CDX bus supports multiple type of devices, which can be
exposed to user-space via vfio-cdx.
vfio-cdx provides the MMIO IO_MEMORY regions as well as the
DMA interface for the device (IOMMU).
This support aims to enable the DPDK to support the cdx
devices in user-space using VFIO interface.
Signed-off-by: Nipun Gupta <nipun.gu...@amd.com>
---
MAINTAINERS | 5 +
drivers/bus/cdx/cdx.c | 570 ++++++++++++++++++++++++++++++++++
drivers/bus/cdx/cdx.h | 54 ++++
drivers/bus/cdx/cdx_logs.h | 37 +++
drivers/bus/cdx/cdx_vfio.c | 420 +++++++++++++++++++++++++
drivers/bus/cdx/meson.build | 13 +
drivers/bus/cdx/rte_bus_cdx.h | 219 +++++++++++++
drivers/bus/cdx/version.map | 19 ++
8 files changed, 1337 insertions(+)
create mode 100644 drivers/bus/cdx/cdx.c
create mode 100644 drivers/bus/cdx/cdx.h
create mode 100644 drivers/bus/cdx/cdx_logs.h
create mode 100644 drivers/bus/cdx/cdx_vfio.c
create mode 100644 drivers/bus/cdx/meson.build
create mode 100644 drivers/bus/cdx/rte_bus_cdx.h
create mode 100644 drivers/bus/cdx/version.map
diff --git a/MAINTAINERS b/MAINTAINERS
index 8df23e5099..1f9b6af9b9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -569,6 +569,11 @@ M: Parav Pandit <pa...@nvidia.com>
M: Xueming Li <xuemi...@nvidia.com>
F: drivers/bus/auxiliary/
+CDX bus driver
+M: Nipun Gupta <nipun.gu...@amd.com>
+M: Nikhil Agarwal <nikhil.agar...@amd.com>
+F: drivers/bus/cdx/
+
Intel FPGA bus
M: Rosen Xu <rosen...@intel.com>
F: drivers/bus/ifpga/
diff --git a/drivers/bus/cdx/cdx.c b/drivers/bus/cdx/cdx.c
new file mode 100644
index 0000000000..c5f8e37a2f
--- /dev/null
+++ b/drivers/bus/cdx/cdx.c
@@ -0,0 +1,570 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+ */
+
+/*
+ * Architecture Overview
+ * =====================
+ * CDX is a Hardware Architecture designed for AMD FPGA devices. It
+ * consists of sophisticated mechanism for interaction between FPGA,
+ * Firmware and the APUs (Application CPUs).
+ *
+ * Firmware resides on RPU (Realtime CPUs) which interacts with
+ * the FPGA program manager and the APUs. The RPU provides memory-mapped
+ * interface (RPU if) which is used to communicate with APUs.
+ *
+ * The diagram below shows an overview of the CDX architecture:
+ *
+ * +--------------------------------------+
+ * | DPDK |
+ * | DPDK CDX drivers |
+ * | | |
+ * | DPDK CDX bus |
+ * | | |
+ * +-----------------------------|--------+
+ * |
+ * +-----------------------------|--------+
+ * | Application CPUs (APU) | |
+ * | | |
+ * | VFIO CDX driver |
+ * | Linux OS | |
+ * | Linux CDX bus |
+ * | | |
+ * +-----------------------------|--------+
+ * |
+ * |
+ * +------------------------| RPU if |----+
+ * | | |
+ * | V |
+ * | Realtime CPUs (RPU) |
+ * | |
+ * +--------------------------------------+
+ * |
+ * +---------------------|----------------+
+ * | FPGA | |
+ * | +-----------------------+ |
+ * | | | | |
+ * | +-------+ +-------+ +-------+ |
+ * | | dev 1 | | dev 2 | | dev 3 | |
+ * | +-------+ +-------+ +-------+ |
+ * +--------------------------------------+
+ *
+ * The RPU firmware extracts the device information from the loaded FPGA
+ * image and implements a mechanism that allows the APU drivers to
+ * enumerate such devices (device personality and resource details) via
+ * a dedicated communication channel.
+ *
+ * VFIO CDX driver provides the CDX device resources like MMIO and interrupts
+ * to map to user-space. DPDK CDX bus uses sysfs interface and the vfio-cdx
+ * driver to discover and initialize the CDX devices for user-space
+ * applications.
+ */
+
+#include <string.h>
+#include <dirent.h>
+
+#include <rte_log.h>
+#include <rte_bus.h>
+#include <rte_bus_cdx.h>
+#include <rte_eal_paging.h>
+#include <rte_errno.h>
+#include <rte_devargs.h>
+#include <rte_malloc.h>
+#include <rte_memcpy.h>
+#include <rte_vfio.h>
+
+#include <eal_filesystem.h>
+
+#include "cdx.h"
+#include "cdx_logs.h"
+
+#define SYSFS_CDX_DEVICES "/sys/bus/cdx/devices"
+#define CDX_BUS_NAME cdx
+#define CDX_DEV_PREFIX "cdx-"
+
+/**
+ * @file
+ * CDX probing using Linux sysfs.
+ */
+
+/* Add a device to CDX bus */
+static void
+rte_cdx_add_device(struct rte_cdx_device *cdx_dev)
+{
+ TAILQ_INSERT_TAIL(&rte_cdx_bus.device_list, cdx_dev, next);
+}
+
+static int
+cdx_get_kernel_driver_by_path(const char *filename, char *driver_name,
+ size_t len)
+{
+ int count;
+ char path[PATH_MAX];
+ char *name;
+
+ if (!filename || !driver_name)
+ return -1;
+
+ count = readlink(filename, path, PATH_MAX);
+ if (count >= PATH_MAX)
+ return -1;
+
+ /* For device does not have a driver */
+ if (count < 0)
+ return 1;
+
+ path[count] = '\0';
+
+ name = strrchr(path, '/');
+ if (name) {
+ strlcpy(driver_name, name + 1, len);
+ return 0;
+ }
+
+ return -1;
+}
+
+int rte_cdx_map_device(struct rte_cdx_device *dev)
+{
+ return cdx_vfio_map_resource(dev);
+}
+
+void rte_cdx_unmap_device(struct rte_cdx_device *dev)
+{
+ cdx_vfio_unmap_resource(dev);
+}
+
+static int
+find_max_end_va(const struct rte_memseg_list *msl, void *arg)
+{
+ size_t sz = msl->len;
+ void *end_va = RTE_PTR_ADD(msl->base_va, sz);
+ void **max_va = arg;
+
+ if (*max_va < end_va)
+ *max_va = end_va;
+ return 0;
+}
+
+void *
+cdx_find_max_end_va(void)
+{
+ void *va = NULL;
+
+ rte_memseg_list_walk(find_max_end_va, &va);
+ return va;
+}
+
+static struct rte_devargs *
+cdx_devargs_lookup(const char *dev_name)
+{
+ struct rte_devargs *devargs;
+
+ RTE_EAL_DEVARGS_FOREACH("cdx", devargs) {
+ if (strcmp(devargs->name, dev_name) == 0)
+ return devargs;
+ }
+ return NULL;
+}
+
+static bool
+cdx_ignore_device(const char *dev_name)
+{
+ struct rte_devargs *devargs = cdx_devargs_lookup(dev_name);
+
+ switch (rte_cdx_bus.bus.conf.scan_mode) {
+ case RTE_BUS_SCAN_ALLOWLIST:
+ if (devargs && devargs->policy == RTE_DEV_ALLOWED)
+ return false;
+ break;
+ case RTE_BUS_SCAN_UNDEFINED:
+ case RTE_BUS_SCAN_BLOCKLIST:
+ if (devargs == NULL || devargs->policy != RTE_DEV_BLOCKED)
+ return false;
+ break;
+ }
+ return true;
+}
+
+/*
+ * Scan one cdx sysfs entry, and fill the devices list from it.
+ * It checks if the CDX device is bound to vfio-cdx driver. In case
+ * the device is vfio bound, it reads the vendor and device id and
+ * stores it for device-driver matching.
+ */
+static int
+cdx_scan_one(const char *dirname, const char *dev_name)
+{
+ char filename[PATH_MAX];
+ struct rte_cdx_device *dev = NULL;
+ char driver[PATH_MAX];
+ unsigned long tmp;
+ char *name = NULL;
+ int ret;
+
+ dev = calloc(1, sizeof(*dev));
+ if (!dev)
+ return -ENOMEM;
+
+ name = calloc(1, RTE_DEV_NAME_MAX_LEN);
+ if (!name) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ dev->device.bus = &rte_cdx_bus.bus;
+ memcpy(name, dev_name, RTE_DEV_NAME_MAX_LEN);
+ dev->device.name = name;
+
+ /* parse driver */
+ snprintf(filename, sizeof(filename), "%s/driver", dirname);
+ ret = cdx_get_kernel_driver_by_path(filename, driver, sizeof(driver));
+ if (ret < 0) {
+ CDX_BUS_ERR("Fail to get kernel driver");
+ ret = -1;
+ goto err;
+ }
+
+ /*
+ * Check if device is bound to 'vfio-cdx' driver, so that user-space
+ * can gracefully access the device.
+ */
+ if (ret || strcmp(driver, "vfio-cdx")) {
+ ret = 0;
+ goto err;
+ }
+
+ /* get vendor id */
+ snprintf(filename, sizeof(filename), "%s/vendor", dirname);
+ if (eal_parse_sysfs_value(filename, &tmp) < 0) {
+ ret = -1;
+ goto err;
+ }
+ dev->id.vendor_id = (uint16_t)tmp;
+
+ /* get device id */
+ snprintf(filename, sizeof(filename), "%s/device", dirname);
+ if (eal_parse_sysfs_value(filename, &tmp) < 0) {
+ free(dev);
+ return -1;
+ }
+ dev->id.device_id = (uint16_t)tmp;
+
+ rte_cdx_add_device(dev);
+
+ return 0;
+
+err:
+ if (name)
+ free(name);
+ if (dev)
+ free(dev);
+ return ret;
+}
+
+/*
+ * Scan the content of the CDX bus, and the devices in the devices
+ * list.
+ */
+static int
+rte_cdx_scan(void)
+{
+ struct dirent *e;
+ DIR *dir;
+ char dirname[PATH_MAX];
+
+ dir = opendir(rte_cdx_get_sysfs_path());
+ if (dir == NULL) {
+ CDX_BUS_ERR("%s(): opendir failed: %s", __func__,
+ strerror(errno));
+ return -1;
+ }
+
+ while ((e = readdir(dir)) != NULL) {
+ if (e->d_name[0] == '.')
+ continue;
+
+ if (cdx_ignore_device(e->d_name))
+ continue;
+
+ snprintf(dirname, sizeof(dirname), "%s/%s",
+ rte_cdx_get_sysfs_path(), e->d_name);
+
+ if (cdx_scan_one(dirname, e->d_name) < 0)
+ goto error;
+ }
+ closedir(dir);
+ return 0;
+
+error:
+ closedir(dir);
+ return -1;
+}
+
+const char *
+rte_cdx_get_sysfs_path(void)
+{
+ return SYSFS_CDX_DEVICES;
+}
+
+/* map a particular resource from a file */
+void *
+cdx_map_resource(void *requested_addr, int fd, off_t offset, size_t size,
+ int additional_flags)
+{
+ void *mapaddr;
+
+ /* Map the cdx MMIO memory resource of device */
+ mapaddr = rte_mem_map(requested_addr, size,
+ RTE_PROT_READ | RTE_PROT_WRITE,
+ RTE_MAP_SHARED | additional_flags, fd, offset);
+ if (mapaddr == NULL) {
+ CDX_BUS_ERR("%s(): cannot map resource(%d, %p, 0x%zx, 0x%llx):
%s (%p)",
+ __func__, fd, requested_addr, size,
+ (unsigned long long)offset,
+ rte_strerror(rte_errno), mapaddr);
+ }
+ CDX_BUS_DEBUG("CDX MMIO memory mapped at %p", mapaddr);
+
+ return mapaddr;
+}
+
+/* unmap a particular resource */
+void
+cdx_unmap_resource(void *requested_addr, size_t size)
+{
+ if (requested_addr == NULL)
+ return;
+
+ /* Unmap the CDX memory resource of device */
+ if (rte_mem_unmap(requested_addr, size)) {
+ CDX_BUS_ERR("%s(): cannot mem unmap(%p, %#zx): %s", __func__,
+ requested_addr, size, rte_strerror(rte_errno));
+ }
+ CDX_BUS_DEBUG("CDX memory unmapped at %p", requested_addr);
+}
+/*
+ * Match the CDX Driver and Device using device id and vendor id.
+ */
+static int
+rte_cdx_match(const struct rte_cdx_driver *cdx_drv,
+ const struct rte_cdx_device *cdx_dev)
+{
+ const struct rte_cdx_id *id_table;
+
+ for (id_table = cdx_drv->id_table; id_table->vendor_id != 0;
+ id_table++) {
+ /* check if device's identifiers match the driver's ones */
+ if (id_table->vendor_id != cdx_dev->id.vendor_id &&
+ id_table->vendor_id != RTE_CDX_ANY_ID)
+ continue;
+ if (id_table->device_id != cdx_dev->id.device_id &&
+ id_table->device_id != RTE_CDX_ANY_ID)
+ continue;
+
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * If vendor id and device id match, call the probe() function of the
+ * driver.
+ */
+static int
+rte_cdx_probe_one_driver(struct rte_cdx_driver *dr,
+ struct rte_cdx_device *dev)
+{
+ const char *dev_name = dev->device.name;
+ bool already_probed;
+ int ret;
+
+ if ((dr == NULL) || (dev == NULL))
+ return -EINVAL;
+
+ /* The device is not blocked; Check if driver supports it */
+ if (!rte_cdx_match(dr, dev))
+ /* Match of device and driver failed */
+ return 1;
+
+ already_probed = rte_dev_is_probed(&dev->device);
+ if (already_probed) {
+ CDX_BUS_INFO("Device %s is already probed", dev->device.name);
+ return -EEXIST;
+ }
+
+ CDX_BUS_DEBUG(" probe device %s using driver: %s", dev_name,
+ dr->driver.name);
+
+ ret = cdx_vfio_map_resource(dev);
+ if (ret != 0) {
+ CDX_BUS_ERR("CDX map device failed: %d", ret);
+ goto error_map_device;
+ }
+
+ /* call the driver probe() function */
+ ret = dr->probe(dr, dev);
+ if (ret) {
+ CDX_BUS_ERR("Probe CDX driver: %s device: %s failed: %d",
+ dr->driver.name, dev_name, ret);
+ goto error_probe;
+ } else {
+ dev->device.driver = &dr->driver;
+ }
+
+ return ret;
+
+error_probe:
+ cdx_vfio_unmap_resource(dev);
+error_map_device:
+ return ret;
+}
+
+/*
+ * If vendor/device ID match, call the probe() function of all
+ * registered driver for the given device. Return < 0 if initialization
+ * failed, return 1 if no driver is found for this device.
+ */
+static int
+cdx_probe_all_drivers(struct rte_cdx_device *dev)
+{
+ struct rte_cdx_driver *dr = NULL;
+ int rc = 0;
+
+ if (dev == NULL)
+ return -EINVAL;
+
+ FOREACH_DRIVER_ON_CDXBUS(dr) {
+ rc = rte_cdx_probe_one_driver(dr, dev);
+ if (rc < 0)
+ /* negative value is an error */
+ return rc;
+ if (rc > 0)
+ /* positive value means driver doesn't support it */
+ continue;
+ return 0;
+ }
+ return 1;
+}
+
+/*
+ * Scan the content of the CDX bus, and call the probe() function for
+ * all registered drivers that have a matching entry in its id_table
+ * for discovered devices.
+ */
+static int
+cdx_probe(void)
+{
+ struct rte_cdx_device *dev = NULL;
+ size_t probed = 0, failed = 0;
+ int ret = 0;
+
+ FOREACH_DEVICE_ON_CDXBUS(dev) {
+ probed++;
+
+ ret = cdx_probe_all_drivers(dev);
+ if (ret < 0) {
+ CDX_BUS_ERR("Requested device %s cannot be used",
+ dev->device.name);
+ rte_errno = errno;
+ failed++;
+ ret = 0;
+ }
+ }
+
+ return (probed && probed == failed) ? -1 : 0;
+}
+
+/* dump one device */
+static int
+cdx_dump_one_device(FILE *f, struct rte_cdx_device *dev)
+{
+ int i;
+
+ fprintf(f, "cdx device %s\n", dev->device.name);
+
+ for (i = 0; i != sizeof(dev->mem_resource) /
+ sizeof(dev->mem_resource[0]); i++) {
+ if (dev->mem_resource[i].len)
+ fprintf(f, " Resource[%d]: %p %16.16"PRIx64"\n",
+ i, dev->mem_resource[i].addr,
+ dev->mem_resource[i].len);
+ }
+ return 0;
+}
+
+/* dump devices on the bus */
+void
+rte_cdx_dump(FILE *f)
+{
+ struct rte_cdx_device *dev = NULL;
+
+ FOREACH_DEVICE_ON_CDXBUS(dev)
+ cdx_dump_one_device(f, dev);
+}
+
+static int
+cdx_parse(const char *name, void *addr)
+{
+ const char **out = addr;
+ int ret;
+
+ ret = strncmp(name, CDX_DEV_PREFIX, strlen(CDX_DEV_PREFIX));
+
+ if (ret == 0 && addr)
+ *out = name;
+
+ return ret;
+}
+
+/* register a driver */
+void
+rte_cdx_register(struct rte_cdx_driver *driver)
+{
+ TAILQ_INSERT_TAIL(&rte_cdx_bus.driver_list, driver, next);
+ driver->bus = &rte_cdx_bus;
+}
+
+/* unregister a driver */
+void
+rte_cdx_unregister(struct rte_cdx_driver *driver)
+{
+ TAILQ_REMOVE(&rte_cdx_bus.driver_list, driver, next);
+ driver->bus = NULL;
+}
+
+static struct rte_device *
+cdx_find_device(const struct rte_device *start, rte_dev_cmp_t cmp,
+ const void *data)
+{
+ const struct rte_cdx_device *cdx_start;
+ struct rte_cdx_device *cdx_dev;
+
+ if (start != NULL) {
+ cdx_start = RTE_DEV_TO_CDX_DEV_CONST(start);
+ cdx_dev = TAILQ_NEXT(cdx_start, next);
+ } else {
+ cdx_dev = TAILQ_FIRST(&rte_cdx_bus.device_list);
+ }
+ while (cdx_dev != NULL) {
+ if (cmp(&cdx_dev->device, data) == 0)
+ return &cdx_dev->device;
+ cdx_dev = TAILQ_NEXT(cdx_dev, next);
+ }
+ return NULL;
+}
+
+struct rte_cdx_bus rte_cdx_bus = {
+ .bus = {
+ .scan = rte_cdx_scan,
+ .probe = cdx_probe,
+ .find_device = cdx_find_device,
+ .parse = cdx_parse,
+ },
+ .device_list = TAILQ_HEAD_INITIALIZER(rte_cdx_bus.device_list),
+ .driver_list = TAILQ_HEAD_INITIALIZER(rte_cdx_bus.driver_list),
+};
+
+RTE_REGISTER_BUS(cdx, rte_cdx_bus.bus);
+RTE_LOG_REGISTER_DEFAULT(cdx_logtype_bus, NOTICE);
diff --git a/drivers/bus/cdx/cdx.h b/drivers/bus/cdx/cdx.h
new file mode 100644
index 0000000000..d428149bb9
--- /dev/null
+++ b/drivers/bus/cdx/cdx.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _CDX_H_
+#define _CDX_H_
+
+#include <stdbool.h>
+#include <stdio.h>
+
+#include "rte_bus_cdx.h"
+
+extern struct rte_cdx_bus rte_cdx_bus;
+
+/**
+ * Map a particular resource from a file.
+ *
+ * @param requested_addr
+ * The starting address for the new mapping range.
+ * @param fd
+ * The file descriptor.
+ * @param offset
+ * The offset for the mapping range.
+ * @param size
+ * The size for the mapping range.
+ * @param additional_flags
+ * The additional rte_mem_map() flags for the mapping range.
+ * @return
+ * - On success, the function returns a pointer to the mapped area.
+ * - On error, NULL is returned.
+ */
+void *cdx_map_resource(void *requested_addr, int fd, off_t offset,
+ size_t size, int additional_flags);
+
+/**
+ * Unmap a particular resource.
+ *
+ * @param requested_addr
+ * The address for the unmapping range.
+ * @param size
+ * The size for the unmapping range.
+ */
+void cdx_unmap_resource(void *requested_addr, size_t size);
+
+/*
+ * Helper function to map CDX resources right after hugepages in virtual memory
+ */
+void *cdx_find_max_end_va(void);
+
+/* map/unmap VFIO resource */
+int cdx_vfio_map_resource(struct rte_cdx_device *dev);
+int cdx_vfio_unmap_resource(struct rte_cdx_device *dev);
+
+#endif /* _CDX_H_ */
diff --git a/drivers/bus/cdx/cdx_logs.h b/drivers/bus/cdx/cdx_logs.h
new file mode 100644
index 0000000000..7a53633a1b
--- /dev/null
+++ b/drivers/bus/cdx/cdx_logs.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _CDX_LOGS_H_
+#define _CDX_LOGS_H_
+
+extern int cdx_logtype_bus;
+
+#define CDX_BUS_LOG(level, fmt, args...) \
+ rte_log(RTE_LOG_ ## level, cdx_logtype_bus, "fslmc: " fmt "\n", \
+ ##args)
+
+/* Debug logs are with Function names */
+#define CDX_BUS_DEBUG(fmt, args...) \
+ rte_log(RTE_LOG_DEBUG, cdx_logtype_bus, "fslmc: %s(): " fmt "\n", \
+ __func__, ##args)
+
+#define CDX_BUS_INFO(fmt, args...) \
+ CDX_BUS_LOG(INFO, fmt, ## args)
+#define CDX_BUS_ERR(fmt, args...) \
+ CDX_BUS_LOG(ERR, fmt, ## args)
+#define CDX_BUS_WARN(fmt, args...) \
+ CDX_BUS_LOG(WARNING, fmt, ## args)
+
+/* DP Logs, toggled out at compile time if level lower than current level */
+#define CDX_BUS_DP_LOG(level, fmt, args...) \
+ RTE_LOG_DP(level, PMD, fmt, ## args)
+
+#define CDX_BUS_DP_DEBUG(fmt, args...) \
+ CDX_BUS_DP_LOG(DEBUG, fmt, ## args)
+#define CDX_BUS_DP_INFO(fmt, args...) \
+ CDX_BUS_DP_LOG(INFO, fmt, ## args)
+#define CDX_BUS_DP_WARN(fmt, args...) \
+ CDX_BUS_DP_LOG(WARNING, fmt, ## args)
+
+#endif /* _CDX_LOGS_H_ */
diff --git a/drivers/bus/cdx/cdx_vfio.c b/drivers/bus/cdx/cdx_vfio.c
new file mode 100644
index 0000000000..a53137c416
--- /dev/null
+++ b/drivers/bus/cdx/cdx_vfio.c
@@ -0,0 +1,420 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+ */
+
+/**
+ * @file
+ * CDX probing using Linux VFIO.
+ *
+ * This code tries to determine if the CDX device is bound to VFIO driver,
+ * and initialize it (map BARs, set up interrupts) if that's the case.
+ *
+ */
+
+#include <string.h>
+#include <fcntl.h>
+#include <sys/eventfd.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+
+#include <rte_log.h>
+#include <rte_bus_cdx.h>
+#include <rte_eal_paging.h>
+#include <rte_malloc.h>
+#include <rte_vfio.h>
+#include <rte_eal.h>
+#include <rte_bus.h>
+#include <rte_spinlock.h>
+#include <rte_tailq.h>
+
+#include "eal_filesystem.h"
+
+#include "cdx.h"
+#include "cdx_logs.h"
+
+/**
+ * A structure describing a CDX mapping.
+ */
+struct cdx_map {
+ void *addr;
+ char *path;
+ uint64_t offset;
+ uint64_t size;
+};
+
+/**
+ * A structure describing a mapped CDX resource.
+ * For multi-process we need to reproduce all CDX mappings in secondary
+ * processes, so save them in a tailq.
+ */
+struct mapped_cdx_resource {
+ TAILQ_ENTRY(mapped_cdx_resource) next;
+ char name[RTE_DEV_NAME_MAX_LEN]; /**< CDX device name */
+ char path[PATH_MAX];
+ int nb_maps;
+ struct cdx_map maps[CDX_MAX_RESOURCE];
+};
+
+/** mapped cdx device list */
+TAILQ_HEAD(mapped_cdx_res_list, mapped_cdx_resource);
+
+static struct rte_tailq_elem cdx_vfio_tailq = {
+ .name = "VFIO_CDX_RESOURCE_LIST",
+};
+EAL_REGISTER_TAILQ(cdx_vfio_tailq)
+
+static struct mapped_cdx_resource *
+cdx_vfio_find_and_unmap_resource(struct mapped_cdx_res_list *vfio_res_list,
+ struct rte_cdx_device *dev)
+{
+ struct mapped_cdx_resource *vfio_res = NULL;
+ const char *dev_name = dev->device.name;
+ struct cdx_map *maps;
+ int i;
+
+ /* Get vfio_res */
+ TAILQ_FOREACH(vfio_res, vfio_res_list, next) {
+ if (strcmp(vfio_res->name, dev_name))
+ continue;
+ break;
+ }
+
+ if (vfio_res == NULL)
+ return vfio_res;
+
+ CDX_BUS_INFO("Releasing CDX mapped resource for %s", dev_name);
+
+ maps = vfio_res->maps;
+ for (i = 0; i < vfio_res->nb_maps; i++) {
+ /*
+ * We do not need to be aware of MSI-X table BAR mappings as
+ * when mapping. Just using current maps array is enough
+ */
+ if (maps[i].addr) {
+ CDX_BUS_DEBUG("Calling cdx_unmap_resource for %s at %p",
+ dev_name, maps[i].addr);
+ cdx_unmap_resource(maps[i].addr, maps[i].size);
+ }
+ }
+
+ return vfio_res;
+}
+
+static int
+cdx_vfio_unmap_resource_primary(struct rte_cdx_device *dev)
+{
+ char cdx_addr[PATH_MAX] = {0};
+ struct mapped_cdx_resource *vfio_res = NULL;
+ struct mapped_cdx_res_list *vfio_res_list;
+
+ vfio_res_list =
+ RTE_TAILQ_CAST(cdx_vfio_tailq.head, mapped_cdx_res_list);
+ vfio_res = cdx_vfio_find_and_unmap_resource(vfio_res_list, dev);
+
+ /* if we haven't found our tailq entry, something's wrong */
+ if (vfio_res == NULL) {
+ CDX_BUS_ERR("%s cannot find TAILQ entry for cdx device!",
+ cdx_addr);
+ return -1;
+ }
+
+ TAILQ_REMOVE(vfio_res_list, vfio_res, next);
+ rte_free(vfio_res);
+ return 0;
+}
+
+static int
+cdx_vfio_unmap_resource_secondary(struct rte_cdx_device *dev)
+{
+ struct mapped_cdx_resource *vfio_res = NULL;
+ struct mapped_cdx_res_list *vfio_res_list;
+
+ vfio_res_list =
+ RTE_TAILQ_CAST(cdx_vfio_tailq.head, mapped_cdx_res_list);
+ vfio_res = cdx_vfio_find_and_unmap_resource(vfio_res_list, dev);
+
+ /* if we haven't found our tailq entry, something's wrong */
+ if (vfio_res == NULL) {
+ CDX_BUS_ERR("%s cannot find TAILQ entry for CDX device!",
+ dev->device.name);
+ return -1;
+ }
+
+ return 0;
+}
+
+int
+cdx_vfio_unmap_resource(struct rte_cdx_device *dev)
+{
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+ return cdx_vfio_unmap_resource_primary(dev);
+ else
+ return cdx_vfio_unmap_resource_secondary(dev);
+}
+
+static int
+cdx_rte_vfio_setup_device(int vfio_dev_fd)
+{
+ /*
+ * Reset the device. If the device is not capable of resetting,
+ * then it updates errno as EINVAL.
+ */
+ if (ioctl(vfio_dev_fd, VFIO_DEVICE_RESET) && errno != EINVAL) {
+ CDX_BUS_ERR("Unable to reset device! Error: %d (%s)", errno,
+ strerror(errno));
+ return -1;
+ }
+
+ return 0;
+}
+
+static int
+cdx_vfio_mmap_resource(int vfio_dev_fd, struct mapped_cdx_resource *vfio_res,
+ int index, int additional_flags)
+{
+ struct cdx_map *map = &vfio_res->maps[index];
+ void *vaddr;
+
+ if (map->size == 0) {
+ CDX_BUS_DEBUG("map size is 0, skip region %d", index);
+ return 0;
+ }
+
+ /* reserve the address using an inaccessible mapping */
+ vaddr = mmap(map->addr, map->size, 0, MAP_PRIVATE |
+ MAP_ANONYMOUS | additional_flags, -1, 0);
+ if (vaddr != MAP_FAILED) {
+ void *map_addr = NULL;
+
+ if (map->size) {
+ /* actual map of first part */
+ map_addr = cdx_map_resource(vaddr, vfio_dev_fd,
+ map->offset, map->size,
+ RTE_MAP_FORCE_ADDRESS);
+ }
+
+ if (map_addr == NULL) {
+ munmap(vaddr, map->size);
+ vaddr = MAP_FAILED;
+ CDX_BUS_ERR("Failed to map cdx MMIO region %d", index);
+ return -1;
+ }
+ } else {
+ CDX_BUS_ERR("Failed to create inaccessible mapping for MMIO
region %d",
+ index);
+ return -1;
+ }
+
+ map->addr = vaddr;
+ return 0;
+}
+
+/*
+ * region info may contain capability headers, so we need to keep reallocating
+ * the memory until we match allocated memory size with argsz.
+ */
+static int
+cdx_vfio_get_region_info(int vfio_dev_fd, struct vfio_region_info **info,
+ int region)
+{
+ struct vfio_region_info *ri;
+ size_t argsz = sizeof(*ri);
+ int ret;
+
+ ri = malloc(sizeof(*ri));
+ if (ri == NULL) {
+ CDX_BUS_ERR("Cannot allocate memory for VFIO region info");
+ return -1;
+ }
+again:
+ memset(ri, 0, argsz);
+ ri->argsz = argsz;
+ ri->index = region;
+
+ ret = ioctl(vfio_dev_fd, VFIO_DEVICE_GET_REGION_INFO, ri);
+ if (ret < 0) {
+ free(ri);
+ return ret;
+ }
+ if (ri->argsz != argsz) {
+ struct vfio_region_info *tmp;
+
+ argsz = ri->argsz;
+ tmp = realloc(ri, argsz);
+
+ if (tmp == NULL) {
+ /* realloc failed but the ri is still there */
+ free(ri);
+ CDX_BUS_ERR("Cannot reallocate memory for VFIO region
info");
+ return -1;
+ }
+ ri = tmp;
+ goto again;
+ }
+ *info = ri;
+
+ return 0;
+}
+
+static int
+cdx_vfio_map_resource_primary(struct rte_cdx_device *dev)
+{
+ struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
+ char cdx_addr[PATH_MAX] = {0};
+ static void *cdx_map_addr;
+ struct mapped_cdx_resource *vfio_res = NULL;
+ struct mapped_cdx_res_list *vfio_res_list =
+ RTE_TAILQ_CAST(cdx_vfio_tailq.head, mapped_cdx_res_list);
+ const char *dev_name = dev->device.name;
+ struct cdx_map *maps;
+ int vfio_dev_fd, i, ret;
+
+ ret = rte_vfio_setup_device(rte_cdx_get_sysfs_path(), dev_name,
+ &vfio_dev_fd, &device_info);
+ if (ret)
+ return ret;
+
+ /* allocate vfio_res and get region info */
+ vfio_res = rte_zmalloc("VFIO_RES", sizeof(*vfio_res), 0);
+ if (vfio_res == NULL) {
+ CDX_BUS_ERR("Cannot store VFIO mmap details");
+ goto err_vfio_dev_fd;
+ }
+ memcpy(vfio_res->name, dev_name, RTE_DEV_NAME_MAX_LEN);
+
+ /* get number of registers */
+ vfio_res->nb_maps = device_info.num_regions;
+
+ /* map memory regions */
+ maps = vfio_res->maps;
+
+ for (i = 0; i < vfio_res->nb_maps; i++) {
+ struct vfio_region_info *reg = NULL;
+ void *vaddr;
+
+ ret = cdx_vfio_get_region_info(vfio_dev_fd, ®, i);
+ if (ret < 0) {
+ CDX_BUS_ERR("%s cannot get device region info error %i
(%s)",
+ dev_name, errno, strerror(errno));
+ goto err_vfio_res;
+ }
+
+ /* skip non-mmappable regions */
+ if ((reg->flags & VFIO_REGION_INFO_FLAG_MMAP) == 0) {
+ free(reg);
+ continue;
+ }
+
+ /* try mapping somewhere close to the end of hugepages */
+ if (cdx_map_addr == NULL)
+ cdx_map_addr = cdx_find_max_end_va();
+
+ vaddr = cdx_map_addr;
+ cdx_map_addr = RTE_PTR_ADD(vaddr, (size_t)reg->size);
+
+ cdx_map_addr = RTE_PTR_ALIGN(cdx_map_addr,
+ sysconf(_SC_PAGE_SIZE));
+
+ maps[i].addr = vaddr;
+ maps[i].offset = reg->offset;
+ maps[i].size = reg->size;
+ maps[i].path = NULL; /* vfio doesn't have per-resource paths */
+
+ ret = cdx_vfio_mmap_resource(vfio_dev_fd, vfio_res, i, 0);
+ if (ret < 0) {
+ CDX_BUS_ERR("%s mapping region %i failed: %s",
+ cdx_addr, i, strerror(errno));
+ free(reg);
+ goto err_vfio_res;
+ }
+
+ dev->mem_resource[i].addr = maps[i].addr;
+ dev->mem_resource[i].len = maps[i].size;
+
+ free(reg);
+ }
+
+ if (cdx_rte_vfio_setup_device(vfio_dev_fd) < 0) {
+ CDX_BUS_ERR("%s setup device failed", dev_name);
+ goto err_vfio_res;
+ }
+
+ TAILQ_INSERT_TAIL(vfio_res_list, vfio_res, next);
+
+ return 0;
+err_vfio_res:
+ cdx_vfio_find_and_unmap_resource(vfio_res_list, dev);
+ rte_free(vfio_res);
+err_vfio_dev_fd:
+ rte_vfio_release_device(rte_cdx_get_sysfs_path(),
+ dev_name, vfio_dev_fd);
+ return -1;
+}
+
+static int
+cdx_vfio_map_resource_secondary(struct rte_cdx_device *dev)
+{
+ struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
+ char cdx_addr[PATH_MAX] = {0};
+ int vfio_dev_fd;
+ int i, ret;
+ struct mapped_cdx_resource *vfio_res = NULL;
+ struct mapped_cdx_res_list *vfio_res_list =
+ RTE_TAILQ_CAST(cdx_vfio_tailq.head, mapped_cdx_res_list);
+ const char *dev_name = dev->device.name;
+ struct cdx_map *maps;
+
+ /* if we're in a secondary process, just find our tailq entry */
+ TAILQ_FOREACH(vfio_res, vfio_res_list, next) {
+ if (strcmp(vfio_res->name, dev_name))
+ continue;
+ break;
+ }
+ /* if we haven't found our tailq entry, something's wrong */
+ if (vfio_res == NULL) {
+ CDX_BUS_ERR("%s cannot find TAILQ entry for cdx device!",
+ dev_name);
+ return -1;
+ }
+
+ ret = rte_vfio_setup_device(rte_cdx_get_sysfs_path(), dev_name,
+ &vfio_dev_fd, &device_info);
+ if (ret)
+ return ret;
+
+ /* map MMIO regions */
+ maps = vfio_res->maps;
+
+ for (i = 0; i < vfio_res->nb_maps; i++) {
+ ret = cdx_vfio_mmap_resource(vfio_dev_fd, vfio_res, i,
MAP_FIXED);
+ if (ret < 0) {
+ CDX_BUS_ERR("%s mapping MMIO region %i failed: %s",
+ dev_name, i, strerror(errno));
+ goto err_vfio_dev_fd;
+ }
+
+ dev->mem_resource[i].addr = maps[i].addr;
+ dev->mem_resource[i].len = maps[i].size;
+ }
+
+ return 0;
+err_vfio_dev_fd:
+ rte_vfio_release_device(rte_cdx_get_sysfs_path(),
+ cdx_addr, vfio_dev_fd);
+ return -1;
+}
+
+/*
+ * map the CDX resources of a CDX device in virtual memory (VFIO version).
+ * primary and secondary processes follow almost exactly the same path
+ */
+int
+cdx_vfio_map_resource(struct rte_cdx_device *dev)
+{
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+ return cdx_vfio_map_resource_primary(dev);
+ else
+ return cdx_vfio_map_resource_secondary(dev);
+}
diff --git a/drivers/bus/cdx/meson.build b/drivers/bus/cdx/meson.build
new file mode 100644
index 0000000000..2fb0e1cefd
--- /dev/null
+++ b/drivers/bus/cdx/meson.build
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+
+if not is_linux
+ build = false
+ reason = 'only supported on Linux'
+endif
+
+headers = files('rte_bus_cdx.h')
+sources = files(
+ 'cdx.c',
+ 'cdx_vfio.c',
+)
diff --git a/drivers/bus/cdx/rte_bus_cdx.h b/drivers/bus/cdx/rte_bus_cdx.h
new file mode 100644
index 0000000000..2ebe2a0dcc
--- /dev/null
+++ b/drivers/bus/cdx/rte_bus_cdx.h
@@ -0,0 +1,219 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _RTE_BUS_CDX_H_
+#define _RTE_BUS_CDX_H_
+
+/**
+ * @file
+ *
+ * CDX device & driver interface
+ *
+ * @warning
+ * @b EXPERIMENTAL:
+ * All functions in this file may be changed or removed without prior notice.
+ *
+ * CDX is a Hardware Architecture designed for AMD FPGA and HNIC devices.
+ * These devices are provided as CDX devices for the user. This driver
+ * provides user interface for devices on the CDX bus.
+ *
+ */
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <limits.h>
+#include <errno.h>
+#include <stdint.h>
+#include <inttypes.h>
+
+#include <bus_driver.h>
+#include <dev_driver.h>
+#include <rte_debug.h>
+#include <rte_interrupts.h>
+#include <rte_dev.h>
+#include <rte_bus.h>
+
+/* Forward declarations */
+struct rte_cdx_device;
+struct rte_cdx_driver;
+
+#define CDX_MAX_RESOURCE 4
+
+/** List of CDX devices */
+RTE_TAILQ_HEAD(rte_cdx_device_list, rte_cdx_device);
+/** List of CDX drivers */
+RTE_TAILQ_HEAD(rte_cdx_driver_list, rte_cdx_driver);
+
+/* CDX Bus iterators */
+#define FOREACH_DEVICE_ON_CDXBUS(p) \
+ RTE_TAILQ_FOREACH(p, &rte_cdx_bus.device_list, next)
+
+#define FOREACH_DRIVER_ON_CDXBUS(p) \
+ RTE_TAILQ_FOREACH(p, &rte_cdx_bus.driver_list, next)
+
+/** Any CDX device identifier (vendor, device) */
+#define RTE_CDX_ANY_ID (0xffff)
+
+#define RTE_PMD_REGISTER_CDX_TABLE(name, table) \
+static const char DRV_EXP_TAG(name, cdx_tbl_export)[] __rte_used = \
+RTE_STR(table)
+
+/**
+ * A structure describing an ID for a CDX driver. Each driver provides a
+ * table of these IDs for each device that it supports.
+ */
+struct rte_cdx_id {
+ uint16_t vendor_id; /**< Vendor ID. */
+ uint16_t device_id; /**< Device ID. */
+};
+
+/**
+ * A structure describing a CDX device.
+ */
+struct rte_cdx_device {
+ RTE_TAILQ_ENTRY(rte_cdx_device) next; /**< Next probed CDX device. */
+ struct rte_device device; /**< Inherit core device */
+ struct rte_cdx_id id; /**< CDX ID. */
+ struct rte_mem_resource mem_resource[CDX_MAX_RESOURCE];
+ /**< CDX Memory Resource */
+};
+
+/**
+ * @internal
+ * Helper macro for drivers that need to convert to struct rte_cdx_device.
+ */
+#define RTE_DEV_TO_CDX_DEV(ptr) \
+ container_of(ptr, struct rte_cdx_device, device)
+
+#define RTE_DEV_TO_CDX_DEV_CONST(ptr) \
+ container_of(ptr, const struct rte_cdx_device, device)
+
+#define RTE_ETH_DEV_TO_CDX_DEV(eth_dev)
RTE_DEV_TO_CDX_DEV((eth_dev)->device)
+
+#ifdef __cplusplus
+/** C++ macro used to help building up tables of device IDs */
+#define RTE_CDX_DEVICE(vend, dev) \
+ (vend), \
+ (dev)
+#else
+/** Macro used to help building up tables of device IDs */
+#define RTE_CDX_DEVICE(vend, dev) \
+ .vendor_id = (vend), \
+ .device_id = (dev)
+#endif
+
+/**
+ * Initialisation function for the driver called during CDX probing.
+ */
+typedef int (rte_cdx_probe_t)(struct rte_cdx_driver *, struct rte_cdx_device
*);
+
+/**
+ * Uninitialisation function for the driver called during hotplugging.
+ */
+typedef int (rte_cdx_remove_t)(struct rte_cdx_device *);
+
+/**
+ * A structure describing a CDX driver.
+ */
+struct rte_cdx_driver {
+ RTE_TAILQ_ENTRY(rte_cdx_driver) next; /**< Next in list. */
+ struct rte_driver driver; /**< Inherit core driver. */
+ struct rte_cdx_bus *bus; /**< CDX bus reference. */
+ rte_cdx_probe_t *probe; /**< Device probe function. */
+ rte_cdx_remove_t *remove; /**< Device remove function. */
+ const struct rte_cdx_id *id_table; /**< ID table, NULL terminated.
*/
+ uint32_t drv_flags; /**< Flags RTE_CDX_DRV_*. */
+};
+
+/**
+ * Structure describing the CDX bus
+ */
+struct rte_cdx_bus {
+ struct rte_bus bus; /**< Inherit the generic class
*/
+ struct rte_cdx_device_list device_list; /**< List of CDX devices */
+ struct rte_cdx_driver_list driver_list; /**< List of CDX drivers */
+};
+
+/**
+ * Get Pathname of CDX devices directory.
+ *
+ * @return
+ * sysfs path for CDX devices.
+ */
+__rte_internal
+const char *rte_cdx_get_sysfs_path(void);
+
+/**
+ * Map the CDX device resources in user space virtual memory address
+ *
+ * @param dev
+ * A pointer to a rte_cdx_device structure describing the device
+ * to use
+ *
+ * @return
+ * 0 on success, negative on error and positive if no driver
+ * is found for the device.
+ */
+__rte_internal
+int rte_cdx_map_device(struct rte_cdx_device *dev);
+
+/**
+ * Unmap this device
+ *
+ * @param dev
+ * A pointer to a rte_cdx_device structure describing the device
+ * to use
+ */
+__rte_internal
+void rte_cdx_unmap_device(struct rte_cdx_device *dev);
+
+/**
+ * Dump the content of the CDX bus.
+ *
+ * @param f
+ * A pointer to a file for output
+ */
+__rte_experimental
+void rte_cdx_dump(FILE *f);
+
+/**
+ * Register a CDX driver.
+ *
+ * @param driver
+ * A pointer to a rte_cdx_driver structure describing the driver
+ * to be registered.
+ */
+__rte_internal
+void rte_cdx_register(struct rte_cdx_driver *driver);
+
+/**
+ * Helper for CDX device registration from driver (eth, crypto, raw) instance
+ */
+#define RTE_PMD_REGISTER_CDX(nm, cdx_drv) \
+ RTE_INIT(cdxinitfn_ ##nm) \
+ {\
+ (cdx_drv).driver.name = RTE_STR(nm);\
+ rte_cdx_register(&cdx_drv); \
+ } \
+ RTE_PMD_EXPORT_NAME(nm, __COUNTER__)
+
+/**
+ * Unregister a CDX driver.
+ *
+ * @param driver
+ * A pointer to a rte_cdx_driver structure describing the driver
+ * to be unregistered.
+ */
+__rte_internal
+void rte_cdx_unregister(struct rte_cdx_driver *driver);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_BUS_CDX_H_ */
diff --git a/drivers/bus/cdx/version.map b/drivers/bus/cdx/version.map
new file mode 100644
index 0000000000..4e8dd24f91
--- /dev/null
+++ b/drivers/bus/cdx/version.map
@@ -0,0 +1,19 @@
+EXPERIMENTAL {
+ global:
+
+ rte_cdx_dump;
+
+ local: *;
+};
+
+INTERNAL {
+ global:
+
+ rte_cdx_get_sysfs_path;
+ rte_cdx_map_device;
+ rte_cdx_register;
+ rte_cdx_unmap_device;
+ rte_cdx_unregister;
+
+ local: *;
+};
--
2.17.1
