#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>
* 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
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)
static int
pci_vfio_setup_interrupts(struct rte_pci_device *dev, int vfio_dev_fd)
{
- char irq_set_buf[sizeof(struct vfio_irq_set) + sizeof(int)];
- struct vfio_irq_set *irq_set;
- enum rte_intr_mode intr_mode;
int i, ret, intr_idx;
- int fd;
+ enum rte_intr_mode intr_mode;
/* default to invalid index */
intr_idx = VFIO_PCI_NUM_IRQS;
/* start from MSI-X interrupt type */
for (i = VFIO_PCI_MSIX_IRQ_INDEX; i >= 0; i--) {
struct vfio_irq_info irq = { .argsz = sizeof(irq) };
+ int fd = -1;
/* skip interrupt modes we don't want */
if (intr_mode != RTE_INTR_MODE_NONE &&
return -1;
}
- /* found a usable interrupt mode */
- if ((irq.flags & VFIO_IRQ_INFO_EVENTFD) != 0)
- break;
-
/* if this vector cannot be used with eventfd, fail if we explicitly
* specified interrupt type, otherwise continue */
- if (intr_mode != RTE_INTR_MODE_NONE) {
- RTE_LOG(ERR, EAL, " interrupt vector does not support eventfd!\n");
+ if ((irq.flags & VFIO_IRQ_INFO_EVENTFD) == 0) {
+ if (intr_mode != RTE_INTR_MODE_NONE) {
+ RTE_LOG(ERR, EAL,
+ " interrupt vector does not support eventfd!\n");
+ return -1;
+ } else
+ continue;
+ }
+
+ /* set up an eventfd for interrupts */
+ 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;
}
- }
- if (i < 0)
- return -1;
+ dev->intr_handle.fd = fd;
+ dev->intr_handle.vfio_dev_fd = vfio_dev_fd;
- 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;
- }
+ switch (i) {
+ case VFIO_PCI_MSIX_IRQ_INDEX:
+ intr_mode = RTE_INTR_MODE_MSIX;
+ dev->intr_handle.type = RTE_INTR_HANDLE_VFIO_MSIX;
+ break;
+ case VFIO_PCI_MSI_IRQ_INDEX:
+ intr_mode = RTE_INTR_MODE_MSI;
+ dev->intr_handle.type = RTE_INTR_HANDLE_VFIO_MSI;
+ break;
+ case VFIO_PCI_INTX_IRQ_INDEX:
+ intr_mode = RTE_INTR_MODE_LEGACY;
+ dev->intr_handle.type = RTE_INTR_HANDLE_VFIO_LEGACY;
+ break;
+ default:
+ RTE_LOG(ERR, EAL, " unknown interrupt type!\n");
+ return -1;
+ }
- irq_set = (struct vfio_irq_set *)irq_set_buf;
- irq_set->argsz = sizeof(irq_set_buf);
- irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD|VFIO_IRQ_SET_ACTION_TRIGGER;
- irq_set->index = i;
- irq_set->start = 0;
- irq_set->count = 1;
- memcpy(&irq_set->data, &fd, sizeof(int));
- if (ioctl(vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set) < 0) {
- RTE_LOG(ERR, EAL, " error configuring interrupt\n");
- close(fd);
- return -1;
+ return 0;
}
- dev->intr_handle.fd = fd;
- dev->intr_handle.vfio_dev_fd = vfio_dev_fd;
- if (i == VFIO_PCI_MSIX_IRQ_INDEX)
- dev->intr_handle.type = RTE_INTR_HANDLE_VFIO_MSIX;
- else if (i == VFIO_PCI_MSI_IRQ_INDEX)
- dev->intr_handle.type = RTE_INTR_HANDLE_VFIO_MSI;
- else if (i == VFIO_PCI_INTX_IRQ_INDEX)
- dev->intr_handle.type = RTE_INTR_HANDLE_VFIO_LEGACY;
-
- return 0;
+ /* if we're here, we haven't found a suitable interrupt vector */
+ return -1;
}
#ifdef HAVE_VFIO_DEV_REQ_INTERFACE
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;
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",
}
}
- 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;
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;
}
/* 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",
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
}
TAILQ_REMOVE(vfio_res_list, vfio_res, next);
-
+ rte_free(vfio_res);
return 0;
}
git.droids-corp.org / dpdk.git / blobdiff