diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-15 15:04:25 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-15 15:04:25 -0700 |
commit | 9a76aba02a37718242d7cdc294f0a3901928aa57 (patch) | |
tree | 2040d038f85d2120f21af83b0793efd5af1864e3 /net/core/dev.c | |
parent | 0a957467c5fd46142bc9c52758ffc552d4c5e2f7 (diff) | |
parent | 26a1ccc6c117be8e33e0410fce8c5298b0015b99 (diff) | |
download | linux-9a76aba02a37718242d7cdc294f0a3901928aa57.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
- Gustavo A. R. Silva keeps working on the implicit switch fallthru
changes.
- Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
Luca Coelho.
- Re-enable ASPM in r8169, from Kai-Heng Feng.
- Add virtual XFRM interfaces, which avoids all of the limitations of
existing IPSEC tunnels. From Steffen Klassert.
- Convert GRO over to use a hash table, so that when we have many
flows active we don't traverse a long list during accumluation.
- Many new self tests for routing, TC, tunnels, etc. Too many
contributors to mention them all, but I'm really happy to keep
seeing this stuff.
- Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.
- Lots of cleanups and fixes in L2TP code from Guillaume Nault.
- Add IPSEC offload support to netdevsim, from Shannon Nelson.
- Add support for slotting with non-uniform distribution to netem
packet scheduler, from Yousuk Seung.
- Add UDP GSO support to mlx5e, from Boris Pismenny.
- Support offloading of Team LAG in NFP, from John Hurley.
- Allow to configure TX queue selection based upon RX queue, from
Amritha Nambiar.
- Support ethtool ring size configuration in aquantia, from Anton
Mikaev.
- Support DSCP and flowlabel per-transport in SCTP, from Xin Long.
- Support list based batching and stack traversal of SKBs, this is
very exciting work. From Edward Cree.
- Busyloop optimizations in vhost_net, from Toshiaki Makita.
- Introduce the ETF qdisc, which allows time based transmissions. IGB
can offload this in hardware. From Vinicius Costa Gomes.
- Add parameter support to devlink, from Moshe Shemesh.
- Several multiplication and division optimizations for BPF JIT in
nfp driver, from Jiong Wang.
- Lots of prepatory work to make more of the packet scheduler layer
lockless, when possible, from Vlad Buslov.
- Add ACK filter and NAT awareness to sch_cake packet scheduler, from
Toke Høiland-Jørgensen.
- Support regions and region snapshots in devlink, from Alex Vesker.
- Allow to attach XDP programs to both HW and SW at the same time on
a given device, with initial support in nfp. From Jakub Kicinski.
- Add TLS RX offload and support in mlx5, from Ilya Lesokhin.
- Use PHYLIB in r8169 driver, from Heiner Kallweit.
- All sorts of changes to support Spectrum 2 in mlxsw driver, from
Ido Schimmel.
- PTP support in mv88e6xxx DSA driver, from Andrew Lunn.
- Make TCP_USER_TIMEOUT socket option more accurate, from Jon
Maxwell.
- Support for templates in packet scheduler classifier, from Jiri
Pirko.
- IPV6 support in RDS, from Ka-Cheong Poon.
- Native tproxy support in nf_tables, from Máté Eckl.
- Maintain IP fragment queue in an rbtree, but optimize properly for
in-order frags. From Peter Oskolkov.
- Improvde handling of ACKs on hole repairs, from Yuchung Cheng"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
hv/netvsc: Fix NULL dereference at single queue mode fallback
net: filter: mark expected switch fall-through
xen-netfront: fix warn message as irq device name has '/'
cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
net: dsa: mv88e6xxx: missing unlock on error path
rds: fix building with IPV6=m
inet/connection_sock: prefer _THIS_IP_ to current_text_addr
net: dsa: mv88e6xxx: bitwise vs logical bug
net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
ieee802154: hwsim: using right kind of iteration
net: hns3: Add vlan filter setting by ethtool command -K
net: hns3: Set tx ring' tc info when netdev is up
net: hns3: Remove tx ring BD len register in hns3_enet
net: hns3: Fix desc num set to default when setting channel
net: hns3: Fix for phy link issue when using marvell phy driver
net: hns3: Fix for information of phydev lost problem when down/up
net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
net: hns3: Add support for serdes loopback selftest
bnxt_en: take coredump_record structure off stack
...
Diffstat (limited to 'net/core/dev.c')
-rw-r--r-- | net/core/dev.c | 874 |
1 files changed, 678 insertions, 196 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 559a91271f82..325fc5088370 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -149,7 +149,6 @@ #include "net-sysfs.h" -/* Instead of increasing this, you should create a hash table. */ #define MAX_GRO_SKBS 8 /* This should be increased if a protocol with a bigger head is added. */ @@ -2068,11 +2067,13 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; int i; + /* walk through the TCs and see if it falls into any of them */ for (i = 0; i < TC_MAX_QUEUE; i++, tc++) { if ((txq - tc->offset) < tc->count) return i; } + /* didn't find it, just return -1 to indicate no match */ return -1; } @@ -2081,6 +2082,10 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS +struct static_key xps_needed __read_mostly; +EXPORT_SYMBOL(xps_needed); +struct static_key xps_rxqs_needed __read_mostly; +EXPORT_SYMBOL(xps_rxqs_needed); static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) @@ -2092,7 +2097,7 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps, int pos; if (dev_maps) - map = xmap_dereference(dev_maps->cpu_map[tci]); + map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) return false; @@ -2105,7 +2110,7 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps, break; } - RCU_INIT_POINTER(dev_maps->cpu_map[tci], NULL); + RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); return false; } @@ -2135,34 +2140,71 @@ static bool remove_xps_queue_cpu(struct net_device *dev, return active; } +static void clean_xps_maps(struct net_device *dev, const unsigned long *mask, + struct xps_dev_maps *dev_maps, unsigned int nr_ids, + u16 offset, u16 count, bool is_rxqs_map) +{ + bool active = false; + int i, j; + + for (j = -1; j = netif_attrmask_next(j, mask, nr_ids), + j < nr_ids;) + active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, + count); + if (!active) { + if (is_rxqs_map) { + RCU_INIT_POINTER(dev->xps_rxqs_map, NULL); + } else { + RCU_INIT_POINTER(dev->xps_cpus_map, NULL); + + for (i = offset + (count - 1); count--; i--) + netdev_queue_numa_node_write( + netdev_get_tx_queue(dev, i), + NUMA_NO_NODE); + } + kfree_rcu(dev_maps, rcu); + } +} + static void netif_reset_xps_queues(struct net_device *dev, u16 offset, u16 count) { + const unsigned long *possible_mask = NULL; struct xps_dev_maps *dev_maps; - int cpu, i; - bool active = false; + unsigned int nr_ids; + + if (!static_key_false(&xps_needed)) + return; + cpus_read_lock(); mutex_lock(&xps_map_mutex); - dev_maps = xmap_dereference(dev->xps_maps); + if (static_key_false(&xps_rxqs_needed)) { + dev_maps = xmap_dereference(dev->xps_rxqs_map); + if (dev_maps) { + nr_ids = dev->num_rx_queues; + clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, + offset, count, true); + } + } + + dev_maps = xmap_dereference(dev->xps_cpus_map); if (!dev_maps) goto out_no_maps; - for_each_possible_cpu(cpu) - active |= remove_xps_queue_cpu(dev, dev_maps, cpu, - offset, count); - - if (!active) { - RCU_INIT_POINTER(dev->xps_maps, NULL); - kfree_rcu(dev_maps, rcu); - } - - for (i = offset + (count - 1); count--; i--) - netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i), - NUMA_NO_NODE); + if (num_possible_cpus() > 1) + possible_mask = cpumask_bits(cpu_possible_mask); + nr_ids = nr_cpu_ids; + clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, offset, count, + false); out_no_maps: + if (static_key_enabled(&xps_rxqs_needed)) + static_key_slow_dec_cpuslocked(&xps_rxqs_needed); + + static_key_slow_dec_cpuslocked(&xps_needed); mutex_unlock(&xps_map_mutex); + cpus_read_unlock(); } static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) @@ -2170,8 +2212,8 @@ static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) netif_reset_xps_queues(dev, index, dev->num_tx_queues - index); } -static struct xps_map *expand_xps_map(struct xps_map *map, - int cpu, u16 index) +static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index, + u16 index, bool is_rxqs_map) { struct xps_map *new_map; int alloc_len = XPS_MIN_MAP_ALLOC; @@ -2183,7 +2225,7 @@ static struct xps_map *expand_xps_map(struct xps_map *map, return map; } - /* Need to add queue to this CPU's existing map */ + /* Need to add tx-queue to this CPU's/rx-queue's existing map */ if (map) { if (pos < map->alloc_len) return map; @@ -2191,9 +2233,14 @@ static struct xps_map *expand_xps_map(struct xps_map *map, alloc_len = map->alloc_len * 2; } - /* Need to allocate new map to store queue on this CPU's map */ - new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, - cpu_to_node(cpu)); + /* Need to allocate new map to store tx-queue on this CPU's/rx-queue's + * map + */ + if (is_rxqs_map) + new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL); + else + new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, + cpu_to_node(attr_index)); if (!new_map) return NULL; @@ -2205,32 +2252,53 @@ static struct xps_map *expand_xps_map(struct xps_map *map, return new_map; } -int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, - u16 index) +/* Must be called under cpus_read_lock */ +int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, + u16 index, bool is_rxqs_map) { + const unsigned long *online_mask = NULL, *possible_mask = NULL; struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; - int i, cpu, tci, numa_node_id = -2; + int i, j, tci, numa_node_id = -2; int maps_sz, num_tc = 1, tc = 0; struct xps_map *map, *new_map; bool active = false; + unsigned int nr_ids; if (dev->num_tc) { + /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; + if (num_tc < 0) + return -EINVAL; + + /* If queue belongs to subordinate dev use its map */ + dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; + tc = netdev_txq_to_tc(dev, index); if (tc < 0) return -EINVAL; } - maps_sz = XPS_DEV_MAPS_SIZE(num_tc); - if (maps_sz < L1_CACHE_BYTES) - maps_sz = L1_CACHE_BYTES; - mutex_lock(&xps_map_mutex); + if (is_rxqs_map) { + maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues); + dev_maps = xmap_dereference(dev->xps_rxqs_map); + nr_ids = dev->num_rx_queues; + } else { + maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc); + if (num_possible_cpus() > 1) { + online_mask = cpumask_bits(cpu_online_mask); + possible_mask = cpumask_bits(cpu_possible_mask); + } + dev_maps = xmap_dereference(dev->xps_cpus_map); + nr_ids = nr_cpu_ids; + } - dev_maps = xmap_dereference(dev->xps_maps); + if (maps_sz < L1_CACHE_BYTES) + maps_sz = L1_CACHE_BYTES; /* allocate memory for queue storage */ - for_each_cpu_and(cpu, cpu_online_mask, mask) { + for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids), + j < nr_ids;) { if (!new_dev_maps) new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); if (!new_dev_maps) { @@ -2238,73 +2306,85 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, return -ENOMEM; } - tci = cpu * num_tc + tc; - map = dev_maps ? xmap_dereference(dev_maps->cpu_map[tci]) : + tci = j * num_tc + tc; + map = dev_maps ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; - map = expand_xps_map(map, cpu, index); + map = expand_xps_map(map, j, index, is_rxqs_map); if (!map) goto error; - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } if (!new_dev_maps) goto out_no_new_maps; - for_each_possible_cpu(cpu) { + static_key_slow_inc_cpuslocked(&xps_needed); + if (is_rxqs_map) + static_key_slow_inc_cpuslocked(&xps_rxqs_needed); + + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { /* copy maps belonging to foreign traffic classes */ - for (i = tc, tci = cpu * num_tc; dev_maps && i--; tci++) { + for (i = tc, tci = j * num_tc; dev_maps && i--; tci++) { /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->cpu_map[tci]); - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + map = xmap_dereference(dev_maps->attr_map[tci]); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } /* We need to explicitly update tci as prevous loop * could break out early if dev_maps is NULL. */ - tci = cpu * num_tc + tc; + tci = j * num_tc + tc; - if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) { - /* add queue to CPU maps */ + if (netif_attr_test_mask(j, mask, nr_ids) && + netif_attr_test_online(j, online_mask, nr_ids)) { + /* add tx-queue to CPU/rx-queue maps */ int pos = 0; - map = xmap_dereference(new_dev_maps->cpu_map[tci]); + map = xmap_dereference(new_dev_maps->attr_map[tci]); while ((pos < map->len) && (map->queues[pos] != index)) pos++; if (pos == map->len) map->queues[map->len++] = index; #ifdef CONFIG_NUMA - if (numa_node_id == -2) - numa_node_id = cpu_to_node(cpu); - else if (numa_node_id != cpu_to_node(cpu)) - numa_node_id = -1; + if (!is_rxqs_map) { + if (numa_node_id == -2) + numa_node_id = cpu_to_node(j); + else if (numa_node_id != cpu_to_node(j)) + numa_node_id = -1; + } #endif } else if (dev_maps) { /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->cpu_map[tci]); - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + map = xmap_dereference(dev_maps->attr_map[tci]); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } /* copy maps belonging to foreign traffic classes */ for (i = num_tc - tc, tci++; dev_maps && --i; tci++) { /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->cpu_map[tci]); - RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + map = xmap_dereference(dev_maps->attr_map[tci]); + RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } } - rcu_assign_pointer(dev->xps_maps, new_dev_maps); + if (is_rxqs_map) + rcu_assign_pointer(dev->xps_rxqs_map, new_dev_maps); + else + rcu_assign_pointer(dev->xps_cpus_map, new_dev_maps); /* Cleanup old maps */ if (!dev_maps) goto out_no_old_maps; - for_each_possible_cpu(cpu) { - for (i = num_tc, tci = cpu * num_tc; i--; tci++) { - new_map = xmap_dereference(new_dev_maps->cpu_map[tci]); - map = xmap_dereference(dev_maps->cpu_map[tci]); + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { + for (i = num_tc, tci = j * num_tc; i--; tci++) { + new_map = xmap_dereference(new_dev_maps->attr_map[tci]); + map = xmap_dereference(dev_maps->attr_map[tci]); if (map && map != new_map) kfree_rcu(map, rcu); } @@ -2317,19 +2397,23 @@ out_no_old_maps: active = true; out_no_new_maps: - /* update Tx queue numa node */ - netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), - (numa_node_id >= 0) ? numa_node_id : - NUMA_NO_NODE); + if (!is_rxqs_map) { + /* update Tx queue numa node */ + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), + (numa_node_id >= 0) ? + numa_node_id : NUMA_NO_NODE); + } if (!dev_maps) goto out_no_maps; - /* removes queue from unused CPUs */ - for_each_possible_cpu(cpu) { - for (i = tc, tci = cpu * num_tc; i--; tci++) + /* removes tx-queue from unused CPUs/rx-queues */ + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { + for (i = tc, tci = j * num_tc; i--; tci++) active |= remove_xps_queue(dev_maps, tci, index); - if (!cpumask_test_cpu(cpu, mask) || !cpu_online(cpu)) + if (!netif_attr_test_mask(j, mask, nr_ids) || + !netif_attr_test_online(j, online_mask, nr_ids)) active |= remove_xps_queue(dev_maps, tci, index); for (i = num_tc - tc, tci++; --i; tci++) active |= remove_xps_queue(dev_maps, tci, index); @@ -2337,7 +2421,10 @@ out_no_new_maps: /* free map if not active */ if (!active) { - RCU_INIT_POINTER(dev->xps_maps, NULL); + if (is_rxqs_map) + RCU_INIT_POINTER(dev->xps_rxqs_map, NULL); + else + RCU_INIT_POINTER(dev->xps_cpus_map, NULL); kfree_rcu(dev_maps, rcu); } @@ -2347,11 +2434,12 @@ out_no_maps: return 0; error: /* remove any maps that we added */ - for_each_possible_cpu(cpu) { - for (i = num_tc, tci = cpu * num_tc; i--; tci++) { - new_map = xmap_dereference(new_dev_maps->cpu_map[tci]); + for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids), + j < nr_ids;) { + for (i = num_tc, tci = j * num_tc; i--; tci++) { + new_map = xmap_dereference(new_dev_maps->attr_map[tci]); map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[tci]) : + xmap_dereference(dev_maps->attr_map[tci]) : NULL; if (new_map && new_map != map) kfree(new_map); @@ -2363,14 +2451,41 @@ error: kfree(new_dev_maps); return -ENOMEM; } +EXPORT_SYMBOL_GPL(__netif_set_xps_queue); + +int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, + u16 index) +{ + int ret; + + cpus_read_lock(); + ret = __netif_set_xps_queue(dev, cpumask_bits(mask), index, false); + cpus_read_unlock(); + + return ret; +} EXPORT_SYMBOL(netif_set_xps_queue); #endif +static void netdev_unbind_all_sb_channels(struct net_device *dev) +{ + struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; + + /* Unbind any subordinate channels */ + while (txq-- != &dev->_tx[0]) { + if (txq->sb_dev) + netdev_unbind_sb_channel(dev, txq->sb_dev); + } +} + void netdev_reset_tc(struct net_device *dev) { #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif + netdev_unbind_all_sb_channels(dev); + + /* Reset TC configuration of device */ dev->num_tc = 0; memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); @@ -2399,11 +2514,77 @@ int netdev_set_num_tc(struct net_device *dev, u8 num_tc) #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif + netdev_unbind_all_sb_channels(dev); + dev->num_tc = num_tc; return 0; } EXPORT_SYMBOL(netdev_set_num_tc); +void netdev_unbind_sb_channel(struct net_device *dev, + struct net_device *sb_dev) +{ + struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; + +#ifdef CONFIG_XPS + netif_reset_xps_queues_gt(sb_dev, 0); +#endif + memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq)); + memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map)); + + while (txq-- != &dev->_tx[0]) { + if (txq->sb_dev == sb_dev) + txq->sb_dev = NULL; + } +} +EXPORT_SYMBOL(netdev_unbind_sb_channel); + +int netdev_bind_sb_channel_queue(struct net_device *dev, + struct net_device *sb_dev, + u8 tc, u16 count, u16 offset) +{ + /* Make certain the sb_dev and dev are already configured */ + if (sb_dev->num_tc >= 0 || tc >= dev->num_tc) + return -EINVAL; + + /* We cannot hand out queues we don't have */ + if ((offset + count) > dev->real_num_tx_queues) + return -EINVAL; + + /* Record the mapping */ + sb_dev->tc_to_txq[tc].count = count; + sb_dev->tc_to_txq[tc].offset = offset; + + /* Provide a way for Tx queue to find the tc_to_txq map or + * XPS map for itself. + */ + while (count--) + netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev; + + return 0; +} +EXPORT_SYMBOL(netdev_bind_sb_channel_queue); + +int netdev_set_sb_channel(struct net_device *dev, u16 channel) +{ + /* Do not use a multiqueue device to represent a subordinate channel */ + if (netif_is_multiqueue(dev)) + return -ENODEV; + + /* We allow channels 1 - 32767 to be used for subordinate channels. + * Channel 0 is meant to be "native" mode and used only to represent + * the main root device. We allow writing 0 to reset the device back + * to normal mode after being used as a subordinate channel. + */ + if (channel > S16_MAX) + return -EINVAL; + + dev->num_tc = -channel; + + return 0; +} +EXPORT_SYMBOL(netdev_set_sb_channel); + /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater than real_num_tx_queues stale skbs on the qdisc must be flushed. @@ -2615,24 +2796,26 @@ EXPORT_SYMBOL(netif_device_attach); * Returns a Tx hash based on the given packet descriptor a Tx queues' number * to be used as a distribution range. */ -static u16 skb_tx_hash(const struct net_device *dev, struct sk_buff *skb) +static u16 skb_tx_hash(const struct net_device *dev, + const struct net_device *sb_dev, + struct sk_buff *skb) { u32 hash; u16 qoffset = 0; u16 qcount = dev->real_num_tx_queues; + if (dev->num_tc) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + + qoffset = sb_dev->tc_to_txq[tc].offset; + qcount = sb_dev->tc_to_txq[tc].count; + } + if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); while (unlikely(hash >= qcount)) hash -= qcount; - return hash; - } - - if (dev->num_tc) { - u8 tc = netdev_get_prio_tc_map(dev, skb->priority); - - qoffset = dev->tc_to_txq[tc].offset; - qcount = dev->tc_to_txq[tc].count; + return hash + qoffset; } return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; @@ -3376,32 +3559,64 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) } #endif /* CONFIG_NET_EGRESS */ -static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +#ifdef CONFIG_XPS +static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb, + struct xps_dev_maps *dev_maps, unsigned int tci) +{ + struct xps_map *map; + int queue_index = -1; + + if (dev->num_tc) { + tci *= dev->num_tc; + tci += netdev_get_prio_tc_map(dev, skb->priority); + } + + map = rcu_dereference(dev_maps->attr_map[tci]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else + queue_index = map->queues[reciprocal_scale( + skb_get_hash(skb), map->len)]; + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + return queue_index; +} +#endif + +static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev, + struct sk_buff *skb) { #ifdef CONFIG_XPS struct xps_dev_maps *dev_maps; - struct xps_map *map; + struct sock *sk = skb->sk; int queue_index = -1; + if (!static_key_false(&xps_needed)) + return -1; + rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_maps); + if (!static_key_false(&xps_rxqs_needed)) + goto get_cpus_map; + + dev_maps = rcu_dereference(sb_dev->xps_rxqs_map); if (dev_maps) { - unsigned int tci = skb->sender_cpu - 1; + int tci = sk_rx_queue_get(sk); - if (dev->num_tc) { - tci *= dev->num_tc; - tci += netdev_get_prio_tc_map(dev, skb->priority); - } + if (tci >= 0 && tci < dev->num_rx_queues) + queue_index = __get_xps_queue_idx(dev, skb, dev_maps, + tci); + } - map = rcu_dereference(dev_maps->cpu_map[tci]); - if (map) { - if (map->len == 1) - queue_index = map->queues[0]; - else - queue_index = map->queues[reciprocal_scale(skb_get_hash(skb), - map->len)]; - if (unlikely(queue_index >= dev->real_num_tx_queues)) - queue_index = -1; +get_cpus_map: + if (queue_index < 0) { + dev_maps = rcu_dereference(sb_dev->xps_cpus_map); + if (dev_maps) { + unsigned int tci = skb->sender_cpu - 1; + + queue_index = __get_xps_queue_idx(dev, skb, dev_maps, + tci); } } rcu_read_unlock(); @@ -3412,17 +3627,36 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) #endif } -static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback) +{ + return 0; +} +EXPORT_SYMBOL(dev_pick_tx_zero); + +u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback) +{ + return (u16)raw_smp_processor_id() % dev->real_num_tx_queues; +} +EXPORT_SYMBOL(dev_pick_tx_cpu_id); + +static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); + sb_dev = sb_dev ? : dev; + if (queue_index < 0 || skb->ooo_okay || queue_index >= dev->real_num_tx_queues) { - int new_index = get_xps_queue(dev, skb); + int new_index = get_xps_queue(dev, sb_dev, skb); if (new_index < 0) - new_index = skb_tx_hash(dev, skb); + new_index = skb_tx_hash(dev, sb_dev, skb); if (queue_index != new_index && sk && sk_fullsock(sk) && @@ -3437,7 +3671,7 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + struct net_device *sb_dev) { int queue_index = 0; @@ -3452,10 +3686,10 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb, accel_priv, + queue_index = ops->ndo_select_queue(dev, skb, sb_dev, __netdev_pick_tx); else - queue_index = __netdev_pick_tx(dev, skb); + queue_index = __netdev_pick_tx(dev, skb, sb_dev); queue_index = netdev_cap_txqueue(dev, queue_index); } @@ -3467,7 +3701,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, /** * __dev_queue_xmit - transmit a buffer * @skb: buffer to transmit - * @accel_priv: private data used for L2 forwarding offload + * @sb_dev: suboordinate device used for L2 forwarding offload * * Queue a buffer for transmission to a network device. The caller must * have set the device and priority and built the buffer before calling @@ -3490,7 +3724,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, * the BH enable code must have IRQs enabled so that it will not deadlock. * --BLG */ -static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) +static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) { struct net_device *dev = skb->dev; struct netdev_queue *txq; @@ -3529,7 +3763,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) else skb_dst_force(skb); - txq = netdev_pick_tx(dev, skb, accel_priv); + txq = netdev_pick_tx(dev, skb, sb_dev); q = rcu_dereference_bh(txq->qdisc); trace_net_dev_queue(skb); @@ -3603,9 +3837,9 @@ int dev_queue_xmit(struct sk_buff *skb) } EXPORT_SYMBOL(dev_queue_xmit); -int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) +int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev) { - return __dev_queue_xmit(skb, accel_priv); + return __dev_queue_xmit(skb, sb_dev); } EXPORT_SYMBOL(dev_queue_xmit_accel); @@ -4028,7 +4262,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ - if (skb_cloned(skb)) + if (skb_cloned(skb) || skb_is_tc_redirected(skb)) return XDP_PASS; /* XDP packets must be linear and must have sufficient headroom @@ -4378,6 +4612,10 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, __skb_push(skb, skb->mac_len); skb_do_redirect(skb); return NULL; + case TC_ACT_REINSERT: + /* this does not scrub the packet, and updates stats on error */ + skb_tc_reinsert(skb, &cl_res); + return NULL; default: break; } @@ -4494,7 +4732,8 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, return 0; } -static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) +static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc, + struct packet_type **ppt_prev) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; @@ -4624,8 +4863,7 @@ skip_classify: if (pt_prev) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) goto drop; - else - ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + *ppt_prev = pt_prev; } else { drop: if (!deliver_exact) @@ -4643,6 +4881,18 @@ out: return ret; } +static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) +{ + struct net_device *orig_dev = skb->dev; + struct packet_type *pt_prev = NULL; + int ret; + + ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev); + if (pt_prev) + ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + return ret; +} + /** * netif_receive_skb_core - special purpose version of netif_receive_skb * @skb: buffer to process @@ -4663,13 +4913,72 @@ int netif_receive_skb_core(struct sk_buff *skb) int ret; rcu_read_lock(); - ret = __netif_receive_skb_core(skb, false); + ret = __netif_receive_skb_one_core(skb, false); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(netif_receive_skb_core); +static inline void __netif_receive_skb_list_ptype(struct list_head *head, + struct packet_type *pt_prev, + struct net_device *orig_dev) +{ + struct sk_buff *skb, *next; + + if (!pt_prev) + return; + if (list_empty(head)) + return; + if (pt_prev->list_func != NULL) + pt_prev->list_func(head, pt_prev, orig_dev); + else + list_for_each_entry_safe(skb, next, head, list) + pt_prev->func(skb, skb->dev, pt_prev, orig_dev); +} + +static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc) +{ + /* Fast-path assumptions: + * - There is no RX handler. + * - Only one packet_type matches. + * If either of these fails, we will end up doing some per-packet + * processing in-line, then handling the 'last ptype' for the whole + * sublist. This can't cause out-of-order delivery to any single ptype, + * because the 'last ptype' must be constant across the sublist, and all + * other ptypes are handled per-packet. + */ + /* Current (common) ptype of sublist */ + struct packet_type *pt_curr = NULL; + /* Current (common) orig_dev of sublist */ + struct net_device *od_curr = NULL; + struct list_head sublist; + struct sk_buff *skb, *next; + + INIT_LIST_HEAD(&sublist); + list_for_each_entry_safe(skb, next, head, list) { + struct net_device *orig_dev = skb->dev; + struct packet_type *pt_prev = NULL; + + list_del(&skb->list); + __netif_receive_skb_core(skb, pfmemalloc, &pt_prev); + if (!pt_prev) + continue; + if (pt_curr != pt_prev || od_curr != orig_dev) { + /* dispatch old sublist */ + __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); + /* start new sublist */ + INIT_LIST_HEAD(&sublist); + pt_curr = pt_prev; + od_curr = orig_dev; + } + list_add_tail(&skb->list, &sublist); + } + + /* dispatch final sublist */ + __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); +} + static int __netif_receive_skb(struct sk_buff *skb) { int ret; @@ -4687,14 +4996,44 @@ static int __netif_receive_skb(struct sk_buff *skb) * context down to all allocation sites. */ noreclaim_flag = memalloc_noreclaim_save(); - ret = __netif_receive_skb_core(skb, true); + ret = __netif_receive_skb_one_core(skb, true); memalloc_noreclaim_restore(noreclaim_flag); } else - ret = __netif_receive_skb_core(skb, false); + ret = __netif_receive_skb_one_core(skb, false); return ret; } +static void __netif_receive_skb_list(struct list_head *head) +{ + unsigned long noreclaim_flag = 0; + struct sk_buff *skb, *next; + bool pfmemalloc = false; /* Is current sublist PF_MEMALLOC? */ + + list_for_each_entry_safe(skb, next, head, list) { + if ((sk_memalloc_socks() && skb_pfmemalloc(skb)) != pfmemalloc) { + struct list_head sublist; + + /* Handle the previous sublist */ + list_cut_before(&sublist, head, &skb->list); + if (!list_empty(&sublist)) + __netif_receive_skb_list_core(&sublist, pfmemalloc); + pfmemalloc = !pfmemalloc; + /* See comments in __netif_receive_skb */ + if (pfmemalloc) + noreclaim_flag = memalloc_noreclaim_save(); + else + memalloc_noreclaim_restore(noreclaim_flag); + } + } + /* Handle the remaining sublist */ + if (!list_empty(head)) + __netif_receive_skb_list_core(head, pfmemalloc); + /* Restore pflags */ + if (pfmemalloc) + memalloc_noreclaim_restore(noreclaim_flag); +} + static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) { struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); @@ -4717,7 +5056,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) break; case XDP_QUERY_PROG: - xdp->prog_attached = !!old; xdp->prog_id = old ? old->aux->id : 0; break; @@ -4769,6 +5107,55 @@ static int netif_receive_skb_internal(struct sk_buff *skb) return ret; } +static void netif_receive_skb_list_internal(struct list_head *head) +{ + struct bpf_prog *xdp_prog = NULL; + struct sk_buff *skb, *next; + struct list_head sublist; + + INIT_LIST_HEAD(&sublist); + list_for_each_entry_safe(skb, next, head, list) { + net_timestamp_check(netdev_tstamp_prequeue, skb); + list_del(&skb->list); + if (!skb_defer_rx_timestamp(skb)) + list_add_tail(&skb->list, &sublist); + } + list_splice_init(&sublist, head); + + if (static_branch_unlikely(&generic_xdp_needed_key)) { + preempt_disable(); + rcu_read_lock(); + list_for_each_entry_safe(skb, next, head, list) { + xdp_prog = rcu_dereference(skb->dev->xdp_prog); + list_del(&skb->list); + if (do_xdp_generic(xdp_prog, skb) == XDP_PASS) + list_add_tail(&skb->list, &sublist); + } + rcu_read_unlock(); + preempt_enable(); + /* Put passed packets back on main list */ + list_splice_init(&sublist, head); + } + + rcu_read_lock(); +#ifdef CONFIG_RPS + if (static_key_false(&rps_needed)) { + list_for_each_entry_safe(skb, next, head, list) { + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu = get_rps_cpu(skb->dev, skb, &rflow); + + if (cpu >= 0) { + /* Will be handled, remove from list */ + list_del(&skb->list); + enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + } + } + } +#endif + __netif_receive_skb_list(head); + rcu_read_unlock(); +} + /** * netif_receive_skb - process receive buffer from network * @skb: buffer to process @@ -4792,6 +5179,28 @@ int netif_receive_skb(struct sk_buff *skb) } EXPORT_SYMBOL(netif_receive_skb); +/** + * netif_receive_skb_list - process many receive buffers from network + * @head: list of skbs to process. + * + * Since return value of netif_receive_skb() is normally ignored, and + * wouldn't be meaningful for a list, this function returns void. + * + * This function may only be called from softirq context and interrupts + * should be enabled. + */ +void netif_receive_skb_list(struct list_head *head) +{ + struct sk_buff *skb; + + if (list_empty(head)) + return; + list_for_each_entry(skb, head, list) + trace_netif_receive_skb_list_entry(skb); + netif_receive_skb_list_internal(head); +} +EXPORT_SYMBOL(netif_receive_skb_list); + DEFINE_PER_CPU(struct work_struct, flush_works); /* Network device is going away, flush any packets still pending */ @@ -4875,42 +5284,50 @@ out: return netif_receive_skb_internal(skb); } -/* napi->gro_list contains packets ordered by age. - * youngest packets at the head of it. - * Complete skbs in reverse order to reduce latencies. - */ -void napi_gro_flush(struct napi_struct *napi, bool flush_old) +static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, + bool flush_old) { - struct sk_buff *skb, *prev = NULL; - - /* scan list and build reverse chain */ - for (skb = napi->gro_list; skb != NULL; skb = skb->next) { - skb->prev = prev; - prev = skb; - } - - for (skb = prev; skb; skb = prev) { - skb->next = NULL; + struct list_head *head = &napi->gro_hash[index].list; + struct sk_buff *skb, *p; + list_for_each_entry_safe_reverse(skb, p, head, list) { if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; - - prev = skb->prev; + list_del(&skb->list); + skb->next = NULL; napi_gro_complete(skb); - napi->gro_count--; + napi->gro_hash[index].count--; } - napi->gro_list = NULL; + if (!napi->gro_hash[index].count) + __clear_bit(index, &napi->gro_bitmask); +} + +/* napi->gro_hash[].list contains packets ordered by age. + * youngest packets at the head of it. + * Complete skbs in reverse order to reduce latencies. + */ +void napi_gro_flush(struct napi_struct *napi, bool flush_old) +{ + u32 i; + + for (i = 0; i < GRO_HASH_BUCKETS; i++) { + if (test_bit(i, &napi->gro_bitmask)) + __napi_gro_flush_chain(napi, i, flush_old); + } } EXPORT_SYMBOL(napi_gro_flush); -static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) +static struct list_head *gro_list_prepare(struct napi_struct *napi, + struct sk_buff *skb) { - struct sk_buff *p; unsigned int maclen = skb->dev->hard_header_len; u32 hash = skb_get_hash_raw(skb); + struct list_head *head; + struct sk_buff *p; - for (p = napi->gro_list; p; p = p->next) { + head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)].list; + list_for_each_entry(p, head, list) { unsigned long diffs; NAPI_GRO_CB(p)->flush = 0; @@ -4933,6 +5350,8 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) maclen); NAPI_GRO_CB(p)->same_flow = !diffs; } + + return head; } static void skb_gro_reset_offset(struct sk_buff *skb) @@ -4975,20 +5394,41 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) } } +static void gro_flush_oldest(struct list_head *head) +{ + struct sk_buff *oldest; + + oldest = list_last_entry(head, struct sk_buff, list); + + /* We are called with head length >= MAX_GRO_SKBS, so this is + * impossible. + */ + if (WARN_ON_ONCE(!oldest)) + return; + + /* Do not adjust napi->gro_hash[].count, caller is adding a new + * SKB to the chain. + */ + list_del(&oldest->list); + napi_gro_complete(oldest); +} + static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { - struct sk_buff **pp = NULL; + u32 hash = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); + struct list_head *head = &offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &offload_base; - int same_flow; + struct list_head *gro_head; + struct sk_buff *pp = NULL; enum gro_result ret; + int same_flow; int grow; if (netif_elide_gro(skb->dev)) goto normal; - gro_list_prepare(napi, skb); + gro_head = gro_list_prepare(napi, skb); rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { @@ -5022,7 +5462,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->csum_valid = 0; } - pp = ptype->callbacks.gro_receive(&napi->gro_list, skb); + pp = ptype->callbacks.gro_receive(gro_head, skb); break; } rcu_read_unlock(); @@ -5039,12 +5479,10 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; if (pp) { - struct sk_buff *nskb = *pp; - - *pp = nskb->next; - nskb->next = NULL; - napi_gro_complete(nskb); - napi->gro_count--; + list_del(&pp->list); + pp->next = NULL; + napi_gro_complete(pp); + napi->gro_hash[hash].count--; } if (same_flow) @@ -5053,26 +5491,16 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (NAPI_GRO_CB(skb)->flush) goto normal; - if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { - struct sk_buff *nskb = napi->gro_list; - - /* locate the end of the list to select the 'oldest' flow */ - while (nskb->next) { - pp = &nskb->next; - nskb = *pp; - } - *pp = NULL; - nskb->next = NULL; - napi_gro_complete(nskb); + if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) { + gro_flush_oldest(gro_head); } else { - napi->gro_count++; + napi->gro_hash[hash].count++; } NAPI_GRO_CB(skb)->count = 1; NAPI_GRO_CB(skb)->age = jiffies; NAPI_GRO_CB(skb)->last = skb; skb_shinfo(skb)->gso_size = skb_gro_len(skb); - skb->next = napi->gro_list; - napi->gro_list = skb; + list_add(&skb->list, gro_head); ret = GRO_HELD; pull: @@ -5080,6 +5508,13 @@ pull: if (grow > 0) gro_pull_from_frag0(skb, grow); ok: + if (napi->gro_hash[hash].count) { + if (!test_bit(hash, &napi->gro_bitmask)) + __set_bit(hash, &napi->gro_bitmask); + } else if (test_bit(hash, &napi->gro_bitmask)) { + __clear_bit(hash, &napi->gro_bitmask); + } + return ret; normal: @@ -5478,7 +5913,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; - if (n->gro_list) { + if (n->gro_bitmask) { unsigned long timeout = 0; if (work_done) @@ -5687,21 +6122,31 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ - if (napi->gro_list && !napi_disable_pending(napi) && + if (napi->gro_bitmask && !napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) __napi_schedule_irqoff(napi); return HRTIMER_NORESTART; } +static void init_gro_hash(struct napi_struct *napi) +{ + int i; + + for (i = 0; i < GRO_HASH_BUCKETS; i++) { + INIT_LIST_HEAD(&napi->gro_hash[i].list); + napi->gro_hash[i].count = 0; + } + napi->gro_bitmask = 0; +} + void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { INIT_LIST_HEAD(&napi->poll_list); hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; - napi->gro_count = 0; - napi->gro_list = NULL; + init_gro_hash(napi); napi->skb = NULL; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) @@ -5734,6 +6179,19 @@ void napi_disable(struct napi_struct *n) } EXPORT_SYMBOL(napi_disable); +static void flush_gro_hash(struct napi_struct *napi) +{ + int i; + + for (i = 0; i < GRO_HASH_BUCKETS; i++) { + struct sk_buff *skb, *n; + + list_for_each_entry_safe(skb, n, &napi->gro_hash[i].list, list) + kfree_skb(skb); + napi->gro_hash[i].count = 0; + } +} + /* Must be called in process context */ void netif_napi_del(struct napi_struct *napi) { @@ -5743,9 +6201,8 @@ void netif_napi_del(struct napi_struct *napi) list_del_init(&napi->dev_list); napi_free_frags(napi); - kfree_skb_list(napi->gro_list); - napi->gro_list = NULL; - napi->gro_count = 0; + flush_gro_hash(napi); + napi->gro_bitmask = 0; } EXPORT_SYMBOL(netif_napi_del); @@ -5787,7 +6244,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } - if (n->gro_list) { + if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. */ @@ -7080,13 +7537,15 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) EXPORT_SYMBOL(__dev_set_mtu); /** - * dev_set_mtu - Change maximum transfer unit + * dev_set_mtu_ext - Change maximum transfer unit * @dev: device * @new_mtu: new transfer unit + * @extack: netlink extended ack * * Change the maximum transfer size of the network device. */ -int dev_set_mtu(struct net_device *dev, int new_mtu) +int dev_set_mtu_ext(struct net_device *dev, int new_mtu, + struct netlink_ext_ack *extack) { int err, orig_mtu; @@ -7095,14 +7554,12 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) /* MTU must be positive, and in range */ if (new_mtu < 0 || new_mtu < dev->min_mtu) { - net_err_ratelimited("%s: Invalid MTU %d requested, hw min %d\n", - dev->name, new_mtu, dev->min_mtu); + NL_SET_ERR_MSG(extack, "mtu less than device minimum"); return -EINVAL; } if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { - net_err_ratelimited("%s: Invalid MTU %d requested, hw max %d\n", - dev->name, new_mtu, dev->max_mtu); + NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); return -EINVAL; } @@ -7130,6 +7587,18 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) } return err; } + +int dev_set_mtu(struct net_device *dev, int new_mtu) +{ + struct netlink_ext_ack extack; + int err; + + memset(&extack, 0, sizeof(extack)); + err = dev_set_mtu_ext(dev, new_mtu, &extack); + if (err && extack._msg) + net_err_ratelimited("%s: %s\n", dev->name, extack._msg); + return err; +} EXPORT_SYMBOL(dev_set_mtu); /** @@ -7279,23 +7748,21 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down) } EXPORT_SYMBOL(dev_change_proto_down); -void __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op, - struct netdev_bpf *xdp) +u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op, + enum bpf_netdev_command cmd) { - memset(xdp, 0, sizeof(*xdp)); - xdp->command = XDP_QUERY_PROG; + struct netdev_bpf xdp; - /* Query must always succeed. */ - WARN_ON(bpf_op(dev, xdp) < 0); -} + if (!bpf_op) + return 0; -static u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op) -{ - struct netdev_bpf xdp; + memset(&xdp, 0, sizeof(xdp)); + xdp.command = cmd; - __dev_xdp_query(dev, bpf_op, &xdp); + /* Query must always succeed. */ + WARN_ON(bpf_op(dev, &xdp) < 0 && cmd == XDP_QUERY_PROG); - return xdp.prog_attached; + return xdp.prog_id; } static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op, @@ -7329,12 +7796,19 @@ static void dev_xdp_uninstall(struct net_device *dev) if (!ndo_bpf) return; - __dev_xdp_query(dev, ndo_bpf, &xdp); - if (xdp.prog_attached == XDP_ATTACHED_NONE) - return; + memset(&xdp, 0, sizeof(xdp)); + xdp.command = XDP_QUERY_PROG; + WARN_ON(ndo_bpf(dev, &xdp)); + if (xdp.prog_id) + WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, + NULL)); - /* Program removal should always succeed */ - WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, NULL)); + /* Remove HW offload */ + memset(&xdp, 0, sizeof(xdp)); + xdp.command = XDP_QUERY_PROG_HW; + if (!ndo_bpf(dev, &xdp) && xdp.prog_id) + WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, + NULL)); } /** @@ -7350,12 +7824,15 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags) { const struct net_device_ops *ops = dev->netdev_ops; + enum bpf_netdev_command query; struct bpf_prog *prog = NULL; bpf_op_t bpf_op, bpf_chk; int err; ASSERT_RTNL(); + query = flags & XDP_FLAGS_HW_MODE ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG; + bpf_op = bpf_chk = ops->ndo_bpf; if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) return -EOPNOTSUPP; @@ -7365,10 +7842,11 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, bpf_chk = generic_xdp_install; if (fd >= 0) { - if (bpf_chk && __dev_xdp_attached(dev, bpf_chk)) + if (__dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG) || + __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG_HW)) return -EEXIST; if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && - __dev_xdp_attached(dev, bpf_op)) + __dev_xdp_query(dev, bpf_op, query)) return -EBUSY; prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, @@ -8837,6 +9315,9 @@ static struct hlist_head * __net_init netdev_create_hash(void) /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { + BUILD_BUG_ON(GRO_HASH_BUCKETS > + 8 * FIELD_SIZEOF(struct napi_struct, gro_bitmask)); + if (net != &init_net) INIT_LIST_HEAD(&net->dev_base_head); @@ -9107,6 +9588,7 @@ static int __init net_dev_init(void) sd->cpu = i; #endif + init_gro_hash(&sd->backlog); sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; } |