE_PCI_DEV_H_
+
+#include <linux/atomic.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/wait.h>
+
+/**
+ * DOC: Nitro Enclaves (NE) PCI device
+ */
+
+/**
+ * PCI_DEVICE_ID_NE - Nitro Enclaves PCI device id.
+ */
+#define PCI_DEVICE_ID_NE (0xe4c1)
+/**
+ * PCI_BAR_NE - Nitro Enclaves PCI device MMIO BAR.
+ */
+#define PCI_BAR_NE (0x03)
+
+/**
+ * DOC: Device registers in the NE PCI device MMIO BAR
+ */
+
+/**
+ * NE_ENABLE - (1 byte) Register to notify the device that the driver is using
+ * it (Read/Write).
+ */
+#define NE_ENABLE (0x0000)
+#define NE_ENABLE_OFF (0x00)
+#define NE_ENABLE_ON (0x01)
+
+/**
+ * NE_VERSION - (2 bytes) Register to select the device run-time version
+ * (Read/Write).
+ */
+#define NE_VERSION (0x0002)
+#define NE_VERSION_MAX (0x0001)
+
+/**
+ * NE_COMMAND - (4 bytes) Register to notify the device what command was
+ * requested (Write-Only).
+ */
+#define NE_COMMAND (0x0004)
+
+/**
+ * NE_EVTCNT - (4 bytes) Register to notify the driver that a reply or a device
+ * event is available (Read-Only):
+ * - Lower half - command reply counter
+ * - Higher half - out-of-band device event counter
+ */
+#define NE_EVTCNT (0x000c)
+#define NE_EVTCNT_REPLY_SHIFT (0)
+#define NE_EVTCNT_REPLY_MASK (0x0000ffff)
+#define NE_EVTCNT_REPLY(cnt) (((cnt) & NE_EVTCNT_REPLY_MASK) >> \
+ NE_EVTCNT_REPLY_SHIFT)
+#define NE_EVTCNT_EVENT_SHIFT (16)
+#define NE_EVTCNT_EVENT_MASK (0xffff0000)
+#define NE_EVTCNT_EVENT(cnt) (((cnt) & NE_EVTCNT_EVENT_MASK) >> \
+ NE_EVTCNT_EVENT_SHIFT)
+
+/**
+ * NE_SEND_DATA - (240 bytes) Buffer for sending the command request payload
+ * (Read/Write).
+ */
+#define NE_SEND_DATA (0x0010)
+
+/**
+ * NE_RECV_DATA - (240 bytes) Buffer for receiving the command reply payload
+ * (Read-Only).
+ */
+#define NE_RECV_DATA (0x0100)
+
+/**
+ * DOC: Device MMIO buffer sizes
+ */
+
+/**
+ * NE_SEND_DATA_SIZE - Size of the send buffer, in bytes.
+ */
+#define NE_SEND_DATA_SIZE (240)
+
+/**
+ * NE_RECV_DATA_SIZE - Size of the receive buffer, in bytes.
+ */
+#define NE_RECV_DATA_SIZE (240)
+
+/**
+ * DOC: MSI-X interrupt vectors
+ */
+
+/**
+ * NE_VEC_REPLY - MSI-X vector used for command reply notification.
+ */
+#define NE_VEC_REPLY (0)
+
+/**
+ * NE_VEC_EVENT - MSI-X vector used for out-of-band events e.g. enclave crash.
+ */
+#define NE_VEC_EVENT (1)
+
+/**
+ * enum ne_pci_dev_cmd_type - Device command types.
+ * @INVALID_CMD: Invalid command.
+ * @ENCLAVE_START: Start an enclave, after setting its resources.
+ * @ENCLAVE_GET_SLOT: Get the slot uid of an enclave.
+ * @ENCLAVE_STOP: Terminate an enclave.
+ * @SLOT_ALLOC : Allocate a slot for an enclave.
+ * @SLOT_FREE: Free the slot allocated for an enclave
+ * @SLOT_ADD_MEM: Add a memory region to an enclave slot.
+ * @SLOT_ADD_VCPU: Add a vCPU to an enclave slot.
+ * @SLOT_COUNT : Get the number of allocated slots.
+ * @NEXT_SLOT: Get the next slot in the list of allocated slots.
+ * @SLOT_INFO: Get the info for a slot e.g. slot uid, vCPUs count.
+ * @SLOT_ADD_BULK_VCPUS: Add a number of vCPUs, not providing CPU ids.
+ * @MAX_CMD: A gatekeeper for max possible command type.
+ */
+enum ne_pci_dev_cmd_type {
+ INVALID_CMD = 0,
+ ENCLAVE_START = 1,
+ ENCLAVE_GET_SLOT = 2,
+ ENCLAVE_STOP = 3,
+ SLOT_ALLOC = 4,
+ SLOT_FREE = 5,
+ SLOT_ADD_MEM = 6,
+ SLOT_ADD_VCPU = 7,
+ SLOT_COUNT = 8,
+ NEXT_SLOT = 9,
+ SLOT_INFO = 10,
+ SLOT_ADD_BULK_VCPUS = 11,
+ MAX_CMD,
+};
+
+/**
+ * DOC: Device commands - payload structure for requests and replies.
+ */
+
+/**
+ * struct enclave_start_req - ENCLAVE_START request.
+ * @slot_uid: Slot unique id mapped to the enclave to start.
+ * @enclave_cid: Context ID (CID) for the enclave vsock device.
+ * If 0, CID is autogenerated.
+ * @flags: Flags for the enclave to start with (e.g. debug mode).
+ */
+struct enclave_start_req {
+ u64 slot_uid;
+ u64 enclave_cid;
+ u64 flags;
+};
+
+/**
+ * struct enclave_get_slot_req - ENCLAVE_GET_SLOT request.
+ * @enclave_cid: Context ID (CID) for the enclave vsock device.
+ */
+struct enclave_get_slot_req {
+ u64 enclave_cid;
+};
+
+/**
+ * struct enclave_stop_req - ENCLAVE_STOP request.
+ * @slot_uid: Slot unique id mapped to the enclave to stop.
+ */
+struct enclave_stop_req {
+ u64 slot_uid;
+};
+
+/**
+ * struct slot_alloc_req - SLOT_ALLOC request.
+ * @unused: In order to avoid weird sizeof edge cases.
+ */
+struct slot_alloc_req {
+ u8 unused;
+};
+
+/**
+ * struct slot_free_req - SLOT_FREE request.
+ * @slot_uid: Slot unique id mapped to the slot to free.
+ */
+struct slot_free_req {
+ u64 slot_uid;
+};
+
+/* TODO: Add flags field to the request to add memory region. */
+/**
+ * struct slot_add_mem_req - SLOT_ADD_MEM request.
+ * @slot_uid: Slot unique id mapped to the slot to add the memory region to.
+ * @paddr: Physical address of the memory region to add to the slot.
+ * @size: Memory size, in bytes, of the memory region to add to the slot.
+ */
+struct slot_add_mem_req {
+ u64 slot_uid;
+ u64 paddr;
+ u64 size;
+};
+
+/**
+ * struct slot_add_vcpu_req - SLOT_ADD_VCPU request.
+ * @slot_uid: Slot unique id mapped to the slot to add the vCPU to.
+ * @vcpu_id: vCPU ID of the CPU to add to the enclave.
+ * @padding: Padding for the overall data structure.
+ */
+struct slot_add_vcpu_req {
+ u64 slot_uid;
+ u32 vcpu_id;
+ u8 padding[4];
+};
+
+/**
+ * struct slot_count_req - SLOT_COUNT request.
+ * @unused: In order to avoid weird sizeof edge cases.
+ */
+struct slot_count_req {
+ u8 unused;
+};
+
+/**
+ * struct next_slot_req - NEXT_SLOT request.
+ * @slot_uid: Slot unique id of the next slot in the iteration.
+ */
+struct next_slot_req {
+ u64 slot_uid;
+};
+
+/**
+ * struct slot_info_req - SLOT_INFO request.
+ * @slot_uid: Slot unique id mapped to the slot to get information about.
+ */
+struct slot_info_req {
+ u64 slot_uid;
+};
+
+/**
+ * struct slot_add_bulk_vcpus_req - SLOT_ADD_BULK_VCPUS request.
+ * @slot_uid: Slot unique id mapped to the slot to add vCPUs to.
+ * @nr_vcpus: Number of vCPUs to add to the slot.
+ */
+struct slot_add_bulk_vcpus_req {
+ u64 slot_uid;
+ u64 nr_vcpus;
+};
+
+/**
+ * struct ne_pci_dev_cmd_reply - NE PCI device command reply.
+ * @rc : Return code of the logic that processed the request.
+ * @padding0: Padding for the overall data structure.
+ * @slot_uid: Valid for all commands except SLOT_COUNT.
+ * @enclave_cid: Valid for ENCLAVE_START command.
+ * @slot_count : Valid for SLOT_COUNT command.
+ * @mem_regions: Valid for SLOT_ALLOC and SLOT_INFO commands.
+ * @mem_size: Valid for SLOT_INFO command.
+ * @nr_vcpus: Valid for SLOT_INFO command.
+ * @flags: Valid for SLOT_INFO command.
+ * @state: Valid for SLOT_INFO command.
+ * @padding1: Padding for the overall data structure.
+ */
+struct ne_pci_dev_cmd_reply {
+ s32 rc;
+ u8 padding0[4];
+ u64 slot_uid;
+ u64 enclave_cid;
+ u64 slot_count;
+ u64 mem_regions;
+ u64 mem_size;
+ u64 nr_vcpus;
+ u64 flags;
+ u16 state;
+ u8 padding1[6];
+};
+
+/**
+ * struct ne_pci_dev - Nitro Enclaves (NE) PCI device.
+ * @cmd_reply_avail: Variable set if a reply has been sent by the
+ * PCI device.
+ * @cmd_reply_wait_q: Wait queue for handling command reply from the
+ * PCI device.
+ * @enclaves_list: List of the enclaves managed by the PCI device.
+ * @enclaves_list_mutex: Mutex for accessing the list of enclaves.
+ * @event_wq: Work queue for handling out-of-band events
+ * triggered by the Nitro Hypervisor which require
+ * enclave state scanning and propagation to the
+ * enclave process.
+ * @iomem_base : MMIO region of the PCI device.
+ * @notify_work: Work item for every received out-of-band event.
+ * @pci_dev_mutex: Mutex for accessing the PCI device MMIO space.
+ * @pdev: PCI device data structure.
+ */
+struct ne_pci_dev {
+ atomic_t cmd_reply_avail;
+ wait_queue_head_t cmd_reply_wait_q;
+ struct list_head enclaves_list;
+ struct mutex enclaves_list_mutex;
+ struct workqueue_struct *event_wq;
+ void __iomem *iomem_base;
+ struct work_struct notify_work;
+ struct mutex pci_dev_mutex;
+ struct pci_dev *pdev;
+};
+
+/**
+ * ne_do_request() - Submit command request to the PCI device based on the command
+ * type and retrieve the associated reply.
+ * @pdev: PCI device to send the command to and receive the reply from.
+ * @cmd_type: Command type of the request sent to the PCI device.
+ * @cmd_request: Command request payload.
+ * @cmd_request_size: Size of the command request payload.
+ * @cmd_reply: Command reply payload.
+ * @cmd_reply_size: Size of the command reply payload.
+ *
+ * Context: Process context. This function uses the ne_pci_dev mutex to handle
+ * one command at a time.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+int ne_do_request(struct pci_dev *pdev, enum ne_pci_dev_cmd_type cmd_type,
+ void *cmd_request, size_t cmd_request_size,
+ struct ne_pci_dev_cmd_reply *cmd_reply,
+ size_t cmd_reply_size);
+
+/* Nitro Enclaves (NE) PCI device driver */
+extern struct pci_driver ne_pci_driver;
+
+#endif /* _NE_PCI_DEV_H_ */