diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-06 14:45:08 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-06 14:45:08 -0700 |
commit | aae3dbb4776e7916b6cd442d00159bea27a695c1 (patch) | |
tree | d074c5d783a81e7e2e084b1eba77f57459da7e37 /kernel | |
parent | ec3604c7a5aae8953545b0d05495357009a960e5 (diff) | |
parent | 66bed8465a808400eb14562510e26c8818082cb8 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Support ipv6 checksum offload in sunvnet driver, from Shannon
Nelson.
2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
Dumazet.
3) Allow generic XDP to work on virtual devices, from John Fastabend.
4) Add bpf device maps and XDP_REDIRECT, which can be used to build
arbitrary switching frameworks using XDP. From John Fastabend.
5) Remove UFO offloads from the tree, gave us little other than bugs.
6) Remove the IPSEC flow cache, from Florian Westphal.
7) Support ipv6 route offload in mlxsw driver.
8) Support VF representors in bnxt_en, from Sathya Perla.
9) Add support for forward error correction modes to ethtool, from
Vidya Sagar Ravipati.
10) Add time filter for packet scheduler action dumping, from Jamal Hadi
Salim.
11) Extend the zerocopy sendmsg() used by virtio and tap to regular
sockets via MSG_ZEROCOPY. From Willem de Bruijn.
12) Significantly rework value tracking in the BPF verifier, from Edward
Cree.
13) Add new jump instructions to eBPF, from Daniel Borkmann.
14) Rework rtnetlink plumbing so that operations can be run without
taking the RTNL semaphore. From Florian Westphal.
15) Support XDP in tap driver, from Jason Wang.
16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.
17) Add Huawei hinic ethernet driver.
18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
Delalande.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
i40e: avoid NVM acquire deadlock during NVM update
drivers: net: xgene: Remove return statement from void function
drivers: net: xgene: Configure tx/rx delay for ACPI
drivers: net: xgene: Read tx/rx delay for ACPI
rocker: fix kcalloc parameter order
rds: Fix non-atomic operation on shared flag variable
net: sched: don't use GFP_KERNEL under spin lock
vhost_net: correctly check tx avail during rx busy polling
net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
rxrpc: Make service connection lookup always check for retry
net: stmmac: Delete dead code for MDIO registration
gianfar: Fix Tx flow control deactivation
cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
cxgb4: Fix pause frame count in t4_get_port_stats
cxgb4: fix memory leak
tun: rename generic_xdp to skb_xdp
tun: reserve extra headroom only when XDP is set
net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
net: dsa: bcm_sf2: Advertise number of egress queues
...
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/Makefile | 8 | ||||
-rw-r--r-- | kernel/bpf/arraymap.c | 33 | ||||
-rw-r--r-- | kernel/bpf/bpf_lru_list.h | 3 | ||||
-rw-r--r-- | kernel/bpf/core.c | 61 | ||||
-rw-r--r-- | kernel/bpf/devmap.c | 409 | ||||
-rw-r--r-- | kernel/bpf/hashtab.c | 60 | ||||
-rw-r--r-- | kernel/bpf/lpm_trie.c | 9 | ||||
-rw-r--r-- | kernel/bpf/sockmap.c | 873 | ||||
-rw-r--r-- | kernel/bpf/stackmap.c | 8 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 129 | ||||
-rw-r--r-- | kernel/bpf/tnum.c | 180 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 2448 | ||||
-rw-r--r-- | kernel/events/core.c | 10 | ||||
-rw-r--r-- | kernel/trace/trace_syscalls.c | 53 |
14 files changed, 3249 insertions, 1035 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index e1e5e658f2db..897daa005b23 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,7 +1,13 @@ obj-y := core.o -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +ifeq ($(CONFIG_NET),y) +obj-$(CONFIG_BPF_SYSCALL) += devmap.o +ifeq ($(CONFIG_STREAM_PARSER),y) +obj-$(CONFIG_BPF_SYSCALL) += sockmap.o +endif +endif ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o endif diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index d771a3872500..98c0f00c3f5e 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -49,13 +49,15 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) static struct bpf_map *array_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; + int numa_node = bpf_map_attr_numa_node(attr); struct bpf_array *array; u64 array_size; u32 elem_size; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size == 0 || attr->map_flags) + attr->value_size == 0 || attr->map_flags & ~BPF_F_NUMA_NODE || + (percpu && numa_node != NUMA_NO_NODE)) return ERR_PTR(-EINVAL); if (attr->value_size > KMALLOC_MAX_SIZE) @@ -77,7 +79,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); /* allocate all map elements and zero-initialize them */ - array = bpf_map_area_alloc(array_size); + array = bpf_map_area_alloc(array_size, numa_node); if (!array) return ERR_PTR(-ENOMEM); @@ -87,6 +89,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array->map.value_size = attr->value_size; array->map.max_entries = attr->max_entries; array->map.map_flags = attr->map_flags; + array->map.numa_node = numa_node; array->elem_size = elem_size; if (!percpu) @@ -603,6 +606,31 @@ static void *array_of_map_lookup_elem(struct bpf_map *map, void *key) return READ_ONCE(*inner_map); } +static u32 array_of_map_gen_lookup(struct bpf_map *map, + struct bpf_insn *insn_buf) +{ + u32 elem_size = round_up(map->value_size, 8); + struct bpf_insn *insn = insn_buf; + const int ret = BPF_REG_0; + const int map_ptr = BPF_REG_1; + const int index = BPF_REG_2; + + *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); + *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5); + if (is_power_of_2(elem_size)) + *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); + else + *insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size); + *insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr); + *insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0); + *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); + *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *insn++ = BPF_MOV64_IMM(ret, 0); + + return insn - insn_buf; +} + const struct bpf_map_ops array_of_maps_map_ops = { .map_alloc = array_of_map_alloc, .map_free = array_of_map_free, @@ -612,4 +640,5 @@ const struct bpf_map_ops array_of_maps_map_ops = { .map_fd_get_ptr = bpf_map_fd_get_ptr, .map_fd_put_ptr = bpf_map_fd_put_ptr, .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, + .map_gen_lookup = array_of_map_gen_lookup, }; diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index 5c35a98d02bf..7d4f89b7cb84 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -69,7 +69,8 @@ static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node) /* ref is an approximation on access frequency. It does not * have to be very accurate. Hence, no protection is used. */ - node->ref = 1; + if (!node->ref) + node->ref = 1; } int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ad5f55922a13..917cc04a0a94 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -595,9 +595,13 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; @@ -833,12 +837,20 @@ static unsigned int ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K, [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X, [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K, + [BPF_JMP | BPF_JLT | BPF_X] = &&JMP_JLT_X, + [BPF_JMP | BPF_JLT | BPF_K] = &&JMP_JLT_K, [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X, [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K, + [BPF_JMP | BPF_JLE | BPF_X] = &&JMP_JLE_X, + [BPF_JMP | BPF_JLE | BPF_K] = &&JMP_JLE_K, [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X, [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K, + [BPF_JMP | BPF_JSLT | BPF_X] = &&JMP_JSLT_X, + [BPF_JMP | BPF_JSLT | BPF_K] = &&JMP_JSLT_K, [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X, [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K, + [BPF_JMP | BPF_JSLE | BPF_X] = &&JMP_JSLE_X, + [BPF_JMP | BPF_JSLE | BPF_K] = &&JMP_JSLE_K, [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X, [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K, /* Program return */ @@ -1073,6 +1085,18 @@ out: CONT_JMP; } CONT; + JMP_JLT_X: + if (DST < SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JLT_K: + if (DST < IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JGE_X: if (DST >= SRC) { insn += insn->off; @@ -1085,6 +1109,18 @@ out: CONT_JMP; } CONT; + JMP_JLE_X: + if (DST <= SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JLE_K: + if (DST <= IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JSGT_X: if (((s64) DST) > ((s64) SRC)) { insn += insn->off; @@ -1097,6 +1133,18 @@ out: CONT_JMP; } CONT; + JMP_JSLT_X: + if (((s64) DST) < ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSLT_K: + if (((s64) DST) < ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JSGE_X: if (((s64) DST) >= ((s64) SRC)) { insn += insn->off; @@ -1109,6 +1157,18 @@ out: CONT_JMP; } CONT; + JMP_JSLE_X: + if (((s64) DST) <= ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSLE_K: + if (((s64) DST) <= ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JSET_X: if (DST & SRC) { insn += insn->off; @@ -1378,6 +1438,7 @@ const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; +const struct bpf_func_proto bpf_sock_map_update_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c new file mode 100644 index 000000000000..ecf9f99ecc57 --- /dev/null +++ b/kernel/bpf/devmap.c @@ -0,0 +1,409 @@ +/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +/* Devmaps primary use is as a backend map for XDP BPF helper call + * bpf_redirect_map(). Because XDP is mostly concerned with performance we + * spent some effort to ensure the datapath with redirect maps does not use + * any locking. This is a quick note on the details. + * + * We have three possible paths to get into the devmap control plane bpf + * syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall + * will invoke an update, delete, or lookup operation. To ensure updates and + * deletes appear atomic from the datapath side xchg() is used to modify the + * netdev_map array. Then because the datapath does a lookup into the netdev_map + * array (read-only) from an RCU critical section we use call_rcu() to wait for + * an rcu grace period before free'ing the old data structures. This ensures the + * datapath always has a valid copy. However, the datapath does a "flush" + * operation that pushes any pending packets in the driver outside the RCU + * critical section. Each bpf_dtab_netdev tracks these pending operations using + * an atomic per-cpu bitmap. The bpf_dtab_netdev object will not be destroyed + * until all bits are cleared indicating outstanding flush operations have + * completed. + * + * BPF syscalls may race with BPF program calls on any of the update, delete + * or lookup operations. As noted above the xchg() operation also keep the + * netdev_map consistent in this case. From the devmap side BPF programs + * calling into these operations are the same as multiple user space threads + * making system calls. + * + * Finally, any of the above may race with a netdev_unregister notifier. The + * unregister notifier must search for net devices in the map structure that + * contain a reference to the net device and remove them. This is a two step + * process (a) dereference the bpf_dtab_netdev object in netdev_map and (b) + * check to see if the ifindex is the same as the net_device being removed. + * When removing the dev a cmpxchg() is used to ensure the correct dev is + * removed, in the case of a concurrent update or delete operation it is + * possible that the initially referenced dev is no longer in the map. As the + * notifier hook walks the map we know that new dev references can not be + * added by the user because core infrastructure ensures dev_get_by_index() + * calls will fail at this point. + */ +#include <linux/bpf.h> +#include <linux/filter.h> + +struct bpf_dtab_netdev { + struct net_device *dev; + struct bpf_dtab *dtab; + unsigned int bit; + struct rcu_head rcu; +}; + +struct bpf_dtab { + struct bpf_map map; + struct bpf_dtab_netdev **netdev_map; + unsigned long __percpu *flush_needed; + struct list_head list; +}; + +static DEFINE_SPINLOCK(dev_map_lock); +static LIST_HEAD(dev_map_list); + +static u64 dev_map_bitmap_size(const union bpf_attr *attr) +{ + return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); +} + +static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +{ + struct bpf_dtab *dtab; + u64 cost; + int err; + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + return ERR_PTR(-EINVAL); + + dtab = kzalloc(sizeof(*dtab), GFP_USER); + if (!dtab) + return ERR_PTR(-ENOMEM); + + /* mandatory map attributes */ + dtab->map.map_type = attr->map_type; + dtab->map.key_size = attr->key_size; + dtab->map.value_size = attr->value_size; + dtab->map.max_entries = attr->max_entries; + dtab->map.map_flags = attr->map_flags; + dtab->map.numa_node = bpf_map_attr_numa_node(attr); + + /* make sure page count doesn't overflow */ + cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); + cost += dev_map_bitmap_size(attr) * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_dtab; + + dtab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* if map size is larger than memlock limit, reject it early */ + err = bpf_map_precharge_memlock(dtab->map.pages); + if (err) + goto free_dtab; + + /* A per cpu bitfield with a bit per possible net device */ + dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr), + __alignof__(unsigned long)); + if (!dtab->flush_needed) + goto free_dtab; + + dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries * + sizeof(struct bpf_dtab_netdev *), + dtab->map.numa_node); + if (!dtab->netdev_map) + goto free_dtab; + + spin_lock(&dev_map_lock); + list_add_tail_rcu(&dtab->list, &dev_map_list); + spin_unlock(&dev_map_lock); + + return &dtab->map; +free_dtab: + free_percpu(dtab->flush_needed); + kfree(dtab); + return ERR_PTR(-ENOMEM); +} + +static void dev_map_free(struct bpf_map *map) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + int i, cpu; + + /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete. The rcu critical section only guarantees + * no further reads against netdev_map. It does __not__ ensure pending + * flush operations (if any) are complete. + */ + + spin_lock(&dev_map_lock); + list_del_rcu(&dtab->list); + spin_unlock(&dev_map_lock); + + synchronize_rcu(); + + /* To ensure all pending flush operations have completed wait for flush + * bitmap to indicate all flush_needed bits to be zero on _all_ cpus. + * Because the above synchronize_rcu() ensures the map is disconnected + * from the program we can assume no new bits will be set. + */ + for_each_online_cpu(cpu) { + unsigned long *bitmap = per_cpu_ptr(dtab->flush_needed, cpu); + + while (!bitmap_empty(bitmap, dtab->map.max_entries)) + cpu_relax(); + } + + for (i = 0; i < dtab->map.max_entries; i++) { + struct bpf_dtab_netdev *dev; + + dev = dtab->netdev_map[i]; + if (!dev) + continue; + + dev_put(dev->dev); + kfree(dev); + } + + free_percpu(dtab->flush_needed); + bpf_map_area_free(dtab->netdev_map); + kfree(dtab); +} + +static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = next_key; + + if (index >= dtab->map.max_entries) { + *next = 0; + return 0; + } + + if (index == dtab->map.max_entries - 1) + return -ENOENT; + *next = index + 1; + return 0; +} + +void __dev_map_insert_ctx(struct bpf_map *map, u32 bit) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed); + + __set_bit(bit, bitmap); +} + +/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled + * from the driver before returning from its napi->poll() routine. The poll() + * routine is called either from busy_poll context or net_rx_action signaled + * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the + * net device can be torn down. On devmap tear down we ensure the ctx bitmap + * is zeroed before completing to ensure all flush operations have completed. + */ +void __dev_map_flush(struct bpf_map *map) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed); + u32 bit; + + for_each_set_bit(bit, bitmap, map->max_entries) { + struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]); + struct net_device *netdev; + + /* This is possible if the dev entry is removed by user space + * between xdp redirect and flush op. + */ + if (unlikely(!dev)) + continue; + + __clear_bit(bit, bitmap); + netdev = dev->dev; + if (likely(netdev->netdev_ops->ndo_xdp_flush)) + netdev->netdev_ops->ndo_xdp_flush(netdev); + } +} + +/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or + * update happens in parallel here a dev_put wont happen until after reading the + * ifindex. + */ +struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dev; + + if (key >= map->max_entries) + return NULL; + + dev = READ_ONCE(dtab->netdev_map[key]); + return dev ? dev->dev : NULL; +} + +static void *dev_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct net_device *dev = __dev_map_lookup_elem(map, *(u32 *)key); + + return dev ? &dev->ifindex : NULL; +} + +static void dev_map_flush_old(struct bpf_dtab_netdev *dev) +{ + if (dev->dev->netdev_ops->ndo_xdp_flush) { + struct net_device *fl = dev->dev; + unsigned long *bitmap; + int cpu; + + for_each_online_cpu(cpu) { + bitmap = per_cpu_ptr(dev->dtab->flush_needed, cpu); + __clear_bit(dev->bit, bitmap); + + fl->netdev_ops->ndo_xdp_flush(dev->dev); + } + } +} + +static void __dev_map_entry_free(struct rcu_head *rcu) +{ + struct bpf_dtab_netdev *dev; + + dev = container_of(rcu, struct bpf_dtab_netdev, rcu); + dev_map_flush_old(dev); + dev_put(dev->dev); + kfree(dev); +} + +static int dev_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *old_dev; + int k = *(u32 *)key; + + if (k >= map->max_entries) + return -EINVAL; + + /* Use call_rcu() here to ensure any rcu critical sections have + * completed, but this does not guarantee a flush has happened + * yet. Because driver side rcu_read_lock/unlock only protects the + * running XDP program. However, for pending flush operations the + * dev and ctx are stored in another per cpu map. And additionally, + * the driver tear down ensures all soft irqs are complete before + * removing the net device in the case of dev_put equals zero. + */ + old_dev = xchg(&dtab->netdev_map[k], NULL); + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + return 0; +} + +static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct net *net = current->nsproxy->net_ns; + struct bpf_dtab_netdev *dev, *old_dev; + u32 i = *(u32 *)key; + u32 ifindex = *(u32 *)value; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + if (unlikely(i >= dtab->map.max_entries)) + return -E2BIG; + if (unlikely(map_flags == BPF_NOEXIST)) + return -EEXIST; + + if (!ifindex) { + dev = NULL; + } else { + dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, + map->numa_node); + if (!dev) + return -ENOMEM; + + dev->dev = dev_get_by_index(net, ifindex); + if (!dev->dev) { + kfree(dev); + return -EINVAL; + } + + dev->bit = i; + dev->dtab = dtab; + } + + /* Use call_rcu() here to ensure rcu critical sections have completed + * Remembering the driver side flush operation will happen before the + * net device is removed. + */ + old_dev = xchg(&dtab->netdev_map[i], dev); + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + + return 0; +} + +const struct bpf_map_ops dev_map_ops = { + .map_alloc = dev_map_alloc, + .map_free = dev_map_free, + .map_get_next_key = dev_map_get_next_key, + .map_lookup_elem = dev_map_lookup_elem, + .map_update_elem = dev_map_update_elem, + .map_delete_elem = dev_map_delete_elem, +}; + +static int dev_map_notification(struct notifier_block *notifier, + ulong event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct bpf_dtab *dtab; + int i; + + switch (event) { + case NETDEV_UNREGISTER: + /* This rcu_read_lock/unlock pair is needed because + * dev_map_list is an RCU list AND to ensure a delete + * operation does not free a netdev_map entry while we + * are comparing it against the netdev being unregistered. + */ + rcu_read_lock(); + list_for_each_entry_rcu(dtab, &dev_map_list, list) { + for (i = 0; i < dtab->map.max_entries; i++) { + struct bpf_dtab_netdev *dev, *odev; + + dev = READ_ONCE(dtab->netdev_map[i]); + if (!dev || + dev->dev->ifindex != netdev->ifindex) + continue; + odev = cmpxchg(&dtab->netdev_map[i], dev, NULL); + if (dev == odev) + call_rcu(&dev->rcu, + __dev_map_entry_free); + } + } + rcu_read_unlock(); + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block dev_map_notifier = { + .notifier_call = dev_map_notification, +}; + +static int __init dev_map_init(void) +{ + register_netdevice_notifier(&dev_map_notifier); + return 0; +} + +subsys_initcall(dev_map_init); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index d11c8181f4c5..431126f31ea3 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -18,6 +18,9 @@ #include "bpf_lru_list.h" #include "map_in_map.h" +#define HTAB_CREATE_FLAG_MASK \ + (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE) + struct bucket { struct hlist_nulls_head head; raw_spinlock_t lock; @@ -138,7 +141,8 @@ static int prealloc_init(struct bpf_htab *htab) if (!htab_is_percpu(htab) && !htab_is_lru(htab)) num_entries += num_possible_cpus(); - htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries); + htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries, + htab->map.numa_node); if (!htab->elems) return -ENOMEM; @@ -233,6 +237,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); + int numa_node = bpf_map_attr_numa_node(attr); struct bpf_htab *htab; int err, i; u64 cost; @@ -248,7 +253,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ return ERR_PTR(-EPERM); - if (attr->map_flags & ~(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU)) + if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK) /* reserved bits should not be used */ return ERR_PTR(-EINVAL); @@ -258,6 +263,9 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (lru && !prealloc) return ERR_PTR(-ENOTSUPP); + if (numa_node != NUMA_NO_NODE && (percpu || percpu_lru)) + return ERR_PTR(-EINVAL); + htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) return ERR_PTR(-ENOMEM); @@ -268,6 +276,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->map.value_size = attr->value_size; htab->map.max_entries = attr->max_entries; htab->map.map_flags = attr->map_flags; + htab->map.numa_node = numa_node; /* check sanity of attributes. * value_size == 0 may be allowed in the future to use map as a set @@ -346,7 +355,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) err = -ENOMEM; htab->buckets = bpf_map_area_alloc(htab->n_buckets * - sizeof(struct bucket)); + sizeof(struct bucket), + htab->map.numa_node); if (!htab->buckets) goto free_htab; @@ -504,6 +514,29 @@ static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key) return NULL; } +static u32 htab_lru_map_gen_lookup(struct bpf_map *map, + struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + const int ret = BPF_REG_0; + const int ref_reg = BPF_REG_1; + + *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4); + *insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret, + offsetof(struct htab_elem, lru_node) + + offsetof(struct bpf_lru_node, ref)); + *insn++ = BPF_JMP_IMM(BPF_JNE, ref_reg, 0, 1); + *insn++ = BPF_ST_MEM(BPF_B, ret, + offsetof(struct htab_elem, lru_node) + + offsetof(struct bpf_lru_node, ref), + 1); + *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, + offsetof(struct htab_elem, key) + + round_up(map->key_size, 8)); + return insn - insn_buf; +} + /* It is called from the bpf_lru_list when the LRU needs to delete * older elements from the htab. */ @@ -704,7 +737,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, atomic_dec(&htab->count); return ERR_PTR(-E2BIG); } - l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); + l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, + htab->map.numa_node); if (!l_new) return ERR_PTR(-ENOMEM); } @@ -1126,6 +1160,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_lookup_elem = htab_lru_map_lookup_elem, .map_update_elem = htab_lru_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, + .map_gen_lookup = htab_lru_map_gen_lookup, }; /* Called from eBPF program */ @@ -1315,6 +1350,22 @@ static void *htab_of_map_lookup_elem(struct bpf_map *map, void *key) return READ_ONCE(*inner_map); } +static u32 htab_of_map_gen_lookup(struct bpf_map *map, + struct bpf_insn *insn_buf) +{ + struct bpf_insn *insn = insn_buf; + const int ret = BPF_REG_0; + + *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2); + *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, + offsetof(struct htab_elem, key) + + round_up(map->key_size, 8)); + *insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0); + + return insn - insn_buf; +} + static void htab_of_map_free(struct bpf_map *map) { bpf_map_meta_free(map->inner_map_meta); @@ -1330,4 +1381,5 @@ const struct bpf_map_ops htab_of_maps_map_ops = { .map_fd_get_ptr = bpf_map_fd_get_ptr, .map_fd_put_ptr = bpf_map_fd_put_ptr, .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, + .map_gen_lookup = htab_of_map_gen_lookup, }; diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index b09185f0f17d..1b767844a76f 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -244,7 +244,8 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, if (value) size += trie->map.value_size; - node = kmalloc(size, GFP_ATOMIC | __GFP_NOWARN); + node = kmalloc_node(size, GFP_ATOMIC | __GFP_NOWARN, + trie->map.numa_node); if (!node) return NULL; @@ -405,6 +406,8 @@ static int trie_delete_elem(struct bpf_map *map, void *key) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) +#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE) + static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; @@ -416,7 +419,8 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || - attr->map_flags != BPF_F_NO_PREALLOC || + !(attr->map_flags & BPF_F_NO_PREALLOC) || + attr->map_flags & ~LPM_CREATE_FLAG_MASK || attr->key_size < LPM_KEY_SIZE_MIN || attr->key_size > LPM_KEY_SIZE_MAX || attr->value_size < LPM_VAL_SIZE_MIN || @@ -433,6 +437,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) trie->map.value_size = attr->value_size; trie->map.max_entries = attr->max_entries; trie->map.map_flags = attr->map_flags; + trie->map.numa_node = bpf_map_attr_numa_node(attr); trie->data_size = attr->key_size - offsetof(struct bpf_lpm_trie_key, data); trie->max_prefixlen = trie->data_size * 8; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c new file mode 100644 index 000000000000..f6ffde9c6a68 --- /dev/null +++ b/kernel/bpf/sockmap.c @@ -0,0 +1,873 @@ +/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +/* A BPF sock_map is used to store sock objects. This is primarly used + * for doing socket redirect with BPF helper routines. + * + * A sock map may have BPF programs attached to it, currently a program + * used to parse packets and a program to provide a verdict and redirect + * decision on the packet are supported. Any programs attached to a sock + * map are inherited by sock objects when they are added to the map. If + * no BPF programs are attached the sock object may only be used for sock + * redirect. + * + * A sock object may be in multiple maps, but can only inherit a single + * parse or verdict program. If adding a sock object to a map would result + * in having multiple parsing programs the update will return an EBUSY error. + * + * For reference this program is similar to devmap used in XDP context + * reviewing these together may be useful. For an example please review + * ./samples/bpf/sockmap/. + */ +#include <linux/bpf.h> +#include <net/sock.h> +#include <linux/filter.h> +#include <linux/errno.h> +#include <linux/file.h> +#include <linux/kernel.h> +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/workqueue.h> +#include <linux/list.h> +#include <net/strparser.h> + +struct bpf_stab { + struct bpf_map map; + struct sock **sock_map; + struct bpf_prog *bpf_parse; + struct bpf_prog *bpf_verdict; +}; + +enum smap_psock_state { + SMAP_TX_RUNNING, +}; + +struct smap_psock_map_entry { + struct list_head list; + struct sock **entry; +}; + +struct smap_psock { + struct rcu_head rcu; + /* refcnt is used inside sk_callback_lock */ + u32 refcnt; + + /* datapath variables */ + struct sk_buff_head rxqueue; + bool strp_enabled; + + /* datapath error path cache across tx work invoca |