#include <rte_log.h>
#include <rte_pci.h>
#include <rte_bus_pci.h>
-#include <rte_eal_memconfig.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"
* This code tries to determine if the PCI device is bound to VFIO driver,
* and initialize it (map BARs, set up interrupts) if that's the case.
*
- * This file is only compiled if CONFIG_RTE_EAL_VFIO is set to "y".
*/
#ifdef VFIO_PRESENT
+#ifndef PAGE_SIZE
#define PAGE_SIZE (sysconf(_SC_PAGESIZE))
+#endif
#define PAGE_MASK (~(PAGE_SIZE - 1))
static struct rte_tailq_elem rte_vfio_tailq = {
return 0;
}
+/* enable PCI bus memory space */
+static int
+pci_vfio_enable_bus_memory(int dev_fd)
+{
+ uint16_t cmd;
+ int ret;
+
+ ret = pread64(dev_fd, &cmd, sizeof(cmd),
+ VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
+ PCI_COMMAND);
+
+ if (ret != sizeof(cmd)) {
+ RTE_LOG(ERR, EAL, "Cannot read command from PCI config space!\n");
+ return -1;
+ }
+
+ if (cmd & PCI_COMMAND_MEMORY)
+ return 0;
+
+ cmd |= PCI_COMMAND_MEMORY;
+ ret = pwrite64(dev_fd, &cmd, sizeof(cmd),
+ VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
+ PCI_COMMAND);
+
+ if (ret != sizeof(cmd)) {
+ RTE_LOG(ERR, EAL, "Cannot write command to PCI config space!\n");
+ return -1;
+ }
+
+ return 0;
+}
+
/* set PCI bus mastering */
static int
pci_vfio_set_bus_master(int dev_fd, bool op)
return -1;
}
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+/*
+ * Spinlock for device hot-unplug failure handling.
+ * If it tries to access bus or device, such as handle sigbus on bus
+ * or handle memory failure for device, just need to use this lock.
+ * It could protect the bus and the device to avoid race condition.
+ */
+static rte_spinlock_t failure_handle_lock = RTE_SPINLOCK_INITIALIZER;
+
+static void
+pci_vfio_req_handler(void *param)
+{
+ struct rte_bus *bus;
+ int ret;
+ struct rte_device *device = (struct rte_device *)param;
+
+ rte_spinlock_lock(&failure_handle_lock);
+ bus = rte_bus_find_by_device(device);
+ if (bus == NULL) {
+ RTE_LOG(ERR, EAL, "Cannot find bus for device (%s)\n",
+ device->name);
+ goto handle_end;
+ }
+
+ /*
+ * vfio kernel module request user space to release allocated
+ * resources before device be deleted in kernel, so it can directly
+ * call the vfio bus hot-unplug handler to process it.
+ */
+ ret = bus->hot_unplug_handler(device);
+ if (ret)
+ RTE_LOG(ERR, EAL,
+ "Can not handle hot-unplug for device (%s)\n",
+ device->name);
+handle_end:
+ rte_spinlock_unlock(&failure_handle_lock);
+}
+
+/* enable notifier (only enable req now) */
+static int
+pci_vfio_enable_notifier(struct rte_pci_device *dev, int vfio_dev_fd)
+{
+ int ret;
+ int fd = -1;
+
+ /* set up an eventfd for req notifier */
+ fd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC);
+ if (fd < 0) {
+ RTE_LOG(ERR, EAL, "Cannot set up eventfd, error %i (%s)\n",
+ errno, strerror(errno));
+ return -1;
+ }
+
+ dev->vfio_req_intr_handle.fd = fd;
+ dev->vfio_req_intr_handle.type = RTE_INTR_HANDLE_VFIO_REQ;
+ dev->vfio_req_intr_handle.vfio_dev_fd = vfio_dev_fd;
+
+ ret = rte_intr_callback_register(&dev->vfio_req_intr_handle,
+ pci_vfio_req_handler,
+ (void *)&dev->device);
+ if (ret) {
+ RTE_LOG(ERR, EAL, "Fail to register req notifier handler.\n");
+ goto error;
+ }
+
+ ret = rte_intr_enable(&dev->vfio_req_intr_handle);
+ if (ret) {
+ RTE_LOG(ERR, EAL, "Fail to enable req notifier.\n");
+ ret = rte_intr_callback_unregister(&dev->vfio_req_intr_handle,
+ pci_vfio_req_handler,
+ (void *)&dev->device);
+ if (ret < 0)
+ RTE_LOG(ERR, EAL,
+ "Fail to unregister req notifier handler.\n");
+ goto error;
+ }
+
+ return 0;
+error:
+ close(fd);
+
+ dev->vfio_req_intr_handle.fd = -1;
+ dev->vfio_req_intr_handle.type = RTE_INTR_HANDLE_UNKNOWN;
+ dev->vfio_req_intr_handle.vfio_dev_fd = -1;
+
+ return -1;
+}
+
+/* disable notifier (only disable req now) */
+static int
+pci_vfio_disable_notifier(struct rte_pci_device *dev)
+{
+ int ret;
+
+ ret = rte_intr_disable(&dev->vfio_req_intr_handle);
+ if (ret) {
+ RTE_LOG(ERR, EAL, "fail to disable req notifier.\n");
+ return -1;
+ }
+
+ ret = rte_intr_callback_unregister(&dev->vfio_req_intr_handle,
+ pci_vfio_req_handler,
+ (void *)&dev->device);
+ if (ret < 0) {
+ RTE_LOG(ERR, EAL,
+ "fail to unregister req notifier handler.\n");
+ return -1;
+ }
+
+ close(dev->vfio_req_intr_handle.fd);
+
+ dev->vfio_req_intr_handle.fd = -1;
+ dev->vfio_req_intr_handle.type = RTE_INTR_HANDLE_UNKNOWN;
+ dev->vfio_req_intr_handle.vfio_dev_fd = -1;
+
+ return 0;
+}
+#endif
+
static int
pci_vfio_is_ioport_bar(int vfio_dev_fd, int bar_index)
{
return -1;
}
+ if (pci_vfio_enable_bus_memory(vfio_dev_fd)) {
+ RTE_LOG(ERR, EAL, "Cannot enable bus memory!\n");
+ return -1;
+ }
+
/* set bus mastering for the device */
if (pci_vfio_set_bus_master(vfio_dev_fd, true)) {
RTE_LOG(ERR, EAL, "Cannot set up bus mastering!\n");
int bar_index, int additional_flags)
{
struct memreg {
- unsigned long offset, size;
+ uint64_t offset;
+ size_t size;
} memreg[2] = {};
void *bar_addr;
struct pci_msix_table *msix_table = &vfio_res->msix_table;
struct pci_map *bar = &vfio_res->maps[bar_index];
- if (bar->size == 0)
- /* Skip this BAR */
+ if (bar->size == 0) {
+ RTE_LOG(DEBUG, EAL, "Bar size is 0, skip BAR%d\n", bar_index);
return 0;
+ }
if (msix_table->bar_index == bar_index) {
/*
*/
uint32_t table_start = msix_table->offset;
uint32_t table_end = table_start + msix_table->size;
- table_end = (table_end + ~PAGE_MASK) & PAGE_MASK;
- table_start &= PAGE_MASK;
+ table_end = RTE_ALIGN(table_end, PAGE_SIZE);
+ table_start = RTE_ALIGN_FLOOR(table_start, PAGE_SIZE);
+
+ /* If page-aligned start of MSI-X table is less than the
+ * actual MSI-X table start address, reassign to the actual
+ * start address.
+ */
+ if (table_start < msix_table->offset)
+ table_start = msix_table->offset;
if (table_start == 0 && table_end >= bar->size) {
/* Cannot map this BAR */
memreg[0].offset = bar->offset;
memreg[0].size = table_start;
- memreg[1].offset = bar->offset + table_end;
- memreg[1].size = bar->size - table_end;
+ if (bar->size < table_end) {
+ /*
+ * If MSI-X table end is beyond BAR end, don't attempt
+ * to perform second mapping.
+ */
+ memreg[1].offset = 0;
+ memreg[1].size = 0;
+ } else {
+ memreg[1].offset = bar->offset + table_end;
+ memreg[1].size = bar->size - table_end;
+ }
RTE_LOG(DEBUG, EAL,
"Trying to map BAR%d that contains the MSI-X "
"table. Trying offsets: "
- "0x%04lx:0x%04lx, 0x%04lx:0x%04lx\n", bar_index,
+ "0x%04" PRIx64 ":0x%04zx, 0x%04" PRIx64 ":0x%04zx\n",
+ bar_index,
memreg[0].offset, memreg[0].size,
memreg[1].offset, memreg[1].size);
} else {
map_addr = pci_map_resource(bar_addr, vfio_dev_fd,
memreg[0].offset,
memreg[0].size,
- MAP_FIXED);
+ RTE_MAP_FORCE_ADDRESS);
}
+ /*
+ * Regarding "memreg[0].size == 0":
+ * If this BAR has MSI-X table, memreg[0].size (the
+ * first part or the part before the table) can
+ * legitimately be 0 for hardware using vector table
+ * offset 0 (i.e. first part does not exist).
+ *
+ * When memreg[0].size is 0, "mapping the first part"
+ * never happens, and map_addr is NULL at this
+ * point. So check that mapping has been actually
+ * attempted.
+ */
/* if there's a second part, try to map it */
- if (map_addr != MAP_FAILED
+ if ((map_addr != NULL || memreg[0].size == 0)
&& memreg[1].offset && memreg[1].size) {
void *second_addr = RTE_PTR_ADD(bar_addr,
- memreg[1].offset -
- (uintptr_t)bar->offset);
+ (uintptr_t)(memreg[1].offset -
+ bar->offset));
map_addr = pci_map_resource(second_addr,
vfio_dev_fd,
memreg[1].offset,
memreg[1].size,
- MAP_FIXED);
+ RTE_MAP_FORCE_ADDRESS);
}
- if (map_addr == MAP_FAILED || !map_addr) {
+ if (map_addr == NULL) {
munmap(bar_addr, bar->size);
bar_addr = MAP_FAILED;
RTE_LOG(ERR, EAL, "Failed to map pci BAR%d\n",
struct pci_map *maps;
dev->intr_handle.fd = -1;
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+ dev->vfio_req_intr_handle.fd = -1;
+#endif
/* store PCI address string */
snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
vfio_res = rte_zmalloc("VFIO_RES", sizeof(*vfio_res), 0);
if (vfio_res == NULL) {
RTE_LOG(ERR, EAL,
- "%s(): cannot store uio mmap details\n", __func__);
+ "%s(): cannot store vfio mmap details\n", __func__);
goto err_vfio_dev_fd;
}
memcpy(&vfio_res->pci_addr, &dev->addr, sizeof(vfio_res->pci_addr));
}
}
- for (i = 0; i < (int) vfio_res->nb_maps; i++) {
+ for (i = 0; i < vfio_res->nb_maps; i++) {
struct vfio_region_info *reg = NULL;
void *bar_addr;
bar_addr = pci_map_addr;
pci_map_addr = RTE_PTR_ADD(bar_addr, (size_t) reg->size);
+ pci_map_addr = RTE_PTR_ALIGN(pci_map_addr,
+ sysconf(_SC_PAGE_SIZE));
+
maps[i].addr = bar_addr;
maps[i].offset = reg->offset;
maps[i].size = reg->size;
goto err_vfio_res;
}
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+ if (pci_vfio_enable_notifier(dev, vfio_dev_fd) != 0) {
+ RTE_LOG(ERR, EAL, "Error setting up notifier!\n");
+ goto err_vfio_res;
+ }
+
+#endif
TAILQ_INSERT_TAIL(vfio_res_list, vfio_res, next);
return 0;
err_vfio_res:
rte_free(vfio_res);
err_vfio_dev_fd:
- close(vfio_dev_fd);
+ rte_vfio_release_device(rte_pci_get_sysfs_path(),
+ pci_addr, vfio_dev_fd);
return -1;
}
struct pci_map *maps;
dev->intr_handle.fd = -1;
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+ dev->vfio_req_intr_handle.fd = -1;
+#endif
/* store PCI address string */
snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
loc->domain, loc->bus, loc->devid, loc->function);
- ret = rte_vfio_setup_device(rte_pci_get_sysfs_path(), pci_addr,
- &vfio_dev_fd, &device_info);
- if (ret)
- return ret;
-
/* if we're in a secondary process, just find our tailq entry */
TAILQ_FOREACH(vfio_res, vfio_res_list, next) {
if (rte_pci_addr_cmp(&vfio_res->pci_addr,
if (vfio_res == NULL) {
RTE_LOG(ERR, EAL, " %s cannot find TAILQ entry for PCI device!\n",
pci_addr);
- goto err_vfio_dev_fd;
+ return -1;
}
+ ret = rte_vfio_setup_device(rte_pci_get_sysfs_path(), pci_addr,
+ &vfio_dev_fd, &device_info);
+ if (ret)
+ return ret;
+
/* map BARs */
maps = vfio_res->maps;
- for (i = 0; i < (int) vfio_res->nb_maps; i++) {
+ for (i = 0; i < vfio_res->nb_maps; i++) {
ret = pci_vfio_mmap_bar(vfio_dev_fd, vfio_res, i, MAP_FIXED);
if (ret < 0) {
RTE_LOG(ERR, EAL, " %s mapping BAR%i failed: %s\n",
/* we need save vfio_dev_fd, so it can be used during release */
dev->intr_handle.vfio_dev_fd = vfio_dev_fd;
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+ dev->vfio_req_intr_handle.vfio_dev_fd = vfio_dev_fd;
+#endif
return 0;
err_vfio_dev_fd:
- close(vfio_dev_fd);
+ rte_vfio_release_device(rte_pci_get_sysfs_path(),
+ pci_addr, vfio_dev_fd);
return -1;
}
pci_addr);
maps = vfio_res->maps;
- for (i = 0; i < (int) vfio_res->nb_maps; i++) {
+ for (i = 0; i < vfio_res->nb_maps; i++) {
/*
* We do not need to be aware of MSI-X table BAR mappings as
snprintf(pci_addr, sizeof(pci_addr), PCI_PRI_FMT,
loc->domain, loc->bus, loc->devid, loc->function);
+#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
+ ret = pci_vfio_disable_notifier(dev);
+ if (ret) {
+ RTE_LOG(ERR, EAL, "fail to disable req notifier.\n");
+ return -1;
+ }
+
+#endif
if (close(dev->intr_handle.fd) < 0) {
RTE_LOG(INFO, EAL, "Error when closing eventfd file descriptor for %s\n",
pci_addr);
}
TAILQ_REMOVE(vfio_res_list, vfio_res, next);
-
+ rte_free(vfio_res);
return 0;
}