diff options
author | Christian Ehrhardt <christian.ehrhardt@canonical.com> | 2017-03-02 16:15:51 +0100 |
---|---|---|
committer | Christian Ehrhardt <christian.ehrhardt@canonical.com> | 2017-03-03 14:41:36 +0100 |
commit | ce3d555e43e3795b5d9507fcfc76b7a0a92fd0d6 (patch) | |
tree | 3a9e9f8f6a62c7146fb391eae34481b2af4f7ff2 /lib | |
parent | 6b3e017e5d25f15da73f7700f7f2ac553ef1a2e9 (diff) |
Imported Upstream version 16.11.1
Change-Id: I1e965265578efaaf08e5628607f53d2386d2df9f
Signed-off-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>
Diffstat (limited to 'lib')
-rw-r--r-- | lib/librte_cryptodev/rte_cryptodev.c | 5 | ||||
-rw-r--r-- | lib/librte_cryptodev/rte_cryptodev_pmd.h | 5 | ||||
-rw-r--r-- | lib/librte_eal/common/eal_common_devargs.c | 1 | ||||
-rw-r--r-- | lib/librte_eal/common/eal_common_vdev.c | 8 | ||||
-rw-r--r-- | lib/librte_eal/common/include/rte_version.h | 2 | ||||
-rw-r--r-- | lib/librte_eal/linuxapp/eal/eal_pci_uio.c | 2 | ||||
-rw-r--r-- | lib/librte_eal/linuxapp/eal/eal_vfio_mp_sync.c | 1 | ||||
-rw-r--r-- | lib/librte_ether/rte_ethdev.c | 105 | ||||
-rw-r--r-- | lib/librte_ether/rte_ether_version.map | 1 | ||||
-rw-r--r-- | lib/librte_mempool/rte_mempool.h | 4 | ||||
-rw-r--r-- | lib/librte_mempool/rte_mempool_stack.c | 2 | ||||
-rw-r--r-- | lib/librte_sched/rte_sched.c | 4 | ||||
-rw-r--r-- | lib/librte_vhost/fd_man.c | 200 | ||||
-rw-r--r-- | lib/librte_vhost/fd_man.h | 2 | ||||
-rw-r--r-- | lib/librte_vhost/vhost.c | 1 | ||||
-rw-r--r-- | lib/librte_vhost/vhost_user.c | 13 | ||||
-rw-r--r-- | lib/librte_vhost/virtio_net.c | 7 |
17 files changed, 220 insertions, 143 deletions
diff --git a/lib/librte_cryptodev/rte_cryptodev.c b/lib/librte_cryptodev/rte_cryptodev.c index 127e8d0d..54e95d5c 100644 --- a/lib/librte_cryptodev/rte_cryptodev.c +++ b/lib/librte_cryptodev/rte_cryptodev.c @@ -225,13 +225,14 @@ rte_cryptodev_create_vdev(const char *name, const char *args) } int -rte_cryptodev_get_dev_id(const char *name) { +rte_cryptodev_get_dev_id(const char *name) +{ unsigned i; if (name == NULL) return -1; - for (i = 0; i < rte_cryptodev_globals->max_devs; i++) + for (i = 0; i < rte_cryptodev_globals->nb_devs; i++) if ((strcmp(rte_cryptodev_globals->devs[i].data->name, name) == 0) && (rte_cryptodev_globals->devs[i].attached == diff --git a/lib/librte_cryptodev/rte_cryptodev_pmd.h b/lib/librte_cryptodev/rte_cryptodev_pmd.h index abfe2dc1..c6a57945 100644 --- a/lib/librte_cryptodev/rte_cryptodev_pmd.h +++ b/lib/librte_cryptodev/rte_cryptodev_pmd.h @@ -183,8 +183,9 @@ rte_cryptodev_pmd_get_named_dev(const char *name) if (name == NULL) return NULL; - for (i = 0, dev = &rte_cryptodev_globals->devs[i]; - i < rte_cryptodev_globals->max_devs; i++) { + for (i = 0; i < rte_cryptodev_globals->max_devs; i++) { + dev = &rte_cryptodev_globals->devs[i]; + if ((dev->attached == RTE_CRYPTODEV_ATTACHED) && (strcmp(dev->data->name, name) == 0)) return dev; diff --git a/lib/librte_eal/common/eal_common_devargs.c b/lib/librte_eal/common/eal_common_devargs.c index e403717b..ffa8ad96 100644 --- a/lib/librte_eal/common/eal_common_devargs.c +++ b/lib/librte_eal/common/eal_common_devargs.c @@ -72,6 +72,7 @@ rte_eal_parse_devargs_str(const char *devargs_str, if (*drvargs == NULL) { free(*drvname); + *drvname = NULL; return -1; } return 0; diff --git a/lib/librte_eal/common/eal_common_vdev.c b/lib/librte_eal/common/eal_common_vdev.c index 0ff2377d..7d6e54f4 100644 --- a/lib/librte_eal/common/eal_common_vdev.c +++ b/lib/librte_eal/common/eal_common_vdev.c @@ -111,6 +111,14 @@ rte_eal_vdev_uninit(const char *name) return driver->remove(name); } + /* Give new names precedence over aliases. */ + TAILQ_FOREACH(driver, &vdev_driver_list, next) { + if (driver->driver.alias && + !strncmp(driver->driver.alias, name, + strlen(driver->driver.alias))) + return driver->remove(name); + } + RTE_LOG(ERR, EAL, "no driver found for %s\n", name); return -EINVAL; } diff --git a/lib/librte_eal/common/include/rte_version.h b/lib/librte_eal/common/include/rte_version.h index da204e63..0de35fb7 100644 --- a/lib/librte_eal/common/include/rte_version.h +++ b/lib/librte_eal/common/include/rte_version.h @@ -66,7 +66,7 @@ extern "C" { /** * Patch level number i.e. the z in yy.mm.z */ -#define RTE_VER_MINOR 0 +#define RTE_VER_MINOR 1 /** * Extra string to be appended to version number diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_uio.c b/lib/librte_eal/linuxapp/eal/eal_pci_uio.c index 1786b754..3e4ffb57 100644 --- a/lib/librte_eal/linuxapp/eal/eal_pci_uio.c +++ b/lib/librte_eal/linuxapp/eal/eal_pci_uio.c @@ -133,7 +133,7 @@ pci_mknod_uio_dev(const char *sysfs_uio_path, unsigned uio_num) snprintf(filename, sizeof(filename), "/dev/uio%u", uio_num); dev = makedev(major, minor); ret = mknod(filename, S_IFCHR | S_IRUSR | S_IWUSR, dev); - if (f == NULL) { + if (ret != 0) { RTE_LOG(ERR, EAL, "%s(): mknod() failed %s\n", __func__, strerror(errno)); return -1; diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio_mp_sync.c b/lib/librte_eal/linuxapp/eal/eal_vfio_mp_sync.c index 00cf919b..fb4a2f84 100644 --- a/lib/librte_eal/linuxapp/eal/eal_vfio_mp_sync.c +++ b/lib/librte_eal/linuxapp/eal/eal_vfio_mp_sync.c @@ -301,6 +301,7 @@ vfio_mp_sync_thread(void __rte_unused * arg) vfio_mp_sync_send_request(conn_sock, SOCKET_ERR); else vfio_mp_sync_send_fd(conn_sock, fd); + close(fd); break; case SOCKET_REQ_GROUP: /* wait for group number */ diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c index fde8112f..5a317594 100644 --- a/lib/librte_ether/rte_ethdev.c +++ b/lib/librte_ether/rte_ethdev.c @@ -189,6 +189,20 @@ rte_eth_dev_find_free_port(void) return RTE_MAX_ETHPORTS; } +static struct rte_eth_dev * +eth_dev_get(uint8_t port_id) +{ + struct rte_eth_dev *eth_dev = &rte_eth_devices[port_id]; + + eth_dev->data = &rte_eth_dev_data[port_id]; + eth_dev->attached = DEV_ATTACHED; + + eth_dev_last_created_port = port_id; + nb_ports++; + + return eth_dev; +} + struct rte_eth_dev * rte_eth_dev_allocate(const char *name) { @@ -210,13 +224,41 @@ rte_eth_dev_allocate(const char *name) return NULL; } - eth_dev = &rte_eth_devices[port_id]; - eth_dev->data = &rte_eth_dev_data[port_id]; + eth_dev = eth_dev_get(port_id); snprintf(eth_dev->data->name, sizeof(eth_dev->data->name), "%s", name); eth_dev->data->port_id = port_id; - eth_dev->attached = DEV_ATTACHED; - eth_dev_last_created_port = port_id; - nb_ports++; + + return eth_dev; +} + +/* + * Attach to a port already registered by the primary process, which + * makes sure that the same device would have the same port id both + * in the primary and secondary process. + */ +static struct rte_eth_dev * +eth_dev_attach_secondary(const char *name) +{ + uint8_t i; + struct rte_eth_dev *eth_dev; + + if (rte_eth_dev_data == NULL) + rte_eth_dev_data_alloc(); + + for (i = 0; i < RTE_MAX_ETHPORTS; i++) { + if (strcmp(rte_eth_dev_data[i].name, name) == 0) + break; + } + if (i == RTE_MAX_ETHPORTS) { + RTE_PMD_DEBUG_TRACE( + "device %s is not driven by the primary process\n", + name); + return NULL; + } + + eth_dev = eth_dev_get(i); + RTE_ASSERT(eth_dev->data->port_id == i); + return eth_dev; } @@ -246,16 +288,28 @@ rte_eth_dev_pci_probe(struct rte_pci_driver *pci_drv, rte_eal_pci_device_name(&pci_dev->addr, ethdev_name, sizeof(ethdev_name)); - eth_dev = rte_eth_dev_allocate(ethdev_name); - if (eth_dev == NULL) - return -ENOMEM; - if (rte_eal_process_type() == RTE_PROC_PRIMARY) { + eth_dev = rte_eth_dev_allocate(ethdev_name); + if (eth_dev == NULL) + return -ENOMEM; + eth_dev->data->dev_private = rte_zmalloc("ethdev private structure", eth_drv->dev_private_size, RTE_CACHE_LINE_SIZE); if (eth_dev->data->dev_private == NULL) rte_panic("Cannot allocate memzone for private port data\n"); + } else { + eth_dev = eth_dev_attach_secondary(ethdev_name); + if (eth_dev == NULL) { + /* + * if we failed to attach a device, it means the + * device is skipped in primary process, due to + * some errors. If so, we return a positive value, + * to let EAL skip it for the secondary process + * as well. + */ + return 1; + } } eth_dev->pci_dev = pci_dev; eth_dev->driver = eth_drv; @@ -376,6 +430,9 @@ rte_eth_dev_get_port_by_name(const char *name, uint8_t *port_id) return -EINVAL; } + if (!nb_ports) + return -ENODEV; + *port_id = RTE_MAX_ETHPORTS; for (i = 0; i < RTE_MAX_ETHPORTS; i++) { @@ -1343,8 +1400,10 @@ get_xstats_count(uint8_t port_id) } else count = 0; count += RTE_NB_STATS; - count += dev->data->nb_rx_queues * RTE_NB_RXQ_STATS; - count += dev->data->nb_tx_queues * RTE_NB_TXQ_STATS; + count += RTE_MIN(dev->data->nb_rx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS) * + RTE_NB_RXQ_STATS; + count += RTE_MIN(dev->data->nb_tx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS) * + RTE_NB_TXQ_STATS; return count; } @@ -1358,6 +1417,7 @@ rte_eth_xstats_get_names(uint8_t port_id, int cnt_expected_entries; int cnt_driver_entries; uint32_t idx, id_queue; + uint16_t num_q; cnt_expected_entries = get_xstats_count(port_id); if (xstats_names == NULL || cnt_expected_entries < 0 || @@ -1374,7 +1434,8 @@ rte_eth_xstats_get_names(uint8_t port_id, "%s", rte_stats_strings[idx].name); cnt_used_entries++; } - for (id_queue = 0; id_queue < dev->data->nb_rx_queues; id_queue++) { + num_q = RTE_MIN(dev->data->nb_rx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS); + for (id_queue = 0; id_queue < num_q; id_queue++) { for (idx = 0; idx < RTE_NB_RXQ_STATS; idx++) { snprintf(xstats_names[cnt_used_entries].name, sizeof(xstats_names[0].name), @@ -1384,7 +1445,8 @@ rte_eth_xstats_get_names(uint8_t port_id, } } - for (id_queue = 0; id_queue < dev->data->nb_tx_queues; id_queue++) { + num_q = RTE_MIN(dev->data->nb_tx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS); + for (id_queue = 0; id_queue < num_q; id_queue++) { for (idx = 0; idx < RTE_NB_TXQ_STATS; idx++) { snprintf(xstats_names[cnt_used_entries].name, sizeof(xstats_names[0].name), @@ -1420,14 +1482,18 @@ rte_eth_xstats_get(uint8_t port_id, struct rte_eth_xstat *xstats, unsigned count = 0, i, q; signed xcount = 0; uint64_t val, *stats_ptr; + uint16_t nb_rxqs, nb_txqs; RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL); dev = &rte_eth_devices[port_id]; + nb_rxqs = RTE_MIN(dev->data->nb_rx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS); + nb_txqs = RTE_MIN(dev->data->nb_tx_queues, RTE_ETHDEV_QUEUE_STAT_CNTRS); + /* Return generic statistics */ - count = RTE_NB_STATS + (dev->data->nb_rx_queues * RTE_NB_RXQ_STATS) + - (dev->data->nb_tx_queues * RTE_NB_TXQ_STATS); + count = RTE_NB_STATS + (nb_rxqs * RTE_NB_RXQ_STATS) + + (nb_txqs * RTE_NB_TXQ_STATS); /* implemented by the driver */ if (dev->dev_ops->xstats_get != NULL) { @@ -1458,7 +1524,7 @@ rte_eth_xstats_get(uint8_t port_id, struct rte_eth_xstat *xstats, } /* per-rxq stats */ - for (q = 0; q < dev->data->nb_rx_queues; q++) { + for (q = 0; q < nb_rxqs; q++) { for (i = 0; i < RTE_NB_RXQ_STATS; i++) { stats_ptr = RTE_PTR_ADD(ð_stats, rte_rxq_stats_strings[i].offset + @@ -1469,7 +1535,7 @@ rte_eth_xstats_get(uint8_t port_id, struct rte_eth_xstat *xstats, } /* per-txq stats */ - for (q = 0; q < dev->data->nb_tx_queues; q++) { + for (q = 0; q < nb_txqs; q++) { for (i = 0; i < RTE_NB_TXQ_STATS; i++) { stats_ptr = RTE_PTR_ADD(ð_stats, rte_txq_stats_strings[i].offset + @@ -1479,8 +1545,11 @@ rte_eth_xstats_get(uint8_t port_id, struct rte_eth_xstat *xstats, } } - for (i = 0; i < count + xcount; i++) + for (i = 0; i < count; i++) xstats[i].id = i; + /* add an offset to driver-specific stats */ + for ( ; i < count + xcount; i++) + xstats[i].id += count; return count + xcount; } diff --git a/lib/librte_ether/rte_ether_version.map b/lib/librte_ether/rte_ether_version.map index 72be66d8..fd622635 100644 --- a/lib/librte_ether/rte_ether_version.map +++ b/lib/librte_ether/rte_ether_version.map @@ -19,7 +19,6 @@ DPDK_2.2 { rte_eth_dev_bypass_ver_show; rte_eth_dev_bypass_wd_reset; rte_eth_dev_bypass_wd_timeout_show; - rte_eth_dev_callback_process; rte_eth_dev_callback_register; rte_eth_dev_callback_unregister; rte_eth_dev_close; diff --git a/lib/librte_mempool/rte_mempool.h b/lib/librte_mempool/rte_mempool.h index 440f3b1b..956ce04b 100644 --- a/lib/librte_mempool/rte_mempool.h +++ b/lib/librte_mempool/rte_mempool.h @@ -610,9 +610,7 @@ typedef void (rte_mempool_ctor_t)(struct rte_mempool *, void *); * never be used. The access to the per-lcore table is of course * faster than the multi-producer/consumer pool. The cache can be * disabled if the cache_size argument is set to 0; it can be useful to - * avoid losing objects in cache. Note that even if not used, the - * memory space for cache is always reserved in a mempool structure, - * except if CONFIG_RTE_MEMPOOL_CACHE_MAX_SIZE is set to 0. + * avoid losing objects in cache. * @param private_data_size * The size of the private data appended after the mempool * structure. This is useful for storing some private data after the diff --git a/lib/librte_mempool/rte_mempool_stack.c b/lib/librte_mempool/rte_mempool_stack.c index 5fd8af24..817f77e6 100644 --- a/lib/librte_mempool/rte_mempool_stack.c +++ b/lib/librte_mempool/rte_mempool_stack.c @@ -118,7 +118,7 @@ stack_dequeue(struct rte_mempool *mp, void **obj_table, s->len -= n; rte_spinlock_unlock(&s->sl); - return n; + return 0; } static unsigned diff --git a/lib/librte_sched/rte_sched.c b/lib/librte_sched/rte_sched.c index e6dace2f..614705d8 100644 --- a/lib/librte_sched/rte_sched.c +++ b/lib/librte_sched/rte_sched.c @@ -735,12 +735,14 @@ void rte_sched_port_free(struct rte_sched_port *port) { uint32_t qindex; - uint32_t n_queues_per_port = rte_sched_port_queues_per_port(port); + uint32_t n_queues_per_port; /* Check user parameters */ if (port == NULL) return; + n_queues_per_port = rte_sched_port_queues_per_port(port); + /* Free enqueued mbufs */ for (qindex = 0; qindex < n_queues_per_port; qindex++) { struct rte_mbuf **mbufs = rte_sched_port_qbase(port, qindex); diff --git a/lib/librte_vhost/fd_man.c b/lib/librte_vhost/fd_man.c index 2d3eeb7d..8a075da2 100644 --- a/lib/librte_vhost/fd_man.c +++ b/lib/librte_vhost/fd_man.c @@ -35,93 +35,91 @@ #include <stdio.h> #include <stdlib.h> #include <sys/socket.h> -#include <sys/select.h> #include <sys/time.h> #include <sys/types.h> #include <unistd.h> +#include <string.h> #include <rte_common.h> #include <rte_log.h> #include "fd_man.h" -/** - * Returns the index in the fdset for a given fd. - * If fd is -1, it means to search for a free entry. - * @return - * index for the fd, or -1 if fd isn't in the fdset. - */ +#define FDPOLLERR (POLLERR | POLLHUP | POLLNVAL) + static int -fdset_find_fd(struct fdset *pfdset, int fd) +get_last_valid_idx(struct fdset *pfdset, int last_valid_idx) { int i; - if (pfdset == NULL) - return -1; - - for (i = 0; i < MAX_FDS && pfdset->fd[i].fd != fd; i++) + for (i = last_valid_idx; i >= 0 && pfdset->fd[i].fd == -1; i--) ; - return i == MAX_FDS ? -1 : i; + return i; } -static int -fdset_find_free_slot(struct fdset *pfdset) +static void +fdset_move(struct fdset *pfdset, int dst, int src) { - return fdset_find_fd(pfdset, -1); + pfdset->fd[dst] = pfdset->fd[src]; + pfdset->rwfds[dst] = pfdset->rwfds[src]; } -static int -fdset_add_fd(struct fdset *pfdset, int idx, int fd, - fd_cb rcb, fd_cb wcb, void *dat) +/* + * Find deleted fd entries and remove them + */ +static void +fdset_shrink(struct fdset *pfdset) { - struct fdentry *pfdentry; + int i; + int last_valid_idx = get_last_valid_idx(pfdset, pfdset->num - 1); - if (pfdset == NULL || idx >= MAX_FDS || fd >= FD_SETSIZE) - return -1; + pthread_mutex_lock(&pfdset->fd_mutex); - pfdentry = &pfdset->fd[idx]; - pfdentry->fd = fd; - pfdentry->rcb = rcb; - pfdentry->wcb = wcb; - pfdentry->dat = dat; + for (i = 0; i < last_valid_idx; i++) { + if (pfdset->fd[i].fd != -1) + continue; - return 0; + fdset_move(pfdset, i, last_valid_idx); + last_valid_idx = get_last_valid_idx(pfdset, last_valid_idx - 1); + } + pfdset->num = last_valid_idx + 1; + + pthread_mutex_unlock(&pfdset->fd_mutex); } /** - * Fill the read/write fd_set with the fds in the fdset. + * Returns the index in the fdset for a given fd. * @return - * the maximum fds filled in the read/write fd_set. + * index for the fd, or -1 if fd isn't in the fdset. */ static int -fdset_fill(fd_set *rfset, fd_set *wfset, struct fdset *pfdset) +fdset_find_fd(struct fdset *pfdset, int fd) { - struct fdentry *pfdentry; - int i, maxfds = -1; - int num = MAX_FDS; + int i; - if (pfdset == NULL) - return -1; + for (i = 0; i < pfdset->num && pfdset->fd[i].fd != fd; i++) + ; - for (i = 0; i < num; i++) { - pfdentry = &pfdset->fd[i]; - if (pfdentry->fd != -1) { - int added = 0; - if (pfdentry->rcb && rfset) { - FD_SET(pfdentry->fd, rfset); - added = 1; - } - if (pfdentry->wcb && wfset) { - FD_SET(pfdentry->fd, wfset); - added = 1; - } - if (added) - maxfds = pfdentry->fd < maxfds ? - maxfds : pfdentry->fd; - } - } - return maxfds; + return i == pfdset->num ? -1 : i; +} + +static void +fdset_add_fd(struct fdset *pfdset, int idx, int fd, + fd_cb rcb, fd_cb wcb, void *dat) +{ + struct fdentry *pfdentry = &pfdset->fd[idx]; + struct pollfd *pfd = &pfdset->rwfds[idx]; + + pfdentry->fd = fd; + pfdentry->rcb = rcb; + pfdentry->wcb = wcb; + pfdentry->dat = dat; + + pfd->fd = fd; + pfd->events = rcb ? POLLIN : 0; + pfd->events |= wcb ? POLLOUT : 0; + pfd->revents = 0; } void @@ -151,16 +149,13 @@ fdset_add(struct fdset *pfdset, int fd, fd_cb rcb, fd_cb wcb, void *dat) return -1; pthread_mutex_lock(&pfdset->fd_mutex); - - /* Find a free slot in the list. */ - i = fdset_find_free_slot(pfdset); - if (i == -1 || fdset_add_fd(pfdset, i, fd, rcb, wcb, dat) < 0) { + i = pfdset->num < MAX_FDS ? pfdset->num++ : -1; + if (i == -1) { pthread_mutex_unlock(&pfdset->fd_mutex); return -2; } - pfdset->num++; - + fdset_add_fd(pfdset, i, fd, rcb, wcb, dat); pthread_mutex_unlock(&pfdset->fd_mutex); return 0; @@ -189,7 +184,6 @@ fdset_del(struct fdset *pfdset, int fd) pfdset->fd[i].fd = -1; pfdset->fd[i].rcb = pfdset->fd[i].wcb = NULL; pfdset->fd[i].dat = NULL; - pfdset->num--; i = -1; } pthread_mutex_unlock(&pfdset->fd_mutex); @@ -198,24 +192,6 @@ fdset_del(struct fdset *pfdset, int fd) return dat; } -/** - * Unregister the fd at the specified slot from the fdset. - */ -static void -fdset_del_slot(struct fdset *pfdset, int index) -{ - if (pfdset == NULL || index < 0 || index >= MAX_FDS) - return; - - pthread_mutex_lock(&pfdset->fd_mutex); - - pfdset->fd[index].fd = -1; - pfdset->fd[index].rcb = pfdset->fd[index].wcb = NULL; - pfdset->fd[index].dat = NULL; - pfdset->num--; - - pthread_mutex_unlock(&pfdset->fd_mutex); -} /** * This functions runs in infinite blocking loop until there is no fd in @@ -229,55 +205,64 @@ fdset_del_slot(struct fdset *pfdset, int index) void fdset_event_dispatch(struct fdset *pfdset) { - fd_set rfds, wfds; - int i, maxfds; + int i; + struct pollfd *pfd; struct fdentry *pfdentry; - int num = MAX_FDS; fd_cb rcb, wcb; void *dat; - int fd; + int fd, numfds; int remove1, remove2; - int ret; + int need_shrink; if (pfdset == NULL) return; while (1) { - struct timeval tv; - tv.tv_sec = 1; - tv.tv_usec = 0; - FD_ZERO(&rfds); - FD_ZERO(&wfds); - pthread_mutex_lock(&pfdset->fd_mutex); - - maxfds = fdset_fill(&rfds, &wfds, pfdset); - - pthread_mutex_unlock(&pfdset->fd_mutex); /* - * When select is blocked, other threads might unregister + * When poll is blocked, other threads might unregister * listenfds from and register new listenfds into fdset. - * When select returns, the entries for listenfds in the fdset + * When poll returns, the entries for listenfds in the fdset * might have been updated. It is ok if there is unwanted call * for new listenfds. */ - ret = select(maxfds + 1, &rfds, &wfds, NULL, &tv); - if (ret <= 0) - continue; + pthread_mutex_lock(&pfdset->fd_mutex); + numfds = pfdset->num; + pthread_mutex_unlock(&pfdset->fd_mutex); - for (i = 0; i < num; i++) { - remove1 = remove2 = 0; + poll(pfdset->rwfds, numfds, 1000 /* millisecs */); + + need_shrink = 0; + for (i = 0; i < numfds; i++) { pthread_mutex_lock(&pfdset->fd_mutex); + pfdentry = &pfdset->fd[i]; fd = pfdentry->fd; + pfd = &pfdset->rwfds[i]; + + if (fd < 0) { + need_shrink = 1; + pthread_mutex_unlock(&pfdset->fd_mutex); + continue; + } + + if (!pfd->revents) { + pthread_mutex_unlock(&pfdset->fd_mutex); + continue; + } + + remove1 = remove2 = 0; + rcb = pfdentry->rcb; wcb = pfdentry->wcb; dat = pfdentry->dat; pfdentry->busy = 1; + pthread_mutex_unlock(&pfdset->fd_mutex); - if (fd >= 0 && FD_ISSET(fd, &rfds) && rcb) + + if (rcb && pfd->revents & (POLLIN | FDPOLLERR)) rcb(fd, dat, &remove1); - if (fd >= 0 && FD_ISSET(fd, &wfds) && wcb) + if (wcb && pfd->revents & (POLLOUT | FDPOLLERR)) wcb(fd, dat, &remove2); pfdentry->busy = 0; /* @@ -292,8 +277,13 @@ fdset_event_dispatch(struct fdset *pfdset) * listen fd in another thread, we couldn't call * fd_set_del. */ - if (remove1 || remove2) - fdset_del_slot(pfdset, i); + if (remove1 || remove2) { + pfdentry->fd = -1; + need_shrink = 1; + } } + + if (need_shrink) + fdset_shrink(pfdset); } } diff --git a/lib/librte_vhost/fd_man.h b/lib/librte_vhost/fd_man.h index bd66ed1c..d319cac6 100644 --- a/lib/librte_vhost/fd_man.h +++ b/lib/librte_vhost/fd_man.h @@ -35,6 +35,7 @@ #define _FD_MAN_H_ #include <stdint.h> #include <pthread.h> +#include <poll.h> #define MAX_FDS 1024 @@ -49,6 +50,7 @@ struct fdentry { }; struct fdset { + struct pollfd rwfds[MAX_FDS]; struct fdentry fd[MAX_FDS]; pthread_mutex_t fd_mutex; int num; /* current fd number of this fdset */ diff --git a/lib/librte_vhost/vhost.c b/lib/librte_vhost/vhost.c index 31825b82..e4150934 100644 --- a/lib/librte_vhost/vhost.c +++ b/lib/librte_vhost/vhost.c @@ -250,6 +250,7 @@ vhost_new_device(void) if (i == MAX_VHOST_DEVICE) { RTE_LOG(ERR, VHOST_CONFIG, "Failed to find a free slot for new device.\n"); + rte_free(dev); return -1; } diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c index 6b83c15f..0cb1c677 100644 --- a/lib/librte_vhost/vhost_user.c +++ b/lib/librte_vhost/vhost_user.c @@ -447,14 +447,14 @@ add_guest_pages(struct virtio_net *dev, struct virtio_memory_region *reg, reg_size -= size; while (reg_size > 0) { + size = RTE_MIN(reg_size, page_size); host_phys_addr = rte_mem_virt2phy((void *)(uintptr_t) host_user_addr); - add_one_guest_page(dev, guest_phys_addr, host_phys_addr, - page_size); + add_one_guest_page(dev, guest_phys_addr, host_phys_addr, size); - host_user_addr += page_size; - guest_phys_addr += page_size; - reg_size -= page_size; + host_user_addr += size; + guest_phys_addr += size; + reg_size -= size; } } @@ -567,7 +567,8 @@ vhost_user_set_mem_table(struct virtio_net *dev, struct VhostUserMsg *pmsg) reg->host_user_addr = (uint64_t)(uintptr_t)mmap_addr + mmap_offset; - add_guest_pages(dev, reg, alignment); + if (dev->dequeue_zero_copy) + add_guest_pages(dev, reg, alignment); RTE_LOG(INFO, VHOST_CONFIG, "guest memory region %u, size: 0x%" PRIx64 "\n" diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c index 595f67c4..337470d6 100644 --- a/lib/librte_vhost/virtio_net.c +++ b/lib/librte_vhost/virtio_net.c @@ -195,6 +195,8 @@ copy_mbuf_to_desc(struct virtio_net *dev, struct vring_desc *descs, struct vring_desc *desc; uint64_t desc_addr; struct virtio_net_hdr_mrg_rxbuf virtio_hdr = {{0, 0, 0, 0, 0, 0}, 0}; + /* A counter to avoid desc dead loop chain */ + uint16_t nr_desc = 1; desc = &descs[desc_idx]; desc_addr = gpa_to_vva(dev, desc->addr); @@ -233,7 +235,7 @@ copy_mbuf_to_desc(struct virtio_net *dev, struct vring_desc *descs, /* Room in vring buffer is not enough */ return -1; } - if (unlikely(desc->next >= size)) + if (unlikely(desc->next >= size || ++nr_desc > size)) return -1; desc = &descs[desc->next]; @@ -677,6 +679,7 @@ parse_ethernet(struct rte_mbuf *m, uint16_t *l4_proto, void **l4_hdr) default: m->l3_len = 0; *l4_proto = 0; + *l4_hdr = NULL; break; } } @@ -713,7 +716,7 @@ vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m) } } - if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { + if (l4_hdr && hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_TCPV6: |