X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fbus%2Fpci%2Fpci_common.c;h=a8e5fd52c1d092e2c4e77eac45754904f7f8ef84;hb=79e5b5ed8e5350734e34484db33820c09ac99a7f;hp=94b0f4143e154b8b2c1c946d552ff557eec04237;hpb=1d20a073fa5eb04b9ab4a06ea71b770c17bc35c6;p=dpdk.git diff --git a/drivers/bus/pci/pci_common.c b/drivers/bus/pci/pci_common.c index 94b0f4143e..a8e5fd52c1 100644 --- a/drivers/bus/pci/pci_common.c +++ b/drivers/bus/pci/pci_common.c @@ -6,11 +6,10 @@ #include #include #include +#include #include #include #include -#include - #include #include #include @@ -23,35 +22,35 @@ #include #include #include +#include #include "private.h" -static void rte_pci_remove_device(struct rte_pci_device *pci_device); - -extern struct rte_pci_bus rte_pci_bus; - #define SYSFS_PCI_DEVICES "/sys/bus/pci/devices" const char *rte_pci_get_sysfs_path(void) { const char *path = NULL; +#ifdef RTE_EXEC_ENV_LINUX path = getenv("SYSFS_PCI_DEVICES"); if (path == NULL) return SYSFS_PCI_DEVICES; +#endif return path; } -static struct rte_devargs *pci_devargs_lookup(struct rte_pci_device *dev) +static struct rte_devargs * +pci_devargs_lookup(const struct rte_pci_addr *pci_addr) { struct rte_devargs *devargs; struct rte_pci_addr addr; RTE_EAL_DEVARGS_FOREACH("pci", devargs) { devargs->bus->parse(devargs->name, &addr); - if (!rte_pci_addr_cmp(&dev->addr, &addr)) + if (!rte_pci_addr_cmp(pci_addr, &addr)) return devargs; } return NULL; @@ -65,14 +64,14 @@ pci_name_set(struct rte_pci_device *dev) /* Each device has its internal, canonical name set. */ rte_pci_device_name(&dev->addr, dev->name, sizeof(dev->name)); - devargs = pci_devargs_lookup(dev); + devargs = pci_devargs_lookup(&dev->addr); dev->device.devargs = devargs; /* In blacklist mode, if the device is not blacklisted, no * rte_devargs exists for it. */ if (devargs != NULL) /* If an rte_devargs exists, the generic rte_device uses the - * given name as its namea + * given name as its name. */ dev->device.name = dev->device.devargs->name; else @@ -125,6 +124,7 @@ rte_pci_probe_one_driver(struct rte_pci_driver *dr, struct rte_pci_device *dev) { int ret; + bool already_probed; struct rte_pci_addr *loc; if ((dr == NULL) || (dev == NULL)) @@ -137,7 +137,7 @@ rte_pci_probe_one_driver(struct rte_pci_driver *dr, /* Match of device and driver failed */ return 1; - RTE_LOG(INFO, EAL, "PCI device "PCI_PRI_FMT" on NUMA socket %i\n", + RTE_LOG(DEBUG, EAL, "PCI device "PCI_PRI_FMT" on NUMA socket %i\n", loc->domain, loc->bus, loc->devid, loc->function, dev->device.numa_node); @@ -155,7 +155,14 @@ rte_pci_probe_one_driver(struct rte_pci_driver *dr, dev->device.numa_node = 0; } - RTE_LOG(INFO, EAL, " probe driver: %x:%x %s\n", dev->id.vendor_id, + already_probed = rte_dev_is_probed(&dev->device); + if (already_probed && !(dr->drv_flags & RTE_PCI_DRV_PROBE_AGAIN)) { + RTE_LOG(DEBUG, EAL, "Device %s is already probed\n", + dev->device.name); + return -EEXIST; + } + + RTE_LOG(DEBUG, EAL, " probe driver: %x:%x %s\n", dev->id.vendor_id, dev->id.device_id, dr->driver.name); /* @@ -163,24 +170,42 @@ rte_pci_probe_one_driver(struct rte_pci_driver *dr, * This needs to be before rte_pci_map_device(), as it enables to use * driver flags for adjusting configuration. */ - dev->driver = dr; - dev->device.driver = &dr->driver; + if (!already_probed) { + enum rte_iova_mode dev_iova_mode; + enum rte_iova_mode iova_mode; + + dev_iova_mode = pci_device_iova_mode(dr, dev); + iova_mode = rte_eal_iova_mode(); + if (dev_iova_mode != RTE_IOVA_DC && + dev_iova_mode != iova_mode) { + RTE_LOG(ERR, EAL, " Expecting '%s' IOVA mode but current mode is '%s', not initializing\n", + dev_iova_mode == RTE_IOVA_PA ? "PA" : "VA", + iova_mode == RTE_IOVA_PA ? "PA" : "VA"); + return -EINVAL; + } + + dev->driver = dr; + } - if (dr->drv_flags & RTE_PCI_DRV_NEED_MAPPING) { + if (!already_probed && (dr->drv_flags & RTE_PCI_DRV_NEED_MAPPING)) { /* map resources for devices that use igb_uio */ ret = rte_pci_map_device(dev); if (ret != 0) { dev->driver = NULL; - dev->device.driver = NULL; return ret; } } + RTE_LOG(INFO, EAL, "Probe PCI driver: %s (%x:%x) device: "PCI_PRI_FMT" (socket %i)\n", + dr->driver.name, dev->id.vendor_id, dev->id.device_id, + loc->domain, loc->bus, loc->devid, loc->function, + dev->device.numa_node); /* call the driver probe() function */ ret = dr->probe(dr, dev); + if (already_probed) + return ret; /* no rollback if already succeeded earlier */ if (ret) { dev->driver = NULL; - dev->device.driver = NULL; if ((dr->drv_flags & RTE_PCI_DRV_NEED_MAPPING) && /* Don't unmap if device is unsupported and * driver needs mapped resources. @@ -188,6 +213,8 @@ rte_pci_probe_one_driver(struct rte_pci_driver *dr, !(ret > 0 && (dr->drv_flags & RTE_PCI_DRV_KEEP_MAPPED_RES))) rte_pci_unmap_device(dev); + } else { + dev->device.driver = &dr->driver; } return ret; @@ -225,6 +252,7 @@ rte_pci_detach_dev(struct rte_pci_device *dev) /* clear driver structure */ dev->driver = NULL; + dev->device.driver = NULL; if (dr->drv_flags & RTE_PCI_DRV_NEED_MAPPING) /* unmap resources for devices that use igb_uio */ @@ -235,7 +263,7 @@ rte_pci_detach_dev(struct rte_pci_device *dev) /* * If vendor/device ID match, call the probe() function of all - * registered driver for the given device. Return -1 if initialization + * registered driver for the given device. Return < 0 if initialization * failed, return 1 if no driver is found for this device. */ static int @@ -245,17 +273,13 @@ pci_probe_all_drivers(struct rte_pci_device *dev) int rc = 0; if (dev == NULL) - return -1; - - /* Check if a driver is already loaded */ - if (dev->driver != NULL) - return 0; + return -EINVAL; FOREACH_DRIVER_ON_PCIBUS(dr) { rc = rte_pci_probe_one_driver(dr, dev); if (rc < 0) /* negative value is an error */ - return -1; + return rc; if (rc > 0) /* positive value means driver doesn't support it */ continue; @@ -269,34 +293,26 @@ pci_probe_all_drivers(struct rte_pci_device *dev) * all registered drivers that have a matching entry in its id_table * for discovered devices. */ -int -rte_pci_probe(void) +static int +pci_probe(void) { struct rte_pci_device *dev = NULL; size_t probed = 0, failed = 0; - struct rte_devargs *devargs; - int probe_all = 0; int ret = 0; - if (rte_pci_bus.bus.conf.scan_mode != RTE_BUS_SCAN_WHITELIST) - probe_all = 1; - FOREACH_DEVICE_ON_PCIBUS(dev) { probed++; - devargs = dev->device.devargs; - /* probe all or only whitelisted devices */ - if (probe_all) - ret = pci_probe_all_drivers(dev); - else if (devargs != NULL && - devargs->policy == RTE_DEV_WHITELISTED) - ret = pci_probe_all_drivers(dev); + ret = pci_probe_all_drivers(dev); if (ret < 0) { - RTE_LOG(ERR, EAL, "Requested device " PCI_PRI_FMT - " cannot be used\n", dev->addr.domain, dev->addr.bus, - dev->addr.devid, dev->addr.function); - rte_errno = errno; - failed++; + if (ret != -EEXIST) { + RTE_LOG(ERR, EAL, "Requested device " + PCI_PRI_FMT " cannot be used\n", + dev->addr.domain, dev->addr.bus, + dev->addr.devid, dev->addr.function); + rte_errno = errno; + failed++; + } ret = 0; } } @@ -407,6 +423,98 @@ pci_find_device(const struct rte_device *start, rte_dev_cmp_t cmp, return NULL; } +/* + * find the device which encounter the failure, by iterate over all device on + * PCI bus to check if the memory failure address is located in the range + * of the BARs of the device. + */ +static struct rte_pci_device * +pci_find_device_by_addr(const void *failure_addr) +{ + struct rte_pci_device *pdev = NULL; + uint64_t check_point, start, end, len; + int i; + + check_point = (uint64_t)(uintptr_t)failure_addr; + + FOREACH_DEVICE_ON_PCIBUS(pdev) { + for (i = 0; i != RTE_DIM(pdev->mem_resource); i++) { + start = (uint64_t)(uintptr_t)pdev->mem_resource[i].addr; + len = pdev->mem_resource[i].len; + end = start + len; + if (check_point >= start && check_point < end) { + RTE_LOG(DEBUG, EAL, "Failure address %16.16" + PRIx64" belongs to device %s!\n", + check_point, pdev->device.name); + return pdev; + } + } + } + return NULL; +} + +static int +pci_hot_unplug_handler(struct rte_device *dev) +{ + struct rte_pci_device *pdev = NULL; + int ret = 0; + + pdev = RTE_DEV_TO_PCI(dev); + if (!pdev) + return -1; + + switch (pdev->kdrv) { +#ifdef HAVE_VFIO_DEV_REQ_INTERFACE + case RTE_KDRV_VFIO: + /* + * vfio kernel module guaranty the pci device would not be + * deleted until the user space release the resource, so no + * need to remap BARs resource here, just directly notify + * the req event to the user space to handle it. + */ + rte_dev_event_callback_process(dev->name, + RTE_DEV_EVENT_REMOVE); + break; +#endif + case RTE_KDRV_IGB_UIO: + case RTE_KDRV_UIO_GENERIC: + case RTE_KDRV_NIC_UIO: + /* BARs resource is invalid, remap it to be safe. */ + ret = pci_uio_remap_resource(pdev); + break; + default: + RTE_LOG(DEBUG, EAL, + "Not managed by a supported kernel driver, skipped\n"); + ret = -1; + break; + } + + return ret; +} + +static int +pci_sigbus_handler(const void *failure_addr) +{ + struct rte_pci_device *pdev = NULL; + int ret = 0; + + pdev = pci_find_device_by_addr(failure_addr); + if (!pdev) { + /* It is a generic sigbus error, no bus would handle it. */ + ret = 1; + } else { + /* The sigbus error is caused of hot-unplug. */ + ret = pci_hot_unplug_handler(&pdev->device); + if (ret) { + RTE_LOG(ERR, EAL, + "Failed to handle hot-unplug for device %s", + pdev->name); + ret = -1; + } + } + return ret; +} + static int pci_plug(struct rte_device *dev) { @@ -423,20 +531,154 @@ pci_unplug(struct rte_device *dev) ret = rte_pci_detach_dev(pdev); if (ret == 0) { rte_pci_remove_device(pdev); + rte_devargs_remove(dev->devargs); free(pdev); } return ret; } +static int +pci_dma_map(struct rte_device *dev, void *addr, uint64_t iova, size_t len) +{ + struct rte_pci_device *pdev = RTE_DEV_TO_PCI(dev); + + if (!pdev || !pdev->driver) { + rte_errno = EINVAL; + return -1; + } + if (pdev->driver->dma_map) + return pdev->driver->dma_map(pdev, addr, iova, len); + /** + * In case driver don't provides any specific mapping + * try fallback to VFIO. + */ + if (pdev->kdrv == RTE_KDRV_VFIO) + return rte_vfio_container_dma_map + (RTE_VFIO_DEFAULT_CONTAINER_FD, (uintptr_t)addr, + iova, len); + rte_errno = ENOTSUP; + return -1; +} + +static int +pci_dma_unmap(struct rte_device *dev, void *addr, uint64_t iova, size_t len) +{ + struct rte_pci_device *pdev = RTE_DEV_TO_PCI(dev); + + if (!pdev || !pdev->driver) { + rte_errno = EINVAL; + return -1; + } + if (pdev->driver->dma_unmap) + return pdev->driver->dma_unmap(pdev, addr, iova, len); + /** + * In case driver don't provides any specific mapping + * try fallback to VFIO. + */ + if (pdev->kdrv == RTE_KDRV_VFIO) + return rte_vfio_container_dma_unmap + (RTE_VFIO_DEFAULT_CONTAINER_FD, (uintptr_t)addr, + iova, len); + rte_errno = ENOTSUP; + return -1; +} + +bool +rte_pci_ignore_device(const struct rte_pci_addr *pci_addr) +{ + struct rte_devargs *devargs = pci_devargs_lookup(pci_addr); + + switch (rte_pci_bus.bus.conf.scan_mode) { + case RTE_BUS_SCAN_WHITELIST: + if (devargs && devargs->policy == RTE_DEV_WHITELISTED) + return false; + break; + case RTE_BUS_SCAN_UNDEFINED: + case RTE_BUS_SCAN_BLACKLIST: + if (devargs == NULL || + devargs->policy != RTE_DEV_BLACKLISTED) + return false; + break; + } + return true; +} + +enum rte_iova_mode +rte_pci_get_iommu_class(void) +{ + enum rte_iova_mode iova_mode = RTE_IOVA_DC; + const struct rte_pci_device *dev; + const struct rte_pci_driver *drv; + bool devices_want_va = false; + bool devices_want_pa = false; + int iommu_no_va = -1; + + FOREACH_DEVICE_ON_PCIBUS(dev) { + /* + * We can check this only once, because the IOMMU hardware is + * the same for all of them. + */ + if (iommu_no_va == -1) + iommu_no_va = pci_device_iommu_support_va(dev) + ? 0 : 1; + + if (dev->kdrv == RTE_KDRV_UNKNOWN || + dev->kdrv == RTE_KDRV_NONE) + continue; + FOREACH_DRIVER_ON_PCIBUS(drv) { + enum rte_iova_mode dev_iova_mode; + + if (!rte_pci_match(drv, dev)) + continue; + + dev_iova_mode = pci_device_iova_mode(drv, dev); + RTE_LOG(DEBUG, EAL, "PCI driver %s for device " + PCI_PRI_FMT " wants IOVA as '%s'\n", + drv->driver.name, + dev->addr.domain, dev->addr.bus, + dev->addr.devid, dev->addr.function, + dev_iova_mode == RTE_IOVA_DC ? "DC" : + (dev_iova_mode == RTE_IOVA_PA ? "PA" : "VA")); + if (dev_iova_mode == RTE_IOVA_PA) + devices_want_pa = true; + else if (dev_iova_mode == RTE_IOVA_VA) + devices_want_va = true; + } + } + if (iommu_no_va == 1) { + iova_mode = RTE_IOVA_PA; + if (devices_want_va) { + RTE_LOG(WARNING, EAL, "Some devices want 'VA' but IOMMU does not support 'VA'.\n"); + RTE_LOG(WARNING, EAL, "The devices that want 'VA' won't initialize.\n"); + } + } else if (devices_want_va && !devices_want_pa) { + iova_mode = RTE_IOVA_VA; + } else if (devices_want_pa && !devices_want_va) { + iova_mode = RTE_IOVA_PA; + } else { + iova_mode = RTE_IOVA_DC; + if (devices_want_va) { + RTE_LOG(WARNING, EAL, "Some devices want 'VA' but forcing 'DC' because other devices want 'PA'.\n"); + RTE_LOG(WARNING, EAL, "Depending on the final decision by the EAL, not all devices may be able to initialize.\n"); + } + } + return iova_mode; +} + struct rte_pci_bus rte_pci_bus = { .bus = { .scan = rte_pci_scan, - .probe = rte_pci_probe, + .probe = pci_probe, .find_device = pci_find_device, .plug = pci_plug, .unplug = pci_unplug, .parse = pci_parse, + .dma_map = pci_dma_map, + .dma_unmap = pci_dma_unmap, .get_iommu_class = rte_pci_get_iommu_class, + .dev_iterate = rte_pci_dev_iterate, + .hot_unplug_handler = pci_hot_unplug_handler, + .sigbus_handler = pci_sigbus_handler, }, .device_list = TAILQ_HEAD_INITIALIZER(rte_pci_bus.device_list), .driver_list = TAILQ_HEAD_INITIALIZER(rte_pci_bus.driver_list),