#include <rte_bus.h>
#include <rte_pci.h>
#include <rte_bus_pci.h>
-#include <rte_eal_memconfig.h>
#include <rte_malloc.h>
#include <rte_devargs.h>
#include <rte_memcpy.h>
#include <rte_vfio.h>
-#include "eal_private.h"
#include "eal_filesystem.h"
#include "private.h"
extern struct rte_pci_bus rte_pci_bus;
static int
-pci_get_kernel_driver_by_path(const char *filename, char *dri_name)
+pci_get_kernel_driver_by_path(const char *filename, char *dri_name,
+ size_t len)
{
int count;
char path[PATH_MAX];
name = strrchr(path, '/');
if (name) {
- strncpy(dri_name, name + 1, strlen(name + 1) + 1);
+ strlcpy(dri_name, name + 1, len);
return 0;
}
}
}
-void *
-pci_find_max_end_va(void)
+static int
+find_max_end_va(const struct rte_memseg_list *msl, void *arg)
{
- const struct rte_memseg *seg = rte_eal_get_physmem_layout();
- const struct rte_memseg *last = seg;
- unsigned i = 0;
+ size_t sz = msl->len;
+ void *end_va = RTE_PTR_ADD(msl->base_va, sz);
+ void **max_va = arg;
- for (i = 0; i < RTE_MAX_MEMSEG; i++, seg++) {
- if (seg->addr == NULL)
- break;
+ if (*max_va < end_va)
+ *max_va = end_va;
+ return 0;
+}
- if (seg->addr > last->addr)
- last = seg;
+void *
+pci_find_max_end_va(void)
+{
+ void *va = NULL;
- }
- return RTE_PTR_ADD(last->addr, last->len);
+ rte_memseg_list_walk(find_max_end_va, &va);
+ return va;
}
+
/* parse one line of the "resource" sysfs file (note that the 'line'
* string is modified)
*/
return -1;
memset(dev, 0, sizeof(*dev));
+ dev->device.bus = &rte_pci_bus.bus;
dev->addr = *addr;
/* get vendor id */
/* parse driver */
snprintf(filename, sizeof(filename), "%s/driver", dirname);
- ret = pci_get_kernel_driver_by_path(filename, driver);
+ ret = pci_get_kernel_driver_by_path(filename, driver, sizeof(driver));
if (ret < 0) {
RTE_LOG(ERR, EAL, "Fail to get kernel driver\n");
free(dev);
if (ret < 0) {
rte_pci_insert_device(dev2, dev);
} else { /* already registered */
- dev2->kdrv = dev->kdrv;
- dev2->max_vfs = dev->max_vfs;
- pci_name_set(dev2);
- memmove(dev2->mem_resource, dev->mem_resource,
- sizeof(dev->mem_resource));
+ if (!rte_dev_is_probed(&dev2->device)) {
+ dev2->kdrv = dev->kdrv;
+ dev2->max_vfs = dev->max_vfs;
+ pci_name_set(dev2);
+ memmove(dev2->mem_resource,
+ dev->mem_resource,
+ sizeof(dev->mem_resource));
+ } else {
+ /**
+ * If device is plugged and driver is
+ * probed already, (This happens when
+ * we call rte_dev_probe which will
+ * scan all device on the bus) we don't
+ * need to do anything here unless...
+ **/
+ if (dev2->kdrv != dev->kdrv ||
+ dev2->max_vfs != dev->max_vfs)
+ /*
+ * This should not happens.
+ * But it is still possible if
+ * we unbind a device from
+ * vfio or uio before hotplug
+ * remove and rebind it with
+ * a different configure.
+ * So we just print out the
+ * error as an alarm.
+ */
+ RTE_LOG(ERR, EAL, "Unexpected device scan at %s!\n",
+ filename);
+ }
free(dev);
}
return 0;
return -1;
}
-/*
- * Is pci device bound to any kdrv
- */
-static inline int
-pci_one_device_is_bound(void)
+#if defined(RTE_ARCH_X86)
+bool
+pci_device_iommu_support_va(const struct rte_pci_device *dev)
{
- struct rte_pci_device *dev = NULL;
- int ret = 0;
-
- FOREACH_DEVICE_ON_PCIBUS(dev) {
- if (dev->kdrv == RTE_KDRV_UNKNOWN ||
- dev->kdrv == RTE_KDRV_NONE) {
- continue;
- } else {
- ret = 1;
- break;
- }
- }
- return ret;
-}
+#define VTD_CAP_MGAW_SHIFT 16
+#define VTD_CAP_MGAW_MASK (0x3fULL << VTD_CAP_MGAW_SHIFT)
+ const struct rte_pci_addr *addr = &dev->addr;
+ char filename[PATH_MAX];
+ FILE *fp;
+ uint64_t mgaw, vtd_cap_reg = 0;
-/*
- * Any one of the device bound to uio
- */
-static inline int
-pci_one_device_bound_uio(void)
-{
- struct rte_pci_device *dev = NULL;
- struct rte_devargs *devargs;
- int need_check;
-
- FOREACH_DEVICE_ON_PCIBUS(dev) {
- devargs = dev->device.devargs;
-
- need_check = 0;
- switch (rte_pci_bus.bus.conf.scan_mode) {
- case RTE_BUS_SCAN_WHITELIST:
- if (devargs && devargs->policy == RTE_DEV_WHITELISTED)
- need_check = 1;
- break;
- case RTE_BUS_SCAN_UNDEFINED:
- case RTE_BUS_SCAN_BLACKLIST:
- if (devargs == NULL ||
- devargs->policy != RTE_DEV_BLACKLISTED)
- need_check = 1;
- break;
- }
+ snprintf(filename, sizeof(filename),
+ "%s/" PCI_PRI_FMT "/iommu/intel-iommu/cap",
+ rte_pci_get_sysfs_path(), addr->domain, addr->bus, addr->devid,
+ addr->function);
- if (!need_check)
- continue;
+ fp = fopen(filename, "r");
+ if (fp == NULL) {
+ /* We don't have an Intel IOMMU, assume VA supported */
+ if (errno == ENOENT)
+ return true;
- if (dev->kdrv == RTE_KDRV_IGB_UIO ||
- dev->kdrv == RTE_KDRV_UIO_GENERIC) {
- return 1;
- }
+ RTE_LOG(ERR, EAL, "%s(): can't open %s: %s\n",
+ __func__, filename, strerror(errno));
+ return false;
}
- return 0;
-}
-/*
- * Any one of the device has iova as va
- */
-static inline int
-pci_one_device_has_iova_va(void)
-{
- struct rte_pci_device *dev = NULL;
- struct rte_pci_driver *drv = NULL;
-
- FOREACH_DRIVER_ON_PCIBUS(drv) {
- if (drv && drv->drv_flags & RTE_PCI_DRV_IOVA_AS_VA) {
- FOREACH_DEVICE_ON_PCIBUS(dev) {
- if (dev->kdrv == RTE_KDRV_VFIO &&
- rte_pci_match(drv, dev))
- return 1;
- }
- }
+ /* We have an Intel IOMMU */
+ if (fscanf(fp, "%" PRIx64, &vtd_cap_reg) != 1) {
+ RTE_LOG(ERR, EAL, "%s(): can't read %s\n", __func__, filename);
+ fclose(fp);
+ return false;
}
- return 0;
-}
-/*
- * Get iommu class of PCI devices on the bus.
- */
-enum rte_iova_mode
-rte_pci_get_iommu_class(void)
+ fclose(fp);
+
+ mgaw = ((vtd_cap_reg & VTD_CAP_MGAW_MASK) >> VTD_CAP_MGAW_SHIFT) + 1;
+
+ /*
+ * Assuming there is no limitation by now. We can not know at this point
+ * because the memory has not been initialized yet. Setting the dma mask
+ * will force a check once memory initialization is done. We can not do
+ * a fallback to IOVA PA now, but if the dma check fails, the error
+ * message should advice for using '--iova-mode pa' if IOVA VA is the
+ * current mode.
+ */
+ rte_mem_set_dma_mask(mgaw);
+ return true;
+}
+#elif defined(RTE_ARCH_PPC_64)
+bool
+pci_device_iommu_support_va(__rte_unused const struct rte_pci_device *dev)
{
- bool is_bound;
- bool is_vfio_noiommu_enabled = true;
- bool has_iova_va;
- bool is_bound_uio;
- bool spapr_iommu =
-#if defined(RTE_ARCH_PPC_64)
- true;
+ return false;
+}
#else
- false;
+bool
+pci_device_iommu_support_va(__rte_unused const struct rte_pci_device *dev)
+{
+ return true;
+}
#endif
- is_bound = pci_one_device_is_bound();
- if (!is_bound)
- return RTE_IOVA_DC;
+enum rte_iova_mode
+pci_device_iova_mode(const struct rte_pci_driver *pdrv,
+ const struct rte_pci_device *pdev)
+{
+ enum rte_iova_mode iova_mode = RTE_IOVA_DC;
- has_iova_va = pci_one_device_has_iova_va();
- is_bound_uio = pci_one_device_bound_uio();
+ switch (pdev->kdrv) {
+ case RTE_KDRV_VFIO: {
#ifdef VFIO_PRESENT
- is_vfio_noiommu_enabled = rte_vfio_noiommu_is_enabled() == true ?
- true : false;
+ static int is_vfio_noiommu_enabled = -1;
+
+ if (is_vfio_noiommu_enabled == -1) {
+ if (rte_vfio_noiommu_is_enabled() == 1)
+ is_vfio_noiommu_enabled = 1;
+ else
+ is_vfio_noiommu_enabled = 0;
+ }
+ if (is_vfio_noiommu_enabled != 0)
+ iova_mode = RTE_IOVA_PA;
+ else if ((pdrv->drv_flags & RTE_PCI_DRV_NEED_IOVA_AS_VA) != 0)
+ iova_mode = RTE_IOVA_VA;
#endif
+ break;
+ }
- if (has_iova_va && !is_bound_uio && !is_vfio_noiommu_enabled &&
- !spapr_iommu)
- return RTE_IOVA_VA;
+ case RTE_KDRV_IGB_UIO:
+ case RTE_KDRV_UIO_GENERIC:
+ iova_mode = RTE_IOVA_PA;
+ break;
- if (has_iova_va) {
- RTE_LOG(WARNING, EAL, "Some devices want iova as va but pa will be used because.. ");
- if (is_vfio_noiommu_enabled)
- RTE_LOG(WARNING, EAL, "vfio-noiommu mode configured\n");
- if (is_bound_uio)
- RTE_LOG(WARNING, EAL, "few device bound to UIO\n");
- if (spapr_iommu)
- RTE_LOG(WARNING, EAL, "sPAPR IOMMU does not support IOVA as VA\n");
+ default:
+ if ((pdrv->drv_flags & RTE_PCI_DRV_NEED_IOVA_AS_VA) != 0)
+ iova_mode = RTE_IOVA_VA;
+ break;
}
-
- return RTE_IOVA_PA;
+ return iova_mode;
}
/* Read PCI config space. */
int rte_pci_read_config(const struct rte_pci_device *device,
void *buf, size_t len, off_t offset)
{
+ char devname[RTE_DEV_NAME_MAX_LEN] = "";
const struct rte_intr_handle *intr_handle = &device->intr_handle;
- switch (intr_handle->type) {
- case RTE_INTR_HANDLE_UIO:
- case RTE_INTR_HANDLE_UIO_INTX:
+ switch (device->kdrv) {
+ case RTE_KDRV_IGB_UIO:
+ case RTE_KDRV_UIO_GENERIC:
return pci_uio_read_config(intr_handle, buf, len, offset);
-
#ifdef VFIO_PRESENT
- case RTE_INTR_HANDLE_VFIO_MSIX:
- case RTE_INTR_HANDLE_VFIO_MSI:
- case RTE_INTR_HANDLE_VFIO_LEGACY:
+ case RTE_KDRV_VFIO:
return pci_vfio_read_config(intr_handle, buf, len, offset);
#endif
default:
+ rte_pci_device_name(&device->addr, devname,
+ RTE_DEV_NAME_MAX_LEN);
RTE_LOG(ERR, EAL,
- "Unknown handle type of fd %d\n",
- intr_handle->fd);
+ "Unknown driver type for %s\n", devname);
return -1;
}
}
int rte_pci_write_config(const struct rte_pci_device *device,
const void *buf, size_t len, off_t offset)
{
+ char devname[RTE_DEV_NAME_MAX_LEN] = "";
const struct rte_intr_handle *intr_handle = &device->intr_handle;
- switch (intr_handle->type) {
- case RTE_INTR_HANDLE_UIO:
- case RTE_INTR_HANDLE_UIO_INTX:
+ switch (device->kdrv) {
+ case RTE_KDRV_IGB_UIO:
+ case RTE_KDRV_UIO_GENERIC:
return pci_uio_write_config(intr_handle, buf, len, offset);
-
#ifdef VFIO_PRESENT
- case RTE_INTR_HANDLE_VFIO_MSIX:
- case RTE_INTR_HANDLE_VFIO_MSI:
- case RTE_INTR_HANDLE_VFIO_LEGACY:
+ case RTE_KDRV_VFIO:
return pci_vfio_write_config(intr_handle, buf, len, offset);
#endif
default:
+ rte_pci_device_name(&device->addr, devname,
+ RTE_DEV_NAME_MAX_LEN);
RTE_LOG(ERR, EAL,
- "Unknown handle type of fd %d\n",
- intr_handle->fd);
+ "Unknown driver type for %s\n", devname);
return -1;
}
}
int found = 0;
size_t linesz;
+ if (rte_eal_iopl_init() != 0) {
+ RTE_LOG(ERR, EAL, "%s(): insufficient ioport permissions for PCI device %s\n",
+ __func__, dev->name);
+ return -1;
+ }
+
snprintf(pci_id, sizeof(pci_id), PCI_PRI_FMT,
dev->addr.domain, dev->addr.bus,
dev->addr.devid, dev->addr.function);